An intelligent analysis method and system for cost management services of a cloud platform

Abstract

The present invention provides an intelligent analysis method and system for cloud platform cost management services, relating to the technical field of cost service recommendation. The method includes: obtaining historical cost service record data of the cloud platform, performing stage correlation analysis on multiple cost management services provided by the cloud platform and constructing a stage service correlation matrix; performing stage contribution analysis on multiple cost management services provided by the cloud platform and constructing a service local collaboration matrix for each software project; performing service heat difference analysis on each software project stage and generating a heat difference distribution matrix for each industry; after determining the industry data and project stage data of the target user, determining multiple candidate services for the target user according to the stage service correlation matrix and the heat difference distribution matrix, determining multiple target cost services from the multiple candidate services and generating a cost management service adaptation analysis result. The present invention realizes accurate analysis of the adaptability between users and different services.

Description

Technical Field

[0001] The present invention relates to the technical field of cost service recommendation, and particularly to an intelligent analysis method and system for cost management services on a cloud platform. Background Art

[0002] In the modern software development process, the cost management of projects has become an important part of enterprise operation and resource optimization. More and more enterprises providing software project cost management services host various services through a cloud platform and provide corresponding cost management services according to different software project states of users. The aim is to help users reduce development risks, optimize resource allocation, and improve project success rates through these cost management services. However, with the diversification of user needs and the intensification of industry characteristic differences, how to accurately recommend suitable service items for different users has become a key issue in platform promotion.

[0003] There are certain differences in the demand for cost management services in different industries, and there is a certain combination relationship among multiple services, that is, higher value can be generated when multiple services are used together. However, some service analysis schemes focus on the recommendation of single services and lack attention to the synergy between services, resulting in limitations in the process of analyzing the adaptability of multiple services to the current project state of users according to the popularity of different services in different stages of software projects, and the matching degree between the analysis results and the real needs of users is relatively low. Summary of the Invention

[0004] The present invention proposes an intelligent analysis method and system for cost management services on a cloud platform, aiming to solve at least one technical problem existing in the above background art.

[0005] In the first aspect of the present invention, an intelligent analysis method for cost management services on a cloud platform is provided, including:

[0006] Obtain historical cost service record data of multiple users on the cloud platform, conduct stage correlation analysis on multiple cost management services provided by the cloud platform according to the historical cost service record data, calculate the selection frequency parameter and global contribution parameter of each cost management service for different software project stages, and construct a stage-service correlation matrix between software project stages and cost management services;

[0007] Extract industry data of different users from the historical cost service record data, conduct stage contribution analysis on multiple cost management services provided by the cloud platform according to the historical cost service record data, calculate the local contribution parameter and synergy gain parameter of each cost management service in each software project stage within different industries, and construct a service local synergy matrix for each software project stage within different industries;

[0008] Perform a service heat difference analysis for each software project phase based on historical cost service record data, calculate the heat difference parameters of each cost management service in each software project phase within different industries, and generate a heat difference distribution matrix of cost management services within each industry;

[0009] After determining the industry data and project phase data of the target user, determine multiple candidate services according to the phase service association matrix and the heat difference distribution matrix, and determine multiple target cost services from the multiple candidate services in combination with the service local collaboration matrix of the software project phase, and generate the adaptation analysis result of the cost management service for the target user.

[0010] Preferably, calculate the local contribution parameter and the collaborative gain parameter of each cost management service in each software project phase within different industries, and construct a service local collaboration matrix for each software project phase regarding different industries, including:

[0011] For the th cost management service in any software project phase , calculate the selection frequency parameter and the success contribution parameter of the th cost management service in different industries based on the historical cost service record data, and generate the local contribution parameter of the th cost management service in different industries by correcting the success contribution parameter based on the selection frequency parameter;

[0012] Calculate the global gain parameter of the th cost management service according to the historical cost service record data, and the local gain parameters of the th cost management service in different industries. Correct the multiple local gain parameters of the th cost management service based on the global gain parameter to generate the collaborative gain parameter of the th cost management service in different industries. Calculate the phase service collaboration parameter of the th cost management service in different industries according to the local contribution parameter and the collaborative gain parameter, and construct the service local collaboration matrix of the th cost management service regarding different industries.

[0013] Preferably, for the global gain parameter and the local gain parameter, it further includes:

[0014] Use the following formula to calculate the Item cost management service The global gain parameter of: In the formula, Is the Item cost management service And the Item cost management service Under the collaboration of the Item cost management service Global gain parameter, Is the success rate of the software project under the condition of including the Item cost management service And the Item cost management service ; Is the success rate of the software project under the condition of including the Item cost management service ;

[0015] The local gain parameter of the Item cost management service In the target industry is calculated using the following formula: In the formula, Is the Item cost management service And the Item cost management service Under the collaboration of the Item cost management service Local gain parameter, Is the success rate of the software project under the condition of including the Item cost management service And the Item cost management service ; Is the success rate of the software project under the condition of including the Item cost management service ;

[0016] Preferably, multiple candidate services are determined according to the stage service correlation matrix and the heat difference distribution matrix, and multiple target cost services are determined from the multiple candidate services in combination with the service local collaboration matrix of the software project stage, including:

[0017] According to the industry data and project stage data of the target user, the heat difference parameter of the target user for each cost management service is determined from the heat difference distribution matrix, and the stage service correlation parameter of the target user for each cost management service is determined from the stage service correlation matrix;

[0018] Filter multiple candidate services from multiple cost management services provided by the cloud platform according to the heat difference parameter and the stage service association parameter, including calculating the global matching degree of each cost management service according to the heat difference parameter and the stage service association parameter, filtering out the cost management services with the global matching degree greater than the preset matching threshold and recording them as candidate services, determining the adaptation parameters of each candidate service, and determining multiple target cost services from multiple candidate services according to the adaptation parameters.

[0019] Preferably, determining the adaptation parameters of each candidate service and determining multiple target cost services from multiple candidate services according to the adaptation parameters includes:

[0020] Determine the service local collaboration matrix corresponding to the target user according to the industry data and project stage data of the target user, record the candidate service corresponding to the maximum value of the global matching degree as the benchmark cost service, remove the benchmark cost service from multiple candidate services and write it into the adaptation analysis list;

[0021] Analyze multiple candidate services through the service local collaboration matrix and the benchmark cost service, determine the stage service collaboration parameter of each candidate service under the benchmark cost service according to the service local collaboration matrix, and sort multiple candidate services according to the stage service collaboration parameter and the benchmark cost service, including generating a sorting value by weighting the adaptation parameter through the stage service collaboration parameter, and completing the sorting of multiple candidate services based on the sorting value;

[0022] Update the benchmark cost service according to the candidate service ranked first, remove the updated benchmark cost service from multiple candidate services and write it into the adaptation analysis list. Repeat the above operations until all candidate services are written into the adaptation analysis list, then determine the adaptation parameters of multiple candidate services according to the order in which the candidate services are written into the adaptation analysis list, and record the candidate services with the adaptation parameter greater than the preset adaptation threshold as the target cost services.

[0023] Preferably, calculate the heat difference parameter of each cost management service in each software project stage in different industries, and generate a heat difference distribution matrix of cost management services in each industry, including:

[0024] For the th cost management service in any software project stage , according to the selection frequency parameter of the th cost management service in different industries, use the following formula to calculate the selection difference degree between the th cost management service between any two industries: In the formula, represents the th cost management service Industry and industry The selection difference degree between them 、 respectively represent the th cost management service in the industry and the industry The selection frequency parameter within;

[0025] For the th cost management service in the software project stage, calculate the average value of multiple selection difference degrees to obtain the selection difference parameter, and calculate the th cost management service The heat value in the software project stage. After correcting the heat value through the selection difference parameter, generate the th cost management service Heat difference parameter of. According to the heat difference parameters of multiple cost management services in different software project stages, construct a heat difference distribution matrix of cost management services within each industry.

[0026] The second aspect of the present invention provides a cloud platform cost management service intelligent analysis system for implementing the above-mentioned cloud platform cost management service intelligent analysis method, including:

[0027] Historical data acquisition module, used to acquire historical cost service record data of the cloud platform regarding multiple users;

[0028] Stage service correlation analysis module, used to perform stage correlation analysis on multiple cost management services provided by the cloud platform according to the historical cost service record data, calculate the selection frequency parameter and global contribution parameter of each cost management service regarding different software project stages, and construct a stage service correlation matrix between the software project stage and the cost management service;

[0029] Service local collaboration analysis module, used to extract industry data of different users from the historical cost service record data, perform stage contribution analysis on multiple cost management services provided by the cloud platform according to the historical cost service record data, calculate the local contribution parameter and collaboration gain parameter of each cost management service in each software project stage within different industries, and construct a service local collaboration matrix of each software project stage regarding different industries;

[0030] A heat difference distribution analysis module, which is used to perform service heat difference analysis on each software project stage according to historical cost service record data, calculate the heat difference parameters of each cost management service in each software project stage within different industries, and generate a heat difference distribution matrix of cost management services within each industry;

[0031] A service adaptation analysis module, which is used to determine multiple candidate services according to the stage service association matrix and the heat difference distribution matrix after determining the industry data and project stage data of the target user, and determine multiple target cost services from multiple candidate services in combination with the service local collaboration matrix of the software project stage, and generate a cost management service adaptation analysis result for the target user.

[0032] The present invention has the following beneficial effects:

[0033] Through the stage association analysis of multiple cost management services provided by the cloud platform from a global perspective, the present invention determines the global association characteristics between different cost management services and different software project stages, conducts stage contribution analysis on multiple cost management services from the industry perspective, determines the industry-internal local collaboration characteristics between multiple cost management services in different software project stages under different industries, conducts service heat difference analysis on multiple cost management services from the perspective of industry heat difference, determines the heat difference hotlines of cost management services under different industries, quantifies the adaptability and collaboration benefits of services from both global and local perspectives, and finally analyzes the adaptability between users and different cost management services according to the industry fields associated with users and the actual development stages of software projects, so as to realize providing accurate service recommendations for users, effectively improving the adaptability and reliability of service recommendations, and providing significant advantages for the cloud platform in aspects such as improving user satisfaction and optimizing market promotion. Description of the Drawings

[0034] Figure 1 It is a schematic flow chart of a method for intelligent analysis of cost management services of a cloud platform provided by one embodiment of the present invention.

[0035] Figure 2 It is a schematic structural diagram of a system for intelligent analysis of cost management services of a cloud platform provided by one embodiment of the present invention. Detailed Embodiments

[0036] In order to enable those skilled in the art to better understand the technical solutions in the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0037] Please refer to Figure 1, which shows a schematic flowchart of an intelligent analysis method for cloud platform cost management services provided by one embodiment of the present invention. The method includes:

[0038] Step S1: Obtain historical cost service record data of the cloud platform for multiple users, perform stage correlation analysis on multiple cost management services provided by the cloud platform according to the historical cost service record data, and construct a stage service correlation matrix between the software project stage and the cost management service.

[0039] Specifically, an enterprise provides cost management-related services for various software projects for different users through the cloud platform, including providing cost decomposition and estimation within the entire project life cycle for users, helping users optimize resource allocation through data analysis, reducing unnecessary expenses, and providing cost management suggestions and assisting user decision-making in aspects such as technology selection, risk assessment, and performance optimization. The historical cost service record data at least includes record data in the enterprise's cloud platform regarding the selection of relevant cost management services by multiple users, including user basic information such as industry, company scale, budget, etc., service data such as service name, user evaluation, etc., and project results such as whether the project is completed on schedule and whether the budget control meets the standard.

[0040] First, analyze the historical cost service record data from a global perspective, including performing stage correlation analysis on multiple cost management services provided by the cloud platform. In this process, extract the records of cost management services selected by users in different project stages such as requirements, development, testing, operation and maintenance, etc. from the historical cost service record data, so as to calculate the selection frequency parameter and the successful contribution parameter of each cost management service regarding different software project stages. Among them, the selection frequency parameter can specifically be the ratio of the number of times a certain cost management service is selected by users in a certain software project stage to the total number of times all cost management services are selected in this software project stage. The successful contribution parameter can be the ratio of the number of times a project is successful after a certain cost management service is selected in a certain stage to the total number of successful projects. After correcting the selection frequency parameter through the successful contribution parameter, obtain the global contribution parameter of this cost management service in this software project stage, which characterizes the correlation characteristic between the cost management service and the project success status globally, and use the global contribution parameter as the stage service correlation parameter of the cost management service in this software project stage. After obtaining the stage service correlation parameters corresponding to each cost management service in different software project stages in this way, finally, construct a stage service correlation matrix between the software project stage and the cost management service according to the multiple stage service correlation parameters of each cost management service to reflect the selection tendency and contribution degree of different services in each project stage.

[0041] Step S2: Extract the industry data of different users from the historical cost service record data, conduct a stage contribution analysis on multiple cost management services provided by the cloud platform based on the historical cost service record data, and construct a service local collaboration matrix for each software project stage in different industries.

[0042] Specifically, the industry data is specifically used to indicate the industry category corresponding to the software project for which the user currently needs to conduct cost analysis, such as medical, financial, educational, etc. The purpose of the stage contribution analysis is to calculate the local contribution parameter and collaborative gain parameter of each cost management service in each software project stage in different industries. Among them, the calculation of the local contribution parameter is similar to the aforementioned global contribution parameter, but is specifically limited to a certain industry. That is, for a certain industry, through the selection frequency parameter and successful contribution parameter of the cost management service in a certain software project stage, the local contribution parameter is calculated to characterize the correlation characteristics between the cost management service and the project success status in this industry. Then, service collaboration analysis is carried out for each industry, specifically analyzing the influence relationship between the combined selection of two services and the selection of only a single service to calculate the collaborative gain parameter of the cost management service in each software project stage in different industries.

[0043] Finally, based on the local contribution parameter and collaborative gain parameter, determine the stage service correlation parameter of the cost management service in a certain software project stage within this industry. By obtaining the stage service correlation parameters corresponding to each cost management service in different software project stages for each industry in this way, based on the software project stage, construct a service local collaboration matrix for each software project stage in different industries, which is used to comprehensively characterize the correlation characteristics between the cost management service and the industry after considering industry characteristics.

[0044] Step S3: Conduct a service popularity difference analysis on each software project stage based on the historical cost service record data, calculate the popularity difference parameter of each cost management service in each software project stage in different industries, and generate a popularity difference distribution matrix of cost management services within each industry.

[0045] Specifically, for each software project phase, for some of the high-heat cost management services therein, the heat difference levels of these cost management services among different industries are analyzed in depth, and the heat difference parameters of each cost management service are calculated. The heat difference parameters further consider the differences among cost management services in different industries on the basis of the regular heat, and characterize the adaptability between cost management services and multiple industries. If the heat of a cost management service in a certain software project phase is high and the heat difference distribution is small, it means that the cost management service has a wide applicability in the current software project phase. The larger the corresponding heat difference parameter is, finally, through the multiple heat difference parameters of the cost management services, a heat difference distribution matrix of cost management services within the industry is constructed. The heat difference distribution matrix represents the heat difference distribution performance of multiple cost management services in different software project phases within one industry.

[0046] Step S4: After determining the industry data and project phase data of the target user, determine multiple candidate services according to the phase service association matrix and the heat difference distribution matrix, and determine multiple target cost services from the multiple candidate services in combination with the service local collaboration matrix of the software project phase, so as to generate the adaptability analysis result of the cost management service for the target user.

[0047] Specifically, for the target user who needs to analyze the software project through the cost management service, when the cloud platform determines the industry data and project phase data of the target user, that is, the specific industry field corresponding to the software project of the target user and the current project phase, multiple candidate services are comprehensively determined according to the phase service association matrix and the heat difference distribution matrix. Among them, the phase service association matrix represents the popularity of different cost management services in different software project phases from a global perspective, that is, the overall perspective of multiple industries. The heat difference distribution matrix specifically considers the detailed heat distribution of different cost management services in different industries, so as to select multiple cost management services as candidates. Then, through the service local collaboration matrix, the collaborative relevance between different cost management services is analyzed. For example, after selecting a certain service, selecting some other services at the same time may achieve a better linkage effect. Finally, some key service items are determined from the multiple candidate services and recorded as the target cost services. As the adaptability analysis result of the cost management service obtained after the service adaptability analysis between the target user and the multiple cost management services provided by the cloud platform, it indicates the matching situation between the target user's current software project state and different cost management services, which is convenient for providing cost service items with high adaptability for the target user.

[0048] Through the above steps, the present invention adopts a stage correlation analysis strategy and an industry local contribution analysis strategy, analyzes the adaptation of multiple cost management services provided by the cloud platform to different software projects from the overall perspective and the industry local perspective respectively, further conducts a synergy benefit analysis between services, organically integrates the multi-dimensional analysis results, realizes the accurate service adaptability analysis based on user characteristics and industry needs, and this method significantly improves the adaptability and reliability of the recommended solutions, providing strong technical support for the promotion of the cost management services of the cloud platform.

[0049] In the above content, for step S2, in the process of conducting a stage contribution analysis on multiple cost management services provided by the cloud platform according to the historical cost service record data, calculate the local contribution parameters and synergy gain parameters of each cost management service in each software project stage within different industries, and construct a service local synergy matrix for each software project stage regarding different industries, which specifically includes:

[0050] For the th cost management service in any one software project stage, calculate the selection frequency parameter and the successful contribution parameter of the th cost management service in different industries based on the historical cost service record data, and generate the local contribution parameter of the th cost management service in different industries by correcting the successful contribution parameter based on the selection frequency parameter.

[0051] Specifically, taking the th cost management service in any one software project stage as an example, referring to the calculation method of the foregoing global contribution parameter, for the specific performance of different cost management services in each industry, analyze the unique selection tendency and successful performance of the cost management service in different industries according to the historical cost service record data, and calculate the local contribution parameter corresponding to the cost management service in each industry after comprehensively considering the specific successful performance and the actual selection tendency.

[0052] Calculate the global gain parameter of the th cost management service , and the local gain parameter of the th cost management service in different industries according to the historical cost service record data. Among them, for the calculation process of the global gain parameter and the local gain parameter, it includes the following content:

[0053] Use the following formula to calculate the global gain parameter of the th cost management service : In the formula, is the th cost management service and the th cost management service under the collaboration of the th cost management service global gain parameter, is the success rate of the software project under the condition of including the th cost management service and the th cost management service ; the global gain parameter can evaluate the collaboration of the two services across the entire industry, that is, on the basis of one service, the improvement in the implicit success rate of the project brought by selecting the other service.

[0054] The local gain parameter of the th cost management service in the target industry is calculated using the following formula: In the formula, is the th cost management service and the th cost management service under the collaboration of the th cost management service local gain parameter, is the success rate of the software project under the condition of including the th cost management service and the th cost management service in the target industry; is the success rate of the software project under the condition of including the th cost management service in the target industry. The local gain parameter can evaluate the collaboration of the two services in a specific industry, that is, how the combination of the two services affects the success status of the software project in a specific industry.

[0055] It should be noted that although the software project implementation cannot be guaranteed solely by cost management services, as the implementation process of software projects is also affected by some other factors. However, the global gain parameter and local gain parameters can still measure the relative benefits of service combinations to a certain extent, reflect the marginal contribution of a certain service to the project success rate when used in combination, serve as a global basis for analyzing service adaptability, and represent the service benefit differences in specific scenarios, providing industry-specific service adaptability analysis.

[0056] Then, the global gain parameter and multiple local gain parameters are fused. That is, for the th cost management service with local gain parameters in different industries, considering the influence in the global state, the multiple local gain parameters of the th cost management service are weighted and corrected according to the global gain parameter to generate the th cost management service with collaborative gain parameters in different industries.

[0057] Finally, based on the local contribution parameter and collaborative gain parameter, the th cost management service with stage service collaboration parameters in different industries is calculated. That is, on the basis of considering the collaborative relationship between multiple services in the industry, and integrating the quantitative performance of the cost management service itself in the industry, i.e., the local contribution parameter, the product of the local contribution parameter and the collaborative gain parameter is used as the service collaboration parameter of the cost management service in the corresponding industry. Based on the multiple service collaboration parameters of the cost management service in each industry, the th cost management service forms a service local collaboration matrix for different industries, which represents the overall collaboration in the industry between each cost management service and the remaining cost management services with itself as the core, that is, on the basis of itself, the marginal benefit that can be brought by combining other cost management services.

[0058] In the above content, for step S3, during the process of analyzing the service popularity difference for each software project stage based on historical cost service record data, the popularity difference parameter of each cost management service in each software project stage in different industries is calculated, and a popularity difference distribution matrix for cost management services in each industry is generated, specifically including:

[0059] For the th cost management service in any software project stage, according to the th cost management service The selection frequency parameter within different industries is calculated using the following formula to obtain the th cost management service The selection difference degree between any two industries: In the formula, represents the th cost management service industry and industry The selection difference degree between them. and respectively represent the selection frequency parameters of the th cost management service in industry and industry The value range of the selection difference degree is from 0 to 1. If the selection difference degree of a certain cost management service approaches 0, it means that there is a relatively similar preference for this cost management service between the corresponding two industries. Otherwise, it means that there are significant differences in preferences between the two industries for this cost management service.

[0060] The mean value of multiple selection difference degrees of the th cost management service in the software project stage is obtained to get the selection difference parameter, which comprehensively represents the overall preference difference degree of the selection frequency of this cost management service in all industries. Then, according to the historical cost service record data, the th cost management service in the software project stage is calculated for its heat value, which can specifically be the frequency of selection of this cost management service in the software project stage. Finally, considering the heat situation of the cost management service itself and the performance difference in different industries, after correcting the heat value through the selection difference parameter, the heat difference parameter of the th cost management service in the software project stage is generated.

[0061] Among them, the heat difference parameter = heat value × (1 - selection difference degree). It means that when the selection difference degree of the cost management service is relatively high, that is, when there are significant differences in preferences in different industries, its heat value is greatly corrected, reflecting that it may not be applicable in some industries. On the contrary, it means that the cost management service has a relatively wide applicability. Finally, considering the preference differences of the service in each industry, based on the heat difference parameters of multiple cost management services in different software project stages, a heat difference distribution matrix of cost management services within each industry is constructed to reflect the adaptability changes of cost management services in different industries.

[0062] In the above content, for step S4, a plurality of candidate services are determined according to the phase service association matrix and the heat difference distribution matrix, and a plurality of target cost services are determined from the plurality of candidate services in combination with the service local collaboration matrix of the software project phase, specifically including:

[0063] According to the industry data and project phase data of the target user, determine the heat difference parameter of the target user for each cost management service from the heat difference distribution matrix, and determine the phase service association parameter of the target user for each cost management service from the phase service association matrix; screen out a plurality of candidate services from the plurality of cost management services provided by the cloud platform according to the heat difference parameter and the phase service association parameter.

[0064] Specifically, after determining the specific industry of the target user and the software project phase in which the software project requiring cost analysis is currently located according to the industry data and project phase data of the target user, according to the industry and the software project phase, determine the heat difference parameters corresponding to each of the plurality of cost management services in this industry and phase from the heat difference distribution matrix. Similarly, determine the phase service association parameters corresponding to each of the plurality of cost management services from the phase service association matrix, that is, the aforementioned global contribution parameters. The two respectively represent the preference situation of the cost management service in the specific industry and the performance status within the entire industry. Then, combine the two to determine the candidate services.

[0065] In this process, calculate the global matching degree of each cost management service according to the heat difference parameter and the phase service association parameter. Specifically, it can be the product of the two. Those skilled in the art can also determine the relative importance according to the actual tendency, such as quantitatively considering the industry adaptability and the phase adaptability within the overall range, and then perform weighted calculation on the heat difference parameter and the phase service association parameter to generate the global matching degree. The larger the global matching degree, the higher the industry demand and phase adaptability of the cost management service. Then, screen out the cost management services with a global matching degree greater than the preset matching threshold and record them as candidate services to determine the dual high-benefit services that meet the industry demand and project phase adaptability. Further calculate the adaptation parameter of each candidate service, and determine a plurality of target cost services from the plurality of candidate services according to the adaptation parameter.

[0066] In this process, for the calculation of the adaptation parameter of the candidate service and the determination of a plurality of target cost services from the plurality of candidate services according to the adaptation parameter, specifically including:

[0067] Determine the service local collaboration matrix corresponding to the target user according to the industry data and project phase data of the target user, record the candidate service corresponding to the maximum value of the global matching degree as the benchmark cost service, and write the benchmark cost service into the adaptation analysis list after removing it from the plurality of candidate services.

[0068] Specifically, after determining multiple candidate services, the relevance between each candidate service and other cost management services is further analyzed. First, a matching service partial collaboration matrix is determined according to the industry field and project stage corresponding to the target user, which contains candidate services suitable for analyzing a high degree of adaptability with the target user in the current scenario and the collaborative relevance with other services. The candidate service corresponding to the maximum global matching degree is first recorded as the benchmark cost service, that is, the core service for reference, which is the most representative service among the current multiple candidate services. Then, it is removed from the multiple candidate services and written into the adaptation analysis list, which is used to sort the multiple candidate services according to their adaptability.

[0069] Then, the multiple candidate services are analyzed through the service partial collaboration matrix and the benchmark cost service. According to the service partial collaboration matrix, the stage service collaboration parameter of each candidate service under the benchmark cost service is determined, and the multiple candidate services are sorted according to the stage service collaboration parameter and the benchmark cost service.

[0070] Specifically, for the remaining multiple candidate services, with the benchmark cost service as a reference, the collaborative association characteristics between the multiple candidate services and the benchmark cost service are determined through the service partial collaboration matrix, that is, the stage service collaboration parameter of each candidate service is determined. In this process, the stage service collaboration parameter between the benchmark cost service and each candidate service is first determined, and then the product of the stage service collaboration parameter and the global matching degree of the candidate service is taken as the sorting value of the candidate service. Specifically, the global matching degree comprehensively considers the adaptation situation between a single service and the target user, and the stage service collaboration parameter reflects the associated collaborative relationship between two services. Therefore, after determining the representative benchmark cost service, further combining the collaborative characteristics between the candidate service and the benchmark cost service, the sorting value of each candidate service is calculated to achieve the sorting of the remaining multiple candidate services.

[0071] The benchmark cost service is updated according to the candidate service ranked first, that is, the candidate service ranked first is used as the most representative service among the remaining multiple candidate services and is used as the new benchmark cost service. Then, the updated benchmark cost service is removed from the multiple candidate services and written into the adaptation analysis list. For the remaining multiple candidate services, the above operations are repeated until all candidate services are written into the adaptation analysis list. The writing process specifically considers the representativeness level among multiple candidate services. Therefore, the adaptation parameters of multiple candidate services can be determined according to the order in which the candidate services are written into the adaptation analysis list. For example, they are numbered in order, and the candidate services with adaptation parameters greater than the preset adaptation threshold are recorded as target cost services. The preset adaptation threshold can be reasonably set according to the recommended number of services required specifically, and no specific limitation is provided here.

[0072] Finally, based on the determined multiple target cost management services, an adaptation analysis result of the cost management service for the target user can be generated. The cloud platform can generate a precise cost management service recommendation plan for the target user based on the adaptation analysis result of the cost management service.

[0073] Please refer to Figure 2 , which shows a schematic structural diagram of an intelligent analysis system for cloud platform cost management services provided by one embodiment of the present invention. This system is specifically used to implement the above-mentioned intelligent analysis method for cloud platform cost management services, including:

[0074] A historical data acquisition module, configured to acquire historical cost service record data of the cloud platform for multiple users;

[0075] A stage service association analysis module, configured to perform stage association analysis on multiple cost management services provided by the cloud platform according to the historical cost service record data, calculate the selection frequency parameter and global contribution parameter of each cost management service for different software project stages, and construct a stage service association matrix between the software project stage and the cost management service;

[0076] A service local collaboration analysis module, configured to extract industry data of different users from the historical cost service record data, perform stage contribution analysis on multiple cost management services provided by the cloud platform according to the historical cost service record data, calculate the local contribution parameter and collaboration gain parameter of each cost management service in each software project stage within different industries, and construct a service local collaboration matrix for each software project stage within different industries;

[0077] A heat difference distribution analysis module, configured to perform service heat difference analysis on each software project stage according to the historical cost service record data, calculate the heat difference parameter of each cost management service in each software project stage within different industries, and generate a heat difference distribution matrix of cost management services within each industry;

[0078] A service adaptation analysis module, configured to determine multiple candidate services according to the stage service association matrix and the heat difference distribution matrix after determining the industry data and project stage data of the target user, determine multiple target cost management services from the multiple candidate services in combination with the service local collaboration matrix of the software project stage, and generate an adaptation analysis result of the cost management service for the target user.

[0079] It can be understood that the functions or modules included in the system provided by the embodiments of the present invention can be used to execute the methods described in the above method embodiments. The specific implementation can refer to the description of the above method embodiments. For the sake of brevity, it will not be repeated here.

[0080] The above are only specific embodiments of the present invention, enabling those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be obvious to those skilled in the art. The parts not described in detail in this specification belong to the prior art well-known to those skilled in the art.

Claims

1. A cloud platform cost management service intelligent analysis method, characterized in that: include: Obtain historical cost service record data of multiple users on the cloud platform, perform phase correlation analysis on multiple cost management services provided by the cloud platform based on the historical cost service record data, calculate the selection frequency parameters and global contribution parameters of each cost management service for different software project phases, and construct a phase service correlation matrix between software project phases and cost management services; Extract the industry data of different users from the historical cost service record data, conduct stage contribution analysis on multiple cost management services provided by the cloud platform based on the historical cost service record data, calculate the local contribution parameters and synergy gain parameters of each cost management service in each software project stage in different industries, and construct the local synergy matrix of services in different industries in each software project stage; According to the historical cost service record data, the service heat difference analysis is carried out for each software project stage, and the heat difference parameters of each cost management service in each software project stage in different industries are calculated to generate the heat difference distribution matrix of cost management services in each industry; After determining the industry data and project stage data of the target user, multiple candidate services are determined based on the stage service association matrix and the heat difference distribution matrix. Combined with the service local collaboration matrix of the software project stage, multiple target cost services are determined from multiple candidate services to generate the cost management service adaptation analysis results for the target user.

2. According to claim 1, a cloud platform cost management service intelligent analysis method is characterized in that: Calculate the local contribution parameters and synergy gain parameters of each cost management service in each software project stage in different industries, and construct the local synergy matrix of services in different industries in each software project stage, including: For any software project phase Cost management services , calculated based on historical cost service record data Cost management services The selection frequency parameters and success contribution parameters in different industries are used to modify the success contribution parameters based on the selection frequency parameters to generate the first Cost management services Local contribution parameters within different industries; Calculate the cost based on historical cost service record data Cost management services The global gain parameter, and Cost management services The local gain parameters in different industries are adjusted according to the global gain parameters. Cost management services The multiple local gain parameters are modified to generate the Cost management services The synergy gain parameters in different industries are calculated based on the local contribution parameters and synergy gain parameters. Cost management services The service coordination parameters in different stages of the industry are constructed to obtain the Cost management services About the local synergy matrix of services within different industries.

3. According to claim 2, a cloud platform cost management service intelligent analysis method is characterized in that: For global gain parameters and local gain parameters, it also includes: Use the following formula to calculate the Cost management services The global gain parameter of : In the formula, For the Cost management services and Cost management services Collaborative Cost management services The global gain parameter, To include Cost management services and Cost management services The success rate of software projects under the conditions of To include Cost management services The success rate of software projects under the conditions of Use the following formula to calculate the Cost management services The local gain parameters in the target industry: In the formula, The first in the target industry Cost management services and Cost management services Collaborative Cost management services The local gain parameter, For the target industry, including Cost management services and Cost management services The success rate of software projects under the conditions of For the target industry, including Cost management services The success rate of software projects under certain conditions.

4. According to claim 3, a cloud platform cost management service intelligent analysis method is characterized in that: According to the phase service association matrix and the heat difference distribution matrix, multiple candidate services are determined. Combined with the service local coordination matrix of the software project phase, multiple target cost services are determined from multiple candidate services, including: According to the target user's industry data and project stage data, determine the target user's heat difference parameters for each cost management service from the heat difference distribution matrix, and determine the target user's stage service association parameters for each cost management service from the stage service association matrix; According to the heat difference parameters and the stage service association parameters, multiple candidate services are screened out from the multiple cost management services provided by the cloud platform, including calculating the global matching degree of each cost management service according to the heat difference parameters and the stage service association parameters, screening out the cost management services with a global matching degree greater than a preset matching threshold and recording them as candidate services, determining the adaptation parameters of each candidate service, and determining multiple target cost services from the multiple candidate services according to the adaptation parameters.

5. According to claim 4, a cloud platform cost management service intelligent analysis method is characterized in that: Determine the adaptation parameters of each candidate service, and determine multiple target cost services from multiple candidate services according to the adaptation parameters, including: Determine the local service coordination matrix corresponding to the target user based on the target user's industry data and project stage data, record the candidate service corresponding to the maximum global matching degree as the benchmark cost service, remove the benchmark cost service from multiple candidate services and write it into the adaptation analysis list; Analyze multiple candidate services through the service local coordination matrix and the benchmark cost service, determine the stage service coordination parameter of each candidate service under the benchmark cost service according to the service local coordination matrix, sort the multiple candidate services according to the stage service coordination parameter and the benchmark cost service, including weighting the adaptation parameter by the stage service coordination parameter to generate a sorting value, and sort the multiple candidate services based on the sorting value; The benchmark cost service is updated according to the candidate service ranked first, and the updated benchmark cost service is removed from the multiple candidate services and written into the adaptation analysis list. The above operation is repeated until all candidate services are written into the adaptation analysis list, and the adaptation parameters of the multiple candidate services are determined according to the order in which the candidate services are written into the adaptation analysis list. The candidate service whose adaptation parameter is greater than the preset adaptation threshold is recorded as the target cost service.

6. According to claim 2, a cloud platform cost management service intelligent analysis method is characterized in that: Calculate the heat difference parameters of each cost management service in each software project stage in different industries, and generate the heat difference distribution matrix of cost management services in each industry, including: For any software project phase Cost management services , according to Cost management services The selection frequency parameters in different industries are calculated using the following formula Cost management services The degree of choice difference between any two industries: In the formula, Indicates Cost management services industry and Industry The difference in choice between , Respectively represent Cost management services In the industry and Industry The selection frequency parameter within; The first Cost management services The average value of multiple selection differences in the software project stage is obtained to obtain the selection difference parameter, and the first Cost management services The heat value in the software project stage is modified by selecting the difference parameter to generate the first heat value in the software project stage. Cost management services According to the heat difference parameters of multiple cost management services in different software project stages, a heat difference distribution matrix of cost management services in each industry is constructed.

7. A cloud platform cost management service intelligent analysis system, characterized in that: The system is used to implement a cloud platform cost management service intelligent analysis method as described in any one of claims 1 to 6, including: The historical data acquisition module is used to obtain the historical cost service record data of multiple users on the cloud platform; The phase service correlation analysis module is used to perform phase correlation analysis on multiple cost management services provided by the cloud platform based on historical cost service record data, calculate the selection frequency parameters and global contribution parameters of each cost management service for different software project phases, and construct a phase service correlation matrix between software project phases and cost management services; The service local collaboration analysis module is used to extract the industry data of different users from the historical cost service record data, conduct stage contribution analysis on multiple cost management services provided by the cloud platform based on the historical cost service record data, calculate the local contribution parameters and collaborative gain parameters of each cost management service in each software project stage in different industries, and construct a service local collaboration matrix for different industries in each software project stage; The heat difference distribution analysis module is used to perform service heat difference analysis on each software project stage based on historical cost service record data, calculate the heat difference parameters of each cost management service in each software project stage in different industries, and generate a heat difference distribution matrix for cost management services in each industry; The service adaptation analysis module is used to determine multiple candidate services based on the stage service association matrix and the heat difference distribution matrix after determining the industry data and project stage data of the target user, and to determine multiple target cost services from multiple candidate services in combination with the service local collaboration matrix of the software project stage to generate the cost management service adaptation analysis results for the target user.

Images