An integrated system for collaborative design and engineering management

Abstract

The present invention discloses an integrated system for collaborative design and engineering management, including a user authentication and permission management module, a notification and communication module, a collaborative design module, a data integration and sharing module, an engineering management module, and a reporting and analysis module. The user authentication and permission management module is used for user authentication and permission management. The notification and communication module is used for real-time notification and user communication. The collaborative design module is used for real-time design collaboration and file management. The data integration and sharing module is used for collaborative design data integration and integrated data sharing. The engineering management module is used for task and resource allocation, as well as project progress tracking and feedback. The reporting and analysis module is used for generating reports and engineering analysis. The integrated system for collaborative design and engineering management of the present invention proposes a collaborative design algorithm based on Bayesian network to intelligently process engineering projects, and proposes a resource balance optimization algorithm based on evolutionary strategy to balance and optimize project resource management.

Description

Technical Field

[0001] The present invention relates to the technical fields of Bayesian networks, evolutionary strategies, and resource optimization, and particularly to an integrated system for collaborative design and engineering management. Background Art

[0002] Bayesian network technology is a probabilistic graphical model aimed at solving uncertainty and probabilistic inference problems in complex systems. In the integrated system for collaborative design and engineering management, the real-time collaboration unit intelligently collaborates to process design data through Bayesian network technology. Through probability-based association analysis, the system can more accurately capture the dependencies between design changes, improve the intelligence and efficiency of the design process, ensure that users are more agile and targeted in the design stage, contribute to optimizing the workflow of collaborative design, and improve the collaborative efficiency of the system.

[0003] Evolutionary strategies and resource optimization technology is a heuristic search and optimization method aimed at solving complex problems of resource allocation and optimization in engineering projects. In the integrated system for collaborative design and engineering management, the introduction of evolutionary strategies and resource optimization technology based on the biological principles of natural selection, crossover, and mutation automatically adjusts and optimizes the workload of system users to achieve the best state of resource balance and project progress, helps improve the intelligent level of engineering management, enables the system to respond more flexibly to changes, and ensures that the project can achieve optimal results with limited resources.

[0004] However, the existing integrated systems for collaborative design and engineering management lack sufficient intelligent processing when facing complex engineering projects, lack accuracy and flexibility in dealing with design changes, and have relatively low performance in intelligent collaborative processing of design data and resource allocation optimization. This limits the system's adaptability to complex project environments, resulting in unbalanced resource allocation and unreasonable workloads in project management, affecting the progress and efficiency of the entire project. Summary of the Invention

[0005] The purpose of the present invention is to provide an integrated system for collaborative design and engineering management to solve the problems raised in the above background art, including the lack of sufficient intelligent processing of the existing integrated systems for collaborative design and engineering management when facing complex engineering projects, the lack of accuracy and flexibility in dealing with design changes, the relatively low performance in intelligent collaborative processing of design data and resource allocation optimization, and the limited adaptability of the system to complex project environments, as well as the problems of unbalanced resource allocation and unreasonable workloads in project management, which affect the progress and efficiency of the entire project.

[0006] To achieve the above object, the present invention provides the following technical solutions: An integrated system for collaborative design and project management, including a user authentication and permission management module, a notification and communication module, a collaborative design module, a data integration and sharing module, a project management module, and a reporting and analysis module, characterized in that: The user authentication and permission management module is used to provide a user authentication mechanism and flexible permission allocation to ensure that only authorized users can access and operate the system. The notification and communication module is used to realize the functions of real-time system notifications and communication between users, through emails, short messages, and in-app notifications, to ensure efficient communication and collaboration between users. The collaborative design module includes a real-time collaboration unit and a design file management unit. The real-time collaboration unit proposes a collaborative design algorithm based on Bayesian networks for multi-user real-time collaboration, effective identification of design files, and intelligent processing of the design process. The design file management unit is used to effectively manage and organize design files, providing functions such as file upload, download, sharing, and classification to ensure the safe and orderly storage of design files. The data integration and sharing module is used for the close integration and information sharing between the collaborative design module and the project management module, and to achieve the coordination and consistency of each functional module within the system. The project management module includes a resource allocation and optimization unit and a project tracking and feedback unit. The resource allocation and optimization unit proposes a resource balance optimization algorithm based on evolutionary strategies for the reasonable allocation and optimization of resources within a project, ensuring workload balance and the optimal utilization of project resources. The project tracking and feedback unit is used to monitor the progress of a project in real time and provide immediate feedback, enabling users to quickly identify potential problems, adjust plans, and optimize work processes. The reporting and analysis module is used to generate comprehensive project reports and detailed analysis results to assist users in formulating and implementing project management decisions.

[0007] Preferably, the user authentication and permission management module, through a secure user authentication mechanism and a flexible permission management system, ensures that only authorized users can access the system and assigns corresponding permissions according to user roles, safeguarding the security of system information and data privacy.

[0008] Preferably, the notification and communication module, through instant notifications and a multi-dimensional communication mechanism, ensures that system users can obtain key information in real time, quickly respond to design changes and project progress, and promote efficient communication and collaborative work among system users.

[0009] Preferably, the collaborative design module includes a real-time collaboration unit. The real-time collaboration unit proposes a collaborative design algorithm based on Bayesian networks, which, by effectively combining the design intentions and feedback of each user, provides an efficient real-time collaboration environment, intelligently infers and processes project designs, realizes intelligent collaborative processing in the design stage of a project, and provides a reliable foundation for the overall system.

[0010] Specifically, the collaborative design algorithm based on the Bayesian network is as follows: First, for each designer i, according to the different interests of different designers in the interested regions in the design space, a local Bayesian network model is constructed, and the joint kernel probability density function is used to represent the interested regions. The formula is expressed as:

[0011]

[0012] where P kernels (a, a i ) represents the joint kernel probability density function, representing the probability distribution of the interested region of designer i in the design space. a represents the vector of design variables, representing a design point in the design space. a i represents the design point of designer i in the local design space. I represents the total number of design points. p i (a, a i ) represents the probability density function of an individual design point. P kernels (a, a i ) is composed of the weighted combination of the joint probability density functions p i (a, a i ) of multiple individual design points. The calculation formula of the probability density function of an individual design point is expressed as:

[0013]

[0014] p i (a, a i ) represents the degree of interest of designer i in a specific design point. Among them, D represents the dimensionality of the design space, d j represents the width of the j-th dimension in the design space. j represents the dimension index of the design space. a j represents the j-th component of the design variable vector a that designer i is interested in, representing the value of the design point on the j-th dimension. represents the j-th component of the design variable vector a. H(·) represents the Hilbert step function, which is used to represent the probability density in the design space. Specifically, represents the value when the design point a j is greater than or equal to in the j-th dimension. represents the value when the design point a j is less than or equal to The value at a certain time is obtained by constructing a local Bayesian network to determine the conditional dependence relationship of the regions of interest of the designers, so as to improve the intelligence and efficiency in collaborative design. Secondly, through an adaptive selection mechanism, the algorithm automatically selects representative and information - gain - maximized design points for different designers according to the information in the design space and the goals of collaborative design, and incorporates them into the construction process of the Bayesian network model. Suppose the set of adaptively selected design points is represented as K adaptive The calculation formula for the probability distribution of the adaptively selected design points is as follows:

[0015]

[0016] Among them, p adaptive (a, a i ) represents the probability density function of the adaptively selected design points, a k represents the design point with the maximum information gain, δ(·) represents the Dirac δ function, representing the probability distribution of the selected design point, and the calculation formula of K adaptive is expressed as:

[0017]

[0018] Among them, InfoGain(x k ) represents the information gain of the design point x k , representing the contribution degree to the system information after adding it to the Bayesian network. By calculating the information gain of the design points, the system automatically selects the design points with the greatest contribution to collaborative design, making the Bayesian network of collaborative design better reflect different designers' key information in the design space. Then, the local Bayesian networks constructed by each designer are shared with other designers. Considering the situation of shared design variables, map the regions of interest of the collaborating designers to the local Bayesian networks of the designers, and express the joint kernel probability density function of the shared design variables as the joint probability distribution of the design variables jointly concerned by multiple designers. The calculation formula is as follows:

[0019]

[0020] Among them, P share (a, a i ) represents the joint kernel probability density function of the shared design variables, representing the joint probability distribution of the design variables jointly concerned by multiple designers, w i represents the weight of designer i for the shared design variables, used to adjust the influence degree of different designers on the shared design variables. Through the intersection operation, weight adjustment and cross - probability distribution are carried out to narrow the search area of the design space. The calculation formula is as follows:

[0021]

[0022] Among them, represents the probability density function of the intersection operation of the design variable a that all designers are jointly concerned about. This probability density function represents the common area that all designers are concerned about, p i (a) represents the probability density function of designer i on the design variable a. ∫(·)d represents the integration operation. Through the union operation, weight adjustment and combination of probability distributions are carried out to expand the design space search area. The calculation formula is:

[0023]

[0024] Among them, represents the probability density function of the union operation of the design variable a that all designers are jointly concerned about. This probability density function represents the overall area that all designers are concerned about. Through sharing the Bayesian network, more efficient local design space search among designers is promoted, ensuring the globality and integrity of collaborative design, mapping the area of interest of shared design variables, and ensuring that designers can jointly consider the key design variables in collaborative design; finally, based on the search results and design goals, iterative optimization is carried out, and real-time feedback is obtained through the Bayesian network. During the iterative process, the design strategy and weight are continuously adjusted to gradually optimize the overall design. The iterative calculation formula is:

[0025]

[0026] Among them, a new represents the design variable for the next iteration for a specific designer. f(a) represents the objective function. Through iterative optimization and real-time feedback, the design scheme is continuously improved, making the design variable gradually tend to be optimal. Through sharing and combining local Bayesian networks, deeper collaboration among designers is achieved, effectively solving the conflicts of shared and coupled parameters, promoting more targeted collaborative work among designers, which enables system users to more efficiently collaborate to handle complex multi-level design problems.

[0027] Preferably, the collaborative design module includes a design file management unit. The design file management unit provides functions such as file upload, download, sharing, and classification to store system files in an orderly manner and retrieve them efficiently, ensuring the integrity and traceability of system files.

[0028] Preferably, the data integration and sharing module realizes the close sharing and collaboration between the design data generated in the collaborative design module and the project management module through data integration technology, ensuring the synchronous update of internal design and management in the system and improving the integrity of the system.

[0029] Preferably, the project management module includes a resource allocation and optimization unit, which proposes a resource balance optimization algorithm based on evolutionary strategies. According to the resource usage, workload, and project requirement factors of the system, it dynamically adjusts the resource allocation to ensure the workload balance of each part and maximize the utilization efficiency of project resources, ensuring the accuracy and efficiency of the overall system in project management.

[0030] Specifically, the resource balance optimization algorithm based on evolutionary strategies is as follows: First, the resource balance optimization algorithm of evolutionary strategies represents different resource allocation schemes with a population F. Based on evolutionary strategies, each individual C represents a chromosome to be solved, and the chromosome represents a feasible resource solution. When the algorithm is initialized, an initial population F is formed by randomly generating chromosomes.

[0031] F = {C1, C2,..., C N}

[0032] where N represents the number of chromosomes. By randomly generating an initial feasible resource allocation, each chromosome C n represents the activity arrangement of a project, including the start times of critical activities and non-critical activities. n represents the index of the chromosome number. By creating a population, the starting point of evolution is formed. Secondly, based on the genetic algorithm, new individuals are introduced through crossover operations and mutation operations. The crossover operation is used to generate new individuals, recombining the information and characteristics of two parent chromosomes. Through two-point crossover, the two parent chromosomes are cut and exchanged at two crossover points. The calculation formula is:

[0033]

[0034]

[0035] where, and both represent the gene values of the newly generated offspring chromosomes at time point t. and both represent the gene values of the parent chromosomes at time point t. t represents the time point. CP1 and CP2 represent the two crossover points. By mixing the information of the two parent chromosomes, new individuals with better performance are generated. The mutation operation is used to introduce random changes in the chromosomes, increasing the diversity of the population. By randomly changing the genes in the chromosomes, the calculation formula is:

[0036]

[0037] where C mutant (t) represents the gene value of the mutated chromosome at time point t, C child(t) represents the gene value of the offspring chromosome generated by crossover at time point t, δ represents the random perturbation value, p mutant represents the probability of mutation. Randomness is introduced during the evolution process of the evolutionary strategy through the mutation operation to prevent the algorithm from falling into local optimal solutions. Through the crossover and mutation operations, new individuals are introduced into the population, providing diversity for the optimization of the resource allocation plan. Then, by selecting individuals with better fitness as parents for crossover and mutation operations, it is ensured that during the evolution process, chromosomes with better fitness are more likely to be selected, prompting the genetic algorithm to converge to excellent solutions faster. The calculation formula is:

[0038]

[0039] where P(C n ) represents the probability that chromosome C n is selected, and A(C n ) represents the fitness of chromosome C n . Through the selection operation, better chromosomes, that is, chromosomes with higher fitness, have a greater probability of being selected. By constructing the next-generation population operation, a new population is generated, including the offspring obtained from the crossover operation and the mutated individuals introduced through the mutation operation. The calculation formula is:

[0040] F next = F ∪ {C child , C mutant}

[0041] where F next represents the next-generation population. By constructing the next-generation population, new genetic information is introduced into each generation of the population to maintain the diversity of the population, thereby better exploring the solution space and finding a better resource allocation plan. Finally, in the resource balance optimization, the difference in the overall resource usage of the project is minimized through the fitness function. The calculation formula is:

[0042]

[0043] where f(C n ) represents the fitness function of chromosome C n , T represents the total duration of project management, r n(t) represents the amount of resources used by activity n at time t. The calculation of the fitness function is based on the accumulation of the differences between the resource usages of all project management resources and the overall average resource usage at each time t. The fitness function equalizes resource usage throughout the project, reducing the non-uniformity of resource usage. During the optimization process, through selection, crossover, and mutation operations, the algorithm finds a resource allocation plan that can minimize the fitness function to achieve the goal of resource balance. The resource balance optimization algorithm based on evolutionary strategies uses evolutionary strategies and genetic algorithms to construct populations that only generate feasible solutions, avoiding the generation of infeasible solutions and further improving the efficiency of the algorithm. The algorithm provides a more intelligent and flexible resource allocation plan for the system in project management, enabling the system to effectively address the challenges of resource allocation and collaborative design in complex project management and enabling the system to more effectively respond to changing design requirements and engineering tasks.

[0044] Preferably, the project management module includes a project tracking and feedback unit. The project tracking and feedback unit monitors the project progress and promptly alerts potential delays, helping the system users to comprehensively understand the project status. At the same time, through a feedback mechanism, it provides solutions to ensure that the system users can quickly adjust the plan and optimize resource allocation, thereby ensuring the stable and efficient progress of the project.

[0045] Preferably, the report and analysis module provides in-depth analysis of the design process and project management by generating detailed engineering management analysis reports, supports project evaluation and future decision-making, ensures that the system has comprehensive data support and provides decision-making references to users, and improves the overall system's ability to continuously optimize and innovate in projects.

[0046] Compared with the prior art, the beneficial effects of the present invention are:

[0047] 1. The real-time collaboration unit proposes a collaborative design algorithm based on Bayesian networks. This algorithm first uses Bayesian networks in probabilistic graphical models. By establishing local Bayesian networks, it represents the designers' interests in potential regions within their design spaces. Each designer's constructed local network reflects their unique design preferences and spatial relationships. These local networks can then be shared and combined to achieve information exchange among designers, promoting more efficient local design space search. The core principle of this algorithm is to capture the correlation relationships between design variables through joint probability distributions and to model the designers' preferences for different regions. Through Bayesian networks, the system can intelligently capture the designers' preferences for different design regions, thus more accurately inferring the designers' intentions and requirements, helping to shorten the time for resolving design changes and conflicts during the design process, and improving the iterative efficiency of the design process. Secondly, the dynamic learning feature of Bayesian networks enables the system to continuously evolve as more designs are evaluated, not only capturing the designers' initial interests but also adapting to new discoveries and changing preferences of designers in the design space. This dynamic learning helps to maintain the real-time and accuracy of the system, making the collaborative design process more flexible. Most importantly, through sharing and combining local Bayesian networks, deeper collaboration among designers is achieved, effectively resolving the conflicts of shared and coupled parameters, and promoting more targeted collaborative work among designers. This enables system users to more efficiently collaborate on complex multi-level design problems, thereby enhancing the overall comprehensive effectiveness of the collaborative design and engineering management system. The flexibility and scalability of this algorithm enable the system to effectively adapt to different projects and design strategies, providing strong support for collaborative design and project advancement;

[0048] 2. The resource allocation and optimization unit proposes a resource balance optimization algorithm based on evolutionary strategies. By optimally processing the available resources in candidate projects, this algorithm aims to solve the resource balance optimization problem in the integrated system of collaborative design and engineering management. By intelligently adjusting the start times of non-critical activities in the project, it achieves the balance and optimization of resources, uses genetic operators for iterative optimization to improve the quality of the solution, explores different feasible start time values of the project, and thus generates a high-quality resource management profile. Through a carefully designed hybridization method and mutation process, this algorithm can effectively avoid early convergence to suboptimal solutions, ensure a more comprehensive acquisition of high-quality solutions when exploring the search space. By fully considering project-specific parameters, this algorithm can generate a high-quality resource profile, thereby promoting the system to achieve the optimal solution. By using the hybridization method in the evolution process, this algorithm realizes an innovative modeling of the resource balance problem, making the solution more feasible and efficient in practice. In addition, the algorithm has strong applicability and can effectively cope with the management challenges of various projects without decomposing the problem into sub-problems, reducing the burden on user operations. At the same time, compared with traditional methods, this algorithm uses evolutionary strategies and genetic algorithm population construction to generate only feasible solutions, avoiding the generation of infeasible solutions and further improving the efficiency of the algorithm. This algorithm provides a more intelligent and flexible resource allocation scheme for the system in project management, enabling the system to effectively cope with the challenges of resource allocation and collaborative design in complex project management, and enabling the system to more effectively respond to changing design requirements and engineering tasks, thus providing users with a more intelligent, flexible and efficient resource management solution. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The invention will be further described with reference to the accompanying drawings. However, the embodiments in the drawings do not constitute any limitation to the invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained according to the following drawings.

[0050] Figure 1 It is a schematic structural diagram of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0051] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0052] Please refer to Figure 1, the present invention provides an integrated system for collaborative design and engineering management, including a user authentication and permission management module, a notification and communication module, a collaborative design module, a data integration and sharing module, an engineering management module, and a reporting and analysis module. The user authentication and permission management module is used to provide a user authentication mechanism and flexible permission allocation to ensure that only authorized users can access and operate the system. The notification and communication module is used to realize the functions of real-time system notifications and communication between users, ensuring efficient communication and collaboration between users through emails, short messages, and in-app notifications. The collaborative design module includes a real-time collaboration unit and a design file management unit. The real-time collaboration unit proposes a collaborative design algorithm based on Bayesian networks for multi-user real-time collaboration, effective identification of design files, and intelligent processing of the design process. The design file management unit is used to effectively manage and organize design files, providing functions such as file upload, download, sharing, and classification to ensure the safe and orderly storage of design files. The data integration and sharing module is used for the tight integration and information sharing between the collaborative design module and the engineering management module, and to achieve the coordination and consistency of each functional module within the system. The engineering management module includes a resource allocation and optimization unit and a project tracking and feedback unit. The resource allocation and optimization unit proposes a resource balance optimization algorithm based on evolutionary strategies to reasonably allocate and optimize resources within a project, ensuring workload balance and optimal utilization of project resources. The project tracking and feedback unit is used to monitor the progress of a project in real time and provide immediate feedback to enable users to quickly identify potential problems, adjust plans, and optimize work processes. The reporting and analysis module is used to generate comprehensive project reports and detailed analysis results to assist users in making and implementing project management decisions.

[0053] Refer to Figure 1 , further, the user authentication and permission management module ensures that only authorized users can access the system through a secure user authentication mechanism and a flexible permission management system, and assigns corresponding permissions according to user roles to ensure the security of system information and data privacy.

[0054] Refer to Figure 1 , further, the notification and communication module ensures that system users can obtain key information in real time, quickly respond to design changes and project progress through an instant notification and multi-dimensional communication mechanism, promoting efficient communication and collaborative work among system users.

[0055] Refer to Figure 1 , further, the collaborative design module includes a real-time collaboration unit, and the real-time collaboration unit proposes a collaborative design algorithm based on Bayesian networks. By effectively combining the design intentions and feedback of each user, it provides an efficient real-time collaboration environment, intelligently infers and processes project designs, realizes intelligent collaborative processing in the design phase of a project, and provides a reliable foundation for the overall system.

[0056] See Figure 1 , further, the collaborative design algorithm based on Bayesian network is specifically as follows: First, for each designer i, according to the different regions of interest in the design space of different designers, construct a local Bayesian network model, and use the joint kernel probability density function to represent the region of interest, which is expressed by the formula:

[0057]

[0058] Among them, P kernels (a, a i ) represents the joint kernel probability density function, representing the probability distribution of the region of interest of designer i in the design space, a represents the vector of design variables, representing a design point in the design space, a i represents the design point of designer i in the local design space, I represents the total number of design points, p i (a, a i ) represents the probability density function of an individual design point, P kernels (a, a i ) is composed of the weighted combination of the joint probability density functions p i (a, a i ) of multiple individual design points. The calculation formula of the probability density function of an individual design point is expressed as:

[0059]

[0060] p i (a, a i ) represents the degree of interest of designer i in a specific design point. Among them, D represents the dimensionality of the design space, d j represents the width of the j-th dimension in the design space, j represents the dimension index of the design space, a j represents the j-th component of the design variable vector a that designer i is interested in, representing the value of the design point on the j-th dimension, represents the j-th component of the design variable vector a, and H(·) represents the Hilbert step function, which is used to represent the probability density in the design space. Specifically, represents the value when the design point a j is greater than or equal to in the j-th dimension, represents the value when the design point a j is less than or equal to The value at this time is obtained by constructing a local Bayesian network to judge the conditional dependence relationship of the regions of interest of the designers, so as to improve the intelligence and efficiency in collaborative design. Secondly, through an adaptive selection mechanism, the algorithm automatically selects representative and information-gain-maximizing design points for different designers according to the information in the design space and the goals of collaborative design, and incorporates them into the construction process of the Bayesian network model. Suppose the set of adaptively selected design points is represented as K adaptive The calculation formula for the probability distribution of the adaptively selected design points is as follows:

[0061]

[0062] Among them, p adaptive (a, a i ) represents the probability density function of the adaptively selected design points, a k represents the design point with the maximum information gain, δ(·) represents the Dirac δ function, representing the probability distribution of the selected design points, and the calculation formula of K adaptive is expressed as:

[0063]

[0064] Among them, InfoGain(x k ) represents the information gain of the design point x k , representing the contribution degree to the system information after adding it to the Bayesian network. By calculating the information gain of the design points, the system automatically selects the design points with the greatest contribution to collaborative design, making the Bayesian network of collaborative design better reflect the different key information of different designers in the design space. Then, the local Bayesian networks constructed by each designer are shared with other designers. Considering the situation of shared design variables, the regions of interest of the collaborating designers are mapped to the local Bayesian networks of the designers, and the joint kernel probability density function of the shared design variables is expressed as the joint probability distribution of the design variables jointly concerned by multiple designers. The calculation formula is as follows:

[0065]

[0066] Among them, P share (a, a i ) represents the joint kernel probability density function of the shared design variables, representing the joint probability distribution of the design variables jointly concerned by multiple designers, and w i represents the weight of designer i for the shared design variables, used to adjust the influence degree of different designers on the shared design variables. Through the intersection operation, weight adjustment and cross probability distribution are carried out to narrow the search area of the design space. The calculation formula is as follows:

[0067]

[0068] Among them, represents the probability density function of the intersection operation of the design variable a that all designers are jointly concerned about. This probability density function represents the common area that all designers are concerned about, p i (a) represents the probability density function of designer i on the design variable a. ∫(·)d represents the integration operation. Through the union operation, weight adjustment and combination of probability distributions are carried out to expand the design space search area. The calculation formula is:

[0069]

[0070] Among them, represents the probability density function of the union operation of the design variable a that all designers are jointly concerned about. This probability density function represents the overall area that all designers are concerned about. Through sharing the Bayesian network, more efficient local design space search among designers is promoted, ensuring the globality and integrity of collaborative design, mapping the area of interest of shared design variables, and ensuring that designers can jointly consider the key design variables in collaborative design; finally, based on the search results and design goals, iterative optimization is carried out, and real-time feedback is obtained through the Bayesian network. During the iterative process, the design strategy and weight are continuously adjusted to gradually optimize the overall design. The iterative calculation formula is:

[0071]

[0072] Among them, a new represents the design variable for the next iteration for a specific designer. f(a) represents the objective function. Through iterative optimization and real-time feedback, the design scheme is continuously improved, making the design variable gradually tend to be optimal. Through sharing and combining local Bayesian networks, deeper collaboration among designers is achieved, effectively solving the conflicts of shared and coupled parameters, promoting more targeted collaborative work among designers, which enables system users to more efficiently collaborate to handle complex multi-level design problems.

[0073] Refer to Figure 1 , further, the collaborative design module includes a design file management unit. The design file management unit provides functions such as file upload, download, sharing, and classification to store system files in an orderly manner and retrieve them efficiently, ensuring the integrity and traceability of system files.

[0074] Refer to Figure 1 , further, the data integration and sharing module realizes the close sharing and collaboration between the design data generated in the collaborative design module and the project management module through data integration technology, ensuring the synchronous update of internal design and management in the system and improving the integrity of the system.

[0075] Refer to Figure 1, Further, the project management module includes a resource allocation and optimization unit, which proposes a resource balance optimization algorithm based on evolutionary strategies. According to the system's resource usage, workload, and project requirement factors, it dynamically adjusts resource allocation to ensure balanced workloads in all parts and maximize the utilization efficiency of project resources, ensuring the accuracy and efficiency of the overall system in project management.

[0076] See Figure 1 , Further, the resource balance optimization algorithm based on evolutionary strategies is as follows: First, the resource balance optimization algorithm of evolutionary strategies represents different resource allocation schemes with a population F. Based on evolutionary strategies, each individual C represents a chromosome to be solved, and the chromosome represents a feasible resource solution. When the algorithm is initialized, an initial population F is formed by randomly generating chromosomes.

[0077] F = {C1, C2,..., C N}

[0078] Among them, N represents the number of chromosomes. By randomly generating an initial feasible resource allocation, each chromosome C n represents the activity arrangement of a project, including the start times of critical activities and non-critical activities. n represents the chromosome number index. By creating a population, the starting point of evolution is formed. Second, based on the genetic algorithm, new individuals are introduced through crossover operations and mutation operations. The crossover operation is used to generate new individuals, recombining the information and characteristics of two parent chromosomes. Through two-point crossover, the two parent chromosomes are cut and exchanged at two crossover points. The calculation formula is:

[0079]

[0080]

[0081] Among them, and both represent the gene values of the newly generated offspring chromosome at time point t. and both represent the gene values of the parent chromosome at time point t. t represents the time point. CP1 and CP2 represent the two crossover points. By mixing the information of the two parent chromosomes, a new individual with better performance is generated. The mutation operation is used to introduce random changes in the chromosome, increasing the diversity of the population. By randomly changing the genes in the chromosome, the calculation formula is:

[0082]

[0083] Among them, C mutant (t) represents the gene value of the mutated chromosome at time point t, Cchild (t) represents the gene value of the offspring chromosome generated by crossover at time point t, δ represents the random perturbation value, and p mutant represents the probability of mutation. Randomness is introduced during the evolution process of the evolutionary strategy through the mutation operation to prevent the algorithm from falling into a local optimal solution. Through the crossover and mutation operations, new individuals are introduced into the population, providing diversity for the optimization of the resource allocation plan. Then, by selecting individuals with better fitness as parents for crossover and mutation operations, it is ensured that during the evolution process, chromosomes with better fitness are more likely to be selected, prompting the genetic algorithm to converge to an excellent solution more quickly. The calculation formula is:

[0084]

[0085] where P(C n ) represents the probability that chromosome C n is selected, and A(C n ) represents the fitness of chromosome C n . Through the selection operation, better chromosomes, that is, chromosomes with higher fitness, have a greater probability of being selected. By constructing the next-generation population operation, a new population is generated, including the offspring obtained from the crossover operation and the mutant individuals introduced through the mutation operation. The calculation formula is:

[0086] F next = F ∪ {C child , C mutant}

[0087] where F next represents the next-generation population. By constructing the next-generation population, new genetic information is introduced into each generation of the population to maintain the diversity of the population, thereby better exploring the solution space and finding a better resource allocation plan. Finally, in the resource balance optimization, the difference in the overall resource usage of the project is minimized through the fitness function. The calculation formula is:

[0088]

[0089] where f(C n ) represents the fitness function of chromosome C n , T represents the total duration of project management, and r n(t) represents the amount of resources used by activity n at time t. The calculation of the fitness function is based on the accumulation of the differences between the resource usage of all project management resources and the overall average resource usage at each time t. The fitness function equalizes resource usage throughout the project, reducing the non-uniformity of resource usage. During the optimization process, through selection, crossover, and mutation operations, the algorithm finds a resource allocation plan that can minimize the fitness function to achieve the goal of resource balance. The resource balance optimization algorithm based on evolutionary strategies uses evolutionary strategies and genetic algorithms to construct populations that only generate feasible solutions, avoiding the generation of infeasible solutions and further improving the efficiency of the algorithm. The algorithm provides a more intelligent and flexible resource allocation plan for the system in project management, enabling the system to effectively address the challenges of resource allocation and collaborative design in complex project management, and enabling the system to more effectively respond to changing design requirements and engineering tasks.

[0090] See Figure 1 Furthermore, the project management module includes a project tracking and feedback unit. The project tracking and feedback unit monitors the project progress, alerts potential delays in a timely manner, and helps system users comprehensively understand the project status. At the same time, through a feedback mechanism, it provides solutions to ensure that system users can quickly adjust the plan and optimize resource allocation, thus ensuring the stable and efficient progress of the project.

[0091] See Figure 1 Furthermore, the report and analysis module generates detailed engineering management analysis reports, provides in-depth analysis of the design process and project management, supports project evaluation and future decision-making, ensures that the system has comprehensive data support and provides decision-making references to users, and improves the overall system's ability to continuously optimize and innovate projects.

[0092] In specific use, first, the user authentication and permission management module provides a user authentication mechanism and flexible permission allocation to ensure that only authorized users can access and operate the system. Then, the notification and communication module conducts real-time system notifications and communication between users, through emails, text messages, and in-app notifications, to ensure efficient communication and collaboration among users. Secondly, the real-time collaboration unit in the collaborative design module proposes a collaborative design algorithm based on Bayesian networks for multi-user real-time collaboration, effective identification of design files, and intelligent processing of the design process. The design file management unit in the collaborative design module effectively manages and organizes design files, providing functions such as file upload, download, sharing, and classification to ensure the safe and orderly storage of design files. Further, the data integration and sharing module tightly integrates and shares information between the collaborative design module and the project management module, and achieves the coordination and consistency of each functional module within the system. Then, the resource allocation and optimization unit in the project management module proposes a resource balance optimization algorithm based on evolutionary strategies to reasonably allocate and optimize the resources within the project, ensuring workload balance and optimal utilization of project resources. The project tracking and feedback unit in the project management module monitors the progress of the project in real time and provides instant feedback, enabling users to quickly identify potential problems, adjust plans, and optimize work processes. Finally, the report and analysis module generates comprehensive project reports and detailed analysis results to assist users in making and implementing project management decisions.

[0093] Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. An integrated system for collaborative design and engineering management, comprising a user authentication and permission management module, a notification and communication module, a collaborative design module, a data integration and sharing module, an engineering management module, and a reporting and analysis module, characterized in that: The user authentication and permission management module is used to provide a user authentication mechanism and flexible permission allocation to ensure that only authorized users can access and operate the system. The notification and communication module is used to implement the functions of real-time system notifications and communication between users. Through methods such as emails, text messages, and in-app notifications, it ensures efficient communication and collaboration among users. The collaborative design module includes a real-time collaboration unit and a design file management unit. The real-time collaboration unit proposes a collaborative design algorithm based on Bayesian networks for multi-user real-time collaboration, effective identification of design files, and intelligent processing of the design process. The design file management unit is used to effectively manage and organize design files, providing functions such as file upload, download, sharing, and classification to ensure the safe and orderly storage of design files. The data integration and sharing module is used for the close integration and information sharing between the collaborative design module and the project management module, and to achieve the coordination and consistency of each functional module within the system. The project management module includes a resource allocation and optimization unit and a project tracking and feedback unit. The resource allocation and optimization unit proposes a resource balance optimization algorithm based on evolutionary strategies to reasonably allocate and optimize the resources within a project, ensuring workload balance and the optimal utilization of project resources. The project tracking and feedback unit is used to monitor the progress of a project in real time and provide instant feedback so that users can quickly identify potential problems, adjust plans, and optimize work processes. The report and analysis module is used to generate comprehensive project reports and detailed analysis results to help users make and implement project management decisions; The collaborative design algorithm based on Bayesian networks is as follows: First, for each designer i, according to the different regions of interest in the design space for different designers, a local Bayesian network model is constructed. Second, through an adaptive selection mechanism, the algorithm automatically selects representative and information-gain-maximal design points for different designers according to the information in the design space and the goals of collaborative design, and incorporates them into the construction process of the Bayesian network model. Then, the local Bayesian networks constructed by each designer are shared with other designers. Considering the situation of shared design variables, the regions of interest of collaborating designers are mapped to the local Bayesian networks of designers. Finally, based on the search results and design goals, iterative optimization is carried out, and real-time feedback is obtained through the Bayesian network.

2. The integrated system for collaborative design and engineering management according to claim 1, wherein: The user authentication and permission management module ensures that only authorized users can access the system through a secure user authentication mechanism and a flexible permission management system, and assigns corresponding permissions according to user roles to ensure system information security and data privacy.

3. An integrated system for collaborative design and engineering management according to claim 1, characterized in that: The notification and communication module ensures that system users can obtain key information in real time, quickly respond to design changes and project progress through instant notifications and multi-dimensional communication mechanisms, and promotes efficient communication and collaborative work among system users.

4. An integrated system for collaborative design and engineering management according to claim 1, characterized in that: The collaborative design module includes a real-time collaboration unit. The real-time collaboration unit proposes a collaborative design algorithm based on Bayesian networks. By effectively combining the design intentions and feedback of each user, it provides an efficient real-time collaboration environment, intelligently infers and processes project designs, realizes intelligent collaborative processing in the design phase of engineering projects, and provides a reliable basis for the overall system.

5. An integrated system for collaborative design and engineering management according to claim 4, characterized in that: The collaborative design algorithm based on Bayesian networks is as follows: First, for each designer i, according to the different regions of interest in the design space of different designers, a local Bayesian network model is constructed, and the joint kernel probability density function is used to represent the region of interest, which is expressed by the formula: where, P kernels (a,a i ) represents the joint kernel probability density function, which represents the probability distribution of the region of interest in the design space for designer i, a represents the vector of design variables, representing a design point in the design space, a i represents the design point of designer i in the local design space, I represents the total number of design points, p i (a,a i ) represents the probability density function of an individual design point, P kernels (a,a i ) is composed of the weighted combination of the joint probability density functions p i (a,a i ) of multiple individual design points. The calculation formula for the probability density function of an individual design point is expressed as: p i (a, a i ) represents the degree of interest of designer i in a specific design point. Among them, D represents the number of dimensions of the design space, d j represents the width of the j-th dimension in the design space, j represents the dimension index of the design space, a j represents the j-th component of the design variable vector a that designer i is interested in, representing the value of the design point on the j-th dimension. represents the j-th component of the design variable vector a, and H(·) represents the Hilbert step function, which is used to represent the probability density in the design space. Specifically, represents the design point a on the j-th dimension j greater than or equal to when the value is represents the design point a on the j-th dimension j less than or equal to when the value is. By constructing a local Bayesian network, the conditional dependence relationship of the region of interest of the designer is judged to improve the intelligence and efficiency in collaborative design; secondly, through an adaptive selection mechanism, the algorithm automatically selects representative and information-gain-maximal design points for different designers according to the information in the design space and the goals of collaborative design, and incorporates them into the construction process of the Bayesian network model. Suppose the set of adaptively selected design points is represented as K adaptie , and the calculation formula for the probability distribution of the adaptively selected design points is: where p adaptive (a, a i ) represents the probability density function of the adaptively selected design point, a k represents the design point with the maximum information gain, δ(·) represents the Dirac δ function, representing the probability distribution of the selected design point, K adaptive The calculation formula of is expressed as: Among them, InfoGain(x k ) represents the information gain of the design point x k , which represents the contribution degree to the system information after adding the Bayesian network. By calculating the information gain of the design point, the system automatically selects the design point with the greatest contribution to the collaborative design, making the Bayesian network of the collaborative design better reflect the different key information of different designers in the design space; then, share the local Bayesian network constructed by each designer with other designers. Considering the situation of shared design variables, map the region of interest of the collaborative designer to the local Bayesian network of the designer, and represent the joint kernel probability density function of the shared design variables as the joint probability distribution of the design variables jointly concerned by multiple designers. The calculation formula is: Among them, P share (a,a i ) represents the joint kernel probability density function of the shared design variables, which represents the joint probability distribution of the design variables jointly concerned by multiple designers. w i represents the weight of designer i for the shared design variables, which is used to adjust the influence degree of different designers on the shared design variables. Through the intersection operation, weight adjustment and cross probability distribution are carried out to narrow the design space search area. The calculation formula is as follows: Among them, represents the probability density function of the intersection operation of the design variable a that all designers are jointly concerned about. This probability density function represents the common area that all designers are concerned about, p i (a) represents the probability density function of designer i on the design variable a. ∫(·)d represents the integration operation. Through the union operation, weight adjustment and combination of probability distributions are carried out to expand the design space search area. The calculation formula is: Among them, represents the probability density function of the union operation of the design variable a that all designers are jointly concerned about. This probability density function represents the overall area concerned by all designers. By sharing the Bayesian network, it promotes a more efficient local design space search among designers, ensures the globality and integrity of collaborative design, maps the area of interest of shared design variables, and guarantees that designers can jointly consider the key design variables in collaborative design; finally, based on the search results and design goals, iterative optimization is carried out, and real-time feedback is obtained through the Bayesian network. During the iterative process, the design strategy and weight are continuously adjusted to gradually optimize the overall design. The iterative calculation formula is: Among them, a new represents the design variables for a specific designer in the next iteration, f(a) represents the objective function. Through iterative optimization and real-time feedback, the design scheme is continuously improved, making the design variables gradually tend to be optimal. By sharing and integrating local Bayesian networks, deeper collaboration is achieved among designers, effectively solving the conflicts of shared and coupled parameters, promoting more targeted collaborative work among designers, which enables system users to more efficiently collaborate in dealing with complex multi-level design problems.

6. An integrated system for collaborative design and engineering management according to claim 1, characterized in that: The collaborative design module includes a design file management unit. The design file management unit provides functions such as file upload, download, sharing, and classification, stores system files in an orderly manner, and retrieves them efficiently, ensuring the integrity and traceability of system files.

7. An integrated system for collaborative design and engineering management according to claim 1, characterized in that: The data integration and sharing module realizes the close sharing and collaboration between the design data generated in the collaborative design module and the project management module through data integration technology, ensures the synchronous update of design and management within the system, and improves the integrity of the system.

8. An integrated system for collaborative design and engineering management according to claim 1, characterized in that: The project management module includes a resource allocation and optimization unit. The resource allocation and optimization unit proposes a resource balance optimization algorithm based on evolutionary strategies. According to the system's resource usage, workload, and project requirement factors, it dynamically adjusts resource allocation to ensure the workload balance of each part and maximize the utilization efficiency of project resources, ensuring the accuracy and efficiency of the overall system in project management.

9. An integrated system for collaborative design and engineering management according to claim 8, characterized in that: The resource balance optimization algorithm based on evolutionary strategies is as follows: First, the resource balance optimization algorithm of evolutionary strategies represents different resource allocation schemes with a population F. Based on evolutionary strategies, each individual C represents a chromosome to be solved, and the chromosome represents a feasible resource solution. When the algorithm is initialized, an initial population F is formed by randomly generating chromosomes. F = {C1, C2,..., C N} Where N represents the number of chromosome complexes. By randomly generating an initial feasible resource allocation, each chromosome C n represents the activity arrangement of a project, including the start times of critical activities and non-critical activities. n represents the chromosome number index. By creating a population, the starting point of evolution is formed. Secondly, based on the genetic algorithm, new individuals are introduced through crossover operations and mutation operations. The crossover operation is used to generate new individuals, recombining the information and characteristics of two parent chromosomes. Through two-point crossover, the two parent chromosomes are cut and exchanged at two crossover points. The calculation formula is as follows: Among them, and both represent the gene values of the newly generated offspring chromosomes at time point t. and both represent the gene values of the parental chromosomes at time point t, where t represents the time point, CP1 and CP2 represent two crossover points. By mixing the information of the two parental chromosomes, a new individual with better performance is generated. The mutation operation is used to introduce random changes in the chromosomes to increase the diversity of the population. By randomly changing the genes in the chromosomes, the calculation formula is: Among them, C mutant (t) represents the gene value of the mutated chromosome at time point t, and C child (t) represents the gene value of the offspring chromosome generated by crossover at time point t. δ represents the random perturbation value, and p mutant represents the mutation probability. By introducing randomness through the mutation operation in the evolutionary process of the evolutionary strategy, it prevents the algorithm from falling into a local optimal solution. Through the crossover and mutation operations, new individuals are introduced into the population, providing diversity for the optimization of the resource allocation scheme. Then, by selecting individuals with better fitness as parents for crossover and mutation operations, it ensures that during the evolution process, chromosomes with better fitness are more likely to be selected, promoting the genetic algorithm to converge to excellent solutions faster. The calculation formula is as follows: Among them, P(C n ) represents the probability that chromosome C n is selected. A(C n ) represents the fitness of chromosome C n . Through the selection operation, better chromosomes, that is, chromosomes with higher fitness, have a greater probability of being selected. Through the operation of constructing the next-generation population, a new population is generated, including the offspring obtained from the crossover operation and the mutant individuals introduced through the mutation operation. The calculation formula is as follows: F next = F ∪ {C child , C mutant} Among them, F next represents the population of the next generation. By constructing the population of the next generation, new genetic information is introduced into each generation of the population to maintain the diversity of the population, so as to better explore the solution space and find a better resource allocation scheme. Finally, in the resource balance optimization, the difference in the overall resource usage of the project is minimized through the fitness function, and the calculation formula is: Among them, f(C n ) represents the fitness function of chromosome C n , T represents the total duration of project management, r n (t) represents the amount of resources used by activity n at time t. The calculation of the fitness function is based on the accumulation of the differences between the resource usage amounts of all project management resources and the overall average resource usage amount at each time t. The fitness function equalizes resource usage throughout the project period and reduces the non-uniformity of resource usage. During the optimization process, through selection, crossover, and mutation operations, the algorithm finds a resource allocation plan that can minimize the fitness function to achieve the goal of resource balance. The resource balance optimization algorithm based on evolutionary strategy uses evolutionary strategy and genetic algorithm to construct a population that only generates feasible solutions, avoiding the generation of infeasible solutions and further improving the efficiency of the algorithm. The algorithm provides a more intelligent and flexible resource allocation plan for the system in project management, enabling the system to effectively cope with the challenges of resource allocation and collaborative design in complex project management, and enabling the system to more effectively respond to changing design requirements and engineering tasks.

10. An integrated system for collaborative design and engineering management according to claim 1, characterized in that: The project management module includes a project tracking and feedback unit. The project tracking and feedback unit monitors the project progress, alerts potential delays in a timely manner, helps system users comprehensively understand the project status. At the same time, it provides solutions through a feedback mechanism to ensure that system users can quickly adjust plans and optimize resource allocation, thus ensuring the stable and efficient progress of the project.

Images