A demand review method based on big data analysis

Abstract

The application discloses a demand review method based on big data analysis, which comprises the following steps: collecting various demands to form a demand list of project establishment, and setting a business label according to the business involved in the demand list; determining a project establishment proposal according to the demand list of each project establishment, setting a review weight of different demand dimensions for the project establishment proposal, and obtaining a weighted result; collecting historical project data, combining big data, and performing semantic analysis on project description to identify the business keywords corresponding to the business label in the historical project; performing business coincidence degree analysis on the business label involved in the project establishment proposal and the business keywords in the historical project to obtain a coincidence degree result; and determining the business label for final review according to the weighted result and the coincidence degree result, and obtaining the final project establishment. Through the coincidence degree analysis on the business and the setting of the review weight for the project establishment proposal, the demand review business is obtained, and the review efficiency is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of big data review, and particularly relates to a demand review method based on big data analysis. BACKGROUND

[0002] Currently, the investment plan management reports the project establishment demand through the investment plan system every year, carries out the feasibility study review and project establishment work. Among them, the informationization project demand is scattered, the collection and communication means is single, no systematic demand collection and communication mechanism is formed, the demand details cannot be conveniently traced back and tracked, the demand problems cannot be analyzed by big data and intelligently reviewed, and the informationization project goal is easy to be unclear.

[0003] A large number of project establishment demands are analyzed by human combing, the demand problems cannot be fed back in time, and cannot be repaired in time. The repeated demands of each unit need to spend too much time to investigate, and it is difficult to avoid, resulting in long demand collection time and low efficiency. SUMMARY

[0004] The purpose of the present application is to provide a demand review method based on big data analysis, which can solve the problem of low demand review efficiency caused by the large number of project establishment demands through artificial analysis in the prior art.

[0005] The purpose of the present application is achieved by the following technical scheme:

[0006] The present application provides a demand review method based on big data analysis, comprising the following steps:

[0007] The demands are summarized to form a demand list of project establishment, and a business tag is set according to the business involved in the demand list;

[0008] The project establishment suggestion is determined according to the demand list of each project establishment, and the review weight of different demand dimensions is set for the project establishment suggestion to obtain a weighted result;

[0009] The historical project data is collected, and the semantic analysis of the project description is carried out in combination with big data to identify the business keywords corresponding to the business tags in the historical projects;

[0010] The business coincidence degree analysis is carried out in combination with the business tags involved in the project establishment suggestion and the business keywords in the historical projects to obtain a coincidence degree result;

[0011] According to the weighted result and the coincidence degree result, the business tags for final review are determined, and the final project establishment is obtained.

[0012] Further, the collection history project data, and combine big data to project description carries on semantic analysis, identifies the business keyword corresponding to the business label in the history project, and specifically includes:

[0013] Collecting historical project establishment, according to the corresponding relationship between the establishment function item of historical project establishment and business label, and combining big data to carry out semantic analysis on the establishment description, the business keyword corresponding to the business label is identified;

[0014] Collecting historical project demand, according to the corresponding relationship between the establishment function item involved in historical project demand and business label, and combining big data to carry out semantic analysis on the demand description, the business keyword corresponding to the business label is identified;

[0015] Collecting historical project problem, according to the corresponding relationship between the function optimization suggestion establishment involved in historical project problem and business label, and combining big data to carry out semantic analysis on the problem description, the business keyword corresponding to the business label is identified.

[0016] Further, the coincidence degree result includes:

[0017] The coincidence degree result between the business label involved in the project establishment suggestion and the business involved in the historical project demand;

[0018] The coincidence degree result between the business label involved in the project establishment suggestion and the business involved in the historical project problem;

[0019] The coincidence degree result between the business labels involved in the project establishment suggestions of each unit.

[0020] Further, the business label setting according to the business involved in the demand list includes:

[0021] The business classification setting is carried out on the business involved in the demand list, and the hierarchical business label is formed according to the business classification.

[0022] The beneficial effects of the application are:

[0023] 1. The demand review method based on big data analysis of the application compares the business of historical project with the demand business of each unit, sets review weight for project establishment suggestion, obtains the final demand review business, and then assists personnel review, improves the efficiency of demand review.

[0024] 2. The demand review method based on big data analysis of the application further improves the review efficiency of the reviewer by classifying the business label. BRIEF DESCRIPTION OF DRAWINGS

[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained from these drawings without creative labor.

[0026] Figure 1 A flowchart of a requirement review method based on big data analysis;

[0027] Figure 2 A logic diagram of a requirement review method based on big data analysis. DETAILED DESCRIPTION

[0028] The embodiments of the present disclosure will be described in detail below with reference to the drawings.

[0029] The embodiments of the present disclosure will be described in detail below with reference to the drawings.

[0030] Please refer to Figure 1 and Figure 2 , the embodiments of the present application provide a requirement review method based on big data analysis, comprising the following steps:

[0031] Step S1, aggregate all requirements to form a requirement list for project approval, and set a business tag according to the business involved in the requirement list.

[0032] Each unit aggregates all requirements to form a requirement list for project approval. For unclear requirements, requirement backtracking and tracking can be performed. After the requirements are clear, a business tag is set according to the business involved in the requirements, and finally a business tag library is obtained.

[0033] Step S2, determine a project approval suggestion according to the requirement list for project approval of each project, and set a review weight of different requirement dimensions for the project approval suggestion, to obtain a weighted result.

[0034] The project establishment work can be carried out regularly, the demand information of each unit is collected, the project construction range is determined, and the project establishment suggestion information is proposed. The project establishment suggestion should be reviewed from different dimensions such as demand urgency, coverage degree, economic benefit, social benefit, and the different dimensions are weighted to provide the evaluation standard basis for the evaluators. For example, the demand urgency accounts for the largest weight, and the weight proportion can be set to 50%. The higher the weight proportion is, the more sufficient the evaluation basis for the evaluators is, and the higher the demand evaluation score is.

[0035] Step S3, collect historical project data, and combine big data to perform semantic analysis on the project description to identify the business keywords corresponding to the business tags in the historical projects.

[0036] It should be noted that the related model of big data analysis and semantic screening of keywords is prior art, and there are many related semantic analysis and screening models at present, which will not be repeated here.

[0037] Step S4, business coincidence degree analysis is performed on the business tags involved in the project establishment suggestion and the business keywords in the historical projects to obtain the coincidence degree result. The coincidence degree result includes the following three kinds:

[0038] 1. The coincidence degree result between the business tags involved in the project establishment suggestion and the business involved in the historical project demand;

[0039] 2. The coincidence degree result between the business tags involved in the project establishment suggestion and the business involved in the historical project problem;

[0040] 3. The coincidence degree result between the business tags involved in the project establishment suggestions of each unit.

[0041] The most bottom layer tag coverage of the repeated construction business tag is identified, the coincidence degree of the historical project and the demand description in the business is judged through semantic analysis, so as to judge the possibility of repeated project establishment; the demand coincidence degree between the demands of each unit also needs to be analyzed through the tag and semantic analysis function, and the demands with high coincidence degree are combined. According to the coincidence degree analysis, the project establishment range can be adjusted.

[0042] Step S5, combining the weighted result and the coincidence degree result, the business tags for final evaluation are determined, and the final project establishment is obtained.

[0043] The business tags involved in the demand application are analyzed, the same or similar tags in the historical problems and other demand applications are extracted, the frequency of repeated reporting and the emergency degree of the tags are analyzed, and the necessity of the demand construction is analyzed. Specifically, the reviewer analyzes the business tags in the final review according to the weight proportion of different dimensions in the project demand, and the coincidence degree between the business tags involved in the project proposal and the business involved in the historical project demand and the coincidence degree between the business tags involved in the project proposal and the business involved in the historical project problem. The necessity of the business is analyzed, and the demands with high coincidence degree are combined. The business tags in the final review are obtained. According to the above, the repeated reporting demands and the project proposals with high frequency of repeated reporting of business problems are eliminated, and the final project proposal is obtained.

[0044] The repetition frequency of the repeated reporting demand and the repeated reporting business problem mentioned above can be set according to actual conditions, for example, the frequency of repeated reporting demand is more than 5 times, and the specific number of times can be flexibly set.

[0045] Through steps S1 to S5, the demand review template from demand reporting list, setting business tags, project proposal, business coincidence degree, business necessity analysis to final demand review is formed in turn. According to the project construction goal, the project review template is reasonably set, the review experts are organized to review the project demand according to the review requirements in the template, the business coincidence degree analysis results and the business necessity analysis results data obtained through big data analysis are displayed to the review experts during the review process, which provides reference for expert review. Using this template can improve the efficiency of project demand review.

[0046] Further, in a preferred embodiment of the application, the collection of historical project data and the semantic analysis of project description combined with big data to identify the business keywords corresponding to the business tags in the historical projects specifically include:

[0047] The historical projects consider project proposal, project demand and project problem.

[0048] I. Collect historical project proposal, according to the corresponding relationship between the establishment function item of historical project proposal and business tag, and combine big data (or manual way) to analyze the semantic analysis of the proposal description, and identify the business keywords corresponding to the business tags.

[0049] II. Collect historical project demand, according to the corresponding relationship between the establishment function item involved in the historical project demand and the business tag, and combine big data (or manual way) to analyze the semantic analysis of the demand description, and identify the business keywords corresponding to the business tags.

[0050] III. Collect historical project problems, establish the corresponding relationship with the business label according to the function optimization suggestion involved in the historical project problem, and combine big data (or manually sort out) to analyze the semantics of the problem description, and identify the business keywords corresponding to the business label. The project problem is: various business problems proposed by various units in the project construction and operation process.

[0051] By analyzing the semantics of the main description in the project establishment, project demand and project problem through big data (or manually sorting out), the business keywords corresponding to the business label in the historical project are identified, and the association with the business label is established.

[0052] Further, in a preferred embodiment of the application, the business label setting according to the business involved in the demand list comprises:

[0053] The business involved in the demand list is set for business classification, and the classified business label is formed according to the business classification. When the business overlap analysis and business necessity analysis are performed according to the classified business label, the specific method is as follows:

[0054] By setting the classified business label, when the business overlap analysis is performed, the weight is set according to the demand urgency, the business label with higher priority has higher weight; then the frequency of repeated reporting of the business label in the demand is counted. The demand review business can be screened out with high business weight proportion and low repeated reporting frequency.

[0055] By setting the classified business label, when the business overlap analysis is performed, the weight is set according to the problem urgency, the business label with higher priority has higher weight; then the frequency of repeated reporting of the business label in the problem is counted. The demand review business can be screened out with high business weight proportion and low repeated reporting frequency.

[0056] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described system, device and unit can refer to the corresponding process in the foregoing method embodiments, which will not be repeated here.

[0057] The above only illustrates the embodiments of the application and is not used to limit the application. Any modification, equivalent replacement, improvement, etc. made by those skilled in the art within the spirit and principles of the application without creative labor shall be included in the protection scope of the application.

Claims

1. A big data analysis based requirement review method, characterized in that, The method comprises the following steps: The project proposal is determined according to the project proposal list, and the review weight of different demand dimensions is set to obtain a weighted result. The historical project data is collected, and semantic analysis is performed on the project description in combination with big data to identify the business keywords corresponding to the business tags in the historical projects. The business overlap analysis is performed on the business tags involved in the project proposal and the business keywords in the historical projects to obtain an overlap result. The final review business tags are determined according to the weighted result and the overlap result, and the final project proposal is obtained, including: The historical problems and similar tags in other demand applications are extracted according to the business tags involved in the demand application, the frequency of repeated reporting and the tag emergency degree are analyzed, and the necessity of the demand construction is analyzed. The final review business tags are obtained. The repeated reporting demands and the project proposals with high frequency of repeated reporting of business problems are eliminated according to the above screening to obtain the final project proposal. The collection of historical project data and the semantic analysis of project description in combination with big data to identify the business keywords corresponding to the business tags in the historical projects specifically comprises: The historical project proposals are collected, the corresponding relationship between the establishment function items of the historical project proposals and the business tags is determined, and the semantic analysis of the proposal description in combination with big data is performed to identify the business keywords corresponding to the business tags. The historical project demands are collected, the corresponding relationship between the establishment function items involved in the historical project demands and the business tags is determined, and the semantic analysis of the demand description in combination with big data is performed to identify the business keywords corresponding to the business tags.

2. The big data analytics based requirement review method as claimed in claim 1, wherein, The historical project problems are collected, the corresponding relationship between the function optimization suggestion establishment involved in the historical project problems and the business tags is determined, and the semantic analysis of the problem description in combination with big data is performed to identify the business keywords corresponding to the business tags. The overlap result comprises: The overlap result between the business tags involved in the project proposal and the business involved in the historical project demands. The overlap result between the business tags involved in the project proposal and the business involved in the historical project problems.

3. The big data analytics based requirements review method as claimed in claim 2, wherein, The overlap result between the business tags involved in the project proposal of each unit. The business tag setting according to the business involved in the demand list comprises: The business classification setting is performed on the business involved in the demand list, and the classification business tags are formed according to the business classification.

Images