A method, device, equipment, medium and product for matching a power engineering quota

Abstract

This invention discloses a method, apparatus, equipment, medium, and product for quota matching in power engineering. The method includes: determining candidate project index entries corresponding to the quota data to be allocated in a quota project index information table; constructing project index matching prompts based on the quota data to be allocated and the candidate quota data and candidate project index information in the candidate project index entries, guiding a large-scale project index matching model to determine the target project index entry corresponding to the quota data to be allocated; determining candidate quota information and quota attribute information corresponding to the quota data to be allocated based on the target project index information in the target project index entry; and constructing quota matching prompts based on the quota data to be allocated, quota attribute information, candidate quota information, and power engineering background knowledge, guiding a large-scale quota matching model to determine the target quota information corresponding to the quota data to be allocated, thereby improving the workload efficiency and accuracy of quota matching and reducing the consumption of manual resources.

Description

Technical Field

[0001] This invention relates to the field of project management technology, and in particular to a method, apparatus, equipment, medium and product for matching quotas in power engineering. Background Technology

[0002] With the widespread application of artificial intelligence technology across various industries, the power industry is undergoing a profound transformation towards digitalization and intelligentization. In the field of power engineering construction, technical and economic cost management is a core component of project cost control and investment decision-making, and its quality and efficiency directly affect the project's economic benefits and management level.

[0003] In existing technologies, the matching of cost estimates for power engineering projects primarily relies on manual methods. Specifically, cost estimators must manually consult a vast power engineering cost estimate database based on the "cost estimate list" provided by the design unit, combined with their professional knowledge and experience, to find and select the corresponding cost estimate items. This process has several significant drawbacks: First, it is inefficient. The power engineering cost estimate system is vast and complex, covering multiple professional fields such as electrical engineering, construction, and installation, with numerous items. Manual searching and comparison are extremely time-consuming, especially when dealing with large and complex projects, becoming a key bottleneck restricting the overall cost estimate preparation progress. Second, accuracy is difficult to guarantee. The accuracy of the matching results highly depends on the cost estimator's personal experience and proficiency. Subjective negligence, misunderstandings of cost estimate rules, or unfamiliarity with newly released cost estimates can easily lead to incorrect or omitted cost estimates, directly affecting the accuracy of cost calculations and potentially posing cost risks to the project. Finally, it consumes significant human resources. The repetitive and relatively low-tech task of finding and matching quotas consumes a lot of the cost estimators' energy, making it difficult for them to focus on higher-value cost analysis, optimization, and review work, thus restricting the full utilization of professional talent. Summary of the Invention

[0004] This invention provides a method, apparatus, equipment, medium, and product for matching quotas in power engineering, in order to solve the problems that the existing quota matching work in power engineering mainly relies on manual methods, which is inefficient, inaccurate, and consumes a lot of human resources.

[0005] In a first aspect, embodiments of the present invention provide a method for matching quotas in power engineering, comprising: Obtain data on pending capital increases; Determine the candidate project index entries corresponding to the data to be allocated in the power engineering quota project index information table; the quota project index information table contains the project index entries of the power engineering projects that have been allocated in the power engineering quota document; Based on the pending capital contribution data and the candidate capital contribution data and candidate project index information in the candidate project index entries, project index matching prompt words are constructed. Based on the project index matching prompt words, the project index matching big model is guided to determine the target project index entry corresponding to the pending capital contribution data from the candidate project index entries. Based on the target project index information in the target project index entry, determine the candidate quota information and quota attribute information corresponding to the data to be quota-based in the power engineering quota file; Based on the pending quota increase data, the increase attribute information, the candidate quota information, and power engineering background knowledge, quota matching prompt words are constructed. Based on the quota matching prompt words, the quota matching big model is guided to determine the target quota information corresponding to the pending quota increase data from the candidate quota information.

[0006] Secondly, embodiments of the present invention provide a quota matching device for power engineering, comprising: The funding data acquisition module is used to acquire data on pending funding amounts. The candidate item determination module is used to determine the candidate item index entries corresponding to the data to be allocated in the quota increase project index information table of power engineering; the quota increase project index information table contains the project index entries of the allocated power engineering projects corresponding to the data in the power engineering quota file; The target item determination module is used to construct project index matching prompt words based on the data to be allocated and the candidate data and candidate project index information in the candidate project index entries, and guide the project index matching big model to determine the target project index entry corresponding to the data to be allocated from the candidate project index entries based on the project index matching prompt words; The candidate quota determination module is used to determine the candidate quota information and quota attribute information corresponding to the quota data to be quotated in the power engineering quota file based on the target project index information in the target project index entry. The target quota determination module is used to construct quota matching prompts based on the data to be allocated, the attribute information of the allocation, the candidate quota information and power engineering background knowledge, and guide the quota matching model to determine the target quota information corresponding to the data to be allocated from the candidate quota information based on the quota matching prompts.

[0007] Thirdly, embodiments of the present invention provide an electronic device, the electronic device comprising: At least one processor; and a memory communicatively connected to the at least one processor; The memory stores a computer program that can be executed by the at least one processor, which is then executed by the at least one processor to enable the at least one processor to perform the quota matching method for power engineering as described in any embodiment of the present invention.

[0008] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing computer instructions, which are used to cause a processor to execute and implement the quota matching method for power engineering as described in any embodiment of the present invention.

[0009] Fifthly, embodiments of the present invention provide a computer program product including a computer program, which, when executed by a processor, implements the quota matching method for power engineering as described in any embodiment of the present invention.

[0010] The technical solution of this invention involves: acquiring data for quota allocation; determining candidate project index entries corresponding to the data for quota allocation in the power engineering quota project index information table; the quota project index information table containing project index entries of the power engineering projects with allocated quotas corresponding to the data for quota allocation in the power engineering quota file; constructing project index matching prompts based on the data for quota allocation and the candidate data for quota allocation and candidate project index information in the candidate project index entries; using the project index matching prompts to guide the project index matching model to determine the target project index entry corresponding to the data for quota allocation from the candidate project index entries; determining the candidate quota information and quota allocation attribute information corresponding to the data for quota allocation in the power engineering quota file based on the target project index information in the target project index entry; and constructing quota matching prompts based on the data for quota allocation, quota allocation attribute information, candidate quota information, and power engineering background knowledge; using the quota matching prompts to guide the quota matching model to determine the target quota information corresponding to the data for quota allocation from the candidate quota information. This invention combines the retrieval of data to be allocated quotas, candidate project index entries, candidate quota information, and quota attribute information with the generation of target quota information through Retrieval-Augmented Generation (RAG) technology. This achieves accurate quota data analysis and quota matching, solving the problem that the existing quota matching work in power engineering mainly relies on manual methods, which is inefficient, inaccurate, and consumes a lot of human resources. It has the beneficial effect of improving the efficiency and accuracy of quota matching and reducing the consumption of human resources.

[0011] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0012] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 A flowchart illustrating a quota matching method for power engineering provided in Embodiment 1 of the present invention; Figure 2 A flowchart illustrating a quota matching method for power engineering provided in Embodiment 2 of the present invention; Figure 3 This is a schematic diagram illustrating the principle of a quota matching method for power engineering provided in Embodiment 2 of the present invention; Figure 4 This is a schematic diagram of the structure of a quota matching device for power engineering provided in Embodiment 3 of the present invention; Figure 5 A schematic diagram of the structure of an electronic device for implementing the quota matching method for power engineering in this embodiment of the invention. Detailed Implementation

[0014] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0015] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0016] Example 1 Figure 1This is a flowchart of a quota matching method for power engineering provided in Embodiment 1 of the present invention. This embodiment is applicable to the situation of quota matching for power engineering projects. The method can be executed by a quota matching device for power engineering, which can be implemented in hardware and / or software and can be configured in electronic equipment. Figure 1 As shown, the method includes: S110. Obtain data on pending capital withdrawal.

[0017] Among them, the data to be submitted for quota allocation can be considered as the data for quota matching in a project. The data can be extracted from the data submission documents, which can refer to the documents or information formally submitted by the requesting party (such as the designer, construction party, consultant, etc.) to the provider (such as the owner, other professional departments, suppliers, etc.) during the project construction or work progress, requesting the provision of the required basic data, technical parameters, confirmation opinions, etc.

[0018] For example, in power engineering, relevant information about equipment and materials can be extracted from the obtained cost estimates documents and used to form the cost estimates data to be determined.

[0019] S120. Determine the candidate project index entries corresponding to the data to be allocated in the power engineering quota project index information table; the quota project index information table contains the project index entries of the power engineering projects that have been allocated in the power engineering quota document.

[0020] The "Increased Funds Project Index Information Table" can be considered as data used to store the relationships between increased funds data and the corresponding index entries of already-quoted power engineering projects in the power engineering quota document. The index information of already-quoted power engineering projects can be considered as the index information of relevant content of completed quota-based power engineering projects within the power engineering quota document; the power engineering quota document can be a file containing quota information for relevant power engineering projects, such as relevant standard documents or project proposals. Quota information can include quota number, quota name, and quota indicator data, such as the values ​​corresponding to various resource indicators, like the cost, quantity, and size of various resources.

[0021] Index entries can contain index information (i.e., candidate index information) of the power engineering project corresponding to the data to be included in the quota, as well as the corresponding data in the power engineering quota document (i.e., candidate data for inclusion). The index information can be the chapter, section, page, or paragraph of the power engineering project in the power engineering quota document.

[0022] Candidate project index entries can be considered as project index entries obtained from a preliminary search and matching in the project index information table. It is understood that, in this embodiment, candidate project index entries require further matching to determine the target project index entries.

[0023] In this embodiment, the content of the capital contribution increase and the corresponding index information of its capital contribution information are determined in advance from the power engineering quota documents, and a capital contribution increase project index information table for power engineering is constructed. The index information of the project corresponding to the capital contribution increase content that matches the capital contribution increase data to be determined in the capital contribution increase project index information table is used as candidate project index entries.

[0024] This embodiment does not limit the matching method for candidate item index entries; for example, it can be a semantic matching method, a fuzzy matching method, or a hybrid matching method. To ensure the recall rate of quota matching, the number of candidate item index entries is generally multiple.

[0025] S130. Construct project index matching prompts based on the pending capital contribution data and the candidate capital contribution data and candidate project index information in the candidate project index entries. Based on the project index matching prompts, guide the project index matching big model to determine the target project index entry corresponding to the pending capital contribution data from the candidate project index entries.

[0026] The large-scale item index matching model can be considered as a large model that further determines the target item index from the candidate item index entries. This large-scale model can be pre-trained based on training samples using gradient descent and backpropagation algorithms. Furthermore, it can undergo supervised fine-tuning and alignment training using high-quality instruction data and instruction feedback based on the pre-trained model.

[0027] The target project index entry can be considered as the target project index entry corresponding to the final determined capital contribution data. The target project index entry can contain the index information (i.e., target index information) of the power engineering project corresponding to the capital contribution data to be determined, as well as the capital contribution data (i.e., target capital contribution data) corresponding to the capital contribution data in the power engineering quota document.

[0028] In this embodiment, the funding data and project index information are extracted from the index entries of the candidate projects. Based on the funding data, project index information, and the obtained funding data to be determined, a project index matching prompt is constructed. The project index matching prompt is input into the project index matching model. The project index matching model determines the correlation between the funding data to be determined and the funding data. The candidate project index entry with the highest correlation is determined as the target project index entry.

[0029] S140. Based on the target project index information in the target project index entry, determine the candidate quota information and quota attribute information corresponding to the data to be added in the power engineering quota file.

[0030] Among them, candidate quota information can be considered as quota information determined from the power engineering quota document based on the target project index information, or it can be considered as all quota information under the target project index information in the power engineering quota document.

[0031] In this embodiment, target project index information is determined from the target project index entries, and power engineering quota documents are queried based on the target project index information. The quota information corresponding to the target project index information in the power engineering quota documents is determined as candidate quota information for the quota data to be raised. The quota attribute information corresponding to the target project index information is determined from the power engineering quota documents.

[0032] S150. Construct quota matching prompts based on the data to be allocated, the attribute information of the quota, the candidate quota information, and the background knowledge of power engineering. Based on the quota matching prompts, guide the quota matching model to determine the target quota information corresponding to the data to be allocated from the candidate quota information.

[0033] The quota matching large model can be considered as a large model that further determines the target quota information from the candidate quota information. The quota matching large model can be pre-trained based on training samples combined with gradient descent and backpropagation algorithms. It can also be supervised fine-tuning and alignment training based on the pre-trained model using high-quality instruction data and instruction feedback.

[0034] In this embodiment, quota matching prompts are constructed based on the data to be allocated, candidate quota information, quota attribute information, and power engineering background knowledge. The quota matching prompts are input into the quota matching model. The quota matching model determines the matching degree between the data to be allocated and each quota information on the quota attribute information based on the power engineering background knowledge. The matching degree of each quota information on each quota attribute information is weighted, and the quota information with the highest weighted matching degree is determined as the target quota information.

[0035] The technical solution of this invention involves: acquiring data for quota allocation; determining candidate project index entries corresponding to the data for quota allocation in the power engineering quota project index information table; the quota project index information table containing project index entries of the power engineering projects with allocated quotas corresponding to the data for quota allocation in the power engineering quota file; constructing project index matching prompts based on the data for quota allocation and the candidate data for quota allocation and candidate project index information in the candidate project index entries; using the project index matching prompts to guide the project index matching model to determine the target project index entry corresponding to the data for quota allocation from the candidate project index entries; determining the candidate quota information and quota allocation attribute information corresponding to the data for quota allocation in the power engineering quota file based on the target project index information in the target project index entry; and constructing quota matching prompts based on the data for quota allocation, quota allocation attribute information, candidate quota information, and power engineering background knowledge; using the quota matching prompts to guide the quota matching model to determine the target quota information corresponding to the data for quota allocation from the candidate quota information. This invention combines the retrieval of data to be allocated, candidate project index entries, candidate quota information, and allocation attribute information with the generation of target quota information through Retrieval-Augmented Generation (RAG) technology. This achieves accurate allocation data analysis and quota matching, improves the efficiency and accuracy of quota matching, and reduces the consumption of manual resources.

[0036] Example 2 Figure 2 This is a flowchart of a quota matching method for power engineering provided in Embodiment 2 of the present invention. Figure 3 This is a schematic diagram illustrating the principle of a quota matching method for power engineering provided in Embodiment 2 of the present invention. Based on the above embodiments, this embodiment determines the candidate project index entries corresponding to the quota-to-be-quota-based data in the power engineering quota-based project index information table. Specifically, this involves: vectorizing the quota-to-be-quota-based data to obtain a dense vector and a sparse vector; and then using the dense vector and the sparse vector to perform a mixed search for candidate project index entries in the power engineering quota-based project index information table.

[0037] The step of determining the candidate quota information and quota attribute information corresponding to the data to be allocated quota in the power engineering quota file based on the target project index information in the target project index entry is further specified as follows: Based on the target project index information in the target project index entry, candidate quota information for the data to be allocated quota is determined from the quota sub-item table corresponding to the power engineering quota file; the quota sub-item table contains quota information corresponding to the project index information in the power engineering quota file; and the quota attribute information for the data to be allocated quota is determined from the quota attribute information table corresponding to the power engineering quota file based on the target project index information in the target project index entry; the attribute information table contains attribute information corresponding to the project index information in the power engineering quota file.

[0038] like Figure 2 and Figure 3 As shown, the method includes: S210. Obtain the data for the pending capital increase.

[0039] In this embodiment, the data to be allocated for funding is obtained by: obtaining funding documents for a power engineering project; extracting equipment and material information from the funding documents; and constructing the data to be allocated for funding based on the equipment and material information.

[0040] In this embodiment, a cost estimate document for a power engineering project is obtained. This document may contain equipment and material information for the project, such as the name, quantity, technical parameters, unit, and owner of the equipment and materials. The equipment and material information is extracted from the cost estimate document, and this information is used to construct the cost estimate data to be determined. For example, the cost estimate data to be determined may be in text format.

[0041] S220. Vectorize the data to be allocated to a fixed amount of funding to obtain dense and sparse vectors.

[0042] In this embodiment, the data to be allocated to the fixed amount of funding is sparsely embedded and vectorized to obtain a sparse vector, and the data to be allocated to the fixed amount of funding is densely embedded and vectorized to obtain a dense vector.

[0043] For example, the steps of sparse embedding vectorization may be to count the frequency of each word in the resource document, decompose the resource content into a word sequence; count the in-document frequency of each word; calculate the inverse document frequency to measure the importance of the word in the entire corpus; and generate a Term Frequency-Inverse Document Frequency (TF-IDF) matrix.

[0044] For example, the steps of dense embedding vectorization can be: segmenting the source text into words; mapping each word to a pre-trained word vector; and pooling the word vectors (average, max, weighted average) to obtain dense vectors of fixed dimensions.

[0045] S230. Search for candidate project index entries from the power engineering resource index information table using a combination of dense and sparse vectors.

[0046] In this embodiment, numerical text such as equipment model, voltage level, and capacity are precisely retrieved based on sparse vectors, while semantic text such as installation type is semantically retrieved based on dense vectors. The candidate project index entries corresponding to the data to be allocated are searched from the power engineering investment project index information table in a mixed manner.

[0047] For example, the index information table for the investment project is shown in Table 1.

[0048] Table 1 To facilitate the mixed search of candidate project index entries from the power engineering funding project index information table based on the dense and sparse vectors corresponding to the funding data to be determined, the dense and sparse vectors corresponding to the funding data columns in Table 1 can also be determined. The dense and sparse vectors can then be inserted into Table 1 to obtain the funding project index information table shown in Table 2.

[0049] Table 2 S240. Construct project index matching prompts based on the pending capital contribution data and the candidate capital contribution data and candidate project index information in the candidate project index entries. Based on the project index matching prompts, guide the project index matching big model to determine the target project index entry corresponding to the pending capital contribution data from the candidate project index entries.

[0050] In this embodiment, based on candidate funding data (such as equipment and material information) and candidate project index information (such as chapter names and chapter numbers) as context, the data to be allocated for funding (such as equipment and material information) is used as the question to construct project index matching prompts, which are then fed into the project index matching model for classification matching. The meaning of the project index matching prompts can be to indicate which item in the context the data to be allocated for funding should belong to, and the corresponding target project index entry is output.

[0051] For example, the item index matching suggestion words can be: There is [data pending fixed-amount funding]: Main transformer (220kV three-phase oil-immersed on-load transformer, 240MVA, 220 / 110 / 10, integrated) Three-phase air-cooled three-winding on-load tap-changing transformer, outdoor integrated layout, 240000kVA / 220kV 230(±8×1.25%) / 115 / 10.5kV 240 / 240 / 120MVA, YN,yn0,d1, Uk1-2%=14%, Uk1-3% =64%, Uk2-3%=50%, bushing: low voltage: 4000 / 1A, 5P15×2, 30VA×2; There is [context]: [{"Name": "110kV Main Transformer (110kV Oil-Immersed On-Load Transformer, 63MVA, 110 / 10, Horizontal Split Type)", Chapter Number: 302010200 Chapter Title: Installation of a 110kV Three-Phase Double-Winding Transformer {"Name": "Main Transformer (220kV Three-Phase Oil-Immersed On-Load Transformer, 240MVA, 220 / 110 / 10, Integrated)", Chapter Number: 302010500 Chapter Title: Installation of a 220kV Three-Phase Three-Winding Transformer {"Name": "220kV Main Transformer (Oil-immersed On-load, 50MVA, 220 / 110 / 10, Integrated)"} Chapter Number: 302010500 Chapter Title: Installation of a 220kV Three-Phase Three-Winding Transformer

Task

[0052] S250. Based on the target project index information in the target project index entry, determine the candidate quota information for the data to be submitted for quota from the quota sub-item table corresponding to the power engineering quota document; the quota sub-item table contains the quota information corresponding to the project index information in the power engineering quota document.

[0053] In an optional embodiment of this example, before obtaining the data to be allocated to the quota, the method further includes: extracting the project index information and the quota information and allocation attribute information contained under the project index information from the power engineering quota file; constructing a quota sub-item table based on the project index information and the corresponding quota information; and constructing an allocation attribute information table based on the project index information and the corresponding allocation attribute information.

[0054] In this embodiment, the project index information corresponding to each power engineering project is extracted from the power quota document. Then, the quota information and quota attribute information contained under the project index information are extracted from the power quota document. A quota sub-item table is constructed based on the project index information and the corresponding quota information, as shown in Table 3. The project index information can be represented by the chapter number where the project is located. The quota information can include the quota number, quota name, and quota indicator data. The quota indicator data includes, for example, the values ​​corresponding to various resource indicators, such as the cost, quantity, and size of various resources.

[0055] A funding attribute information table is constructed based on the project index information and the corresponding funding attribute information, as shown in Table 4.

[0056] Table 3 Table 4 In this embodiment, the quota information corresponding to the target project index information is determined from the quota sub-item table shown in Table 3, and is used as the candidate quota information for the data to be provided by quota, such as the candidate quota information corresponding to the chapter number (the candidate quota information may include quota number, quota name and quota indicator data).

[0057] S260. Based on the target project index information in the target project index entry, determine the contribution attribute information of the data to be contributed to the quota from the contribution attribute information table corresponding to the power engineering quota document; the contribution attribute information table contains the contribution attribute information corresponding to the project index information of the power engineering quota document.

[0058] In this embodiment, the capital contribution attribute information corresponding to the target project index information is determined from the capital contribution attribute information table shown in Table 4, and is used as the capital contribution attribute information of the data to be allocated capital contribution, such as the capital contribution attribute information corresponding to the chapter number.

[0059] S270. Construct quota matching prompts based on the data to be allocated, the attribute information of the quota, the candidate quota information, and the background knowledge of power engineering. Based on the quota matching prompts, guide the large quota matching model to determine the target quota information corresponding to the data to be allocated from the candidate quota information.

[0060] In this embodiment, the quota matching prompt word can be, for example: [Data on pending capital withdrawals]: Main transformer (220kV three-phase oil-immersed on-load transformer, 240MVA, 220 / 110 / 10, integrated) Three-phase air-cooled three-winding on-load tap-changing transformer, outdoor integrated layout 240000kVA / 220kV 230(±8×1.25%) / 115 / 10.5kV 240 / 240 / 120MVA, YN,yn0,d1 Uk1-2%=14% Uk1-3% =64% Uk2-3%=50% Bushing: Low voltage: 4000 / 1A, 5P15×2, 30VA×2; [Candidate Quota Information]: [{"Quota Number": "GD2-21", "Quota Name": "220kV Three-Phase Three-Winding Transformer with an Installation Capacity of 120,000kVA or Less", "Quota Index Data": "AAA",} {"Quota Number": "GD2-22","Quota Name": "220kV Three-Phase Three-Winding Transformer with Installation Capacity Within 180000kVA","Quota Index Data": "BBB",}, {"Quota Number": "GD2-23","Quota Name": "220kV Three-Phase Three-Winding Transformer with Installation Capacity within 240000kVA","Quota Index Data": "CCC",}, {"Quota Number": "GD2-24","Quota Name": "220kV Three-Phase Three-Winding Transformer with an Installation Capacity of 360,000kVA or Less","Quota Index Data": "DDD",}] Important information regarding fund withdrawal attributes to pay attention to: Voltage level, windings, number of phases, capacity.

[0061] [Background Knowledge of Electrical Engineering]: To improve the accuracy of quota matching, some background knowledge related to materials and equipment is provided below. The following are examples of capital raising for busbar types: Components such as aluminum-magnesium alloy tubes, insulated busbars, and insulated leads are generally tubular busbars, while strip busbars are generally made of copper or aluminum busbars. Flexible busbars, down conductors, and equipment wiring are generally made of steel-cored aluminum stranded wire.

[0062] The following are examples of GIS data provisioning: Gas disconnect switches, also known as combined electrical appliances, include main transformer overhead incoming line bays, main transformer cable incoming line bays, overhead outgoing line bays, cable outgoing line bays, sectionalizing bays, and bus tie bays, all of which are SF6 fully enclosed combined electrical appliances. (GIS) with circuit breaker.

[0063] Busbar equipment bays and bays marked with "no switch" or "standby" are SF6 fully enclosed GIS switchgear without circuit breakers.

[0064] In addition, the installation quota for the main busbar must be considered separately for GIS. This is calculated based on voltage level: 68 three-phase meters / bay for 750kV, 25 three-phase meters / bay for 500kV, 18 three-phase meters / bay for 330kV, 5 three-phase meters / bay for 220kV, 2.5 three-phase meters / bay for 110kV, and 3.2 three-phase meters / bay for 66kV.

[0065] Unit conversion requirements Capacity unit conversion: 1 MVA = 1000 kVA, 180 MVA = 180000 kVA, 120 MVA = 120000 kVA Length unit conversion: 1m = 10dm, 1dm = 10cm, 1cm = 10mm Area unit conversion: 1m² = 100dm², 1dm² = 100cm², 1cm² = 100mm² Volume unit conversion: 1 m³ = 1000 dm³, 1 dm³ = 1000 cm³, 1 cm³ = 1000 mm³. Voltage levels and their order: 700kV > 500kV > 330kV > 220kV > 110kV > 66kV > 35kV > 10kV

Task

[0066] As an optional embodiment of the present invention, after the quota matching prompt word guides the quota matching big model to determine the target quota information corresponding to the quota to be allocated from the candidate quota information based on the quota allocation attribute information, the method further includes: The item index information corresponding to the target quota information in the quota sub-item table is determined as the quota index information; Determine the quota adjustment requirement information from the quota adjustment information table based on the quota index information; Based on the quota adjustment requirement information, the target quota information, and the data to be adjusted for salary increase, a quota adjustment prompt is constructed, and the quota adjustment prompt is used to guide the quota adjustment model to determine the quota adjustment coefficient of the data to be adjusted for salary increase. The target quota information is adjusted according to the quota adjustment coefficient.

[0067] In this embodiment, the quota adjustment model can be considered as a large model for determining the quota adjustment coefficient, which can be used to adjust the quota indicator data.

[0068] The quota adjustment information table can be considered as a table used to store information related to quota adjustments, such as quota adjustment grouping information and quota adjustment requirement information. For example, a quota adjustment information table is shown in Table 5.

[0069] Table 5 In this embodiment, the project index information corresponding to the quota information in the quota sub-item table is determined as the quota index information; the quota adjustment requirement information is determined from the quota adjustment information table shown in Table 5 based on the quota index information; the determined quota adjustment requirement information, target quota information, and data to be added to the quota are used to construct quota adjustment prompt words; the quota adjustment prompt words are input into the quota adjustment big model; the quota adjustment big model determines the requirement information related to the target quota information from the quota adjustment requirement information, and determines the quota adjustment coefficient of the data to be added to the quota based on the determined requirement information; and the target quota information is adjusted according to the quota adjustment coefficient.

[0070] For example, the prompt for quota adjustment could be: [Data on pending capital withdrawals] Main transformer (220kV three-phase oil-immersed on-load transformer, 240MVA, 220 / 110 / 10, integrated) Three-phase air-cooled three-winding on-load tap-changing transformer, outdoor integrated layout 240000kVA / 220kV 230(±8×1.25%) / 115 / 10.5kV 240 / 240 / 120MVA, YN,yn0,d1 Uk1-2%=14% Uk1-3% =64% Uk2-3%=50% Bushing: Low voltage: 4000 / 1A, 5P15×2, 30VA×2; [Requirements for Quota Adjustment] The installation of transformers with on-load voltage regulation shall be performed in accordance with the installation quota for transformers of the same voltage and capacity, multiplied by a coefficient of 1.1. When the transformer's radiator is arranged in a separate unit, the labor cost should be multiplied by a coefficient of 1.1. The installation of 10kV oil-immersed power transformers shall be carried out in accordance with the 35kV transformer installation quota multiplied by a coefficient of 0.6. For 110kV and above equipment installed indoors, the labor cost should be multiplied by a coefficient of 1.3. [Target Quota Information] { Quota Number: "GD2-23" "Rate Name": "220kV three-phase three-winding transformer with an installed capacity of 240,000kVA or less" "Quota Inference":"..." }

Task

[0071] Example 3 Figure 4 This is a schematic diagram of a quota matching device for power engineering provided in Embodiment 3 of the present invention. Figure 4 As shown, the device includes: a data acquisition module 410, a candidate item determination module 420, a target item determination module 430, a candidate quota determination module 440, and a target quota determination module 450; wherein: The funding data acquisition module 410 is used to acquire funding data to be determined; The candidate item determination module 420 is used to determine the candidate item index entries corresponding to the data to be allocated in the quota in the power engineering quota item index information table; the quota item index information table contains the item index entries of the power engineering projects that have been allocated in the power engineering quota file. The target item determination module 430 is used to construct project index matching prompt words based on the data to be allocated and the candidate data and candidate project index information in the candidate project index entries, and guide the project index matching big model to determine the target project index entry corresponding to the data to be allocated from the candidate project index entries based on the project index matching prompt words. The candidate quota determination module 440 is used to determine the candidate quota information and quota attribute information corresponding to the quota data to be quotated in the power engineering quota file based on the target project index information in the target project index entry. The target quota determination module 450 is used to construct quota matching prompts based on the data to be allocated, the attribute information of the allocation, the candidate quota information and power engineering background knowledge, and guide the quota matching big model to determine the target quota information corresponding to the data to be allocated from the candidate quota information based on the attribute information of the allocation.

[0072] Optionally, the candidate entry determination module is specifically used for: The data to be allocated for funding is vectorized to obtain dense and sparse vectors of the data to be allocated for funding. Candidate project index entries are searched from the power engineering project index information table using a combination of dense and sparse vectors.

[0073] Optionally, the candidate quota determination module is specifically used for: Based on the target project index information in the target project index entry, candidate quota information for the data to be submitted for quota improvement is determined from the quota sub-item table corresponding to the power engineering quota document; the quota sub-item table contains quota information corresponding to the project index information in the power engineering quota document. Based on the target project index information in the target project index entry, the capital contribution attribute information of the data to be included in the capital contribution attribute information table corresponding to the power engineering quota document is determined; the capital contribution attribute information table contains the capital contribution attribute information corresponding to the project index information of the power engineering quota document.

[0074] Optional, also includes: The information extraction module is used to extract the project index information, as well as the quota information and contribution attribute information contained under the project index information, from the power engineering quota file before obtaining the data to be allocated to the quota. The quota sub-item table construction module is used to construct a quota sub-item table based on the project index information and the corresponding quota information. The funding attribute information table construction module is used to construct a funding attribute information table based on the project index information and the corresponding funding attribute information.

[0075] Optionally, it also includes: a quota adjustment module, which is used for: After the quota matching model determines the target quota information corresponding to the quota payment data to be fixed from the candidate quota information based on the quota matching prompt words and the payment attribute information, the project index information corresponding to the target quota information in the quota sub-item table is determined as the quota index information. Determine the quota adjustment requirement information from the quota adjustment information table based on the quota index information; Based on the quota adjustment requirement information, the target quota information, and the data to be adjusted for salary increase, a quota adjustment prompt is constructed, and the quota adjustment prompt is used to guide the quota adjustment model to determine the quota adjustment coefficient of the data to be adjusted for salary increase. The target quota information is adjusted according to the quota adjustment coefficient.

[0076] Optionally, the data acquisition module is specifically used for: Obtain the funding documents for the power engineering project and extract equipment and material information from the funding documents; The data for the proposed quota increase is constructed based on the equipment and material information.

[0077] The power engineering quota matching device provided in this embodiment of the invention can execute the power engineering quota matching method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0078] Example 4 Figure 5 A schematic diagram of an electronic device 10, which can be used to implement embodiments of the present invention, is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0079] like Figure 5 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0080] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0081] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the quota matching method in electrical engineering.

[0082] In some embodiments, the quota matching method for power engineering can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the quota matching method for power engineering described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the quota matching method for power engineering by any other suitable means (e.g., by means of firmware).

[0083] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0084] In some embodiments, the quota matching method for power engineering can be implemented as a computer program, which is implicitly included in a computer program product. When executed by a processor, the computer program implements the quota matching method for power engineering of the present invention. The computer program product can be understood as a software product that primarily implements its solution through a computer program. The computer program used to implement the method of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program can be executed entirely on a machine, partially on a machine, partially on a remote machine as a standalone software package, or entirely on a remote machine or server.

[0085] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0086] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0087] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0088] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0089] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0090] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for matching quotas in power engineering, characterized in that, include: Obtain data on pending capital increases; Determine the candidate project index entry corresponding to the data to be allocated in the power engineering funding project index information table; The index information table for the contribution project includes the project index entries of the already quotated power engineering projects corresponding to the contribution data in the power engineering quota document. Based on the pending capital contribution data and the candidate capital contribution data and candidate project index information in the candidate project index entries, project index matching prompt words are constructed. Based on the project index matching prompt words, the project index matching big model is guided to determine the target project index entry corresponding to the pending capital contribution data from the candidate project index entries. Based on the target project index information in the target project index entry, determine the candidate quota information and quota attribute information corresponding to the data to be quota-based in the power engineering quota file; Based on the pending quota increase data, the increase attribute information, the candidate quota information, and power engineering background knowledge, quota matching prompt words are constructed. Based on the quota matching prompt words, the quota matching big model is guided to determine the target quota information corresponding to the pending quota increase data from the candidate quota information.

2. The method according to claim 1, characterized in that, The process of determining the candidate project index entry corresponding to the data to be allocated funding in the funding project index information table of power engineering includes: The data to be allocated for funding is vectorized to obtain dense and sparse vectors of the data to be allocated for funding. Candidate project index entries are searched from the power engineering project index information table using a combination of dense and sparse vectors.

3. The method according to claim 1, characterized in that, The step of determining the candidate quota information and quota attribute information corresponding to the data to be allocated quota in the power engineering quota file based on the target project index information in the target project index entry includes: Based on the target project index information in the target project index entry, candidate quota information for the data to be submitted for quota improvement is determined from the quota sub-item table corresponding to the power engineering quota document; the quota sub-item table contains quota information corresponding to the project index information in the power engineering quota document. Based on the target project index information in the target project index entry, the capital contribution attribute information of the data to be included in the capital contribution attribute information table corresponding to the power engineering quota document is determined; the capital contribution attribute information table contains the capital contribution attribute information corresponding to the project index information of the power engineering quota document.

4. The method according to claim 3, characterized in that, Before obtaining the pending capital withdrawal data, the following is also included: Extract the project index information from the power engineering quota file, as well as the quota information and contribution attribute information contained under the project index information; Construct a quota sub-item table based on the project index information and the corresponding quota information; Construct a funding attribute information table based on the project index information and the corresponding funding attribute information.

5. The method according to claim 4, characterized in that, After the quota matching model, guided by the quota matching prompt, determines the target quota information corresponding to the quota to be allocated from the candidate quota information based on the quota allocation attribute information, the method further includes: The item index information corresponding to the target quota information in the quota sub-item table is determined as the quota index information; Determine the quota adjustment requirement information from the quota adjustment information table based on the quota index information; Based on the quota adjustment requirement information, the target quota information, and the data to be adjusted for salary increase, a quota adjustment prompt is constructed, and the quota adjustment prompt is used to guide the quota adjustment model to determine the quota adjustment coefficient of the data to be adjusted for salary increase. The target quota information is adjusted according to the quota adjustment coefficient.

6. The method according to claim 1, characterized in that, The acquisition of the data for the pending capital increase includes: Obtain the funding documents for the power engineering project and extract equipment and material information from the funding documents; The data for the proposed quota increase is constructed based on the equipment and material information.

7. A quota matching device for power engineering, characterized in that, include: The funding data acquisition module is used to acquire data on pending funding amounts. The candidate item determination module is used to determine the candidate item index entries corresponding to the data to be allocated in the quota increase project index information table of power engineering; the quota increase project index information table contains the project index entries of the allocated power engineering projects corresponding to the data in the power engineering quota file; The target item determination module is used to construct project index matching prompt words based on the data to be allocated and the candidate data and candidate project index information in the candidate project index entries, and guide the project index matching big model to determine the target project index entry corresponding to the data to be allocated from the candidate project index entries based on the project index matching prompt words; The candidate quota determination module is used to determine the candidate quota information and quota attribute information corresponding to the quota data to be quotated in the power engineering quota file based on the target project index information in the target project index entry. The target quota determination module is used to construct quota matching prompts based on the data to be allocated, the attribute information of the allocation, the candidate quota information and power engineering background knowledge, and guide the quota matching model to determine the target quota information corresponding to the data to be allocated from the candidate quota information based on the quota matching prompts.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and a memory communicatively connected to the at least one processor; The memory stores a computer program that can be executed by the at least one processor, which is then executed by the at least one processor to enable the at least one processor to perform the quota matching method for power engineering as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the quota matching method for power engineering as described in any one of claims 1-6.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the quota matching method for power engineering as described in any one of claims 1-6.

Images