Peer evaluation quality assessment method and system based on data mining, and medium

Abstract

The embodiment of the invention provides a peer evaluation quality assessment method and system based on data mining and a medium. The method comprises the following steps: extracting task package effect characteristics and review table data according to task package effect and comment information of a peer evaluation object task package, and generating a task package review characteristic portrait to extract a task package evaluation data package, quality fitting and peer quality evaluation are carried out on the task package evaluation data set and the task package review feature portrait through a model, a task package quality verification index and peer evaluation quality effect data are obtained, a peer evaluation quality evaluation index and peer recommendation promotion data are obtained through processing, and peer promotion is finally carried out; therefore, a feature portrait of data description is generated based on the data of the peer evaluation task package, task package quality verification and peer evaluation quality evaluation and recommendation evaluation are performed, and the quality evaluation technology of the peer evaluation task package is realized.

Description

Technical Field

[0001] The present application relates to the field of big data and review and evaluation technology, and more specifically, to a peer review quality assessment method, system and medium based on data mining. Background Art

[0002] Peer review is currently an important auxiliary means of evaluating and making decisions on projects or tasks executed in various industries. In the process of peer review, due to the differences in cognition, level and perspective of multiple reviewers, the quality of peer review results has certain inaccuracies, deviations and distortions, which will affect the true judgment of the implementation effect of the project or task, and ultimately affect the true judgment of the effect of the evaluation object. In addition, due to the complex problems of complicated evaluation content, mixed evaluation standards, disordered judgment basis, etc. in peer review tasks, it is difficult to make an accurate assessment and judgment on the quality of peer review. Therefore, there is currently a lack of means to conduct effective quality assessment of the results of peer review in combination with the effectiveness of implementing projects or tasks.

[0003] In view of the above problems, effective technical solutions are urgently needed. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide a peer review quality assessment method, system and medium based on data mining, which can generate a feature portrait of the data description according to the data of the task package of the peer review object and perform quality inspection of the task package implementation and assessment of the peer review quality and recommendation evaluation, thereby realizing quality assessment and recommendation technology for the task package of the peer review object.

[0005] The present application also provides a method for evaluating the quality of peer review based on data mining, comprising the following steps: Obtain the task package performance information and task package evaluation information of the peer evaluation task package; Extracting task package effectiveness feature data and task package review table data respectively according to the task package effectiveness information and task package review information, and generating a task package review feature portrait and extracting a task package evaluation data packet; Performing quality fitting processing on the task package evaluation data set of the task package evaluation data packet through a preset task package quality assessment model to obtain a task package quality verification index; Conducting a peer quality evaluation of the task package on the review feature portrait of the task package according to the trained peer quality evaluation model of the task package, and obtaining the corresponding peer evaluation quality effectiveness data; Processing the task package evaluation data set of the peer evaluation task package in combination with the task package quality verification index and the peer evaluation quality effectiveness data to obtain a peer evaluation quality assessment index; The task peer evaluation quality level corresponding to the peer evaluation quality assessment index is processed in combination with the task package evaluation data set to obtain peer recommendation promotion data and perform peer recommendation.

[0006] Optionally, in the peer review quality assessment method based on data mining described in the embodiment of the present application, the step of obtaining task package performance information and task package review application information of the peer review task package includes: Obtain task package operation information and task package report information of peer evaluation task packages; Extracting task package performance information according to the task package operation information and task package report information, including task package completion status information, task package node timeliness information, task package loss information, task package result output information and task package profit information; Obtain task package application information of the peer-evaluated task package, including task package type information, task package ranking information, task package scale information, task package resource support information, task package influence information, and task package popularity information.

[0007] Optionally, in the peer review quality assessment method based on data mining described in the embodiment of the present application, extracting task package effectiveness feature data and task package review table data respectively according to the task package effectiveness information and task package review information, and generating a task package review feature portrait and extracting a task package evaluation data packet, including: Extracting task package performance characteristic data according to the task package performance information, including completion rate data, total process time efficiency data, task revenue data, achievement profitability data, and asset value-added data; Extract task package review table data based on the task package application information, including task intensity data, scale data, resource peer ratio data, review weight data, and expected risk assessment data; Generate a task package review feature profile based on the completion rate data, total process time efficiency data, task revenue data, achievement profitability data, asset value-added data, and task enthusiasm data, scale data, resource peer ratio data, review weight data, and expected risk assessment data; Extract the task package evaluation data packet according to the task package review feature portrait.

[0008] Optionally, in the peer review quality assessment method based on data mining described in the embodiment of the present application, the quality fitting processing of the task package evaluation data set of the task package evaluation data packet is performed by using a preset task package quality assessment model to obtain the task package quality verification index, including: The task package evaluation data package includes a task package evaluation data set, including revenue surplus data, value evaluation data, resource feedback rate data, scale expansion rate data and risk weight assessment data; According to the task package evaluation data set, quality fitting processing is performed on the peer-evaluated task package through a preset task package quality assessment model to obtain a task package quality verification index.

[0009] Optionally, in the peer review quality assessment method based on data mining described in the embodiment of the present application, the task package peer quality assessment is performed on the task package review feature portrait according to the trained task package peer quality assessment model to obtain the corresponding peer review quality effectiveness data, including: Extracting peer task evaluation data of the peer evaluation task package according to the task package review feature portrait; The peer task evaluation data includes score floating rate data, evaluation compliance rate data, expected assessment difference rate data, risk assessment valuation data and peer assessment profit and loss data; Obtain peer evaluation data of multiple peer evaluation task packages that have completed peer evaluation and corresponding peer evaluation quality effectiveness data through a preset task package evaluation release database, and perform training to obtain a task package peer quality evaluation model; The peer task evaluation data of the peer evaluation task package is input into the trained peer quality assessment model of the task package for processing to obtain peer evaluation quality effectiveness data.

[0010] Optionally, in the peer review quality assessment method based on data mining described in the embodiment of the present application, the task package assessment data set according to the peer review task package is processed in combination with the task package quality verification index and the peer review quality effectiveness data to obtain the peer review quality assessment index, including: Processing the revenue surplus data, value evaluation data, and risk weight assessment data of the peer evaluation task package in combination with the task package quality verification index and the peer evaluation quality effectiveness data to obtain a peer evaluation quality assessment index; The calculation formula of the peer review quality assessment index is: ; in, is a peer review quality assessment index, They are profit and loss data, value evaluation data, and risk weight assessment data. is the task package quality verification index, To peer review quality performance data, is the preset characteristic coefficient.

[0011] Optionally, in the peer review quality assessment method based on data mining described in the embodiment of the present application, the task peer review quality level corresponding to the peer review quality assessment index is processed in combination with the task package evaluation data set to obtain peer recommendation promotion data, and peer recommendation is performed, including: Obtaining a corresponding task peer review quality grade according to the peer review quality assessment index of the peer review task package; Processing is performed based on the task peer evaluation quality level combined with the resource feedback rate data, scale expansion rate data and the peer evaluation quality assessment index to obtain peer recommendation promotion data; The peer evaluation task package is peer promoted according to the peer recommendation promotion data.

[0012] In a second aspect, an embodiment of the present application provides a peer review quality assessment system based on data mining, the system comprising: a memory and a processor, the memory comprising a program of a peer review quality assessment method based on data mining, and the program of the peer review quality assessment method based on data mining is executed by the processor to implement the following steps: Obtain the task package performance information and task package evaluation information of the peer evaluation task package; Extracting task package effectiveness feature data and task package review table data respectively according to the task package effectiveness information and task package review information, and generating a task package review feature portrait and extracting a task package evaluation data packet; Performing quality fitting processing on the task package evaluation data set of the task package evaluation data packet through a preset task package quality assessment model to obtain a task package quality verification index; Conducting a peer quality evaluation of the task package on the review feature portrait of the task package according to the trained peer quality evaluation model of the task package, and obtaining the corresponding peer evaluation quality effectiveness data; Processing the task package evaluation data set of the peer evaluation task package in combination with the task package quality verification index and the peer evaluation quality effectiveness data to obtain a peer evaluation quality assessment index; The task peer evaluation quality level corresponding to the peer evaluation quality assessment index is processed in combination with the task package evaluation data set to obtain peer recommendation promotion data and perform peer recommendation.

[0013] Optionally, in the peer review quality assessment system based on data mining described in the embodiment of the present application, the step of obtaining task package performance information and task package evaluation information of the peer review task package includes: Obtain task package operation information and task package report information of peer evaluation task packages; Extracting task package performance information according to the task package operation information and task package report information, including task package completion status information, task package node timeliness information, task package loss information, task package result output information and task package profit information; Obtain task package application information of the peer-evaluated task package, including task package type information, task package ranking information, task package scale information, task package resource support information, task package influence information, and task package popularity information.

[0014] In a third aspect, an embodiment of the present application further provides a readable storage medium, wherein the readable storage medium includes a peer review quality assessment method program based on data mining. When the peer review quality assessment method program based on data mining is executed by a processor, the steps of a peer review quality assessment method based on data mining as described in any one of the above items are implemented.

[0015] As can be seen from the above, the embodiment of the present application provides a peer review quality assessment method, system and medium based on data mining. The method includes: extracting task package effectiveness characteristics and review form data according to the task package effectiveness and application information of the task package of the peer review object and generating a task package review feature portrait to extract the task package evaluation data packet, and then using the model to perform quality fitting and peer quality assessment on the task package evaluation data set and the task package review feature portrait respectively, and obtain the task package quality verification index and peer evaluation quality effectiveness data respectively, and then process to obtain the peer evaluation quality assessment index and peer recommendation and promotion data, and finally perform peer recommendation; thereby generating a feature portrait of data description based on the data of the task package of the peer review object and performing task package quality verification and peer evaluation quality assessment and recommendation assessment, so as to realize the quality assessment technology of the task package of the peer review object.

[0016] Other features and advantages of the present application will be described in the following description, and partly become apparent from the description, or 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 and the drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] 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.

[0018] Figure 1 A flowchart of a peer review quality assessment method based on data mining provided in an embodiment of the present application; Figure 2 A flowchart of obtaining task package performance information and task package application information of a peer review task package in a peer review quality assessment method based on data mining provided in an embodiment of the present application; Figure 3 A flowchart of generating a task package review feature portrait and extracting a task package evaluation data packet for a peer review quality assessment method based on data mining provided in an embodiment of the present application; Figure 4 A flowchart of obtaining a task package quality verification index for a peer review quality assessment method based on data mining provided in an embodiment of the present application. DETAILED DESCRIPTION

[0019] 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.

[0020] 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.

[0021] Please refer to Figure 1 , Figure 1 The flowchart of a peer review quality assessment method based on data mining in some embodiments of the present application. The peer review quality assessment method based on data mining is used in terminal devices, such as mobile phones, computers, etc. The peer review quality assessment method based on data mining includes the following steps: S11. Obtaining the task package performance information and task package evaluation information of the peer evaluation task package; S12, extracting task package effectiveness feature data and task package review table data respectively according to the task package effectiveness information and task package review information, and generating a task package review feature portrait and extracting a task package evaluation data packet; S13, performing quality fitting processing on the task package evaluation data set of the task package evaluation data packet through a preset task package quality assessment model to obtain a task package quality verification index; S14, performing a task package peer quality evaluation on the task package review feature portrait according to the trained task package peer quality evaluation model, and obtaining corresponding peer evaluation quality effectiveness data; S15, processing the task package evaluation data set of the peer evaluation task package in combination with the task package quality verification index and the peer evaluation quality effectiveness data to obtain a peer evaluation quality assessment index; S16. Process the task peer review quality level corresponding to the peer review quality assessment index in combination with the task package evaluation data set to obtain peer recommendation promotion data and conduct peer recommendation.

[0022] Among them, in order to make an assessment judgment on the evaluation quality of peer evaluation of a certain project or task, the object information and evaluation information of the peer evaluation are combined into a peer evaluation task package, and the object task package is evaluated and verified. The goal is to obtain the quality evaluation results of the peer evaluation and obtain the recommendation and promotion results, so as to promote the projects or tasks of the peer evaluation objects that meet the requirements. First, the task package effectiveness information and task package application information of the peer evaluation object task package are obtained. The task package contains the project or task execution information, evaluation results and review results information of the peer evaluation object, and the submitted application evaluation information. Then, according to the task package effectiveness information and the task package application information, the task package effectiveness feature data and the task package review form data are extracted respectively, that is, the data of the project / task implementation effectiveness of the peer evaluation object and the data of the peer evaluation submission form are extracted through the information in the task package, and the task package review feature portrait for the project / task description and peer evaluation review of the task package is generated, and the task package evaluation data packet is extracted through the feature portrait, and then the task package evaluation data packet is quality fitted on the task package evaluation data packet through the preset task package quality assessment model to obtain the task package quality verification index, that is, the evaluation object task package is obtained. Make a quality inspection, and then conduct a task package peer quality inspection on the task package review feature portrait according to the trained task package peer quality inspection model to obtain the corresponding peer evaluation quality effectiveness data, that is, the quality judgment of the peer evaluation results. Then, according to the task package evaluation data set of the peer evaluation task package, the task package quality inspection index and the peer evaluation quality effectiveness data are processed to obtain the peer evaluation quality assessment index and the corresponding task peer evaluation quality level, and then combined with the task package evaluation data set for processing to obtain peer recommendation and promotion data, that is, make a quality evaluation of the project / task itself and the peer evaluation quality of the peer evaluation object, and generate the promotion degree inspection result of the object project / task, conduct peer recommendation, realize the inspection of the peer evaluation object project / task itself and the accurate judgment of the peer evaluation quality, and improve the assessment accuracy of the evaluation quality of the peer evaluation object task package. Finally, this scheme is a scheme for obtaining information, data, and parameters for technical processing through external data interaction with the preset third-party task evaluation database platform. This technology is a means of information acquisition, data interaction and extraction, and data processing technology, and is a non-artificially set rule or project law. This case has technical laws.

[0023] Please refer to Figure 2 , Figure 2 The present invention is a flowchart of obtaining task package performance information and task package evaluation information of a peer evaluation task package in a method for peer evaluation quality assessment based on data mining in some embodiments of the present application. According to an embodiment of the present invention, the task package performance information and task package evaluation information of the peer evaluation task package are obtained as follows: S21. Obtaining task package operation information and task package report information of the peer evaluation task package; S22, extracting task package performance information according to the task package operation information and task package report information, including task package completion status information, task package node timeliness information, task package loss information, task package result output information and task package profit information; S23. Obtaining the task package application information of the peer-evaluated task package, including task package type information, task package ranking information, task package scale information, task package resource support information, task package influence information, and task package popularity information.

[0024] Among them, in order to achieve accurate evaluation of peer evaluation objects and evaluation results, first of all, the task package operation information and task package report information of the task package of the object of peer evaluation are obtained, and the task package effectiveness information is extracted according to the task package operation information and task package report information, including task package completion status information, task package node timeliness information, task package loss information, task package output information and task package profit information, that is, the operation and report information of the project / task execution of the evaluation object is used to extract effectiveness information, including the completion status, node timeliness, loss, output and profit information of the object's execution, so as to comprehensively reflect the implementation status of the project / task of the peer evaluation object, and at the same time, the task package application information of the peer evaluation task package is obtained, that is, the application evaluation information of the evaluation object, including type, ranking, scale, resource support, influence and popularity information. This information provides an information source basis for the effectiveness evaluation of the peer evaluation object.

[0025] Please refer to Figure 3 , Figure 3 It is a flow chart of generating a task package review feature portrait and extracting a task package evaluation data packet of a peer review quality assessment method based on data mining in some embodiments of the present application. According to an embodiment of the present invention, the task package effectiveness feature data and the task package review table data are respectively extracted according to the task package effectiveness information and the task package evaluation information, and the task package review feature portrait is generated and the task package evaluation data packet is extracted, specifically: S31, extracting task package performance characteristic data according to the task package performance information, including completion rate data, total process time efficiency data, task revenue data, achievement profitability data, and asset value-added data; S32, extracting task package review table data according to the task package review information, including task intensity data, scale data, resource peer ratio data, review weight data, and expected risk assessment data; S33, generating a task package review feature portrait based on the completion rate data, total process time efficiency data, task revenue data, achievement profitability data, asset value-added data, and task enthusiasm data, scale data, resource peer ratio data, review weight data, and expected risk assessment data; S34, extracting the task package evaluation data packet according to the task package review feature portrait.

[0026] Among them, further, task package effectiveness characteristic data is extracted according to the task package effectiveness information, that is, the data on the execution of the target project / task, including the target completion rate, the overall time efficiency of the implementation process, the implementation benefits, the profitability of the results and the data on the asset appreciation; then, task package review form data is extracted according to the task package application information, that is, the review form data of the target project / task, including the data on the enthusiasm of the object implementation, the scale, the proportion of resources among peers, the review weight and the expected risk; then, a characteristic portrait of the task package review description for the target project / task is generated according to the above-extracted data, which is a description portrait of the implementation results information of the task package submitted for peer evaluation of the target task / project, and the evaluation data packet of the task package is extracted according to the task package review characteristic portrait.

[0027] Please refer to Figure 4 , Figure 4 It is a flow chart of obtaining a task package quality verification index of a peer review quality assessment method based on data mining in some embodiments of the present application. According to an embodiment of the present invention, the task package evaluation data set of the task package evaluation data packet is subjected to quality fitting processing by a preset task package quality assessment model to obtain the task package quality verification index, specifically: S41, the task package evaluation data package includes a task package evaluation data set, including revenue and profit data, value evaluation data, resource feedback rate data, scale expansion rate data and risk weight assessment data; S42, performing quality fitting processing on the peer-evaluated task package through a preset task package quality assessment model according to the task package evaluation data set to obtain a task package quality verification index; The fitting procedure of the task package quality verification index is: ; in, is the task package quality verification index, They are profit and loss data, value evaluation data, resource return rate data, and scale expansion rate data. For risk weight assessment data, It is the preset verification characteristic coefficient (the preset verification characteristic coefficient is obtained by querying the preset third-party task evaluation database platform).

[0028] Among them, in order to evaluate the implementation quality of the task packages that are the objects of peer evaluation, the data set of the task package evaluation data package, including the surplus excess data of income, the evaluation degree data of value, the feedback rate data of resources, the scale expansion rate data and the risk weight assessment data, is calculated and processed according to the calculation formula of the preset task package quality evaluation model to obtain the task package quality inspection index for the quality inspection of the task package.

[0029] According to an embodiment of the present invention, the task package peer quality evaluation is performed on the task package review feature portrait according to the trained task package peer quality evaluation model to obtain the corresponding peer evaluation quality effectiveness data, specifically: Extracting peer task evaluation data of the peer evaluation task package according to the task package review feature portrait; The peer task evaluation data includes score floating rate data, evaluation compliance rate data, expected assessment difference rate data, risk assessment valuation data and peer assessment profit and loss data; Obtain peer evaluation data of multiple peer evaluation task packages that have completed peer evaluation and corresponding peer evaluation quality effectiveness data through a preset task package evaluation release database, and perform training to obtain a task package peer quality evaluation model; The peer task evaluation data of the peer evaluation task package is input into the trained peer quality assessment model of the task package for processing to obtain peer evaluation quality effectiveness data.

[0030] At the same time, in order to obtain an effectiveness assessment of the evaluation quality of peer evaluation of project / task implementation task packages, that is, to judge the quality of peer evaluation, the peer task evaluation data of the target project / task is extracted according to the task package review feature portrait, including the score fluctuation rate of each peer evaluation, the evaluation compliance rate, the difference rate with the expected evaluation, the risk valuation and the surplus / deficit data of the total peer evaluation, that is, the statistical data reflecting the quality effect of the peer evaluation, and then the peer quality evaluation model of the task package trained with historical data of multiple completed evaluations is used to perform model processing on the above-mentioned peer task evaluation data to obtain the peer evaluation quality effectiveness data, that is, the quality effectiveness judgment result data of the peer evaluation is obtained through the model.

[0031] According to an embodiment of the present invention, the task package evaluation data set based on the peer evaluation task package is processed in combination with the task package quality verification index and the peer evaluation quality effectiveness data to obtain the peer evaluation quality assessment index, specifically: Processing the revenue surplus data, value evaluation data, and risk weight assessment data of the peer evaluation task package in combination with the task package quality verification index and the peer evaluation quality effectiveness data to obtain a peer evaluation quality assessment index; The calculation formula of the peer review quality assessment index is: ; in, is a peer review quality assessment index, They are profit and loss data, value evaluation data, and risk weight assessment data. is the task package quality verification index, To peer review quality performance data, It is the preset characteristic coefficient (the preset characteristic coefficient is obtained by querying the preset third-party task evaluation database platform).

[0032] Among them, the evaluation index reflecting the evaluation quality of the task package of the peer evaluation object project / task is calculated based on the profit and loss data, value evaluation data, risk weight assessment data, combined with the task package quality inspection index and peer evaluation quality effectiveness data, to obtain the evaluation quality of the task package of the peer evaluation object project / task, that is, to obtain the evaluation quality of the project / task of the peer evaluation task package itself and the quality effectiveness of the peer evaluation, thereby achieving an overall quality evaluation of the task package of the peer evaluation object.

[0033] According to an embodiment of the present invention, the task peer evaluation quality level corresponding to the peer evaluation quality assessment index is processed in combination with the task package evaluation data set to obtain peer recommendation promotion data, and peer recommendation is performed, specifically: Obtaining a corresponding task peer review quality grade according to the peer review quality assessment index of the peer review task package; Processing is performed based on the task peer evaluation quality level combined with the resource feedback rate data, scale expansion rate data and the peer evaluation quality assessment index to obtain peer recommendation promotion data; Peer-promoting the peer evaluation task package according to the peer recommendation promotion data; The calculation formula for the peer recommendation promotion data is: ; in, Recommend promotion data to peers, They are resource feedback rate data and scale expansion rate data. is a peer review quality assessment index, Peer review quality rating for tasks, It is the preset characteristic coefficient (the preset characteristic coefficient is obtained by querying the preset third-party task evaluation database platform).

[0034] Among them, in order to obtain effective recommendations for the projects / tasks of the peer-evaluated task packages, the corresponding task peer evaluation quality level is obtained according to the peer evaluation quality assessment index. The quality level is obtained by comparing and querying the preset third-party task evaluation database platform to obtain the level corresponding to the quality assessment index, and then combining the resource feedback rate data, scale expansion rate data and peer evaluation quality assessment index for calculation to obtain peer recommendation and promotion data, that is, to obtain the evaluation results of the recommendation degree of the task package projects / tasks, and then according to the peer recommendation and promotion data, the peer-evaluated object task packages are peer-promoted in the form of ranking tables or recommendation categories, thereby realizing the evaluation and recommendation evaluation of the peer evaluation quality.

[0035] The present invention also discloses a peer review quality assessment system based on data mining, comprising a memory and a processor, wherein the memory comprises a peer review quality assessment method program based on data mining, and when the peer review quality assessment method program based on data mining is executed by the processor, the following steps are implemented: Obtain the task package performance information and task package evaluation information of the peer evaluation task package; Extracting task package effectiveness feature data and task package review table data respectively according to the task package effectiveness information and task package review information, and generating a task package review feature portrait and extracting a task package evaluation data packet; Performing quality fitting processing on the task package evaluation data set of the task package evaluation data packet through a preset task package quality assessment model to obtain a task package quality verification index; Conducting a peer quality evaluation of the task package on the review feature portrait of the task package according to the trained peer quality evaluation model of the task package, and obtaining the corresponding peer evaluation quality effectiveness data; Processing the task package evaluation data set of the peer evaluation task package in combination with the task package quality verification index and the peer evaluation quality effectiveness data to obtain a peer evaluation quality assessment index; The task peer evaluation quality level corresponding to the peer evaluation quality assessment index is processed in combination with the task package evaluation data set to obtain peer recommendation promotion data and perform peer recommendation.

[0036] Among them, in order to make an assessment judgment on the evaluation quality of peer evaluation of a certain project or task, the object information and evaluation information of the peer evaluation are combined into a peer evaluation task package, and the object task package is evaluated and verified. The goal is to obtain the quality evaluation results of the peer evaluation and obtain the recommendation and promotion results, so as to promote the projects or tasks of the peer evaluation objects that meet the requirements. First, the task package effectiveness information and task package application information of the peer evaluation object task package are obtained. The task package contains the project or task execution information, evaluation results and review results information of the peer evaluation object, and the submitted application evaluation information. Then, according to the task package effectiveness information and the task package application information, the task package effectiveness feature data and the task package review form data are extracted respectively, that is, the data of the project / task implementation effectiveness of the peer evaluation object and the data of the peer evaluation submission form are extracted through the information in the task package, and the task package review feature portrait for the project / task description and peer evaluation review of the task package is generated, and the task package evaluation data packet is extracted through the feature portrait, and then the task package evaluation data packet is quality fitted on the task package evaluation data packet through the preset task package quality assessment model to obtain the task package quality verification index, that is, the evaluation object task package is obtained. Make a quality inspection, and then conduct a task package peer quality inspection on the task package review feature portrait according to the trained task package peer quality inspection model to obtain the corresponding peer evaluation quality effectiveness data, that is, the quality judgment of the peer evaluation results. Then, according to the task package evaluation data set of the peer evaluation task package, the task package quality inspection index and the peer evaluation quality effectiveness data are processed to obtain the peer evaluation quality assessment index and the corresponding task peer evaluation quality level, and then combined with the task package evaluation data set for processing to obtain peer recommendation and promotion data, that is, make a quality evaluation of the project / task itself and the peer evaluation quality of the peer evaluation object, and generate the promotion degree inspection result of the object project / task, conduct peer recommendation, realize the inspection of the peer evaluation object project / task itself and the accurate judgment of the peer evaluation quality, and improve the assessment accuracy of the evaluation quality of the peer evaluation object task package. Finally, this scheme is a scheme for obtaining information, data, and parameters for technical processing through external data interaction with the preset third-party task evaluation database platform. This technology is a means of information acquisition, data interaction and extraction, and data processing technology, and is a non-artificially set rule or project law. This case has technical laws.

[0037] According to an embodiment of the present invention, the step of obtaining task package performance information and task package evaluation information of a peer evaluation task package is as follows: Obtain task package operation information and task package report information of peer evaluation task packages; Extracting task package performance information according to the task package operation information and task package report information, including task package completion status information, task package node timeliness information, task package loss information, task package result output information and task package profit information; Obtain task package application information of the peer-evaluated task package, including task package type information, task package ranking information, task package scale information, task package resource support information, task package influence information, and task package popularity information.

[0038] Among them, in order to achieve accurate evaluation of peer evaluation objects and evaluation results, first of all, the task package operation information and task package report information of the task package of the object of peer evaluation are obtained, and the task package effectiveness information is extracted according to the task package operation information and task package report information, including task package completion status information, task package node timeliness information, task package loss information, task package output information and task package profit information, that is, the operation and report information of the project / task execution of the evaluation object is used to extract effectiveness information, including the completion status, node timeliness, loss, output and profit information of the object's execution, so as to comprehensively reflect the implementation status of the project / task of the peer evaluation object, and at the same time, the task package application information of the peer evaluation task package is obtained, that is, the application evaluation information of the evaluation object, including type, ranking, scale, resource support, influence and popularity information. This information provides an information source basis for the effectiveness evaluation of the peer evaluation object.

[0039] According to an embodiment of the present invention, the task package effectiveness feature data and the task package review table data are respectively extracted according to the task package effectiveness information and the task package review information, and a task package review feature portrait is generated and a task package evaluation data packet is extracted, specifically: Extracting task package performance characteristic data according to the task package performance information, including completion rate data, total process time efficiency data, task revenue data, achievement profitability data, and asset value-added data; Extract task package review table data based on the task package application information, including task intensity data, scale data, resource peer ratio data, review weight data, and expected risk assessment data; Generate a task package review feature profile based on the completion rate data, total process time efficiency data, task revenue data, achievement profitability data, asset value-added data, and task enthusiasm data, scale data, resource peer ratio data, review weight data, and expected risk assessment data; Extract the task package evaluation data packet according to the task package review feature portrait.

[0040] Among them, further, task package effectiveness characteristic data is extracted according to the task package effectiveness information, that is, the data on the execution of the target project / task, including the target completion rate, the overall time efficiency of the implementation process, the implementation benefits, the profitability of the results and the data on the asset appreciation; then, task package review form data is extracted according to the task package application information, that is, the review form data of the target project / task, including the data on the enthusiasm of the object implementation, the scale, the proportion of resources among peers, the review weight and the expected risk; then, a characteristic portrait of the task package review description for the target project / task is generated according to the above-extracted data, which is a description portrait of the implementation results information of the task package submitted for peer evaluation of the target task / project, and the evaluation data packet of the task package is extracted according to the task package review characteristic portrait.

[0041] According to an embodiment of the present invention, the task package evaluation data set of the task package evaluation data packet is subjected to quality fitting processing by a preset task package quality assessment model to obtain a task package quality verification index, specifically: The task package evaluation data package includes a task package evaluation data set, including revenue surplus data, value evaluation data, resource return rate data, scale expansion rate data and risk weight assessment data; According to the task package evaluation data set, quality fitting processing is performed on the peer-evaluated task package through a preset task package quality assessment model to obtain a task package quality verification index; The fitting procedure of the task package quality verification index is: ; in, is the task package quality verification index, They are profit and loss data, value evaluation data, resource return rate data, and scale expansion rate data. For risk weight assessment data, It is the preset verification characteristic coefficient (the preset verification characteristic coefficient is obtained by querying the preset third-party task evaluation database platform).

[0042] Among them, in order to evaluate the implementation quality of the task packages that are the objects of peer evaluation, the data set of the task package evaluation data package, including the surplus excess data of income, the evaluation degree data of value, the feedback rate data of resources, the scale expansion rate data and the risk weight assessment data, is calculated and processed according to the calculation formula of the preset task package quality evaluation model to obtain the task package quality inspection index for the quality inspection of the task package.

[0043] According to an embodiment of the present invention, the task package peer quality evaluation is performed on the task package review feature portrait according to the trained task package peer quality evaluation model to obtain the corresponding peer evaluation quality effectiveness data, specifically: Extracting peer task evaluation data of the peer evaluation task package according to the task package review feature portrait; The peer task evaluation data includes score floating rate data, evaluation compliance rate data, expected assessment difference rate data, risk assessment valuation data and peer assessment profit and loss data; Obtain peer task evaluation data of multiple peer evaluation task packages that have completed peer evaluation and corresponding peer evaluation quality effectiveness data through a preset task package evaluation release database, and perform training to obtain a task package peer quality evaluation model; The peer task evaluation data of the peer evaluation task package is input into the trained peer quality assessment model of the task package for processing to obtain peer evaluation quality effectiveness data.

[0044] At the same time, in order to obtain an effectiveness assessment of the evaluation quality of peer evaluation of project / task implementation task packages, that is, to judge the quality of peer evaluation, the peer task evaluation data of the target project / task is extracted according to the task package review feature portrait, including the score fluctuation rate of each peer evaluation, the evaluation compliance rate, the difference rate with the expected evaluation, the risk valuation and the surplus / deficit data of the total peer evaluation, that is, the statistical data reflecting the quality effect of the peer evaluation, and then the peer quality evaluation model of the task package trained with historical data of multiple completed evaluations is used to perform model processing on the above-mentioned peer task evaluation data to obtain the peer evaluation quality effectiveness data, that is, the quality effectiveness judgment result data of the peer evaluation is obtained through the model.

[0045] According to an embodiment of the present invention, the task package evaluation data set based on the peer evaluation task package is processed in combination with the task package quality verification index and the peer evaluation quality effectiveness data to obtain the peer evaluation quality assessment index, specifically: Processing the revenue surplus data, value evaluation data, and risk weight assessment data of the peer evaluation task package in combination with the task package quality verification index and the peer evaluation quality effectiveness data to obtain a peer evaluation quality assessment index; The calculation formula of the peer review quality assessment index is: ; in, is a peer review quality assessment index, They are profit and loss data, value evaluation data, and risk weight assessment data. is the task package quality verification index, To peer review quality performance data, It is the preset characteristic coefficient (the preset characteristic coefficient is obtained by querying the preset third-party task evaluation database platform).

[0046] Among them, the evaluation index reflecting the evaluation quality of the task package of the peer evaluation object project / task is calculated based on the profit and loss data, value evaluation data, risk weight assessment data, combined with the task package quality inspection index and peer evaluation quality effectiveness data, to obtain the evaluation quality of the task package of the peer evaluation object project / task, that is, to obtain the evaluation quality of the project / task of the peer evaluation task package itself and the quality effectiveness of the peer evaluation, thereby achieving an overall quality evaluation of the task package of the peer evaluation object.

[0047] According to an embodiment of the present invention, the task peer evaluation quality level corresponding to the peer evaluation quality assessment index is processed in combination with the task package evaluation data set to obtain peer recommendation promotion data, and peer recommendation is performed, specifically: Obtaining a corresponding task peer review quality grade according to the peer review quality assessment index of the peer review task package; Processing is performed based on the task peer evaluation quality level combined with the resource feedback rate data, scale expansion rate data and the peer evaluation quality assessment index to obtain peer recommendation promotion data; Peer-promoting the peer evaluation task package according to the peer recommendation promotion data; The calculation formula for the peer recommendation promotion data is: ; in, Recommend promotion data to peers, They are resource feedback rate data and scale expansion rate data. is a peer review quality assessment index, Peer review quality rating for tasks, It is the preset characteristic coefficient (the preset characteristic coefficient is obtained by querying the preset third-party task evaluation database platform).

[0048] Among them, in order to obtain effective recommendations for the projects / tasks of the peer-evaluated task packages, the corresponding task peer evaluation quality level is obtained according to the peer evaluation quality assessment index. The quality level is obtained by comparing and querying the preset third-party task evaluation database platform to obtain the level corresponding to the quality assessment index, and then combining the resource feedback rate data, scale expansion rate data and peer evaluation quality assessment index for calculation to obtain peer recommendation and promotion data, that is, to obtain the evaluation results of the recommendation degree of the task package projects / tasks, and then according to the peer recommendation and promotion data, the peer-evaluated object task packages are peer-promoted in the form of ranking tables or recommendation categories, thereby realizing the evaluation and recommendation evaluation of the peer evaluation quality.

[0049] The third aspect of the present invention provides a readable storage medium, which includes a peer review quality assessment method program based on data mining. When the peer review quality assessment method program based on data mining is executed by a processor, the steps of a peer review quality assessment method based on data mining as described in any one of the above items are implemented.

[0050] The present invention discloses a peer review quality assessment method, system and medium based on data mining. The method extracts task package effectiveness characteristics and review form data according to the task package effectiveness and application information of the peer review object task package, generates a task package review feature portrait, extracts the task package evaluation data packet, and then respectively performs quality fitting and peer quality assessment on the task package evaluation data set and the task package review feature portrait through a model, respectively obtains the task package quality verification index and the peer review quality effectiveness data, and then processes to obtain the peer review quality assessment index and the peer recommendation and promotion data, and finally performs peer recommendation; thereby generating a feature portrait of data description based on the data of the peer review task package, and performing task package quality verification and peer review quality assessment and recommendation assessment, thereby realizing a quality assessment technology for the peer review object task package.

[0051] 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.

[0052] 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.

[0053] 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.

[0054] 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, the aforementioned program can be stored in a readable storage medium, and 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.

[0055] 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, server, or 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. A peer review quality assessment method based on data mining, comprising the following steps: Obtain the task package performance information and task package evaluation information of the peer evaluation task package; Extracting task package effectiveness feature data and task package review table data respectively according to the task package effectiveness information and task package review information, and generating a task package review feature portrait and extracting a task package evaluation data packet; Performing quality fitting processing on the task package evaluation data set of the task package evaluation data packet through a preset task package quality assessment model to obtain a task package quality verification index; Conducting a peer quality evaluation of the task package on the review feature portrait of the task package according to the trained peer quality evaluation model of the task package, and obtaining the corresponding peer evaluation quality effectiveness data; Processing the task package evaluation data set of the peer evaluation task package in combination with the task package quality verification index and the peer evaluation quality effectiveness data to obtain a peer evaluation quality assessment index; The task peer evaluation quality level corresponding to the peer evaluation quality assessment index is processed in combination with the task package evaluation data set to obtain peer recommendation promotion data and perform peer recommendation.

2. The peer review quality assessment method based on data mining according to claim 1 is characterized in that: The task package performance information and task package evaluation information of the peer evaluation task package are obtained, including: Obtain task package operation information and task package report information of peer evaluation task packages; Extracting task package performance information according to the task package operation information and task package report information, including task package completion status information, task package node timeliness information, task package loss information, task package result output information and task package profit information; Obtain task package application information of the peer-evaluated task package, including task package type information, task package ranking information, task package scale information, task package resource support information, task package influence information, and task package popularity information.

3. The peer review quality assessment method based on data mining according to claim 2 is characterized in that: The extracting task package effectiveness feature data and task package review table data according to the task package effectiveness information and task package review information respectively, and generating a task package review feature portrait and extracting a task package evaluation data packet, includes: Extracting task package performance characteristic data according to the task package performance information, including completion rate data, total process time efficiency data, task revenue data, achievement profitability data, and asset value-added data; Extract task package review table data based on the task package application information, including task intensity data, scale data, resource peer ratio data, review weight data, and expected risk assessment data; Generate a task package review feature profile based on the completion rate data, total process time efficiency data, task revenue data, achievement profitability data, asset value-added data, and task enthusiasm data, scale data, resource peer ratio data, review weight data, and expected risk assessment data; Extract the task package evaluation data packet according to the task package review feature portrait.

4. The peer review quality assessment method based on data mining according to claim 3 is characterized in that: The step of performing quality fitting processing on the task package evaluation data set of the task package evaluation data packet by using a preset task package quality assessment model to obtain a task package quality verification index comprises: The task package evaluation data package includes a task package evaluation data set, including revenue surplus data, value evaluation data, resource feedback rate data, scale expansion rate data and risk weight assessment data; According to the task package evaluation data set, quality fitting processing is performed on the peer-evaluated task package through a preset task package quality assessment model to obtain a task package quality verification index.

5. The peer review quality assessment method based on data mining according to claim 4 is characterized in that: The task package peer quality evaluation model trained for the task package is used to evaluate the task package review feature portrait, and the corresponding peer evaluation quality effectiveness data is obtained, including: Extracting peer task evaluation data of the peer evaluation task package according to the task package review feature portrait; The peer task evaluation data includes score floating rate data, evaluation compliance rate data, expected assessment difference rate data, risk assessment valuation data and peer assessment profit and loss data; Obtain peer evaluation data of multiple peer evaluation task packages that have completed peer evaluation and corresponding peer evaluation quality effectiveness data through a preset task package evaluation release database, and perform training to obtain a task package peer quality evaluation model; The peer task evaluation data of the peer evaluation task package is input into the trained peer quality assessment model of the task package for processing to obtain peer evaluation quality effectiveness data.

6. The peer review quality assessment method based on data mining according to claim 5 is characterized in that: The task package evaluation data set according to the peer evaluation task package is processed in combination with the task package quality verification index and the peer evaluation quality effectiveness data to obtain the peer evaluation quality assessment index, including: Processing the revenue surplus data, value evaluation data, and risk weight assessment data of the peer evaluation task package in combination with the task package quality verification index and the peer evaluation quality effectiveness data to obtain a peer evaluation quality assessment index; The calculation formula of the peer review quality assessment index is: ； in, is a peer review quality assessment index, They are profit and loss data, value evaluation data, and risk weight assessment data. is the task package quality verification index, To peer review quality performance data, is the preset characteristic coefficient.

7. The peer review quality assessment method based on data mining according to claim 6 is characterized in that: The task peer evaluation quality level corresponding to the peer evaluation quality assessment index is processed in combination with the task package evaluation data set to obtain peer recommendation promotion data, and peer recommendation is performed, including: Obtaining a corresponding task peer review quality grade according to the peer review quality assessment index of the peer review task package; Processing is performed based on the task peer evaluation quality level combined with the resource feedback rate data, scale expansion rate data and the peer evaluation quality assessment index to obtain peer recommendation promotion data; The peer evaluation task package is peer promoted according to the peer recommendation promotion data.

8. A peer review quality assessment system based on data mining, characterized in that: The system includes: a memory and a processor, wherein the memory includes a program of a peer review quality assessment method based on data mining, and when the program of the peer review quality assessment method based on data mining is executed by the processor, the following steps are implemented: Obtain the task package performance information and task package evaluation information of the peer evaluation task package; Extracting task package effectiveness feature data and task package review table data respectively according to the task package effectiveness information and task package review information, and generating a task package review feature portrait and extracting a task package evaluation data packet; Performing quality fitting processing on the task package evaluation data set of the task package evaluation data packet through a preset task package quality assessment model to obtain a task package quality verification index; Conducting a peer quality evaluation of the task package on the review feature portrait of the task package according to the trained peer quality evaluation model of the task package, and obtaining the corresponding peer evaluation quality effectiveness data; Processing the task package evaluation data set of the peer evaluation task package in combination with the task package quality verification index and the peer evaluation quality effectiveness data to obtain a peer evaluation quality assessment index; The task peer evaluation quality level corresponding to the peer evaluation quality assessment index is processed in combination with the task package evaluation data set to obtain peer recommendation promotion data and perform peer recommendation.

9. The peer review quality assessment system based on data mining according to claim 8, characterized in that: The task package performance information and task package evaluation information of the peer evaluation task package are obtained, including: Obtain task package operation information and task package report information of peer evaluation task packages; Extracting task package performance information according to the task package operation information and task package report information, including task package completion status information, task package node timeliness information, task package loss information, task package result output information and task package profit information; Obtain task package application information of the peer-evaluated task package, including task package type information, task package ranking information, task package scale information, task package resource support information, task package influence information, and task package popularity information.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a peer review quality assessment method program based on data mining. When the peer review quality assessment method program based on data mining is executed by a processor, the steps of a peer review quality assessment method based on data mining as described in any one of claims 1 to 7 are implemented.

Images