Work decomposition structure generation method and device based on decision tree, equipment and medium

Abstract

The invention relates to a work decomposition structure generation method and device based on a decision tree, equipment and a medium. The work decomposition structure generation method based on the decision tree comprises the following steps: acquiring pumped storage engineering project information to be decomposed; performing feature quantization on the pumped storage engineering project information to obtain a corresponding feature vector; analyzing and processing the feature vector through a pre-trained decision tree model to obtain a corresponding analysis result; and generating a work decomposition structure code based on the analysis result. According to the embodiment of the invention, the decomposition efficiency and the decomposition quality can be improved, and the labor cost is reduced.

Description

Technical Field

[0001] The present disclosure relates to the technical field of coding decomposition of a pumped storage power station project, and in particular to a method, device, equipment and medium for generating a work decomposition structure based on a decision tree. Background Art

[0002] As an important energy storage facility, the construction process of a pumped storage power station is complex and long, involving multiple stages and many professional fields. In the engineering management of a pumped storage power station, a complex structural coding system is usually used to identify and manage various engineering units. These coding systems usually have a fixed format, but due to the diversity and complexity of the codes, the process of manually decomposing and parsing these codes is time-consuming and error-prone. The traditional work breakdown structure (WBS) formulation process relies on manual experience and judgment, which is not only time-consuming and labor-intensive, but also difficult to fully consider the complexity and uncertainty of the project, leading to problems such as inefficient management and cost overruns. Summary of the invention

[0003] In order to solve the above technical problems, the present disclosure provides a method, device, equipment and medium for generating a work breakdown structure based on a decision tree.

[0004] In a first aspect, the present disclosure provides a method for generating a work breakdown structure based on a decision tree, comprising:

[0005] Obtain information on pumped storage projects to be decomposed;

[0006] Quantifying the characteristics of the pumped storage project information to obtain a corresponding characteristic vector;

[0007] Analyze and process the feature vector using a pre-trained decision tree model to obtain a corresponding analysis result;

[0008] A work breakdown structure code is generated based on the analysis result.

[0009] In a second aspect, the present disclosure provides a device for generating a work breakdown structure based on a decision tree, comprising:

[0010] The first acquisition module is used to acquire the pumped storage project information to be decomposed;

[0011] A first processing module is used to quantify the characteristics of the pumped storage project information to obtain a corresponding characteristic vector;

[0012] A second processing module is used to analyze and process the feature vector through a pre-trained decision tree model to obtain a corresponding analysis result;

[0013] The structure generation module is used to generate a work breakdown structure code based on the analysis result.

[0014] In a third aspect, the present disclosure provides a work breakdown structure generation device based on a decision tree, comprising:

[0015] processor;

[0016] A memory for storing executable instructions;

[0017] The processor is used to read executable instructions from the memory and execute the executable instructions to implement the decision tree-based work breakdown structure generation method of the first aspect.

[0018] In a fourth aspect, the present disclosure provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the processor implements the decision tree-based work breakdown structure generation method of the first aspect.

[0019] Compared with the prior art, the technical solution provided by the embodiments of the present disclosure has the following advantages:

[0020] The decision tree-based work breakdown structure generation method of the disclosed embodiment can obtain pumped storage project information to be decomposed, then quantify the features of the pumped storage project information to obtain a corresponding feature vector, then analyze and process the feature vector through a pre-trained decision tree model to obtain a corresponding analysis result, and finally generate a work breakdown structure code based on the analysis result. Thus, the pumped storage project information to be decomposed is automatically decomposed through the pre-trained decision tree model to obtain a work breakdown structure code, thereby improving the decomposition efficiency and decomposition quality and reducing labor costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale.

[0022] Figure 1 A flowchart of a method for generating a work breakdown structure based on a decision tree provided in an embodiment of the present disclosure;

[0023] Figure 2 A schematic diagram of the structure of a decision tree model principle provided by an embodiment of the present disclosure;

[0024] Figure 3 A schematic diagram of a work breakdown structure encoding provided by an embodiment of the present disclosure;

[0025] Figure 4A flowchart of another decision tree-based work breakdown structure generation method provided by an embodiment of the present disclosure;

[0026] Figure 5 A schematic diagram of the structure of a device for generating a work breakdown structure based on a decision tree provided by an embodiment of the present disclosure;

[0027] Figure 6 A schematic diagram of the structure of a decision tree-based work breakdown structure generation device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0028] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0029] It should be understood that the various steps described in the method implementation of the present disclosure can be performed in different orders and / or performed in parallel. In addition, the method implementation may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0030] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0031] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0032] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0033] The names of the messages or information exchanged between the multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0034] In order to solve the above problems, the embodiments of the present disclosure provide a method, device, equipment and medium for generating a work breakdown structure based on a decision tree. Figure 1-Figure 4 The decision tree-based work breakdown structure generation method provided in an embodiment of the present disclosure is described in detail.

[0035] Figure 1 A flowchart of a decision tree-based work breakdown structure generation method provided in an embodiment of the present disclosure is shown.

[0036] In the embodiment of the present disclosure, the decision tree-based work breakdown structure generation method may be executed by an electronic device, wherein the electronic device may include but is not limited to devices such as computer devices, cloud servers or cloud server clusters.

[0037] like Figure 1 As shown, the decision tree-based work breakdown structure generation method may include the following steps.

[0038] S110. Obtaining pumped storage project information to be decomposed.

[0039] In the disclosed embodiment, the electronic device may obtain pumped-storage power project information to be decomposed.

[0040] Optionally, the pumped storage project information may include geological and topographic conditions, project scale, environmental protection requirements, project schedule and time limits, human and technical conditions, and technology selection.

[0041] Among them, geological and topographic conditions include: Topographic influence: Some pumped storage projects are located in valleys or mountains, while other projects may be located in plains or hilly areas. Different topographic conditions will lead to adjustments in project content, such as differences in dam type, length and direction of water diversion tunnels. The undulations, slopes, openness, etc. of the terrain will also affect the use of mechanical equipment and the safety and efficiency of construction operations. Geological conditions: Different geological conditions (such as rock type, the presence or absence of faults) will affect the project design, especially the construction methods and difficulty of underground powerhouses and water diversion tunnels.

[0042] Among them, the project scale includes: Capacity: The design capacity (i.e., power generation and reservoir storage capacity) of different projects is different, which will affect the size of the reservoir, the specifications and number of generators, and the design of the transmission system. Project complexity: Larger pumped storage power stations may involve more auxiliary facilities, such as multiple water diversion tunnels, more complex pressure regulation facilities, etc.

[0043] Among them, environmental protection requirements include: Ecological environment: requirements such as protection of wild animals and plants, water source protection areas, etc. will affect the selection of construction equipment and construction methods, such as the need to adopt low-impact construction methods. Soil protection: protect soil and water bodies to avoid pollution or damage to the environment caused by construction activities.

[0044] Among them, the project progress and time constraints include: Construction period requirements: have a direct impact on the construction period and progress, and choose the appropriate construction method to ensure that the project is completed on time. Seasonal restrictions: Seasonal weather changes such as rainfall and snow season affect the construction season selection and construction arrangements.

[0045] Among them, human and technical conditions include: Technical level: the maturity and availability of construction technology, such as special technical requirements such as blasting, deep foundation pit construction, high-altitude operations, etc. Human resources: the professional skills and number of construction teams, which have a direct impact on the selection and implementation capabilities of construction methods.

[0046] Among them, technology selection includes: Technical standards and equipment selection: Different countries or regions may adopt different technical standards and equipment brands, resulting in differences in engineering details. Innovative technology application: Some projects may adopt more advanced technologies, such as reversible pump turbines, intelligent control systems, etc., while other projects may adopt traditional technologies.

[0047] Specifically, the electronic device can obtain the corresponding pumped-storage project information to be decomposed for the pumped-storage project, which may include various engineering parameters such as geological and topographic conditions, project scale, environmental protection requirements, project progress and time limits, human and technical conditions, and technology selection.

[0048] S120, quantifying the characteristics of the pumped storage project information to obtain a corresponding characteristic vector.

[0049] In the disclosed embodiment, the electronic device may perform feature quantification on the pumped storage project information to obtain a corresponding feature vector.

[0050] Specifically, after obtaining the pumped storage project information, namely, multiple engineering parameters, the electronic device can perform feature quantification on the multiple engineering parameters, such as quantifying and encoding these descriptive or categorical engineering parameters to obtain corresponding feature vectors.

[0051] S130, analyzing and processing the feature vector using a pre-trained decision tree model to obtain a corresponding analysis result.

[0052] In the disclosed embodiment, the electronic device may analyze and process the feature vector using a pre-trained decision tree model to obtain a corresponding analysis result.

[0053] Alternatively, the decision tree model is a supervised learning algorithm used to solve classification and regression problems. It recursively divides the data set into smaller subsets, eventually forming a "tree" structure. Each branch represents a decision result, and each leaf node (terminal node) represents the final prediction result or decision. It is simple and intuitive, and is suitable for both numerical and categorical data.

[0054] Specifically, after obtaining the feature vector, the electronic device can input the feature vector into a pre-trained decision tree model, and the pre-trained decision tree model analyzes and processes the feature vector to obtain a corresponding analysis result.

[0055] S140: Generate a work breakdown structure code based on the analysis result.

[0056] In the embodiment of the present disclosure, the electronic device may generate a work breakdown structure code based on the analysis result.

[0057] Optionally, the Work Breakdown Structure (WBS) code is a deliverable-oriented grouping of project elements that summarizes and defines the overall scope of work for the project. Each descending level represents a more detailed definition of the project work.

[0058] Specifically, after obtaining the analysis result, the electronic device may generate a work breakdown structure code according to the analysis result.

[0059] Thus, in the disclosed embodiment, it is possible to obtain the pumped-storage project information to be decomposed, then perform feature quantization on the pumped-storage project information to obtain a corresponding feature vector, then perform analysis and processing on the feature vector through a pre-trained decision tree model to obtain a corresponding analysis result, and finally generate a work breakdown structure code based on the analysis result. Thus, the pumped-storage project information to be decomposed is automatically decomposed through the pre-trained decision tree model to obtain a work breakdown structure code, thereby improving the decomposition efficiency and decomposition quality and reducing labor costs.

[0060] Optionally, S120 may specifically include: based on preset rules, extracting features from the pumped storage project information to obtain corresponding parameter features, the parameter features including reservoir capacity, environmental protection engineering, excavation strategy, equipment selection, construction method and material selection; performing quantization encoding processing on the parameter features to obtain the feature vector.

[0061] In the disclosed embodiment, the electronic device may extract features of the pumped storage project information based on preset rules to obtain corresponding parameter features.

[0062] Optionally, the preset rule may be a pre-set rule.

[0063] Optionally, parameter features may include reservoir capacity, environmental engineering, excavation strategy, equipment selection, construction method, and material selection.

[0064] Specifically, the electronic device can extract features of pumped storage project information based on preset rules to obtain corresponding parameter features, including reservoir capacity, environmental protection projects, excavation strategies, equipment selection, construction methods and material selection.

[0065] For example, these descriptive or categorical engineering parameters are quantified and encoded according to certain rules. Terrain type (valley, mountain, plain, hill): valley → [1, 0, 0, 0]; mountain → [0, 1, 0, 0]; plain → [0, 0, 1, 0]; hill → [0, 0, 0, 1]. Terrain undulation (slope): represented by numerical features, such as slope represented by percentage (e.g., slope = 15% → 15). Openness: represented by numerical features, such as "openness" may be represented by sight distance or horizontal distance (e.g., openness = 100 meters → 100). Rock type (granite, sandstone, limestone, etc.): granite → [1, 0, 0]; sandstone → [0, 1, 0]; limestone → [0, 0, 1]. Fault presence: binary coding can be used to represent the presence of a fault (e.g., fault presence → 1; fault absence → 0).

[0066] For example, capacity size: directly represented by numerical features, such as capacity size can be represented by megawatts (MW) (for example: capacity size = 500MW → 500). Project complexity: can be measured by several dimensions, such as the number of auxiliary facilities, the number of water diversion tunnels, etc. (for example: the number of auxiliary facilities = 3 → 3).

[0067] For example, ecological environmental protection needs: using categorical variables to represent specific protection requirements, such as protecting wild animals and plants, water source protection areas, etc., can use One-Hot Encoding (for example: protecting wild animals and plants → [1, 0]; protecting water source areas → [0, 1]). Soil protection: numerical features can be used to represent the intensity of protection, such as the number or type of protection measures (for example: number of soil protection measures = 2 → 2).

[0068] For example, construction period requirements: can be represented by numerical features, such as total construction period (in days) (for example: construction period = 365 days → 365). Seasonal restrictions: can be represented by categorical variables, such as construction season (rainy season, dry season, winter, etc.) (for example: rainy season → [1, 0, 0]; dry season → [0, 1, 0]; winter → [0, 0, 1]).

[0069] For example, technical level: Use categorical variables to represent the maturity of construction technology (such as high, medium, and low), which can be coded in an ordered or binary manner (for example: technical level = high → [3] or [1, 0, 0]; medium → [2] or [0, 1, 0]; low → [1] or [0, 0, 1]). Human resources: Use numerical features to represent, such as the professional skill level of the construction team (which can be represented by a score, such as 1-10 points) or quantity (for example: skill level = 8 points → 8).

[0070] For example, technical standards and equipment selection: use categorical variables to represent technical standards (such as European and American standards, domestic standards), and use binary coding (for example: European and American standards → [1, 0]; domestic standards → [0, 1]). Innovative technology application: use binary variables to represent whether innovative technology is adopted (adopt innovative technology → 1; do not adopt innovative technology → 0).

[0071] Furthermore, the electronic device may perform quantization encoding processing on the parameter feature to obtain the feature vector.

[0072] Specifically, the electronic device can perform quantitative encoding processing on parameter features. For example, there is a specific engineering project with the following parameters: terrain type: mountainous area; terrain undulation: 20%; rock type: granite; fault existence: yes; capacity: 600MW; project complexity: number of auxiliary facilities is 4; ecological protection requirements: protect water source area; construction period requirement: 450 days; construction season: dry season; technical level: high; human resource skill level: 9 points; technical standards: European and American standards; innovative technology: adopted. The corresponding feature vector is [0, 1, 0, 0, 20, 1, 0, 0, 1, 600, 4, 0, 1, 450, 0, 1, 0, 3, 9, 1, 0].

[0073] Thus, descriptive or categorical engineering parameters can be converted into numerical feature vectors, so that the decision tree model can understand and process these data for automatic selection and coding generation of engineering decomposition units. Each project has different feature vectors, which can be analyzed and processed by the decision tree algorithm model to make scientific and reasonable engineering decisions.

[0074] Optionally, the decision tree-based work breakdown structure generation method may also include: obtaining historical pumped-storage engineering project information; performing data preprocessing on the historical pumped-storage engineering project information to obtain a training data set; performing model training optimization on a decision tree model to be trained based on the training data set to obtain a pre-trained decision tree model.

[0075] In an embodiment of the present disclosure, the electronic device can obtain historical pumped-storage engineering project information.

[0076] Specifically, due to differences in geographical conditions, technical requirements, capacity, and other specific project needs, different pumped storage projects will also have differences in specific engineering content. Electronic equipment can collect WBS decomposition data, project documents, design drawings, task time, resource allocation and other related information of historical pumped storage projects.

[0077] Furthermore, the electronic device may perform data preprocessing on the historical pumped-storage engineering project information to obtain a training data set.

[0078] Specifically, the electronic device can clean, organize and label the collected data to build a training data set. The label should have enough information to effectively support the accuracy and reliability of the training and prediction task decomposition of the decision tree model. For the past construction of pumped storage power stations, the important information in the historical data is labeled, and the WBS decomposition coding selection results based on different labels are obtained, so as to select the appropriate construction method according to the current situation of the pumped storage power station to guide the construction of the project.

[0079] Furthermore, the electronic device may perform model training optimization on the decision tree model to be trained based on the training data set to obtain a pre-trained decision tree model.

[0080] Specifically, after data collection and preprocessing are completed, electronic devices can use decision tree models for training and optimization. The decision tree model is a supervised learning algorithm used to solve classification and regression problems. It recursively divides the data set into smaller subsets, eventually forming a "tree" structure. Each branch represents a decision result, and each leaf node (terminal node) represents the final prediction result or decision. It is simple and intuitive, and is suitable for numerical and categorical data.

[0081] Use the training data set to train the model, continuously optimize the model parameters, and improve the model's ability to identify project features and requirements. Analyze the impact weight of different labels on the WBS automatic decomposition strategy. Taking geological conditions as an example, when the surrounding rock conditions are poor, partial excavation should be used instead of full-section excavation. This will be reflected in the unit coding. In addition, when the surrounding rock conditions are poor, the support method and anchor type selected will be different. Environmental protection will also affect the construction method. Due to the influence of policies and regulations, some areas may not be able to use drilling and blasting methods, etc., and various boundary constraints are imposed. Finally, the automatic decomposition of WBS under different conditions is achieved.

[0082] Figure 2 A structural schematic diagram of a decision tree model principle provided by an embodiment of the present disclosure is shown.

[0083] like Figure 2As shown in the figure, taking geological conditions as an example, different geological conditions have different impacts on decision-making. For example, when the surrounding rock conditions are poor, partial excavation should be used instead of full-section excavation, and pre-support should be carried out; when the surrounding rock conditions are poor, full-section excavation should be used, and pre-support should be carried out; when the surrounding rock conditions are general, full-section excavation should be used, and general support should be carried out; when the surrounding rock conditions are good, full-section excavation should be used, and no support should be required, etc. The support methods and anchor types selected for different surrounding rock conditions will be different.

[0084] Optionally, the analysis process includes selection of major engineering categories, medium engineering categories, minor engineering categories, divisions, sub-items and processes; and the analysis results include major engineering categories, medium engineering categories, minor engineering categories, divisions, sub-items and processes.

[0085] Optionally, S140 may specifically include: performing coding processing based on the engineering major category, engineering medium category, engineering minor category, division, sub-item and process to obtain the work breakdown structure code.

[0086] Specifically, the electronic device can perform coding processing based on the engineering major category, engineering medium category, engineering minor category, division, sub-item and process to obtain the work breakdown structure code. For example, the electronic device assigns a unique code to each work package based on the analysis results, such as the engineering major category, engineering medium category, engineering minor category, division, sub-item and process. The coding should follow certain rules to reflect the hierarchical relationship, the stage, the professional field and other information of the work package to obtain the work breakdown structure code, which includes the engineering code, the unit engineering code, the division engineering code, the sub-item engineering code, the unit engineering code and the process type code.

[0087] Optionally, the decision tree-based work breakdown structure generation method may further include: encoding and storing the work breakdown structure in a database, and performing real-time monitoring.

[0088] Specifically, the electronic device can store the work breakdown structure code in a database, such as storing the decomposition results and coding information in the database, to facilitate subsequent project management and monitoring. Prepare for subsequent access to the engineering management platform. Develop project management software or plug-ins, integrate with the decision tree algorithm model, access the engineering management platform, and achieve real-time monitoring of project progress and WBS decomposition updates. When it is found that the actual project situation deviates from the WBS decomposition result, an alarm is issued in time to prompt the user to make corrections.

[0089] Figure 3 A structural diagram of a work breakdown structure encoding provided by an embodiment of the present disclosure is shown.

[0090] like Figure 3As shown, the WBS project breakdown structure code can generally be divided into six levels of coding according to the different types of projects, namely project, unit project, divisional project, sub-item project, unit project, and process. The format is generally xxx-xxxxxxxxx-xx(xxxx)-xxxx-xxxx-xx, a total of 24 digits.

[0091] Taking pumped storage projects as an example, the project code is generally the abbreviation of the project name. For example, the Hubei Wuhan Pumped Storage Project can be abbreviated as HWC.

[0092] The unit engineering code is nine digits. The first digit is a letter, indicating the type of construction engineering, such as A construction auxiliary engineering, B construction engineering, etc. The last two digits are digital codes for major categories under different engineering types. Taking construction engineering as an example, it can be divided into 01 water retaining buildings, 02 water discharge and energy dissipation buildings, 03 water transmission buildings, 04 power generation buildings, etc. The last two digits are divided into different middle categories. Taking water retaining buildings as an example, it can be divided into 01 concrete dam, 02 earth (stone) dam engineering, etc. The last two digits are different subcategories. Taking concrete dam as an example, it can be divided into different subcategories, including 01 arch dam, 02 gravity dam, etc. The last two digits are sequential codes. In addition, if there is no middle category or subcategory in the unit engineering code, zeros can be added according to the specified number of digits. For example, B01010100 means water retaining building-concrete dam-arch dam.

[0093] The code of the sub-project is six digits long. The first two digits are the classification code, and the second four digits are the mixed code. When the unit project is simple, only the classification code can be used, and the corresponding last four digits can be filled with zeros or omitted. It is mainly used to express the different parts of the unit project. Taking the arch dam as an example, it can be divided into 01 dam top, 02 panel, etc.

[0094] The sub-project code is 4 digits long, the first two categories are major categories, and the last two are minor categories. It is to split the projects of different parts and divide them according to the process flow. The major categories can be divided into 11 earthwork engineering, 12 support engineering, etc., and the minor categories can be further subdivided. Taking support engineering as an example, it can be divided into 01 ordinary anchor rod, 02 self-propelled anchor rod, 03 prestressed anchor rod, etc.

[0095] The unit project code is 4 digits, which is a sequential code in principle, using four digits. For more complex parts, the first digit of the code can be reserved as an auxiliary classification code. For example, the first digit of the excavation project can correspond to the spatial information such as the excavation project orientation and layer blocks.

[0096] The process corresponds to the necessary steps and process stages for each unit project. Taking excavation as an example, it can be coded into processes such as drilling, charging, blasting, clearing hazards, and slag removal.

[0097] When performing automated WBS decomposition of pumped storage projects, the first thing to do is to import the standardized WBS coding standard template into the system. This template includes the division and coding of all units, divisions, sub-items, and unit projects required for pumped storage projects. Since pumped storage projects are based on the same basic principle: using the low electricity period to pump water from the lower reservoir to the upper reservoir, and then generating electricity through hydropower during the peak electricity demand period. Its basic structure has certain similarities. Some major engineering structure coding categories can be used directly, mainly including:

[0098] Upper and lower reservoirs: All pumped storage projects require an upper reservoir and a lower reservoir, which are their core components.

[0099] Water diversion system: includes water diversion tunnels, pressure pipes and pressure regulating wells, etc., which are used for the transportation and regulation of water flow.

[0100] Power plant: Whether it is an underground plant or a ground plant, it is necessary to install a hydro-turbine generator set capable of bidirectional operation.

[0101] Transmission and transformation system: transmits electricity from the generator set to the grid, and at the same time transmits electricity from the grid to the unit for pumping during off-peak hours.

[0102] Figure 4 A flowchart of another decision tree-based work breakdown structure generation method provided in an embodiment of the present disclosure is shown.

[0103] like Figure 4 As shown, the electronic device can obtain the pumped storage project information to be decomposed, and the pumped storage project information may include geological and topographic conditions, project scale, environmental protection requirements, project progress and time limit, manpower and technical conditions and technical selection. Then the electronic device extracts the features of the pumped storage project information to be decomposed to obtain the corresponding parameter features, which include reservoir volume, environmental protection engineering, excavation strategy, equipment selection, construction method and material selection, and performs quantization coding processing on the parameter features to obtain the feature vector. Then the feature vector is input into the pre-trained decision tree model so that the pre-trained decision tree model analyzes and processes the feature vector, such as the analysis and processing includes the selection of engineering major category, engineering medium category, engineering small category, division selection, sub-item selection and process selection, and obtains the corresponding analysis results, which include engineering major category, engineering medium category, engineering small category, division, sub-item and process. Finally, a work breakdown structure code is generated based on the analysis result, and the work breakdown structure code includes engineering code, unit engineering code, division engineering code, sub-item engineering code, unit engineering code and process type code.

[0104] Thus, the decomposition efficiency is improved: the WBS decomposition is automatically completed through the decision tree algorithm, which significantly improves the decomposition efficiency and reduces labor costs. Improve the decomposition quality: the decision tree algorithm model can automatically identify and analyze project characteristics and requirements, comprehensively consider the complexity and uncertainty of the project, and generate a more accurate and reasonable WBS decomposition plan. Facilitate project management: through database management and real-time monitoring functions, real-time tracking and feedback of project progress and WBS decomposition are achieved, improving the efficiency and accuracy of project management.

[0105] Figure 5 A schematic diagram of the structure of a decision tree-based work breakdown structure generation device provided by an embodiment of the present disclosure is shown.

[0106] like Figure 5 As shown, the decision tree-based work breakdown structure generating apparatus 500 may include a first acquisition module 510 , a first processing module 520 , a second processing module 530 and a structure generating module 540 .

[0107] The first acquisition module 510 can be used to acquire pumped storage project information to be decomposed.

[0108] The first processing module 520 can be used to quantify the characteristics of the pumped storage project information to obtain a corresponding characteristic vector.

[0109] The second processing module 530 can be used to analyze and process the feature vector using a pre-trained decision tree model to obtain a corresponding analysis result.

[0110] The structure generation module 540 may be used to generate a work breakdown structure code based on the analysis result.

[0111] Thus, in the disclosed embodiment, it is possible to obtain the pumped-storage project information to be decomposed, then perform feature quantization on the pumped-storage project information to obtain a corresponding feature vector, then perform analysis and processing on the feature vector through a pre-trained decision tree model to obtain a corresponding analysis result, and finally generate a work breakdown structure code based on the analysis result. Thus, the pumped-storage project information to be decomposed is automatically decomposed through the pre-trained decision tree model to obtain a work breakdown structure code, thereby improving the decomposition efficiency and decomposition quality and reducing labor costs.

[0112] In some embodiments of the present disclosure, the pumped storage project information includes geological and topographic conditions, project scale, environmental protection requirements, project progress and time limits, human and technical conditions, and technology selection.

[0113] In some embodiments of the present disclosure, the first processing module 520 may specifically include a first processing unit and a second processing unit.

[0114] The first processing unit can be used to extract features of the pumped storage project information based on preset rules to obtain corresponding parameter features, where the parameter features include reservoir capacity, environmental protection engineering, excavation strategy, equipment selection, construction method and material selection.

[0115] The second processing unit may be used to perform quantization encoding processing on the parameter feature to obtain the feature vector.

[0116] In some embodiments of the present disclosure, the decision tree-based work breakdown structure generation device 500 may include a second acquisition module, a third processing module and a model training module.

[0117] The second acquisition module can be used to acquire historical pumped-storage engineering project information.

[0118] The third processing module can be used to perform data preprocessing on the historical pumped-storage engineering project information to obtain a training data set.

[0119] The model training module can be used to perform model training optimization on the decision tree model to be trained based on the training data set to obtain a pre-trained decision tree model.

[0120] In some embodiments of the present disclosure, the analysis process includes the selection of major engineering categories, medium engineering categories, minor engineering categories, divisions, sub-items and processes; the analysis results include major engineering categories, medium engineering categories, minor engineering categories, divisions, sub-items and processes.

[0121] In some embodiments of the present disclosure, the structure generation module 540 may specifically include a third processing unit.

[0122] The third processing unit can be used to perform coding processing based on major engineering categories, medium engineering categories, minor engineering categories, divisions, sub-items and processes to obtain the work breakdown structure code, and the work breakdown structure code includes engineering code, unit engineering code, division engineering code, sub-item engineering code, unit engineering code and process type code.

[0123] In some embodiments of the present disclosure, the decision tree-based work breakdown structure generating device 500 may include a data storage module.

[0124] The data storage module can be used to store the work breakdown structure code in a database and perform real-time monitoring.

[0125] It should be noted that Figure 5 The decision tree-based work breakdown structure generation device 500 can be executed Figure 1-Figure 4 The various steps in the method embodiment shown in the figure are implemented Figure 1-Figure 4 The various processes and effects in the method embodiment shown are not described in detail here.

[0126] Figure 6 A schematic diagram of the structure of a decision tree-based work breakdown structure generation device provided by an embodiment of the present disclosure is shown.

[0127] In some embodiments of the present disclosure, Figure 6 The work breakdown structure generation device based on the decision tree shown may be an electronic device. Specifically, the electronic device may include but is not limited to devices such as computer devices, cloud servers or cloud server clusters.

[0128] like Figure 6 As shown, the decision tree-based work breakdown structure generation device may include a processor 601 and a memory 602 storing computer program instructions.

[0129] Specifically, the processor 601 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0130] The memory 602 may include a large capacity memory for information or instructions. By way of example and not limitation, the memory 602 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a tape, or a universal serial bus (USB) drive or a combination of two or more of these. Where appropriate, the memory 602 may include a removable or non-removable (or fixed) medium. Where appropriate, the memory 602 may be inside or outside the integrated gateway device. In a particular embodiment, the memory 602 is a non-volatile solid-state memory. In a particular embodiment, the memory 602 includes a read-only memory (ROM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (Electrically Erasable Programmable ROM, EEPROM), an electrically rewritable ROM (EAROM) or a flash memory, or a combination of two or more of these.

[0131] The processor 601 reads and executes the computer program instructions stored in the memory 602 to perform the steps of the decision tree-based work breakdown structure generation method provided in the embodiment of the present disclosure.

[0132] In one example, the decision tree-based work breakdown structure generation device may further include a transceiver 603 and a bus 604. Figure 6 As shown, the processor 601, the memory 602 and the transceiver 603 are connected via a bus 604 and communicate with each other.

[0133] The bus 604 includes hardware, software, or both. For example, but not limitation, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industrial Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a MicroChannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses or a combination of two or more of these. Where appropriate, the bus 604 may include one or more buses. Although embodiments of the present application describe and illustrate a particular bus, the present application contemplates any suitable bus or interconnect.

[0134] The embodiment of the present disclosure further provides a computer-readable storage medium, which may store a computer program. When the computer program is executed by a processor, the processor implements the decision tree-based work breakdown structure generation method provided by the embodiment of the present disclosure.

[0135] The above-mentioned storage medium may, for example, include a memory 602 of computer program instructions, and the above-mentioned instructions may be executed by a processor 601 of a work breakdown structure generation device based on a decision tree to complete the work breakdown structure generation method based on a decision tree provided in an embodiment of the present disclosure. Optionally, the storage medium may be a non-temporary computer-readable storage medium, for example, the non-temporary computer-readable storage medium may be a ROM, a random access memory (Random Access Memory, RAM), a compact disc read-only memory (Compact Disc ROM, CD-ROM), a magnetic tape, a floppy disk, and an optical data storage device, etc.

[0136] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the term "comprising" is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0137] The above description is only a specific embodiment of the present disclosure, so that those skilled in the art can understand or implement the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to the embodiments described herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for generating a work breakdown structure based on a decision tree, characterized in that: include: Obtain information on pumped storage projects to be decomposed; Quantifying the characteristics of the pumped storage project information to obtain a corresponding characteristic vector; Analyze and process the feature vector using a pre-trained decision tree model to obtain a corresponding analysis result; A work breakdown structure code is generated based on the analysis result.

2. The method according to claim 1, characterized in that The pumped storage project information includes geological and topographic conditions, project scale, environmental protection requirements, project progress and time limits, human and technical conditions and technology selection.

3. The method according to claim 1, characterized in that The feature quantification of the pumped storage project information to obtain the corresponding feature vector includes: Based on preset rules, feature extraction is performed on the pumped storage project information to obtain corresponding parameter features, wherein the parameter features include reservoir capacity, environmental protection engineering, excavation strategy, equipment selection, construction method and material selection; The parameter feature is quantized and encoded to obtain the feature vector.

4. The method according to claim 1, characterized in that: The method further comprises: Obtain historical pumped storage project information; Performing data preprocessing on the historical pumped storage engineering project information to obtain a training data set; Model training optimization is performed on the decision tree model to be trained based on the training data set to obtain a pre-trained decision tree model.

5. The method according to claim 1, characterized in that The analysis process includes the selection of major engineering categories, medium engineering categories, minor engineering categories, divisions, sub-items and processes; the analysis results include major engineering categories, medium engineering categories, minor engineering categories, divisions, sub-items and processes.

6. The method according to claim 5, characterized in that Generate a work breakdown structure code based on the analysis results, including: The work breakdown structure code is obtained by coding based on the engineering major category, engineering medium category, engineering minor category, division, sub-item and process. The work breakdown structure code includes engineering code, unit engineering code, division engineering code, sub-item engineering code, unit engineering code and process type code.

7. The method according to claim 1, characterized in that The method further comprises: The work breakdown structure is coded and stored in a database, and is monitored in real time.

8. A work breakdown structure generation device based on a decision tree, characterized in that: include: The first acquisition module is used to acquire the pumped storage project information to be decomposed; A first processing module is used to quantify the characteristics of the pumped storage project information to obtain a corresponding characteristic vector; A second processing module is used to analyze and process the feature vector through a pre-trained decision tree model to obtain a corresponding analysis result; The structure generation module is used to generate a work breakdown structure code based on the analysis result.

9. A work breakdown structure generation device based on a decision tree, characterized in that: include: processor; A memory for storing executable instructions; The processor is used to read the executable instructions from the memory and execute the executable instructions to implement the decision tree-based work breakdown structure generation method described in any one of claims 1 to 5.

10. A non-volatile computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the processor implements the decision tree-based work breakdown structure generation method according to any one of claims 1 to 5.

Images