Project cost index data governance method based on AI technology

Abstract

The invention belongs to the technical field of project cost index data governance, particularly relates to an AI technology-based project cost index data governance method, and aims to solve the problems that a single project and a unit project thereof need to be manually matched according to user requirements before a COS file is warehoused in the prior art, and a system cannot automatically adjust the sequence according to a set template; in order to solve the problems that in the prior art, in the prior art, the data can only judge collection subjects according to list codes and names, the automatic collection success rate is low, the error rate is high, a large amount of manual intervention is needed, and the user experience feeling is poor, the following scheme is provided, and the method comprises the following steps that S1, a treatment system is prepared and comprises a data collection module; according to the method, the single project and the unit project thereof can be automatically matched according to the user requirement in the COS file storage process, the sequence is automatically adjusted according to the established template, the data can be subjected to standardization processing, the automatic collection success rate is improved, the error rate is reduced, and the user experience is effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of engineering cost indicator data management, and in particular to an engineering cost indicator data management method based on AI technology. Background Art

[0002] The data governance methods for engineering cost indicators mainly include data collection, structured processing, weight distribution, dynamic factor correction and indicator index calculation.

[0003] In the existing technology, before the COS file is stored in the database, it is necessary to manually match the single project and its unit project according to user needs. The system cannot automatically adjust the order according to the established template, and the data can only be collected according to the list code and name. The success rate of automatic collection is low and the error rate is high. It requires a lot of manual intervention and the user experience is poor. For this reason, we propose an engineering cost indicator data governance method based on AI technology to solve the above problems. Summary of the invention

[0004] The purpose of the present invention is to solve the shortcomings of the prior art that single projects and their unit projects need to be manually matched according to user needs before COS files are stored in the database, the system cannot automatically adjust the order according to the established template, and the data can only be collected according to the list code and name to determine the collection subject, the automatic collection success rate is low, and the error rate is high, a large amount of manual intervention is required, and the user experience is relatively poor. A method for engineering cost indicator data management based on AI technology is proposed.

[0005] The engineering cost index data governance method based on AI technology provided in this application adopts the following technical solutions:

[0006] A method for engineering cost index data governance based on AI technology, comprising the following steps:

[0007] S1: Prepare a governance system, the governance system includes a data collection module, the data collection module is connected to a data management module and a historical data module, the historical data module is connected to a monitoring module, the monitoring module is connected to a visualization module, the visualization module is connected to a data management module, the data management module is connected to a data cleaning module, the data cleaning module is connected to a data maintenance module and an AI recognition module, the data maintenance module is connected to a security module, the security module is connected to a backup module, the backup module is connected to a feedback module, the feedback module is connected to an optimization module, the optimization module is connected to an update module, the AI ​​recognition module is connected to a knowledge base module, a combination module and a sharing module, the combination module is connected to an automatic matching module, the automatic matching module is connected to a warehousing module, and the sharing module is connected to a recording module and a publishing platform module;

[0008] S2: First, the data collection module is used to collect the engineering cost data, clarify the data source, and standardize the data. The data management module is used to complete data import, export and storage. The data cleaning module cleans the collected engineering cost data and removes invalid data. The data maintenance module is used to regularly update and maintain the data, and the security module and backup module are used to control access to and back up the data.

[0009] S3: Then, the AI ​​recognition module collects the processed data and recognizes the data through AI technology. The combination module combines the data into a complete single project, and the automatic matching module automatically matches it to a professional project. The storage module then processes the data. At the same time, the sharing module uploads the project cost data to the publishing platform module for sharing. The recording module records the shared data in real time.

[0010] S4: Finally, a feedback mechanism for data governance is established through the feedback module to collect opinions and suggestions from users and stakeholders. Based on the feedback and suggestions, the data governance process is continuously optimized through the optimization module, and the governance technology and methods are updated in real time through the update module.

[0011] Furthermore, the data cleaning module includes a verification unit and an invalid processing unit, and the verification unit is connected to the invalid processing unit.

[0012] Furthermore, the historical data module includes a receiving unit, a machine learning unit and a prediction unit, the receiving unit is connected to the machine learning unit, the machine learning unit is connected to the prediction unit, and the historical data module is used to analyze historical data to predict engineering costs.

[0013] Furthermore, the security module includes a data encryption unit, an access control unit and an audit log unit. The data encryption unit is connected to the access control unit, and the access control unit is connected to the audit log unit. The security module is used to encrypt data and perform access control.

[0014] Furthermore, the AI ​​recognition module is used to identify the processed engineering cost data through AI technology, and to combine the data into a complete single project through the combination module, and the automatic matching module is used to automatically match the data to a professional project.

[0015] Furthermore, the data collection module is used to collect engineering cost data and determine the data source, and the data cleaning module is used to clean the collected data to remove errors and invalid data.

[0016] Furthermore, the sharing module includes an input unit, a unified coding unit and an upload unit, the input unit is connected to the unified coding unit, the unified coding unit is connected to the upload unit, and the sharing module is used to exchange and share the engineering cost data.

[0017] Furthermore, the monitoring module includes a monitoring unit, an analyzing unit and an abnormality handling unit. The monitoring unit is connected to the analyzing unit, and the analyzing unit is connected to the abnormality warning unit. The monitoring module is used to monitor the data processing flow in real time.

[0018] Furthermore, the data collection module includes a source identification unit and an integration unit, and the source identification unit is connected to the integration unit.

[0019] Furthermore, the data management module includes an import unit, an export unit and a storage unit, the import unit is connected to the export unit, the export unit is connected to the storage unit, and the data management module is used to provide data management functions.

[0020] In summary, the present application includes at least one of the following beneficial technical effects:

[0021] 1. This solution uses the AI ​​recognition module to identify the unit projects under the project using AI technology, and combines them into complete single projects through the combination module. The automatic matching module can automatically match professional projects, reducing the steps of manual adjustment and improving the efficiency of warehousing;

[0022] 2. This solution collects engineering cost data and determines the data source through the setting of data collection module. According to the set rules, non-standard project feature descriptions and material names can be standardized.

[0023] The present invention can automatically match single projects and their unit projects according to user needs during the COS file storage process, automatically adjust the order according to the established template, and can standardize the data, thereby improving the success rate of automatic aggregation, reducing the error rate, and effectively improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 This is a structural block diagram of the management system in the engineering cost index data management method based on AI technology proposed by the present invention;

[0025] Figure 2 This is a structural block diagram of a data management module in an engineering cost index data management method based on AI technology proposed by the present invention;

[0026] Figure 3 This is a structural block diagram of a data cleaning module in an engineering cost index data management method based on AI technology proposed by the present invention;

[0027] Figure 4 This is a structural block diagram of a data collection module in an engineering cost index data management method based on AI technology proposed by the present invention;

[0028] Figure 5 This is a structural block diagram of the historical data module in the engineering cost index data management method based on AI technology proposed by the present invention;

[0029] Figure 6 This is a structural block diagram of a monitoring module in a method for engineering cost index data management based on AI technology proposed by the present invention;

[0030] Figure 7 This is a structural block diagram of the security module in the engineering cost index data management method based on AI technology proposed by the present invention;

[0031] Figure 8 This is a structural block diagram of a shared module in an engineering cost index data management method based on AI technology proposed by the present invention;

[0032] Fig. 9 This is a storage logic diagram of the automatic matching module in the engineering cost index data management method based on AI technology proposed by the present invention;

[0033] Fig.10 This is a logical diagram of the storage of the data collection module in the engineering cost indicator data management method based on AI technology proposed in the present invention. DETAILED DESCRIPTION

[0034] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0035] Embodiment 1

[0036] Reference Figure 1-Figure 10 , a method for engineering cost index data governance based on AI technology, comprising the following steps:

[0037] S1: Prepare a governance system. The governance system includes a data collection module. The data collection module is connected to a data management module and a historical data module. The historical data module is connected to a monitoring module. The monitoring module is connected to a visualization module. The visualization module is connected to a data management module. The data management module is connected to a data cleaning module. The data cleaning module is connected to a data maintenance module and an AI recognition module. The data maintenance module is connected to a security module. The security module is connected to a backup module. The backup module is connected to a feedback module. The feedback module is connected to an optimization module. The optimization module is connected to an update module. The AI ​​recognition module is connected to a knowledge base module, a combination module and a sharing module. The combination module is connected to an automatic The automatic matching module is connected with the storage module, the sharing module is connected with the recording module and the publishing platform module, the data management module includes an import unit, an export unit and a storage unit, the import unit is connected with the export unit, the export unit is connected with the storage unit, the data management module is used to provide data management functions, the data cleaning module includes a verification unit and an invalid processing unit, the verification unit is connected with the invalid processing unit, the data collection module includes a source identification unit and an integration unit, the source identification unit is connected with the integration unit, the knowledge base module adopts a word vector model, which can improve the efficiency and accuracy of automatic data collection and reduce manual intervention, and the word vector model adopts BERT word vector;

[0038] BERT word vector

[0039] BERT (Bidirectional Encoder Representations from Transformers) is a natural language processing model. Its core is word vector representation. BERT uses a bidirectional Transformer architecture to understand the meaning of words in different contexts.

[0040] The calculation formula of BERT word vector is as follows:

[0041] BERT word vector = [CLS] vector + vector of each word;

[0042] The [CLS] vector is the vector representing the entire sentence, and the vectors of each word are based on

[0043] The input words are learned in different contexts. BERT uses a mask-based language modeling task. It trains the model by masking some words so that it can learn the meaning of words in the context. The dimension of BERT word vector is usually 768 dimensions, which can be used for a variety of natural language processing tasks.

[0044] S2: First, the engineering cost data is collected through the data collection module, the data source is clarified, and the data is standardized. The data management module is used to complete data import, export and storage. The data cleaning module cleans the collected engineering cost data and removes invalid data. The data maintenance module regularly updates and maintains the data, and the security module and backup module perform access control and backup on the data. The AI ​​recognition module is used to identify the processed engineering cost data through AI technology, and the combination module combines the data into a complete single project. The automatic matching module is used to automatically match the data to professional projects. The data collection module is used to collect engineering cost data and determine the data source. The data cleaning module is used to clean the collected data and remove errors and invalid data;

[0045] S3: Then, the AI ​​recognition module collects the processed data and recognizes the data through AI technology. The combination module combines the data into a complete single project, and the automatic matching module automatically matches it to a professional project. The storage module then processes the data. At the same time, the sharing module uploads the project cost data to the publishing platform module for sharing. The recording module records the shared data in real time.

[0046] S4: Finally, a feedback mechanism for data governance is established through the feedback module to collect opinions and suggestions from users and stakeholders. Based on the feedback and suggestions, the data governance process is continuously optimized through the optimization module, and the governance technology and methods are updated in real time through the update module.

[0047] Reference Figure 5-Figure 8 ,The historical data module includes a receiving unit, a machine learning unit and a prediction unit. The receiving unit is connected with the machine learning unit, and the prediction unit. The historical data module is used to analyze the historical data for engineering cost prediction. The machine learning unit adopts a random forest algorithm;

[0048] Random Forest Algorithm:

[0049] Random forest is an ensemble machine learning algorithm that consists of multiple decision trees, each of which is grown based on a random subset of the data and a random subset of the features. The final prediction is made by averaging or voting the predictions of all the trees in the forest. Specifically, the mathematical formula for random forest can be expressed as:

[0050]

[0051] Among them, F(x) represents the output of the random forest, T represents the number of decision trees in the random forest, and ft(x) represents the output of the tth decision tree. This formula combines the results of all decision trees, averages (or votes) the results of each decision tree, and selects the result with the most votes as the final output;

[0052] The monitoring module includes a monitoring unit, an analysis unit and an exception handling unit. The monitoring unit is connected to the analysis unit, and the analysis unit is connected to the exception warning unit. The monitoring module is used to monitor the data processing flow in real time. The security module includes a data encryption unit, an access control unit and an audit log unit. The data encryption unit is connected to the access control unit, and the access control unit is connected to the audit log unit. The security module is used to encrypt data and control access. The sharing module includes an entry unit, a unified coding unit and an upload unit. The entry unit is connected to the unified coding unit, and the unified coding unit is connected to the upload unit. The sharing module is used to exchange and share engineering cost data.

[0053] The implementation principle in this embodiment is as follows: when in use, the engineering cost data is collected through the data collection module, the data source is clarified, and the data is standardized; the data import, export and storage are completed through the data management module; the data cleaning module cleans the collected engineering cost data and removes invalid data; the data maintenance module regularly updates and maintains the data; the security module and the backup module perform access control and backup on the data; the AI ​​recognition module is used to identify the processed engineering cost data through AI technology, and combine the data into a complete single project through the combination module; the automatic matching module is used to automatically match the data to the professional project; the data collection module is used to collect the engineering cost data and determine the data source; the data The cleaning module is used to clean the collected data and remove errors and invalid data. Then, the AI ​​recognition module collects the processed data and identifies the data through AI technology. The combination module combines the data into a complete single project, and automatically matches it to a professional project through the automatic matching module. The data is then stored and collected through the warehousing module. At the same time, the project cost data is uploaded to the publishing platform module for sharing through the sharing module, and the recording module records the shared data in real time. Finally, a feedback mechanism for data governance is established through the feedback module to collect opinions and suggestions from users and stakeholders. According to the feedback and suggestions, the data governance process is continuously optimized through the optimization module, and the governance technology and methods are updated in real time through the update module.

[0054] Embodiment 2

[0055] The difference between this embodiment and the first embodiment is that the data management module is connected to the data mining module, and the data mining uses the data mining algorithm to analyze the engineering cost data, discover the potential rules and trends in the data, and provide strong support for engineering cost decision-making.

[0056] Embodiment 3

[0057] The difference between this embodiment and the second embodiment is that the data management module is connected to the report generation module, and the report generation module supports the generation of various data reports to provide a decision-making basis for engineering cost management.

[0058] Embodiment 4

[0059] The difference between this embodiment and the third embodiment is that the data management module is connected to an operation guidance module, which can guide the user to operate and use, thereby improving the efficiency of engineering cost indicator data management.

[0060] Embodiment 5

[0061] The difference between this embodiment and the fourth embodiment is that the data management module is connected to the expansion module, and the expansion module can be integrated with other engineering cost management systems and has good expansibility.

[0062] Experimental example

[0063] By comparing the engineering cost index data management solutions proposed in Examples 1 to 5 with the conventional engineering cost index data management solutions, the experimental data are as follows:

[0064]

[0065] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A method for engineering cost index data management based on AI technology, characterized by: The following steps are involved: S1: Prepare a governance system, the governance system includes a data collection module, the data collection module is connected to a data management module and a historical data module, the historical data module is connected to a monitoring module, the monitoring module is connected to a visualization module, the visualization module is connected to a data management module, the data management module is connected to a data cleaning module, the data cleaning module is connected to a data maintenance module and an AI recognition module, the data maintenance module is connected to a security module, the security module is connected to a backup module, the backup module is connected to a feedback module, the feedback module is connected to an optimization module, the optimization module is connected to an update module, the AI ​​recognition module is connected to a knowledge base module, a combination module and a sharing module, the combination module is connected to an automatic matching module, the automatic matching module is connected to a warehousing module, and the sharing module is connected to a recording module and a publishing platform module; S2: First, the data collection module is used to collect the engineering cost data, clarify the data source, and standardize the data. The data management module is used to complete data import, export and storage. The data cleaning module cleans the collected engineering cost data and removes invalid data. The data maintenance module is used to regularly update and maintain the data, and the security module and backup module are used to control access to and back up the data. S3: Then, the AI ​​recognition module collects the processed data and recognizes the data through AI technology. The combination module combines the data into a complete single project, and the automatic matching module automatically matches it to a professional project. The storage module then processes the data. At the same time, the sharing module uploads the project cost data to the publishing platform module for sharing. The recording module records the shared data in real time. S4: Finally, a feedback mechanism for data governance is established through the feedback module to collect opinions and suggestions from users and stakeholders. Based on the feedback and suggestions, the data governance process is continuously optimized through the optimization module, and the governance technology and methods are updated in real time through the update module.

2. According to the method for engineering cost index data management based on AI technology in claim 1, it is characterized by: The data management module includes an import unit, an export unit and a storage unit. The import unit is connected to the export unit, and the export unit is connected to the storage unit. The data management module is used to provide data management functions.

3. According to claim 2, a method for engineering cost index data management based on AI technology is characterized by: The data cleaning module includes a verification unit and an invalid processing unit, and the verification unit is connected to the invalid processing unit.

4. According to the method for engineering cost index data management based on AI technology in claim 3, it is characterized by: The data collection module includes a source identification unit and an integration unit, and the source identification unit is connected to the integration unit.

5. According to claim 4, a method for engineering cost index data management based on AI technology is characterized in that: The historical data module includes a receiving unit, a machine learning unit and a prediction unit. The receiving unit is connected to the machine learning unit, and the machine learning unit is connected to the prediction unit. The historical data module is used to analyze historical data to predict the project cost.

6. According to the method for engineering cost index data management based on AI technology in claim 5, it is characterized by: The monitoring module includes a monitoring unit, an analyzing unit and an abnormality processing unit. The monitoring unit is connected to the analyzing unit, and the analyzing unit is connected to the abnormality warning unit. The monitoring module is used to monitor the data processing flow in real time.

7. According to claim 6, a method for engineering cost index data management based on AI technology is characterized by: The security module includes a data encryption unit, an access control unit and an audit log unit. The data encryption unit is connected to the access control unit, and the access control unit is connected to the audit log unit. The security module is used to encrypt data and perform access control.

8. According to claim 7, a method for engineering cost index data management based on AI technology is characterized in that: The sharing module includes an input unit, a unified coding unit and an upload unit. The input unit is connected to the unified coding unit, and the unified coding unit is connected to the upload unit. The sharing module is used to exchange and share engineering cost data.

9. The method for engineering cost index data management based on AI technology according to claim 8 is characterized by: The AI ​​recognition module is used to identify the processed engineering cost data through AI technology, and to combine the data into a complete single project through the combination module. The automatic matching module is used to automatically match the data to a professional project.

10. The method for engineering cost index data management based on AI technology according to claim 9 is characterized in that: The data collection module is used to collect engineering cost data and determine the data source, and the data cleaning module is used to clean the collected data and remove errors and invalid data.

Images