CN112465011B

CN112465011B - Project risk prediction method and system based on project research and development process

Info

Publication number: CN112465011B
Application number: CN202011342989.6A
Authority: CN
Inventors: 黄祥博
Original assignee: Shenzhen Ping An Medical Health Technology Service Co Ltd
Current assignee: Shenzhen Ping An Medical Health Technology Service Co Ltd
Priority date: 2020-11-25
Filing date: 2020-11-25
Publication date: 2022-08-02
Anticipated expiration: 2040-11-25
Also published as: CN112465011A

Abstract

The application relates to big data processing, and provides a project risk prediction method and system based on a project research and development process. The method comprises the following steps: acquiring a project research and development plan, splitting the project research and development plan into a plurality of project tasks, and abstracting a benchmark index attribute based on each project task; acquiring current project research and development process data, analyzing and counting the project research and development process data according to a trained risk estimation algorithm model, and generating project offset data; the risk estimation algorithm model is obtained by training according to the reference index attribute and the historical item risk data; and predicting to obtain the project risk type and the key risk point according to the project deviation data. In addition, the present application also relates to blockchain techniques, and project offset data can be stored in blockchains. By the method, project risk types and key risk points in the future stage can be determined by integrating the project offset data, careless management of the risk points is avoided, the reasonable state of the project risk points is maintained, and the risk management and control efficiency is improved.

Description

Project risk prediction method and system based on project research and development process

Technical Field

The application relates to the technical field of big data processing, in particular to a project risk prediction method and system based on a project research and development process.

Background

With the development and application of a big data processing technology, in the overall research and development process of an IT product, different research and development projects are set for the product, which can include research and development projects such as product requirement determination, product design, product development, product test and release, and project goal achievement is a key factor of project success and failure, and project management is carried out as soon as possible in order to improve project goal achievement rate.

The project management comprises the fields of project scope management, project time management, project cost management, project quality management, project risk management, project resource management, project process management, project overall delivery management and the like, and each project needs to go through a starting process, a planning process, an executing process, a monitoring process, a project ending process and the like. Project risks may be introduced in different areas or processes, and each project risk may result in a failure of the project. Therefore, project risk management is required.

Traditional risk management mainly includes several steps such as risk identification, risk estimation, risk evaluation, risk planning, risk control, and risk monitoring, and through these steps, project risk can be managed. However, due to the complexity of the IT product development project itself and the continuous development of the software product design idea, the development mode, and the like, the complexity of the development project risk management is further increased, so that the traditional IT project risk management is slightly delayed, the management range and the management depth cannot meet the requirements of the existing project risk management, and management omission easily occurs, which results in low risk management and control efficiency.

Disclosure of Invention

In view of the foregoing, it is necessary to provide a project risk prediction method and system based on a project research and development process, which can improve risk management and control efficiency.

A project risk prediction method based on a project development process, the method comprising:

acquiring a project research and development plan, splitting the project research and development plan into a plurality of project tasks, and abstracting a benchmark index attribute based on each project task;

acquiring current project research and development process data, analyzing and counting the project research and development process data according to a trained risk estimation algorithm model, and generating project offset data; the risk estimation algorithm model is obtained by training according to the benchmark index attribute and the historical item risk data;

and predicting to obtain the project risk type and the key risk point according to the project deviation data.

In one embodiment, the method further comprises:

acquiring a risk point eliminating measure corresponding to the key risk point;

executing the risk point eliminating measures, correcting the key risk points, and generating updated research and development process data;

taking the updated research and development process data as sample data of the risk prediction algorithm model, and updating the risk prediction algorithm model according to the sample data;

and correcting the project offset data according to the updated risk estimation algorithm model.

In one embodiment, the step of performing analysis statistics on the project development process data according to the trained risk prediction algorithm model to generate project offset data includes:

classifying the project research and development process data to generate different categories of project research and development process data;

acquiring incidence relations of the project research and development process data of different types, and performing data index extraction on the project research and development process data of different types according to the incidence relations to generate associated project indexes;

according to the trained risk estimation algorithm model, carrying out risk score evaluation on each project index;

and generating project offset data corresponding to the project task according to the risk score of each project index obtained through evaluation.

In one embodiment, the predicting a project risk type and a key risk point according to the project offset data includes:

analyzing the project offset data, and determining a project offset type and an offset influence degree corresponding to a project research and development process; the project offset types comprise a project progress offset type, a project quality offset type and a human cost offset type;

determining a corresponding prediction risk type according to the project offset type; the risk types comprise postponing risks and technical difficulty risks corresponding to the project progress deviation types, resource risks corresponding to the human cost deviation types and quality risks corresponding to the project quality deviation types;

and determining key risk points causing project deviation in the project research and development process according to the deviation influence degree and the predicted risk type.

In one embodiment, the item risk types include deferred risk; training a mode of obtaining the risk estimation algorithm model according to the reference index attribute and the historical item risk data, wherein the mode comprises the following steps:

determining a postponing risk level of the corresponding historical project according to the historical project risk data;

according to the postponing risk level, performing postponing risk assessment on each historical project to generate a corresponding risk assessment result;

and training an original prediction model according to the risk evaluation result and the reference index attribute to generate a trained risk estimation algorithm model.

In one embodiment, the project risk types further include technical difficulty risks; training a mode of obtaining the risk estimation algorithm model according to the reference index attribute and the historical item risk data, wherein the mode comprises the following steps:

acquiring an estimated difficulty coefficient value set for each existing project task;

acquiring a target project task of which the estimated difficulty coefficient threshold is larger than a preset difficulty coefficient threshold;

acquiring task data of each target project task in a project research and development process; the task data comprises task progress data, task quality data and human input data;

performing technical difficulty risk prediction according to the task data to generate a corresponding risk prediction result;

and training to obtain the risk estimation algorithm model according to the reference index attribute and the risk prediction result.

In one embodiment, the obtaining a project research and development plan, splitting the project research and development plan into a plurality of project tasks, and abstracting a benchmark index attribute based on each of the project tasks includes:

acquiring a project research and development plan, and splitting the project research and development plan into a plurality of project tasks;

respectively extracting project research and development elements based on each project task; the project research and development elements comprise project tasks, project requirements and project research and development personnel distribution;

abstracting corresponding benchmark index attributes based on the project research and development elements;

the reference index attributes corresponding to the project tasks comprise task plan completion time, task complexity coefficients, task core point coefficients and task innovation coefficients; the benchmark index attributes corresponding to the project requirements include a staged cost and a staged milestone; the benchmark index attributes corresponding to the project research and development personnel comprise post categories, post grades, technical characteristics and technical capability coefficients.

A project risk prediction system based on a project development process, the system comprising:

the system comprises a benchmark index attribute acquisition module, a project development and development planning module and a data processing module, wherein the benchmark index attribute acquisition module is used for acquiring a project development and development plan, splitting the project development and development plan into a plurality of project tasks and abstracting a benchmark index attribute based on each project task;

the project offset data generation module is used for acquiring current project research and development process data, analyzing and counting the project research and development process data according to the trained risk estimation algorithm model and generating project offset data; the risk estimation algorithm model is obtained by training according to the benchmark index attribute and the historical item risk data;

and the key risk point prediction module is used for predicting to obtain the project risk type and the key risk point according to the project offset data.

A computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:

A computer storage medium having a computer program stored thereon, the computer program when executed by a processor implementing the steps of:

According to the project risk prediction method and system based on the project research and development process, the acquired project research and development plan is divided into a plurality of project tasks, and the benchmark index attribute is abstracted based on each project task. The method comprises the steps of obtaining current project research and development process data, conducting analysis statistics on the project research and development process data according to a risk estimation algorithm model obtained based on benchmark index attributes and historical project risk data training, generating project offset data, and obtaining project risk types and key risk points through prediction according to the project offset data. The risk prediction algorithm model is obtained through collecting data of all parties generating the project risks, then the project research and development process data generated in the project research and development process are combined, project deviation data in the project process are output in real time through the risk prediction algorithm model, project risk types and key risk points in the future stage are determined by integrating the project deviation data, the risk point management omission can be avoided, the reasonable state of the project risk points is maintained, and the risk management and control efficiency is improved.

Drawings

FIG. 1 is a diagram illustrating an example of an application scenario of a project risk prediction method based on a project development process;

FIG. 2 is a schematic flow diagram of a project risk prediction method based on a project development process in one embodiment;

FIG. 3 is a diagram illustrating a relationship between project development factors and benchmark index attributes in one embodiment;

FIG. 4 is a flow diagram that illustrates the generation of project offset data, in one embodiment;

FIG. 5 is a schematic flow chart illustrating a method for predicting risk of a project based on the development process of the project in another embodiment;

FIG. 6 is a schematic diagram illustrating a risk cue effect of a project risk prediction method based on a project development process in an embodiment;

FIG. 7 is a block diagram of a project risk prediction system based on a project development process, in one embodiment;

FIG. 8 is a block diagram of a project risk prediction system based on a project development process in another implementation;

FIG. 9 is a diagram illustrating an internal structure of a computer device according to an embodiment.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.

The project risk prediction method based on the project research and development process can be applied to the application environment shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network. The server 104 splits the project research and development plan into a plurality of project tasks by acquiring the project research and development plan, and abstracts the benchmark index attributes based on each project task. The current project research and development process data are obtained, the project research and development process data are analyzed and counted according to the trained risk estimation algorithm model, project deviation data are generated, the project risk type and the key risk points are predicted according to the project deviation data, and the project risk type and the corresponding key risk points can be fed back to the terminal 102. The project development plan and the project development process data may be stored locally in the terminal 102, or may be stored in the cloud storage of the server 104. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices, and the server 104 may be implemented by an independent server or a server cluster formed by a plurality of servers.

In one embodiment, as shown in fig. 2, a project risk prediction method based on a project development process is provided, which is described by taking the method as an example applied to the server in fig. 1, and includes the following steps:

step S202, a project research and development plan is obtained, the project research and development plan is divided into a plurality of project tasks, and the benchmark index attribute is abstracted based on each project task.

Specifically, a project research and development plan is acquired, the project research and development plan is divided into a plurality of project tasks, and project research and development elements are extracted respectively based on the project tasks, wherein the project research and development elements comprise project tasks, project requirements and project research and development personnel distribution.

Further, the corresponding benchmark index attribute may be abstracted based on each project development element. Referring to fig. 3, it can be seen that the benchmark index attribute corresponding to the project task includes task plan completion time, task complexity coefficient, task core point coefficient and task innovation coefficient, the benchmark index attribute corresponding to the project requirement includes staging cost and staging milestone, and the benchmark index attribute corresponding to the project developer includes post category, post level, technical characteristics and technical capability coefficient.

In one embodiment, after acquiring the project development plan, the method further includes: and (4) counting project milestone time, project quality targets and project resource investment corresponding to the project research and development plan.

The project milestones are key nodes in project management, such as stage acceptance and project quality indexes, and are data representations of requirements on development quality. The project progress indicator is a reference baseline for project completion, and the staff efficiency indicator is a reference indicator for configuration staff at the beginning of the project.

Further, the project task plan includes the predicted completion time of the split project task, the acceptance index of the task, the human cost prediction of the task, the Case number of the task test, the importance level of the task, the influence range of the task and other attributes and measurement indexes related to the specific project task. The ideal progress in the plan refers to the expected progress of the project, and belongs to normal progress planning under all smooth conditions. The personnel efficiency refers to a reference value for comprehensively evaluating factors such as the skill level of personnel, project experience, comprehensive quality and the like, and the larger the reference value is, the higher the skill level of the personnel is, the higher the corresponding task completing capability is, and the lower the time cost is. Planned completion refers to ideal completion, which if the target task is completed within the plan, indicates early completion.

And step S204, acquiring current project research and development process data, analyzing and counting the project research and development process data according to the trained risk estimation algorithm model, and generating project offset data.

Specifically, by classifying the project research and development process data, different categories of project research and development process data are generated. The research and development process data indexes comprise the number of use cases related to the tasks, the number of Bug generated by the tasks, the number of man-hour for completing the tasks, the code quality, the innovation score and the like. And performing data index extraction on the project research and development process data of different categories according to the incidence relation to generate the associated project index.

And further, according to the trained risk estimation algorithm model, performing risk score evaluation on each project index, and generating project offset data corresponding to the project task according to the risk score of each project index obtained through evaluation. The risk estimation algorithm model is obtained by training according to the reference index attribute and the historical item risk data.

And step S206, predicting the project risk type and the key risk point according to the project offset data.

Specifically, the project offset type and the offset influence degree corresponding to the project research and development process are determined by analyzing the project offset data. Wherein the project offset types include a project progress offset type, a project quality offset type, and a human cost offset type.

Furthermore, a corresponding predicted risk type can be determined according to the project offset type, and further, a key risk point causing project offset in the project research and development process is determined according to the offset influence degree and the predicted risk type.

The risk types comprise delay risks and technical difficulty risks corresponding to project progress deviation types, resource risks corresponding to human cost deviation types and quality risks corresponding to project quality deviation types.

It is emphasized that the item offset data may also be stored in a node of a blockchain in order to further ensure privacy and security of the item offset data.

According to the project risk prediction method based on the project research and development process, the acquired project research and development plan is divided into a plurality of project tasks, and the benchmark index attribute is abstracted based on each project task. The method comprises the steps of obtaining current project research and development process data, analyzing and counting the project research and development process data according to a risk estimation algorithm model obtained based on reference index attributes and historical project risk data training, generating project deviation data, and predicting to obtain project risk types and key risk points according to the project deviation data. The risk prediction algorithm model is obtained through collecting data of all parties generating the project risks, then the project research and development process data generated in the project research and development process are combined, project deviation data in the project process are output in real time through the risk prediction algorithm model, project risk types and key risk points in the future stage are determined by integrating the project deviation data, the risk point management omission can be avoided, the reasonable state of the project risk points is maintained, and the risk management and control efficiency is improved.

In an embodiment, as shown in fig. 4, the step of generating the project migration data, that is, the step of analyzing and counting the project development process data according to the trained risk estimation algorithm model to generate the project migration data specifically includes the following steps:

and step S402, classifying the project research and development process data to generate different types of project research and development process data.

Specifically, the current project research and development process data is the ground research and development process data which can be accurately and practically recorded in a daily unit at least, wherein the research and development process data can be divided into: project progress research and development data, project quality research and development data, project resource configuration data, project task splitting data, personnel input time data and the like. The data classification is based on the fact that classification analysis of the project research and development process is convenient to achieve, risk calculation of different categories is convenient, and different risk types are all related to project tasks.

And S404, acquiring the incidence relation of the project research and development process data of different categories, and performing data index extraction on the project research and development process data of different categories according to the incidence relation to generate the associated project indexes.

Specifically, analysis statistics and data index extraction are performed on different types of project research and development process data, such as project progress research and development data, project quality research and development data, project resource configuration data, project task split data, personnel input time data and the like, included in the project research and development process. The method specifically comprises the steps of carrying out data index extraction on project research and development process data of each category, establishing an association relation among the project research and development process data of different categories, and further generating associated project indexes.

And step S406, evaluating the risk value of each project index according to the trained risk estimation algorithm model.

Specifically, according to the trained risk estimation algorithm model, risk score evaluation is performed on project indexes included in different project tasks. The risk score of the project index comprises a postponed risk score, a resource risk score and a quality score of the project task.

Further, the deferred risk score evaluation result is obtained by calculation according to the actual completion score, the plan completion score, the task complexity coefficient and the core point coefficient of the project task. The resource risk score evaluation result is obtained by calculating the man-hour superposition required by the task type of the project, the man-hour number that the resource can bear within a certain time period and the loss coefficient. And the quality risk score evaluation result is obtained by comprehensive superposition calculation of various data indexes of the project task.

And step S408, generating project offset data corresponding to the project task according to the risk score of each project index obtained through evaluation.

Specifically, the project offset data corresponding to the project tasks are generated by obtaining risk score evaluation results of the project tasks for different risk types, including deferred risk score evaluation results, resource risk score evaluation results, quality risk score evaluation results and the like.

And determining a project offset type and an offset influence degree corresponding to the project task according to the project offset data, wherein the project offset type comprises a project progress offset type, a project quality offset type and a human cost offset type. Each shift influence level is a dynamic value that is generated for reference based on a reference initially established for the project plan.

Further, taking the project schedule offset as an example, it can be understood that the original plan completes 3 tasks each day, the actual first day completes 2 tasks, the second day completes 4 tasks, and each day will generate an offset between the actual and the plan.

In this embodiment, the project research and development process data of different categories are generated by classifying the project research and development process data, the incidence relation of the project research and development process data of different categories is obtained, and then the data index extraction is performed on the project research and development process data of different categories according to the incidence relation, so as to generate the associated project index. And according to the trained risk estimation algorithm model, performing risk score evaluation on each project index, and generating project offset data corresponding to the project task according to the risk score of each project index obtained through evaluation. The classification analysis of project research and development process data and the risk score evaluation of different risk types are realized, and the accuracy of the key risk points determined according to the project deviation data obtained through comprehensive risk evaluation is higher because the obtained project deviation data can be used for determining the key risk points.

In one embodiment, as shown in fig. 5, a project risk prediction method based on a project development process is provided, which includes the following steps:

and step S502, acquiring a risk point eliminating measure corresponding to the key risk point.

Specifically, risk point elimination measures corresponding to key risk points of different project risk types are obtained. The risk point eliminating measures comprise a time management strengthening measure, a working hour increasing measure and a task plan duplication measure corresponding to the postponing risk type, and a quality management and control strengthening measure, a quality unit test coverage measure and a quality management and control strengthening measure corresponding to the quality risk type.

Step S504, risk point eliminating measures are executed, key risk points are corrected, and updated research and development process data are generated.

Specifically, the correction of the key risk points is triggered according to the risk elimination measures, so that the project returns to the preset reference value, new project research and development process data are generated in the correction process of the project risk points and after the project risk points are corrected, and the new project research and development process data can be used as sample data used by the next risk estimation algorithm model.

And S506, taking the updated research and development process data as sample data of the risk prediction algorithm model, and updating the risk prediction algorithm model according to the sample data.

Specifically, the updated research and development process data is used as sample data of the risk prediction algorithm model, and the risk prediction algorithm model required to be used next time is retrained according to the sample data to obtain the updated risk prediction algorithm model.

And step S508, correcting the project offset data according to the updated risk estimation algorithm model.

Specifically, an updated risk estimation algorithm model obtained after training by using new research and development process data is obtained, project offset data is corrected according to the updated risk estimation algorithm model, and the reasonable state of each key risk point corresponding to the project offset data is maintained.

In the project risk prediction method based on the project research and development process, the key risk points are corrected by acquiring the risk point eliminating measures corresponding to the key risk points and executing the risk point eliminating measures, so as to generate updated research and development process data. The updated research and development process data is used as sample data of the risk prediction algorithm model, the risk prediction algorithm model is updated according to the sample data, and further project offset data can be corrected according to the updated risk prediction algorithm model. The risk estimation algorithm model is updated according to new research and development process data, further correction of project offset data is achieved, accuracy of key risk points determined according to the project offset data is improved, management and control of the risk points are facilitated to be carried out in advance, and risk management and control effects of research and development projects are improved.

In one embodiment, the method for training the risk prediction algorithm model according to the benchmark index attribute and the historical item risk data includes:

determining a postponing risk level of a corresponding historical project according to the historical project risk data;

and training the original prediction model according to the risk evaluation result and the reference index attribute to generate a trained risk estimation algorithm model.

Specifically, the deferred risk classes include low-level risks, intermediate-level risks, and high-level risks, wherein the low-level risks indicate that the deferred risk score evaluation result thereof is less than the plan completion score 0.5, the intermediate-level risks indicate that the deferred risk score evaluation result thereof is greater than the plan completion score 0.5 and is less than the plan completion score, and the high-level risks indicate that the deferred risk score evaluation result thereof is greater than the plan completion score.

Wherein, the single task postponement risk score is (actual completion score-planned completion score) task complexity coefficient is core point coefficient.

Furthermore, the comprehensive risk scores of a plurality of tasks and the labor hour scores of all task plans in the research and development period are measured according to the postponed risk grade rule, so that the postponed risk of the whole project can be estimated. And then training the original prediction model according to the risk assessment result and the reference index attribute to generate a trained risk estimation algorithm model.

For example, in the current project cycle, delay of three tasks is generated, delay risks of the three tasks are different, delay risk early warning is different, risk suggestions are different, and if the total number of tasks in the current project cycle is 10, 3 of the tasks are delayed, the delay risk of the whole project can be obtained. Specific examples of corresponding risk suggestions are set according to different project task completion conditions, postponing risk levels and the like, and are shown in table 1.

TABLE 1

Aiming at low-level risks, the set risk suggestions are used for strengthening time management, aiming at intermediate-level risks, the set risk suggestions are used for increasing working hours in the later period for prediction, and aiming at high-level risks, project plans are judged and determined to need to be repeated according to difficulty and core coefficients.

In this embodiment, according to the historical item risk data, a postponing risk level corresponding to the historical item is determined, and according to the postponing risk level, postponing risk assessment is performed on each historical item to generate a corresponding risk assessment result, and then according to the risk assessment result and the reference index attribute, the original prediction model is trained to generate a trained risk estimation algorithm model. The risk assessment method and the risk assessment system have the advantages that the risk assessment result obtained by carrying out delay risk assessment on the historical project and the actually determined reference index attribute are trained to obtain the risk estimation algorithm model associated with the delay risk, delay risk early warning in the future stage of the research and development project is achieved on the basis of the risk estimation algorithm model associated with the delay risk, the problem that the project is delayed or interrupted due to the delay risk in the research and development process is solved, and the development efficiency of the research and development project is improved.

In one embodiment, the project risk types also include technical difficulty risks; according to the reference index attribute and the historical item risk data, training to obtain a risk estimation algorithm model, which comprises the following steps:

acquiring a target project task with the estimated difficulty coefficient threshold value larger than a preset difficulty coefficient threshold value;

and training to obtain a risk estimation algorithm model according to the reference index attribute and the risk prediction result.

Specifically, by acquiring a project plan of an existing research and development project, splitting the project plan into tasks, and presetting an estimated difficulty coefficient value or a difficulty level for each task. Wherein, the grade value of each difficulty grade can be customized or adjusted. And allocating different levels of human input and plans of the research and development period according to the difficulty coefficient. The method can determine how to specifically distribute the human input according to the indexes such as personnel efficiency, personnel level, professional ability of personnel and the like, and the larger the difficulty coefficient is, the longer the corresponding research and development period is, so that the data of the basic reference index can be landed.

Further, in the process of project research and development, by calculating various data of each task falling to the ground in real time, including task progress data, task quality data and human input data (namely, the proportion of personnel input into research and development and the like), target project tasks with the estimated difficulty coefficient threshold value larger than the preset difficulty coefficient threshold value are determined, and the summarizing and analyzing of the target project tasks with the difficulty coefficient larger than the preset difficulty coefficient threshold value are realized.

The completion condition, quality condition and delay condition of the task with large difficulty coefficient can be displayed in real time in a preset period, so that the risks of the technical difficulties can be predicted in a unified manner, and a corresponding risk prediction result is generated. And then training to obtain a risk estimation algorithm model according to the reference index attribute and the risk prediction result.

In an embodiment, as shown in fig. 6, a risk prompting effect schematic diagram of a project risk prediction method based on a project research and development process is provided, and referring to fig. 6, for a preset prompting period, for example, within 5 days, a corresponding comparison effect schematic diagram is obtained by comparing the daily planned task number and the predicted risk point number.

In the embodiment, the target project tasks with the pre-estimation difficulty coefficient threshold value larger than the preset difficulty coefficient threshold value are obtained, the task data of each target project task in the project research and development process are obtained, the technical difficulty risk prediction is carried out according to the task data, and the corresponding risk prediction results are generated, so that the risk prediction algorithm model can be obtained through training according to the reference index attribute and the risk prediction results. The risk assessment method and the risk assessment system have the advantages that the risk assessment result obtained by predicting the technical difficulty risks of the task data and the actually determined reference index attribute are trained to obtain the risk estimation algorithm model associated with the technical difficulty risks, delay risk early warning in the future stage of the research and development project is achieved on the basis of the risk estimation algorithm model associated with the technical difficulty risks, the problem that the project is delayed or interrupted due to the technical difficulty risks in the research and development process is solved, and the development efficiency of the research and development project is further improved.

In one embodiment, the project risk type further includes resource risk, and the method for training the obtained risk prediction algorithm model according to the benchmark index attribute and the historical project risk data includes:

acquiring basic resources designed by a research and development project and a calculation formula of risk scores of the resources;

calculating actual resource risk data according to a calculation formula of each resource risk score based on the real-time acquired research and development project process data;

and training to obtain a risk estimation algorithm model according to the reference index attribute and the actual resource risk data.

Specifically, taking a research and development personnel as a research object of project resources as an example, in the development process of an IT project, the ratio and the capacity of the stations of the research and development personnel are key factors of normal progress of the IT project, and for the management of the research and development personnel, basic resources to be considered include project initial planning front-end resources, service resources, test resources, operation and maintenance resources and the like. The resources can be reasonably configured according to the actual output of the resources, the assessment and the capability improvement of the resources are more accurately and digitally identified, the risks of research and development personnel are identified, and the progress of the project is predicted.

Further, a front-end resource risk score calculation formula is specifically as follows:

front-end resource risk score (superposition of man-hours required by front-end task type-man-hours that front-end resources can be accepted in a certain time period) is loss coefficient;

according to a specific calculation formula, the preparation conditions of each resource, including the initial resource and task matching conditions, can be calculated at the beginning of a project plan, actual resource risk data at different stages are obtained through prediction at the beginning of the plan, and a risk estimation algorithm model is obtained through training according to the reference index attribute and the actual resource risk data.

In one embodiment, the project risk types also include quality risks; according to the reference index attribute and the historical item risk data, training to obtain a risk estimation algorithm model, which comprises the following steps:

calculating the quality value of each project task by using operations such as classification, aggregation, association and the like;

performing quality evaluation on the single project task to generate a quality evaluation result corresponding to each project task;

and training to obtain a risk estimation algorithm model according to the reference index attribute and the quality evaluation result.

Specifically, the calculation formula of the quality evaluation result for each project task is as follows: and the quality evaluation result is the comprehensive superposition of the evaluation results of the task indexes of each project task. The higher the quality score is, the better the quality is, a quality reference standard value can be preset, for example, if all indexes meet the requirements, the reference value is 100, and the proportion of all indexes can be customized or modified according to the setting of an actual project.

For example, the reference standard values of the risk scores of the preset items are as follows:

if the quality evaluation result is greater than 70 points, the quality requirement is met; 50< quality evaluation result <70, basically reaching the standard; and the quality evaluation result is less than 50, which is that the standard is not reached.

And the project tasks with the quality scores not meeting the standard need to be analyzed specifically, and reference risk early warning and improvement suggestions are given according to the synthesis of specific indexes. Specific examples of corresponding risk suggestions are set according to the scoring conditions of different project tasks, the quality scores and the like, and are shown in table 2.

TABLE 2

The risk suggestion of the project task with the quality divided into the low grade is the reinforced unit test coverage, the risk suggestion of the project task with the quality divided into the middle grade is the reinforced quality control, and the risk suggestion with the quality divided into the high grade is the better quality.

In the embodiment, actual resource risk data are obtained through calculation according to the resource risk value calculation formulas based on real-time acquired research and development project process data and the resource risk value calculation formulas, and then a risk estimation algorithm model associated with resource risks is obtained through training according to the benchmark index attributes and the actual resource risk data. Calculating the quality value of each project task and performing quality evaluation on a single project task by using operations such as classification, aggregation, association and the like to generate quality evaluation results corresponding to each project task, and training to obtain a risk estimation algorithm model associated with quality risk according to the reference index attribute and the quality evaluation results. The risk prediction algorithm model associated with the resource risk and the updated prediction algorithm model associated with the quality risk are realized, the delay risk early warning of the future stage of the research and development project is realized, the problem of project delay or interruption caused by the technical difficulty risk in the research and development process is avoided, and the development efficiency of the research and development project is further improved.

It should be understood that although the steps in the flowcharts of fig. 2, 4 and 5 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2, 4, and 5 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performing the sub-steps or stages is not necessarily sequential, but may be performed alternately or alternatingly with other steps or at least some of the sub-steps or stages of other steps.

In one embodiment, as shown in fig. 7, a project risk prediction system based on a project development process is provided, comprising: a benchmark index attribute obtaining module 702, a project deviation data generating module 704, and a key risk point predicting module 706, wherein:

the benchmark index attribute obtaining module 702 is configured to obtain a project research and development plan, split the project research and development plan into a plurality of project tasks, and abstract the benchmark index attribute based on each project task.

And the project offset data generation module 704 is used for acquiring current project research and development process data, analyzing and counting the project research and development process data according to the trained risk estimation algorithm model, and generating project offset data.

And a key risk point prediction module 706, configured to predict a project risk type and a key risk point according to the project offset data.

In the project risk prediction system based on the project research and development process, the acquired project research and development plan is divided into a plurality of project tasks, and the benchmark index attribute is abstracted based on each project task. The method comprises the steps of obtaining current project research and development process data, analyzing and counting the project research and development process data according to a risk estimation algorithm model obtained based on reference index attributes and historical project risk data training, generating project deviation data, and predicting to obtain project risk types and key risk points according to the project deviation data. The risk prediction algorithm model is obtained through collecting data of all parties generating the project risks, then the project research and development process data generated in the project research and development process are combined, project deviation data in the project process are output in real time through the risk prediction algorithm model, project risk types and key risk points in the future stage are determined by integrating the project deviation data, the risk point management omission can be avoided, the reasonable state of the project risk points is maintained, and the risk management and control efficiency is improved.

In one embodiment, as shown in fig. 8, a project risk prediction system based on a project development process is provided, including: a risk point elimination measure obtaining module 802, a research and development process data updating module 804, a risk estimation algorithm model updating module 806 and a project deviation data correcting module 808, wherein:

a risk point eliminating measure obtaining module 802, configured to obtain a risk point eliminating measure corresponding to the key risk point.

And the research and development process data updating module 804 is used for executing risk point eliminating measures, correcting the key risk points and generating updated research and development process data.

And a risk prediction algorithm model updating module 806, configured to use the updated research and development process data as sample data of the risk prediction algorithm model, and update the risk prediction algorithm model according to the sample data.

And the project offset data correction module 808 is used for correcting the project offset data according to the updated risk estimation algorithm model.

According to the project risk prediction system based on the project research and development process, the risk estimation algorithm model is updated according to the new research and development process data, and the project offset data is further corrected, so that the accuracy of the key risk points determined according to the project offset data is improved, the risk points can be managed and controlled in advance, and the risk management and control effect of the research and development project is improved.

In one embodiment, the item offset data generation module is further to:

classifying the project research and development process data to generate different categories of project research and development process data; acquiring incidence relations of the project research and development process data of different categories, and performing data index extraction on the project research and development process data of different categories according to the incidence relations to generate associated project indexes; according to the trained risk estimation algorithm model, performing risk score evaluation on each project index; and generating project offset data corresponding to the project task according to the risk score of each project index obtained through evaluation.

In the embodiment, the classification analysis of the project research and development process data and the risk score evaluation of different risk types are realized, and the accuracy of the key risk points determined according to the project offset data obtained through comprehensive risk evaluation is higher because the obtained project offset data can be used for determining the key risk points.

In one embodiment, a project risk prediction system based on a project development process is provided, further comprising a risk prediction algorithm model training module, configured to:

determining a postponing risk level of a corresponding historical project according to the historical project risk data; according to the postponing risk level, performing postponing risk assessment on each historical project to generate a corresponding risk assessment result; and training the original prediction model according to the risk evaluation result and the reference index attribute to generate a trained risk estimation algorithm model.

In the embodiment, the risk assessment result obtained by carrying out delay risk assessment on the historical project and the actually determined reference index attribute are trained to obtain the risk estimation algorithm model associated with the delay risk, delay risk early warning in the future stage of the research and development project is realized on the basis of the risk estimation algorithm model associated with the delay risk, the problem of project delay or interruption caused by delay risk in the research and development process is avoided, and the development efficiency of the research and development project is improved.

In one embodiment, the risk prediction algorithm model training module is further configured to:

acquiring an estimated difficulty coefficient value set for each existing project task; acquiring a target project task with the estimated difficulty coefficient threshold value larger than a preset difficulty coefficient threshold value; acquiring task data of each target project task in a project research and development process; the task data comprises task progress data, task quality data and human input data; performing technical difficulty risk prediction according to the task data to generate a corresponding risk prediction result; and training to obtain a risk estimation algorithm model according to the reference index attribute and the risk prediction result.

In the embodiment, the risk assessment result obtained by predicting the technical difficulty risk of the task data and the actually determined reference index attribute are trained to obtain the risk prediction algorithm model associated with the technical difficulty risk, the deferred risk early warning of the future stage of the research and development project is realized on the basis of the risk prediction algorithm model associated with the technical difficulty risk, the problem of project lag or interruption caused by the technical difficulty risk in the research and development process is avoided, and the development efficiency of the research and development project is further improved.

acquiring basic resources designed by a research and development project and a calculation formula of risk scores of the resources; calculating actual resource risk data according to a calculation formula of each resource risk score based on the real-time acquired research and development project process data; training to obtain a risk estimation algorithm model according to the reference index attribute and the actual resource risk data;

the risk prediction algorithm model training module is further used for:

calculating the quality value of each project task by using operations such as classification, aggregation, association and the like; performing quality evaluation on the single project task to generate a quality evaluation result corresponding to each project task; and training to obtain a risk estimation algorithm model according to the reference index attribute and the quality evaluation result.

In the embodiment, the risk estimation algorithm model associated with the resource risk and the updated estimation algorithm model associated with the quality risk are realized, the delay risk early warning in the future stage of the research and development project is realized, the problem of project delay or interruption caused by the technical difficulty risk in the research and development process is avoided, and the development efficiency of the research and development project is further improved.

In one embodiment, the reference index attribute obtaining module is further configured to:

acquiring a project research and development plan, and splitting the project research and development plan into a plurality of project tasks; respectively extracting project research and development elements based on each project task; the project research and development elements comprise project tasks, project requirements and project research and development personnel distribution; abstracting corresponding benchmark index attributes based on the research and development elements of each project; the basic index attributes corresponding to the project tasks comprise task plan completion time, a task complexity coefficient, a task core point coefficient and a task innovation coefficient; the benchmark index attributes corresponding to the project requirements include stage cost and stage milestones; the benchmark index attributes corresponding to the project research and development personnel comprise post categories, post grades, technical characteristics and technical capability coefficients.

In one embodiment, the key risk point prediction module is further to:

analyzing the project offset data, and determining a project offset type and an offset influence degree corresponding to the project research and development process; the project offset types comprise a project progress offset type, a project quality offset type and a human cost offset type; determining a corresponding prediction risk type according to the project offset type; the risk types comprise delay risks and technical difficulty risks corresponding to the project progress deviation type, resource risks corresponding to the human cost deviation type and quality risks corresponding to the project quality deviation type; and determining key risk points causing project deviation in the project research and development process according to the deviation influence degree and the predicted risk type.

For specific limitations of the project risk prediction system based on the project research and development process, reference may be made to the above limitations of the project risk prediction method based on the project research and development process, which are not described herein again. The various modules in the project risk prediction system based on the project development process described above may be implemented in whole or in part by software, hardware, and combinations thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.

In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 9. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is for storing project offset data. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a project risk prediction method based on a project development process.

Those skilled in the art will appreciate that the architecture shown in fig. 9 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.

In one embodiment, there is provided a computer device comprising a memory storing a computer program and a processor implementing the following steps when the processor executes the computer program:

acquiring a project research and development plan, splitting the project research and development plan into a plurality of project tasks, and abstracting a reference index attribute based on each project task;

acquiring current project research and development process data, analyzing and counting the project research and development process data according to a trained risk estimation algorithm model, and generating project offset data; the risk estimation algorithm model is obtained by training according to the reference index attribute and the historical item risk data;

In one embodiment, the processor, when executing the computer program, further performs the steps of:

acquiring a risk point eliminating measure corresponding to the key risk point;

executing a risk point eliminating measure, correcting the key risk point, and generating updated research and development process data;

correcting the project offset data according to the updated risk estimation algorithm model;

wherein the item offset data can be stored in the blockchain.

acquiring incidence relations of the project research and development process data of different categories, and performing data index extraction on the project research and development process data of different categories according to the incidence relations to generate associated project indexes;

according to the trained risk estimation algorithm model, performing risk score evaluation on each project index;

analyzing the project offset data, and determining a project offset type and an offset influence degree corresponding to the project research and development process; the project migration type comprises a project progress migration type, a project quality migration type and a human cost migration type;

determining a corresponding prediction risk type according to the project offset type; the risk types comprise delay risks and technical difficulty risks corresponding to the project progress deviation types, resource risks corresponding to the human cost deviation types and quality risks corresponding to the project quality deviation types;

and determining key risk points causing project deviation in the project development process according to the deviation influence degree and the predicted risk types.

abstracting corresponding benchmark index attributes based on the research and development elements of each project;

the basic index attributes corresponding to the project tasks comprise task plan completion time, a task complexity coefficient, a task core point coefficient and a task innovation coefficient; the benchmark index attributes corresponding to the project requirements include a staged cost and a staged milestone; the benchmark index attributes corresponding to the project research and development personnel comprise post categories, post grades, technical characteristics and technical capability coefficients.

In one embodiment, a computer storage medium is provided, having a computer program stored thereon, the computer program, when executed by a processor, implementing the steps of:

In one embodiment, the computer program when executed by the processor further performs the steps of:

acquiring a risk point eliminating measure corresponding to the key risk point;

wherein the item offset data can be stored in the blockchain.

analyzing the project offset data, and determining a project offset type and an offset influence degree corresponding to the project research and development process; the project offset types comprise a project progress offset type, a project quality offset type and a human cost offset type;

determining a delay risk level of a corresponding historical project according to the historical project risk data;

acquiring a target project task of which the estimated difficulty coefficient threshold is greater than a preset difficulty coefficient threshold;

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. 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).

The block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.

The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.

The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.

Claims

1. A project risk prediction method based on a project development process, the method comprising:

predicting to obtain a project risk type and a key risk point according to the project offset data;

predicting a project risk type and a key risk point according to the project deviation data, wherein the predicting comprises the following steps:

analyzing the project offset data, and determining a project offset type and an offset influence degree corresponding to a project research and development process; the project offset types comprise a project progress offset type, a project quality offset type and a human cost offset type; determining a corresponding prediction risk type according to the project offset type; the risk types comprise postponing risks and technical difficulty risks corresponding to the project progress deviation types, resource risks corresponding to the human cost deviation types and quality risks corresponding to the project quality deviation types; and determining key risk points causing project deviation in the project research and development process according to the deviation influence degree and the predicted risk type.

2. The method of claim 1, further comprising:

acquiring a risk point eliminating measure corresponding to the key risk point;

wherein the entry offset data may be stored into a blockchain.

3. The method of claim 1, wherein the step of performing analysis statistics on the project development process data according to the trained risk prediction algorithm model to generate project migration data comprises:

4. The method of claim 1, wherein the item risk types include a delay risk; training a mode of obtaining the risk estimation algorithm model according to the reference index attribute and the historical item risk data, wherein the mode comprises the following steps:

5. The method of claim 1, wherein the project risk types further include technical difficulty risks; training a mode of obtaining the risk estimation algorithm model according to the reference index attribute and the historical item risk data, wherein the mode comprises the following steps:

6. The method of claim 1, wherein the obtaining a project development plan, splitting the project development plan into a plurality of project tasks, and abstracting benchmark index attributes based on each of the project tasks comprises:

7. A project risk prediction system based on a project development process, the system comprising:

the key risk point prediction module is used for predicting to obtain a project risk type and a key risk point according to the project offset data;

the key risk point prediction module is further configured to: analyzing the project offset data, and determining a project offset type and an offset influence degree corresponding to a project research and development process; the project offset types comprise a project progress offset type, a project quality offset type and a human cost offset type; determining a corresponding prediction risk type according to the project offset type; the risk types comprise postponing risks and technical difficulty risks corresponding to the project progress deviation types, resource risks corresponding to the human cost deviation types and quality risks corresponding to the project quality deviation types; and determining key risk points causing project deviation in the project research and development process according to the deviation influence degree and the predicted risk type.

8. The system of claim 7, wherein the item offset data generation module is further configured to:

classifying the project research and development process data to generate different categories of project research and development process data; acquiring incidence relations of the project research and development process data of different types, and performing data index extraction on the project research and development process data of different types according to the incidence relations to generate associated project indexes; according to the trained risk estimation algorithm model, performing risk score evaluation on each project index; and generating project offset data corresponding to the project task according to the risk score of each project index obtained through evaluation.

9. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 6 when executing the computer program.

10. A computer storage medium on which a computer program is stored, characterized in that the computer program, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 6.