CN115408223A

CN115408223A - Project quality prediction method, device, computer system and storage medium

Info

Publication number: CN115408223A
Application number: CN202211059735.2A
Authority: CN
Inventors: 翟宏
Original assignee: Industrial and Commercial Bank of China Ltd ICBC; ICBC Technology Co Ltd
Current assignee: Industrial and Commercial Bank of China Ltd ICBC; ICBC Technology Co Ltd
Priority date: 2022-08-31
Filing date: 2022-08-31
Publication date: 2022-11-29

Abstract

The present disclosure provides a project quality prediction method, apparatus, computer system and storage medium, which can be used in the technical field of big data, artificial intelligence or other fields. Wherein, the method comprises the following steps: acquiring index parameter information corresponding to software and hardware indexes influencing the quality of a target project; inputting the index parameter information into a trained reflection propagation neuron network model to obtain a prediction result of the quality level of the characteristic target item, wherein the reflection propagation neuron network model comprises a first number of input layer neuron nodes, a second number of hidden layer neuron nodes and a third number of output layer neuron nodes, the second number is determined according to at least one of a root value and a product, the root value represents a value obtained by performing root sign on the sum of the first number and the third number, and the product represents the product of the sum of the first number and the third number and a predefined coefficient.

Description

Project quality prediction method, device, computer system and storage medium

Technical Field

The present disclosure relates to the field of big data and artificial intelligence technologies, and in particular, to a project quality prediction method, apparatus, computer system, and storage medium.

Background

The project quality prediction and evaluation method mainly adopts manual work. In the manual prediction process, a general quality assessment is performed on the project by means of human experience. Then, the online quality condition of the project is estimated approximately by combining some quality indexes of the project and some historical projects. And if the estimated quality result does not meet the online requirement, manually alarming.

In the course of implementing the disclosed concept, the inventors found that there is at least the following problem in the related art, which is due to the fact that the difference of experience, ability, responsibility and the like between people completely depends on the manual judgment, and the evaluation difference between different people can be caused. For evaluation indexes which can be used for reference, different project applications do not have uniform standards, and differences of different prediction results can be brought.

Disclosure of Invention

In view of the above, the present disclosure provides a project quality prediction method, apparatus, computer system, and storage medium.

One aspect of the present disclosure provides a project quality prediction method, including: acquiring index parameter information corresponding to software and hardware indexes influencing the quality of a target project; inputting the index parameter information into a trained reflection propagation neuron network model to obtain a prediction result representing a quality level of the target item, wherein the reflection propagation neuron network model comprises a first number of input layer neuron nodes, a second number of hidden layer neuron nodes and a third number of output layer neuron nodes, the second number is determined according to at least one of a root value and a product, the root value represents a value after a sum of the first number and the third number is subjected to an opening sign, and the product represents a product of the sum of the first number and the third number and a predefined coefficient.

Another aspect of the present disclosure provides a project quality prediction apparatus including: the first acquisition module is used for acquiring index parameter information corresponding to software and hardware indexes influencing the quality of a target project; a first obtaining module, configured to input the index parameter information into a trained reflection propagation neuron network model to obtain a prediction result characterizing a quality level of the target item, wherein the reflection propagation neuron network model includes a first number of input layer neuron nodes, a second number of hidden layer neuron nodes, and a third number of output layer neuron nodes, the second number is determined according to at least one of a root value and a product, the root value characterizes a value after a sum of the first number and the third number is signed, and the product characterizes a product of the sum of the first number and the third number and a predefined coefficient.

Another aspect of the present disclosure provides a computer system comprising: one or more processors; a memory for storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the project quality prediction method of the present disclosure.

Another aspect of the present disclosure provides a computer-readable storage medium having stored thereon computer-executable instructions for, when executed, implementing a project quality prediction method as described in the present disclosure.

Another aspect of the disclosure provides a computer program product comprising computer executable instructions that when executed are for implementing the project quality prediction method of the disclosure.

According to the embodiment of the disclosure, by adopting the technical means of determining the second number of the hidden layer neuron nodes according to at least one of the root value of the sum of the first number of the input layer neuron nodes and the third number of the output layer neuron nodes and the product of the sum and the predefined coefficient, and inputting the index parameter information into the trained reflection propagation neuron network model comprising the second number of the hidden layer neuron nodes to obtain the prediction result of the quality level of the target item, the technical problem that the manual prediction result is inaccurate is at least partially overcome because the quality of the item can be predicted according to the reflection propagation neuron network model. In addition, by customizing the calculation rule, a reflection propagation neuron network model comprising the most optimal number of hidden layer neuron nodes can be obtained, the training precision can be improved on the basis of reducing the training times, and the project quality can be more accurately predicted.

Drawings

The above and other objects, features and advantages of the present disclosure will become more apparent from the following description of embodiments of the present disclosure with reference to the accompanying drawings, in which:

FIG. 1 schematically illustrates an exemplary system architecture to which a project quality prediction method may be applied, according to an embodiment of the disclosure;

FIG. 2 schematically illustrates a flow diagram of a project quality prediction method according to an embodiment of the present disclosure;

FIG. 3 schematically illustrates a network structure diagram of a reflection propagation neuron network model according to an embodiment of the present disclosure;

FIG. 4 schematically shows a block diagram of an item quality prediction apparatus according to an embodiment of the present disclosure; and

fig. 5 schematically illustrates a block diagram of a computer system suitable for implementing the above-described method according to an embodiment of the present disclosure.

Detailed Description

Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. It should be understood that these descriptions are illustrative only and are not intended to limit the scope of the present disclosure. In the following detailed description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the disclosure. It may be evident, however, that one or more embodiments may be practiced without these specific details. Moreover, in the following description, descriptions of well-known structures and techniques are omitted so as to not unnecessarily obscure the concepts of the present disclosure.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. The terms "comprises," "comprising," and the like, as used herein, specify the presence of stated features, steps, operations, and/or components, but do not preclude the presence or addition of one or more other features, steps, operations, or components.

All terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art unless otherwise defined. It is noted that the terms used herein should be interpreted as having a meaning that is consistent with the context of this specification and should not be interpreted in an idealized or overly formal sense.

Where a convention analogous to "at least one of A, B, and C, etc." is used, in general such a construction is intended in the sense one having skill in the art would understand the convention (e.g., "a system having at least one of A, B, and C" would include but not be limited to systems that have A alone, B alone, C alone, A and B together, A and C together, B and C together, and/or A, B, and C together, etc.). Where a convention analogous to "at least one of A, B, or C, etc." is used, in general such a construction is intended in the sense one having skill in the art would understand the convention (e.g., "a system having at least one of A, B, or C" would include but not be limited to systems that have A alone, B alone, C alone, A and B together, A and C together, B and C together, and/or A, B, and C together, etc.).

The embodiment of the disclosure provides a project quality prediction method, a project quality prediction device, a computer system and a storage medium. Acquiring index parameter information corresponding to software and hardware indexes influencing the quality of a target project; inputting the index parameter information into a trained reflection propagation neuron network model to obtain a prediction result of the quality level of the characteristic target item, wherein the reflection propagation neuron network model comprises a first number of input layer neuron nodes, a second number of hidden layer neuron nodes and a third number of output layer neuron nodes, the second number is determined according to at least one of a root value and a product, the root value represents a value obtained by performing root sign on the sum of the first number and the third number, and the product represents the product of the sum of the first number and the third number and a predefined coefficient.

Fig. 1 schematically illustrates an exemplary system architecture 100 to which a project quality prediction method may be applied, according to an embodiment of the present disclosure. It should be noted that fig. 1 is only an example of a system architecture to which the embodiments of the present disclosure may be applied to help those skilled in the art understand the technical content of the present disclosure, and does not mean that the embodiments of the present disclosure may not be applied to other devices, systems, environments or scenarios.

As shown in fig. 1, a system architecture 100 according to this embodiment may include

terminal devices

101, 102, 103, a network 104, and a server 105. Network 104 is the medium used to provide communication links between

terminal devices

101, 102, 103 and server 105. Network 104 may include various connection types, such as wired and/or wireless communication links, and so forth.

The user may use the

terminal devices

101, 102, 103 to interact with the server 105 via the network 104 to receive or send messages or the like. The

terminal devices

101, 102, 103 may have installed thereon various communication client applications, such as a shopping-like application, a web browser application, a search-like application, an instant messaging tool, a mailbox client, and/or social platform software, etc. (by way of example only).

The

terminal devices

101, 102, 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like.

The server 105 may be a server providing various services, such as a background management server (for example only) providing support for websites browsed by users using the

terminal devices

101, 102, 103. The background management server may analyze and perform other processing on the received data such as the user request, and feed back a processing result (e.g., a webpage, information, or data obtained or generated according to the user request) to the terminal device.

It should be noted that the project quality prediction method provided by the embodiment of the present disclosure may be generally executed by the server 105. Accordingly, the project quality prediction apparatus provided by the embodiments of the present disclosure may be generally disposed in the server 105. The project quality prediction method provided by the embodiments of the present disclosure may also be performed by a server or server cluster that is different from the server 105 and is capable of communicating with the

terminal devices

101, 102, 103 and/or the server 105. Accordingly, the project quality prediction apparatus provided by the embodiment of the present disclosure may also be disposed in a server or a server cluster different from the server 105 and capable of communicating with the

terminal devices

101, 102, 103 and/or the server 105. Alternatively, the item quality prediction method provided by the embodiment of the present disclosure may also be executed by the

terminal device

101, 102, or 103, or may also be executed by another terminal device different from the

terminal device

101, 102, or 103. Accordingly, the project quality prediction apparatus provided by the embodiment of the present disclosure may also be disposed in the

terminal device

101, 102, or 103, or in another terminal device different from the

terminal device

101, 102, or 103.

For example, the metric parameter information may be originally stored in any one of the

terminal apparatuses

101, 102, or 103 (for example, but not limited to, the terminal apparatus 101), or may be stored on an external storage apparatus and may be imported into the terminal apparatus 101. Then, the terminal device 101 may locally execute the project quality prediction method provided by the embodiment of the present disclosure, or transmit the index parameter information to another terminal device, server, or server cluster, and execute the project quality prediction method provided by the embodiment of the present disclosure by another terminal device, server, or server cluster that receives the index parameter information.

It should be understood that the number of terminal devices, networks, and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for an implementation.

It should be noted that the quality prediction method, apparatus, computer system, and storage medium of the present disclosure may be used in the technical fields of big data and artificial intelligence, and may also be used in any fields other than the technical fields of big data and artificial intelligence.

Fig. 2 schematically shows a flow diagram of a project quality prediction method according to an embodiment of the present disclosure.

As shown in fig. 2, the method includes operations S201 to S202.

In operation S201, index parameter information corresponding to software and hardware indexes affecting the quality of the target project is obtained.

According to embodiments of the present disclosure, a target project may characterize a code package written for various types of projects to be developed. The target item quality may characterize at least one of a number of errors, a number of warnings, success or failure conditions, etc. generated when running the code package of the target item. The software and hardware indicators may include at least one of: indexes related to code testing, indexes related to software and hardware performance of a code running environment, indexes related to effectiveness of project requirements and the like.

According to the embodiment of the disclosure, a script program for acquiring index parameter information of corresponding software and hardware indexes can be set aiming at the development and test processes of a target project. Then, by running the script program in the development and test process of the execution project, the index parameter information of the software and hardware indexes can be obtained.

In operation S202, the index parameter information is input into a trained reflection propagation neuron network model to obtain a prediction result characterizing a quality level of the target item, wherein the reflection propagation neuron network model includes a first number of input layer neuron nodes, a second number of hidden layer neuron nodes, and a third number of output layer neuron nodes, the second number is determined according to at least one of a root value characterizing a value of the sum of the first number and the third number after being signed, and a product characterizing a product of the sum of the first number and the third number and a predefined coefficient.

According to the embodiment of the disclosure, a Back Propagation (BP) neural network can be selected as an algorithm of a model for predicting the quality of a project, the algorithm can be trained based on sample index parameter information corresponding to corresponding software and hardware indexes to obtain a trained reflection Propagation neural network model, the quality characterization result of the project can be predicted, and the quality level of the target project can be determined according to the quality characterization result. The quality characterization result can be expressed by the number of the production defects, and the number of the production defects possibly caused by the corresponding items is characterized. The quality characterization result can also be expressed by the difference of quality conditions, for example, 0 or 1,0 can characterize that the instruction condition reaches the standard, 1 can characterize that the instruction condition does not reach the standard, and the like.

According to an embodiment of the present disclosure, the trained reflection propagation neural network model may include a model trained according to index parameter information of software and hardware indexes of a plurality of other items and corresponding actual result information, or may include a model trained according to index parameter information of software and hardware indexes of a history version item corresponding to a target item and corresponding actual result information. It should be noted that the types of the software and hardware indexes used for training each item of the reflection propagation data source network model are the same.

According to the embodiment of the disclosure, the reflection propagation data source network model can be composed of an input layer, a hidden layer and an output layer, and the hidden layer can have one or more layers. In this embodiment, the hidden layer is, for example, one layer, and the reflection propagation data source network model obtained according to this may be a three-layer BP network model. The number of input layer neurons in the reflection propagation data source network model may be determined according to the number of index categories of the software and hardware index, that is, the first number may be equal to the number of index categories of the software and hardware index. The number of output layer neurons in the reflection propagation data source network model can be determined according to the category number of the prediction result. For example, in this embodiment, the prediction result may represent quality characterizing information of the target item, and in the case that the quality characterizing information may be determined by a value (e.g., 0 or 1 or a specific quality assessment value), the information may be determined by a value, and the third number may take a value of 1. In a case that the quality characterization information needs to be determined by N (N is an integer greater than 1) quality indicators of the categories, the second number may be set to N. The third number may be determined based on the first number and the second number in combination with the root-opening value and the product. The predefined coefficient may take a value of 2/3, and may not be limited thereto.

Through the embodiments of the present disclosure, since the project quality can be predicted according to the reflection propagation neural network model, the technical problem of inaccurate artificial prediction results is at least partially overcome. In addition, by customizing the calculation rule, a reflection propagation neuron network model comprising the most optimal number of hidden layer neuron nodes can be obtained, the training precision can be improved on the basis of reducing the training times, and the project quality can be more accurately predicted.

The method shown in fig. 2 is further described below with reference to specific embodiments.

According to an embodiment of the present disclosure, the software and hardware index may include at least one of: the method comprises the following steps of requirement conversion rate, test case passing rate, test case effective rate, code coverage rate, defect number, defect closing rate, defect reopening rate and performance index.

According to embodiments of the present disclosure, the demand conversion rate may characterize a ratio of the number of effective demands in the project to the total number of demands in the project. The test case passing rate can represent the ratio of the passing number of the test cases to the total number of the test cases. The effective rate of the test cases can represent the ratio of the invalid number of the test cases to the total number of the test cases. Code coverage may characterize the ratio of code covered by a unit test to the total number of code lines. The number of defects may include at least one of the number of code scanning defects, the number of high-risk defects, the number of medium-low risk defects, and the like. The number of code scanning defects may characterize the number of problems scanned by the code scanning tool. The high risk defect number may represent the number of defects generating at least one of a fatal error, a more fatal error, and the like, which may include at least one of a dead cycle, a data communication error, a functional error, a dead halt, a program interface error, and the like, for example, and may not be limited thereto. The number of the low-risk defects may represent the number of defects generating at least one of a general error, a minor error, and the like, where the type of errors may include at least one of a format error, an operation interface error, an input/output non-specification, and the like, for example, and may not be limited thereto. The defect turn-off rate may include at least one of a high risk defect turn-off rate and a medium low risk defect turn-off rate. The high-risk defect closing rate can represent the ratio of the number of closed high-risk defects to the number of high-risk defects. The closing rate of the medium-low risk defects can represent the ratio of the closing number of the medium-low risk defects to the number of the medium-low risk defects. The defect reopen ratio (i.e., defect reopening rate) can characterize the ratio of the number of reopening after the defect has returned without passing to the total number of defects. The performance indicator may represent a ratio of a difference between the performance indicator and an actual indicator to the performance indicator.

According to the embodiment of the disclosure, the script program for acquiring the index parameter information of the corresponding software and hardware index may first acquire information of relevant variables of each index parameter, for example, relevant variables of the demand conversion rate may include an effective demand quantity and a total demand quantity. Then, the script program can provide a corresponding calculation mode to calculate and obtain index parameter information of corresponding software and hardware indexes.

Through the embodiment of the disclosure, the quality parameters for predicting the project quality can be defined in more detail, and the purpose of project quality prediction can be more accurately realized by using the parameters.

Regarding the reflection propagation neuron network model, the number of hidden layer neuron nodes is an important basis of the BP neuron network, and the accuracy of estimation prediction is directly determined. The number of nodes is too small, the network cannot learn well, the training times need to be increased, and the training precision is also influenced. Too many nodes, increased training time, and easy overfitting of the network.

According to an embodiment of the present disclosure, with respect to the second number of hidden layer neuron nodes in the reflection propagation neuron network model, in case the second number is determined according to the open root value, the second number may be equal to the rounded-up value of the open root.

For example, where the first number of input layer neuron nodes in the reflection propagation neuron network model is m, the second number of hidden layer neuron nodes is L, and the third number of output layer neuron nodes is n, equation (1) may be determined:

in accordance with an embodiment of the present disclosure, with respect to the second number of hidden layer neuron nodes in the reflection propagation neuron network model, where the second number is determined from the product, the second number may be equal to a rounded down value of the product.

For example, based on the foregoing embodimentsEquation (2) can be determined:

according to an embodiment of the present disclosure, regarding the second number of hidden layer neuron nodes in the reflection propagation neuron network model, in case that the second number is determined according to the open root value and the product, the second number may be equal to a value of any one integer between the open root and the product.

For example, based on the foregoing embodiment, equation (3) may be determined:

by the embodiment of the disclosure, the number of the optimal hidden layer neuron nodes in the reflection propagation neuron network model can be calculated by adopting an own algorithm, so that the training precision can be improved with less training time and training times, and the accuracy of the estimation prediction result can be improved.

Fig. 3 schematically illustrates a network structure diagram of a reflection propagation neuron network model according to an embodiment of the present disclosure.

As shown in fig. 3, the reflection propagation neuron network model 300 may be a three-layer BP network structure, including 11 input layer neuron nodes 310 and 1 output layer neuron node 330. The 11 input layer neuron nodes can be used for inputting the required conversion rate, the pass rate of the test case, the effective rate of the test case, the code coverage rate, the number of code scanning defects, the number of high-risk defects, the closing rate of high-risk defects, the number of middle-low-risk defects, the closing rate of middle-low-risk defects, the proportion of defect reopen and performance indexes. 1 output layer neuron node can be used to output the prediction result of the quality situation. According to the foregoing formula (3) for calculating hidden layer neuron nodes, it can be determined that the number of hidden layer neuron nodes can be 4, 5, 6, 7 or 8. For example, 6 hidden layer neuron nodes 320 may be included in FIG. 3.

According toIn the embodiment of the present disclosure, the hidden excitation function of the reflection propagation neuron network model 300 shown in fig. 3 may be an s-type tangent function tansig shown in equation (4). Wherein x is ₁ The output value of each input layer neuron node can be represented.

According to the embodiment of the present disclosure, the logsig function shown in equation (5) may be selected as the output layer excitation function of the reflection propagation neuron network model 300 shown in fig. 3. Wherein x is ₂ The output value of each hidden layer neuron node can be represented.

According to an embodiment of the present disclosure, the above-mentioned reflection propagation neuron network model may be obtained by training, for example, the following method: and acquiring historical parameter information related to the software and hardware indexes and a quality level detection result corresponding to the historical parameter information. And inputting the historical parameter information into a reflection propagation neuron network model to be trained to obtain a quality level prediction result corresponding to the historical parameter information, wherein the reflection propagation neuron network model to be trained has the same network structure as the trained reflection propagation neuron network model. And according to the quality level detection result and the quality level prediction result, adjusting the weight between the neuron nodes with the connection relation in the to-be-trained reflection propagation neuron network model to obtain the trained reflection propagation neuron network model.

For example, table 1 may be a portion of the data collected for training a reflection propagation neural network model for predicting quality conditions.

TABLE 1

With reference to the data shown in table 1, data information corresponding to the demand conversion rate, test case passing rate, test case effective rate, code coverage rate, code scanning defect number, high risk defect closing rate, medium and low risk defect number, medium and low risk defect closing rate, defect reopen ratio, performance index, and the like of the 1 st to 14 th historical items can be used as the historical parameter information. Data information corresponding to the quality conditions of the 1 st to 14 th history items may be used as the quality level detection result corresponding to the history parameter information of each column. By inputting the historical parameter information corresponding to each of the 1 st to 14 th historical items into the constructed model of the to-be-trained reflex propagation neuron network including the first number of input layer neuron nodes, the second number of hidden layer neuron nodes and the third number of output layer neuron nodes, a quality level prediction result (0 or 1) corresponding to the historical parameter data can be obtained. According to the quality level prediction result and the corresponding quality level detection result, the to-be-trained reflex propagation neuron network model can be trained, and a trained reflex propagation neuron network model which can be used for predicting the quality condition of the project to be 0 (good quality) or 1 (poor quality) is obtained. Based on the trained reflection propagation neuron network model, the quality condition of the 15 th item and other target items can be predicted.

According to the embodiment of the disclosure, the quality condition items as in table 1 can also be replaced by the number of production defects, and can be used for recording the number of production defects generated by each of the 1 st to 14 th history items. Based on the training, the reflection propagation neural network model to be trained is trained, and the trained reflection propagation neural network model which can be used for predicting the number of the production defects of the project can be obtained. Based on the trained reflection propagation neuron network model, the number of production defects of the 15 th project and other target projects can be predicted.

During the training process, the network training function may adopt a traindx (an adaptive gradient training method), the network performance function may adopt an MSC (an editor internal function), the number of network iterations may be at least 10000, and the expected error may be 0.00001.

It should be noted that, the data in columns 1-15 shown in table 1 above are only exemplary embodiments, and in the actual training process, historical parameter information of more items can be collected to implement model training. The values of the above parameters in the training process may not be limited thereto.

According to the embodiment of the disclosure, the input parameters are designed in advance, the historical project data is collected, training and calculation are performed by combining a machine learning algorithm, a reflection propagation neural network model capable of obtaining a more credible prediction result is realized, and the problem of inaccurate artificial prediction can be effectively solved.

According to the embodiment of the disclosure, after the prediction result representing the quality level of the target item is obtained based on the reflection propagation neuron network model prediction, the early warning information may be generated in response to detecting that the prediction result is greater than or equal to the preset threshold.

According to the embodiment of the disclosure, for example, when the quality condition of the 15 th item in table 1 is predicted to be 1, it may be determined that the quality of the 15 th item does not meet the online standard, the warning information may be generated, the result may be recorded on the platform, and the member of the item group is notified in an email manner.

Through the embodiment of the disclosure, a project quality prediction alarm mechanism based on a BP neural network is provided, and through the processes of historical quality data acquisition, model training and the like, the quality condition of a target project can be predicted and whether to alarm the current quality condition of the project or not can be determined. In this way, the result deviation due to manual prediction can be reduced. In addition, by reserving the project quality in advance, the project quality can be improved by means of measures in the project implementation process.

Fig. 4 schematically shows a block diagram of an item quality prediction apparatus according to an embodiment of the present disclosure.

As shown in fig. 4, the item quality prediction apparatus 400 includes a first obtaining module 410 and a first obtaining module 420.

The first obtaining module 410 is configured to obtain index parameter information corresponding to software and hardware indexes that affect the quality of the target project.

A first obtaining module 420, configured to input index parameter information into a trained reflection propagation neuron network model to obtain a prediction result representing a quality level of the target item, where the reflection propagation neuron network model includes a first number of input layer neuron nodes, a second number of hidden layer neuron nodes, and a third number of output layer neuron nodes, the second number is determined according to at least one of a root value and a product, the root value represents a value obtained by performing an opening sign on a sum of the first number and the third number, and the product represents a product of the sum of the first number and the third number and a predefined coefficient.

According to an embodiment of the present disclosure, in case the second number is determined according to the open root value, the second number is equal to the rounded up value of the open root.

According to an embodiment of the present disclosure, in case the second number is determined from the product, the second number is equal to a rounded down value of the product.

According to an embodiment of the present disclosure, in the case where the second number is determined according to the root value and the product, the second number is equal to a value of any one integer between the root value and the product.

According to an embodiment of the present disclosure, the software and hardware index includes at least one of: the method comprises the following steps of requirement conversion rate, test case passing rate, test case effective rate, code coverage rate, defect number, defect closing rate, defect reopening rate and performance index.

According to the embodiment of the disclosure, the reflection propagation neuron network model is obtained by training through the following modules: the device comprises a second acquisition module, a second acquisition module and an adjustment module.

And the second acquisition module is used for acquiring historical parameter information related to the software and hardware indexes and a quality level detection result corresponding to the historical parameter information.

And the second obtaining module is used for inputting the historical parameter information into the to-be-trained reflection propagation neuron network model to obtain a quality level prediction result corresponding to the historical parameter information, wherein the to-be-trained reflection propagation neuron network model and the trained reflection propagation neuron network model have the same network structure.

And the adjusting module is used for adjusting the weight between the neuron nodes with the connection relation in the to-be-trained reflection propagation neuron network model according to the quality level detection result and the quality level prediction result to obtain the trained reflection propagation neuron network model.

According to an embodiment of the present disclosure, the item quality prediction apparatus further includes a generation module.

And the generating module is used for generating early warning information in response to the fact that the prediction result is larger than or equal to a preset threshold value.

Any of the modules according to embodiments of the present disclosure, or at least part of the functionality of any of them, may be implemented in one module. Any one or more of the modules according to the embodiments of the present disclosure may be implemented by being split into a plurality of modules. Any one or more of the modules according to embodiments of the present disclosure may be implemented at least in part as a hardware circuit, such as a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a system on a chip, a system on a substrate, a system on a package, an Application Specific Integrated Circuit (ASIC), or in any other reasonable manner of hardware or firmware by which a circuit is integrated or packaged, or in any one of three implementations, or in any suitable combination of any of the several. Alternatively, one or more of the modules according to embodiments of the disclosure may be implemented at least partly as computer program modules which, when executed, may perform corresponding functions.

For example, any number of the first obtaining module 410 and the first obtaining module 420 may be combined and implemented in one module, or any one of the modules may be split into a plurality of modules. Alternatively, at least part of the functionality of one or more of these modules may be combined with at least part of the functionality of the other modules and implemented in one module. According to an embodiment of the present disclosure, at least one of the first obtaining module 410 and the first obtaining module 420 may be implemented at least partially as a hardware circuit, such as a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a system on a chip, a system on a substrate, a system on a package, an Application Specific Integrated Circuit (ASIC), or may be implemented in hardware or firmware by any other reasonable manner of integrating or packaging a circuit, or may be implemented in any one of three implementations of software, hardware, and firmware, or in a suitable combination of any of them. Alternatively, at least one of the first obtaining module 410 and the first obtaining module 420 may be at least partially implemented as a computer program module, which when executed may perform the respective functions.

It should be noted that the item quality prediction apparatus portion in the embodiment of the present disclosure corresponds to the item quality prediction method portion in the embodiment of the present disclosure, and the description of the item quality prediction apparatus portion specifically refers to the item quality prediction method portion, which is not described herein again.

Fig. 5 schematically illustrates a block diagram of a computer system suitable for implementing the above-described method according to an embodiment of the present disclosure. The computer system illustrated in FIG. 5 is only one example and should not impose any limitations on the scope of use or functionality of embodiments of the disclosure.

As shown in fig. 5, a computer system 500 according to an embodiment of the present disclosure includes a processor 501 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 502 or a program loaded from a storage section 508 into a Random Access Memory (RAM) 503. The processor 501 may comprise, for example, a general purpose microprocessor (e.g., a CPU), an instruction set processor and/or associated chipset, and/or a special purpose microprocessor (e.g., an Application Specific Integrated Circuit (ASIC)), among others. The processor 501 may also include onboard memory for caching purposes. Processor 501 may include a single processing unit or multiple processing units for performing different actions of a method flow according to embodiments of the disclosure.

In the RAM 503, various programs and data necessary for the operation of the system 500 are stored. The processor 501, the ROM502, and the RAM 503 are connected to each other through a bus 504. The processor 501 performs various operations of the method flows according to the embodiments of the present disclosure by executing programs in the ROM502 and/or the RAM 503. Note that the programs may also be stored in one or more memories other than the ROM502 and the RAM 503. The processor 501 may also perform various operations of method flows according to embodiments of the present disclosure by executing programs stored in the one or more memories.

According to an embodiment of the present disclosure, system 500 may also include an input/output (I/O) interface 505, input/output (I/O) interface 505 also being connected to bus 504. The system 500 may also include one or more of the following components connected to the I/O interface 505: an input portion 506 including a keyboard, a mouse, and the like; an output portion 507 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage portion 508 including a hard disk and the like; and a communication section 509 including a network interface card such as a LAN card, a modem, or the like. The communication section 509 performs communication processing via a network such as the internet. A drive 510 is also connected to the I/O interface 505 as needed. A removable medium 511 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 510 as necessary, so that a computer program read out therefrom is mounted on the storage section 508 as necessary.

According to an embodiment of the present disclosure, the method flow according to an embodiment of the present disclosure may be implemented as a computer software program. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable storage medium, the computer program containing program code for performing the method illustrated by the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 509, and/or installed from the removable medium 511. The computer program, when executed by the processor 501, performs the above-described functions defined in the system of the embodiments of the present disclosure. The systems, devices, apparatuses, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the present disclosure.

The present disclosure also provides a computer-readable storage medium, which may be contained in the apparatus/device/system described in the above embodiments; or may exist separately and not be assembled into the device/apparatus/system. The computer-readable storage medium carries one or more programs which, when executed, implement the method according to an embodiment of the disclosure.

According to an embodiment of the present disclosure, the computer readable storage medium may be a non-volatile computer readable storage medium. Examples may include, but are not limited to: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.

For example, according to embodiments of the present disclosure, a computer-readable storage medium may include ROM502 and/or RAM 503 and/or one or more memories other than ROM502 and RAM 503 described above.

Embodiments of the present disclosure also include a computer program product comprising a computer program containing program code for performing the method provided by the embodiments of the present disclosure, when the computer program product is run on an electronic device, the program code being adapted to cause the electronic device to carry out the method of item quality prediction provided by the embodiments of the present disclosure.

The computer program, when executed by the processor 501, performs the above-described functions defined in the system/apparatus of the embodiments of the present disclosure. The above described systems, devices, modules, units, etc. may be implemented by computer program modules according to embodiments of the present disclosure.

In one embodiment, the computer program may be hosted on a tangible storage medium such as an optical storage device, a magnetic storage device, or the like. In another embodiment, the computer program may also be transmitted, distributed in the form of a signal on a network medium, downloaded and installed through the communication section 509, and/or installed from the removable medium 511. The computer program containing program code may be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.

In accordance with embodiments of the present disclosure, program code for executing computer programs provided by embodiments of the present disclosure may be written in any combination of one or more programming languages, and in particular, these computer programs may be implemented using high level procedural and/or object oriented programming languages, and/or assembly/machine languages. The programming language includes, but is not limited to, programming languages such as Java, C + +, python, the "C" language, or the like. The program code may execute entirely on the user's computing device, partly on the user's device, partly on a remote computing device, or entirely on the remote computing device or server. In situations involving remote computing devices, the remote computing devices may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to external computing devices (e.g., through the internet using an internet service provider).

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions. It will be appreciated by those skilled in the art that various combinations and/or combinations of the features recited in the various embodiments of the disclosure and/or the claims may be made even if such combinations or combinations are not explicitly recited in the disclosure. In particular, various combinations and/or combinations of the features recited in the various embodiments and/or claims of the present disclosure may be made without departing from the spirit or teaching of the present disclosure. All such combinations and/or associations are within the scope of the present disclosure.

The embodiments of the present disclosure have been described above. However, these examples are for illustrative purposes only and are not intended to limit the scope of the present disclosure. Although the embodiments are described separately above, this does not mean that the measures in the embodiments cannot be used in advantageous combination. The scope of the disclosure is defined by the appended claims and equivalents thereof. Various alternatives and modifications can be devised by those skilled in the art without departing from the scope of the present disclosure, and such alternatives and modifications are intended to be within the scope of the present disclosure.

Claims

1. A method of project quality prediction, comprising:

acquiring index parameter information corresponding to software and hardware indexes influencing the quality of a target project; and

inputting the index parameter information into a trained reflection propagation neuron network model to obtain a prediction result representing a quality level of the target item, wherein the reflection propagation neuron network model comprises a first number of input layer neuron nodes, a second number of hidden layer neuron nodes and a third number of output layer neuron nodes, the second number is determined according to at least one of a root value and a product, the root value represents a value after a sum of the first number and the third number is subjected to an opening sign, and the product represents a product of the sum of the first number and the third number and a predefined coefficient.

2. A method according to claim 1, wherein the second number is equal to the rounded up value of the root-opened plant if the second number is determined from the root-opened value.

3. The method of claim 1, wherein the second number is equal to a rounded-down value of the product if the second number is determined from the product.

4. A method according to claim 1, wherein, in the case where the second number is determined from the root-opening value and the product, the second number is equal to the value of any integer between the root-opening value and the product.

5. The method of claim 1, wherein the software and hardware indicators comprise at least one of: the method comprises the following steps of requirement conversion rate, test case passing rate, test case effective rate, code coverage rate, defect number, defect closing rate, defect reopening rate and performance index.

6. The method of claim 1, wherein the reflection propagation neuron network model is trained by:

acquiring historical parameter information related to the software and hardware indexes and a quality level detection result corresponding to the historical parameter information;

inputting the historical parameter information into a reflection propagation neuron network model to be trained to obtain a quality level prediction result corresponding to the historical parameter information, wherein the reflection propagation neuron network model to be trained has the same network structure as the trained reflection propagation neuron network model; and

and according to the quality level detection result and the quality level prediction result, adjusting the weight between neuron nodes with connection relation in the to-be-trained reflection propagation neuron network model to obtain the trained reflection propagation neuron network model.

7. The method of claim 1, further comprising:

and generating early warning information in response to the fact that the prediction result is larger than or equal to a preset threshold value.

8. An item quality prediction apparatus comprising:

the first acquisition module is used for acquiring index parameter information corresponding to software and hardware indexes influencing the quality of a target project; and

a first obtaining module, configured to input the indicator parameter information into a trained reflection propagation neuron network model to obtain a prediction result representing a quality level of the target item, wherein the reflection propagation neuron network model includes a first number of input layer neuron nodes, a second number of hidden layer neuron nodes, and a third number of output layer neuron nodes, the second number is determined according to at least one of a root value and a product, the root value represents a value after a sum of the first number and the third number is subjected to a root sign, and the product represents a product of the sum of the first number and the third number and a predefined coefficient.

9. A computer system, comprising:

one or more processors;

a memory for storing one or more programs,

wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of any of claims 1-7.

10. A computer readable storage medium having stored thereon executable instructions which, when executed by a processor, cause the processor to carry out the method of any one of claims 1 to 7.

11. A computer program product comprising computer executable instructions for implementing the method of any one of claims 1 to 7 when executed.