Task plan determination method and device, electronic equipment, program product, medium

Abstract

The present application relates to the technical field of task allocation, and discloses a method and apparatus for determining a task solution, an electronic device, a program product, and a medium. The method comprises: obtaining task requirement information; constructing an initial task map based on the task requirement information; the initial task map includes multiple task nodes; deleting redundant nodes in the initial task map based on the task attributes of each task node to obtain a target task map; the task attributes are indicators for evaluating the historical execution process of the task nodes; and extracting all task solutions from the target task map. In this way, by deleting redundant nodes, the target task map can be formed to reduce redundant task items without losing key links, thereby obtaining a streamlined task solution without affecting the implementation of the overall solution.

Description

Technical Field

[0001] The present application relates to the technical field of task allocation, and in particular to a method and device for determining a task plan, an electronic device, a program product, and a medium. Background Art

[0002] In the work process, it is inevitable that after a task requirement is proposed, a complete task plan needs to be designed according to the task requirement, and then the subtasks in the task plan are distributed to the corresponding users to facilitate the subsequent completion of the task requirement. Currently, there is a problem of redundant task plans.

[0003] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of this application, and therefore may include information that does not constitute prior art known to ordinary technicians in this field. Summary of the Invention

[0004] In order to provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. The summary is not an extensive review, nor is it intended to identify key / critical elements or delineate the scope of protection of these embodiments, but rather serves as a prelude to the detailed description that follows.

[0005] The embodiments of the present application provide a method and device for determining a task plan, an electronic device, a program product, and a medium, so as to provide a streamlined task plan without affecting the implementation of the overall plan.

[0006] An embodiment of the present application provides a method for determining a task plan, including: obtaining task requirement information; constructing an initial task map based on the task requirement information; the initial task map includes multiple task nodes; deleting redundant nodes in the initial task map based on the task attributes of each task node to obtain a target task map; the task attributes are indicators for evaluating the historical execution process of the task nodes; extracting all task plans in the target task map; wherein each path formed by the task nodes in the target task map is a task plan.

[0007] In the above implementation, considering that the task attributes of a task node can reflect the behavior of the task node during past execution, the task attributes of the task node can be used to determine the task nodes that are unnecessary to execute, i.e., redundant nodes. By deleting redundant nodes, the target task map can be formed to reduce redundant task items without losing key links, thereby obtaining a streamlined task solution without affecting the implementation of the overall solution.

[0008] Furthermore, redundant nodes in the initial task graph are deleted according to the task attributes of each task node to obtain a target task graph, including: determining the nodes to be deleted according to the task attributes, deleting the nodes to be deleted from the initial task graph to obtain an intermediate graph; determining whether necessary connection nodes are missing in the intermediate graph; and in the case of missing necessary connection nodes, completing the missing necessary connection nodes in the intermediate graph to obtain the target task graph.

[0009] In the above embodiment, the probability that the task node is a redundant node can be inferred based on the historical execution status of the task node. By completing the necessary connection nodes, the probability of the task node from which the non-redundant nodes are deleted can be reduced, thereby increasing the probability that the task plan can be implemented smoothly, thereby obtaining a streamlined task plan without affecting the implementation of the overall plan.

[0010] Furthermore, the task attributes include historical execution time; determining the nodes to be deleted based on the task attributes includes: obtaining the node out-degree of each task node; determining the to-be-judged score corresponding to each task node based on the historical execution time and node out-degree corresponding to each task node; if the to-be-judged score corresponding to the task node is lower than a preset score, determining the task node as a node to be deleted.

[0011] In the above implementation, the node out-degree of a task node can reflect the degree of association between the task node and other task nodes. At the same time, the historical execution time of the task node can reflect the execution efficiency of the task node. Combining the node out-degree and historical execution time of the task node can comprehensively reflect the importance of the task node, thereby facilitating the deletion of redundant nodes to streamline the task plan.

[0012] Furthermore, determining whether necessary connection nodes are missing in the intermediate graph includes: obtaining a node completion model; the node completion model is obtained by training using a preset historical scheme; the preset historical scheme has sample task nodes, necessary connection nodes of the sample task nodes, and node attributes of the sample task nodes; inputting each of the task nodes and the node attributes of each of the task nodes into the node completion model to obtain necessary connection nodes corresponding to each of the task nodes; determining whether the task node lacks necessary connection nodes based on the necessary connection nodes and actual connection nodes of the task node; the actual connection nodes are other task nodes connected to the task node in the target task graph.

[0013] In the above implementation, the historical scheme can reflect the connection relationships between task nodes. By training the node completion model through the historical scheme, the completion model can capture the dependencies between different task nodes, thereby automatically identifying the necessary connection nodes for each task node. Furthermore, due to the model's inherent generalization capabilities, it is more flexible than other methods for identifying necessary connection nodes for task nodes.

[0014] Furthermore, each task node corresponds to a task item execution subject; the task item execution subject is used to execute the corresponding task node; and the node attributes of each task node in the target task map include: time constraints. The method also includes: obtaining an estimated time corresponding to the task item execution subject of each task node in the target task map; the estimated time reflects the efficiency of the task item execution subject in processing the task node; determining a priority score for each task node in the target task map based on the time constraints and estimated time of each task node; and determining a priority level for each task solution based on the priority score of each task node.

[0015] In the above embodiment, the time constraints of the task nodes are taken into account to reflect the urgency of the task nodes, while the estimated time consumption reflects the efficiency of the task item execution subject in processing the task nodes. Therefore, the time constraints and estimated time consumption of the task nodes can be used to prioritize the task solutions according to their urgency and processing speed, so that the task solutions that can be processed quickly and urgently are given priority.

[0016] Furthermore, the estimated time corresponding to the task item execution subject of each task node in the target task map is obtained, including: inputting the task item execution subject of each task node in the target task map into a preset sorting model to obtain the efficiency ranking of each task item execution subject; and determining the estimated time of each task item execution subject based on the efficiency ranking.

[0017] In the above embodiment, considering that the model can reasonably infer the efficiency ranking of different task item execution entities through learning, the efficiency ranking of the task item execution entities can be obtained conveniently and accurately by inputting the task item execution entities of each task node in the target task map into the preset ranking model.

[0018] Furthermore, the ranking model is obtained in the following manner: obtaining first training data and scores and modification records for historical plans within a historical preset time period; the modification records are used to describe the efficiency ranking of multiple task item execution entities after correction; the first training data is data located before the historical preset time period for training the ranking model; obtaining second training data based on the scores and the modification records; using the first training data and the second training data to train the preset model to obtain a reference ranking model; determining target model parameters based on the first model parameters of the reference ranking model and the second model parameters of the historical ranking model; adjusting the model parameters of the historical ranking model to the target model parameters to obtain the ranking model.

[0019] In the above-described embodiment, by modifying the records to reflect the efficiency ranking of task item execution entities that meets user expectations, and by comprehensively training a new ranking model based on the modified records, the quality of the training data for the new ranking model can be improved, thereby facilitating the improvement of the accuracy of the new ranking model. By comprehensively referencing the first model parameters of the ranking model and the second model parameters of the historical ranking model to determine the target model parameters, and retaining a portion of the historical data, the ranking model parameter updates can be made without causing abrupt changes, thereby improving the stability of the ranking model.

[0020] Furthermore, the target model parameters are determined based on the first model parameters of the reference sorting model and the second model parameters of the historical sorting model, including: obtaining the quality score of the historical solution; the quality score is used to reflect the logical correctness of the historical solution; determining the weight parameter based on the quality score; and weighting the first model parameter and the second model parameter according to the weight parameter to obtain the target model parameter.

[0021] In the above embodiment, the quality score of the historical scheme can reflect the quality of the historical training data used to train the sorting model. The weight parameters of the first model parameter and the second model parameter are determined in combination with the quality score. When the quality of the historical sorting model is good, the proportion of the second model parameter of the historical sorting model can be increased, so that the target model parameters obtained can make the sorting model more accurate.

[0022] Furthermore, the node attributes of each task node in the target task map include a preset node score; the task attributes include a historical execution success rate; and the priority score of each task node is determined based on the estimated time and the urgency coefficient, including: for each task node: determining the priority score of the task node based on the estimated time, the time constraint, the historical execution success rate and the preset node score corresponding to the task node.

[0023] In the above implementation, the historical execution success rate of a task node can reflect the probability of whether the task node can be executed normally. By increasing the execution success rate of the task node to determine the priority score of the task node, the probability of the task plan being unable to be completed due to problems with a task node during execution can be reduced, thereby improving the stability of the task plan.

[0024] Furthermore, the method also includes: inputting the task plan into a preset risk prediction model to obtain the risk type corresponding to the task plan and the risk probability of the risk type; when the risk probability is greater than the preset probability, determining a risk control strategy according to the risk type, and adjusting the task plan according to the risk control strategy.

[0025] In the above implementation scheme, by predicting the risk type of the task plan and the risk probability of the risk type, it is possible to predict whether the task plan has problems, and then adjust the task plan in advance to improve the stability of the task plan.

[0026] Furthermore, the method also includes: when the risk probability is less than or equal to a preset probability, obtaining the execution result of the task plan; performing quality verification on the execution result; when the quality verification fails, determining a risk control strategy based on the risk type, and adjusting the task plan according to the risk control strategy.

[0027] In the above implementation plan, by verifying the quality of the execution results of the task plan and adjusting the task plan, a task plan with qualified execution results can be obtained after continuous adjustment, so that the subsequent task plan formed based on the task requirement information is more reasonable.

[0028] Furthermore, the execution result is quality verified, including: determining the semantic similarity between the execution result and a preset historical execution result, and determining that the quality verification has failed if the semantic similarity is less than the preset similarity; the historical execution result and the execution result belong to the same task scenario; and / or determining whether the execution result meets preset indicators, and determining that the quality verification has failed if the execution result does not meet the preset indicators; the preset indicators are compliance conditions for the task scenario to which the execution result belongs.

[0029] In the above implementation scheme, whether the execution result is compliant is determined by comparing the semantic similarity between the execution result and the preset historical execution result, or by determining whether the execution result meets the preset indicators. The process is simple and relatively accurate, and can easily determine whether the execution result is compliant, thereby reflecting whether the task plan is logical, so as to improve the determination of the task plan.

[0030] Furthermore, an initial task graph is constructed based on the task requirement information, including: converting the task requirement information into structured data; the structured data includes task items; determining the dependency relationship between each of the task items; and connecting the task items as the task nodes according to the dependency relationship to obtain the initial task graph.

[0031] In the above implementation scheme, considering that task requirement information may come from multiple sources, by converting the task requirement information into structured data, data from different sources can be unified, and there is no need to use different parsing methods for task requirement information from different sources, thereby more conveniently constructing a task map.

[0032] An embodiment of the present application provides a task plan determination device, including: an acquisition module for acquiring task requirement information; a construction module for constructing an initial task map based on the task requirement information; the initial task map includes multiple task nodes; an adjustment module for deleting redundant nodes in the initial task map based on the task attributes of each task node to obtain a target task map; the task attributes are indicators for evaluating the historical execution process of the task nodes; a task determination module for extracting all task plans in the target task map; wherein, each path formed by the task nodes in the target task map is a task plan.

[0033] An embodiment of the present application provides an electronic device, including a processor and a memory, wherein the memory stores computer-executable instructions that can be executed by the processor, and the processor executes the computer-executable instructions to implement the above-mentioned task plan determination method.

[0034] An embodiment of the present application provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the above-mentioned task solution determination method.

[0035] An embodiment of the present application provides a storage medium storing computer-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions enable the processor to perform the above-mentioned task solution determination method.

[0036] The above general description and the following description are exemplary and explanatory only and are not intended to limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] One or more embodiments are exemplarily described by corresponding drawings. These exemplary descriptions and drawings do not limit the embodiments. Elements with the same reference numerals in the drawings are shown as similar elements. The drawings do not constitute a scale limitation. In addition,

[0038] Figure 1 This is a schematic diagram of a method for determining a task plan provided in an embodiment of the present application;

[0039] Figure 2 This is a schematic diagram of a task solution provided in an embodiment of the present application;

[0040] Figure 3 This is a flowchart of another method for determining a task solution provided in an embodiment of the present application;

[0041] Figure 4 This is a schematic diagram of a task solution determination device provided in an embodiment of the present application;

[0042] Figure 5 This is a schematic diagram of an electronic device provided in an embodiment of the present application.

[0043] Reference numerals:

[0044] 1: Acquisition module; 2: Construction module; 3: Adjustment module; 4: Task determination module; 5: Processor; 6: Bus; 7: Memory; 8: Communication interface. DETAILED DESCRIPTION

[0045] In order to be able to understand the features and technical contents of the embodiments of the present application in more detail, the implementation of the embodiments of the present application is described in detail below in conjunction with the accompanying drawings. The accompanying drawings are for reference only and are not used to limit the embodiments of the present application. In the following technical description, for the sake of convenience of explanation, a full understanding of the disclosed embodiments is provided through multiple details. However, one or more embodiments can still be implemented without these details. In other cases, to simplify the drawings, well-known structures and devices can be simplified for display.

[0046] In the description and claims of the embodiments of the present application and the accompanying drawings, the terms "first," "second," and the like are used to distinguish similar objects and are not necessarily used to describe a particular order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate for the purposes of describing the embodiments of the present application. In addition, the terms "including," "having," and any variations thereof are intended to cover non-exclusive inclusions.

[0047] Unless otherwise stated, the term "plurality" means two or more.

[0048] The term "correspondence" may refer to an association relationship or a binding relationship. The correspondence between A and B means that there is an association relationship or a binding relationship between A and B.

[0049] Example 1

[0050] The present application provides a method for determining a task plan. Figure 1 As shown, Figure 1 The following is a basic flow chart of the method for determining a task solution provided in the embodiments of the present application, including:

[0051] Step S101: Obtain task requirement information.

[0052] In some embodiments, the task requirement information is used to characterize the task requirements that are expected to be achieved.

[0053] For example, task requirement information may include task items, such as reimbursement approval. It may also include time constraints, which describe the expected completion time. It may also include expected resource requirements, which describe the resources needed to complete the task, such as the need for a financial system interface.

[0054] For example, assume that the task requirement information is that the reimbursement approval process needs to be completed today, including application submission, department preliminary review, financial review, system entry and email notification to the applicant. Figure 2 As shown in the figure, a task plan can be obtained based on the task requirement information. The task plan includes multiple task items, such as "Submit reimbursement application", "Department manager approval", and "Financial system accounting". At the same time, the time constraint is "Today" and the resource requirement is "Financial system interface".

[0055] Step S102: construct an initial task map based on task requirement information.

[0056] Among them, the initial task map includes multiple task nodes.

[0057] Exemplarily, each task node reflects a task item. Each task node in the initial task map also carries node attributes, which may include: time constraints, preset node scores, etc.

[0058] In some embodiments, step S102 may include: converting the task requirement information into structured data; the structured data may include task items; determining dependencies between the task items; and connecting the task items as task nodes according to the dependencies to obtain an initial task graph.

[0059] For example, task requirement information is fed into a pre-defined BERT-Whisper (multimodal encoder) to convert it into a 256-dimensional vector. This 256-dimensional vector is then converted into a set of task triples, yielding structured data containing task items. The task requirement information is then analyzed using dependency syntax to determine the dependencies between task items.

[0060] Among them, the task triplet can be G=(T, C, R). G is the task triplet, T is the task item, C is the time constraint, and R is the expected resource requirement. A 256-dimensional vector can be obtained through V=Transformer_Encoder([Text_Emb;Audio_Emb;Graph_Emb]). Among them, Text_Emb represents the text embedding representation, Audio_Emb represents the audio embedding representation, Graph_Emb represents the graph embedding representation, and V represents a 256-dimensional vector. This formula describes the concatenation of the embedding representations of text, audio, and graph, and inputting them into Transformer_Encoder to generate a unified 256-dimensional vector V. In this way, by first converting the task requirement information into a 256-dimensional vector, the problem of multi-source data alignment can be solved, so that the information in the task requirement information can be better extracted.

[0061] For example, taking "Product Launch Promotion" as an example, the task requirement information might be described as: "This month, new product marketing must be completed, including online advertising, offline event planning, social media operations, KOL (key opinion leader) collaboration (a company or brand with significant influence, expertise, or a fan base in a particular field), and performance monitoring." The initial task map constructed might include the following task nodes: market research, budget allocation, online advertising design, offline event venue booking, social media content production, KOL screening and contracting, advertising execution, event execution, data collection and analysis, and performance report generation. The dependencies between these task nodes might be: market research leads to budget allocation. Budget allocation leads to online advertising design, offline event venue booking, social media content production, and KOL screening and contracting. Specifically, "online advertising design" leads to "advertising execution." "Offline event venue booking" leads to "event execution." "Social media content production" leads to "advertising execution" and "event execution." "KOL screening and contracting" leads to "advertising execution" and "event execution." "Advertising execution" leads to "data collection and analysis." "Event execution" leads to "data collection and analysis." "Data Collection and Analysis" points to "Performance Report Generation".

[0062] Step S103: Delete redundant nodes in the initial task graph according to the task attributes of each task node to obtain the target task graph.

[0063] Optionally, the task attribute is an indicator for evaluating the historical execution process of the task node, for example, historical execution time, which is the length of time the task node took to execute historically.

[0064] In some embodiments, step S103 may include: determining nodes to be deleted based on task attributes, deleting the nodes to be deleted from the initial task graph to obtain an intermediate graph, determining whether necessary connection nodes are missing in the intermediate graph, and if so, completing the missing necessary connection nodes in the intermediate graph to obtain a target task graph.

[0065] In an optional manner of the above embodiment, the task attributes include historical execution time. Determining the nodes to be deleted based on the task attributes may include: obtaining the node out-degree of each task node; determining a pending judgment score corresponding to each task node based on the historical execution time and node out-degree corresponding to each task node; and determining the task node as a node to be deleted if the pending judgment score corresponding to the task node is lower than a preset score.

[0066] The redundant node is a node to be deleted that is not a necessary connection node.

[0067] Among them, the node outdegree is the number of other task nodes connected to the task node.

[0068] In the above optional method, determining the pending judgment score corresponding to each task node based on the historical execution time and node out-degree corresponding to each task node may include: obtaining a first weight set. For each task node, weighting the historical execution time of the task node and the negative first power of the node out-degree of the task node according to the first weight set to obtain the pending judgment score for the task node.

[0069] The first weight set records the first weight corresponding to the historical execution time and the second weight corresponding to the node out-degree.

[0070] For example, the score to be judged = the second weight × the node out-degree -1 + first weight × historical execution time.

[0071] Optionally, the first weight and the second weight may be optimized by using a PPO (Proximal Policy Optimization) algorithm.

[0072] In an optional manner of the above embodiment, determining whether a necessary connection node is missing from the intermediate graph includes: obtaining a node completion model. Inputting each task node and its node attributes into the node completion model to obtain necessary connection nodes corresponding to each task node. Determining whether the task node is missing a necessary connection node based on the necessary connection nodes and the actual connection nodes of the task node.

[0073] Among them, the actual connection nodes are other task nodes connected to the task node in the target task graph.

[0074] Among them, the node completion model is used to determine the necessary connection nodes that the task node needs to connect to.

[0075] In the above optional method, the node completion model can be obtained by using the preset historical scheme training in the following way: the historical scheme with the necessary connection node labels of the sample task node is input into the preset first training model for training to obtain the node completion model.

[0076] The historical plan may include a sample task node, necessary connection nodes of the sample task node, and node attributes of the sample task node.

[0077] Among them, the first training model can be a graph neural network (GNN).

[0078] In the above optional method, whether the task node lacks necessary connection nodes is determined based on the necessary connection nodes and actual connection nodes of the task node, including: for each task node: comparing whether the necessary connection nodes of the task node exist in the actual connection nodes of the task node; if not, the task node lacks necessary connection nodes; if so, the task node does not lack necessary connection nodes.

[0079] In another optional method of the above embodiment, determining whether necessary connection nodes are missing in the intermediate graph includes: for each task node in the intermediate graph: searching for necessary connection nodes corresponding to the task node and the node attributes of the task node in a preset connection node database.

[0080] The connection node database stores the corresponding relationships between task nodes, node attributes of task nodes and necessary connection nodes.

[0081] In some embodiments, each task node corresponds to a task item execution entity, which is used to execute the corresponding task node. Furthermore, the node attributes of each task node in the target task map include time constraints. The task solution determination method further includes: obtaining the estimated time corresponding to the task item execution entity of each task node in the target task map; determining the priority score of each task node based on the time constraints and estimated time of each task node in the target task map; and determining the priority level of each task solution based on the priority score of each task node.

[0082] Optionally, the estimated time consumption reflects the efficiency of the task item execution subject in processing the task nodes.

[0083] In an optional method of the above embodiment, obtaining the estimated time corresponding to the task item execution subject of each task node in the target task map can include: inputting the task item execution subject of each task node in the target task map into a preset sorting model to obtain the efficiency ranking of each task item execution subject; and determining the estimated time of each task item execution subject based on the efficiency ranking.

[0084] The ranking model is used to determine the efficiency of the task item execution subjects of each task node, so as to output the ranking of the task item execution subjects of each task node according to the efficiency.

[0085] In the above optional method, the ranking model can be obtained in the following way: the sample graph with the task item execution subject efficiency ranking label is input into the preset second training model for training to obtain the ranking model.

[0086] Among them, the second training model can be: a multi-armed bandit model.

[0087] In the above optional method, before the current moment, there will be historical solutions determined based on historical task requirement information, as well as historical execution results after executing the historical solutions, and feedback information received from users on the overall process from the formation of the historical solutions to the execution of the historical solutions. The historical ranking model can be adjusted based on the user's feedback information. That is, the ranking model can also be obtained in the following ways: obtaining first training data and the scoring and modification records of the historical solutions within a historical preset time period; obtaining second training data based on the scoring and modification records; using the first training data and the second training data to train the preset model to obtain a reference ranking model; determining the target model parameters based on the first model parameters of the reference ranking model and the second model parameters of the historical ranking model; adjusting the model parameters of the historical ranking model to the target model parameters to obtain the ranking model.

[0088] The first training data is data used to train the ranking model before a preset historical period. The modification record is used to describe the revised efficiency ranking of multiple task item execution entities. The historical ranking model refers to the ranking model obtained before the current moment. For example, the ranking model obtained by the last update before the current moment can be used as the historical ranking model.

[0089] Optionally, obtaining the second training data based on the scoring and modification records may include obtaining the efficiency ranking of each task item execution subject with a score higher than a preset score, and obtaining the efficiency ranking of each task item execution subject modified by the user as the efficiency ranking to be trained. The task item execution subjects corresponding to the efficiency ranking to be trained, the task nodes corresponding to each task item execution subject, and the node attributes of each task node are used as the second training data.

[0090] Before obtaining the second training data based on the scoring and modification records, the scoring and modification records can be processed using differential privacy technology to protect user privacy. The differential privacy noise can be set to 0.1.

[0091] Optionally, the preset model is trained using the first training data and the second training data to obtain a reference ranking model, which may be: obtaining the quality scores of historical solutions. As a loss function, the preset model is trained using the first training data and the second training data to obtain a reference ranking model. Here, L represents the loss function. By designing a specialized loss function, it is possible to prioritize reducing errors in low-quality tasks during model optimization.

[0092] Optionally, the target model parameters are determined based on the first model parameters of the reference ranking model and the second model parameters of the historical ranking model, which can be: obtaining the quality score of the historical solution; determining the weight parameter based on the quality score; weighting the first model parameter and the second model parameter according to the weight parameter to obtain the target model parameter.

[0093] The weight parameters include a sixth weight corresponding to the first model parameter and a seventh weight corresponding to the second model parameter.

[0094] Exemplarily, determining the weight parameter according to the quality score may include searching for the weight parameter corresponding to the quality score in a preset weight database, wherein the weight parameter corresponding to the quality score is stored in the weight database.

[0095] Optionally, the quality score is used to reflect the logical correctness of the historical plan, and the quality score can be obtained in the following way: for each historical plan: determine the structural similarity between the task plan and the historical plan, obtain the semantic similarity and rule pass rate corresponding to the historical plan, weight the structural similarity, semantic similarity and rule pass rate according to a preset third weight set, and obtain the alternative score of the historical plan; calculate the average value of the alternative scores of each historical plan to obtain the quality score.

[0096] Among them, the third weight set records the eighth weight corresponding to the structural similarity, the ninth weight corresponding to the semantic similarity, and the tenth weight corresponding to the rule pass rate.

[0097] In one embodiment, determining the structural similarity between the task solution and the historical solution may include calculating a first similarity between a task node in the task solution and a task node in the historical solution as the structural similarity.

[0098] In the above embodiment, determining the first similarity between the task nodes in the task solution and the task nodes in the historical solution may include obtaining the number of identical task nodes in the task solution and the historical solution, and dividing the number of identical task nodes by the total number to obtain the first similarity. The total number is the number of task nodes in the task solution.

[0099] In another embodiment, determining the structural similarity between the task plan and the historical plan can be: determining a first similarity between the task nodes in the task plan and the task nodes in the historical plan; determining a second similarity between the dependency relationships of each task node in the task plan and the dependency relationships of each task node in the historical plan; and determining the structural similarity by combining the first similarity and the second similarity.

[0100] The dependency relationship of a task node refers to the pointing relationship between the task node and other task nodes. For example, the dependency relationship is as follows: the task node "activity execution" points to "data collection and analysis".

[0101] In the above embodiment, determining the second similarity between the dependency of each task node in the task scheme and the dependency of each task node in the historical scheme can be: converting the dependency of each task node in the task scheme into a first dependency vector. Converting the dependency of each task node in the historical scheme into a second dependency vector. For the first dependency vector of each task node in the task scheme: calculating the vector similarity between the first dependency vector and each second dependency vector in turn, if there is a vector similarity greater than a preset vector similarity, it is considered that the same dependency exists in the historical scheme. Accumulate the number of equivalent dependencies, calculate the number of equivalent dependencies and divide it by the total number of dependencies to obtain the second similarity.

[0102] The first dependency vector represents a single dependency of a task node in the task solution.

[0103] The second dependency vector represents a single dependency of a task node in the historical solution.

[0104] The number of identical dependencies is the number of identical dependencies between the historical solution and the task solution. The total number of dependencies is the total number of dependencies in the task solution.

[0105] In the above embodiment, the structural similarity is determined by combining the first similarity and the second similarity, which may be achieved by weighting the first similarity and the second similarity according to a preset fourth weight set to obtain the structural similarity.

[0106] The fourth weight set records the eleventh weight corresponding to the first similarity and the twelfth weight corresponding to the second similarity.

[0107] In one embodiment, structural similarity, semantic similarity, and rule pass rate are weighted according to a preset third weight set to obtain a candidate score for the historical solution, including: calculating a quality score = α × structural similarity + β × semantic similarity + γ × rule pass rate. α is the eighth weight, β is the ninth weight, and γ is the tenth weight.

[0108] Alternatively, the quality score can be obtained by: determining the structural similarity between the task solution and the historical solution; if there is a case where the structural similarity is greater than the preset structural similarity, for each historical solution with a structural similarity greater than the preset structural similarity: obtaining the semantic similarity and rule pass rate of the historical solution, and determining the score to be used based on the calculated semantic similarity and rule pass rate. Calculate the average of the scores to be used for each historical solution with a structural similarity greater than the preset structural similarity as the quality score. If there is no case where the structural similarity is greater than the preset structural similarity, the set quality score is used as the quality score.

[0109] In the above optional method, determining the estimated time consumption of each task item execution entity based on the efficiency ranking may include: for each task item execution entity: obtaining the sequence number of the task item execution entity in the efficiency ranking; searching for the sequence number in a preset time consumption evaluation database to obtain the estimated time consumption corresponding to the task item execution entity.

[0110] In an optional manner of the above embodiment, determining the priority score of each task node based on the time constraints and estimated time consumption of each task node in the target task map may include: for each task node: searching for the task node, the estimated time consumption corresponding to the task node, and the time constraints corresponding to the task node in a preset first score database to obtain the priority score corresponding to the task node.

[0111] The first score database stores the corresponding relationships among task nodes, estimated time consumption and time constraints.

[0112] In an optional manner of the above embodiment, the node attributes of each task node in the target task map include a preset node score; and the task attributes include a historical execution success rate. Determining the priority score of each task node based on the time constraints and estimated time consumption of each task node in the target task map includes: for each task node: determining the priority score of the task node based on the estimated time consumption, time constraints, historical execution success rate, and preset node score corresponding to the task node.

[0113] The preset node scores are used to reflect the initial priorities of task nodes. Engineers can set the initial priorities of different task nodes based on their experience.

[0114] In the above optional method, the priority score of the task node is determined based on the estimated time consumption, time constraints, historical execution success rate and preset node score corresponding to the task node, which can be: determining the efficiency score based on the time constraints and estimated time consumption corresponding to the task node; determining the alternative score based on the historical execution success rate; and obtaining the priority score corresponding to the task node by combining the preset node score, efficiency score and alternative score.

[0115] In the above optional method, the efficiency score is determined based on the time constraint and the estimated time consumption, which can be: searching the time constraint of the task node in the preset coefficient database to obtain the urgency coefficient of the task node. Get the efficiency score. Where q is the efficiency score, λ is the urgency coefficient, and t is the estimated time.

[0116] In the above optional manner, determining the candidate score according to the historical execution success rate may be performed by searching the historical execution success rate corresponding to the task node in a preset second score database to obtain the candidate score corresponding to the task node.

[0117] The second score database stores the corresponding relationship between the historical execution success rate and the candidate score.

[0118] In the above optional manner, the priority score corresponding to the task node is obtained by comprehensively considering the preset node score, efficiency score and alternative score, which may be: taking the sum of the preset node score, efficiency score and alternative score as the priority score.

[0119] In the above optional manner, the priority score corresponding to the task node is obtained by comprehensively combining the preset node score, the efficiency score, and the alternative score. This may include obtaining a second weight set, and weighting the preset node score, the efficiency score, and the alternative score according to the second weight set to obtain the priority score corresponding to the task node.

[0120] The second weight set includes a third weight corresponding to the preset node score, a fourth weight corresponding to the efficiency score, and a fifth weight corresponding to the alternative score.

[0121] For example, assume that there are task nodes A and task nodes B, and the task item executor of task node A is financial specialist A, and the task item executor of task node B is financial specialist B. At the same time, the time constraints of task nodes A and task node B are both to be completed today, the node attributes of task node A include a preset node score of 0.8, and the node attributes of task node B include a preset node score of 0.5. The efficiency ranking of the task item executors output by the sorting model is financial specialist A in front and financial specialist B in the back. According to the efficiency ranking, the estimated time for financial specialist A is 1 hour, and the estimated time for financial specialist B is 2 hours. The time constraint condition "Complete today" of task nodes A and task node B is searched in the preset coefficient database, and the urgency coefficients of task nodes A and task node B are both 0.1. The efficiency of task node A can be calculated to be divided into The efficiency of task node B can be calculated as follows: Assume that the candidate score of task node A is 0.9, the third weight is 1, the fourth weight is 0.3, and the fifth weight is 1. The priority score of task node A = 0.8 + 0.3 × 0.904 + 0.9 = 1.9712.

[0122] In the above embodiment, the priority level of each task plan is determined according to the priority score of each task node, which can be: for each task plan: calculate the average of the priority scores of each task node in the task plan as the target score; search the target score in a preset priority level database to obtain the priority level corresponding to the target score.

[0123] The priority processing level database stores the corresponding relationship between the target scores and the priority processing levels.

[0124] Step S104: extract all task solutions in the target task map.

[0125] Among them, each path composed of task nodes in the target task graph is a task plan.

[0126] In some embodiments, the task plan determination method also includes: inputting the task plan into a preset risk prediction model to obtain the risk type corresponding to the task plan and the risk probability of the risk type; when the risk probability is greater than the preset probability, determining the risk control strategy according to the risk type, and adjusting the task plan according to the risk control strategy.

[0127] Among them, the task plan determination method may also include: when the risk probability is less than or equal to the preset probability, obtaining the execution result of the task plan; performing quality verification on the execution result; when the quality verification fails, determining the risk control strategy according to the risk type, and adjusting the task plan according to the risk control strategy.

[0128] In the above embodiment, the risk prediction model may be determined in the following manner: historical scenarios with risk type labels are input into a preset third training model for training to obtain a risk prediction model.

[0129] Among them, the third training model can be a Transformer-XL model (a deep learning model), a temporal convolutional network (TCN), etc.

[0130] In an optional manner of the above embodiment, performing quality verification on the execution result may include: determining the semantic similarity between the execution result and the preset historical execution result, and determining that the quality verification has failed if the semantic similarity is less than the preset similarity; and / or determining whether the execution result meets the preset indicators, and determining that the quality verification has failed if the execution result does not meet the preset indicators.

[0131] The historical execution results and the execution results belong to the same task scenario. Exemplarily, historical solutions for obtaining the historical execution results can be stored, and the structural similarity between the task solution for obtaining the execution results and the historical solutions can be compared. If the structural similarity is higher than a preset threshold, it is determined that the historical execution results and the execution results belong to the same task scenario.

[0132] In the above optional manner, determining the semantic similarity between the execution result and the preset historical execution result may be: calculating the similarity between the first vector representing the execution result and the second vector representing the historical execution result as the semantic similarity.

[0133] The preset indicators are the compliance conditions for the task scenario to which the execution result belongs. For example, for a task scenario involving reimbursement, the compliance condition could be that the amount displayed in the execution result is less than the set budget. For a task scenario involving leave application, the compliance condition could be that the leave duration displayed in the execution result is less than the set duration.

[0134] In the above optional method, determining whether the execution result meets the preset indicators may include: comparing the content of the execution result with the corresponding preset indicators; if the content of the execution result does not meet the preset indicators, the preset indicators are not met; otherwise, the preset indicators are met.

[0135] The preset indicator can include multiple sub-indicators. For each sub-indicator, the execution result is compared with the sub-indicator. If the execution result does not meet the sub-indicator, the sub-indicator is not satisfied. Otherwise, the sub-indicator is satisfied. If the number of sub-indicators that are not satisfied exceeds the preset number, the execution result is considered to not meet the preset indicator.

[0136] Correspondingly, if there are multiple sub-indicators, if the execution result does not meet some of the sub-indicators, the rule pass rate can be calculated by dividing the number of satisfied categories by the total number of categories. The number of satisfied categories refers to the number of sub-indicators that are met, and the total number of categories refers to the number of sub-indicators included in the preset indicator.

[0137] In the above embodiment, determining the risk control strategy according to the risk type may include searching a preset risk control database for a risk control strategy corresponding to the risk type.

[0138] The preset risk management and control database stores the corresponding relationship between risk types and risk management and control strategies.

[0139] Optionally, the risk control strategy is a strategy for reducing the risk of the task plan, for example, adding a backup approver.

[0140] For example, the risk control strategy may specifically include adding a task node for approval by a backup approver after the set task node when the risk type is set.

[0141] For example, it can be set to directly reject when the rule pass rate is less than 80%; and trigger manual review when 80% ≤ rule pass rate < 90% and semantic similarity < 85%. This way, it is possible to better determine whether there are problems with the task plan.

[0142] For example, it can be set that when the rule pass rate is greater than 90% and the semantic similarity is greater than 90%, it is determined that the quality verification has passed.

[0143] For example, combined Figure 3As shown, the overall process of this application generally involves multimodal task understanding, dynamic task graph construction, resource optimization and matching, risk prediction and mitigation, quality closed-loop verification, and incremental strategy optimization. For example, task requirement information can be obtained, which can be in the form of voice, text, or a flowchart. The task requirement information is then converted into a structured task tuple G = (T, C, R). Based on the extracted structured task tuple G = (T, C, R), an initial task graph is constructed. The nodes to be deleted in the initial task graph are then deleted to obtain an intermediate graph. If the intermediate graph lacks necessary connecting nodes, the missing necessary connecting nodes are completed in the intermediate graph to obtain the target task graph (i.e., the optimized task graph). Task item execution entities are assigned to the task nodes in the target task graph, and the priority score of each task node in the target task graph is determined based on the time constraints, estimated time consumption, historical execution success rate, and preset node scores of each task node in the target task graph. Based on the target task map, one or more task plans are extracted from the map. The priority level of each task plan is determined based on the priority score of each task node within each task plan, resulting in a prioritized task plan (i.e., resource allocation plan). The task nodes within each task plan are sequentially organized into a task execution status sequence. This task execution status sequence is then input into a pre-set risk prediction model to obtain the corresponding risk type and risk probability (i.e., risk assessment result). The task plan is then adjusted based on the corresponding risk type and risk probability. The adjusted task plan serves as the mitigation strategy. The task plan is then executed, and the execution results (i.e., task execution results) are obtained. The execution results can be quality verified to determine compliance. If they comply, they pass verification. If they do not, they are rejected and manually reviewed. User feedback on the task plans and execution results can also be obtained. Finally, the ranking model can be optimized based on user feedback (i.e., user feedback data), resulting in the updated model weights (model parameters) for the ranking model.

[0144] In this way, the implementation method of the present application can automatically set the overall dialogue goal to generate contextually coherent user actions. It also has sufficient generalization capabilities to generate reasonable behaviors for dialogue situations that do not appear in the corpus. It can also provide quantitative feedback scores to guide model learning optimization. As shown in Table 1, the test environment is 1,000 cross-departmental collaborative task records, deployed on an NVIDIA A100 GPU cluster. Compared with traditional office automation systems, such as traditional AI (artificial intelligence) assistants, this application has higher task processing accuracy, shorter emergency task response time, and shorter new employee training cycle.

[0145] Table 1

[0146]

[0147] Example 2

[0148] Combine Figure 4 As shown, based on the same inventive concept, an embodiment of the present application provides a task solution determination device, comprising: an acquisition module 1, a construction module 2, an adjustment module 3, and a task determination module 4. The acquisition module 1 is used to obtain task requirement information; the construction module 2 is used to construct an initial task map based on the task requirement information; the initial task map includes multiple task nodes; the adjustment module 3 is used to delete redundant nodes in the initial task map based on the task attributes of each task node to obtain a target task map; the task attributes are indicators for evaluating the historical execution process of the task nodes; the task determination module 4 is used to extract all task solutions in the target task map; each path composed of task nodes in the target task map is a task solution.

[0149] In some embodiments, the construction module 2 is used to construct an initial task map based on the task requirement information in the following manner: converting the task requirement information into structured data; the structured data includes task items; determining the dependency relationship between each task item; and connecting the task items as task nodes according to the dependency relationship to obtain an initial task map.

[0150] In some embodiments, the adjustment module 3 is used to delete redundant nodes in the initial task graph according to the task attributes of each task node to obtain a target task graph by: determining the nodes to be deleted according to the task attributes, deleting the nodes to be deleted from the initial task graph to obtain an intermediate graph; determining whether necessary connection nodes are missing in the intermediate graph, and if necessary connection nodes are missing, completing the missing necessary connection nodes in the intermediate graph to obtain a target task graph.

[0151] In some embodiments, the task attributes include historical execution time; the adjustment module 3 is used to determine the nodes to be deleted based on the task attributes in the following manner: obtaining the node out-degree of each task node; determining the to-be-judged score corresponding to each task node based on the historical execution time and node out-degree corresponding to each task node; if the to-be-judged score corresponding to the task node is lower than the preset score, the task node is determined to be a node to be deleted.

[0152] In some embodiments, the adjustment module 3 is used to determine whether the intermediate graph lacks necessary connection nodes in the following manner: obtaining a node completion model; the node completion model is obtained by training using a preset historical scheme; the preset historical scheme has sample task nodes, necessary connection nodes of the sample task nodes, and node attributes of the sample task nodes; each task node and the node attributes of each task node are input into the node completion model to obtain the necessary connection nodes corresponding to each task node; determining whether the task node lacks necessary connection nodes based on the necessary connection nodes and actual connection nodes of the task node; the actual connection nodes are other task nodes connected to the task node in the target task graph.

[0153] In some embodiments, each task node corresponds to a task item execution subject; the task item execution subject is used to execute the corresponding task node; and the node attributes of each task node in the target task map include time constraints. The task solution determination device further includes a priority processing level determination module for obtaining an estimated time consumption corresponding to the task item execution subject of each task node in the target task map; the estimated time consumption reflects the efficiency of the task item execution subject in processing the task node; determining a priority score for each task node based on the time constraints and estimated time consumption of each task node in the target task map; and determining a priority processing level for each task solution based on the priority score of each task node.

[0154] In some embodiments, a priority processing level determination module is used to obtain the estimated time corresponding to the task item execution subject of each task node in the target task map: the task item execution subject of each task node in the target task map is input into a preset sorting model to obtain the efficiency ranking of each task item execution subject; and the estimated time of each task item execution subject is determined based on the efficiency ranking.

[0155] In some embodiments, the task plan determination device also includes: a model determination module, which is used to obtain first training data and scores and modification records for historical plans within a historical preset time period; the first training data is data located before the historical preset time period and used to train the sorting model; the second training data is obtained based on the scores and modification records; the preset model is trained using the first training data and the second training data to obtain a reference sorting model; the target model parameters are determined based on the first model parameters of the reference sorting model and the second model parameters of the historical sorting model; the model parameters of the historical sorting model are adjusted to the target model parameters to obtain the sorting model.

[0156] In some embodiments, the model determination module is used to determine the target model parameters based on the first model parameters of the reference sorting model and the second model parameters of the historical sorting model in the following manner: obtaining the quality score of the historical solution; the quality score is used to reflect the logical correctness of the historical solution; determining the weight parameter based on the quality score; weighting the first model parameter and the second model parameter according to the weight parameter to obtain the target model parameter.

[0157] In some embodiments, the node attributes of each task node in the target task map include a preset node score; the task attributes include a historical execution success rate; the priority processing level determination module is used to determine the priority score of each task node based on the time constraints and estimated time consumption of each task node in the target task map in the following manner: for each task node: determine the priority score of the task node based on the estimated time consumption, time constraints, historical execution success rate and preset node score corresponding to the task node.

[0158] In some embodiments, the task plan determination device also includes: a risk determination module, which is used to input the task plan into a preset risk prediction model to obtain the risk type corresponding to the task plan and the risk probability of the risk type; when the risk probability is greater than the preset probability, the risk control strategy is determined according to the risk type, and the task plan is adjusted according to the risk control strategy.

[0159] In some embodiments, the task plan determination device also includes: a compliance determination module, which is used to obtain the execution result of the task plan when the risk probability is less than or equal to the preset probability; perform quality verification on the execution result; if the quality verification fails, determine the risk control strategy according to the risk type, and adjust the task plan according to the risk control strategy.

[0160] In some embodiments, the compliance determination module is used to perform quality verification on the execution result in the following manner: determining the semantic similarity between the execution result and the preset historical execution result, and determining that the quality verification has failed if the semantic similarity is less than the preset similarity; the historical execution result and the execution result belong to the same task scenario; and / or determining whether the execution result meets the preset indicators, and determining that the quality verification has failed if the execution result does not meet the preset indicators; the preset indicators are the compliance conditions of the task scenario to which the execution result belongs.

[0161] Combine Figure 5 As shown, an embodiment of the present application provides an electronic device, including a processor 5 and a memory 7. Optionally, the device may further include a communication interface 8 and a bus 6. The processor 5, the communication interface 8, and the memory 7 may communicate with each other via the bus 6. The communication interface 8 may be used for information transmission. The processor 5 may call logic instructions in the memory 7 to execute the above-mentioned task solution determination method.

[0162] In addition, the logic instructions in the memory 7 can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product.

[0163] Memory 7, as a computer-readable storage medium, can be used to store software programs and computer-executable programs, such as program instructions / modules corresponding to the methods in the embodiments of the present application. Processor 5 executes the program instructions / modules stored in memory 7 to execute functional applications and data processing, thereby implementing the above-mentioned task solution determination method.

[0164] The memory 7 may include a program storage area and a data storage area. The program storage area may store an operating system and at least one application required for a function; the data storage area may store data generated based on the use of the terminal device. Furthermore, the memory 7 may include a high-speed random access memory and a non-volatile memory.

[0165] The electronic device may be a computer or a server.

[0166] An embodiment of the present application provides a storage medium storing computer-executable instructions, wherein the computer-executable instructions are configured to execute the above-mentioned task solution determination method.

[0167] An embodiment of the present application provides a computer program product, which includes a computer program stored on a storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer executes the above-mentioned task solution determination method.

[0168] The aforementioned computer-readable storage medium may be a transient computer-readable storage medium or a non-transitory computer-readable storage medium.

[0169] The technical solutions of the embodiments of the present application can be embodied in the form of a software product, which is stored in a storage medium and includes one or more instructions for causing a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in the embodiments of the present application. The aforementioned storage medium can be a non-transitory storage medium, including: a USB flash drive, a mobile hard disk, a read-only memory, a random access memory, a magnetic disk, an optical disk, and other media that can store program code, or a transient storage medium.

[0170] In the embodiments provided herein, it should be understood that the disclosed devices and methods may be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of the units is merely a logical functional division, and actual implementation may employ other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not implemented.

[0171] The above description is merely an embodiment of the present application and is not intended to limit the scope of protection of the present application. For those skilled in the art, various modifications and variations of the present application are possible. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application. Furthermore, the above embodiments may be combined with each other to form new embodiments, unless they conflict.

Claims

1. A method for determining a task plan, characterized in that: include: Obtain task requirement information; Constructing an initial task map according to the task requirement information; The initial task graph includes multiple task nodes; Deleting redundant nodes in the initial task graph according to the task attributes of each task node to obtain a target task graph; the task attributes are indicators for evaluating the historical execution process of the task nodes; Extracting all task solutions in the target task map; wherein each path formed by the task nodes in the target task map is a task solution; The method comprises: deleting redundant nodes in the initial task graph according to the task attributes of each task node to obtain a target task graph, including: determining nodes to be deleted according to the task attributes, deleting the nodes to be deleted from the initial task graph to obtain an intermediate graph; determining whether necessary connection nodes are missing in the intermediate graph; and in the case of missing necessary connection nodes, completing the missing necessary connection nodes in the intermediate graph to obtain the target task graph; the redundant nodes are the nodes to be deleted that are not necessary connection nodes; Determining whether necessary connection nodes are missing in the intermediate graph includes: obtaining a node completion model; the node completion model is obtained by training using a preset historical scheme; the preset historical scheme has sample task nodes, necessary connection nodes of the sample task nodes, and node attributes of the sample task nodes; inputting each of the task nodes and the node attributes of each of the task nodes into the node completion model to obtain necessary connection nodes corresponding to each of the task nodes; determining whether the task node lacks necessary connection nodes based on the necessary connection nodes and actual connection nodes of the task node; the actual connection nodes are other task nodes connected to the task node in the target task graph; Each of the task nodes corresponds to a task item execution subject; the task item execution subject is used to execute the corresponding task node; the node attributes of each of the task nodes in the target task map include: time constraints; the method further includes: obtaining the estimated time corresponding to the task item execution subject of each of the task nodes in the target task map; the estimated time reflects the efficiency of the task item execution subject in processing the task node; determining the priority score of each of the task nodes according to the time constraints and the estimated time of each of the task nodes in the target task map; determining the priority processing level of each of the task plans according to the priority score of each of the task nodes; Obtaining the estimated time corresponding to the task item execution subject of each task node in the target task map, including: inputting the task item execution subject of each task node in the target task map into a preset ranking model to obtain the efficiency ranking of each task item execution subject; determining the estimated time of each task item execution subject according to the efficiency ranking; The ranking model is obtained by: obtaining first training data and scores and modification records for historical solutions within a historical preset time period; the first training data is data located before the historical preset time period and used to train the ranking model; the modification records are used to describe the efficiency ranking of multiple task item execution entities after correction; second training data is obtained based on the scores and the modification records; a preset model is trained using the first training data and the second training data to obtain a reference ranking model; target model parameters are determined based on first model parameters of the reference ranking model and second model parameters of the historical ranking model; and the model parameters of the historical ranking model are adjusted to target model parameters to obtain the ranking model; Determining target model parameters based on the first model parameters of the reference ranking model and the second model parameters of the historical ranking model includes: obtaining a quality score of the historical solution; the quality score is used to reflect the logical correctness of the historical solution; determining a weight parameter based on the quality score; and weighting the first model parameter and the second model parameter according to the weight parameter to obtain the target model parameter; The node attributes of each task node in the target task map include a preset node score; the task attributes include a historical execution success rate; and the priority score of each task node is determined according to the time constraint and the estimated time consumption of each task node in the target task map, including: for each task node: determining the priority score of the task node according to the estimated time consumption, the time constraint, the historical execution success rate and the preset node score corresponding to the task node; The quality score is obtained in the following way: for each historical plan: determine the structural similarity between the task plan and the historical plan, obtain the semantic similarity and rule pass rate corresponding to the historical plan, weight the structural similarity, semantic similarity and rule pass rate according to the preset third weight set, and obtain the alternative score of the historical plan; calculate the average value of the alternative scores of each historical plan to obtain the quality score.

2. The method according to claim 1, characterized in that The task attributes include historical execution time; determining the node to be deleted based on the task attributes includes: Obtaining the node out-degree of each task node; Determine the pending judgment score corresponding to each task node according to the historical execution time and node out-degree corresponding to each task node; If the to-be-determined score corresponding to the task node is lower than a preset score, the task node is determined to be a node to be deleted.

3. The method according to claim 1, characterized in that The method further comprises: Inputting the task plan into a preset risk prediction model to obtain the risk type corresponding to the task plan and the risk probability of the risk type; When the risk probability is greater than a preset probability, a risk control strategy is determined according to the risk type, and the task plan is adjusted according to the risk control strategy.

4. The method according to claim 3, characterized in that The method further comprises: When the risk probability is less than or equal to a preset probability, obtaining an execution result of the task plan; Performing quality verification on the execution results; In the event that the quality verification fails, a risk control strategy is determined based on the risk type, and the task plan is adjusted according to the risk control strategy.

5. The method according to claim 4, characterized in that Perform quality verification on the execution results, including: Determining the semantic similarity between the execution result and a preset historical execution result, and determining that the quality verification has failed if the semantic similarity is less than the preset similarity; the historical execution result and the execution result belong to the same task scenario; and / or, Determine whether the execution result meets the preset indicators. If the execution result does not meet the preset indicators, determine that the quality verification has failed; the preset indicators are the compliance conditions of the task scenario to which the execution result belongs.

6. The method according to any one of claims 1 to 5, characterized in that Constructing an initial task map based on the task requirement information, including: Converting the task requirement information into structured data; the structured data includes task items; Determining dependencies between the task items; The task items are used as the task nodes and connected according to the dependency relationship to obtain the initial task graph.

7. A task plan determination device, characterized in that: include: Acquisition module, used to obtain task requirement information; A construction module, configured to construct an initial task map according to the task requirement information; The initial task graph includes multiple task nodes; An adjustment module, configured to delete redundant nodes in the initial task graph according to the task attributes of each task node to obtain a target task graph; the task attributes are indicators for evaluating the historical execution process of the task nodes; A task determination module is used to extract all task solutions in the target task map; wherein each path formed by the task nodes in the target task map is a task solution; The adjustment module is used to delete redundant nodes in the initial task graph according to the task attributes of each task node in the following manner to obtain a target task graph: determine the node to be deleted according to the task attributes, delete the node to be deleted from the initial task graph to obtain an intermediate graph; determine whether the intermediate graph lacks necessary connection nodes; if the necessary connection nodes are missing, fill in the missing necessary connection nodes in the intermediate graph to obtain the target task graph; the redundant nodes are the nodes to be deleted that do not belong to the necessary connection nodes; Determining whether necessary connection nodes are missing in the intermediate graph includes: obtaining a node completion model; the node completion model is obtained by training using a preset historical scheme; the preset historical scheme has sample task nodes, necessary connection nodes of the sample task nodes, and node attributes of the sample task nodes; inputting each of the task nodes and the node attributes of each of the task nodes into the node completion model to obtain necessary connection nodes corresponding to each of the task nodes; determining whether the task node lacks necessary connection nodes based on the necessary connection nodes and actual connection nodes of the task node; the actual connection nodes are other task nodes connected to the task node in the target task graph; Each of the task nodes corresponds to a task item execution subject; the task item execution subject is used to execute the corresponding task node; the node attributes of each of the task nodes in the target task map include: time constraints; the device also includes: obtaining the estimated time corresponding to the task item execution subject of each of the task nodes in the target task map; the estimated time reflects the efficiency of the task item execution subject in processing the task node; determining the priority score of each of the task nodes according to the time constraints and the estimated time of each of the task nodes in the target task map; determining the priority processing level of each of the task plans according to the priority score of each of the task nodes; Obtaining the estimated time corresponding to the task item execution subject of each task node in the target task map, including: inputting the task item execution subject of each task node in the target task map into a preset ranking model to obtain the efficiency ranking of each task item execution subject; determining the estimated time of each task item execution subject according to the efficiency ranking; The ranking model is obtained by: obtaining first training data and scores and modification records for historical solutions within a historical preset time period; the first training data is data located before the historical preset time period and used to train the ranking model; the modification records are used to describe the efficiency ranking of multiple task item execution entities after correction; second training data is obtained based on the scores and the modification records; a preset model is trained using the first training data and the second training data to obtain a reference ranking model; target model parameters are determined based on first model parameters of the reference ranking model and second model parameters of the historical ranking model; and the model parameters of the historical ranking model are adjusted to target model parameters to obtain the ranking model; Determining target model parameters based on the first model parameters of the reference ranking model and the second model parameters of the historical ranking model includes: obtaining a quality score of the historical solution; the quality score is used to reflect the logical correctness of the historical solution; determining a weight parameter based on the quality score; and weighting the first model parameter and the second model parameter according to the weight parameter to obtain the target model parameter; The node attributes of each task node in the target task map include a preset node score; the task attributes include a historical execution success rate; and the priority score of each task node is determined according to the time constraint and the estimated time consumption of each task node in the target task map, including: for each task node: determining the priority score of the task node according to the estimated time consumption, the time constraint, the historical execution success rate and the preset node score corresponding to the task node; The quality score is obtained in the following way: for each historical plan: determine the structural similarity between the task plan and the historical plan, obtain the semantic similarity and rule pass rate corresponding to the historical plan, weight the structural similarity, semantic similarity and rule pass rate according to the preset third weight set, and obtain the alternative score of the historical plan; calculate the average value of the alternative scores of each historical plan to obtain the quality score.

8. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores computer-executable instructions that can be executed by the processor, and the processor executes the computer-executable instructions to implement the task solution determination method according to any one of claims 1 to 6.

9. A computer program product, characterized in that The computer program product includes a computer program, and when the computer program is executed by a processor, the task solution determination method according to any one of claims 1 to 6 is implemented.

10. A storage medium, characterized in that: The storage medium stores computer-executable instructions. When the computer-executable instructions are called and executed by the processor, the computer-executable instructions enable the processor to implement the task solution determination method described in any one of claims 1 to 6.

Images