Method and device for predicting information and credential adaptation migration and electronic equipment

Abstract

The invention provides a method and device for predicting information-credential adaptive migration and electronic equipment, and the method comprises the steps: collecting the research data of an information-credential adaptive migration project, and sorting the research data into a plurality of pieces of sample data; abnormal sample data in the multiple pieces of sample data are cleaned, and cleaned data are obtained; performing feature simplification on the cleaned data through a statistical method of variable dimension reduction and data reduction to obtain simplified features; inputting the simplified features into a credential intelligent evaluation model, predicting the adaptive migration difficulty of the credential adaptive migration project and the number of resources required by adaptive migration, and obtaining a prediction result; the credential intelligent evaluation model is a model pre-constructed based on a machine learning algorithm.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method, device and electronic device for predicting information technology adaptation migration. Background Art

[0002] Trusted innovation migration refers to the process of migrating original applications from overseas systems to trusted innovation systems, mainly to achieve domestic substitution in core chips, basic hardware, operating systems, middleware, databases, cloud platforms and other fields. Usually, applications migrate from non-trusted innovation environments to trusted innovation environments, and corresponding modifications are required to adapt to the trusted innovation environment. Combined with the analysis of the current work, in the process of trusted innovation adaptation, it was found that there were two major problems: insufficient migration risk assessment and disordered resource allocation and control. Summary of the invention

[0003] The present application embodiment provides a method, device and electronic device for predicting ICT adaptation migration, and the related technical solutions are as follows:

[0004] In a first aspect, an embodiment of the present application provides a method for predicting ICT adaptation migration, including:

[0005] Collect survey data of the Xinchuang adaptation and migration project, and organize the survey data into multiple sample data;

[0006] Cleaning abnormal sample data among the plurality of sample data to obtain cleaned data;

[0007] By using statistical methods of variable dimension reduction and data reduction, the cleaned data is subjected to feature simplification to obtain simplified features;

[0008] The simplified features are input into the trusted intelligent evaluation model to predict the difficulty of adaptation and migration of the trusted intelligent adaptation and migration project and the number of resources required for adaptation and migration to obtain prediction results; the trusted intelligent evaluation model is a model pre-built based on a machine learning algorithm.

[0009] In one possible implementation, the statistical method of variable dimension reduction and data reduction is used to simplify the features of the cleaned data to obtain simplified features, including:

[0010] By using a variable dimension reduction method, variable features that are not relevant to the Xinchuang intelligent assessment model are excluded from the cleaned data to obtain excluded features;

[0011] By using a data reduction method, similar features among the excluded features are merged to obtain common features;

[0012] The common features and other features among the excluded features except the common features are used as simplified features.

[0013] In one possible implementation, after inputting the simplified features into the ICT intelligent evaluation model, predicting the difficulty of adaptation and migration of the ICT adaptation and migration project and the number of resources required for adaptation and migration, and obtaining the prediction result, the method further includes:

[0014] determining constraint characteristics that constrain the prediction results;

[0015] Calculate and obtain the Shapley value of the constraint feature;

[0016] The influence of the constraint feature on the prediction result is quantified by the Shapley value. The larger the positive value of the Shapley value is, the greater the contribution of the constraint feature to the accuracy of the prediction result is.

[0017] The influence degree of the constraint feature on the prediction result is displayed.

[0018] In one possible implementation, the simplified features are input into the ICT intelligent evaluation model to predict the difficulty of adaptation and migration of the ICT adaptation and migration project and the number of resources required for adaptation and migration, and obtain prediction results, including:

[0019] Through redundant construction, multiple models including the credible innovation intelligent evaluation model are constructed;

[0020] Building a model decision alliance through the multiple models;

[0021] Import the streamlined features into the multiple models at the same time, and obtain the output results of the adaptation and migration difficulty and the number of resources required for the adaptation and migration of each model for the trusted innovation adaptation and migration project;

[0022] Make coordinated decisions on the output results of each model and take the consistent results as the optimal results for the prediction results.

[0023] In a second aspect, an embodiment of the present application provides a device for predicting ICT adaptation migration, including:

[0024] A collection unit, used to collect survey data of the ICT adaptation and migration project, and organize the survey data into multiple sample data;

[0025] A cleaning unit, used for cleaning abnormal sample data among the plurality of sample data to obtain cleaned data;

[0026] A simplified element is used to simplify the features of the cleaned data by using statistical methods of variable dimension reduction and data reduction to obtain simplified features;

[0027] A prediction unit is used to input the simplified features into the trusted intelligent evaluation model, predict the difficulty of adaptation and migration of the trusted intelligent adaptation and migration project and the number of resources required for adaptation and migration, and obtain a prediction result; the trusted intelligent evaluation model is a model pre-built based on a machine learning algorithm.

[0028] In one possible implementation, the simplified element is specifically used for:

[0029] By using a variable dimension reduction method, variable features that are not relevant to the Xinchuang intelligent assessment model are excluded from the cleaned data to obtain excluded features;

[0030] By using a data reduction method, similar features among the excluded features are merged to obtain common features;

[0031] The common features and other features among the excluded features except the common features are used as simplified features.

[0032] In one possible implementation, the prediction unit inputs the simplified features into the ICT intelligent evaluation model, predicts the difficulty of adaptation and migration of the ICT adaptation and migration project and the number of resources required for adaptation and migration, and after obtaining the prediction result, the device further includes a quantification unit, which is used to:

[0033] determining constraint characteristics that constrain the prediction results;

[0034] Calculate and obtain the Shapley value of the constraint feature;

[0035] The influence of the constraint feature on the prediction result is quantified by the Shapley value. The larger the positive value of the Shapley value is, the greater the contribution of the constraint feature to the accuracy of the prediction result is.

[0036] The influence degree of the constraint feature on the prediction result is displayed.

[0037] In one possible implementation manner, the prediction unit is specifically used to:

[0038] Through redundant construction, multiple models including the credible innovation intelligent evaluation model are constructed;

[0039] Building a model decision alliance through the multiple models;

[0040] Import the streamlined features into the multiple models at the same time, and obtain the output results of the adaptation and migration difficulty and the number of resources required for the adaptation and migration of each model for the trusted innovation adaptation and migration project;

[0041] Make coordinated decisions on the output results of each model and take the consistent results as the optimal results for the prediction results.

[0042] In a third aspect, an embodiment of the present application provides an electronic device, including:

[0043] Memory, used to store computer programs;

[0044] The processor is used to implement any of the method steps described above when executing the computer program stored in the memory.

[0045] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is used to enable a computer to execute the method steps described in any one of the above items.

[0046] In a fifth aspect, an embodiment of the present application provides a computer program product, which includes: a computer program code, and when the computer program code runs on a computer, the computer executes any of the above methods.

[0047] The beneficial effects of the embodiments of the present application are as follows:

[0048] The embodiment of the present application provides a method for predicting the adaptation and migration of credible innovation. First, the survey data of the credible innovation adaptation and migration project is collected, and the survey data is organized into multiple sample data; then, the abnormal sample data in the multiple sample data is cleaned to obtain the cleaned data; then, the statistical methods of variable dimension reduction and data reduction are used to simplify the features of the cleaned data to obtain simplified features; in this way, the number of features that need to be extracted is reduced. Then, the simplified features are input into the credible innovation intelligent evaluation model, and the adaptation and migration difficulty of the credible innovation adaptation and migration project and the number of resources required for the adaptation and migration are predicted to obtain the prediction results; wherein, the credible innovation intelligent evaluation model is a model pre-built based on a machine learning algorithm. In other words, the credible innovation intelligent evaluation model pre-built based on a machine learning algorithm is applied to the credible innovation industry, which realizes the prediction of the credible innovation adaptation and migration difficulty and the number of resources required for the adaptation and migration, and thus realizes the effective evaluation of the adaptation risk. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 A flow chart of a method for predicting credential innovation adaptation migration provided in an embodiment of the present application;

[0050] Figure 2 for Figure 1 The method flow chart of step S103 in FIG.

[0051] Figure 3 For Figure 1The method flow chart after step S104;

[0052] Figure 4 for Figure 1 The method flow chart of step S104;

[0053] Figure 5 A schematic diagram of one of the structures of a device for predicting ICT adaptation migration provided in an embodiment of the present application;

[0054] Figure 6 A schematic diagram of a structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0055] In order to make the purpose, technical scheme and advantages of the present application clearer, the technical scheme in the embodiment of the present application will be clearly and completely described below in conjunction with the drawings in the embodiment of the present application. Obviously, the described embodiment is only a part of the embodiment of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application. In the absence of conflict, the embodiments in the present application and the features in the embodiments can be arbitrarily combined with each other. In addition, although the logical order is shown in the flow chart, in some cases, the steps shown or described can be performed in an order different from that here.

[0056] The terms "first" and "second" in the specification and claims of the present application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the term "comprising" and any of their variations are intended to cover non-exclusive protection. For example, a process, method, system, product or device comprising a series of steps or units is not limited to the listed steps or units, but optionally also includes steps or units that are not listed, or optionally also includes other steps or units inherent to these processes, methods, products or devices. "Multiple" in the present application can mean at least two, for example, two, three or more, and the embodiments of the present application are not limited.

[0057] The following is a description of exemplary embodiments of the present application in conjunction with the accompanying drawings, including various details of the embodiments of the present application to facilitate understanding, which should be considered as merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope of the present application. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted in the following description. It should be noted that in the embodiments of the present application, certain software, components, models and other existing solutions in the industry may be mentioned, which should be considered as exemplary, and their purpose is only to illustrate the feasibility of the implementation of the technical solution of the present application, but it does not mean that the applicant has or will necessarily use the solution.

[0058] In the technical solution of this application, the acquisition, transmission, storage, and use of data are in compliance with the requirements of relevant national laws and regulations.

[0059] Before introducing the method for predicting ICT adaptation migration provided by the embodiment of the present application, in order to facilitate understanding, the technical background of the embodiment of the present application is first introduced in detail.

[0060] In related technologies, the main processing flow of a certain energy company's information innovation migration analysis model is as follows:

[0061] First, the migration project and server data are labeled, the migration projects and servers are classified, and migration project analysis and server evaluation indicators are designed; then, the migration project and server data are collected and training data is constructed; then, the intelligent evaluation model of the information innovation is generated, and the corresponding algorithm is selected according to the characteristics of each indicator, and the model is trained using the data set; finally, the migration evaluation and resource allocation are carried out; according to the project migration situation and migration server indicators, the migration difficulty, server resource allocation, etc. are predicted. However, the information innovation migration analysis model of the energy company uses static indicators combined with the logical judgment of traditional programming methods, and its indicator weights are very arbitrary, resulting in low model accuracy and difficulty in adapting to complex and changing scenarios.

[0062] In view of this, the embodiments of the present application provide a method, device and electronic device for predicting the adaptation migration of ICT, which are used to apply the ICT intelligent assessment model pre-constructed based on the machine learning algorithm to the ICT industry, to achieve the prediction of the difficulty of ICT adaptation migration and the number of resources required for adaptation migration, thereby achieving an effective assessment of adaptation risks.

[0063] like Figure 1 As shown, an embodiment of the present application provides a method for predicting credible innovation adaptation migration, the method comprising:

[0064] S101: Collecting survey data of the ICT adaptation and migration project, and collating the survey data into a plurality of sample data;

[0065] In the specific implementation process, the specific number of multiple sample data can be set according to actual application needs, and is not limited here.

[0066] S102: Cleaning abnormal sample data among the plurality of sample data to obtain cleaned data;

[0067] In a specific implementation process, after obtaining a plurality of sample data, abnormal sample data in the plurality of sample data may be cleaned to obtain cleaned data.

[0068] S103: Simplifying the features of the cleaned data by using statistical methods of variable dimension reduction and data reduction to obtain simplified features;

[0069] In the specific implementation process, variable dimensionality reduction methods can be used to remove variable features that have no effect on the model from the cleaned data; data reduction methods can also be used to find the collinearity between multiple variable features, thereby reducing the number of features that need to be extracted and improving the efficiency of model prediction. In practical applications, data cleaning, as well as statistical methods of variable dimensionality reduction and data reduction, can also be applied to the training of the intelligent evaluation model to be constructed, thereby effectively reducing the interference of invalid data on model training and improving the accuracy of model prediction.

[0070] S104: Input the simplified features into the trusted intelligent evaluation model, predict the difficulty of adaptation and migration of the trusted intelligent adaptation and migration project and the number of resources required for adaptation and migration, and obtain prediction results; the trusted intelligent evaluation model is a model pre-built based on a machine learning algorithm.

[0071] During the specific implementation process, the trusted intelligent assessment model is pre-built based on the machine learning algorithm. In this way, the trusted intelligent assessment model can make full use of the advantages of the machine learning algorithm, making the trusted intelligent assessment model more accurate. It can not only be applicable to projects of various business types, but also can self-iterate and optimize as project data accumulates.

[0072] In the embodiments of the present application, Figure 2 As shown, step S103: using statistical methods of variable dimension reduction and data reduction, the cleaned data is subjected to feature simplification to obtain simplified features, including:

[0073] S201: Excluding variable features that are not relevant to the ICT intelligent assessment model from the cleaned data by using a variable dimension reduction method to obtain excluded features;

[0074] S202: merging similar features among the excluded features by a data reduction method to obtain common features;

[0075] S203: taking the common features and other features of the excluded features except the common features as simplified features.

[0076] In the specific implementation process, the specific implementation process of step S201 to step S203 is as follows:

[0077] First, variable features that are not related to the ICT intelligent assessment model are excluded from the cleaned data through the method of variable dimensionality reduction to obtain the excluded features. For example, when calculating the time consumption of ICT adaptation migration, the migration start date and migration end date are of no substantial help in calculating the migration time consumption. If these data are retained, the workload of the intelligent assessment model will be increased. Therefore, variable features that are not related to the ICT intelligent assessment model can be excluded from the cleaned data through the method of variable dimensionality reduction, thereby reducing the number of features that need to be extracted.

[0078] Moreover, the data reduction method can be used to merge similar features among the excluded features to obtain common features. In other words, the data reduction method can be used to find the collinearity between multiple variable features, thereby reducing the number of features that need to be extracted. Exemplary, the excluded features include ".NET", "Windows Server operating system", "SQL server database", and "IE browser". After merging these features through the data reduction method, the feature "Microsoft products" is obtained. In this way, the workload of the credible intelligent evaluation model is reduced and the efficiency of the use of the credible intelligent evaluation model is improved.

[0079] In the embodiment of the present application, the statistical methods of variable dimension reduction and data reduction are applied to the feature extraction of the credible innovation intelligent evaluation model, thereby scientifically and objectively reducing the number of features. In this way, the workload of the credible innovation intelligent evaluation model is simplified, providing a guarantee for improving the efficiency of the use of the credible innovation intelligent evaluation model.

[0080] In the embodiments of the present application, Figure 3 As shown, in step S104: inputting the simplified features into the ICT intelligent evaluation model, predicting the difficulty of adaptation and migration of the ICT adaptation and migration project and the number of resources required for adaptation and migration, and after obtaining the prediction results, the method further includes:

[0081] S301: Determine the constraint characteristics that constrain the prediction result;

[0082] S302: Calculate and obtain the Shapley value of the constraint feature;

[0083] S303: quantifying the influence of the constraint feature on the prediction result by the Shapley value, wherein the greater the positive value of the Shapley value is, the greater the contribution of the constraint feature to the accuracy of the prediction result is;

[0084] S304: Displaying the influence of the constraint feature on the prediction result.

[0085] In the specific implementation process, the specific implementation process of step S301 to step S304 is as follows:

[0086] After obtaining the difficulty of adaptation and migration of the xinchuang adaptation and migration project and the number of resources required for adaptation and migration through the xinchuang intelligent evaluation model, the constraint features that restrict the prediction results can also be determined; then, the shapley value of the constraint feature is calculated. That is to say, the embodiment of the present application can use the SHAP method to quantitatively analyze the constraint features that restrict the prediction results of the xinchuang intelligent estimation model, and can calculate a shapley value for each constraint feature that restricts the prediction result. Then, the shapley value is used to quantify the degree of influence of the constraint features on the prediction results. The greater the positive shapley value, the greater the contribution of the constraint features to the accuracy of the prediction results. In practical applications, the size and positive and negative shapley values ​​can be used to quantify the degree of influence of the constraint features on the prediction results of the xinchuang intelligent evaluation model, which can make the prediction results of the xinchuang intelligent evaluation model more convincing. Among them, the greater the positive shapley value, the greater the contribution to the accuracy of the prediction results, and vice versa. Then, the degree of influence of the constraint features on the prediction results is displayed to prompt the user to the specific content of the key features that affect the current xinchuang migration.

[0087] It should be noted that SHAP is a method for post-explanation of machine learning models. It can achieve the effect of model interpretability by calculating the Shapley value of each constraint feature in the credible intelligent evaluation model, reflecting the positive and negative impact of the corresponding constraint feature on the model prediction results. Exemplarily, for the credible intelligent evaluation model, the baseline used is 0.1, the development language used is domino, the operating system used is Windows Server, and the database used is MySQL. The prediction result obtained is that the application system needs to be reconstructed; after being explained by the SHAP method, the shapley value corresponding to the development language is +10, the shapley value corresponding to the operating system is +3, and the shapley value corresponding to the database is -3; in this way, according to the shapley value corresponding to the current feature, it can be seen that the development language has the greatest impact on the prediction result that the application system needs to be reconstructed. In practical applications, the SHAP method can be used to quantitatively explain the prediction results of the credible intelligent evaluation model, so that the black box machine learning model (i.e., the credible intelligent evaluation model) has interpretability and makes the prediction results of the model more convincing.

[0088] It should be noted that before predicting the difficulty of adaptation and migration of the ICT adaptation and migration project and the number of resources required for adaptation and migration through the ICT intelligent evaluation model, the method also includes constructing the ICT intelligent evaluation model through a machine learning algorithm. The specific construction process of the ICT intelligent evaluation model is as follows:

[0089] S1: Organize training data; specifically, first, collect survey data of the trusted computing adaptation and migration project, organize the survey data into different sample data, and clean the abnormal sample data; then, through the statistical methods of variable dimension reduction and data reduction, exclude variable features that have no effect on the model, and find the multicollinearity between the remaining multiple variable features, reduce the number of features that need to be extracted, thereby reducing the workload of model training and improving the training efficiency of the model.

[0090] S2: Train the ICT intelligent assessment model to be constructed; specifically, select the machine learning algorithm suitable for the model, use different training data for training, and generate a trained ICT intelligent assessment model.

[0091] In one of the exemplary embodiments, the optimal algorithm suitable for the credible innovation intelligent evaluation model can be selected through steps S21 and S22 in sequence, thereby constructing the required credible innovation intelligent evaluation model.

[0092] S21: Use the algorithm selection method of SciKit-learn to preliminarily screen out multiple machine learning algorithms that meet the requirements. It should be noted that SciKit-learn is a software machine learning library for the Python programming language; it has various classification algorithms, regression algorithms, and clustering algorithms, such as support vector machines, random forests, gradient boosting, k-means, and DBSCAN, etc. Moreover, it is designed to be used in conjunction with the Python numerical science libraries NumPy and SciPy.

[0093] S22: For different initial screening algorithms, use the same training set for training to generate multiple reference models, and then conduct comprehensive consideration and in-depth analysis through the model's test results, algorithm average performance value, recall rate and other indicators to determine the optimal learning algorithm. Exemplarily, the test results, algorithm average performance value, recall rate and other indicators can be weighted and summed. The larger the value obtained, the better the algorithm. In this way, the method of deep analysis algorithm screening used in the embodiment of the present application can perform deep algorithm screening in steps and multiple dimensions to select the optimal algorithm suitable for the credible intelligent evaluation model, thereby ensuring the accuracy of the constructed credible intelligent evaluation model. Traditional algorithm screening selects algorithms based on sample conditions and model application scenarios, and its selection form relies too much on expert experience, resulting in a lack of scientific algorithm screening. The method of deep analysis algorithm screening used in the embodiment of the present application is more scientific and more accurate in constructing a credible intelligent evaluation model.

[0094] In the embodiments of the present application, Figure 4 As shown, step S104: input the simplified features into the ICT intelligent evaluation model, predict the difficulty of adaptation and migration of the ICT adaptation and migration project and the number of resources required for adaptation and migration, and obtain the prediction results, including:

[0095] S401: constructing multiple models including the credible innovation intelligent assessment model through redundant construction;

[0096] S402: constructing a model decision alliance through the multiple models;

[0097] S403: Import the simplified features into the multiple models at the same time, and obtain the output results of the adaptation and migration difficulty and the number of resources required for the adaptation and migration of each model for the ICT adaptation and migration project;

[0098] S404: Make a coordinated decision on the output results of each model, and take the consistent results as the optimal results of the prediction results.

[0099] In the specific implementation process, before explaining the specific implementation process of step S401 to step S404, first of all, the multi-mode collaborative decision-making mechanism provided by the embodiment of the present application is explained accordingly: the traditional machine learning model makes decisions based on a single algorithm model, and the correctness of the decision may be affected by the deviation of the new data. The embodiment of the present application establishes a multi-model collaborative decision-making mechanism by drawing on the idea of ​​mimicry decision-making; wherein, the idea of ​​mimicry decision-making is a new idea that integrates the mimicry phenomenon in biology and decision theory; in biology, the mimicry phenomenon refers to the fact that in order to better adapt to the environment in which it is located, an organism exhibits similar characteristics to other organisms or non-organisms in the environment in terms of morphology, physiological functions or behavioral patterns; this natural adaptation strategy not only exists in the biological world, but also brings new inspiration to the fields of artificial intelligence and decision science.

[0100] After using the trusted intelligent evaluation model to predict the difficulty of adaptation and migration of trusted intelligent migration projects and the number of resources required for adaptation and migration, and obtaining the prediction results, first, multiple models including the trusted intelligent evaluation model are constructed through the redundant construction method; then, a model decision alliance is constructed through these multiple models; then, the streamlined features of the sample data to be predicted are imported into multiple models at the same time, and the output results of each model for the difficulty of adaptation and migration of trusted intelligent migration projects and the number of resources required for adaptation and migration are obtained; then, a coordinated decision is made on the output results of each model, and the consistent results are used as the optimal results of the prediction results. In other words, by comparing the output results of each model and making coordinated decisions, special case data can be avoided from having a greater impact on the prediction results, thereby ensuring that the final conclusion corresponding to the prediction results is more scientific and objective. In this way, the mimicry idea is applied to the model decision-making mechanism, which effectively avoids the adverse effects of special case data on the evaluation results.

[0101] Based on the same inventive concept, Figure 5 As shown, the embodiment of the present application also provides a device for predicting the migration of information innovation adaptation, the device comprising:

[0102] A collection unit 10 is used to collect survey data of the ICT adaptation and migration project and organize the survey data into multiple sample data;

[0103] A cleaning unit 20, configured to clean abnormal sample data from the plurality of sample data to obtain cleaned data;

[0104] A simplified element 30, used to simplify the features of the cleaned data by using statistical methods of variable dimension reduction and data reduction to obtain simplified features;

[0105] The prediction unit 40 is used to input the simplified features into the trusted intelligent evaluation model, predict the difficulty of adaptation and migration of the trusted intelligent adaptation and migration project and the number of resources required for adaptation and migration, and obtain a prediction result; the trusted intelligent evaluation model is a model pre-built based on a machine learning algorithm.

[0106] In the embodiment of the present application, the simplified element 30 is specifically used for:

[0107] By using a variable dimension reduction method, variable features that are not relevant to the Xinchuang intelligent assessment model are excluded from the cleaned data to obtain excluded features;

[0108] By using a data reduction method, similar features among the excluded features are merged to obtain common features;

[0109] The common features and other features among the excluded features except the common features are used as simplified features.

[0110] In the embodiment of the present application, the prediction unit 40 inputs the simplified features into the ICT intelligent evaluation model, predicts the difficulty of adaptation and migration of the ICT adaptation and migration project and the number of resources required for adaptation and migration, and after obtaining the prediction result, the device further includes a quantification unit 50, which is used to:

[0111] determining constraint characteristics that constrain the prediction results;

[0112] Calculate and obtain the Shapley value of the constraint feature;

[0113] The influence of the constraint feature on the prediction result is quantified by the Shapley value. The larger the positive value of the Shapley value is, the greater the contribution of the constraint feature to the accuracy of the prediction result is.

[0114] The influence degree of the constraint feature on the prediction result is displayed.

[0115] In the embodiment of the present application, the prediction unit 40 is specifically used for:

[0116] Through redundant construction, multiple models including the credible innovation intelligent evaluation model are constructed;

[0117] Building a model decision alliance through the multiple models;

[0118] Import the streamlined features into the multiple models at the same time, and obtain the output results of the adaptation and migration difficulty and the number of resources required for the adaptation and migration of each model for the trusted innovation adaptation and migration project;

[0119] Make coordinated decisions on the output results of each model and take the consistent results as the optimal results for the prediction results.

[0120] Based on the same inventive concept, an electronic device is also provided in the embodiment of the present application, and the electronic device can implement the function of the aforementioned method for predicting the adaptation migration of the information innovation, referring to Figure 6 , the electronic device comprises:

[0121] Memory 100, used for storing computer programs;

[0122] The processor 200 is used to implement the method steps of predicting information innovation adaptation migration as described in any of the preceding items when executing the computer program stored in the memory.

[0123] The specific connection medium between the processor 200 and the memory 100 is not limited in the embodiment of the present application. Figure 6 In the example, the processor 200 and the memory 100 are connected via the bus 300. The bus 300 is connected to the memory 100 via the bus 300. Figure 6 The bus 300 is represented by a bold line, and the connection between other components is only for schematic illustration and is not intended to be limiting. The bus 300 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 6 Only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus. Alternatively, the processor 200 can also be called a controller, and there is no limitation on the name.

[0124] In the embodiment of the present application, the memory 100 stores instructions that can be executed by the processor 200. When the processor 200 executes the computer program stored in the memory 100, the method for predicting the adaptation and migration of the information innovation discussed above can be executed. The processor 200 can implement Figure 5 The functions of each module are shown in the figure.

[0125] Among them, the processor 200 is the control center of the device, and can use various interfaces and lines to connect various parts of the entire control device, and through running or executing computer programs stored in the memory 100 and calling data stored in the memory 100, the various functions of the device and process data, thereby monitoring the device as a whole.

[0126] In one possible design, the processor 200 may include one or more processing units, and the processor 200 may integrate an application processor and a modem processor, wherein the application processor mainly processes an operating system, a user interface, and application programs, and the modem processor mainly processes wireless communications. In some embodiments, the processor 200 and the memory 100 may be implemented on the same chip, and in some embodiments, they may also be implemented separately on separate chips.

[0127] The memory 100, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer executable programs and modules. The memory 100 may include at least one type of storage medium, such as a flash memory, a hard disk, a multimedia card, a card-type memory, a random access memory (Random Access Memory, RAM), a static random access memory (Static Random Access Memory, SRAM), a programmable read-only memory (Programmable Read Only Memory, PROM), a read-only memory Read Only Memory, ROM), an electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, EEPROM), a magnetic memory, a disk, an optical disk, etc. Alternatively, the memory 100 is any other medium that can be used to carry or store a desired program code in the form of an instruction or data structure and can be accessed by a computer, but is not limited thereto. The memory 100 in the embodiment of the present application can also be a circuit or any other device that can realize a storage function, for storing program instructions and / or data.

[0128] By designing and programming the processor 200, the code corresponding to the method for predicting the adaptive migration of information innovation introduced in the above embodiment can be fixed into the chip, so that the chip can execute the steps of the method for predicting the adaptive migration of information innovation discussed above during operation. How to design and program the processor 200 is a technology known to those skilled in the art and will not be described in detail here.

[0129] Based on the same inventive concept, an embodiment of the present application also provides a computer-readable storage medium, which stores a computer program, and the computer program is used to enable a computer to execute the method steps of predicting information innovation adaptation migration discussed above.

[0130] In some possible implementations, various aspects of the method based on predictive information-based innovation adaptive migration provided by the present application can also be implemented in the form of a program product, which includes program code. When the program product is run on an apparatus, the program code is used to enable the control device to execute the steps of the method for predictive information-based innovation adaptive migration according to various exemplary embodiments of the present application described above in this specification.

[0131] The embodiment of the present application provides a method for predicting the adaptation and migration of credible innovation. First, the survey data of the credible innovation adaptation and migration project is collected, and the survey data is organized into multiple sample data; then, the abnormal sample data in the multiple sample data is cleaned to obtain the cleaned data; then, the statistical methods of variable dimension reduction and data reduction are used to simplify the features of the cleaned data to obtain simplified features; in this way, the number of features that need to be extracted is reduced. Then, the simplified features are input into the credible innovation intelligent evaluation model, and the adaptation and migration difficulty of the credible innovation adaptation and migration project and the number of resources required for the adaptation and migration are predicted to obtain the prediction results; wherein, the credible innovation intelligent evaluation model is a model pre-built based on a machine learning algorithm. In other words, the credible innovation intelligent evaluation model pre-built based on a machine learning algorithm is applied to the credible innovation industry, which realizes the prediction of the credible innovation adaptation and migration difficulty and the number of resources required for the adaptation and migration, and thus realizes the effective evaluation of the adaptation risk.

[0132] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0133] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0134] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0135] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0136] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A method for predicting information innovation adaptation migration, characterized in that: include: Collect survey data of the Xinchuang adaptation and migration project, and organize the survey data into multiple sample data; Cleaning abnormal sample data among the plurality of sample data to obtain cleaned data; By using statistical methods of variable dimension reduction and data reduction, the cleaned data is subjected to feature simplification to obtain simplified features; The simplified features are input into the trusted intelligent evaluation model to predict the difficulty of adaptation and migration of the trusted intelligent adaptation and migration project and the number of resources required for adaptation and migration to obtain prediction results; the trusted intelligent evaluation model is a model pre-built based on a machine learning algorithm.

2. The method according to claim 1, characterized in that The statistical method of variable dimension reduction and data reduction is used to simplify the features of the cleaned data to obtain simplified features, including: By using a variable dimension reduction method, variable features that are not relevant to the Xinchuang intelligent assessment model are excluded from the cleaned data to obtain excluded features; By using a data reduction method, similar features among the excluded features are merged to obtain common features; The common features and other features among the excluded features except the common features are used as simplified features.

3. The method according to claim 1 or 2, characterized in that After inputting the simplified features into the ICT intelligent evaluation model, predicting the difficulty of adaptation and migration of the ICT adaptation and migration project and the number of resources required for adaptation and migration, and obtaining the prediction results, the method further includes: determining constraint characteristics that constrain the prediction results; Calculate and obtain the Shapley value of the constraint feature; The influence of the constraint feature on the prediction result is quantified by the Shapley value. The larger the positive value of the Shapley value is, the greater the contribution of the constraint feature to the accuracy of the prediction result is. The influence degree of the constraint feature on the prediction result is displayed.

4. The method according to claim 1 or 2, characterized in that: The simplified features are input into the ICT intelligent evaluation model to predict the difficulty of adaptation and migration of the ICT adaptation and migration project and the number of resources required for adaptation and migration, and obtain prediction results, including: Through redundant construction, multiple models including the credible innovation intelligent evaluation model are constructed; Building a model decision alliance through the multiple models; Import the streamlined features into the multiple models at the same time, and obtain the output results of the adaptation and migration difficulty and the number of resources required for the adaptation and migration of each model for the trusted innovation adaptation and migration project; Make coordinated decisions on the output results of each model and take the consistent results as the optimal results for the prediction results.

5. A device for predicting information innovation adaptation migration, characterized in that: include: A collection unit, used to collect survey data of the ICT adaptation and migration project, and organize the survey data into multiple sample data; A cleaning unit, used for cleaning abnormal sample data among the plurality of sample data to obtain cleaned data; A simplified element is used to simplify the features of the cleaned data by using statistical methods of variable dimension reduction and data reduction to obtain simplified features; A prediction unit is used to input the simplified features into the trusted intelligent evaluation model, predict the difficulty of adaptation and migration of the trusted intelligent adaptation and migration project and the number of resources required for adaptation and migration, and obtain a prediction result; the trusted intelligent evaluation model is a model pre-built based on a machine learning algorithm.

6. The device according to claim 5, characterized in that The concise element is specifically used for: By using a variable dimension reduction method, variable features that are not relevant to the Xinchuang intelligent assessment model are excluded from the cleaned data to obtain excluded features; By using a data reduction method, similar features among the excluded features are merged to obtain common features; The common features and other features among the excluded features except the common features are used as simplified features.

7. The device according to claim 5 or 6, characterized in that After the prediction unit inputs the simplified features into the ICT intelligent evaluation model, predicts the difficulty of adaptation and migration of the ICT adaptation and migration project and the number of resources required for adaptation and migration, and obtains the prediction result, the device further includes a quantification unit, which is used to: determining constraint characteristics that constrain the prediction results; Calculate and obtain the Shapley value of the constraint feature; The influence of the constraint feature on the prediction result is quantified by the Shapley value. The larger the positive value of the Shapley value is, the greater the contribution of the constraint feature to the accuracy of the prediction result is. The influence degree of the constraint feature on the prediction result is displayed.

8. An electronic device, characterized in that: include: Memory, used to store computer programs; A processor, configured to implement the method steps of any one of claims 1 to 4 when executing the computer program stored in the memory.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and the computer program is used to enable a computer to execute the method steps according to any one of claims 1 to 4.

10. A computer program product, characterized in that The computer program product comprises: a computer program code, and when the computer program code is run on a computer, the computer is enabled to execute the method according to any one of claims 1 to 4.

Images