Public cloud cloud product recommendation method, device, equipment, medium and computer program

Abstract

The application provides a public cloud product recommendation method, device, equipment, medium and computer program, and relates to the technical field of computers, which comprises obtaining first information and second information; performing feature matching and data analysis according to the first information and the second information to obtain third information; constructing a cloud product prediction mathematical model according to the second information, and taking the third information as an input value of the cloud product prediction mathematical model to predict fourth information; performing comprehensive evaluation processing according to the fourth information to obtain fifth information, wherein the fifth information comprises at least one cloud product combination package and a corresponding analysis result; obtaining feedback information according to a package selected by a user in the fifth information and an actual use condition, and optimizing the cloud product prediction model according to the feedback information. According to the application, a recommendation system based on machine learning is used, cloud resource products suitable for a user are matched according to a demand portrait of the user, and more accurate and diversified cloud product recommendation is provided for the user.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer, in particular, to a public cloud product recommendation method, device, equipment, medium and computer program. BACKGROUND

[0002] With the development of cloud computing, the types of cloud products on the public cloud are increasing, and the number of customers applying for cloud products is also large. How the service provider of cloud products quickly recommends cloud product packages according to the needs of users is a problem to be solved. The existing public cloud product recommendation method is a recommendation system based on fixed rules and templates. In this method, the service provider defines some rules and templates in advance, and according to some basic information provided by the user (such as business type, demand size, budget, etc.), the system will generate some recommended cloud product package information according to these rules and templates. Then display these recommended package information to the user for selection. However, this method has some significant shortcomings. The recommendation based on fixed rules and templates cannot flexibly adapt to various complex user needs and scene changes.

[0003] Based on the above-mentioned shortcomings of the prior art, there is an urgent need for a public cloud product recommendation method, device, equipment, medium and computer program. SUMMARY

[0004] The purpose of the present application is to provide a public cloud product recommendation method, device, equipment, medium and computer program to improve the above-mentioned problems. In order to achieve the above-mentioned purpose, the technical solution adopted by the present application is as follows:

[0005] In a first aspect, the present application provides a public cloud product recommendation method, comprising:

[0006] Obtaining first information and second information, the first information including user identification and user scene data of a client to be recommended, and the second information including historical user data;

[0007] According to the first information and the second information, feature matching and data analysis are performed to obtain third information, the third information including cloud product demand type and demand characteristics of the client to be recommended;

[0008] According to the second information, a cloud product prediction mathematical model is constructed, and the third information is taken as an input value of the cloud product prediction mathematical model to predict fourth information, the fourth information including cloud product package combination information;

[0009] According to the fourth information, comprehensive evaluation processing is performed to obtain fifth information, the fifth information including at least one cloud product combination package and corresponding analysis results;

[0010] According to the feedback information of the package selected by the user in the fifth information and the actual use, the cloud product prediction model is optimized.

[0011] In a second aspect, the application further provides a public cloud product recommendation device, comprising:

[0012] An acquisition module is configured to acquire first information and second information, wherein the first information comprises a user identifier and user scenario data of a client to be recommended, and the second information comprises historical user data.

[0013] A matching module is configured to perform feature matching and data analysis according to the first information and the second information to obtain third information, wherein the third information comprises a cloud product demand type and demand characteristics of the client to be recommended.

[0014] A construction module is configured to construct a cloud product prediction mathematical model according to the second information, and predict fourth information by taking the third information as an input value of the cloud product prediction mathematical model, wherein the fourth information comprises cloud product package combination information.

[0015] An evaluation module is configured to perform comprehensive evaluation processing according to the fourth information to obtain fifth information, wherein the fifth information comprises at least one cloud product combination package and a corresponding analysis result.

[0016] An optimization module is configured to acquire feedback information according to the package selected by the user in the fifth information and the actual use, and optimize the cloud product prediction model according to the feedback information.

[0017] In a third aspect, the application further provides a public cloud product recommendation device, comprising:

[0018] A memory is configured to store a computer program.

[0019] A processor is configured to implement the steps of the public cloud product recommendation method when the computer program is executed.

[0020] In a fourth aspect, the application further provides a medium, wherein the medium stores a computer program, and the computer program is configured to implement the steps of the public cloud product recommendation method when executed by a processor.

[0021] In a fifth aspect, the application further provides a computer program product, wherein the computer program product comprises a computer program, and the computer program is configured to load and execute the steps of the public cloud product recommendation method when executed by a processor.

[0022] The application has the following beneficial effects:

[0023] The present application can provide more accurate and diversified cloud product recommendations for users by utilizing a machine learning-based recommendation system to match cloud resource products suitable for users according to the user's own demand portrait and continuously adjust the model according to the user's feedback, and can also reduce the burden of users when analyzing and selecting cloud products and improve user satisfaction.

[0024] Other features and advantages of the present application will be set forth in the following description, and in part will become apparent from the description, or can be learned by practice of the present application according to the embodiments. The objects and other advantages of the present application can be achieved and obtained by the structure particularly pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF DRAWINGS

[0025] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the embodiments will be briefly introduced below, and it should be understood that the following drawings only show some embodiments of the present application, and therefore should not be regarded as a limitation on the scope, and for those skilled in the art, other related drawings can also be obtained without creative labor on the basis of these drawings.

[0026] Figure 1 The public cloud cloud product recommendation method flowchart described in the embodiments of the present application;

[0027] Figure 2 The public cloud cloud product recommendation device structure diagram described in the embodiments of the present application;

[0028] Figure 3 The public cloud cloud product recommendation device structure diagram described in the embodiments of the present application.

[0029] Marked in the figure: 1, acquisition module; 2, matching module; 21, first extraction unit; 22, first matching unit; 23, first adjustment unit; 3, construction module; 31, second extraction unit; 32, first calculation unit; 33, first processing unit; 331, second processing unit; 332, first judgment unit; 333, third processing unit; 334, first test unit; 4, evaluation module; 41, first screening unit; 42, first analysis unit; 43, fourth processing unit; 5, optimization module; 51, fifth processing unit; 52, first evaluation unit; 53, first adjustment unit; 800, public cloud cloud product recommendation device; 801, processor; 802, memory; 803, multimedia component; 804, I / O interface; 805, communication component. DETAILED DESCRIPTION

[0030] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0031] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this invention, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0032] Example 1:

[0033] This embodiment provides a method for recommending public cloud products.

[0034] See Figure 1 The figure shows that the method includes steps S100, S200, S300, S400 and S500.

[0035] Step S100: Obtain first information and second information. The first information includes the user identifier and user scenario data of the customer to be recommended, and the second information includes historical user data.

[0036] It can be understood that the step is aimed at obtaining the first information and the second information of the to-be-recommended customer to build a comprehensive data foundation for accurate analysis and personalized recommendation in the subsequent public cloud product recommendation process. The acquisition of these information covers multiple aspects, such as user identification, user scenario data and historical user data, as well as user performance characteristics, cost budget, project information, etc. These information will help to accurately identify user demand and behavior patterns, so as to better recommend cloud products. User identification and user scenario data: user identification is information used to uniquely identify each customer, which can be user ID, account name, etc. User scenario data provides information about user behavior and demand in a specific context, covering industry, business type, geographic location, etc. These data help service providers understand the background and specific needs of users, so as to make more targeted recommendations. Performance characteristic data includes transaction volume, number of users, concurrency, data size, etc. Performance indicators to describe the load and demand of users when using cloud products. These indicators can help service providers understand the resource demand size of users, so as to make recommendations according to actual conditions. User cost budget represents the upper limit of the fee that the user is willing to pay, which is crucial for determining a feasible cloud product solution. Questionnaire information further understands the project information and business category of the user, so as to better understand the user demand and background. By analyzing the user's past cloud product usage, their preferences and habits can be understood. At the same time, understanding the user's operating device helps to recommend cloud products suitable for their equipment. User demand and scenario data cover the specific needs of users for cloud products, such as resource addition, expansion, etc. At the same time, obtaining scenario data corresponding to user demand can better understand the operation background of users, so as to better meet their actual needs.

[0037] Step S200, performing feature matching and data analysis according to the first information and the second information to obtain third information, the third information including cloud product demand type and demand characteristics of the to-be-recommended customer.

[0038] It should be noted that step S200 includes step S210, step S220 and step S230.

[0039] Step S210, performing feature extraction processing according to the first information, and analyzing the extracted feature data to obtain an analysis result, the analysis result including feature information, system level and transaction function condition.

[0040] It can be understood that in this step, the service provider performs feature extraction processing based on the user identification in the first information and the historical user data in the second information. The goal of feature extraction is to extract key feature information from user data, which may include user business type, historical transaction volume, cost budget, etc. Then, the service provider analyzes the extracted feature data to obtain analysis results. These results may cover feature information (specific description of user characteristics), system level (such as project size), transaction function situation (special requirements for transactions), etc.

[0041] Step S220, performing feature matching processing according to the analysis results, obtaining matching results by matching similar users and demand situations in the second information.

[0042] It can be understood that in this step, according to the analysis results, the service provider tries to match the user's feature information with the historical user data in the second information. The purpose of matching is to find historical users and similar demand situations that are similar to the to-be-recommended customer in certain specific aspects. Through matching, the service provider can find similar use cases from historical data, which helps to provide more targeted cloud product package recommendations for the to-be-recommended customer.

[0043] Step S230, performing feature data adjustment processing according to the matching results, obtaining third information.

[0044] It can be understood that in this step, according to the matching results, the service provider adjusts the user's feature data as necessary. These adjustments may involve obtaining more accurate feature information from historical user data to better reflect the needs of the to-be-recommended customer. The adjusted feature data will be part of the third information and will be further used in the subsequent recommendation process. Through feature extraction, matching and data adjustment, the service provider can capture the key needs and use characteristics of the user in the cloud product recommendation process, improving the accuracy and practicality of the recommendation.

[0045] Step S300, constructing a cloud product prediction mathematical model according to the second information, and taking the third information as the input value of the cloud product prediction mathematical model to predict the fourth information, the fourth information including cloud product package combination information.

[0046] It should be noted that step S300 includes step S310, step S320 and step S330.

[0047] Step S310, performing feature extraction to obtain cloud product feature data according to the second information, and constructing a cloud product prediction mathematical model according to the cloud product feature data and a preset machine learning mathematical model, the cloud product prediction mathematical model including at least one cloud resource product label prediction model.

[0048] It can be understood that in this step, the service provider constructs a cloud product prediction mathematical model according to the cloud product feature data and the preset machine learning mathematical model (which can include algorithms such as logistic regression, decision tree, neural network, etc.). This model will be used to make predictions based on user features, historical data, and third information to infer suitable cloud product packages for customers. Preferably, a logistic regression algorithm is used in this implementation, and the optimal value of the weight parameter is determined by continuously training the logistic regression cost function to minimize the cost function, thereby obtaining a trained logistic regression model, which is the trained insurance label prediction model (cloud product prediction mathematical model). Its corresponding logistic regression function is:

[0049]

[0050] Where x is the input feature (user basic data and insurance feature data), a is the weight parameter, and h(x) is the output feature (insurance label information).

[0051] Step S320, input the third information into the cloud product prediction mathematical model, and calculate the prediction result by combining the relationship between customer features and historical data.

[0052] It can be understood that in this step, the third information is input as an input value into the cloud product prediction mathematical model that has been constructed. The model calculates the prediction result by combining the relationship between customer features and historical data. The prediction result can include a series of cloud product labels that may be suitable for the customer, and these labels represent different cloud product packages.

[0053] Step S330, resource combination processing is performed according to the prediction result to obtain fourth information.

[0054] It can be understood that in this step, the service provider performs resource combination processing based on the prediction result. According to the cloud product labels in the prediction result, the service provider will combine resource package information suitable for the customer's needs. These resource packages can cover multiple aspects, such as technology stack, deployment unit, deployment area, network area, server configuration, etc. At the same time, according to the cloud product capacity information, the service provider judges the capacity situation of the existing deployment area, and if it does not meet the needs, it will recommend alternative solutions.

[0055] It should be noted that step S330 includes step S331, step S332, and step S333.

[0056] Step S331, generate resource package information according to the prediction result and customer needs.

[0057] It can be understood that in this step, the service provider generates resource package information suitable for the customer according to the prediction results and the customer's needs. These resource package information may include different kinds of cloud product packages, such as open area AP package, open area bare metal AP, big data cloud data collection package, big data cloud data service package, big data cloud real-time processing package, etc. Each package information may include technology stack, deployment unit, deployment area, network area, operating system, server configuration, CBS disk capacity, server quantity, purpose, service type, etc.

[0058] Step S332, capacity judgment and alternative solution generation according to resource package information, to obtain cloud product capacity information.

[0059] It can be understood that in this step, the service provider judges the existing deployment area capacity according to the generated resource package information. If it is found that the capacity of the deployment area is insufficient to meet the customer's needs, the service provider may recommend possible alternative solutions according to the alternative solution generation strategy to ensure that the customer can meet the resource needs.

[0060] Step S333, according to the cloud product capacity information, by allocating the detailed data of cloud hardware devices, software products, network communication, etc. to the corresponding cloud products according to the use purpose, to obtain a cost unit price table.

[0061] It can be understood that in this step, the service provider executes the cost allocation module to collect the detailed data of the cost input of cloud hardware devices, software products, network communication, etc. and allocate the input detailed cost to the corresponding cloud products according to the use purpose. These cost allocations will form the unit price of each cloud product according to the cloud product capacity information. Through the cost unit price table, the multi-dimensional cloud resource usage of each department, project, and tenant can be calculated.

[0062] Step S334, pricing test processing according to resource package information and cost unit price table, verifying the price of the recommended cloud product package, and adjusting the alternative cloud product accordingly, to obtain the fourth information.

[0063] It can be understood that in this step, the service provider uses the cloud product pricing test module to verify whether the price of the recommended cloud product package is within the customer's budget and whether it is possible to exceed the budget. If it exceeds the budget, the service provider may consider calculating according to the alternative cloud product package to obtain a package information that meets the customer's expected price within the budget.

[0064] Step S400, comprehensive evaluation processing according to the fourth information to obtain the fifth information, the fifth information including at least one cloud product combination package and corresponding analysis results.

[0065] It can be understood that this step involves the generation of cloud product combination packages, performance and cost analysis, and providing customized recommendations and analysis results for customers. It should be noted that step S400 includes step S410, step S420 and step S430.

[0066] Step S410, according to the cloud product combination package in the fourth information, combined with the budget limit and business demand of the customer, the candidate scheme is obtained by screening.

[0067] It can be understood that these candidate schemes differ in performance, cost and other aspects to meet the different needs of different customers.

[0068] Step S420, according to the candidate scheme, performance and cost analysis is carried out, and by considering the customer's expansion demand and evaluating the sustainability of the scheme, the analysis result is obtained.

[0069] It can be understood that evaluating the sustainability of the scheme is also one of the important considerations, which ensures that the recommended scheme can meet the future needs of the customer.

[0070] Step S430, according to the analysis result, an analysis report is generated for each candidate scheme to obtain the fifth information, and the analysis report includes the evaluation of the performance, cost, risk of each candidate scheme and the customized recommendations for the customer's business demand.

[0071] It can be understood that these reports include the evaluation of the performance, cost, risk, etc. of each candidate scheme. In addition, the service provider will also provide customized recommendations according to the customer's business demand, helping the customer better understand the advantages and disadvantages of each scheme, so as to make a more intelligent decision.

[0072] Step S500, according to the user-selected package in the fifth information and the actual use, feedback information is obtained, and the cloud product prediction model is optimized according to the feedback information.

[0073] It can be understood that this step collects data from the actual experience of the customer to optimize the cloud product prediction model, so that it is more in line with the needs and expectations of the customer. It should be noted that step S500 includes step S510, step S520 and step S530.

[0074] Step S510, according to the user-selected package and the actual use, the user's product use data is regularly monitored and collected.

[0075] It can be understood that these data cover aspects such as the frequency of use of resources, performance indicators, cost situations, etc. to help the service provider understand the actual use of the recommended products by the customer.

[0076] Step S520, evaluate the recommended cloud product package according to the customer's satisfaction in the feedback information and the use embodiment index to obtain the evaluation result.

[0077] It can be understood that these indicators include customer satisfaction survey results, use experience improvement points, and whether the expected effect is achieved. Through the evaluation of these indicators, the service provider can understand the customer's feelings and opinions about the recommended products.

[0078] Step S530, adjust the weight parameters of the model according to the product use data and the evaluation result, and iterate and improve the cloud product prediction model.

[0079] It can be understood that by analyzing the actual data and evaluation results, the service provider can adjust the weight parameters of the model to more accurately predict customer needs and recommend suitable cloud product combinations. This iterative process helps continuously improve the prediction accuracy and recommendation effect of the model.

[0080] Embodiment 2:

[0081] As shown in Figure 2 The embodiment provides a public cloud product recommendation device, the device comprises:

[0082] The acquisition module 1 is configured to acquire first information and second information, the first information comprising a user identifier and user scenario data of a client to be recommended, and the second information comprising historical user data.

[0083] The matching module 2 is configured to perform feature matching and data analysis according to the first information and the second information to obtain third information, the third information comprising a cloud product demand type and demand characteristics of the client to be recommended.

[0084] The construction module 3 is configured to construct a cloud product prediction mathematical model according to the second information, and predict fourth information by taking the third information as an input value of the cloud product prediction mathematical model, the fourth information comprising cloud product package combination information.

[0085] The evaluation module 4 is configured to perform comprehensive evaluation processing on the fourth information to obtain fifth information, the fifth information comprising at least one cloud product combination package and a corresponding analysis result.

[0086] The optimization module 5 is configured to acquire feedback information according to a package selected by a user in the fifth information and actual use, and optimize the cloud product prediction model according to the feedback information.

[0087] In one specific embodiment of the present disclosure, the matching module 2 comprises:

[0088] The first extraction unit 21 is configured to perform feature extraction processing according to the first information, and analyze the extracted feature data to obtain an analysis result, wherein the analysis result includes feature information, system level and transaction function condition.

[0089] The first matching unit 22 is configured to perform feature matching processing according to the analysis result, and obtain a matching result by matching approximate users and demand conditions in the second information.

[0090] The first adjustment unit 23 is configured to perform feature data adjustment processing according to the matching result, and obtain the third information.

[0091] In one specific embodiment of the present disclosure, the construction module 3 includes:

[0092] The second extraction unit 31 is configured to perform feature extraction to obtain cloud product feature data according to the second information, and construct a cloud product prediction mathematical model according to the cloud product feature data and a preset machine learning mathematical model, wherein the cloud product prediction mathematical model includes at least one cloud resource product label prediction model.

[0093] The first calculation unit 32 is configured to input the third information into the cloud product prediction mathematical model, and perform calculation by combining the relationship between the customer features and the historical data to obtain a prediction result.

[0094] The first processing unit 33 is configured to perform resource combination processing according to the prediction result to obtain the fourth information.

[0095] In one specific embodiment of the present disclosure, the first processing unit 33 includes:

[0096] The second processing unit 331 is configured to generate resource package information according to the prediction result and the customer demand.

[0097] The first judgment unit 332 is configured to perform capacity judgment and alternative scheme generation according to the resource package information to obtain cloud product capacity information.

[0098] The third processing unit 333 is configured to obtain a cost unit price table by allocating detailed data of cloud hardware devices, software products, network communication and the like to corresponding cloud products according to usage purposes according to the cloud product capacity information.

[0099] The first test unit 334 is configured to perform pricing test processing according to the resource package information and the cost unit price table, verify the price of the recommended cloud product package, and correspondingly adjust the alternative cloud product to obtain the fourth information.

[0100] In one specific embodiment of the present disclosure, the evaluation module 4 includes:

[0101] The first screening unit 41 is configured to screen candidate solutions according to the cloud product combination package in the fourth information, in combination with the budget limit and business demand of the customer.

[0102] The first analysis unit 42 is configured to perform performance and cost analysis according to the candidate solutions, to obtain an analysis result by considering the expansion demand of the customer and evaluating the sustainability of the solutions.

[0103] The fourth processing unit 43 is configured to generate an analysis report for each candidate solution according to the analysis result, to obtain fifth information, the analysis report including evaluation of performance, cost, and risk of each candidate solution and customized suggestions for the business demand of the customer.

[0104] In one specific embodiment of the present disclosure, the optimization module 5 includes:

[0105] The fifth processing unit 51 is configured to regularly monitor and collect product usage data of the user according to the selected package and actual usage of the user.

[0106] The first evaluation unit 52 is configured to evaluate the recommended cloud product package according to the satisfaction and usage embodiment indicators of the customer in the feedback information to obtain an evaluation result.

[0107] The first adjustment unit 23 is configured to adjust the weight parameters of the model according to the product usage data and the evaluation result, to iteratively and improve the cloud product prediction model.

[0108] Embodiment 3:

[0109] Corresponding to the above method embodiments, the present embodiment also provides a public cloud cloud product recommendation device, and the public cloud cloud product recommendation device described below can be correspondingly referred to the public cloud cloud product recommendation method described above.

[0110] Figure 3 is a block diagram of a public cloud cloud product recommendation device 800 according to an exemplary embodiment. As shown, the public cloud cloud product recommendation device 800 can include a processor 801 and a memory 802. The public cloud cloud product recommendation device 800 can also include one or more of a multimedia component 803, an I / O interface 804, and a communication component 805. Figure 3

[0111] ​The processor 801 is configured to control overall operations of the public cloud product recommendation device 800 to complete all or part of the steps of the above public cloud product recommendation method. The memory 802 is configured to store various types of data to support the operations of the public cloud product recommendation device 800, which can include, for example, instructions for any application or method operating on the public cloud product recommendation device 800, and application-related data, such as contact data, sent and received messages, pictures, audio, video, and the like. The memory 802 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The multimedia component 803 can include a screen and an audio component. The screen can be a touch screen, for example, and the audio component is configured to output and / or input audio signals. For example, the audio component can include a microphone configured to receive external audio signals. The received audio signals can be further stored in the memory 802 or transmitted through the communication component 805. The audio component also includes at least one speaker configured to output audio signals. The I / O interface 804 provides an interface between the processor 801 and other interface modules, which can be a keyboard, a mouse, a button, and the like. The buttons can be virtual buttons or physical buttons. The communication component 805 is configured to perform wired or wireless communication between the public cloud product recommendation device 800 and other devices. The wireless communication, such as Wi-Fi, Bluetooth, near field communication (NFC), 2G, 3G or 4G, or a combination of one or more of them, so the corresponding communication component 805 can include a Wi-Fi module, a Bluetooth module, an NFC module.

[0112] In an example embodiment, the public cloud cloud product recommendation device 800 can be implemented by one or more Application Specific Integrated Circuit (ASIC), Digital Signal Processor (DSP), Digital Signal Processing Device (DSPD), Programmable Logic Device (PLD), Field Programmable Gate Array (FPGA), controller, microcontroller, microprocessor or other electronic elements for executing the above-mentioned public cloud cloud product recommendation method.

[0113] In another example embodiment, a computer readable storage medium including program instructions is also provided, which when executed by a processor, implement the steps of the above-mentioned public cloud cloud product recommendation method. For example, the computer readable storage medium can be the above-mentioned memory 802 including program instructions, which can be executed by the processor 801 of the public cloud cloud product recommendation device 800 to complete the above-mentioned public cloud cloud product recommendation method.

[0114] Embodiment 4:

[0115] Corresponding to the above method embodiments, the present embodiment also provides a readable storage medium, which can be referred to each other below described a readable storage medium and the above described a public cloud cloud product recommendation method.

[0116] A readable storage medium, the readable storage medium stores a computer program, the computer program is executed by a processor to implement the steps of the above-mentioned public cloud cloud product recommendation method.

[0117] The readable storage medium can be a U disk, a mobile hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and various readable storage media that can store program codes.

[0118] Embodiment 5:

[0119] The present embodiment also provides a computer program product, the computer program product includes a computer program, the computer program is executed by a processor to execute the method provided in any optional embodiment of the present application.

[0120] Based on the same principles as the methods provided in the embodiments of this application, the embodiments of this application also provide a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the common sequence number processing method provided in any of the optional embodiments of this application described above.

[0121] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

[0122] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A public cloud cloud product recommendation method, characterized by, The method comprises the following steps: obtaining first information and second information, wherein the first information comprises user identification and user scenario data of a client to be recommended, and the second information comprises historical user data; performing feature matching and data analysis according to the first information and the second information to obtain third information, wherein the third information comprises a cloud product demand type and demand characteristics of the client to be recommended; performing feature extraction processing according to the second information, and constructing a cloud product prediction model according to extracted cloud product feature data and a preset machine learning mathematical model, wherein the cloud product prediction model comprises at least one cloud resource product label prediction model, and the third information is used as an input value of the cloud product prediction model to predict fourth information, wherein the fourth information comprises cloud product package combination information; performing comprehensive evaluation processing according to the fourth information to obtain fifth information, wherein the fifth information comprises at least one cloud product combination package and corresponding analysis results; obtaining feedback information according to a package selected by a user in the fifth information and actual use, and optimizing the cloud product prediction model according to the feedback information; performing feature matching and data analysis according to the first information and the second information to obtain third information, comprising: performing feature extraction processing according to the first information, and analyzing extracted feature data to obtain analysis results, wherein the analysis results comprise feature information, system level and transaction function conditions; performing feature matching processing according to the analysis results, and obtaining a matching result by matching approximate users and demand conditions in the second information; performing feature data adjustment processing according to the matching result to obtain third information; performing resource combination processing according to a prediction result to obtain fourth information, comprising: generating resource package information according to the prediction result and client demand; performing capacity judgment and alternative scheme generation according to the resource package information to obtain cloud product capacity information; according to the cloud product capacity information, detailed data of cloud hardware devices, software products and network communication costs are allocated to corresponding cloud products according to use purposes to obtain a cost unit price table; performing pricing test processing according to the resource package information and the cost unit price table, verifying a price of a recommended cloud product package, and adjusting a substitute cloud product accordingly to obtain fourth information. 2.The public cloud cloud product recommendation method of claim 1, wherein, performing comprehensive evaluation processing according to the fourth information to obtain fifth information, comprising: obtaining candidate schemes by combining cloud product combination packages in the fourth information with budget limitations and business demands of clients; performing performance and cost analysis according to the candidate schemes, considering expansion demands of clients and sustainability of evaluation schemes to obtain analysis results; generating an analysis report for each candidate scheme according to the analysis results to obtain fifth information, wherein the analysis report comprises evaluation of performance, cost and risk of each candidate scheme, and customized suggestions for business demands of clients. 3.The public cloud cloud product recommendation method of claim 1, wherein, obtaining feedback information according to a package selected by a user in the fifth information and actual use, and optimizing the cloud product prediction model according to the feedback information, comprising: According to the user-selected package and the actual use, the product use data of the user is regularly monitored and collected; According to the satisfaction and use embodiment index of the customer in the feedback information, the recommended cloud product package is evaluated to obtain an evaluation result; According to the product use data and the evaluation result, the weight parameter of the model is adjusted, and the cloud product prediction model is iterated and improved. 4.A public cloud cloud product recommendation apparatus characterized by comprising: Comprise: The acquisition module is used for acquiring first information and second information, the first information comprises user identification and user scene data of a client to be recommended, and the second information comprises historical user data; The matching module is used for performing feature matching and data analysis according to the first information and the second information to obtain third information, the third information comprises a cloud product demand type and demand characteristics of the client to be recommended; The construction module is used for performing feature extraction processing according to the second information, and constructing a cloud product prediction model according to extracted cloud product feature data and a preset machine learning mathematical model, taking the third information as an input value of the cloud product prediction model to predict fourth information, the cloud product prediction model comprises at least one cloud resource product label prediction model, and the fourth information comprises cloud product package combination information; The evaluation module is used for performing comprehensive evaluation processing according to the fourth information to obtain fifth information, the fifth information comprises at least one cloud product combination package and a corresponding analysis result; The optimization module is used for acquiring feedback information according to a user-selected package and actual use in the fifth information, and optimizing the cloud product prediction model according to the feedback information; The matching module comprises: The first extraction unit is used for performing feature extraction processing according to the first information, and performing analysis on the extracted feature data to obtain an analysis result, the analysis result comprises feature information, system level and transaction function condition; The first matching unit is used for performing feature matching processing according to the analysis result, and obtaining a matching result by matching approximate users and demand conditions in the second information; The first adjustment unit is used for performing feature data adjustment processing according to the matching result to obtain the third information; The first processing unit comprises: The second processing unit is used for generating resource package information according to a prediction result and customer demand; The first judgment unit is used for performing capacity judgment and alternative scheme generation according to the resource package information to obtain cloud product capacity information; The third processing unit is used for obtaining a cost unit price table by allocating detailed data of cloud hardware devices, software products and network communication costs to corresponding cloud products according to use purposes according to the cloud product capacity information; The first test unit is used for performing pricing test processing according to the resource package information and the cost unit price table, verifying a price of a recommended cloud product package, and adjusting a substitute cloud product correspondingly to obtain fourth information.

5. The public cloud cloud product recommendation apparatus of claim 4, wherein, The evaluation module comprises: The first screening unit is used for screening a candidate scheme by combining a budget limit and a business demand of a customer according to a cloud product combination package in the fourth information; The first analysis unit is configured to perform performance and cost analysis on the candidate schemes, obtain analysis results by considering the expansion needs of the customer and evaluating the sustainability of the schemes. The fourth processing unit is configured to generate an analysis report for each of the candidate schemes according to the analysis results, obtain fifth information, and the analysis report includes evaluation of performance, cost, and risk of each of the candidate schemes and customized suggestions for the business needs of the customer.

6. The public cloud cloud product recommendation apparatus of claim 4, wherein, The optimization module comprises: The fifth processing unit is configured to regularly monitor and collect product usage data of the user according to the selected package and actual usage of the user. The first evaluation unit is configured to evaluate the recommended cloud product package according to the satisfaction and usage indicators of the customer in the feedback information to obtain evaluation results. The first adjustment unit is configured to adjust the weight parameters of the model according to the product usage data and the evaluation results, and iteratively and improve the cloud product prediction model. 7.A public cloud cloud product recommendation device, characterized by, It comprises: The memory is configured to store a computer program; The processor is configured to execute the computer program to implement the steps of the public cloud product recommendation method according to any one of claims 1 to 3.

8. A readable storage medium characterized by: The computer program is stored on the medium, and the computer program is executed by the processor to implement the steps of the public cloud product recommendation method according to any one of claims 1 to 3.

9. A computer program product, characterised in that, The computer program product comprises a computer program, and the computer program is executed by the processor to load and execute the steps of the public cloud product recommendation method according to any one of claims 1 to 3.

Images