FMEA-Based Permission Collaborative Management System and Method

Abstract

This application relates to the technical field of business management. Specifically, it discloses a permission collaborative management system and method based on FMEA. According to the FMEA method, the project product is disassembled according to its composition structure to form an object structure tree, and each node in the object structure tree is associated with specific R & D, production, and management tasks to form several task structure trees. Then, an artificial intelligence algorithm based on deep learning is introduced to perform data analysis on the task structure trees. Based on the node attributes of each task node in the task structure tree and the association relationships between the task nodes, a deep understanding of the task structure is achieved, so as to intelligently allocate the task structure trees to appropriate execution areas. On this basis, the production execution of tasks and the permission collaborative management between execution areas are carried out. In this way, more accurate task allocation and resource scheduling can be realized, ensuring the efficient execution of tasks and the optimal allocation of resources, and enhancing the flexibility and efficiency of cross-departmental collaboration.

Description

Technical Field

[0001] This application relates to the technical field of business management, and more specifically, to a permission collaborative management system and method based on FMEA. Background Art

[0002] With the complication of the global business production chain and the intensification of technological competition, the product or process R & D tasks faced by enterprises are becoming increasingly huge and complex. To ensure the quality and reliability of products or processes, it is crucial to introduce a systematic risk management method in the R & D stage. The traditional project management mode often focuses on the independent operation of a single department or function, which leads to low collaboration efficiency and poor information flow among different functional departments, thus affecting the overall R & D progress and quality control.

[0003] In response to this, the invention patent with the publication number CN116993305A proposes a management and analysis method for multi-person permission collaboration based on FMEA. It disassembles project products based on FMEA, constructs an object structure tree, and further distributes the R & D tasks of different node objects on the object structure tree to different R & D functional departments within a cross-functional team. Different department heads have the viewing and operating permissions to manage the R & D status of their own departments. In addition, different department heads can also grant viewing permissions to each other to achieve online business collaboration, thereby improving the R & D efficiency.

[0004] Based on the cross-functional team collaboration mechanism provided by the above solution, it can solve the problem of decentralized management of business by managers in different business departments in the prior art and promote efficient cross-departmental collaboration. However, in the process of product R & D and production, different tasks require the participation of personnel with different professional backgrounds. In the prior art, for task allocation, it mainly relies on pre-set rules and manual judgment, which is difficult to adapt to the rapidly changing project requirements and technological development trends, and is easily affected by factors such as personal biases and knowledge blind spots of decision-makers, which may lead to resource waste and further affect the progress and quality of the entire project.

[0005] Therefore, an optimized permission collaborative management system and method based on FMEA are expected. Summary of the Invention

[0006] To solve the above technical problems, this application is proposed. Embodiments of this application provide a permission collaborative management system and method based on FMEA. Based on the FMEA method, the project product is disassembled according to its composition structure to form an object structure tree, and each node in the object structure tree is associated with specific R & D, production, and management tasks to form several task structure trees. Then, an artificial intelligence algorithm based on deep learning is further introduced to perform data analysis on the task structure trees. Based on the node attributes of each task node in the task structure tree and the association relationships between the task nodes, a deep understanding of the task structure is achieved, so as to intelligently allocate the task structure trees to appropriate execution areas, facilitating the production execution of tasks and the permission collaborative management between execution areas on this basis. In this way, more accurate task allocation and resource scheduling can be achieved, ensuring the efficient execution of tasks and the optimal allocation of resources, and enhancing the flexibility and efficiency of cross-departmental collaboration.

[0007] According to one aspect of this application, a permission collaborative management method based on FMEA is provided, which includes: disassembling the project product based on FMEA to construct an object structure tree; disassembling the object structure tree into several task structure trees and allocating the task structure trees to execution areas; all the execution areas analyze and manage the production of the task structure trees they are responsible for; all the execution areas access each other based on preset permission rules and then conduct business collaboration.

[0008] In the above permission collaborative management method based on FMEA, disassembling the object structure tree into several task structure trees and allocating the task structure trees to execution areas includes: extracting a first task structure tree from the several task structure trees; extracting the node attributes of each task node from the first task structure tree; performing semantic embedding encoding on the node attributes of each task node to obtain a set of task node attribute semantic embedding encoding vectors; performing semantic optimization processing based on medium-grained semantic association constraints on the set of task node attribute semantic embedding encoding vectors to obtain a set of medium-grained semantic enhanced task node attribute semantic embedding encoding vectors; based on the association relationships between the task nodes in the first task structure tree, performing context semantic encoding on the set of medium-grained semantic enhanced task node attribute semantic embedding encoding vectors to obtain a first task structure tree context semantic encoding matrix; based on the first task structure tree context semantic encoding matrix, determining the allocation result of the first task structure tree.

[0009] According to another aspect of the present application, a permission collaborative management system based on FMEA is provided, which includes: a task structure extraction module for extracting a first task structure tree from a plurality of task structure trees; a node attribute extraction module for extracting the node attributes of each task node from the first task structure tree; a semantic embedding encoding module for performing semantic embedding encoding on the node attributes of each task node to obtain a set of task node attribute semantic embedding encoding vectors; a semantic optimization module for performing semantic optimization processing based on medium-grained semantic association constraints on the set of task node attribute semantic embedding encoding vectors to obtain a set of medium-grained semantic enhanced task node attribute semantic embedding encoding vectors; a context semantic encoding module for performing context semantic encoding on the set of medium-grained semantic enhanced task node attribute semantic embedding encoding vectors based on the association relationships between the task nodes in the first task structure tree to obtain a first task structure tree context semantic encoding matrix; and an allocation result determination module for determining the allocation result of the first task structure tree based on the first task structure tree context semantic encoding matrix.

[0010] Compared with the prior art, the permission collaborative management system and method based on FMEA provided by the present application disassemble the project product according to its composition structure based on the FMEA method to form an object structure tree, and associate each node in the object structure tree with specific R & D, production, and management tasks to form a plurality of task structure trees. Then, an artificial intelligence algorithm based on deep learning is further introduced to perform data analysis on the task structure trees. Based on the node attributes of each task node in the task structure trees and the association relationships between the task nodes, a deep understanding of the task structure is realized, so as to intelligently allocate the task structure trees to appropriate execution areas, facilitate the production execution of tasks and the permission collaborative management between execution areas on this basis. In this way, more accurate task allocation and resource scheduling can be achieved, ensuring the efficient execution of tasks and the optimal allocation of resources, and enhancing the flexibility and efficiency of cross-departmental collaboration. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other objects, features, and advantages of the present application will become more obvious. The accompanying drawings are used to provide a further understanding of the embodiments of the present application, and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation to the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0012] Figure 1 It is a flowchart of a permission collaborative management method based on FMEA according to an embodiment of the present application.

[0013] Figure 2Schematic diagram of data flow for the FMEA-based permission collaborative management method according to an embodiment of the present application.

[0014] Figure 3 Flowchart of sub-step S4 of the FMEA-based permission collaborative management method according to an embodiment of the present application.

[0015] Figure 4 Flowchart of sub-step S41 of the FMEA-based permission collaborative management method according to an embodiment of the present application.

[0016] Figure 5 Flowchart of sub-step S5 of the FMEA-based permission collaborative management method according to an embodiment of the present application.

[0017] Figure 6 Block diagram of the FMEA-based permission collaborative management system according to an embodiment of the present application. Detailed implementation manners

[0018] As shown in the present application and the claims, unless the context clearly indicates otherwise, words such as "a", "an", "one", and / or "the" are not specifically singular and may also include the plural. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of the clearly identified steps and elements, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0019] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, however, any number of different modules can be used and run on the user terminal and / or the server. The modules are only illustrative, and different aspects of the system and method can use different modules.

[0020] In the present application, flowcharts are used to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the operations before or below do not necessarily need to be executed precisely in sequence. On the contrary, according to needs, various steps can be executed in reverse order or simultaneously. At the same time, other operations can also be added to these processes, or one or several steps can be removed from these processes.

[0021] Next, exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. It should be understood that the present application is not limited by the exemplary embodiments described herein.

[0022] It should be noted that in the present application, all actions of obtaining data are carried out on the premise of complying with the corresponding data protection regulations and policies of the country where the data is located and obtaining the authorization given by the owner of the corresponding device.

[0023] As described in the above background art, patent CN116993305A proposes a management and analysis method for multi-person permission collaboration based on FMEA, which includes: disassembling project products based on FMEA to construct an object structure tree; disassembling the object structure tree into several task structure trees and assigning the task structure trees to execution areas; all the execution areas analyze and manage production for the responsible task structure trees; all the execution areas access each other based on preset permission rules and then conduct business collaboration.

[0024] Based on the cross-functional team collaboration solution provided by the above scheme, it can solve the problem of decentralized management of business by managers in different business departments in the prior art and promote efficient cross-departmental collaboration. However, in the process of product R & D and production, different tasks require personnel with different professional backgrounds. In the prior art, for task allocation, it mainly relies on preset rules and manual judgment, which is difficult to adapt to the rapidly changing project requirements and technological development trends, and is easily affected by factors such as personal biases and knowledge blind spots of decision-makers, which may lead to waste of resources and then affect the progress and quality of the entire project. To address this technical problem, this application proposes an optimized permission collaboration management method based on FMEA. On the basis of the prior art, it further introduces an artificial intelligence algorithm based on deep learning to perform data analysis on the task structure tree. Based on the node attributes of each task node in the task structure tree and the association relationships between each task node, it realizes a deep understanding of the task structure, so as to intelligently assign the task structure tree to a suitable execution area, facilitating the production execution of tasks and the permission collaboration management between execution areas on this basis. In this way, more accurate task allocation and resource scheduling can be achieved, ensuring the efficient execution of tasks and the optimized allocation of resources, and enhancing the flexibility and efficiency of cross-departmental collaboration.

[0025] In the above permission collaboration management method based on FMEA, it is first necessary to use the FMEA method to conduct a comprehensive risk assessment of project products. FMEA is a preventive quality management tool that can help identify possible failure modes and their potential impacts, so as to take measures in the early stages of design and production to reduce risks. By systematically analyzing the functions, failure probabilities, and failure consequences of each component, it can be determined which parts need special attention or improvement. The result of this step is a detailed risk list that contains all the identified risk points and their priority rankings.

[0026] Next, construct an object structure tree based on the results of FMEA. The object structure tree is a hierarchical representation of the entire project product, which decomposes the product or process according to functional modules, subsystems, or other logical units. Each node represents a component of the product or a stage of the process, and the connections between nodes reflect the dependencies between nodes. The purpose of constructing the object structure tree is to provide a clear framework for subsequent task decomposition and resource allocation. In this process, it is important to maintain the rationality and integrity of the structure tree to ensure that all key elements are covered and the hierarchical relationships are correct.

[0027] With the object structure tree as the basis, it is then further decomposed into several task structure trees. The task structure tree is a refined description of a specific functional module or subsystem, which breaks down each large task into a series of specific work items. These work items constitute the complete R & D process, from preliminary design to final test verification, and each task node carries rich attribute information, such as name, type, estimated time-consuming, required resources, responsible person, etc. In this way, the originally complex product or process is converted into multiple relatively independent but interrelated task sets, which is convenient for management and tracking.

[0028] Figure 1 It is a flowchart of the FMEA-based permission collaborative management method according to an embodiment of the present application. Figure 2 It is a schematic diagram of data flow of the FMEA-based permission collaborative management method according to an embodiment of the present application. As Figure 1 and Figure 2 shown, the FMEA-based permission collaborative management method includes the steps: S1, extracting a first task structure tree from the several task structure trees; S2, extracting the node attributes of each task node from the first task structure tree; S3, performing semantic embedding encoding on the node attributes of each task node to obtain a set of task node attribute semantic embedding encoding vectors; S4, performing semantic optimization processing based on medium-grained semantic association constraints on the set of task node attribute semantic embedding encoding vectors to obtain a set of medium-grained semantic enhanced task node attribute semantic embedding encoding vectors; S5, based on the association relationships between the task nodes in the first task structure tree, performing context semantic encoding on the set of medium-grained semantic enhanced task node attribute semantic embedding encoding vectors to obtain a first task structure tree context semantic encoding matrix; S6, determining the allocation result of the first task structure tree based on the first task structure tree context semantic encoding matrix.

[0029] In the above-mentioned FMEA-based permission collaborative management method, in step S1, the first task structure tree is extracted from the several task structure trees. It should be understood that project products usually have complex composition structures. Decomposing them according to the composition structure to establish an object structure tree helps to more meticulously analyze and manage the R & D analysis tasks of each component. Each node in the object structure tree represents each component of the project product. For the convenience of subsequent planning and scheduling, further according to the functional requirements of each node in the object structure tree, it is converted into a specific task list, and a task structure tree corresponding to each component is created. By independently analyzing the data of each task structure tree, it helps to more precisely understand and allocate and manage the R & D analysis tasks of each component of the project product. Based on this, in this application, by extracting the first task structure tree from the several task structure trees, independent analysis and allocation management of the task structure tree are achieved.

[0030] Specifically, when establishing the task structure tree, comprehensive considerations must be based on factors such as project priority, risk assessment, and resource availability. The project schedule and importance determine which task nodes should be processed first; the results of FMEA (Failure Mode and Effects Analysis) or other risk management tools help identify potential risk points and adjust the order of task nodes accordingly; at the same time, the capabilities and limitations of existing resources also need to be evaluated to ensure that the selected task nodes can be carried out smoothly under the current conditions. In addition, it is also very important to analyze whether there are preconditions or post-effects between each task node, which helps to plan a reasonable task sequence and avoid unnecessary delays and resource waste.

[0031] In addition to the above quantitative analysis, qualitative factors such as the professional backgrounds and technical capabilities of team members also need to be considered to ensure that the team's advantages are fully utilized and do not exceed their capabilities. In this way, the enthusiasm and work efficiency of the team can be improved, and at the same time, the probability of problems caused by skill mismatches can also be reduced.

[0032] Next, it is also necessary to test the performance of the extracted first task structure tree throughout the project life cycle through simulation, including but not limited to aspects such as schedule, cost, and quality. This method can not only discover potential problems in advance but also provide a basis for optimizing the plan. The simulation results should reflect the actual situation as detailed as possible to make a more scientific and reasonable judgment. If obvious defects are exposed in the first task structure tree during the simulation process, it is necessary to return to the previous step to re-evaluate other options to ensure that the established task structure tree better meets the actual needs and expected goals. Through repeated simulation and optimization, the robustness and adaptability of the task structure tree can be ensured. Finally, when the first task structure tree passes the simulation test, it can be used as the basis for project implementation for subsequent allocation work.

[0033] In the above-mentioned authority collaboration management method based on FMEA, in step S2, the node attributes of each task node are extracted from the first task structure tree. It should be understood that the task structure tree contains multiple subtasks involved in the production and R & D process of product components, and each subtask corresponds to specific node attributes, including but not limited to key information such as the type, priority, functional requirements, required professional skills, resource requirements, time limit, etc. of the task node, which is the key basis for task allocation and execution. For example, in an automobile manufacturing project, the node attributes of the "engine assembly" task node include: task name: engine assembly; task type: assembly; priority: high; functional requirements: construction and debugging of the engine assembly line; required professional skills: mechanical engineering, electronic engineering; resource requirements: assembly line equipment, professional tools; performance indicators: ensure that the maximum output power of the engine reaches the design value and there is no leakage phenomenon; potential failure mode: air leakage caused by improper installation of piston rings; failure consequence: the engine cannot work properly and the vehicle cannot drive. Therefore, by extracting the node attributes of each task node from the first task structure tree, this application helps to understand the specific content, execution objectives and requirements of each task node in detail, so as to provide detailed data support for subsequent task allocation and resource scheduling.

[0034] Node attributes refer to the set of information carried by each task node in the task structure tree, and these information describe the basic characteristics, requirements, limiting conditions, etc. of the task. For example, a task node may have attributes such as name, type (such as design, test), estimated time-consuming, required resources, responsible person, prerequisite task, post-task, etc. By extracting and analyzing these attributes, it is possible to understand the specific content of each task and its position and role in the entire project more deeply, so as to achieve the purposes of refined management, optimized resource allocation, risk assessment and control, improved communication efficiency and enhanced decision-making quality.

[0035] In order to effectively extract the node attributes of each task node from the first task structure tree, a systematic process must be followed, that is, to define a standard attribute set applicable to all task nodes. The attribute set should cover the key elements of the task and also consider the special requirements of the project. For example, in some cases, in addition to the regular attributes, specific domain indicators such as safety requirements and regulatory compliance may also need to be added.

[0036] Next, for each task node, data collection is carried out according to a predefined set of standard attributes. Considering that the collected data is not always completely accurate or complete, it must undergo strict verification and validation. On the one hand, the consistency and rationality of the data should be checked to avoid logical errors or obvious deviations; on the other hand, for uncertain or ambiguous parts, further investigation and verification should be carried out, and data should be recollected if necessary. Only the verified data can be used as the basis for subsequent work to ensure that the decisions made based on this data are scientific and reasonable.

[0037] After ensuring the accuracy and integrity of the data, additional dimensions can also be considered to enrich the node attributes. For example, connecting the task node with its related documents, code repositories, test cases, etc., to facilitate subsequent query and use; or adding external factors such as geographical location and environmental conditions as auxiliary attributes to help better understand and process the task. Such extensions not only enhance the depth and breadth of the node attributes but also provide more flexibility and support for subsequent work.

[0038] Finally, considering that the project is a dynamically developing process, as the project progresses, the content and requirements of the tasks may change. Therefore, a mechanism needs to be established to continuously track and update the node attributes to ensure that they always reflect the latest situation. Through continuous data update and maintenance, it not only helps to maintain the timeliness of the data but also promotes the efficient management and high-quality delivery of the entire project.

[0039] In the above-mentioned FMEA-based permission collaborative management method, in step S3, semantic embedding encoding is performed on the node attributes of each task node to obtain a set of task node attribute semantic embedding encoding vectors. In a specific example of this application, step S3 includes: using a semantic embedding encoder based on the Bert model to perform semantic embedding encoding on the node attributes of each task node to obtain the set of task node attribute semantic embedding encoding vectors. It should be understood that since the attribute descriptions of each task node usually contain rich text information, in order to further use computer models to perform efficient data analysis and processing on this text information, it is necessary to convert the node attributes of each task node into a numerical form that can be understood by a computer. Based on this, this application uses a semantic embedding encoder based on the Bert model to perform semantic embedding encoding on the node attributes of each task node respectively, so as to map the node attributes of each task node to a high-dimensional semantic space and form a set of task node attribute semantic embedding encoding vectors. Those of ordinary skill in the art should know that the Bert model uses a bidirectional Transformer encoder architecture, which can consider the context information of each word in the text sequence at the same time, so as to capture richer and more accurate semantic representations. When processing the node attributes of task nodes, the Bert model can understand and parse the complex semantic relationships in the attribute descriptions, map them to specific positions in the high-dimensional semantic space, and form vectors with semantic meanings.

[0040] In the above-mentioned FMEA-based permission collaborative management method, in step S4, semantic optimization processing based on medium-grained semantic association constraints is performed on the set of task node attribute semantic embedding encoding vectors to obtain a set of medium-grained semantic enhanced task node attribute semantic embedding encoding vectors. That is, in order to capture the complex semantic relationships between each task node at a higher level, such as implicit logical connections, context dependence relationships, and potential interaction effects, etc., this application further performs context-aware enhancement processing based on local windows on the semantic embedding encoding vectors of each task node attribute, so as to utilize the context semantic association information within the local window to enhance the expression ability of the semantic embedding encoding vectors of each task node attribute, thereby more accurately understanding the relevance between task nodes and providing a more accurate basis for subsequent task assignment and collaborative management. Among them, Figure 3 is a flowchart of sub-step S4 of the FMEA-based permission collaborative management method according to an embodiment of this application. As Figure 3As shown, step S4 includes steps: S41, calculating the syntactic depth of each task node attribute semantic embedding encoding vector in the set of task node attribute semantic embedding encoding vectors to obtain the set distribution of task node attribute syntactic depth implicit representation values; S42, based on the set distribution of the task node attribute syntactic depth implicit representation values, determining the medium-grained semantic association window of each task node attribute semantic embedding encoding vector in the set of task node attribute semantic embedding encoding vectors; S43, based on the medium-grained semantic association window of each task node attribute semantic embedding encoding vector, performing medium-grained context semantic enhancement on each task node attribute semantic embedding encoding vector respectively to obtain the set of medium-grained semantic enhanced task node attribute semantic embedding encoding vectors.

[0041] Figure 4 It is a flowchart of sub-step S41 of the FMEA-based permission collaborative management method according to an embodiment of the present application. As Figure 4 shown, step S41 includes steps: S411, mapping each task node attribute semantic embedding encoding vector in the set of task node attribute semantic embedding encoding vectors to the hyperbolic space respectively to obtain the set of hyperbolic space task node attribute semantic embedding encoding vectors; S412, calculating the syntactic depth implicit representation value of each hyperbolic space task node attribute semantic embedding encoding vector in the set of hyperbolic space task node attribute semantic embedding encoding vectors to obtain the set distribution of the task node attribute syntactic depth implicit representation values.

[0042] More specifically, step S411 is represented by the formula:

[0043]

[0044]

[0045] where represents the set of task node attribute semantic embedding encoding vectors, , , , respectively represent the 1st, 2nd, th, th task node attribute semantic embedding encoding vectors in the set of task node attribute semantic embedding encoding vectors, is the hyperbolic space mapping function, and respectively represent the first mapping weight matrix and the second mapping weight matrix, represents the corresponding hyperbolic space task node attribute semantic embedding encoding vector.

[0046] That is, considering that compared with Euclidean space, the exponentially growing volume of hyperbolic space allows for a more natural embedding of tree structures, making it more suitable for representing task structures with hierarchical relationships. Therefore, the present application further maps the semantic embedding encoding vectors of each task node attribute into hyperbolic space to utilize the special properties of hyperbolic geometry to better represent the hierarchical structure of each task node attribute, revealing the semantic hierarchy and relevance between each task node attribute.

[0047] More specifically, step S412 is expressed by the formula:

[0048]

[0049] where represents the square of the norm of the vector, represents the logarithmic function with base 2, represents the syntactic depth metric function, represents the corresponding implicit representation value of the syntactic depth of the task node attribute.

[0050] That is, by calculating the implicit representation value of the syntactic depth of the semantic embedding encoding vectors of each task node attribute after mapping in hyperbolic space, the depth in the task structure tree is analyzed, revealing the importance of each task node attribute in the task structure tree and its hierarchical relationship with other components. For example, in the task structure tree, the greater the depth of a node, the more likely it is to involve more specific subtasks or operation steps. In this way, it helps to further strengthen the semantic understanding of each task node attribute by utilizing this hierarchical information, thereby providing a more accurate basis for the intelligent allocation of tasks.

[0051] Specifically, in step S42, based on the set distribution of the syntax-depth implicit representation values of the task node attributes, determine the medium-grained semantic association window for each task node attribute semantic embedding coding vector in the set of task node attribute semantic embedding coding vectors. It should be understood that by setting a reasonable semantic association window, it can be ensured that when strengthening the semantic features of each task node attribute, important context information will not be missed, and excessive irrelevant information interference will not be introduced, which helps to capture the semantic connections between each task node attribute and other medium-scale task node attributes in a specific context, thereby improving the model's understanding ability of complex semantic structures and reducing the computational complexity. In a specific example of the present application, step S42 includes: extracting the syntax-depth implicit representation value of the first task node attribute semantic embedding coding vector in the set of task node attribute semantic embedding coding vectors as the starting position of the medium-grained semantic association window; along the set distribution of the syntax-depth implicit representation values of the task node attributes, find the task node attribute syntax-depth implicit representation value that is closest to the syntax-depth implicit representation value of the first task node attribute semantic embedding coding vector as the ending position of the medium-grained semantic association window; based on the starting position and the ending position of the medium-grained semantic association window, determine the medium-grained semantic association window of the first task node attribute semantic embedding coding vector from the set of task node attribute semantic embedding coding vectors, which is expressed by the formula:

[0052]

[0053] wherein, represents taking the absolute value, represents taking the index corresponding to the minimum value, represents the medium-grained semantic association window of, is the position index of the ; is the position index of the task node attribute syntax-depth implicit representation value that is closest to the syntax-depth implicit representation value of the ; represents the task node attribute syntax-depth implicit representation value at the th position in the set distribution of the task node attribute syntax-depth implicit representation values.

[0054] Specifically, in a specific example of the present application, the step S43 includes: calculating the semantic association scores of each task node attribute semantic embedding encoding vector in the medium-grained semantic association window of the first task node attribute semantic embedding encoding vector with respect to the first task node attribute semantic embedding encoding vector to obtain a set of first task node attribute semantic association scores; normalizing the set of first task node attribute semantic association scores to obtain a set of normalized first task node attribute semantic association scores; based on the set of normalized first task node attribute semantic association scores, calculating the position-weighted sum between each task node attribute semantic embedding encoding vector in the medium-grained semantic association window of the first task node attribute semantic embedding encoding vector to obtain the medium-grained semantic enhanced task node attribute semantic embedding encoding vector corresponding to the first task node attribute semantic embedding encoding vector, which is expressed by the formula:

[0055]

[0056] Wherein, represents the th task node attribute semantic embedding encoding vector in the set of task node attribute semantic embedding encoding vectors, represents matrix multiplication operation, is a scoring reference vector, is a scoring reference weight matrix, is a scoring bias vector, is the natural exponential function, represents the corresponding medium-grained semantic enhanced task node attribute semantic embedding encoding vector.

[0057] That is, based on the semantic association and hierarchical relationship between each task node attribute and other task node attributes within a specific window, the feature representation of the task node attribute is adjusted to better reflect the actual meaning of each task node attribute in the current context, so as to obtain a set of medium-grained semantic enhanced task node attribute semantic embedding encoding vectors. In this way, the perception ability of the semantic dependence relationship of task node attributes in the local area of the task structure tree can be effectively improved, thereby enhancing the accuracy of the semantic representation of each task node attribute.

[0058] In the above-mentioned FMEA-based permission collaboration management method, in the step S5, based on the association relationship between each task node in the first task structure tree, the set of medium-grained semantic enhanced task node attribute semantic embedding encoding vectors is contextually semantically encoded to obtain a first task structure tree context semantic encoding matrix. Wherein, Figure 5 is a flowchart of sub-step S5 of the FMEA-based permission collaboration management method according to an embodiment of the present application. AsFigure 5 As shown, step S5 includes steps: S51, extracting the association relationships between each task node from the first task structure tree to obtain an association relationship matrix; S52, inputting the set of medium-grained semantic enhanced task node attribute semantic embedding encoding vectors and the association relationship matrix into a task tree context semantic encoder based on a graph convolutional neural network model to obtain the first task structure tree context semantic encoding matrix.

[0059] Specifically, in step S51, the association relationships between each task node are extracted from the first task structure tree to obtain an association relationship matrix. It should be understood that in a task structure tree, there are usually direct or indirect dependencies between each task node. For example, the start of node a1 may depend on the prior completion of node a2, the task of node a3 can be started after the task of node a1 is completed, node a4 and node a5 can be executed in parallel and there is a certain resource sharing relationship between them, etc. These dependencies constitute the logical framework for task execution. Therefore, in order to clearly depict the pre, post, or parallel relationships between each task node and other tasks, the present application further extracts the association relationships between each task node from the first task structure tree to construct an association relationship matrix. In the association relationship matrix, each element represents the degree and type of dependence between the corresponding two task nodes. For example, if a1 is a pre-task of a2, then in the association relationship matrix A it is 1. If a2 is a pre-task of a3, then in the matrix it is 1. If a1 and a4 are parallel tasks and there is a certain resource sharing relationship between them, then in the matrix and are both assigned 0.5. In this way, the dependence relationships between task nodes can be intuitively represented, providing a basis for the reasonable arrangement and scheduling of tasks.

[0060] Specifically, in step S52, the set of semantic embedding encoding vectors of the medium-grained semantic enhancement task node attributes and the association relationship matrix are input into the task tree context semantic encoder based on the graph convolutional neural network model to obtain the first task structure tree context semantic encoding matrix. That is, in order to further utilize the association relationships between various task nodes and perform global context semantic association encoding on the attributes of each task node to achieve an understanding of the task tree structure at the global level, the present application further uses a graph convolutional neural network model to process the set of semantic embedding encoding vectors of the medium-grained semantic enhancement task node attributes and the association relationship matrix. In the technical solution of the present application, the set of semantic embedding encoding vectors of the medium-grained semantic enhancement task node attributes is used as the feature input of each node in the graph structure, and the association relationship matrix is used as the edge information of the graph structure. Through the information propagation mechanism, the graph convolutional neural network model can aggregate the information of neighbor nodes at different levels to update the feature representation of the central node, thereby effectively capturing the direct and indirect associations between task nodes, achieving global context awareness of the first task structure tree, and obtaining the first task structure tree context semantic encoding matrix. In this way, not only can the dependency relationships between task nodes be learned, but also the global semantics and positions of task nodes in the entire task structure can be understood, revealing the task association patterns hidden in the deep structure of the task tree, helping to understand the overall layout of the task structure, and thus providing a more comprehensive and in-depth information basis for the intelligent scheduling of tasks.

[0061] In the above-mentioned FMEA-based permission collaboration management method, in step S6, based on the first task structure tree context semantic encoding matrix, the allocation result of the first task structure tree is determined. In a specific example of the present application, step S6 includes: inputting the first task structure tree context semantic encoding matrix into the intelligent allocation module based on a classifier to obtain the allocation result, and the allocation result is used to represent the type label of the execution area. Specifically, the classifier learns the best matching pattern between tasks and execution areas through a training data set. In practical applications, after receiving the first task structure tree context semantic encoding matrix, the classifier performs feature learning on the first task structure tree context semantic encoding matrix to comprehensively consider the semantic features of each task node attribute and the global context information of the task structure tree, and at the same time combines the matching relationships learned during the training process to intelligently assign tasks to the most suitable execution area, thereby ensuring the efficient execution of tasks and the reasonable utilization of resources.

[0062] In a preferred example of the present application, inputting the first task structure tree context semantic encoding vector into the intelligent allocation module based on a classifier to obtain the allocation result includes:

[0063] First, calculate the distance between each pair of eigenvalues of the context semantic encoding vector of the first task structure tree, such as the L2 distance, and take the square root of the distance to obtain the first task structure tree context semantic distance representation matrix, which is expressed by the formula:

[0064]

[0065] where, represents the element value at the position in the first task structure tree context semantic distance representation matrix, and respectively represent the eigenvalue at the th position and the th position in the context semantic encoding vector of the first task structure tree, represents the distance metric function, represents the context semantic encoding vector of the first task structure tree;

[0066] Secondly, obtain the first task structure tree context semantic self - association matrix of the context semantic encoding vector of the first task structure tree as a row vector, which is expressed by the formula:

[0067]

[0068] where, represents the first task structure tree context semantic self - association matrix of the context semantic encoding vector of the first task structure tree, represents the context semantic encoding vector of the first task structure tree, and is a row vector, represents the transpose of the vector, represents matrix multiplication;

[0069] Then, multiply the context semantic encoding vector of the first task structure tree with the first task structure tree context semantic distance representation matrix to obtain the first task structure tree context semantic first - level mapping vector, which is expressed by the formula:

[0070]

[0071] where, represents the first task structure tree context semantic first - level mapping vector, represents the first task structure tree context semantic distance representation matrix;

[0072] Then, multiply the first task structure tree context semantic first-level mapping vector with the matrix product of the first task structure tree context semantic distance representation matrix and the first task structure tree context semantic self-correlation matrix to obtain the first task structure tree context semantic multi-level mapping vector, which is expressed by the formula:

[0073]

[0074] Where, represents the first task structure tree context semantic multi-level mapping vector;

[0075] Then, perform a dot product of the first task structure tree context semantic multi-level mapping vector and the first task structure tree context semantic correlation eigenvector composed of the eigenvalues of the first task structure tree context semantic self-correlation matrix to obtain an optimized first task structure tree context semantic encoding vector, where interpolation or zero-padding is performed when the eigenvalues are insufficient.

[0076] Finally, input the optimized first task structure tree context semantic encoding vector into the intelligent allocation module based on the classifier to obtain the allocation result.

[0077] This application takes into account that the set of medium-grained semantic enhancement task node attribute semantic embedding encoding vectors and the association relationship matrix respectively represent the task node attribute enhancement semantic encoding features and the task node attribute association topological features. When performing task tree context semantic encoding based on the graph convolutional neural network model, the semantic encoding enhancement of nodes will cause the graph encoding topology between nodes and edges to be unbalanced, resulting in the lack of instance judgment of the context semantic encoding features of the first task structure tree context semantic encoding vector, thereby affecting the accuracy of the allocation result obtained through the intelligent allocation module based on the classifier.

[0078] Therefore, this application performs a quadratic objective mapping representation based on the multi-level distribution hierarchy for the complete similarity instantiation of the self-correlation of the first task structure tree context semantic encoding vector through the linear objective mapping representation of the similarity distance representation matrix of the first task structure tree context semantic encoding vector obtained by expanding based on the first task structure tree context semantic encoding matrix, and compensates for the negative influence factor of association mismatch through the associated fusion kernel bias, so as to improve the eigenvalue instance judgment degree of the first task structure tree context semantic encoding vector under similarity constraints, that is, the significance degree of the eigenvalue as an instance for classification regression judgment, and improve the accuracy of the allocation result obtained by the first task structure tree context semantic encoding matrix through the intelligent allocation module based on the classifier.

[0079] After the tasks are assigned, all execution areas start to conduct in-depth analysis and production management on the task structure trees they are responsible for. This stage includes formulating detailed implementation plans, allocating necessary resources, monitoring progress, and resolving encountered problems. The execution areas not only need to ensure the tasks are completed on time and with high quality but also maintain close communication with other relevant parties, sharing information and feedback in a timely manner. Such close cooperation helps form an organic whole and jointly promote the project's progress.

[0080] Finally, all execution areas access each other based on preset permission rules, thus achieving efficient business collaboration. The permission rules define the interaction methods between different execution areas, including aspects such as data sharing and decision-making participation. For example, an execution area may have the right to view the work results of another execution area, but must obtain the consent of the other party before making modifications; or, in major decisions, all relevant execution areas need to participate in discussions and reach a consensus. Such a mechanism not only ensures the smooth flow of information but also maintains the respective responsibility boundaries.

[0081] In summary, the FMEA-based permission collaborative management method according to the embodiments of the present application is elucidated. It disassembles the project product according to its composition structure based on the FMEA method to form an object structure tree, and associates each node in the object structure tree with specific R & D, production, and management tasks to form several task structure trees. Then, an artificial intelligence algorithm based on deep learning is further introduced to conduct data analysis on the task structure trees. Based on the node attributes of each task node and the association relationships between the task nodes in the task structure tree, a deep understanding of the task structure is achieved, so as to intelligently allocate the task structure trees to appropriate execution areas, facilitating the production execution of tasks and the permission collaborative management between execution areas on this basis. In this way, more accurate task allocation and resource scheduling can be achieved, ensuring the efficient execution of tasks and the optimal allocation of resources, and enhancing the flexibility and efficiency of cross-departmental collaboration.

[0082] Furthermore, an FMEA-based permission collaborative management system is also provided.

[0083] Figure 6 It is a block diagram of the FMEA-based permission collaborative management system according to the embodiments of the present application. As Figure 6As shown, the FMEA-based permission collaborative management system 100 according to an embodiment of the present application includes: a task structure extraction module 110, configured to extract a first task structure tree from a plurality of task structure trees; a node attribute extraction module 120, configured to extract node attributes of each task node from the first task structure tree; a semantic embedding encoding module 130, configured to perform semantic embedding encoding on the node attributes of each task node to obtain a set of task node attribute semantic embedding encoding vectors; a semantic optimization module 140, configured to perform semantic optimization processing based on medium-grained semantic association constraints on the set of task node attribute semantic embedding encoding vectors to obtain a set of medium-grained semantic enhanced task node attribute semantic embedding encoding vectors; a context semantic encoding module 150, configured to perform context semantic encoding on the set of medium-grained semantic enhanced task node attribute semantic embedding encoding vectors based on the association relationships between the task nodes in the first task structure tree to obtain a first task structure tree context semantic encoding matrix; and an allocation result determination module 160, configured to determine an allocation result of the first task structure tree based on the first task structure tree context semantic encoding matrix.

[0084] Here, those skilled in the art can understand that the specific operations of each module in the above FMEA-based permission collaborative management system have been described in detail above with reference to Figures 1 to 5 the description of the FMEA-based permission collaborative management method, and therefore, the repeated description thereof will be omitted.

[0085] The basic principles of the present invention have been described above in conjunction with specific embodiments. However, it should be noted that the advantages, benefits, effects, etc. mentioned in the present invention are only examples and not limitations, and it cannot be considered that these advantages, benefits, effects, etc. are essential for each embodiment of the present invention. In addition, the specific details of the above embodiments are only for the purpose of illustration and easy understanding, rather than limitations. The above details do not limit the present invention to necessarily adopt the above specific details to implement.

[0086] In the above embodiments, the descriptions of each embodiment have their own emphases. For parts not detailed or recorded in a certain embodiment, reference may be made to the relevant descriptions of other embodiments. In the several embodiments provided by the present invention, it should be understood that the disclosed system and method can be implemented in other ways. For example, the system embodiments described above are only illustrative. For example, the unit division is only a logical function division, and there may be other division methods in actual implementation. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0087] It is obvious to those skilled in the art that the present invention is not limited to the details of the above-described exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be embraced by the present invention. Any reference signs in the claims should not be construed as limiting the claims involved.

[0088] In addition, it is obvious that the term "comprising" does not exclude other units or steps, and the singular does not exclude the plural. The multiple units recited in the system claims can also be implemented by one unit through software or hardware.

[0089] Finally, it should be noted that the above description has been given for purposes of illustration and description. In addition, the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A permission collaborative management method based on FMEA, comprising: Decompose the project product based on FMEA and construct an object structure tree; Decompose the object structure tree into several task structure trees and allocate the task structure trees to the execution areas; All the execution areas analyze and manage the production of the responsible task structure trees; all the execution areas access each other based on preset permission rules and then conduct business collaboration. It is characterized in that decomposing the object structure tree into several task structure trees and allocating the task structure trees to the execution areas includes: Extract the first task structure tree from the several task structure trees; Extract the node attributes of each task node from the first task structure tree; Perform semantic embedding encoding on the node attributes of each task node to obtain a set of task node attribute semantic embedding encoding vectors; Perform semantic optimization processing based on medium-grained semantic association constraints on the set of task node attribute semantic embedding encoding vectors to obtain a set of medium-grained semantic enhanced task node attribute semantic embedding encoding vectors; Based on the association relationships between the task nodes in the first task structure tree, perform context semantic encoding on the set of medium-grained semantic enhanced task node attribute semantic embedding encoding vectors to obtain a first task structure tree context semantic encoding matrix; Based on the first task structure tree context semantic encoding matrix, determine the allocation result of the first task structure tree; Among them, based on the association relationships between the task nodes in the first task structure tree, performing context semantic encoding on the set of medium-grained semantic enhanced task node attribute semantic embedding encoding vectors to obtain a first task structure tree context semantic encoding matrix includes: Extract the association relationships between the task nodes from the first task structure tree to obtain an association relationship matrix; Input the set of medium-grained semantic enhanced task node attribute semantic embedding encoding vectors and the association relationship matrix into a task tree context semantic encoder based on a graph convolutional neural network model to obtain the first task structure tree context semantic encoding matrix; Among them, performing semantic optimization processing based on medium-grained semantic association constraints on the set of task node attribute semantic embedding encoding vectors to obtain a set of medium-grained semantic enhanced task node attribute semantic embedding encoding vectors includes: Calculate the syntactic depth of each task node attribute semantic embedding encoding vector in the set of task node attribute semantic embedding encoding vectors to obtain a set distribution of task node attribute syntactic depth implicit representation values; Based on the set distribution of task node attribute syntactic depth implicit representation values, determine the medium-grained semantic association window of each task node attribute semantic embedding encoding vector in the set of task node attribute semantic embedding encoding vectors; Based on the medium-grained semantic association window of each task node attribute semantic embedding encoding vector, perform medium-grained context semantic enhancement on each task node attribute semantic embedding encoding vector respectively to obtain the set of medium-grained semantic enhanced task node attribute semantic embedding encoding vectors.

2. The FMEA-based permission collaborative management method according to claim 1, wherein Performing semantic embedding encoding on the node attributes of each task node to obtain a set of task node attribute semantic embedding encoding vectors includes: Use a semantic embedding encoder based on the Bert model to perform semantic embedding encoding on the node attributes of each of the task nodes to obtain a set of task node attribute semantic embedding encoding vectors.

3. The method for permission collaborative management based on FMEA according to claim 2, wherein Calculate the syntactic depth of each task node attribute semantic embedding encoding vector in the set of task node attribute semantic embedding encoding vectors to obtain a set distribution of task node attribute syntactic depth implicit representation values, including: Map each task node attribute semantic embedding encoding vector in the set of task node attribute semantic embedding encoding vectors to the hyperbolic space respectively to obtain a set of hyperbolic space task node attribute semantic embedding encoding vectors; Calculate the syntactic depth implicit representation values of each hyperbolic space task node attribute semantic embedding encoding vector in the set of hyperbolic space task node attribute semantic embedding encoding vectors to obtain the set distribution of the task node attribute syntactic depth implicit representation values.

4. The method for permission collaborative management based on FMEA according to claim 3, wherein Based on the set distribution of the task node attribute syntactic depth implicit representation values, determine the medium-grained semantic association window of each task node attribute semantic embedding encoding vector in the set of task node attribute semantic embedding encoding vectors, including: Extract the syntactic depth implicit representation value of the first task node attribute semantic embedding encoding vector in the set of task node attribute semantic embedding encoding vectors as the starting position of the medium-grained semantic association window; Along the set distribution of the task node attribute syntactic depth implicit representation values, find the task node attribute syntactic depth implicit representation value closest to the syntactic depth implicit representation value of the first task node attribute semantic embedding encoding vector as the ending position of the medium-grained semantic association window; Based on the starting position and the ending position of the medium-grained semantic association window, determine the medium-grained semantic association window of the first task node attribute semantic embedding encoding vector from the set of task node attribute semantic embedding encoding vectors.

5. The method for permission collaborative management based on FMEA according to claim 4, wherein Based on the medium-grained semantic association windows of each task node attribute semantic embedding encoding vector, perform medium-grained context semantic enhancement on each task node attribute semantic embedding encoding vector respectively to obtain a set of medium-grained semantic enhanced task node attribute semantic embedding encoding vectors, including: Calculate the semantic association scores of each task node attribute semantic embedding encoding vector in the medium-grained semantic association window of the first task node attribute semantic embedding encoding vector relative to the first task node attribute semantic embedding encoding vector to obtain a set of first task node attribute semantic association scores; Perform normalization processing on the set of first task node attribute semantic association scores to obtain a set of normalized first task node attribute semantic association scores; Based on the set of normalized first task node attribute semantic association scores, calculate the position-weighted sum of each task node attribute semantic embedding encoding vector in the medium-grained semantic association window of the first task node attribute semantic embedding encoding vector to obtain the medium-grained semantic enhanced task node attribute semantic embedding encoding vector corresponding to the first task node attribute semantic embedding encoding vector.

6. The FMEA-based permission collaborative management method according to claim 5, wherein Based on the context semantic encoding matrix of the first task structure tree, determining the allocation result of the first task structure tree, including: Inputting the context semantic encoding matrix of the first task structure tree into an intelligent allocation module based on a classifier to obtain the allocation result, where the allocation result is used to represent the type label of the execution area.

7. A permission collaborative management system based on FMEA, which can implement the permission collaborative management method based on FMEA according to any one of claims 1-6, characterized in that, Including: A task structure extraction module, configured to extract the first task structure tree from a plurality of task structure trees; A node attribute extraction module, configured to extract the node attributes of each task node from the first task structure tree; A semantic embedding encoding module, configured to perform semantic embedding encoding on the node attributes of each task node to obtain a set of task node attribute semantic embedding encoding vectors; A semantic optimization module, configured to perform semantic optimization processing on the set of task node attribute semantic embedding encoding vectors based on medium-grained semantic association constraints to obtain a set of medium-grained semantic enhanced task node attribute semantic embedding encoding vectors; A context semantic encoding module, configured to perform context semantic encoding on the set of medium-grained semantic enhanced task node attribute semantic embedding encoding vectors based on the association relationship between each task node in the first task structure tree to obtain a context semantic encoding matrix of the first task structure tree; An allocation result determination module, configured to determine the allocation result of the first task structure tree based on the context semantic encoding matrix of the first task structure tree.

Images