Project benefit deviation early warning method and device
By constructing a benefit deviation calculation model and using a rough clustering algorithm and a mixed particle swarm algorithm, the problem of benefit deviation in engineering project management in waterway rectification projects is solved, and real-time early warning and accurate management of project benefits are achieved.
Patent Information
- Application Number
- CN202410991345.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-23
- Publication Date
- 2024-11-22
AI Technical Summary
Traditional engineering project management methods cannot meet the real-time and accuracy of waterway rectification projects, resulting in deviations from the target benefits of engineering projects, and the need for construction complexity cannot be effectively managed.
A benefit deviation calculation model is constructed, and the factors influencing the entire project process are processed through the rough clustering algorithm and the mixed particle swarm algorithm, the deviation warning range is determined, and the deviation value of the predicted benefit result is matched with these intervals to achieve project benefit deviation warning.
It improves the accuracy of the efficiency of the project, realizes real-time efficiency result deviation prediction during the construction process, and meets the complexity and real-time requirements of waterway rectification projects.
Smart Images

Figure CN119005680A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of project management, and in particular to a project benefit deviation early warning method and device. Background Art
[0002] Channel regulation construction projects are usually funded by the government and are very expensive. They play a vital role in the performance of the transportation system and the national economy. They are also an important way to promote economic transformation, adjust the industrial structure, and optimize the regional layout. However, under the background of dual circulation, the world trade pattern is quietly changing. Many uncertainties have put forward new requirements for the construction goals, construction process and construction quality of channel regulation projects. Emerging technologies and new generation information technology have increased the complexity of the construction of channel regulation projects while putting forward higher requirements for project quality management. Due to the long construction period and many links of such projects, the benefits of the project deviate from the target benefits. Internal and external environmental factors jointly determine the urgency and necessity of benefit management and control of construction companies of channel construction projects. However, traditional project management methods can no longer meet the requirements of real-time, accuracy and complexity of channel regulation projects.
[0003] Therefore, it is urgent to propose a project benefit deviation early warning method and device to solve the technical problem that there is a deviation between the project benefit and the target benefit in the engineering project management method in the existing technology, resulting in the inability to meet the real-time and accuracy requirements of waterway regulation projects. Summary of the invention
[0004] In view of this, it is necessary to provide a project benefit deviation early warning method and device to solve the technical problem that there is a deviation between the project benefit and the target benefit in the engineering project management method in the prior art, resulting in the inability to meet the real-time and accuracy requirements of waterway regulation projects.
[0005] In order to solve the above problems, the present invention provides a project benefit deviation early warning method, comprising: Construct a benefit deviation calculation model and determine the factors affecting the entire project process based on the project construction process; According to the influencing factors of the whole process of the project, multiple deviation warning intervals are obtained; Predicting the influencing factors of the entire process of the project according to the benefit deviation calculation model to obtain a predicted benefit result deviation value; The predicted benefit result deviation value is matched with each deviation warning interval to obtain the project benefit deviation warning result.
[0006] In a possible implementation, multiple deviation warning intervals are obtained based on the influencing factors of the entire process of the project, including: The influencing factors of the whole process of the project are processed based on the rough clustering set algorithm to obtain multiple initial threshold intervals; The multiple threshold intervals are optimized based on a hybrid particle swarm algorithm to obtain multiple deviation warning intervals.
[0007] In a possible implementation, the rough clustering algorithm is used to process the influencing factors of the entire project process to obtain multiple initial threshold intervals, including: Based on the rough clustering set algorithm, each influencing factor in the project full process is processed respectively to obtain a clustering distance difference; Determine multiple lower approximations and multiple upper approximations according to the cluster distance difference and all influencing factors; A plurality of initial threshold intervals are obtained according to the plurality of lower approximations and the plurality of upper approximations.
[0008] In a possible implementation, the multiple threshold intervals are optimized based on the hybrid particle swarm algorithm to obtain multiple deviation warning intervals, including: According to the factors affecting the whole process of the project, the crossover rate is obtained; Optimizing the multiple threshold intervals based on a hybrid particle swarm algorithm and the crossover rate to obtain an optimal solution fitness value; According to the fitness value of the optimal solution, a plurality of deviation warning intervals are obtained.
[0009] In a possible implementation, obtaining the crossover rate according to the factors affecting the entire process of the project includes: Determine the weight of each influencing factor based on the influencing factors of the entire project process; Processing the weight ratio of each influencing factor to obtain an amplified target weight ratio; The crossover rate is obtained by comparing the weight proportions of all targets with the preset random number.
[0010] In a possible implementation, the optimizing the multiple threshold intervals based on the hybrid particle swarm algorithm and the crossover rate to obtain the optimal solution fitness value includes: Processing the influencing factors in the multiple threshold intervals based on a hybrid particle swarm algorithm and the crossover rate to obtain offspring particles; The offspring particles are mapped into the feasible domain of the chaos equation and then mapped back to the original solution space, and the fitness value of the optimal solution is calculated.
[0011] In a possible implementation, the multiple deviation warning intervals are obtained according to the optimal solution fitness value, including: Determine whether the current number of iterations has reached the maximum number of iterations; If yes, then the optimal solution fitness value is selected for effectiveness to obtain the alarm situation classification clustering center; The region is segmented according to the alarm classification cluster center to obtain a plurality of deviation alarm intervals.
[0012] In a possible implementation, the multiple deviation warning intervals include a construction-continued area, a first-level warning area, a second-level warning area, and a source-tracing rectification area; the predicted benefit result deviation value is matched with each deviation warning interval to obtain a project benefit deviation warning result, including: Matching the predicted benefit result deviation value with the continued construction area, the first-level warning area, the second-level warning area, and the traceability rectification area respectively, to determine the target area where the predicted benefit result deviation value is located; According to the target area, a project benefit deviation warning result of the project construction process is determined.
[0013] In a possible implementation, the fitness function in the hybrid particle swarm algorithm is:
[0014] in,
[0015]
[0016] In the formula, Expressed as a density function between 0 and 1; Indicates i Correction coefficients of classes based on historical data sets; and Respectively represent i The number of data in the lower approximate set and the boundary set of the class; Representation data x With i Cluster Centers The Euclidean distance between Representation data x With k Cluster Centers The Euclidean distance between Represents the critical region i Class by Boundary Collection The proportion of the total number of critical area data; Represents the critical region i Class close to the lower approximate set The percentage of the total number of critical area data; m represents the number of deviation warning intervals.
[0017] On the other hand, the present invention also provides a project benefit deviation early warning device, comprising: The factor determination module is used to build a benefit deviation calculation model and determine the factors affecting the entire project process based on the project construction process; The interval determination module obtains multiple deviation warning intervals according to the influencing factors of the entire process of the project; A deviation prediction module is used to predict the influencing factors of the entire process of the project according to the benefit deviation calculation model to obtain a deviation value of the predicted benefit result; The result determination module is used to match the predicted benefit result deviation value with each deviation warning interval to obtain the project benefit deviation warning result.
[0018] The beneficial effect of the present invention is that a benefit deviation calculation model is constructed, and the influencing factors of the entire project process can be determined according to the project construction process; and then a plurality of deviation warning intervals can be obtained according to the influencing factors of the entire project process; therefore, when the project construction period is long and there are many links, the influencing factors of the entire project process in the entire project construction process are analyzed to determine a plurality of deviation warning intervals, thereby improving the accuracy of the project benefit; further, during the course of the project, the influencing factors of the entire project process can be predicted by the benefit deviation calculation model to obtain the predicted benefit result deviation value; and the predicted benefit result deviation value is matched with each deviation warning interval to obtain the project benefit deviation early warning result, so that the benefit result deviation of the project can be predicted during the project construction process, without having to wait until the project is completed to detect the deviation during the project construction process, thereby meeting the real-time requirements of waterway regulation projects. BRIEF DESCRIPTION OF THE DRAWINGS
[0019] Figure 1 A schematic diagram of a process flow of an embodiment of a project benefit deviation early warning method provided by the present invention; Figure 2 A schematic diagram of a flow chart of an embodiment of determining a threshold interval provided by the present invention; Figure 3 A schematic diagram of a flow chart of an embodiment of determining a deviation warning interval provided by the present invention; Figure 4 For the present invention Figure 3 A schematic flow chart of an embodiment of step S301; Figure 5 A schematic diagram of the structure of an embodiment of the project benefit deviation early warning device provided by the present invention; Figure 6 A schematic structural diagram of an embodiment of an electronic device provided by the present invention. DETAILED DESCRIPTION
[0020] The preferred embodiments of the present invention are described in detail below in conjunction with the accompanying drawings, wherein the accompanying drawings constitute a part of this application and are used together with the embodiments of the present invention to illustrate the principles of the present invention, but are not used to limit the scope of the present invention.
[0021] like Figure 1 As shown, a specific embodiment of the present invention discloses a project benefit deviation early warning method, comprising: S101. Construct a benefit deviation calculation model and determine the factors affecting the entire project process based on the project construction process; S102. Obtain multiple deviation warning intervals based on the influencing factors of the entire project process; S103. Predict the factors affecting the entire process of the project according to the benefit deviation calculation model to obtain the deviation value of the predicted benefit result; S104. Match the predicted benefit result deviation value with each deviation warning interval to obtain the project benefit deviation warning result.
[0022] In a specific embodiment of the present scheme, the project construction process can be divided into the early stage, mid-stage and late stage of the project. Each stage has corresponding influencing factors. When predicting the benefit deviation of the project construction, a prediction can be made based on the influencing factors of the current stage to obtain multiple deviation warning intervals of the current stage. The influencing factors of the current stage can also be predicted through a benefit deviation calculation model to obtain a predicted benefit result deviation value. Then, the multiple deviation warning intervals of the current stage can be matched with the predicted benefit result deviation value to obtain the project benefit deviation warning result of the current stage.
[0023] Based on the principle of system dynamics, the control of target deviation of waterway regulation project is studied, the transmission relationship between the deviation influencing factors in the early stage, mid-term stage and late stage of waterway regulation project is identified, endogenous variables and exogenous variables are analyzed, and the influencing factors are determined. Among them, the early decision-making stage is the proposal of the benefit control target of the entire project, that is, the foundation construction stage. The main work is to conduct feasibility demonstration for different construction plans and optimize the construction plan. The influencing factors are shown in Table 1: Table 1. Influencing factors in the early stage
[0024] The mid-term implementation stage of a construction project is the stage where the early project design, construction materials and construction equipment are put into construction. It is the longest, most influential and most involved stage in the project internal control process, and is also the decisive stage for benefit deviation control. Its influencing factors are shown in Table 2: Table 2. Influencing factors in the mid-term stage
[0025] During the completion review and settlement process, due to calculation errors, changes in material unit prices, changes in acceptance procedures and other factors, the benefits and goals of construction acceptance deviate from each other. This mainly includes three factors: project acceptance, settlement management and team management. The influencing factors are shown in Table 3: Table 3. Influencing factors in the later stage
[0026] Taking into account the one-time and procedural characteristics of engineering projects, there is a phenomenon that the cost of construction projects is transmitted from the early stage to the later stage. The deviation of costs in the transmission process may lead to a "butterfly effect" in engineering costs. Therefore, building a benefit deviation early warning model is of great significance for the cost management of construction projects.
[0027] BP neural network is used for benefit prediction. The input layer, hidden layer and output layer parameters are designed according to the pre-construction, mid-construction and post-construction stages. The input layer is the influencing factors of each stage. In order to reduce the prediction error, two hidden layers are designed. The first layer is the structural equation of the influencing factors of each stage, and the second layer is the BP reverse correction parameter. The correction parameter is the result of empirical regression of the deviation value in the historical rough set. It is designed according to the specific work content of each stage, such as feasibility study, survey and design, bidding, construction, acceptance and settlement, etc. The output layer is the prediction result. Finally, the actual total deviation is used as the output value to train the neural network model in a loop, thereby forming a set of adaptive and self-correcting benefit deviation prediction system. Finally, the deviation of multiple benefit activity points in three stages of waterway regulation construction projects is calculated as shown in Table 4: Table 4. Deviation of benefit monitoring points
[0028] Compared with the prior art, the present embodiment provides a benefit deviation calculation model, and can also determine the influencing factors of the entire project process according to the project construction process; and then, multiple deviation warning intervals can be obtained according to the influencing factors of the entire project process; therefore, when the project construction period is long and there are many links, by analyzing the influencing factors of the entire project process in the entire project construction process, multiple deviation warning intervals can be determined, thereby improving the accuracy of the project benefits; further, during the project, the influencing factors of the entire project process can be predicted by the benefit deviation calculation model to obtain the predicted benefit result deviation value; and the predicted benefit result deviation value can be matched with each deviation warning interval to obtain the project benefit deviation warning result, so that the benefit result deviation of the project can be predicted during the project construction process, without having to wait until the project is completed to detect the deviation during the project construction process, thereby meeting the real-time requirements of waterway regulation projects.
[0029] In some embodiments of the present invention, step S102 includes: Based on the rough clustering algorithm, the factors affecting the entire project process are processed to obtain multiple initial threshold intervals; Based on the hybrid particle swarm algorithm, multiple threshold intervals are optimized to obtain multiple deviation warning intervals.
[0030] In a specific embodiment of the present invention, according to the types and characteristics of the factors affecting the benefit deviation in the early, mid and late stages of construction, the thresholds of the upper and lower approximations of the rough clustering of the benefit deviation are determined according to the four-level warning, so as to reduce the impact of improper threshold setting on the rough clustering performance, thereby obtaining an initial threshold interval composed of upper and lower approximations, and then obtaining multiple initial threshold intervals through multiple upper and lower approximations; in order to improve the accuracy of the intervals, multiple threshold intervals can also be optimized through a hybrid particle swarm algorithm, so as to obtain multiple optimized deviation warning intervals.
[0031] In some embodiments of the present invention, Figure 2 As shown in the figure, the factors affecting the whole process of the project are processed based on the rough clustering set algorithm to obtain multiple initial threshold intervals, including: S201, processing each influencing factor in the whole process of the project based on a rough clustering algorithm to obtain a clustering distance difference; S202, determining multiple lower approximations and multiple upper approximations according to the cluster distance difference and all influencing factors; S203 . Obtain multiple initial threshold intervals according to multiple lower approximations and multiple upper approximations.
[0032] In a specific embodiment of the present invention, the encoding method of the rough clustering set algorithm is that the particle encoding position represents different cluster centers. Since the current project is divided into three construction stages and is classified according to four levels of warning, according to the particle length design method, the length of the particle is 12. The Latin hypercube sampling strategy is adopted to randomly generate the position of each particle in the initialization population within the range of [L, U], where L is the lower bound of the decision space and U is the upper bound of the decision space. In the process of deviation alarm, there is a situation where the alarm interval is difficult to divide. In order to determine the composition of the deviation alarm rough set and further determine the threshold for reducing the upper approximate set and the lower approximate set division, the cluster distance difference is calculated and set as the threshold. The calculation is shown in formula (1): (1) Where: , Respectively represent data i Closest to the cluster center o Class and next closest d Minimum and second-minimum distances between classes; Representation data iThe distance difference between the two cluster centers is < , then the data i belong o The lower approximation of the class, otherwise the data i belong d Class and o Upper approximation of class; n is the total number of data. For example, The deviation values are 1%, 2.3%, 5%, 7%, 1.2%, 4.6%, 7.3%, 6.9%, 9%, and 2% respectively. After a column of data is re-sorted, the clustering algorithm is used. The calculation results are four types of deviation warning intervals, namely {1%, 1.2%, 2%, 2.3%}, {4.6%, 5%}, {6.9%, 7%, 7.3%}, and {9%}.
[0033] Since the traditional clustering method cannot achieve the continuity of the final segmentation interval, there will be {1%, 1.2%, 2%, 2.3%}, {4.6%, 5%}, {6.9%, 7%, 7.3%}, {9%}. When the actual data is 5.5%, it cannot be classified according to the existing four categories. Therefore, the hybrid particle swarm algorithm is further used on the basis of clustering to optimize the interval to make it continuous.
[0034] In some embodiments of the present invention, Figure 3 As shown in the figure, multiple threshold intervals are optimized based on the hybrid particle swarm algorithm to obtain multiple deviation warning intervals, including: S301. Obtain the crossover rate based on the factors affecting the entire process of the project; S302, optimizing multiple threshold intervals based on a hybrid particle swarm algorithm and a crossover rate to obtain an optimal solution fitness value; S303. Obtain multiple deviation warning intervals according to the fitness value of the optimal solution.
[0035] In a specific embodiment of the present invention, the iteration of the genetic algorithm is carried out through a natural selection mechanism, and the particles are sorted by comparing the fitness values of the chromosomes. A 50% chromosome elimination mechanism is adopted and the historical optimal value of each individual is retained after the comparison is completed. This is the key to the rapid convergence of the particle swarm algorithm and avoids falling into a local optimal solution. In the hybrid particle swarm algorithm, by drawing on the crossover mechanism in the genetic algorithm, in each iteration, according to the set crossover rate, the same proportion of particles are taken and put into the hybridization pool. These particles are randomly cross-operated in pairs to produce the same number of offspring particles n as the parent generation m. The position of the offspring particles is obtained by the crossover operation of the parent particles, that is, through the crossover operation, compared with the genetic mechanism, the offspring particles can combine the advantages of the parent particles and increase the chance of searching the space, and obtain different types of solutions faster.
[0036] A fitness function can be provided to replace the objective function in the hybrid particle swarm algorithm. The fitness function is shown in formula (2): (2) in,
[0037]
[0038] In the formula, Expressed as a density function between 0 and 1; Indicates i Correction coefficients of classes based on historical data sets; and Respectively represent i The number of data in the lower approximate set and the boundary set of the class; Representation data x With i Cluster Centers The Euclidean distance between Representation data x With k Cluster Centers The Euclidean distance between Represents the critical region i Class by Boundary Collection The proportion of the total number of critical area data; Represents the critical region i Class close to the lower approximate set The proportion of the total number of critical area data; m Indicates the number of deviation warning intervals.
[0039] In some embodiments of the present invention, Figure 4 As shown, step S301 includes: S401. Determine the weight of each influencing factor based on the factors affecting the entire project process; S402, processing the weight proportion of each influencing factor to obtain an amplified target weight proportion; S403: Compare the proportions of all target weights with a preset random number to obtain a crossover rate.
[0040] In a specific embodiment of the present invention, it is also necessary to set the crossover rate in the hybrid particle swarm algorithm. In the process of setting the crossover rate, it is divided into two steps: first, design an expert consultation questionnaire. The expert consultation questionnaire includes five parts: consultation instructions, expert general situation questionnaire, boundary point valuation questionnaire, three-stage construction influencing factor weight table, and expert familiarity with the consultation content and judgment basis self-assessment table: then calculate the weight ratio of each influencing factor, magnify the weight ratio by 10 times and compare it with the generated preset random number, and take the larger one as the crossover rate to realize the generation of offspring particles. The specific magnification can be set according to the actual situation. As shown in formula (3): (3) In the formula, is a random number between [0,1]; is the weight ratio of the influencing factors; m is the number of influencing factors.
[0041] In order to improve the consistency and computational efficiency of the hybrid particle swarm algorithm in the segmented area, chaos theory is introduced to optimize the particle velocity. The mapping formula is shown in formula (4): 0 (0, 12) (4) In the formula, express k particle.
[0042] The value calculated by the chaotic map is used as the optimization value of the fitness function, and then the final fitness value is sorted and selected and stored. At the same time, the control coefficient can be adjusted k Accelerate the convergence process of particle swarm optimization.
[0043] is the control variable in the logistic mapping process, and is used by the above formula Generate a new solution sequence, { }, and The values are different, and the generated sequences are quite different. If the new chaotic sequence is used as a map to the original solution space, then the range of the solution is represented by the newly generated chaotic sequence. The fitness function is calculated in the new feasible domain interval, and the final fitness value is sorted, selected and stored. At the same time, the control coefficient can be adjusted k Accelerate the convergence process of the particle swarm algorithm. At this time, the characteristics of the chaotic sequence can be expressed by a probability density function (not used in the model): (5) In some embodiments of the present invention, step S302 includes: Based on the hybrid particle swarm algorithm and crossover rate, the influencing factors in multiple threshold intervals are processed to obtain the offspring particles; The descendant particles are mapped to the feasible domain of the chaotic equation and then mapped back to the original solution space, and the fitness value of the optimal solution is calculated.
[0044] In some embodiments of the present invention, step S303 includes: Determine whether the current number of iterations has reached the maximum number of iterations; If so, the optimal solution fitness value is selected for effectiveness, and the alarm situation classification clustering center is obtained; The region is segmented according to the alarm classification cluster center to obtain multiple deviation alarm intervals.
[0045] In a specific embodiment of the present invention, after replacing the formulas and contents in the hybrid particle swarm algorithm with the above contents, the updated hybrid particle swarm algorithm process is as follows: 1) Randomly initialize particle speed and position.
[0046] 2) Calculate the fitness value of each particle, store the particle position and fitness value in the individual extreme value pbest, and keep the individual position and fitness value of the best fitness value in pbest in the global extreme value gbest.
[0047] 3) Update the particle displacement and velocity, compare the fitness value of each particle with the optimal position, take the optimal position value, and update the optimal value variable.
[0048] 4) Sort the population according to the fitness value, and the particles with poor fitness are replaced by particles with good fitness in proportion, retaining the historical optimal value of the original particle.
[0049] 5) According to the importance coefficients obtained from questionnaires distributed in the early, mid- and late stages of the project, the crossover rate is obtained by combining the proportion of the factors in this stage in the total influencing factors. A proportional number of particles are randomly selected according to the crossover rate and put into the hybridization pool to generate offspring particles.
[0050] 6) p and g The set is mapped into the feasible domain of the chaotic equation and then mapped back to the original solution space, and the fitness value of the optimal solution is calculated.
[0051] 7) Carry out the t +1 round of iteration, determine whether the maximum number of iterations has been reached, if the condition is met, execute step 8; otherwise, return to step 4.
[0052] 8) Select the optimal solution for effectiveness, obtain the alarm classification clustering center, and determine the alarm monitoring point.
[0053] 9) The domain is segmented according to the cluster center, and the final thresholds of the four-level warning areas (continue construction, level 1 warning, level 2 warning, and source tracing and rectification) are returned.
[0054] In some embodiments of the present invention, the plurality of deviation warning intervals include a continuing construction area, a first-level warning area, a second-level warning area, and a source tracing and rectification area; step S104 includes: Match the predicted benefit result deviation value with the continued construction area, the first-level warning area, the second-level warning area, and the traceability rectification area respectively to determine the target area where the predicted benefit result deviation value is located; According to the target area, determine the project benefit deviation warning results of the project construction process.
[0055] In a specific embodiment of the present invention, multiple deviation warning intervals may include a continued construction area, a first-level warning area, a second-level warning area, and a traceability rectification area. After obtaining multiple deviation warning intervals and predicted benefit result deviation values, the predicted benefit result deviation value can be matched with the multiple deviation warning intervals to determine in which deviation warning interval the predicted benefit result deviation value is located, so that the matched interval can be determined as the target area, and then the prediction result of the target area can be determined as the project benefit deviation warning result of the project construction process. For example, when the target area is the traceability rectification area, the project benefit deviation warning result of the project construction process can be obtained as the need to rectify the project construction.
[0056] Taking the second phase of the Jiangxinzhou-Wujiang River section waterway regulation project as an example, it mainly includes the regulation of building projects and habitat improvement.
[0057] For the six projects of dredging, navigation projects, temporary projects, and maintenance projects during the construction period, the warning thresholds are shown in Table 5 and the warning results are shown in Table 6 based on the rough clustering of the hybrid particle swarm. The prediction results are consistent with the actual situation during the construction process, but because the project has not been completed, the prediction deviation of the maintenance project cost during the construction period is large and needs further verification.
[0058] Table 5. Alarm Threshold Table
[0059] Table 6. Early warning results table
[0060] The embodiment of the present invention analyzes the demand and deviation characteristics of benefit deviation control of waterway regulation construction projects from the perspective of the whole process, all aspects and all elements, accurately identifies the influencing factors that cause deviations from the construction benefit targets of construction projects, explores the mechanism and intensity of the influencing factors on the deviations, and uses the system dynamics model to construct the influencing factor conduction equation; based on the evolution mechanism of the influencing factors, the early warning target is achieved from the two stages of "benefit deviation interval division-alarm matching dynamic early warning", and a rough clustering model based on the hybrid particle swarm algorithm is constructed to determine the deviation alarm area division and specific thresholds; on this basis, a benefit deviation early warning model based on the BP neural network is proposed, and the future project benefits are predicted through the specific values of the influencing factors of the three stages of "early construction-mid-construction-late construction" under the current conditions, and the predicted benefit result deviation value is matched with the deviation alarm interval to realize the dynamic full-process dynamic benefit deviation early warning.
[0061] In order to better implement the project benefit deviation early warning method in the embodiment of the present invention, based on the project benefit deviation early warning method, the embodiment of the present invention also provides a project benefit deviation early warning device, such as Figure 5 As shown, the project benefit deviation early warning device 500 includes: The factor determination module 501 is used to construct a benefit deviation calculation model and determine the factors affecting the entire project process according to the project construction process; The interval determination module 502 obtains multiple deviation warning intervals according to the influencing factors of the entire project process; Deviation prediction module 503, used to predict the factors affecting the whole process of the project according to the benefit deviation calculation model, and obtain the deviation value of the predicted benefit result; The result determination module 504 is used to match the predicted benefit result deviation value with each deviation warning interval to obtain the project benefit deviation warning result.
[0062] The project benefit deviation warning device 500 provided in the above embodiment can implement the technical solution described in the above project benefit deviation warning method embodiment. The specific implementation principles of the above modules or units can refer to the corresponding contents in the above project benefit deviation warning method embodiment, which will not be repeated here.
[0063] like Figure 6 As shown, the present invention also provides an electronic device 600. The electronic device 600 includes a processor 601, a memory 602 and a display 603. Figure 6 Only some components of the electronic device 600 are shown, but it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.
[0064] In some embodiments, the memory 602 may be an internal storage unit of the electronic device 600, such as a hard disk or memory of the electronic device 600. In other embodiments, the memory 602 may also be an external storage device of the electronic device 600, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc., equipped on the electronic device 600.
[0065] Furthermore, the memory 602 may include both an internal storage unit of the electronic device 600 and an external storage device. The memory 602 is used to store application software installed in the electronic device 600 and various data.
[0066] In some embodiments, the processor 601 may be a central processing unit (CPU), a microprocessor or other data processing chip, used to run program codes or process data stored in the memory 602, such as the project benefit deviation early warning method of the present invention.
[0067] In some embodiments, the display 603 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, etc. The display 603 is used to display information of the electronic device 600 and to display a visual user interface. The components 601-603 of the electronic device 600 communicate with each other through a system bus.
[0068] In some embodiments of the present invention, when the processor 601 executes the project benefit deviation early warning program in the memory 602, the following steps may be implemented: Construct a benefit deviation calculation model and determine the factors affecting the entire project process based on the project construction process; According to the factors affecting the entire process of the project, multiple deviation warning intervals are obtained; According to the benefit deviation calculation model, the factors affecting the entire process of the project are predicted to obtain the deviation value of the predicted benefit result; Match the predicted benefit result deviation value with each deviation warning interval to obtain the project benefit deviation warning result.
[0069] It should be understood that: when the processor 601 executes the project benefit deviation warning program in the memory 602, in addition to the above functions, other functions can also be implemented. For details, please refer to the description of the corresponding method embodiment above.
[0070] Furthermore, the embodiment of the present invention does not specifically limit the type of the electronic device 600 mentioned, and the electronic device 600 may be a portable electronic device such as a mobile phone, a tablet computer, a personal digital assistant (PDA), a wearable device, a laptop computer, etc. Exemplary embodiments of portable electronic devices include but are not limited to portable electronic devices equipped with IOS, Android, Microsoft or other operating systems. The above-mentioned portable electronic devices may also be other portable electronic devices, such as a laptop computer with a touch-sensitive surface (e.g., a touch panel). It should also be understood that in some other embodiments of the present invention, the electronic device 600 may not be a portable electronic device, but a desktop computer with a touch-sensitive surface (e.g., a touch panel).
[0071] Accordingly, an embodiment of the present application also provides a computer-readable storage medium, which is used to store computer-readable programs or instructions. When the program or instructions are executed by a processor, the project benefit deviation warning method steps or functions provided in the above-mentioned method embodiments can be implemented.
[0072] Those skilled in the art will appreciate that all or part of the processes of the above-mentioned embodiments can be implemented by instructing related hardware (such as a processor, a controller, etc.) through a computer program, and the computer program can be stored in a computer-readable storage medium, wherein the computer-readable storage medium is a disk, an optical disk, a read-only storage memory, or a random access memory, etc.
[0073] The project benefit deviation early warning method and device provided by the present invention are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for technical personnel in this field, according to the idea of the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.
Claims
1. A project benefit deviation early warning method, characterized in that: include: Construct a benefit deviation calculation model and determine the factors affecting the entire project process based on the project construction process; According to the influencing factors of the whole process of the project, multiple deviation warning intervals are obtained; Predicting the influencing factors of the entire process of the project according to the benefit deviation calculation model to obtain a predicted benefit result deviation value; The predicted benefit result deviation value is matched with each deviation warning interval to obtain the project benefit deviation warning result.
2. The project benefit deviation early warning method according to claim 1 is characterized in that: According to the influencing factors of the whole process of the project, multiple deviation warning intervals are obtained, including: The influencing factors of the whole process of the project are processed based on the rough clustering set algorithm to obtain multiple initial threshold intervals; The multiple threshold intervals are optimized based on a hybrid particle swarm algorithm to obtain multiple deviation warning intervals.
3. The project benefit deviation early warning method according to claim 2 is characterized in that: The rough clustering algorithm is used to process the influencing factors of the entire project process to obtain multiple initial threshold intervals, including: Based on the rough clustering set algorithm, each influencing factor in the project full process is processed respectively to obtain a clustering distance difference; Determine multiple lower approximations and multiple upper approximations according to the cluster distance difference and all influencing factors; A plurality of initial threshold intervals are obtained according to the plurality of lower approximations and the plurality of upper approximations.
4. The project benefit deviation early warning method according to claim 2 is characterized in that: The multiple threshold intervals are optimized based on the hybrid particle swarm algorithm to obtain multiple deviation warning intervals, including: According to the factors affecting the whole process of the project, the crossover rate is obtained; Optimizing the multiple threshold intervals based on a hybrid particle swarm algorithm and the crossover rate to obtain an optimal solution fitness value; According to the fitness value of the optimal solution, a plurality of deviation warning intervals are obtained.
5. The project benefit deviation early warning method according to claim 4 is characterized in that: The crossover rate is obtained based on the influencing factors of the entire process of the project, including: Determine the weight of each influencing factor based on the influencing factors of the entire project process; Processing the weight ratio of each influencing factor to obtain an amplified target weight ratio; The crossover rate is obtained by comparing the weight proportions of all targets with the preset random number.
6. The project benefit deviation early warning method according to claim 4 is characterized in that: The step of optimizing the multiple threshold intervals based on the hybrid particle swarm algorithm and the crossover rate to obtain an optimal solution fitness value includes: Processing the influencing factors in the multiple threshold intervals based on a hybrid particle swarm algorithm and the crossover rate to obtain offspring particles; The offspring particles are mapped into the feasible domain of the chaos equation and then mapped back to the original solution space, and the fitness value of the optimal solution is calculated.
7. The project benefit deviation early warning method according to claim 4 is characterized in that: According to the fitness value of the optimal solution, a plurality of deviation warning intervals are obtained, including: Determine whether the current number of iterations has reached the maximum number of iterations; If yes, then the optimal solution fitness value is selected for effectiveness to obtain the alarm situation classification clustering center; The region is segmented according to the alarm classification cluster center to obtain a plurality of deviation alarm intervals.
8. The project benefit deviation early warning method according to claim 1 is characterized in that: The multiple deviation warning intervals include a construction-continued area, a first-level warning area, a second-level warning area, and a source-tracing rectification area; the predicted benefit result deviation value is matched with each deviation warning interval to obtain a project benefit deviation warning result, including: Matching the predicted benefit result deviation value with the continued construction area, the first-level warning area, the second-level warning area, and the traceability rectification area respectively, to determine the target area where the predicted benefit result deviation value is located; According to the target area, a project benefit deviation warning result of the project construction process is determined.
9. The project benefit deviation early warning method according to claim 2 is characterized in that: The fitness function in the hybrid particle swarm algorithm is: in, In the formula, Expressed as a density function between 0 and 1; Indicates i Correction coefficients of classes based on historical data sets; and Respectively represent i The number of data in the approximate set and boundary set of the class; Representation data x With i Cluster Centers The Euclidean distance between Representation data x With k Cluster Centers The Euclidean distance between Represents the critical region i Class by Boundary Collection The proportion of the total number of critical area data; Represents the critical region i Class close to the lower approximate set The proportion of the total number of critical area data; m Indicates the number of deviation warning intervals.
10. A project benefit deviation early warning device, characterized in that: include: The factor determination module is used to build a benefit deviation calculation model and determine the factors affecting the entire project process based on the project construction process; The interval determination module obtains multiple deviation warning intervals according to the influencing factors of the entire process of the project; A deviation prediction module is used to predict the influencing factors of the entire process of the project according to the benefit deviation calculation model to obtain a deviation value of the predicted benefit result; The result determination module is used to match the predicted benefit result deviation value with each deviation warning interval to obtain the project benefit deviation warning result.
