CN114049095A - Infrastructure construction business monitoring method, device, equipment and storage medium - Google Patents
Infrastructure construction business monitoring method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN114049095A CN114049095A CN202111405038.3A CN202111405038A CN114049095A CN 114049095 A CN114049095 A CN 114049095A CN 202111405038 A CN202111405038 A CN 202111405038A CN 114049095 A CN114049095 A CN 114049095A
- Authority
- CN
- China
- Prior art keywords
- service
- infrastructure
- data
- business
- processed
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 177
- 238000009440 infrastructure construction Methods 0.000 title claims abstract description 71
- 238000000034 method Methods 0.000 title claims abstract description 55
- 238000010276 construction Methods 0.000 claims abstract description 53
- 238000012549 training Methods 0.000 claims description 46
- 230000000694 effects Effects 0.000 claims description 13
- 238000012806 monitoring device Methods 0.000 claims description 9
- 238000010586 diagram Methods 0.000 claims description 5
- 230000008569 process Effects 0.000 description 13
- 230000006870 function Effects 0.000 description 7
- 238000002372 labelling Methods 0.000 description 6
- 238000000605 extraction Methods 0.000 description 5
- 238000001514 detection method Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000012552 review Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000013075 data extraction Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/103—Workflow collaboration or project management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/08—Construction
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Data Mining & Analysis (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Primary Health Care (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Game Theory and Decision Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention discloses a method, a device, equipment and a storage medium for monitoring infrastructure construction business. The method comprises the following steps: acquiring to-be-processed service data and a capital construction service label corresponding to the to-be-processed service data; the business data to be processed comprises at least one of unstructured documents to be processed and pictures to be processed; and inputting the service data to be processed and the corresponding infrastructure service label into a preset service monitoring network model, and determining a service monitoring result according to an output result of the service monitoring network model. According to the technical scheme of the embodiment of the invention, the service monitoring network model automatically determines the problems existing in the service data according to the corresponding service rules in the infrastructure service labels, so that the problem that the service problem determination in the traditional infrastructure engineering needs manual participation and judgment, the large time and the labor cost are consumed is solved, the requirement on the quality of unstructured data in the service data is reduced, and the infrastructure engineering service monitoring efficiency and the problem determination accuracy are improved.
Description
Technical Field
The embodiment of the invention relates to the technical field of data processing, in particular to a method, a device, equipment and a storage medium for monitoring infrastructure construction business.
Background
With the continuous promotion of national recovery economic measures, a plurality of large-scale capital construction project constructions are continuously started to respond to strategic requirements of national 'new capital construction' and the like. However, most of the data in the whole construction process of the infrastructure construction project are submitted offline, the workload of manual review is huge, and huge workload is caused for relevant departments to review and supervise the progress of the project, review the quality of the project and manage and control the safety of the project.
At present, although the construction site generally builds high-definition camera equipment, can all-round monitoring and management and control job site operation, these monitoring means still need the monitoring personnel to spend equal time and give artifical judgement to the problem that exists and then solve the problem in the discovery work progress, does not obtain fundamental promotion and change in efficiency.
Meanwhile, project documents in the infrastructure construction project are often unstructured documents with various formats, which greatly affects the accuracy of data labeling and extraction in the documents, and if the documents and video image information collected in the infrastructure construction project are completely processed in a semi-automatic mode, the accuracy of identification results is difficult to guarantee, so that the problems existing in the construction process cannot be accurately determined, and the safety of service implementation in the infrastructure construction project is greatly affected.
Disclosure of Invention
The invention provides a method, a device, equipment and a storage medium for monitoring a construction project service, which are used for directly determining problems existing in the execution process of the project according to unstructured service data in the construction project without manual judgment, reducing the labor cost of service monitoring in the construction project and improving the efficiency of service monitoring and the safety in the construction of the construction project.
In a first aspect, an embodiment of the present invention provides a method for monitoring infrastructure engineering services, including:
acquiring to-be-processed service data and a capital construction service label corresponding to the to-be-processed service data; the business data to be processed comprises at least one of unstructured documents to be processed and pictures to be processed;
and inputting the service data to be processed and the corresponding infrastructure service label into a preset service monitoring network model, and determining a service monitoring result according to an output result of the service monitoring network model.
Further, acquiring the service data to be processed includes:
acquiring original platform service data;
extracting infrastructure construction business data in the original platform business data according to the business data type;
extracting service information in the capital construction project service data;
and marking the infrastructure construction business data by utilizing the business information, and determining the marked infrastructure construction business data as the business data to be processed.
Further, the infrastructure service label is a service activity or logic entity with the minimum granularity in the infrastructure project, which is determined according to the five-in-one flow chart.
Further, the training step of the service monitoring network model comprises:
acquiring at least one group of sample service data corresponding to each infrastructure service label in infrastructure construction;
extracting sample service information in the sample service data, marking the sample service data by using the sample service information, and determining the marked sample service data as target sample service data;
constructing a training sample set according to each infrastructure service label and target sample service data corresponding to each infrastructure service label;
and training the initial service monitoring network model through the training sample set until a preset convergence condition is met to obtain the service monitoring network model.
Further, constructing a training sample set according to each infrastructure service label and target sample service data corresponding to each infrastructure service label, including:
calibrating the service problems in the service data of each target sample according to the service rules corresponding to each infrastructure service label, and determining the calibrated service data of the target sample as the service data of the calibration sample;
determining target sample service data corresponding to the same infrastructure service label as a target sample service data set, and determining corresponding calibration sample service data as a calibration sample service data set;
and determining each infrastructure service label, and each corresponding target sample service data set and each calibration sample service data set as a training sample set.
Further, inputting the service data to be processed and the corresponding infrastructure service tag into a preset service monitoring network model, including:
inputting the service data to be processed and the corresponding infrastructure service label into a preset service monitoring network model;
and determining a service problem in the service data to be processed according to the service rule corresponding to the infrastructure service label, and determining the service problem as an output result of the service monitoring network model.
Further, after determining the service monitoring result according to the output result of the service monitoring network model, the method further includes:
and generating a service problem alarm according to the service monitoring result, and carrying out corresponding alarm prompt according to the service problem alarm.
In a second aspect, an embodiment of the present invention further provides a device for monitoring infrastructure construction business, including:
the data acquisition module is used for acquiring the service data to be processed and the infrastructure service tag corresponding to the service data to be processed; the business data to be processed comprises at least one of unstructured documents to be processed and pictures to be processed;
and the monitoring result determining module is used for inputting the service data to be processed and the corresponding infrastructure service labels into a preset service monitoring network model and determining a service monitoring result according to the output result of the service monitoring network model.
In a third aspect, an embodiment of the present invention further provides infrastructure engineering service monitoring equipment, including:
a storage device and one or more processors;
storage means for storing one or more programs;
when the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the infrastructure traffic monitoring method as described above in the first aspect.
In a fourth aspect, an embodiment of the present invention further provides a storage medium containing computer-executable instructions, which when executed by a computer processor, are configured to perform the infrastructure traffic monitoring method according to the first aspect.
The embodiment of the invention provides a method, a device, equipment and a storage medium for monitoring infrastructure construction engineering business, which are characterized in that to-be-processed business data and infrastructure construction business labels corresponding to the to-be-processed business data are obtained; the business data to be processed comprises at least one of unstructured documents to be processed and pictures to be processed; and inputting the service data to be processed and the corresponding infrastructure service label into a preset service monitoring network model, and determining a service monitoring result according to an output result of the service monitoring network model. By adopting the technical scheme, the business data to be processed containing at least one content of the unstructured documents and pictures and the corresponding infrastructure business labels are input into the pre-trained business monitoring network model, the business data to be monitored are matched with the more professional infrastructure business labels before being input, and the business data are determined by the business monitoring network model according to the corresponding business rules in the infrastructure business labels, so that the problem that the business problem determination in the traditional infrastructure engineering needs manual participation and judgment, a large amount of time and labor cost are consumed is solved, the requirement on the quality of unstructured data in the business data is lowered, the infrastructure engineering business monitoring efficiency and the problem determination accuracy are improved, and the infrastructure engineering construction safety is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.
Fig. 1 is a flowchart of a method for monitoring infrastructure construction business in a first embodiment of the present invention;
fig. 2 is a flowchart of a method for monitoring infrastructure construction business in the second embodiment of the present invention;
fig. 3 is a flowchart of a method for training a service monitoring network model according to a second embodiment of the present invention;
fig. 4 is a schematic flowchart of a second embodiment of the present invention, where a training sample set is constructed according to each infrastructure service tag and target sample service data corresponding to each infrastructure service tag;
fig. 5 is a schematic structural diagram of a infrastructure engineering business monitoring apparatus in a third embodiment of the present invention;
fig. 6 is a schematic structural diagram of infrastructure engineering business monitoring equipment in a fourth embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be described in detail with reference to the accompanying drawings. It should be understood that the described embodiments are only some embodiments of the invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example one
Fig. 1 is a flowchart of a infrastructure construction business monitoring method according to an embodiment of the present invention, where the embodiment is applicable to a situation where business problems are automatically monitored on unstructured business data in a infrastructure construction, the method may be executed by a infrastructure construction business monitoring device, the infrastructure construction business monitoring device may be implemented by software and/or hardware, the infrastructure construction business monitoring device may be configured on infrastructure construction business monitoring equipment, the infrastructure construction business basic data may be computer equipment, and the computer equipment may be composed of two or more physical entities or may be composed of one physical entity. In general, the computer device may be a notebook, a desktop level smart tablet, and the like.
As shown in fig. 1, a method for monitoring infrastructure engineering services provided in this embodiment specifically includes the following steps:
s101, acquiring to-be-processed business data and a capital construction business label corresponding to the to-be-processed business data.
The business data to be processed comprises at least one of unstructured documents to be processed and pictures to be processed.
The capital construction business label is a business activity or logic entity with the minimum granularity in the capital construction project, which is determined according to the five-in-one flow chart.
In this embodiment, the service data to be processed may be specifically understood as service data used for monitoring the project progress, the project quality, and the project safety during the execution of the infrastructure project. The to-be-processed unstructured document may be specifically understood as a data document with an irregular or incomplete data structure in the infrastructure engineering and a larger difference from a standard document template format, for example, the to-be-processed unstructured document may be a project contract in the infrastructure engineering or a permission request sheet in a project process, where the types of the documents are merely examples, and the embodiment of the present invention is not limited thereto. The picture to be processed can be specifically understood as a construction site operation image acquired by high-definition camera equipment arranged on a construction site in capital construction, wherein the construction site operation image can comprise service information such as construction equipment information, construction date information and construction unit information. The infrastructure service label can be specifically understood as a service activity or logic entity which is determined according to a five-in-one flow chart serving as a basis in a 'five-in-one' cooperative mechanism of a national power grid and is used for representing the minimum granularity in the infrastructure project according to the checking relationship between different services in each stage in the execution of a professional project in the infrastructure project and the incidence relationship between a construction site picture and a project and equipment, wherein the checking relationship is determined according to the content related to the infrastructure project.
It should be clear that one infrastructure service tag may correspond to one or more unstructured documents and pictures, that is, the unstructured documents and pictures corresponding to the infrastructure service tag may be understood as documents and pictures involved in performing a service activity corresponding to the infrastructure service tag or applying to a logical entity corresponding to the infrastructure service tag. Similarly, an unstructured document and picture may also correspond to one or more infrastructure service tags, and be represented for different dimensions. Exemplarily, business activities such as an signing process and qualification approval can be included in the project early stage of the infrastructure project, contract signing in the signing process can be understood as a infrastructure business tag, and the related contract is an unstructured document corresponding to the infrastructure business tag; if the construction of the transformer is involved in the construction process, the transformer is a logic entity corresponding to the capital construction service label, the contract related to the transformer is a corresponding unstructured document, and the construction photo of the transformer is a corresponding picture.
Specifically, in the process of constructing a project, the business performed therein needs to be monitored to ensure the correct completion of project tasks and ensure the safe performance of the project. When monitoring the service, the service data related to the infrastructure project is acquired from the integrated system platform containing different kinds of service information, the service data to be monitored is selected as the service data to be processed, and meanwhile, because the service data and the infrastructure service label used for representing the service activity or logic entity in the infrastructure project have a corresponding relation, the infrastructure service label corresponding to the service data to be monitored can be determined according to the acquired service data to be processed.
In the embodiment of the invention, the service data to be monitored is matched with the nearest infrastructure service label for the service data determined according to the five-in-one flow chart and corresponding to the service activity or logic entity with the minimum granularity in the infrastructure, and different service activities corresponding to different infrastructure service labels have different service rules and different work execution concerns of different logic entities, so that the monitoring of the service data to be processed is more targeted, and the accuracy of the monitoring of the infrastructure service is improved. And the infrastructure service label is the finest granularity in the infrastructure project, so that the omission of services with less frequency in the infrastructure project is avoided, and the integrity of service monitoring is improved.
S102, inputting the service data to be processed and the corresponding infrastructure service labels into a preset service monitoring network model, and determining a service monitoring result according to an output result of the service monitoring network model.
In this embodiment, the preset traffic monitoring network model may be understood as a neural network model trained in advance by using a set training method. Further, the service monitoring network model may be specifically understood as a neural network model for determining a service problem existing in the input to-be-processed service data according to a service rule in the input infrastructure service tag. The service monitoring result can be specifically understood as a monitoring report which is determined according to the output result of the service monitoring network model and contains the service problem in the service data to be processed.
Specifically, the service data to be processed and the corresponding infrastructure service tags are input into a trained preset service monitoring network model, the preset service monitoring network model processes or compares the unstructured document to be processed and/or the picture to be processed in the service data to be processed according to the service rules corresponding to the infrastructure service tags to determine whether a service problem exists, if so, the service problem is calibrated, the calibrated service data is used as an output result of the service monitoring network model, if not, the preset output result without the service problem is output, and the service monitoring result corresponding to the service data to be processed is determined according to the output result.
In the embodiment of the invention, the business data to be processed and the infrastructure business label corresponding to the business data to be processed are obtained; the business data to be processed comprises at least one of unstructured documents to be processed and pictures to be processed; and inputting the service data to be processed and the corresponding infrastructure service label into a preset service monitoring network model, and determining a service monitoring result according to an output result of the service monitoring network model. By adopting the technical scheme, the business data to be processed containing at least one content of the unstructured documents and pictures and the corresponding infrastructure business labels are input into the pre-trained business monitoring network model, the business data to be monitored are matched with the more professional infrastructure business labels before being input, and the business data are determined by the business monitoring network model according to the corresponding business rules in the infrastructure business labels, so that the problem that the business problem determination in the traditional infrastructure engineering needs manual participation and judgment, a large amount of time and labor cost are consumed is solved, the requirement on the quality of unstructured data in the business data is lowered, the infrastructure engineering business monitoring efficiency and the problem determination accuracy are improved, and the infrastructure engineering construction safety is improved.
Example two
Fig. 2 is a flowchart of a infrastructure construction business monitoring method provided by the second embodiment of the present invention, the technical solution of the second embodiment of the present invention is further optimized based on the above optional technical solutions, the business data about infrastructure construction is obtained from the original platform business data, then the infrastructure construction business data is labeled according to the business information and the labeled data is determined as the business data to be processed, since the label already contains the main information in the unstructured infrastructure construction business data, it is not necessary to consider the information extraction pressure caused by the unstructured service data after the business data is used as the business data to be processed, and meanwhile, after the business data to be processed and the corresponding infrastructure construction business label are input into the preset business monitoring network model, the business monitoring network model determines the business problem in the business data to be processed according to the business rules corresponding to the infrastructure construction business label and outputs the business problem as the output result of the business monitoring network model, and after the service detection result is determined, a corresponding service problem alarm can be generated according to the service detection result to carry out corresponding alarm prompt, so that the service problem can be timely alarmed while the infrastructure construction project service monitoring efficiency is improved, the service problem can be timely solved, and the safety of infrastructure construction project construction is improved.
Furthermore, before the infrastructure construction business monitoring, a business monitoring network model needs to be trained first, fig. 3 is a flowchart of a method for training a service monitoring network model according to a second embodiment of the present invention, which shows the steps of training the service monitoring network model, obtaining at least one group of sample service data corresponding to each infrastructure service label in the infrastructure project, labeling the sample service data according to the sample service information in the sample service data to obtain labeled target sample service data, further, a training sample set is constructed according to each basic construction business label and corresponding target sample business data, the initial business monitoring network model is trained through the training sample set, and in the training process, the weight parameters in the network layer are adjusted for each god of the initial service monitoring network model until the service monitoring network model meeting the preset convergence condition is determined. The trained service monitoring network model can automatically calibrate the service problems of the to-be-processed service data and the infrastructure service labels input into the service monitoring network model, and the monitoring efficiency of infrastructure engineering services and the accuracy of determining the service problems are improved.
As shown in fig. 3, a method for training a service monitoring network model according to a second embodiment of the present invention specifically includes the following steps:
s301, at least one group of sample service data corresponding to each infrastructure service label in the infrastructure project is obtained.
In this embodiment, the sample service data may be specifically understood as an unstructured document corresponding to a service activity or a logic entity corresponding to a infrastructure service tag acquired in the stages of starting, establishing items, tendering and bidding, performing contract, constructing, completing acceptance check and the like of a infrastructure professional project in a infrastructure project, or a picture corresponding to a service activity or a logic entity corresponding to a infrastructure service tag determined in basic information such as project and data by monitoring screenshot data through a field camera of the infrastructure project, where the unstructured document, the picture and the infrastructure service tag have a corresponding relationship, and have a good representativeness, and may be used as a sample to train a model.
S302, extracting sample service information in the sample service data, marking the sample service data by using the sample service information, and determining the marked sample service data as target sample service data.
In this embodiment, the sample service information may be specifically understood as information corresponding to the sample service data and used for representing main content included in the sample service data, and the sample service information may be obtained by preprocessing the sample service data through image recognition, character recognition, and the like. For example, if the sample business data is business data of an unstructured document type, the sample business information contained therein may be a project name, a construction period length, a start/stop date, a construction unit, a construction object, construction equipment, and the like; if the sample service data is the service data of the picture type, the sample service information included therein may be a project name, a shooting date, a construction unit, a construction object, construction equipment, and the like, and the sample service information is only a part of examples, which is not limited in this embodiment of the present invention.
Specifically, according to sample service information extracted from sample service data, corresponding service information tags are generated, the sample service data are labeled by using each service information tag, and the labeled sample service data are determined as target sample service data, wherein the service information tags can include intelligent tags, character remarks and other forms.
In the embodiment of the invention, the sample business data is marked through the sample business information, so that the main information contained in the sample business data can be clearly embodied, and the sample business data can be accurately searched and matched to obtain the sample business data when the subsequent comparison and traction are carried out.
S303, constructing a training sample set according to each infrastructure service label and the target sample service data corresponding to each infrastructure service label.
Further, fig. 4 is a schematic flow chart of constructing a training sample set according to each infrastructure service tag and target sample service data corresponding to each infrastructure service tag, which is provided in the second embodiment of the present invention, and as shown in fig. 4, the method specifically includes the following steps:
s3031, according to the business rules corresponding to the infrastructure business labels, business problems in the target sample business data are calibrated, and the calibrated target sample business data are determined as calibration sample business data.
In this embodiment, the business rules may be specifically understood as rules to be followed by each business of the infrastructure construction during the execution process, for example, the model of the logical entity used at the current site of the project should be the same as the model of the logical entity signed in the contract, each constructor needs to wear a safety helmet and execute operations corresponding to the other preset safety rules in order to meet the safety requirements during the construction activities at the site of the project, which are only part of the situations included in the embodiment of the present invention, and the embodiment of the present invention does not limit the specifically included business rules.
In this embodiment, the business problem can be understood as a problem that the target sample business data does not conform to the business rule corresponding to the corresponding infrastructure business label, which would cause a risk to the infrastructure engineering project. The calibration sample business data can be specifically understood as target sample business data for completing business problem calibration, that is, the business data contained in the calibration sample business data is marked with problems which exist in the calibration sample business data and can cause problems to the infrastructure engineering project.
Specifically, according to the business rule corresponding to the infrastructure business label, whether an operation which does not accord with the business rule exists in the target sample business data corresponding to the infrastructure business label is determined, the operation which does not accord with the business rule is determined as a business problem, the business problem is calibrated in the corresponding target sample business data, and the target sample business data after calibration is determined as calibration sample business data. Optionally, the service problem may be marked in the target sample service data in the form of an intelligent tag or a text remark, or a part of the target sample service data having the service problem may be marked by a circle.
S3032, determining the target sample service data corresponding to the same infrastructure service label as a target sample service data set, and determining the corresponding calibration sample service data as a calibration sample service data set.
Specifically, for one infrastructure service tag, the infrastructure service tag can correspond to a plurality of target sample service data, so that all target sample service data corresponding to the infrastructure service tag can form a target sample service data set, each target sample service data can obtain a calibration sample service data after being calibrated, the number of the calibration sample service data is the same as that of the target sample service data, and therefore all calibration sample service data corresponding to the same infrastructure service tag can form a calibration sample service data set.
S3033, determining each basic building business label, each corresponding target sample business data set and each calibration sample business data set as a training sample set.
Specifically, each infrastructure service label, and a target sample service data set and a calibration sample service data set corresponding to the infrastructure service label are determined as a group of training samples, and a set of each group of training samples corresponding to each infrastructure service label is determined as a training sample set.
S304, training the initial service monitoring network model through the training sample set until a preset convergence condition is met to obtain the service monitoring network model.
In this embodiment, the preset convergence condition may be specifically understood as a condition for determining whether the trained initial traffic monitoring network model enters a convergence state. Optionally, the preset convergence condition may include that a change of a weight parameter between two iterations of model training is smaller than a preset parameter change threshold, the iteration exceeds a set maximum iteration number, or all training samples are completely trained, and the like, which is not limited in the embodiment of the present invention.
Specifically, a training sample set is input into an initial service monitoring network model for training, a plurality of different intermediate results of the initial service monitoring network model can be extracted in the training process, a loss function for training the initial service monitoring network model can be determined according to the plurality of different intermediate results and a preset weighting rule, and the determined loss function is used for performing back propagation on the initial service monitoring network model, so that weight parameters in each neural network layer for forming the initial service monitoring network model can be adjusted according to the determined loss function, and a trained chef service monitoring network model is determined as the service monitoring network model until a preset convergence condition is met.
As shown in fig. 2, the method for monitoring infrastructure engineering service provided in the second embodiment specifically includes the following steps:
s201, acquiring original platform service data.
In this embodiment, the original platform service data may be specifically understood as service data that is uploaded to the integrated system platform by a department executing different types of work and contains different types of service information.
For example, assuming that the original platform is a "five-in-one" collaborative management platform of the national network, the department service data corresponding to each department uploaded by different enterprises and different functional departments can be acquired from the "five-in-one" collaborative management platform, and all the department service data can be collectively referred to as original platform service data.
S202, extracting the capital construction project service data in the original platform service data according to the service data type.
Specifically, each original platform service data is uploaded through a dedicated uploading channel when being uploaded, so that the service data type included in each original platform service data can be considered to be labeled when being uploaded, and the service data including the service data type label of the 'infrastructure construction' is extracted from all the acquired original platform service data and is used as the infrastructure construction service data.
And S203, extracting service information in the business data of the infrastructure project.
And S204, marking the infrastructure construction business data by utilizing the business information, and determining the marked infrastructure construction business data as the business data to be processed.
It should be understood that the extraction of the service information and the labeling of the service data in steps S203-S204 are basically the same as those in step S302, and will not be described again.
Specifically, according to the service information extracted from the infrastructure construction service data, corresponding service information tags are generated, the infrastructure construction service data are labeled by using the service information tags, and the infrastructure construction service data after the labeling is determined as the service data to be processed.
S205, acquiring a capital construction service label corresponding to the service data to be processed.
And S206, inputting the service data to be processed and the corresponding infrastructure service label into a preset service monitoring network model.
Specifically, the service data to be processed and the corresponding infrastructure service tag are input into a preset service monitoring network model, and the service monitoring network model is used for completing matching of the infrastructure service tag and the specific service data in the service data to be processed.
S207, determining a service problem in the service data to be processed according to the service rule corresponding to the infrastructure service label, and determining the service problem as an output result of the service monitoring network model.
Specifically, according to a business rule corresponding to a infrastructure business tag, whether a business problem corresponding to the infrastructure business tag exists in the matched to-be-processed business data is determined, if the business problem exists, the business problem is calibrated by adopting a calibration method same as that for calibrating sample business data, and the calibrated to-be-processed business data is used as an output result of a business monitoring network model; if the service problem does not exist, calibrating the to-be-processed service data by adopting a preset calibration mode without the service problem, and taking the calibrated to-be-processed service data as an output result of the service monitoring network model.
For example, assuming that the infrastructure service tag corresponds to the transformer construction, the corresponding service rule may include that the model of the constructed transformer is the same as the model of the transformer in the contract, at this time, the transformer model information included in the to-be-processed unstructured document in the to-be-processed service data is compared with the transformer model information included in the to-be-processed picture, if the two are different, it may be determined that a service problem exists in the to-be-processed service data that the models of the transformers are not matched, a part of the to-be-processed picture and the to-be-processed unstructured document, which is related to the transformer model information, may be circled, and output the part as an output result of the service monitoring network model.
In connection with the above example, assuming that the capital construction service tag corresponds to a project safety check, the corresponding service rule may include that a constructor must wear a safety helmet, at this time, image recognition is performed on a to-be-processed picture included in the to-be-processed service data, whether a worker who does not wear the safety helmet exists is determined, if yes, a service problem that potential safety hazards exist in the to-be-processed service data may be determined, a circle may be drawn on the worker who does not wear the safety helmet in the to-be-processed picture, and the circle is output as an output result of the service monitoring network model.
And S208, determining a service monitoring result according to the output result of the service monitoring network model.
Specifically, whether a service problem exists or not is determined according to an output result of the service monitoring network model, if the service problem exists, the service problem is integrated into a service monitoring result, and if the service problem does not exist, the service monitoring result is determined to be problem-free.
S209, generating a service problem alarm according to the service monitoring result, and carrying out corresponding alarm prompt according to the service problem alarm.
Specifically, when a business problem exists in a business monitoring result, business information corresponding to business data with the business problem is determined, information of items, equipment, personnel and the like with the business problem is determined according to the business information, and a business problem alarm is generated according to the information, so that corresponding alarm prompt is performed on personnel related to the business problem alarm, the item monitoring personnel and the like.
The technical scheme of this embodiment includes acquiring service data related to infrastructure construction from original platform service data, labeling the infrastructure construction service data according to service information, determining the labeled data as service data to be processed, inputting the service data to be processed and a corresponding infrastructure construction service label into a preset service monitoring network model, determining a service problem in the service data to be processed according to a service rule corresponding to the infrastructure construction service label by the service monitoring network model, outputting the service problem as an output result of the service monitoring network model, generating a corresponding service problem alarm according to a service detection result after determining the service detection result, and labeling the service data according to sample service information in the sample service data by acquiring at least one set of sample service data corresponding to each infrastructure construction service label in the infrastructure construction, and obtaining the marked target sample business data, further constructing a training sample set according to each basic construction business label and each corresponding target sample business data, training the initial business monitoring network model through the training sample set, and adjusting the weight parameters in the network layer for each spirit of the initial business monitoring network model in the training process until the business monitoring network model meeting the preset convergence condition is determined. The main information in the infrastructure construction business data is contained in the service data when the business data is labeled, so that the information extraction pressure caused by unstructured information is not needed to be considered after the service data is used as the to-be-processed business data, the business monitoring network model obtained through training can automatically calibrate the to-be-processed business data and the infrastructure construction business label input into the business monitoring network model, the monitoring efficiency of infrastructure construction business and the accuracy of determining the business problem are improved, meanwhile, the occurring business problem is timely alarmed, the business problem can be timely solved, and the safety of infrastructure construction is improved.
EXAMPLE III
Fig. 5 is a schematic structural diagram of a infrastructure engineering business monitoring device according to a third embodiment of the present invention, where the infrastructure engineering business monitoring device includes: a data acquisition module 41 and a monitoring result determination module 42.
The data obtaining module 41 is configured to obtain to-be-processed service data and a infrastructure service tag corresponding to the to-be-processed service data; the business data to be processed comprises at least one of unstructured documents to be processed and pictures to be processed; and the monitoring result determining module 42 is configured to input the to-be-processed service data and the corresponding infrastructure service tag into a preset service monitoring network model, and determine a service monitoring result according to an output result of the service monitoring network model.
According to the technical scheme, the problems existing in the service data are automatically determined according to the corresponding service rules in the infrastructure service labels through the service monitoring network model, the problem that a large amount of time and labor cost are consumed for determining the service problems in the traditional infrastructure engineering is solved, the requirement on the quality of unstructured data in the service data is lowered, the infrastructure engineering service monitoring efficiency and the problem determination accuracy are improved, and the safety of infrastructure engineering construction is improved.
Optionally, the infrastructure service label is a service activity or logic entity with the minimum granularity in the infrastructure engineering, which is determined according to the five-in-one flowchart.
Optionally, the data obtaining module 41 includes:
and the platform data acquisition unit is used for acquiring the original platform service data.
And the data extraction unit is used for extracting the infrastructure construction business data in the original platform business data according to the business data type.
And the service information extraction unit is used for extracting the service information in the capital construction project service data.
And the information marking unit is used for marking the infrastructure construction business data by utilizing the business information and determining the marked infrastructure construction business data as the business data to be processed.
Optionally, the monitoring result determining module 42 is specifically configured to: inputting the service data to be processed and the corresponding infrastructure service label into a preset service monitoring network model; and determining a service problem in the service data to be processed according to a service rule corresponding to the infrastructure service label, and determining the service problem as an output result of the service monitoring network model.
Optionally, the infrastructure engineering service monitoring apparatus further includes:
and the alarm module is used for generating a service problem alarm according to the service monitoring result and carrying out corresponding alarm prompt according to the service problem alarm.
Further, the training step of the service monitoring network model in the monitoring result determination module 42 includes:
acquiring at least one group of sample service data corresponding to each infrastructure service label in infrastructure construction;
extracting sample service information in the sample service data, marking the sample service data by using the sample service information, and determining the marked sample service data as target sample service data;
constructing a training sample set according to each infrastructure service label and target sample service data corresponding to each infrastructure service label;
and training the initial service monitoring network model through the training sample set until a preset convergence condition is met to obtain the service monitoring network model.
Further, constructing a training sample set according to each of the infrastructure service labels and target sample service data corresponding to each of the infrastructure service labels, including:
calibrating the business problems in the target sample business data according to the business rules corresponding to the infrastructure business labels, and determining the calibrated target sample business data as calibrated sample business data;
determining target sample service data corresponding to the same infrastructure service label as a target sample service data set, and determining corresponding calibration sample service data as a calibration sample service data set;
and determining each infrastructure service label, each corresponding target sample service data set and each corresponding calibration sample service data set as a training sample set.
The infrastructure construction business monitoring device provided by the embodiment of the invention can execute the infrastructure construction business monitoring method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.
Example four
Fig. 6 is a schematic structural diagram of infrastructure engineering business monitoring equipment according to a fourth embodiment of the present invention, where the infrastructure engineering business monitoring equipment includes: a processor 50, a storage device 51, a display 52, an input device 53, and an output device 54. The number of the processors 50 in the infrastructure construction business monitoring device may be one or more, and one processor 50 is taken as an example in fig. 6. The number of the storage devices 51 in the infrastructure construction business monitoring equipment may be one or more, and one storage device 51 is taken as an example in fig. 6. The processor 50, the storage device 51, the display screen 52, the input device 53 and the output device 54 of the infrastructure construction business monitoring equipment may be connected by a bus or in other ways, and the bus connection is taken as an example in fig. 6. In an embodiment, the infrastructure construction business monitoring device may be a computer, a notebook, or an intelligent tablet.
The storage device 51 is a computer-readable storage medium, and can be used to store software programs, computer-executable programs, and modules, such as program instructions/modules (for example, the data acquisition module 41 and the monitoring result determination module 42) corresponding to the infrastructure engineering business monitoring equipment according to any embodiment of the present application. The storage device 51 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to use of the device, and the like. Further, the storage 51 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, the storage 51 may further include memory located remotely from the processor 50, which may be connected to the device over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The display screen 52 may be a touch-enabled display screen 52, which may be a capacitive screen, an electromagnetic screen, or an infrared screen. In general, the display screen 52 is used for displaying data according to instructions from the processor 50, and is also used for receiving touch operations applied to the display screen 52 and sending corresponding signals to the processor 50 or other devices.
The input means 53 may be used to receive input numeric or character information and generate key signal inputs related to user settings and function controls of the presentation apparatus, and may also be a camera for acquiring images and a sound pickup apparatus for acquiring audio data. The output device 54 may include an audio device such as a speaker. It should be noted that the specific composition of the input device 53 and the output device 54 may be set according to actual conditions.
The processor 50 executes various functional applications and data processing of the device by running software programs, instructions and modules stored in the storage device 51, so as to implement the infrastructure construction business monitoring method.
The computer equipment provided by the above can be used for executing the infrastructure construction business monitoring method provided by any of the above embodiments, and has corresponding functions and beneficial effects.
EXAMPLE five
An embodiment of the present invention further provides a storage medium containing computer-executable instructions, where the computer-executable instructions are executed by a computer processor to perform a method for monitoring infrastructure construction business, and the method includes:
acquiring to-be-processed service data and a capital construction service label corresponding to the to-be-processed service data; the business data to be processed comprises at least one of unstructured documents to be processed and pictures to be processed;
and inputting the service data to be processed and the corresponding infrastructure service label into a preset service monitoring network model, and determining a service monitoring result according to an output result of the service monitoring network model.
Of course, the storage medium provided by the embodiment of the present invention includes computer-executable instructions, and the computer-executable instructions are not limited to the method operations described above, and may also perform related operations in the infrastructure construction business monitoring method provided by any embodiment of the present invention.
From the above description of the embodiments, it is obvious for those skilled in the art that the present invention can be implemented by software and necessary general hardware, and certainly, can also be implemented by hardware, but the former is a better embodiment in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a FLASH Memory (FLASH), a hard disk or an optical disk of a computer, and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device) to execute the methods according to the embodiments of the present invention.
It should be noted that, in the embodiment of the above search apparatus, each included unit and module are merely divided according to functional logic, but are not limited to the above division as long as the corresponding functions can be implemented; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (10)
1. A method for monitoring infrastructure construction business is characterized by comprising the following steps:
acquiring to-be-processed service data and a capital construction service label corresponding to the to-be-processed service data; the business data to be processed comprises at least one of unstructured documents to be processed and pictures to be processed;
and inputting the service data to be processed and the corresponding infrastructure service label into a preset service monitoring network model, and determining a service monitoring result according to an output result of the service monitoring network model.
2. The method according to claim 1, wherein the obtaining the service data to be processed comprises:
acquiring original platform service data;
extracting the capital construction project service data in the original platform service data according to the service data type;
extracting service information in the capital construction project service data;
and marking the infrastructure construction business data by utilizing the business information, and determining the marked infrastructure construction business data as business data to be processed.
3. The method of claim 1, wherein the infrastructure business label is a business activity or logical entity of minimum granularity in the infrastructure project, determined according to a five-in-one flow diagram.
4. The method of claim 3, wherein the step of training the traffic monitoring network model comprises:
acquiring at least one group of sample service data corresponding to each infrastructure service label in infrastructure construction;
extracting sample service information in the sample service data, marking the sample service data by using the sample service information, and determining the marked sample service data as target sample service data;
constructing a training sample set according to each infrastructure service label and target sample service data corresponding to each infrastructure service label;
and training the initial service monitoring network model through the training sample set until a preset convergence condition is met to obtain the service monitoring network model.
5. The method of claim 4, wherein constructing a training sample set according to each of the infrastructure traffic labels and target sample traffic data corresponding to each of the infrastructure traffic labels comprises:
calibrating the business problems in the target sample business data according to the business rules corresponding to the infrastructure business labels, and determining the calibrated target sample business data as calibrated sample business data;
determining target sample service data corresponding to the same infrastructure service label as a target sample service data set, and determining corresponding calibration sample service data as a calibration sample service data set;
and determining each infrastructure service label, each corresponding target sample service data set and each corresponding calibration sample service data set as a training sample set.
6. The method according to claim 2, wherein the inputting the to-be-processed service data and the corresponding infrastructure service tag into a preset service monitoring network model comprises:
inputting the service data to be processed and the corresponding infrastructure service label into a preset service monitoring network model;
and determining a service problem in the service data to be processed according to a service rule corresponding to the infrastructure service label, and determining the service problem as an output result of the service monitoring network model.
7. The method of claim 1, wherein after determining the traffic monitoring result according to the output result of the traffic monitoring network model, further comprising:
and generating a service problem alarm according to the service monitoring result, and carrying out corresponding alarm prompt according to the service problem alarm.
8. A infrastructure construction business monitoring device, comprising:
the data acquisition module is used for acquiring to-be-processed business data and a capital construction business label corresponding to the to-be-processed business data; the business data to be processed comprises at least one of unstructured documents to be processed and pictures to be processed;
and the monitoring result determining module is used for inputting the to-be-processed service data and the corresponding infrastructure service label into a preset service monitoring network model and determining a service monitoring result according to an output result of the service monitoring network model.
9. The infrastructure construction business monitoring equipment is characterized by comprising a storage device and one or more processors;
the storage device to store one or more programs;
when executed by the one or more processors, cause the one or more processors to implement the infrastructure traffic monitoring method of any one of claims 1-7.
10. A storage medium containing computer executable instructions for performing the infrastructure traffic monitoring method of any one of claims 1-7 when executed by a computer processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111405038.3A CN114049095A (en) | 2021-11-24 | 2021-11-24 | Infrastructure construction business monitoring method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111405038.3A CN114049095A (en) | 2021-11-24 | 2021-11-24 | Infrastructure construction business monitoring method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114049095A true CN114049095A (en) | 2022-02-15 |
Family
ID=80210835
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111405038.3A Pending CN114049095A (en) | 2021-11-24 | 2021-11-24 | Infrastructure construction business monitoring method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114049095A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115809833A (en) * | 2023-01-13 | 2023-03-17 | 佰聆数据股份有限公司 | Intelligent monitoring method and device for capital construction project based on portrait technology |
-
2021
- 2021-11-24 CN CN202111405038.3A patent/CN114049095A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115809833A (en) * | 2023-01-13 | 2023-03-17 | 佰聆数据股份有限公司 | Intelligent monitoring method and device for capital construction project based on portrait technology |
| CN115809833B (en) * | 2023-01-13 | 2023-05-05 | 佰聆数据股份有限公司 | Intelligent supervision method and device for foundation project based on portrait technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110119413B (en) | Data fusion method and device | |
| CN110287316A (en) | A kind of Alarm Classification method, apparatus, electronic equipment and storage medium | |
| CN111860522B (en) | Identity card picture processing method, device, terminal and storage medium | |
| CN114997263B (en) | Method, device, equipment and storage medium for analyzing training rate based on machine learning | |
| EP4138004A1 (en) | Method and apparatus for assisting machine learning model to go online | |
| CN113963186A (en) | Training method of target detection model, target detection method and related device | |
| CN118195329A (en) | Multidimensional fusion processing method and system for intelligent risk identification in coal mine safety production | |
| CN114049095A (en) | Infrastructure construction business monitoring method, device, equipment and storage medium | |
| CN114445682A (en) | Method, device, electronic equipment, storage medium and product for training model | |
| CN113344064A (en) | Event processing method and device | |
| CN116824455A (en) | Event detection method, device, equipment and storage medium | |
| CN111798352A (en) | Enterprise state supervision method, device, equipment and computer readable storage medium | |
| CN116432069A (en) | Information processing method, service providing method, device, equipment and medium | |
| CN111062827A (en) | Engineering supervision method based on artificial intelligence mode | |
| CN115757075A (en) | Task abnormity detection method and device, computer equipment and storage medium | |
| CN113449083B (en) | Operation safety management method, device, equipment and storage medium | |
| CN115761362A (en) | Intelligent construction stage identification model, method and device based on feature fusion | |
| CN111080444B (en) | Information auditing method and device | |
| CN115393034A (en) | Method for carrying out risk identification on enterprise account based on natural language processing technology | |
| CN112200602B (en) | Neural network model training method and device for advertisement recommendation | |
| CN111444170B (en) | Automatic machine learning method and equipment based on predictive business scene | |
| CN110414186B (en) | Data asset segmentation verification method and device | |
| CN113159344A (en) | Multimedia information processing method and device, computer storage medium and electronic equipment | |
| CN117933699A (en) | Task analysis method, device, computer equipment and storage medium | |
| WO2020255269A1 (en) | Evaluation device, evaluation method, and program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |