CN114429297A - Method and device for monitoring risk of project, computer equipment and storage medium - Google Patents
Method and device for monitoring risk of project, computer equipment and storage medium Download PDFInfo
- Publication number
- CN114429297A CN114429297A CN202210080934.5A CN202210080934A CN114429297A CN 114429297 A CN114429297 A CN 114429297A CN 202210080934 A CN202210080934 A CN 202210080934A CN 114429297 A CN114429297 A CN 114429297A
- Authority
- CN
- China
- Prior art keywords
- project
- management stage
- model data
- risk prediction
- stage
- 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
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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/103—Workflow collaboration or project management
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to an artificial intelligence technology, and provides a risk monitoring method for a project, wherein a model data label of each management stage is obtained through ER graph modeling according to a preset parameter of each management stage in the project; the method is convenient for targeted monitoring, the numerical value of the model data label of each management stage is collected, the risk prediction model of each management stage in the project is respectively constructed, risk prediction is carried out, so that adjustment and correction can be timely carried out, and the risk prediction value of each management stage of different project versions is respectively obtained according to the numerical value of the model data label of each management stage of different project versions monitored in real time; by utilizing an analysis tool, the risk prediction value of each management stage of different project versions is subjected to statistical analysis, so that the detailed condition of the project versions can be comprehensively and objectively presented, the trend of the project versions is accurately predicted in a possibility manner, and a project manager is assisted in project version management.
Description
Technical Field
The invention relates to the field of artificial intelligence, in particular to a risk monitoring method and device for projects, computer equipment and a storage medium.
Background
With the continuous development of science and technology, high requirements are placed on the online time and quality of projects, and in the process from on-demand development to online of projects, various problems are often accompanied in each management stage, and the problems lead to the fact that the projects cannot be delivered in time or the quality of the projects is reduced. Therefore, the project needs to be managed and monitored in the whole period, and the encountered problems are corrected in time.
In the prior art, only a demand management tool, a code management tool, a case defect management tool and the like are used for managing and monitoring projects, and only each stage is respectively monitored and managed, so that the obtained monitoring data are discrete, the risk prediction of the projects often has deviation, the projects in the whole life cycle cannot be timely risk predicted, different risks are timely adjusted and corrected, the delivery time of the projects is prolonged, and the delivery quality of the projects is reduced, so that the problem that the management and monitoring of the projects in the prior art are not beneficial to the rapid and high-quality delivery of the projects is solved.
Disclosure of Invention
In view of the above, it is necessary to provide a method, an apparatus, a computer device and a storage medium for risk monitoring of a project to solve the problem that the project cannot be delivered quickly and with high quality.
A first aspect of an embodiment of the present application provides a risk monitoring method for a project, including:
according to parameters preset in each management stage in the project, establishing a project data model through ER graph modeling, and obtaining a model data label of each management stage from the project data model;
monitoring nodes corresponding to the model data labels of each management stage in the project according to the model data labels of each management stage, and collecting the numerical values of the model data labels of each management stage;
respectively constructing a risk prediction model of each management stage in the project through a full-connection neural network algorithm according to the numerical value of the model data label of each management stage;
respectively obtaining a risk prediction value of each management stage of different project versions through a risk prediction model of each management stage in the project according to the real-time monitored numerical value of the model data label of each management stage of different project versions;
and utilizing an analysis tool to carry out statistical analysis on the risk prediction value of each management stage of different project versions to obtain a risk prediction report of each management stage of different project versions, and sending the risk prediction report to a terminal.
A second aspect of the embodiments of the present application provides a method and an apparatus for risk monitoring of a project, including:
a construction unit: according to parameters preset in each management stage in the project, establishing a project data model through ER graph modeling, and obtaining a model data label of each management stage from the project data model;
a monitoring unit: monitoring nodes corresponding to the model data labels of each management stage in the project according to the model data labels of each management stage, and collecting the numerical values of the model data labels of each management stage;
a training unit: respectively constructing a risk prediction model of each management stage in the project through a full-connection neural network algorithm according to the numerical value of the model data label of each management stage;
a prediction unit: respectively obtaining a risk prediction value of each management stage of different project versions through a risk prediction model of each management stage in the project according to the real-time monitored numerical value of the model data label of each management stage of different project versions;
an output unit: and utilizing an analysis tool to carry out statistical analysis on the risk prediction value of each management stage of different project versions to obtain a risk prediction report of each management stage of different project versions, and sending the risk prediction report to a terminal.
A third aspect of embodiments of the present application provides a computer device, including: a memory, a processor, and computer readable instructions stored in the memory and executable on the processor for causing the computer to perform the steps of the method for risk monitoring of a project.
A fourth aspect of embodiments of the present application provides a computer-readable storage medium having stored thereon a computer program for execution by a processor of steps of a method of risk monitoring of an item.
The method for monitoring the risk of the project, provided by the embodiment of the application, has the following beneficial effects:
the invention provides a risk monitoring method of a project, which comprises the steps of obtaining a model data label of each management stage through ER graph modeling according to a preset parameter of each management stage in the project; the method is convenient for targeted monitoring, the numerical value of the model data label of each management stage is collected, the risk prediction model of each management stage in the project is respectively constructed, risk prediction is carried out, so that adjustment and correction can be timely carried out, and the risk prediction value of each management stage of different project versions is respectively obtained according to the numerical value of the model data label of each management stage of different project versions monitored in real time; by utilizing an analysis tool, the risk prediction value of each management stage of different project versions is subjected to statistical analysis, so that the detailed condition of the project versions can be comprehensively and objectively presented, the trend of the project versions is accurately predicted in a possibility manner, and a project manager is assisted in project version management.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments of the present invention will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without inventive labor.
FIG. 1 is a flow chart of an implementation of a risk monitoring method for a project according to an embodiment of the present application;
FIG. 2 is a flow chart of a method for risk monitoring of a project according to another embodiment of the present application;
fig. 3 is a block diagram of a risk monitoring method and apparatus for a project according to an embodiment of the present disclosure;
fig. 4 is a block diagram of a server-side device according to an embodiment of the present disclosure.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. 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.
The risk monitoring method for the project is applied to the field of artificial intelligence and can be executed by a server side.
Referring to fig. 1, fig. 1 is a flowchart illustrating an implementation of a risk monitoring method for a project according to an embodiment of the present application.
As shown in fig. 1, a risk monitoring method for a project includes:
s11: according to parameters preset in each management stage in the project, establishing a project data model through ER graph modeling, and obtaining a model data label of each management stage from the project data model;
in step S11, the project management phase typically has a flow restriction, with a start point, an end point, or a control point. The end of a phase is usually the beginning of the next phase, for example, a project starts from the demand planning phase, and when the demand planning phase ends, the development iteration phase starts, and a project often includes multiple phases, and each phase is performed according to the project flow. Each stage has parameters which are preset for determining the normal operation of the stage, for example, the parameters preset in the demand planning stage include the estimation of the total demand amount which can be accommodated by the current version, or the estimation of the resources required to be invested and the production time by combining the total demand amount which needs to be completed currently, and the like. The ER model is the most common conceptual model representation method in database design, and is based on the knowledge of the real world consisting of a set of basic objects called entities and the connections between these objects. In the ER model, each entity is identified by a name (called entity name) and includes some attributes, and the values of these attributes have a predefined domain, for example, the number of interfaces, the number of pages, the number of code submission lines and the frequency are parameters preset in the iterative stage of the project development, and there is an inclusion relationship between the iterative stage of the development and the number of interfaces, the number of pages, the number of code submission lines and the frequency.
In this embodiment, the project data model is constructed by ER graph modeling according to parameters preset in each management stage in the project, for example, a project includes a requirement planning stage, a research and development iteration stage, a testing stage, in a commissioning stage, a daily operation stage, etc., the requirement planning stage estimates resources required to be invested and commissioning time, in estimating total amount of receivable requirements, the complexity of the requirements, matching degree of current resource skills, and influence of individual and team productivity promotion curves need to be fully considered, in the research and development stage, design evaluation time, design evaluation times, interface number, page number, code submission line number and frequency, test case evaluation time, test case evaluation times, self-test case evaluation time and times, etc., data in the test stage, such as bug total number and performance test, etc., and comparing the current version with the historical version data in real time, predicting relevant parameters such as quality deviation, progress deviation and the like of the current version, and comparing the current version with the historical version, the progress deviation and the like in real time in a production stage.
When ER modeling is carried out on each stage, ER graph modeling is carried out according to parameters preset in each stage in a project, project organization process assets, historical experience training, process change expert judgment and standardized processes: the standardized process is the problem to be solved by the project version management auxiliary monitoring tool, the roles that the project management auxiliary monitoring tool participates in and the work items of processing required by each role in different stages. Determining entities, attributes and relationships in the ER diagram according to a standardized process, for example, if research and development are taken as one entity, the research and development role needs to participate in demand-research and development-test-commissioning-operation in the whole project, and work items to be processed in each stage are different, how to monitor and predict that the work items are completed under the target of expected planning will generate a plurality of preset parameters, and these relevant parameters are the attributes of the research and development entity. Regarding the relationship, for example, how the research and development entity is related to the product entity, the most obvious is the requirement, the research and development needs to pay attention to the quality of the requirement document, whether the description is clear, whether the granularity meets the requirement, and whether the development admission standard is met.
And inquiring the relation between the entity and each attribute from the ER graph model according to the constructed ER graph model, and obtaining the model data label of each stage according to the relation between the entity and each attribute.
It should be noted that the model data label of each stage can be input as a data source of the subsequent risk prediction model.
S12: monitoring nodes corresponding to the model data labels of each management stage in the project according to the model data labels of each management stage, and collecting the numerical values of the model data labels of each management stage;
in step S12, the model data tag of each stage of the project is monitored to obtain a model data tag value, where the model data tag is a role that the project management auxiliary monitoring tool participates in and an attribute of a work item that each role needs to process at different stages, and a value of the obtained model data tag is an attribute value by monitoring each stage of the project.
In this embodiment, according to a monitoring tool, a model data tag node of each management stage in a project is monitored, and monitoring data of each node is collected, for example, in the monitoring nodes of stage monitoring, design review time, design review times, interface number, page number, code submission line number and frequency, test case review time, test case review times, self-test case review time and times, and the like in research and development, data such as bug total number, performance test and the like in a test stage are compared with historical version data in real time to predict quality deviation, progress deviation and the like of a current version.
As an embodiment of the present application, step S12 specifically includes:
and collecting the numerical value of the model data label of each management stage by collecting the access log information of the API interface at the node corresponding to the model data label.
In this embodiment, the monitoring is performed through an API gateway, and the API gateway service is used to monitor and manage an API interface of a deployed service, in this embodiment, the API interface may be deployed at a model data tag of each stage, and the API gateway service is responsible for collecting log information accessed by an API, transmitting log content to a background streaming calculation only in a JSON format, and acquiring data required for monitoring through the streaming calculation. The streaming computation is deployed outside an API gateway, for example, the service uses Kong to collect and manage all APIs, uses a Web page constructed by React to perform operations of adding, editing, deleting and inquiring on the APIs, realizes the collection of log information and the management of API strategies through Kong, and performs index visualization display through the Web page constructed by React to obtain a data value of a required model data tag.
It should be noted that the monitoring of the model data tags may also be performed by using a nodes tool, adding a node to be monitored in the nodes tool, and dynamically displaying the model data tags of each stage in a graphical manner. When monitoring is performed through the revops tool, a code warehouse and a corresponding code management tool are needed to realize the function. The tool can store the submission records of the codes to perform differential analysis on the codes, and can perform revocation operation on the codes back to the previous version if necessary, so that the loss and mutual coverage of the codes are avoided. In this embodiment, open source Git is used as the code management tool, and the code repository is Gitlab. The code repository is open-sourced and can be deployed in the form of containers in a kubernets cluster.
In the monitoring process, monitoring data can be obtained through ETL, which refers to extracting data (e.g., relational data, flat data files) in distributed and heterogeneous data sources to a temporary middle layer, then cleaning, converting, integrating, and finally loading the data into a data warehouse. If the ETL tasks which can be currently operated exist, selecting one ETL task which can be currently operated from the ETL tasks which can be currently operated, and acquiring the data value of the model data label of the corresponding node of each stage from the project database. In practical applications, some nodes may be currently running one ETL task, and in this case, such nodes will not generally run other ETL tasks. Therefore, if the nodes with a plurality of ETL tasks exist in the query, it may be further determined whether a node capable of running the selected ETL task exists among the nodes dedicated to running the selected ETL task, and the node capable of running the selected ETL task may refer to a node that does not currently run the ETL task.
S13: respectively constructing a risk prediction model of each management stage in the project through a full-connection neural network algorithm according to the numerical value of the model data label of each management stage;
in step S13, according to the obtained value of the model data label of each stage, in combination with project organization process assets, historical experience training, and process improvement expert judgment, a risk prediction model of each stage in the whole project is respectively constructed through a fully-connected neural network algorithm. When the risk prediction model is constructed, the model data label of each stage is taken as the characteristic and is used as the input of the risk prediction model.
In the embodiment, the value of the model data label of each management stage is used as input, and the difference degree between the output value and the true value of the VGG convolutional neural network is evaluated by adopting a cross entropy loss function; by adopting a ReLU activation function, the nonlinearity of the VGG convolutional neural network is improved, and the sparsity of the VGG convolutional neural network is increased; therefore, the overfitting effect and the gradient disappearance of the model can be effectively avoided, and the calculation speed is improved; a Dropout layer is adopted to act on a full connection layer of the VGG convolutional neural network; therefore, interaction among hidden layer nodes can be effectively reduced, complex co-adaptation relations among neurons are reduced, and overfitting is effectively avoided. After the Batchnorm layer is used on each convolution layer of the VGG convolution neural network, the distribution of the neuron input values of each neural network layer is pulled back to the standard normal distribution, so that the training speed is improved, gradient explosion and gradient disappearance are effectively prevented, and the over-fitting effect is avoided. And obtaining a risk prediction model of each management stage through a full-connection neural network algorithm.
As an embodiment of the present application, step S13 specifically includes:
dividing the numerical value of the model data label of each management stage into a positive sample and a negative sample according to the numerical value of the model data label of each management stage to obtain the positive sample and the negative sample of the model data label of each management stage; and respectively constructing a risk prediction model of each management stage in the project through a full-connection neural network algorithm according to the positive sample and the negative sample of the model data label of each management stage.
In the embodiment, according to the value of the model data label of each collected stage, in combination with the assets of the project organization process, the historical experience training and the judgment of the process improvement expert, dividing positive samples and negative samples into the numerical value of the model data label of each stage, for example, in a demand planning stage, the numerical value of the model data label with the production capacity of the human-average/team and the production time of more than 100 days in the model data label is a negative sample, the numerical value of the model data label with the production time of less than 100 days is a positive sample, the numerical value of the model data label with the complexity of more than 0.7 is a negative sample, the numerical value of the model data label with the complexity of less than 0.7 is a positive sample, the sample label of the positive sample is labeled as 1, the sample label of the negative sample is labeled as 0, and the positive sample and the negative sample form a training set and serve as input of a neural network structure to obtain a risk prediction model of each management stage.
S14: respectively obtaining a risk prediction value of each management stage of different project versions through a risk prediction model of each management stage in the project according to the real-time monitored numerical value of the model data label of each management stage of different project versions;
in step S14, the real-time data value of the model data tag of each stage is obtained by monitoring the different versions of the project, the real-time data value of the model data tag of each stage is brought into the risk prediction model of each stage to obtain the risk prediction value of the corresponding stage, and the deviation of the different versions of the project is corrected according to the risk prediction value, so as to conveniently take corresponding measures for each stage of the different versions of the project, so that the different versions of the project can normally operate.
In this embodiment, taking the case that a risk prediction model is used to evaluate manpower and schedule in a demand planning stage, if a planning cycle of a project version is 4W, planning 1W, developing 2W, and testing 2W (the development and testing cycles are crossed, and generally, after 1W is developed, contents are continuously provided and tested, so as to improve the iterative manpower productivity of the whole version) according to a conventional schedule, a hypothetical condition method is used to input current development manpower to predict the total amount of demand that can be accommodated by iteration of the version, and input total amount of demand to predict the development manpower that needs to be input by iteration of the version; and (3) predicting according to the ratio of 5:1 of research and development and testing, synchronously predicting required testing manpower, if the total quantity of the demand is fixed, the manpower is fixed, and predicting the risk value of the scheduling of the project version according to the risk prediction value obtained by a risk prediction model according to the productivity curve of the current project team.
S15: and utilizing an analysis tool to carry out statistical analysis on the risk prediction value of each management stage of different project versions to obtain a risk prediction report of each management stage of different project versions, and sending the risk prediction report to a terminal.
In step S15, the risk prediction value obtained by the risk prediction model of each stage is analyzed and processed by using an analysis tool to determine whether there is a risk in each stage, where the analysis tool includes a series of tools such as an auxiliary checklist analysis, a hypothesis analysis, a graphical analysis, an expert judgment, a risk and probability influence evaluation, and a probability and influence matrix. And after analysis, obtaining a risk prediction report of each stage of different project versions, inquiring from the risk prediction report, and when the risk of the corresponding stage is obtained through analysis, taking corresponding measures for the corresponding stage, and adjusting each stage so that the project can be completed in high quality on time.
In this embodiment, according to the obtained risk prediction value of each stage, a probability and influence matrix tool is used for analysis, in a probability and influence matrix, rows of the matrix represent changes that may occur to model data labels in each stage, columns of the matrix represent works that may be influenced, and middle values represent degree values that the changes in the columns have change influences (influence of indirect propagation is not considered) on the works in the rows, and according to the probability and influence matrix analysis, a risk prediction report is obtained and sent to a terminal.
As an embodiment of the present application, step S15 specifically includes:
and classifying the risk prediction reports through calculation according to the risk prediction reports of each management stage of different project versions and a risk threshold, and sending classification results to the terminal.
In this embodiment, according to the project management requirement, a corresponding risk threshold is set for each stage of the project, where the risk threshold includes a risk factor threshold and a prediction difference threshold. The risk prediction report of each stage comprises a risk prediction value of each stage and a numerical value of a model data label of each stage, the number of risk factors in each stage is determined according to the risk prediction report, the number of the risk factors is obtained through the model data label in the risk prediction report, when the value of the model data label is different from the value of the model data label obtained in advance, the model data label is a risk factor, the number of the risk factors of each stage is calculated, then, the risk prediction value is compared with a preset prediction threshold value to obtain a prediction difference value, the risk prediction report is classified according to the number of the risk factors and the prediction difference value, when the number of the risk factors and the prediction difference value are respectively smaller than the risk factor threshold value and the prediction difference value threshold value, the risk prediction report is considered to be a positive risk, otherwise, the risk prediction report is sent to a terminal, according to different risk prediction reports, corresponding measures are implemented, for example, inconsistency between the project version management plan (target) obtained by analysis in the requirement planning stage and the formulated project version management plan (target) has influence on the progress, quality, cost and the like of the current project version, for example, the progress is delayed, the quality does not meet the acceptance criteria, the cost is overburdened and the like are negative risks. Aiming at different risks, different measures are adopted for adjustment, and aiming at threatened risks, the measures which can be adopted mainly comprise avoidance, transfer, mitigation and acceptance; the coping strategy aiming at the active risk mainly comprises development, improvement, sharing and acceptance.
Referring to fig. 2, fig. 2 is a flowchart illustrating an implementation of a risk monitoring method for a project according to another embodiment of the present application. With respect to the embodiment corresponding to fig. 1, the method for monitoring the risk of the project provided by the present embodiment further includes step S10 before step S11. The details are as follows:
s10: and dividing the project into different management stages according to the management requirement of the project.
In this embodiment, the completion of the project requires a series of stages of the project from beginning to end, the project stages are usually arranged in chronological order, and the names and number of the stages depend on the management and control needs of one or more organizations participating in the project, the characteristics of the project itself, and the application field in which the project is located. In this embodiment, according to the management requirement of the project, the project is divided into different management phases, for example, the project is divided into a requirement planning phase, a research and development iteration phase, a testing phase, a production phase, a daily operation phase, and the like. Or for convenience of management, combining multiple stages, wherein both the research and development iteration stage and the test stage are used for researching project codes, and the research and development iteration stage and the test stage are combined into one stage.
Referring to fig. 3, fig. 3 is a block diagram of an apparatus structure of a method for monitoring risk of a project according to an embodiment of the present disclosure. In this embodiment, the server includes 6 units for executing the steps in the embodiment corresponding to fig. 1 to fig. 2, and refer to the description in the embodiment corresponding to fig. 1 to fig. 2 and fig. 1 to fig. 2. For convenience of explanation, only the portions related to the present embodiment are shown. Referring to fig. 3, a risk monitoring method for an item 30 includes: dividing unit 31, constructing unit 32, monitoring unit 33, training unit 34, predicting unit 35, and outputting unit 36, wherein:
the dividing unit 31 is configured to divide the project into different management phases according to the management requirement of the project.
The construction unit 32 is used for constructing the project data model through ER graph modeling according to parameters preset in each management stage in the project, and obtaining a model data label of each management stage from the project data model;
the monitoring unit 33 is configured to monitor a node corresponding to the model data tag of each management stage in the project according to the model data tag of each management stage, and acquire a numerical value of the model data tag of each management stage;
the training unit 34 is used for respectively constructing a risk prediction model of each management stage in the project through a full-connection neural network algorithm according to the numerical value of the model data label of each management stage;
the prediction unit 35 is configured to obtain, according to the real-time monitored value of the model data tag of each management stage of different project versions, a risk prediction value of each management stage of different project versions through a risk prediction model of each management stage in the project;
and the output unit 36 is configured to perform statistical analysis on the risk prediction value of each management stage of different project versions by using an analysis tool, obtain a risk prediction report of each management stage of different project versions, and send the risk prediction report to the terminal.
As an embodiment of the present application, the method and apparatus for risk monitoring of a project 30 further include:
the first execution unit 37 is configured to collect the numerical value of the model data tag at each management stage by collecting access log information of the API interface at the node corresponding to the model data tag.
As an embodiment of the present application, the monitoring unit 33 is specifically configured to monitor a model data tag of each stage of a project to obtain a model data tag value, where the model data tag is a role that the project management auxiliary monitoring tool participates in and an attribute of a work item that each role needs to process at different stages, and by monitoring each stage of the project in a full life cycle, a value of the obtained model data tag is an attribute value.
The second execution unit 38 is configured to divide the value of the model data tag of each management stage into a positive sample and a negative sample according to the value of the model data tag of each management stage, so as to obtain the positive sample and the negative sample of the model data tag of each management stage; and respectively constructing a risk prediction model of each management stage in the project through a full-connection neural network algorithm according to the positive sample and the negative sample of the model data label of each management stage.
And a third executing unit 39, configured to classify the risk prediction reports according to the risk prediction reports of each management stage of different project versions and a risk threshold, through calculation, and send a classification result to a corresponding terminal.
It should be understood that, in the structural block diagram of the risk monitoring method for a project shown in fig. 3, each unit is used to execute each step in the embodiment corresponding to fig. 1 to fig. 2, and each step in the embodiment corresponding to fig. 1 to fig. 2 has been explained in detail in the above embodiment, and specific reference is made to the relevant description in the embodiment corresponding to fig. 1 to fig. 2 and fig. 1 to fig. 2, which is not repeated herein.
In one embodiment, a computer device is provided, the computer device is a server, and the internal structure diagram of the computer device can be as shown in fig. 4. The computer device 40 includes a processor 41, an internal memory 43, and a network interface 44 connected by a system bus 42. Wherein the processor 41 of the computer device is arranged to provide computing and control capabilities. The memory of the computer device 40 comprises a readable storage medium 45, an internal memory 43. The readable storage medium 45 stores an operating system 46, computer readable instructions 47, and a database 48. The internal memory 43 provides an environment for the operation of an operating system 46 and computer readable instructions 47 in the readable storage medium 45. The database 48 of the computer device 40 is used to store data relating to risk monitoring methods for a project. The network interface 44 of the computer device 40 is used for communicating with an external terminal through a network connection. The computer readable instructions 47, when executed by the processor 41, implement a method of risk monitoring of a project. The readable storage medium 45 provided by the present embodiment includes a nonvolatile readable storage medium and a volatile readable storage medium.
It will be understood by those of ordinary skill in the art that all or part of the processes of the methods of the above embodiments may be implemented by hardware related to computer readable instructions, which may be stored in a non-volatile readable storage medium or a volatile readable storage medium, and when executed, the computer readable instructions may include processes of the above embodiments of the methods. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include non-volatile and/or volatile memory. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present invention, and are intended to be included within the scope of the present invention.
Claims (10)
1. A method of risk monitoring of a project, comprising:
according to parameters preset in each management stage in the project, establishing a project data model through ER graph modeling, and obtaining a model data label of each management stage from the project data model;
monitoring nodes corresponding to the model data labels of each management stage in the project according to the model data labels of each management stage, and collecting the numerical values of the model data labels of each management stage;
respectively constructing a risk prediction model of each management stage in the project through a full-connection neural network algorithm according to the numerical value of the model data label of each management stage;
respectively obtaining a risk prediction value of each management stage of different project versions through a risk prediction model of each management stage in the project according to the real-time monitored numerical value of the model data label of each management stage of different project versions;
and utilizing an analysis tool to carry out statistical analysis on the risk prediction value of each management stage of different project versions to obtain a risk prediction report of each management stage of different project versions, and sending the risk prediction report to a terminal.
2. The method for risk monitoring of a project according to claim 1, wherein the step of building the project data model by ER graph modeling according to the preset parameters of each management stage in the project, and before obtaining the model data label of each management stage from the project data model, further comprises:
and dividing the project into different management stages according to the management requirement of the project.
3. The method for risk monitoring of a project according to claim 1, wherein the monitoring the node corresponding to the model data tag of each management stage in the project according to the model data tag of each management stage, and the collecting the value of the model data tag of each management stage comprises:
and collecting the numerical value of the model data label of each management stage by collecting the access log information of the API interface at the node corresponding to the model data label.
4. The method for risk monitoring of a project according to claim 3, wherein the collecting the values of the model data tags of each management phase by collecting access log information of the API interfaces at the nodes corresponding to the model data tags comprises:
and converting the access log information into a JSON format, and obtaining the numerical value of the model data tag of each management stage by a stream calculation method.
5. The method for risk monitoring of a project according to claim 1, wherein the step of separately constructing a risk prediction model of each management stage in the project by a fully-connected neural network algorithm according to the value of the model data tag of each management stage comprises:
dividing the numerical value of the model data label of each management stage into a positive sample and a negative sample according to the numerical value of the model data label of each management stage to obtain the positive sample and the negative sample of the model data label of each management stage;
and respectively constructing a risk prediction model of each management stage in the project through a full-connection neural network algorithm according to the positive sample and the negative sample of the model data label of each management stage.
6. The method for risk monitoring of a project according to claim 1, wherein the using an analysis tool to perform statistical analysis on the risk prediction value of each management stage of different project versions to obtain a risk prediction report of each management stage of different project versions, and sending the risk prediction report to the terminal includes:
and classifying the risk prediction reports through calculation according to the risk prediction reports of each management stage of different project versions and a risk threshold, and sending classification results to the terminal.
7. The method for risk monitoring of a project of claim 6, wherein said classifying a risk prediction report comprises:
the risk prediction reports are divided into positive risk prediction reports and negative risk prediction reports.
8. A method and a device for monitoring risk of a project,
a construction unit: according to parameters preset in each management stage in the project, establishing a project data model through ER graph modeling, and obtaining a model data label of each management stage from the project data model;
a monitoring unit: monitoring nodes corresponding to the model data labels of each management stage in the project according to the model data labels of each management stage, and collecting the numerical values of the model data labels of each management stage;
a training unit: respectively constructing a risk prediction model of each management stage in the project through a full-connection neural network algorithm according to the numerical value of the model data label of each management stage;
a prediction unit: respectively obtaining a risk prediction value of each management stage of different project versions through a risk prediction model of each management stage in the project according to the real-time monitored numerical value of the model data label of each management stage of different project versions;
an output unit: and utilizing an analysis tool to carry out statistical analysis on the risk prediction value of each management stage of different project versions to obtain a risk prediction report of each management stage of different project versions, and sending the risk prediction report to a terminal.
9. A computer device comprising a memory, a processor, and computer readable instructions stored in the memory and executable on the processor, wherein the computer readable instructions are readable instructions generated by the engine of any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores computer instructions for causing the computer to perform the steps of the method of any of the preceding claims 1-7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210080934.5A CN114429297A (en) | 2022-01-24 | 2022-01-24 | Method and device for monitoring risk of project, computer equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210080934.5A CN114429297A (en) | 2022-01-24 | 2022-01-24 | Method and device for monitoring risk of project, computer equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114429297A true CN114429297A (en) | 2022-05-03 |
Family
ID=81313860
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210080934.5A Pending CN114429297A (en) | 2022-01-24 | 2022-01-24 | Method and device for monitoring risk of project, computer equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114429297A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115796604A (en) * | 2023-01-29 | 2023-03-14 | 中建深圳装饰有限公司 | BIM model-based project full-life-cycle digital management early warning system |
-
2022
- 2022-01-24 CN CN202210080934.5A patent/CN114429297A/en active Pending
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115796604A (en) * | 2023-01-29 | 2023-03-14 | 中建深圳装饰有限公司 | BIM model-based project full-life-cycle digital management early warning system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109784806B (en) | Supply chain control method, system and storage medium | |
Choueiri et al. | An extended model for remaining time prediction in manufacturing systems using process mining | |
WO2021252734A1 (en) | Systems and methods for managing machine learning models | |
WO2019015631A1 (en) | Method for generating combined features for machine learning samples and system | |
Hompes et al. | Discovering causal factors explaining business process performance variation | |
Bendre et al. | Time series decomposition and predictive analytics using MapReduce framework | |
WO2020073727A1 (en) | Risk forecast method, device, computer apparatus, and storage medium | |
JP7401677B2 (en) | Model update system, model update method and related equipment | |
Raju et al. | An approach for demand forecasting in steel industries using ensemble learning | |
Shi et al. | Anomaly detection for key performance indicators through machine learning | |
CN112598443A (en) | Online channel business data processing method and system based on deep learning | |
Taghizadeh | Utilizing artificial neural networks to predict demand for weather-sensitive products at retail stores | |
CN115422402A (en) | Engineering prediction analysis method | |
CN115204648A (en) | Method and device for acquiring quality index of power engineering based on mathematical model | |
CN117807377B (en) | Multidimensional logistics data mining and predicting method and system | |
Madykh et al. | Analysis of the world experience of economic and mathematical modeling of smart enterprises | |
CN114429297A (en) | Method and device for monitoring risk of project, computer equipment and storage medium | |
Große Kamphake et al. | Digitalization in controlling | |
CN116235158A (en) | System and method for implementing automated feature engineering | |
BRZOZOWSKA et al. | Data Engineering In Crisp-Dm Process Production Data–Case Study | |
US20230267007A1 (en) | System and method to simulate demand and optimize control parameters for a technology platform | |
EP4034952A1 (en) | Method and system for identification and analysis of regime shift | |
US20230409460A1 (en) | System and method for optimizing performance of a process | |
Shah et al. | Predictive Analytic Modeling: A Walkthrough | |
Khayyati et al. | A machine learning approach for implementing data-driven production control policies |
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 |