Project intelligent prediction and evaluation method, system and readable storage medium based on big data

Abstract

The embodiment of the present application provides a method, system and readable storage medium for intelligent prediction and evaluation of projects based on big data. The method includes: obtaining project attribute information and feature information of the project to be evaluated, extracting evaluation information data based on the project attribute information and feature information of the project to be evaluated to generate a feature portrait of the evaluation project, extracting an evaluation data package based on the feature portrait of the evaluation project, performing an indicator fit analysis on the project evaluation data set in the evaluation data package according to a first preset model to obtain project indicator fit data, performing project evaluation on the feature portrait of the evaluation project according to a second preset model to obtain project expected data, and correcting the project expected data based on the project evaluation data set and the project indicator fit data of the project to be evaluated to obtain project target data; thereby generating an evaluation project feature portrait based on the evaluation information data to perform project evaluation to obtain project expected data and correcting the project target data in combination with the project indicator fit data and the project evaluation data set to obtain project target data, thereby obtaining a high-precision technology for intelligent prediction and evaluation of projects based on big data.

Description

Technical Field

[0001] The present application relates to the technical field of big data and intelligent data processing, and specifically, to a method, system and readable storage medium for intelligent prediction and evaluation of projects based on big data. Background Art

[0002] Project evaluation is the review and evaluation of project design and application conducted by enterprises or institutions based on key research topics, research tasks or bidding projects. Currently, with the development of the economy and the emergence of multiple industries, the number of scientific and technological innovation projects has increased rapidly. Therefore, the number, categories and series of project applications in various industries have become more and more diversified and complex. How to conduct targeted evaluation of projects of different professions, different topics and different categories is a social issue.

[0003] At present, manual review is usually adopted for projects submitted by different industries and units and institutions, which limits the efficiency and effectiveness of the review. Since manual review is subject to great influence and is prone to errors or disagreements, it may lead to deviations in the review results between projects, affecting the correct and objective review of the projects, and thus leading to the common phenomenon of unreasonable, inaccurate and inefficient review.

[0004] Therefore, in response to the above problems, there is an urgent need to implement a technical solution that can conduct intelligent review of projects of different categories, industries, and subjects. Summary of the invention

[0005] The purpose of the embodiments of the present application is to provide a method, system and readable storage medium for intelligent prediction and evaluation of projects based on big data, which can realize high-precision intelligent prediction and evaluation of projects through big data.

[0006] The present application also provides a method for intelligent prediction and evaluation of projects based on big data, comprising the following steps:

[0007] Obtaining project attribute information and feature information of the project to be evaluated;

[0008] Extracting evaluation information data based on the project attribute information and feature information of the project to be evaluated to generate an evaluation project feature portrait, and extracting an evaluation data package based on the evaluation project feature portrait;

[0009] Performing an indicator consistency analysis on the project evaluation data set in the evaluation data package according to the first preset model to obtain project indicator consistency data;

[0010] Performing project evaluation on the evaluation project feature portrait according to the second preset model to obtain project expected data;

[0011] The project target data is obtained by correcting the project expected data according to the project evaluation data set and the project indicator consistency data of the project to be evaluated.

[0012] Optionally, in the project intelligent prediction and evaluation method based on big data described in the embodiment of the present application, the step of obtaining project attribute information and feature information of the project to be evaluated includes:

[0013] Obtain application information and project description information of the project to be evaluated;

[0014] Extracting project attribute information from the application information and project description information, including: R&D core information, technical field information, technical background information, and research subject information;

[0015] Characteristic information is obtained based on the project description information and project attribute information, including: key technology information, core research information, project magnitude data, research team information and project benefit indicator data.

[0016] Optionally, in the project intelligent prediction and evaluation method based on big data described in the embodiment of the present application, the step of extracting evaluation information data according to the project attribute information and feature information of the project to be evaluated to generate a feature portrait of the evaluation project includes:

[0017] Generate a project feature tree based on the R&D core information, technical field information, technical background information, research subject information, key technology information, core research information, project magnitude data, and research team information of the project to be evaluated;

[0018] The project feature tree includes team data information, frontier background information, core task information, surrounding policy information and budget financial information of the project to be evaluated;

[0019] Extracting evaluation information data according to the project feature tree, including: team R&D capability information, subject prospect information, project level information, financial support information and investment return information;

[0020] An assessment project feature portrait is generated based on the team's R&D capability information, subject prospect information, project level information, financial support information, and investment return information.

[0021] Optionally, in the project intelligent prediction and evaluation method based on big data described in the embodiment of the present application, the step of performing an indicator consistency analysis on the project evaluation data set in the evaluation data package according to the first preset model to obtain project indicator consistency data includes:

[0022] The evaluation data package is extracted through the evaluation information data in the characteristic portrait of the evaluation item;

[0023] The evaluation data package includes a project evaluation data set, including team R&D value data, achievement value data, number of project R&D patents, policy and funding support data, and project proposed profit data;

[0024] According to the project evaluation data set, a first preset model is input to calculate the index consistency of the project to be evaluated to obtain the project index consistency data.

[0025] Optionally, in the project intelligent prediction and evaluation method based on big data described in the embodiment of the present application, the step of performing project evaluation on the evaluation project feature portrait according to the second preset model to obtain project expected data includes:

[0026] Acquire a project database, wherein the project database includes project evaluation information data and project achievement data of completed evaluation projects of various categories;

[0027] A second preset model is obtained by training the project evaluation information data and project achievement data of each category of completed evaluation projects in the project database;

[0028] According to the team R&D capability information, subject prospect information, project level information, and financial support information of the project to be evaluated, input into the trained second preset model to obtain corresponding project achievement data;

[0029] The project achievement data include patent research and development data, research and production transformation value data, project profit data and secondary research and development value data;

[0030] The project profit data obtained from the project achievement data is used as the project expected data for the project to be evaluated.

[0031] Optionally, in the project intelligent prediction and evaluation method based on big data described in the embodiment of the present application, the step of correcting the project expected data according to the project evaluation data set and the project indicator consistency data of the project to be evaluated to obtain the project target data includes:

[0032] According to the project evaluation data set and project indicator consistency data of the project to be evaluated, combined with the project parameters of the project to be evaluated, the project profit data is corrected to obtain project target data;

[0033] The project target data calculation formula is:

[0034]

[0035] Among them, V is the project target data, σ is the team's industry value coefficient, and P is the team's R&D value data. is the project social value coefficient, H is the outcome value data, τ is the policy support coefficient, R is the obtained project profit data, a is the project risk coefficient, Q is the project indicator fit data, the team industry value coefficient, project social value coefficient, policy support coefficient and project risk coefficient are obtained by querying the third-party project evaluation platform based on the project to be evaluated.

[0036] In a second aspect, an embodiment of the present application provides a project intelligent prediction and evaluation system based on big data, the system comprising: a memory and a processor, the memory comprising a program of a project intelligent prediction and evaluation method based on big data, and the program of the project intelligent prediction and evaluation method based on big data is executed by the processor to implement the following steps:

[0037] Obtaining project attribute information and feature information of the project to be evaluated;

[0038] Extracting evaluation information data based on the project attribute information and feature information of the project to be evaluated to generate an evaluation project feature portrait, and extracting an evaluation data package based on the evaluation project feature portrait;

[0039] Performing an indicator consistency analysis on the project evaluation data set in the evaluation data package according to the first preset model to obtain project indicator consistency data;

[0040] Performing project evaluation on the evaluation project feature portrait according to the second preset model to obtain project expected data;

[0041] The project target data is obtained by correcting the project expected data according to the project evaluation data set and the project indicator consistency data of the project to be evaluated.

[0042] Optionally, in the project intelligent prediction and evaluation system based on big data described in the embodiment of the present application, the step of obtaining project attribute information and feature information of the project to be evaluated includes:

[0043] Obtain application information and project description information of the project to be evaluated;

[0044] Extracting project attribute information from the application information and project description information, including: R&D core information, technical field information, technical background information, and research subject information;

[0045] Characteristic information is obtained based on the project description information and project attribute information, including: key technology information, core research information, project magnitude data, research team information and project benefit indicator data.

[0046] Optionally, in the project intelligent prediction and evaluation system based on big data described in the embodiment of the present application, the step of extracting evaluation information data according to the project attribute information and feature information of the project to be evaluated to generate a feature portrait of the evaluation project includes:

[0047] Generate a project feature tree based on the R&D core information, technical field information, technical background information, research subject information, key technology information, core research information, project magnitude data, and research team information of the project to be evaluated;

[0048] The project feature tree includes team data information, frontier background information, core task information, surrounding policy information and budget financial information of the project;

[0049] Extracting evaluation information data according to the project feature tree, including: team R&D capability information, subject prospect information, project level information, financial support information and investment return information;

[0050] An assessment project feature portrait is generated based on the team's R&D capability information, subject prospect information, project level information, financial support information, and investment return information.

[0051] In the third aspect, an embodiment of the present application also provides a readable storage medium, which includes a project intelligent prediction and evaluation method program based on big data. When the project intelligent prediction and evaluation method program based on big data is executed by a processor, the steps of a project intelligent prediction and evaluation method based on big data as described in any one of the above items are implemented.

[0052] As can be seen from the above, the project intelligent prediction and evaluation method, system and readable storage medium based on big data provided by the embodiments of the present application obtain the project attribute information and feature information of the project to be evaluated, extract the evaluation information data according to the project attribute information and feature information of the project to be evaluated to generate an evaluation project feature portrait, extract the evaluation data package according to the evaluation project feature portrait, perform indicator consistency analysis on the project evaluation data set in the evaluation data package according to the first preset model to obtain project indicator consistency data, perform project evaluation on the evaluation project feature portrait according to the second preset model to obtain project expected data, and correct the project expected data according to the project evaluation data set and the project indicator consistency data of the project to be evaluated to obtain project target data; thereby generating an evaluation project feature portrait based on the evaluation information data to perform project evaluation to obtain project expected data and correct the project target data in combination with the project indicator consistency data and the project evaluation data set, thereby obtaining a high-precision technology for realizing intelligent prediction and evaluation of projects based on big data.

[0053] Other features and advantages of the present application will be described in the following description, and partly become apparent from the description, or be understood by practicing the embodiments of the present application. The purpose and other advantages of the present application can be realized and obtained by the structures specifically pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0055] Figure 1 A flowchart of a project intelligent prediction and evaluation method based on big data provided in an embodiment of the present application;

[0056] Figure 2 A flowchart of a project intelligent prediction and evaluation method based on big data provided in an embodiment of the present application;

[0057] Figure 3 A flowchart of a project intelligent prediction and evaluation method based on big data provided in an embodiment of the present application;

[0058] Figure 4 A schematic diagram of the structure of a project intelligent prediction and evaluation system based on big data provided in an embodiment of the present application. DETAILED DESCRIPTION

[0059] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0060] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0061] Please refer to Figure 1 , Figure 1 The flowchart of a project intelligent prediction and evaluation based on big data in some embodiments of the present application. The project intelligent prediction and evaluation method based on big data is used in terminal devices, such as mobile phones, computers, etc. The project intelligent prediction and evaluation method based on big data includes the following steps:

[0062] S101, obtaining project attribute information and feature information of the project to be evaluated;

[0063] S102, extracting evaluation information data according to the project attribute information and feature information of the project to be evaluated to generate an evaluation project feature portrait, and extracting an evaluation data package according to the evaluation project feature portrait;

[0064] S103, performing an indicator consistency analysis on the project evaluation data set in the evaluation data package according to the first preset model to obtain project indicator consistency data;

[0065] S104, performing project evaluation on the evaluation project feature portrait according to the second preset model to obtain project expected data;

[0066] S105: According to the project evaluation data set and project indicator consistency data of the project to be evaluated, the project expected data is corrected to obtain project target data.

[0067] It should be noted that first, the project attribute information and feature information of the project to be evaluated are obtained, and the evaluation information data is extracted to generate an evaluation project feature portrait and extract the evaluation data package. According to the project evaluation data set in the evaluation data package, the first preset model is input to calculate the indicator fit of the project to be evaluated to obtain the project indicator fit data. Then, according to the trained second preset model, the data information in the evaluation project feature portrait is evaluated to obtain the project profit data as the project expected data. Then, according to the data in the project evaluation data set combined with the project indicator fit data and the project coefficient, the project target data is corrected to obtain the project data, thereby realizing the intelligent technology for predicting and reviewing projects based on big data and improving the accuracy of the review and judgment of project data.

[0068] Please refer to Figure 2 , Figure 2 This is a flowchart of a project intelligent prediction and evaluation based on big data in some embodiments of the present application. According to an embodiment of the present invention, the project attribute information and feature information of the project to be evaluated are obtained as follows:

[0069] S201, obtaining application information and project description information of the project to be evaluated;

[0070] S202, extracting project attribute information from the application information and project description information, including: R&D core information, technical field information, technical background information, and research subject information;

[0071] S203. Acquire characteristic information according to the project description information and project attribute information, including: key technology information, core research information, project magnitude data, research team information and project benefit indicator data.

[0072] It should be noted that in order to achieve accurate prediction and review of the projects to be evaluated, it is necessary to collect relevant data information of the projects. The data information of the projects includes information on project themes, core topics, team information, financial information, policy support information, etc. By obtaining the application information and project description information of the projects to be evaluated, the project attribute information in the application information and project description information is extracted, including core R&D information, technical field information, technical background information and research subject information. Based on the project description information and project attribute information, feature information including key technology information, core research information, project magnitude data, research team information and project benefit indicator data is obtained, so as to prepare for data information collection for project prediction and review, so as to ensure the accuracy of project prediction and review.

[0073] Please refer to Figure 3 , Figure 3 It is a flowchart of a project intelligent prediction and evaluation based on big data in some embodiments of the present application. According to an embodiment of the present invention, the evaluation information data is extracted based on the project attribute information and feature information of the project to be evaluated to generate the evaluation project feature portrait, specifically:

[0074] S301, generating a project feature tree according to the R&D core information, technical field information, technical background information, research subject information, key technology information, core research information, project magnitude data, and research team information of the project to be evaluated;

[0075] S302, the project feature tree includes team data information, frontier background information, core task information, surrounding policy information and budget financial information of the project to be evaluated;

[0076] S303, extracting evaluation information data according to the project feature tree, including: team R&D capability information, subject prospect information, project level information, financial support information and investment return information;

[0077] S304. Generate an assessment project feature portrait based on the team's R&D capability information, subject prospect information, project level information, financial support information, and investment return information.

[0078] It should be noted that the project feature tree is a data information structure that describes the background architecture and project hardware of the project to be evaluated. It is dependent on a third-party project evaluation platform. The background data and component information of the project to be evaluated can be queried through the project feature tree. In this case, the project feature tree is collected and generated by the R&D core information, technical field information, technical background information, research subject information, key technology information, core research information, project magnitude data, and research team information of the project to be evaluated, including team data information, frontier background information, core task information, surrounding policy information, and budget financial information of the project to be evaluated. Evaluation information data including team R&D capability information, subject prospect information, project level information, financial support information, and investment return information are extracted according to the project feature tree to generate an evaluation project feature portrait. The evaluation project feature portrait is a digital depiction of the project's various resource information, including human resources, subject background, project level, financial resources, and investment return information. It is a digital map that reflects the background resources and organizational structure of the project implementation, which facilitates real-time acquisition of the background situation of project resources and project information.

[0079] According to an embodiment of the present invention, performing an indicator conformity analysis on the project evaluation data set in the evaluation data package according to the first preset model to obtain project indicator conformity data is specifically as follows:

[0080] The evaluation data package is extracted through the evaluation information data in the characteristic portrait of the evaluation item;

[0081] The evaluation data package includes a project evaluation data set, including team R&D value data, achievement value data, number of project R&D patents, policy and funding support data, and project proposed profit data;

[0082] According to the project evaluation data set, a first preset model is input to calculate the index consistency of the project to be evaluated to obtain the project index consistency data.

[0083] It should be noted that in order to evaluate the matching degree between data information such as project topics, R&D themes, and financial budgets and the indicator data of project bidding information, it is necessary to obtain the indicator matching data of the project. The project evaluation data set in the evaluation data package extracted from the evaluation project feature portrait includes team R&D value data, achievement value data, number of project R&D patents, policy and funding support data, and project proposed profit data, which are input into the first preset model for indicator matching calculation to obtain the project indicator matching data. Among them, the first preset model is a calculation model obtained through a third-party project evaluation platform;

[0084] The calculation formula for the project indicator consistency data is:

[0085]

[0086] Among them, Q represents the project indicator fit data, Y0 represents the project's expected profit data, Y1 represents the team's R&D value data, Y2 represents the achievement value data, Y3 represents the number of project R&D patents, Y4 represents policy and financial support data, ε, γ and λ are corresponding data response coefficients (obtained through the first preset model).

[0087] According to an embodiment of the present invention, the project evaluation is performed on the evaluation project feature portrait according to the second preset model to obtain the project expected data, specifically:

[0088] Acquire a project database, wherein the project database includes project evaluation information data and project achievement data of completed evaluation projects of various categories;

[0089] A second preset model is obtained by training the project evaluation information data and project achievement data of each category of completed evaluation projects in the project database;

[0090] According to the team R&D capability information, subject prospect information, project level information, and financial support information of the project to be evaluated, input into the trained second preset model to obtain corresponding project achievement data;

[0091] The project achievement data include patent research and development data, research and production transformation value data, project profit data and secondary research and development value data;

[0092] The project profit data obtained from the project achievement data is used as the project expected data for the project to be evaluated.

[0093] It should be noted that in order to obtain the expected data of the project to be evaluated, data processing is performed through the second preset model. The second preset model is a data processing model obtained through a third-party project evaluation platform, and data is linked to the project database. The project database includes a large amount of data information of various categories of projects that have completed the evaluation. The second preset model is trained with the project evaluation information data and project achievement data of the completed evaluation projects to obtain the trained second preset model. The project evaluation information data can be processed by the second preset model to obtain the corresponding project achievement data. The larger the data volume, the higher the data processing accuracy of the second preset model. According to the team R&D capability information, subject prospect information, project level information, and financial support information of the project to be evaluated, the corresponding project achievement data including patent R&D data, R&D-production conversion value data, project profit data, and secondary R&D value data are input into the second preset model. The project profit data is used as the expected data of the project to be evaluated. The achievement data corresponding to the project data information can be obtained by processing the second preset model obtained through a large amount of data training.

[0094] According to an embodiment of the present invention, the project target data is obtained by correcting the project expected data according to the project evaluation data set and the project indicator consistency data of the project to be evaluated, specifically:

[0095] According to the project evaluation data set and project indicator consistency data of the project to be evaluated, combined with the project parameters of the project to be evaluated, the project profit data is corrected to obtain project target data;

[0096] The project target data calculation formula is:

[0097]

[0098] Among them, V is the project target data, σ is the team's industry value coefficient, and P is the team's R&D value data. is the project social value coefficient, H is the outcome value data, τ is the policy support coefficient, R is the obtained project profit data, a is the project risk coefficient, Q is the project indicator fit data, the team industry value coefficient, project social value coefficient, policy support coefficient and project risk coefficient are obtained by querying the third-party project evaluation platform based on the project to be evaluated.

[0099] It should be noted that in order to obtain more accurate project profit target data, it is necessary to correct the project profit data obtained by processing, and correct the project profit data by combining the project indicator consistency data and multiple data in the project evaluation data set. The target data corrected by the project's own data has higher accuracy, and the target value of the project can be predicted as a basis for evaluation.

[0100] According to an embodiment of the present invention, it also includes:

[0101] The project attribute information of the project to be evaluated, the team R&D value data, the achievement value data, the number of project R&D patents and the project's expected profit data are input into a third preset model to obtain the project indicator level;

[0102] Input the project attribute information into a third-party project evaluation platform to obtain a third preset model that matches the attributes of the project to be evaluated;

[0103] Perform threshold comparisons based on the team R&D value data, achievement value data, number of project R&D patents and project expected profit data with the team capability threshold, achievement value threshold, R&D patent number threshold and project profit threshold in the third preset model;

[0104] The team capability threshold, achievement value threshold, R&D patent number threshold and project profit threshold are divided into four levels, namely, I, II, III and IV;

[0105] According to the comparison results of the four thresholds of the team's R&D value data, the achievement value data, the number of project R&D patents and the project's proposed profit data, the corresponding levels are averaged and rounded to obtain the project indicator level of the project to be evaluated;

[0106] Adjust the project policies and requirements of the project to be evaluated according to the project indicator level.

[0107] It should be noted that the corresponding project policies and requirements are obtained according to the project to be evaluated. The project policies and requirements are divided according to the project indicator levels. The project indicator levels are divided into four levels, namely level one to level four, among which level one is the highest and level four is the lowest. In order to obtain the project indicator level corresponding to the project to be evaluated, the third preset model matching the attributes is obtained through a third-party project evaluation platform based on the project attribute information of the project to be evaluated. Then, the team R&D value data, achievement value data, number of project R&D patents and project proposed profit data of the project to be evaluated are input into the third preset model for threshold comparison. The third preset model contains the team capability threshold, achievement value threshold, R&D patent number threshold and project profit threshold corresponding to each data. The four thresholds are divided into There are four levels, namely I, II, III, and IV. The threshold range of level I is (0.75, 1], the threshold range of level II is (0.5, 0.75], the threshold range of level III is (0.25, 0.5], and the threshold range of level IV is [0, 0.25]. According to the threshold comparison results of the four data items, the corresponding threshold range levels are obtained respectively. The average of the four threshold range levels is calculated and rounded to obtain the average threshold range level as the project indicator level of the project to be evaluated. For example, the threshold comparison results of the four data items of project A are II, II, III, and IV respectively, then the average threshold range level is (2+2+3+4) / 4=2.75, which is rounded to 3, that is, the threshold range level of project A is III, and the corresponding project indicator level is III.

[0108] According to an embodiment of the present invention, it also includes:

[0109] Obtain corresponding financial support data according to the project indicator level of the project to be evaluated;

[0110] The financial support data is weighted according to the project target data, the project planned profit data and the correlation coefficient to obtain the financial budget data;

[0111] Providing project support to the project to be evaluated according to the financial budget data;

[0112] The weighted calculation formula for the fiscal budget data is:

[0113]

[0114] Among them, V is the project target data, V0 is the project's planned profit data, τ is the policy support coefficient, a is the project risk coefficient, S is the financial support data, and T is the financial budget data.

[0115] It should be noted that the financial support budget for the implementation of the project in this case is obtained by weighting the project target data and the project's planned profit data of the project to be evaluated. The financial budget data is obtained by weighting the bidding financial support data based on the project target data and the project's planned profit data combined with the project's correlation coefficient queried on the third-party project evaluation platform as the actual financial support budget for the project. The accuracy of the project's financial support budget can be improved by correcting the coefficient combined with the project's predicted target data.

[0116] like Figure 4 As shown, the present invention also discloses a project intelligent prediction and evaluation system 4 based on big data, including a memory 41 and a processor 42, wherein the memory includes a project intelligent prediction and evaluation method program based on big data, and when the project intelligent prediction and evaluation method program based on big data is executed by the processor, the following steps are implemented:

[0117] Obtaining project attribute information and feature information of the project to be evaluated;

[0118] Extracting evaluation information data based on the project attribute information and feature information of the project to be evaluated to generate an evaluation project feature portrait, and extracting an evaluation data package based on the evaluation project feature portrait;

[0119] Performing an indicator consistency analysis on the project evaluation data set in the evaluation data package according to the first preset model to obtain project indicator consistency data;

[0120] Performing project evaluation on the evaluation project feature portrait according to the second preset model to obtain project expected data;

[0121] The project target data is obtained by correcting the project expected data according to the project evaluation data set and the project indicator consistency data of the project to be evaluated.

[0122] It should be noted that first, the project attribute information and feature information of the project to be evaluated are obtained, and the evaluation information data is extracted to generate an evaluation project feature portrait and extract the evaluation data package. According to the project evaluation data set in the evaluation data package, the first preset model is input to calculate the indicator fit of the project to be evaluated to obtain the project indicator fit data. Then, according to the trained second preset model, the data information in the evaluation project feature portrait is evaluated to obtain the project profit data as the project expected data. Then, according to the data in the project evaluation data set combined with the project indicator fit data and the project coefficient, the project target data is corrected to obtain the project data, thereby realizing the intelligent technology for predicting and reviewing projects based on big data and improving the accuracy of the review and judgment of project data.

[0123] According to an embodiment of the present invention, the acquisition of project attribute information and feature information of the project to be evaluated is specifically as follows:

[0124] Obtain application information and project description information of the project to be evaluated;

[0125] Extracting project attribute information from the application information and project description information, including: R&D core information, technical field information, technical background information, and research subject information;

[0126] Characteristic information is obtained based on the project description information and project attribute information, including: key technology information, core research information, project magnitude data, research team information and project benefit indicator data.

[0127] It should be noted that in order to achieve accurate prediction and review of the projects to be evaluated, it is necessary to collect relevant data information of the projects. The data information of the projects includes information on project themes, core topics, team information, financial information, policy support information, etc. By obtaining the application information and project description information of the projects to be evaluated, the project attribute information in the application information and project description information is extracted, including core R&D information, technical field information, technical background information and research subject information. Based on the project description information and project attribute information, feature information including key technology information, core research information, project magnitude data, research team information and project benefit indicator data is obtained, so as to prepare for data information collection for project prediction and review, so as to ensure the accuracy of project prediction and review.

[0128] According to an embodiment of the present invention, extracting evaluation information data based on the project attribute information and feature information of the project to be evaluated to generate a feature portrait of the evaluation project is specifically as follows:

[0129] Generate a project feature tree based on the R&D core information, technical field information, technical background information, research subject information, key technology information, core research information, project magnitude data, and research team information of the project to be evaluated;

[0130] The project feature tree includes team data information, frontier background information, core task information, surrounding policy information and budget financial information of the project to be evaluated;

[0131] Extracting evaluation information data according to the project feature tree, including: team R&D capability information, subject prospect information, project level information, financial support information and investment return information;

[0132] A characteristic portrait of the evaluation project is generated based on the team's R&D capability information, subject prospect information, project level information, financial support information and investment return information.

[0133] It should be noted that the project feature tree is a data information structure that describes the background architecture and project hardware of the project to be evaluated. It is dependent on a third-party project evaluation platform. The background data and component information of the project to be evaluated can be queried through the project feature tree. In this case, the project feature tree is collected and generated by the R&D core information, technical field information, technical background information, research subject information, key technology information, core research information, project magnitude data, and research team information of the project to be evaluated, including team data information, frontier background information, core task information, surrounding policy information, and budget financial information of the project to be evaluated. Evaluation information data including team R&D capability information, subject prospect information, project level information, financial support information, and investment return information are extracted according to the project feature tree to generate an evaluation project feature portrait. The evaluation project feature portrait is a digital depiction of the project's various resource information, including human resources, subject background, project level, financial resources, and investment return information. It is a digital map that reflects the background resources and organizational structure of the project implementation, which facilitates real-time acquisition of the background situation of project resources and project information.

[0134] According to an embodiment of the present invention, performing an indicator conformity analysis on the project evaluation data set in the evaluation data package according to the first preset model to obtain project indicator conformity data is specifically as follows:

[0135] The evaluation data package is extracted through the evaluation information data in the characteristic portrait of the evaluation item;

[0136] The evaluation data package includes a project evaluation data set, including team R&D value data, achievement value data, number of project R&D patents, policy and funding support data, and project proposed profit data;

[0137] According to the project evaluation data set, a first preset model is input to calculate the index consistency of the project to be evaluated to obtain the project index consistency data.

[0138] It should be noted that in order to evaluate the matching degree between data information such as project topics, R&D themes, and financial budgets and the indicator data of project bidding information, it is necessary to obtain the indicator matching data of the project. The project evaluation data set in the evaluation data package extracted from the evaluation project feature portrait includes team R&D value data, achievement value data, number of project R&D patents, policy and funding support data, and project proposed profit data, which are input into the first preset model for indicator matching calculation to obtain the project indicator matching data. Among them, the first preset model is a calculation model obtained through a third-party project evaluation platform;

[0139] The calculation formula for the project indicator consistency data is:

[0140]

[0141] Among them, Q represents the project indicator fit data, Y0 represents the project's expected profit data, Y1 represents the team's R&D value data, Y2 represents the achievement value data, Y3 represents the number of project R&D patents, Y4 represents policy and financial support data, ε, γ and λ are corresponding data response coefficients (obtained through the first preset model).

[0142] According to an embodiment of the present invention, the project evaluation is performed on the evaluation project feature portrait according to the second preset model to obtain the project expected data, specifically:

[0143] Acquire a project database, wherein the project database includes project evaluation information data and project achievement data of completed evaluation projects of various categories;

[0144] A second preset model is obtained by training the project evaluation information data and project achievement data of each category of completed evaluation projects in the project database;

[0145] According to the team R&D capability information, subject prospect information, project level information, and financial support information of the project to be evaluated, input into the trained second preset model to obtain corresponding project achievement data;

[0146] The project achievement data include patent research and development data, research and production transformation value data, project profit data and secondary research and development value data;

[0147] The project profit data obtained from the project achievement data is used as the project expected data for the project to be evaluated.

[0148] It should be noted that in order to obtain the expected data of the project to be evaluated, data processing is performed through the second preset model. The second preset model is a data processing model obtained through a third-party project evaluation platform, and data is linked to the project database. The project database includes a large amount of data information of various categories of projects that have completed the evaluation. The second preset model is trained with the project evaluation information data and project achievement data of the completed evaluation projects to obtain the trained second preset model. The project evaluation information data can be processed by the second preset model to obtain the corresponding project achievement data. The larger the data volume, the higher the data processing accuracy of the second preset model. According to the team R&D capability information, subject prospect information, project level information, and financial support information of the project to be evaluated, the corresponding project achievement data including patent R&D data, R&D-production conversion value data, project profit data, and secondary R&D value data are input into the second preset model. The project profit data is used as the expected data of the project to be evaluated. The achievement data corresponding to the project data information can be obtained by processing the second preset model obtained through a large amount of data training.

[0149] According to an embodiment of the present invention, the project target data is obtained by correcting the project expected data according to the project evaluation data set and the project indicator consistency data of the project to be evaluated, specifically:

[0150] According to the project evaluation data set and project indicator consistency data of the project to be evaluated, combined with the project parameters of the project to be evaluated, the project profit data is corrected to obtain project target data;

[0151] The project target data calculation formula is:

[0152]

[0153] Among them, V is the project target data, σ is the team's industry value coefficient, and P is the team's R&D value data. is the project social value coefficient, H is the outcome value data, τ is the policy support coefficient, R is the obtained project profit data, a is the project risk coefficient, Q is the project indicator fit data, the team industry value coefficient, project social value coefficient, policy support coefficient and project risk coefficient are obtained by querying the third-party project evaluation platform based on the project to be evaluated.

[0154] It should be noted that in order to obtain more accurate project profit target data, it is necessary to correct the project profit data obtained by processing, and correct the project profit data by combining the project indicator consistency data and multiple data in the project evaluation data set. The target data corrected by the project's own data has higher accuracy, and the target value of the project can be predicted as a basis for evaluation.

[0155] According to an embodiment of the present invention, it also includes:

[0156] The project attribute information of the project to be evaluated, the team R&D value data, the achievement value data, the number of project R&D patents and the project's expected profit data are input into a third preset model to obtain the project indicator level;

[0157] Input the project attribute information into a third-party project evaluation platform to obtain a third preset model that matches the attributes of the project to be evaluated;

[0158] Perform threshold comparisons based on the team R&D value data, achievement value data, number of project R&D patents and project expected profit data with the team capability threshold, achievement value threshold, R&D patent number threshold and project profit threshold in the third preset model;

[0159] The team capability threshold, achievement value threshold, R&D patent number threshold and project profit threshold are divided into four levels, namely, I, II, III and IV;

[0160] According to the comparison results of the four thresholds of the team's R&D value data, the achievement value data, the number of project R&D patents and the project's proposed profit data, the corresponding levels are averaged and rounded to obtain the project indicator level of the project to be evaluated;

[0161] Adjust the project policies and requirements of the project to be evaluated according to the project indicator level.

[0162] It should be noted that the corresponding project policies and requirements are obtained according to the project to be evaluated. The project policies and requirements are divided according to the project indicator levels. The project indicator levels are divided into four levels, namely level one to level four, among which level one is the highest and level four is the lowest. In order to obtain the project indicator level corresponding to the project to be evaluated, the third preset model matching the attributes is obtained through a third-party project evaluation platform based on the project attribute information of the project to be evaluated. Then, the team R&D value data, achievement value data, number of project R&D patents and project proposed profit data of the project to be evaluated are input into the third preset model for threshold comparison. The third preset model contains the team capability threshold, achievement value threshold, R&D patent number threshold and project profit threshold corresponding to each data. The four thresholds are divided into There are four levels, namely I, II, III, and IV. The threshold range of level I is (0.75, 1], the threshold range of level II is (0.5, 0.75], the threshold range of level III is (0.25, 0.5], and the threshold range of level IV is [0, 0.25]. According to the threshold comparison results of the four data items, the corresponding threshold range levels are obtained respectively. The average of the four threshold range levels is calculated and rounded to obtain the average threshold range level as the project indicator level of the project to be evaluated. For example, the threshold comparison results of the four data items of project A are II, II, III, and IV respectively, then the average threshold range level is (2+2+3+4) / 4=2.75, which is rounded to 3, that is, the threshold range level of project A is III, and the corresponding project indicator level is III.

[0163] According to an embodiment of the present invention, it also includes:

[0164] Obtain corresponding financial support data according to the project indicator level of the project to be evaluated;

[0165] The financial support data is weighted according to the project target data, the project planned profit data and the correlation coefficient to obtain the financial budget data;

[0166] Providing project support to the project to be evaluated according to the financial budget data;

[0167] The weighted calculation formula for the fiscal budget data is:

[0168]

[0169] Among them, V is the project target data, V0 is the project's planned profit data, τ is the policy support coefficient, a is the project risk coefficient, S is the financial support data, and T is the financial budget data.

[0170] It should be noted that the financial support budget for the implementation of the project in this case is obtained by weighting the project target data and the project's planned profit data of the project to be evaluated. The financial budget data is obtained by weighting the bidding financial support data based on the project target data and the project's planned profit data combined with the project's correlation coefficient queried on the third-party project evaluation platform as the actual financial support budget for the project. The accuracy of the project's financial support budget can be improved by correcting the coefficient combined with the project's predicted target data.

[0171] The third aspect of the present invention provides a readable storage medium, which includes a project intelligent prediction and evaluation method program based on big data. When the project intelligent prediction and evaluation method program based on big data is executed by a processor, the steps of a project intelligent prediction and evaluation method based on big data as described in any one of the above items are implemented.

[0172] The present invention discloses a method, system and readable storage medium for intelligent prediction and evaluation of projects based on big data. The method obtains project attribute information and feature information of a project to be evaluated, extracts evaluation information data according to the project attribute information and feature information of the project to be evaluated, generates an evaluation project feature portrait, extracts an evaluation data package according to the evaluation project feature portrait, performs indicator fit analysis on the project evaluation data set in the evaluation data package according to a first preset model to obtain project indicator fit data, performs project evaluation on the evaluation project feature portrait according to a second preset model to obtain project expected data, and corrects the project expected data according to the project evaluation data set and the project indicator fit data of the project to be evaluated to obtain project target data; thereby, a high-precision technology for realizing intelligent prediction and evaluation of projects according to big data is obtained.

[0173] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0174] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0175] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0176] Those skilled in the art can understand that: all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions, and the aforementioned program can be stored in a readable storage medium. When the program is executed, it executes the steps of the above method embodiments; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), disks or optical disks, and other media that can store program codes.

[0177] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

Claims

1. Project intelligent prediction and evaluation method based on big data, characterized by: include: Obtaining project attribute information and feature information of the project to be evaluated; Extracting evaluation information data based on the project attribute information and feature information of the project to be evaluated to generate an evaluation project feature portrait, and extracting an evaluation data package based on the evaluation project feature portrait; Performing an indicator consistency analysis on the project evaluation data set in the evaluation data package according to the first preset model to obtain project indicator consistency data; Performing project evaluation on the evaluation project feature portrait according to the second preset model to obtain project expected data; According to the project evaluation data set and project indicator consistency data of the project to be evaluated, the project expected data is corrected to obtain project target data; The obtaining of the project attribute information and feature information of the project to be evaluated includes: Obtain application information and project description information of the project to be evaluated; Extracting project attribute information from the application information and project description information, including: R&D core information, technical field information, technical background information, and research subject information; Acquire characteristic information according to the project description information and project attribute information, including: key technology information, core research information, project magnitude data, participating research team information and project benefit indicator data; The step of extracting evaluation information data according to the project attribute information and feature information of the project to be evaluated to generate a feature portrait of the evaluation project includes: Generate a project feature tree based on the R&D core information, technical field information, technical background information, research subject information, key technology information, core research information, project magnitude data, and research team information of the project to be evaluated, wherein the project feature tree is based on a third-party project evaluation platform; The project feature tree includes team data information, frontier background information, core task information, surrounding policy information and budget financial information of the project to be evaluated; Extracting evaluation information data according to the project feature tree, including: team R&D capability information, subject prospect information, project level information, financial support information and investment return information; Generate an evaluation project feature portrait based on the team's R&D capability information, subject prospect information, project level information, financial support information, and investment return information. The evaluation project feature portrait is a digital depiction of various resource information of the project; The step of performing an indicator consistency analysis on the project evaluation data set in the evaluation data package according to the first preset model to obtain project indicator consistency data includes: The evaluation data package is extracted through the evaluation information data in the characteristic portrait of the evaluation item; The evaluation data package includes a project evaluation data set, including team R&D value data, achievement value data, number of project R&D patents, policy and funding support data, and project proposed profit data; Inputting a first preset model according to the project evaluation data set to calculate the index consistency of the project to be evaluated to obtain the project index consistency data; The calculation formula for the project indicator consistency data is: ； in, Indicates the project indicator fit data, Indicates the project's proposed profit data, Indicates the team's R&D value data, Indicates the value of the outcome data, Indicates the number of project R&D patents, Indicates policy and financial support data, is the corresponding data response coefficient; The step of performing project evaluation on the evaluation project feature portrait according to the second preset model to obtain project expected data includes: Acquire a project database, wherein the project database includes project evaluation information data and project achievement data of completed evaluation projects of various categories; A second preset model is obtained by training the project evaluation information data and project achievement data of each category of completed evaluation projects in the project database, wherein the second preset model is a data processing model obtained through a third-party project evaluation platform; According to the team R&D capability information, subject prospect information, project level information, and financial support information of the project to be evaluated, input into the trained second preset model to obtain corresponding project achievement data; The project achievement data include patent research and development data, research and production transformation value data, project profit data and secondary research and development value data; Using the project profit data of the project achievement data obtained as the project expected data of the project to be evaluated; The step of correcting the project expected data according to the project evaluation data set and the project indicator consistency data of the project to be evaluated to obtain the project target data includes: According to the project evaluation data set and project indicator consistency data of the project to be evaluated, combined with the project parameters of the project to be evaluated, the project profit data is corrected to obtain project target data; The project target data calculation formula is: ； Among them, V is the project target data, is the team's industry value coefficient, P is the team's R&D value data, is the project social value coefficient, H is the outcome value data, is the policy support coefficient, R is the obtained project profit data, a is the project risk coefficient, Q is the project indicator consistency data, and the team industry value coefficient, project social value coefficient, policy support coefficient and project risk coefficient are obtained by querying the third-party project evaluation platform based on the project to be evaluated; Also includes: Obtain corresponding financial support data according to the project indicator level of the project to be evaluated; The financial support data is weighted according to the project target data, the project planned profit data and the correlation coefficient to obtain the financial budget data; Providing project support to the project to be evaluated according to the financial budget data; The weighted calculation formula for the fiscal budget data is: ； Among them, V is the project target data, Propose profit data for the project, is the policy support coefficient, a is the project risk coefficient, S is the financial support data, and T is the financial budget data; Also includes: The project attribute information of the project to be evaluated and the team R&D value data, achievement value data, number of project R&D patents and project expected profit data are input into a third preset model to obtain the project indicator level; Input the project attribute information into a third-party project evaluation platform to obtain a third preset model that matches the attributes of the project to be evaluated; Perform threshold comparisons based on the team R&D value data, achievement value data, number of project R&D patents, and project proposed profit data with the team capability threshold, achievement value threshold, R&D patent number threshold, and project profit threshold in the third preset model; The team capability threshold, achievement value threshold, R&D patent number threshold and project profit threshold are divided into four levels, namely, I, II, III and IV; According to the comparison results of the four thresholds of the team's R&D value data, the achievement value data, the number of project R&D patents and the project's proposed profit data, the corresponding levels are averaged and rounded to obtain the project indicator level of the project to be evaluated; Adjust the project policies and requirements of the project to be evaluated according to the project indicator level.

2. A project intelligent prediction and evaluation system based on big data, characterized in that: The system includes: a memory and a processor, wherein the memory includes a program of a project intelligent prediction and evaluation method based on big data, and when the program of the project intelligent prediction and evaluation method based on big data is executed by the processor, the following steps are implemented: Obtaining project attribute information and feature information of the project to be evaluated; Extracting evaluation information data based on the project attribute information and feature information of the project to be evaluated to generate an evaluation project feature portrait, and extracting an evaluation data package based on the evaluation project feature portrait; Performing an indicator consistency analysis on the project evaluation data set in the evaluation data package according to the first preset model to obtain project indicator consistency data; Performing project evaluation on the evaluation project feature portrait according to the second preset model to obtain project expected data; According to the project evaluation data set and project indicator consistency data of the project to be evaluated, the project expected data is corrected to obtain project target data; The obtaining of the project attribute information and feature information of the project to be evaluated includes: Obtain application information and project description information of the project to be evaluated; Extracting project attribute information from the application information and project description information, including: R&D core information, technical field information, technical background information, and research subject information; Acquire characteristic information according to the project description information and project attribute information, including: key technology information, core research information, project magnitude data, participating research team information and project benefit indicator data; The step of extracting evaluation information data according to the project attribute information and feature information of the project to be evaluated to generate a feature portrait of the evaluation project includes: Generate a project feature tree based on the R&D core information, technical field information, technical background information, research subject information, key technology information, core research information, project magnitude data, and research team information of the project to be evaluated, wherein the project feature tree is based on a third-party project evaluation platform; The project feature tree includes team data information, frontier background information, core task information, surrounding policy information and budget financial information of the project to be evaluated; Extracting evaluation information data according to the project feature tree, including: team R&D capability information, subject prospect information, project level information, financial support information and investment return information; Generate an evaluation project feature portrait based on the team's R&D capability information, subject prospect information, project level information, financial support information, and investment return information. The evaluation project feature portrait is a digital depiction of various resource information of the project; The step of performing an indicator consistency analysis on the project evaluation data set in the evaluation data package according to the first preset model to obtain project indicator consistency data includes: The evaluation data package is extracted through the evaluation information data in the characteristic portrait of the evaluation item; The evaluation data package includes a project evaluation data set, including team R&D value data, achievement value data, number of project R&D patents, policy and funding support data, and project proposed profit data; Inputting a first preset model according to the project evaluation data set to calculate the index consistency of the project to be evaluated to obtain the project index consistency data; The calculation formula for the project indicator consistency data is: ； in, Indicates the project indicator fit data, Indicates the project's proposed profit data, Indicates the team's R&D value data, Indicates the value of the outcome data, Indicates the number of project R&D patents, Indicates policy and financial support data, is the corresponding data response coefficient; The step of performing project evaluation on the evaluation project feature portrait according to the second preset model to obtain project expected data includes: Acquire a project database, wherein the project database includes project evaluation information data and project achievement data of completed evaluation projects of various categories; A second preset model is obtained by training the project evaluation information data and project achievement data of each category of completed evaluation projects in the project database, wherein the second preset model is a data processing model obtained through a third-party project evaluation platform; According to the team R&D capability information, subject prospect information, project level information, and financial support information of the project to be evaluated, input into the trained second preset model to obtain corresponding project achievement data; The project achievement data include patent research and development data, research and production transformation value data, project profit data and secondary research and development value data; Using the project profit data of the project achievement data obtained as the project expected data of the project to be evaluated; The step of correcting the project expected data according to the project evaluation data set and the project indicator consistency data of the project to be evaluated to obtain the project target data includes: According to the project evaluation data set and project indicator consistency data of the project to be evaluated, combined with the project parameters of the project to be evaluated, the project profit data is corrected to obtain project target data; The project target data calculation formula is: ； Among them, V is the project target data, is the team's industry value coefficient, P is the team's R&D value data, is the project social value coefficient, H is the outcome value data, is the policy support coefficient, R is the obtained project profit data, a is the project risk coefficient, Q is the project indicator consistency data, and the team industry value coefficient, project social value coefficient, policy support coefficient and project risk coefficient are obtained by querying the third-party project evaluation platform based on the project to be evaluated; Also includes: Obtain corresponding financial support data according to the project indicator level of the project to be evaluated; The financial support data is weighted according to the project target data, the project planned profit data and the correlation coefficient to obtain the financial budget data; Providing project support to the project to be evaluated according to the financial budget data; The weighted calculation formula for the fiscal budget data is: ； Among them, V is the project target data, Propose profit data for the project, is the policy support coefficient, a is the project risk coefficient, S is the financial support data, and T is the financial budget data; Also includes: The project attribute information of the project to be evaluated and the team R&D value data, achievement value data, number of project R&D patents and project expected profit data are input into a third preset model to obtain the project indicator level; Input the project attribute information into a third-party project evaluation platform to obtain a third preset model that matches the attributes of the project to be evaluated; Perform threshold comparisons based on the team R&D value data, achievement value data, number of project R&D patents, and project proposed profit data with the team capability threshold, achievement value threshold, R&D patent number threshold, and project profit threshold in the third preset model; The team capability threshold, achievement value threshold, R&D patent number threshold and project profit threshold are divided into four levels, namely, I, II, III and IV; According to the comparison results of the four thresholds of the team's R&D value data, the achievement value data, the number of project R&D patents and the project's proposed profit data, the corresponding levels are averaged and rounded to obtain the project indicator level of the project to be evaluated; Adjust the project policies and requirements of the project to be evaluated according to the project indicator level.

3. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a project intelligent prediction and evaluation method program based on big data. When the project intelligent prediction and evaluation method program based on big data is executed by a processor, the steps of a project intelligent prediction and evaluation method based on big data as described in claim 1 are implemented.

Images