CN-121998570-A - Method, device, medium and equipment for processing project characteristics in engineering quantity list

CN121998570ACN 121998570 ACN121998570 ACN 121998570ACN-121998570-A

Abstract

The application discloses a processing method, a device, a medium and electronic equipment of project characteristics in an engineering quantity list, wherein the method comprises the steps of obtaining a target engineering quantity list to be processed, and determining a project characteristic group associated with the target engineering quantity list; the method comprises the steps of associating a project feature group with a job type, determining a keyword template corresponding to the job type, wherein the keyword template is a data structure defined with a keyword extraction rule under a specific job type, comprises a field list and a format specification, extracting keywords of the project feature group based on the keyword template to obtain feature keywords corresponding to the project feature group, and determining a target expense item corresponding to a target engineering quantity list based on the project feature group and the feature keywords corresponding to the project feature group. The application can extract the key information of project features in the engineering quantity list, ensure the parameter integrity, the structure normalization and the information accuracy, and is beneficial to improving the accuracy of determining the expense items.

Inventors

HONG PENG
WANG HUI
Han Aisheng

Assignees

杭州新中大科技股份有限公司

Dates

Publication Date: 20260508
Application Date: 20251117

Claims (10)

1. A method for processing project features in an engineering quantity list, the method comprising: acquiring a target engineering quantity list to be processed, and determining a project feature group associated with the target engineering quantity list, wherein the project feature group is associated with a job type; determining a keyword template corresponding to the operation type, wherein the keyword template is a data structure defined with a keyword extraction rule under a specific operation type, and comprises a field list and a format specification; extracting keywords from the project feature group based on the keyword template to obtain feature keywords corresponding to the project feature group; And determining a target expense item corresponding to the target engineering quantity list based on the project feature group and the feature keywords corresponding to the project feature group.
2. The method according to claim 1, wherein the keyword extraction of the item feature set based on the keyword template, to obtain feature keywords corresponding to the item feature set, includes: generating a keyword extraction prompt word for a keyword extraction model based on the item feature group and a keyword template corresponding to the item feature group; Extracting keywords from the project feature group by the keyword extraction model through the keyword extraction prompt words to obtain feature keywords corresponding to the project feature group; The keyword extraction model is obtained by fine-tuning a large language model based on a first sample with labels, the first sample is the item feature group, and a sample label of the first sample is a feature keyword extracted from the first sample based on the keyword template.
3. The method of claim 2, wherein generating a keyword extraction hint term for a keyword extraction model based on the set of item features and a keyword template corresponding to the set of item features comprises: obtaining a keyword record, wherein the keyword record comprises at least two sample feature groups and feature keywords extracted from the sample feature groups based on the keyword template; Determining text similarity between the item feature set and the sample feature set, and determining a target feature set from the sample feature set based on the text similarity; generating auxiliary prompt words based on the target feature group and feature keywords corresponding to the target feature group; generating a demand prompt word based on the project feature group and a keyword template corresponding to the project feature group; And generating a keyword extraction prompt word for a keyword extraction model based on the auxiliary prompt word and the demand prompt word.
4. The method of claim 1, wherein prior to the determining the target cost item corresponding to the target engineering quantity inventory based on the project feature set and the feature key corresponding to the project feature set, the method further comprises: Acquiring a correction request for the characteristic key words; correcting the feature keywords corresponding to the project feature groups based on the correction request and/or the operation types corresponding to the feature keywords to obtain new keywords; and updating the feature keywords corresponding to the project feature groups by adopting the new keywords.
5. The method of claim 4, wherein modifying the feature key corresponding to the item feature set to obtain a new key based on the job type corresponding to the feature key, comprises: If the operation type corresponding to the characteristic keyword belongs to a preset type, determining whether the characteristic keyword is a nonstandard keyword or not based on a keyword set corresponding to the preset type; if the feature keywords are the nonstandard keywords, inputting the item feature groups corresponding to the nonstandard keywords into a keyword correction model corresponding to the preset type; Outputting a standard keyword corresponding to the project feature group through the keyword correction model, and taking the standard keyword as the new keyword; the keyword correction model is a multi-classification model which is obtained by training based on a second sample with a label in advance, the second sample is a project feature group corresponding to the preset type, and the sample label of the second sample is a standard keyword corresponding to the second sample.
6. The method of claim 1, wherein the determining the target cost item corresponding to the target engineering quantity list based on the project feature set and the feature key corresponding to the project feature set comprises: acquiring a first corresponding relation between preset project features and candidate expense items and feature keywords corresponding to the preset project features; performing similarity matching on the item feature group and the preset item feature to obtain a first matching result; If the first matching result is that the matching is failed, performing similarity matching on the feature keywords corresponding to the item feature groups and the feature keywords corresponding to the preset item features to obtain a second matching result; if the second matching result is that the matching is successful, determining the preset project characteristic matched with the project characteristic set as a target project characteristic; And determining a target expense item corresponding to the item feature group from the candidate expense items based on the first corresponding relation and the target item feature.
7. The method of claim 1, wherein the determining the set of project features associated with the target engineering quantity inventory comprises: Splitting the project feature text of the target engineering quantity list to obtain at least two candidate project features to be grouped; determining the job type and the importance level corresponding to the candidate project feature, wherein the importance level is determined based on whether the candidate project feature can independently describe a cost item related to the target engineering quantity list; And grouping the candidate project features based on the job type and the importance level to obtain a project feature group corresponding to the target engineering quantity list.
8. A processing device for item features in an engineering quantity list, the device comprising: The job type determining module is used for acquiring a target engineering quantity list to be processed and determining a project characteristic group associated with the target engineering quantity list, wherein the project characteristic group is associated with a job type; the system comprises a keyword template determining module, a keyword template processing module and a processing module, wherein the keyword template determining module is used for determining a keyword template corresponding to the operation type, wherein the keyword template is a data structure defined with a keyword extraction rule under a specific operation type; the keyword extraction module is used for extracting keywords of the project feature group based on the keyword template to obtain feature keywords corresponding to the project feature group; And Fei Yongxiang determining a target cost item corresponding to the target engineering quantity list based on the project feature group and the feature keywords corresponding to the project feature group.
9. A computer-readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements a method for processing item features in an engineering quantity list according to any one of claims 1-7.
10. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements a method for processing item features in an engineering quantity list according to any one of claims 1-7 when the computer program is executed by the processor.

Description

Method, device, medium and equipment for processing project characteristics in engineering quantity list Technical Field The present application relates to the field of construction engineering management and construction engineering data processing, and in particular, to a method, an apparatus, a medium, and an electronic device for processing project features in an engineering quantity list. Background In the field of engineering cost management, the core of accurately generating the cost item corresponding to the engineering quantity list is to effectively extract key information in item characteristics. The project features are used as technical description carriers of the list items, and directly determine the constituent elements and parameters of cost items such as manpower, materials, machinery and the like. At present, information extraction methods based on traditional natural language processing technology are commonly adopted in the industry, such as solid extraction and grammar analysis, and an attempt is made to extract key information from project features of an engineering quantity list. However, the information extraction method has the problems of missing parameter details, unfixed format and insufficient information accuracy when processing the engineering quantity list, and further severely restricts the accuracy and reliability of the subsequent fee item determination. Disclosure of Invention The application provides a processing method, a processing device, a medium and electronic equipment for project characteristics in an engineering quantity list, which can achieve the purposes of ensuring parameter integrity, structure standardization and information accuracy and improving accuracy of cost item determination. According to a first aspect of the present application, there is provided a method of processing item features in an engineering quantity list, the method comprising: acquiring a target engineering quantity list to be processed, and determining a project feature group associated with the target engineering quantity list, wherein the project feature group is associated with a job type; determining a keyword template corresponding to the operation type, wherein the keyword template is a data structure defined with a keyword extraction rule under a specific operation type, and comprises a field list and a format specification; extracting keywords from the project feature group based on the keyword template to obtain feature keywords corresponding to the project feature group; And determining a target expense item corresponding to the target engineering quantity list based on the project feature group and the feature keywords corresponding to the project feature group. According to a second aspect of the present application, there is provided a processing apparatus for processing item features in an engineering quantity list, the apparatus comprising: The job type determining module is used for acquiring a target engineering quantity list to be processed and determining a project characteristic group associated with the target engineering quantity list, wherein the project characteristic group is associated with a job type; the system comprises a keyword template determining module, a keyword template processing module and a processing module, wherein the keyword template determining module is used for determining a keyword template corresponding to the operation type, wherein the keyword template is a data structure defined with a keyword extraction rule under a specific operation type; the keyword extraction module is used for extracting keywords of the project feature group based on the keyword template to obtain feature keywords corresponding to the project feature group; And Fei Yongxiang determining a target cost item corresponding to the target engineering quantity list based on the project feature group and the feature keywords corresponding to the project feature group. According to a third aspect of the present application, an embodiment of the present application provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a method for processing an item feature in an engineering quantity list according to an embodiment of the present application. According to a fourth aspect of the present application, an embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable by the processor, where the processor executes the computer program to implement a method for processing an item feature in an engineering quantity list according to the embodiment of the present application. According to a fifth aspect of the present application, embodiments of the present application provide a computer program product comprising a computer program which, when executed by a processor, implements a method of processing ite