Charge item determination method and device based on list splitting, medium and electronic equipment

Abstract

The invention discloses an expense item determination method and device based on list splitting, a medium and electronic equipment, and the method comprises the steps: splitting an item feature text in a to-be-split list, and obtaining at least two to-be-grouped candidate item features; determining job types and importance levels corresponding to the candidate item features; wherein the importance level is determined based on whether the candidate item features can independently illustrate the cost items involved in the to-be-split list or not; based on the job type and the importance level, grouping the candidate item features to obtain an item feature group corresponding to the to-be-split list; and determining a target cost item corresponding to the to-be-split list based on the item feature group. By executing the technical scheme provided by the invention, the accuracy and efficiency of list splitting can be improved, and the accuracy of cost item determination can be improved.

Description

Technical Field

[0001] This application relates to the fields of construction project management and construction project data processing, and in particular to a method, apparatus, medium and electronic equipment for determining cost items based on bill of quantities splitting. Background Technology

[0002] A bill of quantities is a standardized document used in construction project bidding and contract management to clarify core information such as project code, project name, project characteristics, unit of measurement, and quantities, providing a basis for project cost estimation and contract performance.

[0003] The bill of quantities is the basic framework for pricing costs. Costs, in turn, rely on project information within the bill of quantities, such as project characteristics, and are categorized into specific types like material costs, professional subcontracting fees, and labor subcontracting fees. This process transforms the project content in the bill of quantities into actual costs and prices. The two are interdependent and jointly support the preparation of project costs and the settlement of expenses during contract performance.

[0004] Currently, in the field of construction project management, the breakdown of bills of quantities mainly relies on manual methods. This is not only inefficient, but also prone to omissions due to the reliance on the experience of the operators, and there is also the problem of low accuracy in determining cost items. Summary of the Invention

[0005] This application provides a method, apparatus, medium, and electronic device for determining cost items based on bill of quantities splitting, which can improve the accuracy and efficiency of bill of quantities splitting, thereby improving the accuracy of cost item determination.

[0006] According to a first aspect of this application, a method for determining cost items based on list splitting is provided, the method comprising:

[0007] Split the feature text of the items in the list to be split to obtain at least two candidate features to be grouped.

[0008] Determine the job type and importance level corresponding to the candidate project characteristics; wherein, the importance level is determined based on whether the candidate project characteristics can independently explain the cost items involved in the list to be split.

[0009] Based on the job type and the importance level, the candidate project features are grouped to obtain the project feature groups corresponding to the list to be split;

[0010] Based on the project feature group, the target cost item corresponding to the list to be split is determined.

[0011] According to a second aspect of this application, an apparatus for determining cost items based on list splitting is provided, the apparatus comprising:

[0012] The project feature splitting module is used to split the project feature text in the list to be split, and obtain at least two candidate project features to be grouped.

[0013] The feature attribute determination module is used to determine the job type and importance level corresponding to the candidate project features; wherein, the importance level is determined based on whether the candidate project features can independently explain the cost items involved in the list to be split.

[0014] The project feature grouping module is used to group the candidate project features based on the job type and the importance level to obtain the project feature groups corresponding to the list to be split.

[0015] The cost item determination module is used to determine the target cost item corresponding to the list to be split based on the project feature group.

[0016] According to a third aspect of the present invention, embodiments of this application provide a computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the cost item determination method based on list splitting as described in embodiments of this application.

[0017] According to a fourth aspect of the present invention, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the cost item determination method based on list splitting as described in the embodiments of the present application.

[0018] According to a fifth aspect of this application, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the cost item determination method based on list splitting as described in embodiments of this application.

[0019] The technical solution of this application, through splitting the project feature text in the list to be split, achieves item-by-item parsing of the project feature text, transforming the originally mixed project feature text into candidate project features with appropriate granularity, laying the foundation for subsequent analysis. When grouping candidate project features, the work type is considered, ensuring the semantic integrity of the project feature group under a specific work type. The importance level is also considered when grouping candidate project features; by judging whether the candidate feature can independently describe the corresponding cost item in the list to be split, the grouping of candidate project features is closely linked to the cost item determination requirements. Through the collaborative grouping mechanism of work type and importance level, a logically rigorous project feature group is constructed, which not only conforms to the professional classification habits in the construction engineering field but also clearly presents the decision-making path for cost item determination. This significantly improves the accuracy and efficiency of list splitting. Based on the project feature group, the target cost item corresponding to the list to be split is determined, which helps to improve the accuracy of cost item determination.

[0020] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent from the following description. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of this application, 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 this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a flowchart of the method for determining cost items based on list splitting provided in Embodiment 1;

[0023] Figure 2 This is a flowchart of the method for determining cost items based on list splitting provided in Embodiment 2;

[0024] Figure 3 This is a schematic diagram of the cost item determination device based on list splitting provided in Embodiment 3 of this application;

[0025] Figure 4 This is a schematic diagram of the structure of an electronic device provided in Embodiment 4 of this application. Detailed Implementation

[0026] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0027] It should be noted that the terms "first," "second," "target," and "candidate," etc., used in the specification, claims, and accompanying drawings of this application 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 this application 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.

[0028] Example 1

[0029] Figure 1 This is a flowchart of the method for determining cost items based on bill of quantities splitting according to Embodiment 1. This embodiment can be applied to the case of determining cost items based on the bill of quantities. The method can be executed by a cost item determination device based on bill of quantities splitting. The cost item determination device based on bill of quantities splitting is implemented in hardware and / or software and can be integrated into an electronic device running this system.

[0030] like Figure 1 As shown, the method includes:

[0031] S110. Split the item feature text in the list to be split to obtain at least two candidate item features to be grouped.

[0032] S120. Determine the job type and importance level corresponding to the candidate project characteristics; wherein, the importance level is determined based on whether the candidate project characteristics can independently explain the cost items involved in the list to be split.

[0033] S130. Based on the job type and the importance level, the candidate project features are grouped to obtain the project feature groups corresponding to the list to be split.

[0034] S140. Based on the project feature group, determine the target cost item corresponding to the list to be split.

[0035] The "Bill of Quantities to be Split" refers to the bill of quantities that needs to be split based on project characteristics. The bill of quantities to be split includes project characteristic text. Table 1 shows a portion of the bill of quantities. Referring to Table 1, the bill of quantities to be split includes content identifiers such as codes, names, and project characteristics to distinguish different text content within the bill of quantities. Optionally, project characteristic text can be extracted from the bill of quantities to be split based on these content identifiers. Optionally, the project characteristic text in the bill of quantities to be split includes at least two project characteristics. The bill of quantities shown in Table 1 demonstrates that the project characteristic text includes at least five project characteristics.

[0036] The candidate project features are obtained by splitting the project feature text. Taking the project feature text shown in Table 1 as an example, the candidate project features obtained by splitting include at least the following 5 items: 10mm thick cement mortar with a 1% slope towards the drainage outlet, coated with the same textured paint; 5mm thick dry powder polymer cement waterproof mortar, with a layer of alkali-resistant glass fiber mesh pressed in the middle; 2 layers of 1.5mm thick polyurethane waterproof coating, with a height and width of 300mm on the waterproof coating (see waterproof engineering list for details); 15mm thick (thinnest part) 1:2 cement mortar with a 2% slope; cast-in-place reinforced concrete roof slab, with the surface cleaned.

[0037] Table 1

[0038]

[0039] Candidate project features are the objects of feature grouping, while job type and importance level are important bases for grouping candidate project features. Job type belongs to the classification of the construction engineering field. Job type can cover engineering sub-items, construction measures, material and process attributes, and auxiliary information such as bill of quantities descriptions involved in construction engineering. Job type is used to group candidate project features. Optionally, candidate project features belonging to the same job type are grouped into the same feature group to ensure the semantic integrity of the project feature group under a specific job type.

[0040] The specific content of the work type is not limited here, and will be determined according to actual business needs. For example, the work types include the following categories: {Location, Transport Distance, Plain Cement, Block Materials, Formwork, Pile Foundation and Support, Pricing, Subbase, Concrete Engineering, Surface Materials, Ceiling Engineering, Reinforcing Steel Engineering, Base Cleaning, Work Content, Painting Engineering, Masonry Engineering, Unit Price Measures, Insulation, Scaffolding, Painting, Earthwork Engineering, Leveling, Drainage and Ventilation, Keel, Waterproofing, Skirting Board, Metal Structure Engineering}.

[0041] Continuing with the previous example, the job type corresponding to the candidate project feature "10mm thinnest cement mortar with a 1% slope towards the drainage outlet, with a matching textured paint applied on the outside" is determined to be paint; the job type corresponding to the candidate project feature "5mm thick dry powder polymer cement waterproof mortar, with a layer of alkali-resistant glass fiber mesh pressed in the middle" is determined to be waterproof.

[0042] The importance level is determined based on whether the candidate project characteristics can independently describe the cost items involved in the bill of quantities to be split, quantifying the independence of project characteristic groups in the cost item descriptions. Optionally, the importance level includes a first level and a second level, with the first level being higher than the second. Candidate project characteristics of the first level can independently describe the cost items involved in the bill of quantities to be split; candidate project characteristics of the second level need to be combined to describe the cost items involved in the bill of quantities to be split. Cost items convert the engineering content of the bill of quantities into actual costs and prices. The specific content of cost items is determined according to actual business needs and is not limited here. For example, cost items may include material costs and labor subcontracting fees.

[0043] The importance level determines whether candidate item features can be grouped as independent features. Optionally, first-level candidate item features can be grouped as independent features. Second-level candidate item features need to be combined to form a combined feature group. The work type guides how to combine candidate item features. Each item feature group must include at least two candidate item features, at least one of which must be a basic item feature. A basic item feature refers to a candidate item feature whose work type belongs to a basic type. Work types related to the bill of quantities description auxiliary information can be determined as basic types. Optionally, basic types include locations. The bill of quantities description auxiliary information essentially describes non-physical, non-process-related auxiliary information in the bill of quantities.

[0044] The project feature group serves as the data basis for determining cost items. In other words, the technical solution in this application determines the target cost items corresponding to the list to be split based on accurate project feature groups with complete contextual semantics, not the entire feature text of the list to be split, nor isolated feature words extracted from the entire feature text. This avoids contextual interference and contextual fragmentation, ensuring the accuracy of cost item determination and preventing omissions and errors.

[0045] The technical solution of this application, through splitting the project feature text in the list to be split, achieves item-by-item parsing of the project feature text, transforming the originally mixed project feature text into candidate project features with appropriate granularity, laying the foundation for subsequent analysis. When grouping candidate project features, the work type is considered, ensuring the semantic integrity of the project feature group under a specific work type. The importance level is also considered when grouping candidate project features; by judging whether the candidate feature can independently describe the corresponding cost item in the list to be split, the grouping of candidate project features is closely linked to the cost item determination requirements. Through the collaborative grouping mechanism of work type and importance level, a logically rigorous project feature group is constructed, which not only conforms to the professional classification habits in the construction engineering field but also clearly presents the decision-making path for cost item determination. This significantly improves the accuracy and efficiency of list splitting. Based on the project feature group, the target cost item corresponding to the list to be split is determined, which helps to improve the accuracy of cost item determination.

[0046] In an optional embodiment, determining the job type and importance level corresponding to the candidate project features includes: inputting the candidate project features into a job type determination model, and outputting the job type corresponding to the candidate project features through the job type determination model; inputting the candidate project features into an importance level determination model, and outputting the importance level corresponding to the candidate project features through the importance level determination model; wherein, the job type determination model and the importance level determination model are a multi-classification model and a binary classification model pre-trained based on labeled training samples, respectively; the training samples used to train the job type determination model and the importance level determination model are project features obtained by splitting the project feature text in the bill of quantities; the sample label corresponding to the job type determination model is the job type; and the sample label corresponding to the importance level determination model is the importance level.

[0047] The job type determination model is used to determine the job type corresponding to the candidate project features. The candidate project features are the input data of the job type determination model, and the project type is the output result of the job type determination model.

[0048] The job type determination model is a multi-classification model pre-trained based on labeled training samples. Optionally, the job type determination model is the BERT model (Bidirectional Encoder Representations from Transformers).

[0049] The importance ranking model is used to determine the importance ranking of candidate item features. Candidate item features are the input data to the importance ranking model, and the importance ranking is the output result. The importance ranking model is a binary classification model pre-trained based on labeled training samples.

[0050] Optionally, the same training samples with different sample labels can be used to train both the job type determination model and the importance level determination model. The training samples are the project features obtained by splitting the project feature text in the bill of quantities.

[0051] The sample labels corresponding to the job type determination model can be called type labels, which represent the job type. The sample labels corresponding to the importance level determination model can be called level labels, which represent the importance level.

[0052] The training samples and sample labels used in the training task type determination model and importance level determination model are not limited here, and are determined according to actual business needs. For example, training sample 1 can be "5mm thick polymer crack-resistant mortar (with 1 layer of alkali-resistant fiberglass mesh pressed in) as a protective layer", type label 1 can be "thermal insulation", and level label 1 can be "first level"; training sample 2 is "concrete type: commercial concrete", type label 2 is "concrete engineering", and level label 2 can be "second level".

[0053] The above technical solution provides a practical method for determining job types and importance levels, achieving semantic parsing and value stratification of candidate item features. The job type determination model identifies the job type of candidate items, and the importance level determination model determines the importance level of each candidate item type. This transforms the traditional fragmented judgment relying on human experience into iterative algorithmic decision-making, automating the determination of job types and importance levels, and improving the accuracy and efficiency of list splitting.

[0054] In an optional embodiment, before inputting the candidate project features into the importance level determination model and outputting the importance level corresponding to the candidate project features through the importance level determination model, the method further includes: determining whether the job type corresponding to the candidate project feature belongs to the basic type; if the job type corresponding to the candidate project feature does not belong to the basic type, then inputting the candidate project features into the importance level determination model.

[0055] Here, "basic type" refers to the type of operation that involves auxiliary information in the bill of quantities description. "Basic project characteristics" refers to the candidate project characteristics of the operation type as the basic type. Basic project characteristics do not directly constitute the engineering entity, nor do they describe specific construction actions; they are used to provide boundary constraints and scenario rules for cost item determination. Basic project characteristics are a necessary component of the project characteristic group. In other words, each project characteristic group includes basic project characteristics.

[0056] Therefore, if the job type corresponding to the candidate project feature has been determined, then it is determined whether the job type corresponding to the candidate project feature belongs to the basic type. Optionally, which job types belong to the basic type are pre-labeled. For example, "location" is determined as the basic type.

[0057] The candidate project features corresponding to the basic type are identified as basic project features. Since basic project features do not directly constitute the engineering entity or describe specific construction actions, they cannot be considered as an independent feature group. Therefore, it is unnecessary to determine the importance level corresponding to the basic project features.

[0058] If the job type corresponding to a candidate project feature does not belong to the basic type, it indicates that the candidate project feature may directly constitute an engineering entity or may describe specific construction actions. It is necessary to further determine the importance level of the candidate project feature to determine whether it can be used as an independent feature group. If the job type corresponding to a candidate project feature does not belong to the basic type, then the candidate project features are input into the importance level determination model, and the model is assigned to the importance level corresponding to the candidate project feature.

[0059] The above technical solution first separates basic type features by job type before candidate project features enter the importance level determination model. This ensures that the importance level determination model only focuses on candidate project features that need to be dynamically evaluated for importance level. This helps to reduce the computational load of the model. More importantly, it solidifies the rule priority of basic project features. Since basic project features have been forcibly retained in the project feature group by job type, the loss of key constraint information due to model volatility is avoided, which helps to improve the accuracy of list splitting.

[0060] In an optional embodiment, splitting the item feature text in the list to be split to obtain at least two candidate item features to be grouped includes: extracting the item feature text from the list to be split based on the content identifier in the list to be split; identifying the feature separator in the item feature text and determining the position of the feature separator as the split position; and splitting the item feature text based on the split position to obtain at least two candidate item features to be grouped.

[0061] The content identifier is used to distinguish different text content in the list to be split. Optionally, the content identifier corresponding to the item feature text in the list to be split is "item feature". The text content identified by "item feature" is extracted from the list to be split and used as the item feature text.

[0062] The project feature text includes at least two project features, each distinguished by a feature segmentation identifier. The feature segmentation identifier determines the natural semantic boundaries of each project feature. Optionally, the feature segmentation identifier can be a newline character, a semicolon, or a conjunction. The location of the feature segmentation identifier is determined as the segmentation position, which serves as the coordinate basis for physically splitting the project features, dividing the project feature text in the list to be split into two candidate project features. The candidate project features are independent semantic units with engineering pricing significance, and they are the objects of feature grouping.

[0063] The above technical solution accurately extracts item feature text from the list to be split by content identification and positioning, then determines the cutting position based on feature separation identifiers, and finally achieves complete candidate item feature splitting according to natural semantic boundaries. This ensures the integrity of feature descriptions, improves the parsing robustness of complex lists, and enhances the accuracy of list splitting.

[0064] In an optional embodiment, determining the target expense item corresponding to the list to be split based on the project feature group includes: obtaining a first correspondence between preset project features and candidate expense items; determining the text similarity between the project feature group and the preset project features, and determining the target project feature from the preset project features based on the text similarity; and determining the target expense item corresponding to the project feature group from the candidate expense items based on the first correspondence and the target project feature.

[0065] The first correspondence record records the association between project characteristics and candidate cost items. The first correspondence is predefined according to business requirements, and this application supports the expansion and adjustment of the first correspondence.

[0066] Text similarity is used to quantify the degree of textual similarity between a group of project feature elements and preset project features. Text similarity is adaptable to natural language variations in feature descriptions and can handle new or complex project feature expressions. Optionally, the group of project feature elements and the preset project features are vectorized separately to obtain a first feature vector and a second feature vector. The vector similarity between the first and second feature vectors is calculated as the textual similarity between the group of project feature elements and the preset project features.

[0067] Optionally, the preset project feature with the highest text similarity can be used as the target project feature. Based on the first correspondence, the target cost item corresponding to the target project feature can be determined from the candidate cost items. The target cost item is then determined as the target cost item corresponding to the project feature group.

[0068] The above technical solution matches expense items based on project feature groups, ensuring the accuracy of expense item identification. Simultaneously, it automates and precisely matches expense items, significantly improving matching efficiency and accuracy, strengthening the standardization and consistency of expense classification, and using the first correspondence relationship as the core rule to ensure the standardization and normalization of expense item matching results, thereby improving data governance.

[0069] Example 2

[0070] Figure 2 This is a flowchart of the method for determining cost items based on list splitting provided in Embodiment 2. This embodiment is a further optimization based on the above embodiments.

[0071] like Figure 2 As shown, the method includes:

[0072] S210. Split the item feature text in the list to be split to obtain at least two candidate item features to be grouped.

[0073] S220. Determine the job type and importance level corresponding to the candidate project characteristics; wherein, the importance level is determined based on whether the candidate project characteristics can independently explain the cost items involved in the list to be split.

[0074] S230. If the importance level corresponding to the candidate item feature is the first level, then the candidate item feature is treated as an independent feature group.

[0075] The importance level quantifies the independence of a group of project features in the cost item description. Optionally, the importance level includes a first level and a second level. The first level is higher than the second level; candidate project features of the first level can independently describe the cost items involved in the cost item to be split; candidate project features of the second level need to be combined to describe the cost items involved in the cost item to be split.

[0076] The importance level corresponding to the candidate item features is Level 1, indicating that the candidate item features can independently describe the cost items involved in the list to be split. Candidate item features are treated as independent feature groups. Each independent feature group is directly composed of Level 1 candidate item features. An independent feature group contains only one Level 1 candidate item feature.

[0077] For example, two candidate project features were extracted from the project feature text of the list to be split: "10mm thinnest cement mortar with a 1% slope towards the drainage outlet, coated with the same color textured paint; 5mm thick dry powder polymer cement waterproof mortar, with a layer of alkali-resistant fiberglass mesh pressed in the middle." The work type corresponding to "10mm thinnest cement mortar with a 1% slope towards the drainage outlet, coated with the same color textured paint" is leveling, with an importance level of 1. The work type corresponding to "5mm thick dry powder polymer cement waterproof mortar, with a layer of alkali-resistant fiberglass mesh pressed in the middle" is waterproofing, with an importance level of 1. These two candidate project features are treated as independent feature groups.

[0078] S240. If the importance level corresponding to the candidate project feature is the second level, then based on the job type corresponding to the candidate project feature, the candidate project features belonging to the same job type are combined to obtain a combined feature group.

[0079] The candidate item features correspond to a importance level of 2, indicating that the candidate item features need to be combined to explain the cost items involved in the list to be split. Candidate item features belonging to the same job type are combined to form a combined feature group. A combined feature group is formed by combining candidate item features of the same job type with an importance level of 2. A combined feature group includes at least two candidate item features of the same job type with an importance level of 2.

[0080] For example, three candidate project features were extracted from the project feature text of the list to be split: "Concrete type: commercial concrete; Concrete strength grade: C30; Other: Concrete delivery method, related costs to be considered by the bidder in the unit price." All three candidate project features are for concrete engineering, and their importance level is second level. Therefore, these three candidate project features need to be combined to obtain a combined feature group.

[0081] S250. Based on the independent feature group, the combined feature group, and the job type corresponding to the candidate project features, determine the project feature group corresponding to the list to be split.

[0082] It is worth noting that the independent feature groups and combined feature groups are not the final project feature groups. The independent feature groups and combined feature groups also lack the necessary boundary constraints and scenario rules for determining cost items.

[0083] Based on the job type corresponding to the candidate project features, basic project features that can provide boundary constraints and scenario rules for cost item determination are identified from the candidate project features.

[0084] Only independent feature groups and combined feature groups that incorporate basic project characteristics can be used as the project feature groups corresponding to the list to be split.

[0085] S260. Based on the project feature group, determine the target cost item corresponding to the list to be split.

[0086] Among them, the project feature group is the feature splitting result of the project feature splitting of the list to be split, and the project feature group is the basic unit for determining the cost item.

[0087] The technical solution of this application implements a differentiated processing strategy based on importance level. For candidate project features at the first importance level that can independently explain expense items, these are directly retained as independent feature groups. This avoids the weakening or omission of key information during the combination process, ensuring the complete expression of high-value features. For candidate project features at the second importance level that require collaborative explanation of expense items, they are forcibly aggregated into combined feature groups according to work type, forming the smallest unit with complete pricing semantics. This eliminates the risk of misjudgment of expense items due to feature fragmentation from the source. This significantly improves the accuracy, efficiency, and business adaptability of project feature grouping, providing a data foundation with a clear structure and reasonable granularity for expense item determination.

[0088] In an optional embodiment, determining the project feature group corresponding to the list to be split based on the independent feature group, the combined feature group, and the job type corresponding to the candidate project features includes: determining the candidate project features whose job type belongs to the basic type as basic project features; and adding the basic project features to the independent feature group and the combined feature group respectively to obtain the combined feature group.

[0089] Among them, the basic type refers to the type of work involving auxiliary information in the bill of quantities description. This auxiliary information essentially describes non-physical and non-process-related auxiliary information in the bill of quantities.

[0090] Basic project characteristics are candidate project characteristics whose task type belongs to the basic type.

[0091] Basic project features do not directly constitute the engineering entity, nor do they describe specific construction actions. They are used to provide boundary constraints and scenario rules for cost item determination. Basic project features are a necessary component of the project feature group. In other words, each project feature group includes basic project features.

[0092] By adding the basic project features to the independent feature group and the combined feature group respectively, and providing the necessary boundary constraints and scenario rules for determining the cost items for the independent feature group and the combined feature group, the combined feature group can be obtained.

[0093] The above technical solution significantly enhances the completeness and business rationality of expense item determination by introducing a global embedding mechanism for basic project features. Forcibly injecting basic project features into each independent feature group and combined feature group allows these groups to bear the necessary boundary constraints and scenario rules for determining expense items, thus improving the accuracy of expense item determination.

[0094] Example 3

[0095] Figure 3 This is a schematic diagram of the structure of the cost item determination device based on bill of quantities splitting provided in Embodiment 3 of this application. This embodiment can be applied to the situation of determining cost items based on the bill of quantities. The device can be implemented by software and / or hardware and can be integrated into electronic devices such as smart terminals.

[0096] like Figure 3 As shown, the device may include:

[0097] The project feature splitting module 310 is used to split the project feature text in the list to be split, and obtain at least two candidate project features to be grouped.

[0098] The feature attribute determination module 320 is used to determine the job type and importance level corresponding to the candidate project features; wherein, the importance level is determined based on whether the candidate project features can independently explain the cost items involved in the list to be split.

[0099] The project feature grouping module 330 is used to group the candidate project features based on the job type and the importance level to obtain the project feature group corresponding to the list to be split.

[0100] The cost item determination module 340 is used to determine the target cost item corresponding to the list to be split based on the project feature group.

[0101] The technical solution of this application, through splitting the project feature text in the list to be split, achieves item-by-item parsing of the project feature text, transforming the originally mixed project feature text into candidate project features with appropriate granularity, laying the foundation for subsequent analysis. When grouping candidate project features, the work type is considered, ensuring the semantic integrity of the project feature group under a specific work type. The importance level is also considered when grouping candidate project features; by judging whether the candidate feature can independently describe the corresponding cost item in the list to be split, the grouping of candidate project features is closely linked to the cost item determination requirements. Through the collaborative grouping mechanism of work type and importance level, a logically rigorous project feature group is constructed, which not only conforms to the professional classification habits in the construction engineering field but also clearly presents the decision-making path for cost item determination. This significantly improves the accuracy and efficiency of list splitting. Based on the project feature group, the target cost item corresponding to the list to be split is determined, which helps to improve the accuracy of cost item determination.

[0102] Optionally, the project feature grouping module 330 includes: a first grouping submodule, used to group the candidate project feature as an independent feature group if the importance level corresponding to the candidate project feature is first level; a second grouping submodule, used to combine the candidate project features belonging to the same job type to obtain a combined feature group based on the job type corresponding to the candidate project feature if the importance level corresponding to the candidate project feature is second level; and a feature group determination submodule, used to determine the project feature group corresponding to the list to be split based on the independent feature group, the combined feature group, and the job type corresponding to the candidate project feature; wherein, the first level is higher than the second level, and the candidate project features of the first level can independently describe the cost items involved in the list to be split; the candidate project features of the second level need to be combined to describe the cost items involved in the list to be split.

[0103] Optionally, the second grouping submodule includes: a basic feature determination unit, used to determine candidate project features whose job type belongs to the basic type as basic project features; and a feature group determination unit, used to add the basic project features to the independent feature group and the combined feature group respectively to obtain the combined feature group.

[0104] Optionally, the feature attribute determination module 320 includes: a job type determination submodule, used to input the candidate project features into a job type determination model, and output the job type corresponding to the candidate project features through the job type determination model; and an importance level determination submodule, used to determine the importance level model, and output the importance level corresponding to the candidate project features through the importance level determination model; wherein, the job type determination model and the importance level determination model are a multi-classification model and a binary classification model pre-trained based on labeled training samples, respectively; the training samples used to train the job type determination model and the importance level determination model are project features obtained by splitting the project feature text in the bill of quantities; the sample label corresponding to the job type determination model is the job type; and the sample label corresponding to the importance level determination model is the importance level.

[0105] Optionally, the device further includes: a basic type identification module, used to determine whether the job type corresponding to the candidate project feature belongs to a basic type before inputting the candidate project features into the importance level determination model and outputting the importance level corresponding to the candidate project feature through the importance level determination model; and a project feature input module, used to input the candidate project feature into the importance level determination model if the job type corresponding to the candidate project feature does not belong to the basic type.

[0106] Optionally, the project feature splitting module 310 includes: a feature text extraction submodule, used to extract the project feature text from the list to be split based on the content identifier in the list to be split; a segmentation position determination submodule, used to identify the feature separation identifier in the project feature text and determine the position of the feature separation identifier as the segmentation position; and a feature text splitting submodule, used to split the project feature text based on the segmentation position to obtain at least two candidate project features to be grouped.

[0107] The expense item determination apparatus based on bill of quantities splitting provided in the embodiments of the invention can execute the expense item determination method based on bill of quantities splitting provided in any embodiment of this application, and has the corresponding performance modules and beneficial effects for executing the expense item determination method based on bill of quantities splitting.

[0108] Example 4

[0109] According to embodiments of this application, this application also provides an electronic device, a readable storage medium, and a computer program product.

[0110] Figure 4A schematic diagram of an electronic device 410, which can be implemented using an embodiment, is shown. The electronic device 410 includes at least one processor 411 and a memory, such as a read-only memory (ROM) 412, a random access memory (RAM) 413, etc., communicatively connected to the at least one processor 411. The memory stores computer programs executable by the at least one processor. The processor 411 can perform various appropriate actions and processes based on the computer program stored in the ROM 412 or loaded from storage unit 418 into the RAM 413. The RAM 413 may also store various programs and data required for the operation of the electronic device 410. The processor 411, ROM 412, and RAM 413 are interconnected via a bus 414. An input / output (I / O) interface 415 is also connected to the bus 414.

[0111] Multiple components in electronic device 410 are connected to I / O interface 415, including: input unit 416, such as keyboard, mouse, etc.; output unit 417, such as various types of displays, speakers, etc.; storage unit 418, such as disk, optical disk, etc.; and communication unit 419, such as network card, modem, wireless transceiver, etc. Communication unit 419 allows electronic device 410 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0112] Processor 411 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 411 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 411 performs the various methods and processes described above, such as the cost item determination method based on list splitting.

[0113] In some embodiments, the bill of quantities-based cost item determination method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 418. In some embodiments, part or all of the computer program may be loaded and / or mounted on electronic device 410 via ROM 412 and / or communication unit 419. When the computer program is loaded into RAM 413 and executed by processor 411, one or more steps of the bill of quantities-based cost item determination method described above may be performed. Alternatively, in other embodiments, processor 411 may be configured to perform the bill of quantities-based cost item determination method by any other suitable means (e.g., by means of firmware).

[0114] Various implementations 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), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations 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.

[0115] Computer programs used to implement the methods of this application may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable cost item determination device based on bill of quantities splitting, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The computer programs may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0116] In the context of this application, 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 can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can 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 fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0117] 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).

[0118] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., a bill of lading-based expense item determination server), or middleware components (e.g., an application server), or frontend components (e.g., a user computer with a graphical user interface or web browser through which a user 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., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0119] 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.

[0120] This application also discloses a computer program product, which includes a computer program that, when executed by a processor, implements the cost item determination method based on bill of quantities splitting provided in any embodiment of this application. This program product and the cost item determination method based on bill of quantities splitting disclosed in the embodiments of this application belong to the same inventive concept, and therefore will not be described in detail here.

[0121] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this application can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this application can be achieved, and this is not limited herein.

[0122] The specific embodiments described above do not constitute a limitation on the scope of protection of this application. 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 application should be included within the scope of protection of this application.

Claims

1. A method for determining cost items based on bill of quantities splitting, characterized in that, The method includes: Split the feature text of the items in the list to be split to obtain at least two candidate features to be grouped. Determine the job type and importance level corresponding to the candidate project characteristics; wherein, the importance level is determined based on whether the candidate project characteristics can independently explain the cost items involved in the list to be split. Based on the job type and the importance level, the candidate project features are grouped to obtain the project feature groups corresponding to the list to be split; Based on the project feature group, the target cost item corresponding to the list to be split is determined.

2. The method according to claim 1, characterized in that, The process of grouping the candidate project features based on the job type and the importance level to obtain the project feature groups corresponding to the list to be split includes: If the importance level corresponding to the candidate item feature is the first level, then the candidate item feature is treated as an independent feature group. If the importance level corresponding to the candidate project feature is the second level, then based on the job type corresponding to the candidate project feature, the candidate project features belonging to the same job type are combined to obtain a combined feature group; Based on the independent feature groups, the combined feature groups, and the job types corresponding to the candidate project features, the project feature groups corresponding to the list to be split are determined; The first level is higher than the second level. The candidate item features of the first level can independently describe the cost items involved in the list to be split; the candidate item features of the second level need to be combined to describe the cost items involved in the list to be split.

3. The method according to claim 2, characterized in that, The step of determining the project feature group corresponding to the list to be split based on the independent feature group, the combined feature group, and the job type corresponding to the candidate project features includes: Candidate project features whose job type belongs to the basic type are identified as basic project features; The basic project features are added to the independent feature group and the combined feature group respectively to obtain the combined feature group.

4. The method according to claim 1, characterized in that, Determining the job type and importance level corresponding to the candidate project characteristics includes: The candidate project features are input into the job type determination model, and the job type determination model outputs the job type corresponding to the candidate project features. The candidate project features are input into the importance level determination model, and the importance level determination model outputs the importance level corresponding to the candidate project features. The job type determination model and the importance level determination model are respectively a multi-classification model and a binary classification model pre-trained based on labeled training samples; the training samples used to train the job type determination model and the importance level determination model are project features obtained by splitting the project feature text in the bill of quantities; the sample label corresponding to the job type determination model is the job type; and the sample label corresponding to the importance level determination model is the importance level.

5. The method according to claim 4, characterized in that, Before inputting the candidate item features into the importance level determination model and outputting the importance level corresponding to the candidate item features through the importance level determination model, the method further includes: Determine whether the job type corresponding to the candidate project feature belongs to the basic type; If the job type corresponding to the candidate project feature does not belong to the basic type, then the candidate project feature is input into the importance level determination model.

6. The method according to claim 1, characterized in that, The item feature text in the list to be split is split to obtain at least two candidate item features to be grouped, including: Based on the content identifiers in the list to be split, extract the project feature text from the list to be split; The feature separators in the project feature text are identified, and the location of the feature separators is determined as the segmentation location; Based on the segmentation position, the project feature text is split to obtain at least two candidate project features to be grouped.

7. A device for determining cost items based on bill of quantities splitting, characterized in that, The device includes: The project feature splitting module is used to split the project feature text in the list to be split, and obtain at least two candidate project features to be grouped. The feature attribute determination module is used to determine the job type and importance level corresponding to the candidate project features; wherein, the importance level is determined based on whether the candidate project features can independently explain the cost items involved in the list to be split. The project feature grouping module is used to group the candidate project features based on the job type and the importance level to obtain the project feature groups corresponding to the list to be split. The cost item determination module is used to determine the target cost item corresponding to the list to be split based on the project feature group.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the cost item determination method based on list splitting as described in any one of claims 1-6.

9. An electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the cost item determination method based on list splitting as described in any one of claims 1-6.

10. A computer program product comprising a computer program that, when executed by a processor, implements the cost item determination method based on list splitting as described in any one of claims 1-6.

Images