Cost management method and device, electronic equipment and storage medium

Abstract

The invention provides a cost management method and device, electronic equipment and a storage medium, and the method comprises the steps: carrying out the unified fusion of multiple sources, such as cloud bill information, budget information, monitoring data and the like, carrying out the prediction and anomaly detection of a cost trend based on the multi-source data through an AI large model, and obtaining a corresponding cost detection result, the cost detection result is compared with budget data, hyperbranched early warning is generated in real time, the cost anomaly detection efficiency is improved, and stable operation of data processing services is guaranteed.

Description

Technical Field

[0001] This invention relates to the field of machine learning technology, and in particular to a cost management method, apparatus, electronic device, and storage medium. Background Technology

[0002] Against the backdrop of digital transformation and intensified market competition, enterprise cost data is scattered across multiple sources, including invoicing, budgeting, monitoring, and finance systems. This results in issues such as inconsistent formats, data redundancy, and discrepancies in data definitions. Existing technologies largely rely on manual data integration, analysis, and processing. Traditional manual accounting methods are inefficient, prone to errors, and ill-suited to the demands of real-time cost control. Summary of the Invention

[0003] In view of this, embodiments of the present invention provide a cost management method, apparatus, electronic device, and storage medium to improve cost management efficiency.

[0004] According to one aspect of the present invention, a cost management method is provided, the method comprising: Acquire multi-source cost data, including cloud billing data, budget data, and monitoring data; The multi-source cost data is input into the AI ​​big model so that the AI ​​big model outputs cost trend prediction results and anomaly detection results based on the multi-source cost data; By comparing the cost trend forecast results with the budget data, an alert is triggered if the cost trend forecast results exceed the budget data.

[0005] In one possible embodiment, the method further includes: The multi-source cost data is cleaned and filtered to obtain filtered multi-source cost data; The multi-source cost data is converted to a unified format based on the target format.

[0006] In one possible embodiment, the AI ​​big model outputs cost trend prediction results based on the multi-source cost data, including: The AI ​​big data model outputs cost trend prediction results for various cost types based on the multi-source cost data. The cost types include at least user groups and products. The cost trend prediction results include cost trends and cost risk scores.

[0007] In one possible embodiment, the method further includes: When an alert is triggered, the AI ​​big data model outputs optimization suggestions based on the multi-source cost data. These optimization suggestions include instance scaling up / down and / or budget adjustments.

[0008] In one possible embodiment, the method further includes: The cost trend prediction results and optimization suggestions are displayed using a preset display format.

[0009] According to another aspect of the present invention, a cost management device is provided, the device comprising: The acquisition module is used to acquire multi-source cost data, wherein the multi-source cost data includes cloud billing data, budget data, and monitoring data; The prediction module is used to input the multi-source cost data into the AI ​​big model, so that the AI ​​big model outputs cost trend prediction results and anomaly detection results based on the multi-source cost data; The comparison module is used to compare the cost trend prediction result with the budget data, and to trigger an early warning if the cost trend prediction result exceeds the budget data.

[0010] In one possible embodiment, the device further includes: The filtering module is used to clean and filter the multi-source cost data to obtain filtered multi-source cost data. The multi-source cost data is converted to a unified format based on the target format.

[0011] In one possible embodiment, the AI ​​big model outputs cost trend prediction results based on the multi-source cost data, including: The AI ​​big data model outputs cost trend prediction results for various cost types based on the multi-source cost data. The cost types include at least user groups and products. The cost trend prediction results include cost trends and cost risk scores. The device further includes: The optimization module is used to output optimization suggestions based on the multi-source cost data through the AI ​​big model when an early warning is triggered. The optimization suggestions include instance scaling up or down and / or budget adjustment. The display module is used to display the cost trend prediction results and the optimization suggestions in a preset display format.

[0012] According to another aspect of the present invention, an electronic device is provided, comprising: Processor; and Stored program memory, The program includes instructions that, when executed by the processor, cause the processor to perform any of the cost management methods described above.

[0013] According to another aspect of the present invention, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause a computer to perform any of the cost management methods described above.

[0014] The one or more technical solutions provided in this embodiment of the invention integrate multiple sources such as cloud billing information, budget information, and monitoring data, and use AI big data models to predict cost trends and detect anomalies based on multi-source data to obtain corresponding cost detection results. The cost detection results are compared with budget data to generate overspending warnings in real time, thereby improving the efficiency of cost anomaly detection and ensuring the stable operation of data processing services. Attached Figure Description

[0015] Further details, features, and advantages of the invention are disclosed in the following description of exemplary embodiments in conjunction with the accompanying drawings, in which: Figure 1 A flowchart illustrating the cost management method provided by the present invention; Figure 2 Another flowchart illustrating the cost management method provided by the present invention; Figure 3 This is a schematic diagram of a system architecture for implementing the cost management method provided by the present invention; Figure 4 A schematic diagram of the cost management device provided by the present invention; Figure 5 A structural block diagram of an exemplary electronic device that can be used to implement embodiments of the present invention is shown. Detailed Implementation

[0016] Embodiments of the present invention will now be described in more detail with reference to the accompanying drawings. While some embodiments of the invention are shown in the drawings, it should be understood that the invention can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the invention. It should be understood that the accompanying drawings and embodiments are for illustrative purposes only and are not intended to limit the scope of protection of the invention.

[0017] It should be understood that the various steps described in the method embodiments of the present invention may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present invention is not limited in this respect.

[0018] The term "comprising" and its variations as used herein are open-ended, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the following description. It should be noted that the concepts of "first", "second", etc., mentioned in this invention are used only to distinguish different devices, modules, or units, and are not intended to limit the order of functions performed by these devices, modules, or units or their interdependencies.

[0019] It should be noted that the terms "a" and "a plurality of" used in this invention are illustrative rather than restrictive. Those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0020] The names of the messages or information exchanged between the multiple devices in the embodiments of the present invention are for illustrative purposes only and are not intended to limit the scope of these messages or information.

[0021] The existing technology has the following drawbacks: Lack of unified integration: The existing system fails to integrate data from billing, budgeting, monitoring, and financial systems, making it impossible for enterprise managers to have a holistic grasp of cost changes.

[0022] Delayed early warning: Businesses typically only discover budget overruns after bill settlement, lacking the ability to forecast and dynamically adjust in real time.

[0023] Lack of intelligent analysis: Most existing methods rely on fixed rule thresholds and cannot be dynamically adjusted according to complex business scenarios (such as resource consumption trends in different departments).

[0024] Lack of optimization suggestions: Even when alerts are generated, there is a lack of cost optimization decision support based on historical data and intelligent models.

[0025] Based on this, the present invention provides a cost management method, apparatus, electronic device, and storage medium. The cost management method provided by the present invention can be applied to any electronic device with cost management function, such as a server, computer, or mobile terminal. The following describes the solution of the present invention with reference to the accompanying drawings: Figure 1 A flowchart illustrating the cost management method provided by the present invention may include the following steps: S101. Obtain multi-source cost data, wherein the multi-source cost data includes cloud billing data, budget data, and monitoring data; S102. Input the multi-source cost data into the AI ​​big model so that the AI ​​big model outputs cost trend prediction results and anomaly detection results based on the multi-source cost data; S103. Compare the cost trend prediction result with the budget data, and trigger an early warning if the cost trend prediction result exceeds the budget data.

[0026] By applying the embodiments of the present invention, cloud billing information, budget information, monitoring data and other multiple sources are integrated in a unified manner, and an AI big data model is used to predict cost trends and detect anomalies based on multi-source data to obtain corresponding cost detection results. The cost detection results are compared with budget data to generate overspending warnings in real time, thereby improving the efficiency of cost anomaly detection and ensuring the stable operation of data processing business.

[0027] The following provides an exemplary description of S101-S103: Enterprises typically monitor cloud service provider billing data, corporate financial budget information, monitoring platform performance metrics, and departmental business needs data separately through different systems. This means that the above data is managed independently through billing, budgeting, monitoring, and financial systems. This invention integrates and manages the data from these various systems. In one possible embodiment, billing data, budgeting data, and monitoring data can be obtained from each system and processed uniformly. Since different systems may collect and manage data in different ways, corresponding data collection methods can be preset for each system.

[0028] Billing systems typically record transaction details such as expenses, income, and expense reports. Data can be retrieved through API calls, backend data export, or direct database connections. For example, most mainstream commercial systems provide official APIs, allowing data retrieval via HTTP / HTTPS requests, supporting real-time synchronization or scheduled retrieval. Bank statements, for instance, can be retrieved via a direct bank-enterprise API, often in JSON / XML format. Systems without open APIs can export data through the backend interface, typically in Excel, CSV, or PDF formats, which can be automatically downloaded periodically using scripts. For enterprise-developed billing systems with open database permissions, queries can be performed directly using SQL statements, allowing access to core tables such as transaction and account tables.

[0029] Monitoring systems can include server monitoring, business monitoring, and financial metric monitoring, with data primarily consisting of real-time metrics and log data. For example, professional monitoring tools such as Prometheus, Zabbix, and Grafana all provide APIs. Prometheus, for instance, exposes metric data via an HTTP API, allowing users to retrieve data such as server CPU utilization and financial system response time; Grafana supports exporting monitoring dashboard data as JSON / CSV. Log-based monitoring data can be collected using tools like Flume and Logstash, synchronized to a big data platform, and subsequently queried and analyzed from the platform. Monitoring system data can also be directly collected from a database.

[0030] Data collection for budget and financial systems can be done using methods similar to those for billing systems, which will not be elaborated here.

[0031] The aforementioned multi-source data typically comes in various formats. To improve subsequent data processing efficiency, a unified format conversion can be performed on each data source. In one possible embodiment, the method further includes: S201. Clean and filter the multi-source cost data to obtain filtered multi-source cost data; S202. Based on the target format, the multi-source cost data is converted to obtain multi-source cost data in a unified format.

[0032] The aforementioned data cleaning and filtering can include deduplication, filling in missing values, removing / correcting outliers, and dimension alignment. The filtered data can then undergo format conversion. Format conversion can include numerical standardization: unifying monetary units and decimal places, for example, converting 5000 yuan and 0.5 million yuan to 5000.00 yuan. Text standardization: removing spaces, newlines, and special characters from fields. Date standardization: converting timestamps to date formats, such as converting 1699996800 to 2023-11-15. Data can also be converted to JSON or other structured formats for storage.

[0033] The AI ​​big data model can perform cost trend prediction and anomaly detection based on the above multi-source data. This AI big data model can be an LLM (Limited Linear Model) that includes time-series modeling and anomaly detection model functionalities. In one possible embodiment, multi-source data can be input into the AI ​​big data model, and preset prompts can be output. These preset prompts can include the content to be output, the output data format, etc. The AI ​​big data model can output target content based on the multi-source data according to the preset prompts.

[0034] The target content that the AI ​​big model needs to output can be set according to the actual application scenario. As one possible implementation method, the AI ​​big model can be required to output cost trend prediction results of multiple cost types based on the multi-source cost data. The cost types include at least user groups and products. The cost trend prediction results include cost trends and cost risk scores.

[0035] Guided by preset prompts, the AI ​​big data model can output the cost distribution and anomaly detection results of cost data across departments, projects, and products. Specifically, the anomaly detection results can be cost risk scores, which are used to identify the degree of risk of cost overruns.

[0036] The system compares the output of a large AI model with a budget threshold. If the output exceeds the budget threshold, an alert is triggered. This budget threshold can be pre-set based on the actual application scenario and may include cost budgets for multiple time periods or points in time. When an alert is triggered, the alert information can be synchronized in real time, such as via email, messaging systems, or monitoring dashboards. This alert information may include the cost trend prediction result, the budget threshold, and the time and amount of cost exceeding the budget threshold.

[0037] In one possible embodiment, the method further includes: upon triggering an alert, outputting optimization suggestions based on the multi-source cost data through the AI ​​big model, the optimization suggestions including instance scaling up / down and / or budget adjustment.

[0038] When an alert is triggered, the AI ​​big data model can automatically perform a step-by-step analysis based on multi-source data and provide optimization suggestions. It can also output a second prompt word to the AI ​​big data model. This second prompt word can include the requirements for outputting optimization suggestions and can also limit the types of optimizations included in the optimization suggestions, such as taking idle instances offline, adjusting storage packages, cross-regional resource scheduling, and dynamic budget adjustment.

[0039] The AI ​​big model can output corresponding optimization suggestions, which may include the storage location of instances that can be taken offline, the types of storage package changes and the corresponding storage amount, budget adjustment amount, resource expansion and contraction capacity, etc. The resource expansion and contraction capacity may be the increase or decrease of resources such as CPU and storage control, as well as the corresponding resource changes, etc.

[0040] In one possible embodiment, the cost trend prediction results and optimization suggestions can be displayed using a preset display format. For example, the cost trend prediction results, anomaly detection results, and optimization suggestions can be displayed through charts, reports, API interface data, etc.

[0041] like Figure 2 As shown, Figure 2 A flowchart illustrating a cost management method provided in an embodiment of the present invention may include: S1: Data collection, including collecting cloud service provider billing information, enterprise budget information, monitoring platform indicators, and financial system data, and storing them in a unified resource cost database; S2: Data preprocessing, which involves preprocessing the collected data, including deduplication, standardization, and dimension alignment; S3: Cost Prediction: Based on the AI ​​big data model, predict future resource consumption and corresponding costs to obtain a cost trend curve; S4: Budget Comparison: Compare the forecast results with the preset budget threshold. If the forecast cost will exceed the budget, an overspending warning will be generated. S5: Optimization suggestions: Based on historical costs, resource utilization, and financial strategies, optimization suggestions are generated using AI models; S6: Visual output, providing early warnings and optimization suggestions through visual dashboards, message notifications, and other means.

[0042] Figure 3 A system architecture diagram for implementing the cost management method provided in the embodiments of the present invention may include the following modules: Data Acquisition Module: Inputs include cloud service provider billing data, enterprise financial budget information, monitoring platform performance indicators, and departmental business requirement data. It is used to standardize, clean, and normalize multi-source heterogeneous data to output a resource cost database in a unified format.

[0043] Cost Analysis and Modeling Module: The input is a resource cost database, used to predict cost trends based on large AI models (such as time series forecasting models and anomaly detection models); it analyzes cost distribution across departments, projects, and products. Outputs prediction results and cost risk scores.

[0044] Budget Comparison and Early Warning Module: Inputs include the above forecast results and the company's budget plan. It compares the forecast values ​​with budget thresholds and triggers an early warning when the trend exceeds the budget. Real-time early warning information is output (via email, messaging system, and monitoring dashboard).

[0045] The optimization suggestion generation module takes historical bills, resource utilization, and financial rules as input and provides optimization suggestions based on a large AI model, such as decommissioning idle instances, adjusting storage packages, cross-regional resource scheduling, and dynamic budget adjustments. It can output a report of specific, actionable optimization suggestions.

[0046] Visualization and Interface Module: The input is the output data of each module, which is used to generate visual dashboards. It supports API / SDK integration with existing enterprise systems. Specific outputs can include charts, reports, API interface data, etc.

[0047] This invention utilizes embodiments to integrate multi-source heterogeneous data, such as invoices, financial budgets, and monitoring indicators, to construct a unified resource cost database; it features cost trend prediction and anomaly detection based on AI-powered large-scale models; a real-time budget comparison and early warning mechanism, distinct from traditional post-invoice analysis; and intelligent optimization suggestions for automated decision-making. Its pluggable architecture design supports multi-cloud and multi-department expansion.

[0048] Based on the same inventive concept, according to another aspect of the present invention, a cost management device is provided, such as... Figure 4 As shown, the device 400 may include: The acquisition module 401 is used to acquire multi-source cost data, wherein the multi-source cost data includes cloud billing data, budget data and monitoring data; Prediction module 402 is used to input the multi-source cost data into the AI ​​big model, so that the AI ​​big model outputs cost trend prediction results and anomaly detection results based on the multi-source cost data; The comparison module 403 is used to compare the cost trend prediction result with the budget data, and to trigger an early warning if the cost trend prediction result exceeds the budget data.

[0049] In one possible embodiment, the device further includes: The filtering module is used to clean and filter the multi-source cost data to obtain filtered multi-source cost data. The multi-source cost data is converted to a unified format based on the target format.

[0050] In one possible embodiment, the AI ​​big model outputs cost trend prediction results based on the multi-source cost data, including: The AI ​​big data model outputs cost trend prediction results for various cost types based on the multi-source cost data. The cost types include at least user groups and products. The cost trend prediction results include cost trends and cost risk scores. The device further includes: The optimization module is used to output optimization suggestions based on the multi-source cost data through the AI ​​big model when an early warning is triggered. The optimization suggestions include instance scaling up or down and / or budget adjustment. The display module is used to display the cost trend prediction results and the optimization suggestions in a preset display format.

[0051] The collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in this invention comply with relevant laws and regulations and do not violate public order and good morals.

[0052] An exemplary embodiment of the present invention also provides an electronic device, including: at least one processor; and a memory communicatively connected to the at least one processor. The memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to cause the electronic device to perform a method according to an embodiment of the present invention.

[0053] An exemplary embodiment of the present invention also provides a non-transitory computer-readable storage medium storing a computer program, wherein the computer program, when executed by a computer's processor, is used to cause the computer to perform a method according to an embodiment of the present invention.

[0054] An exemplary embodiment of the present invention also provides a computer program product, including a computer program, wherein, when executed by a computer's processor, the computer program is used to cause the computer to perform a method according to an embodiment of the present invention.

[0055] refer to Figure 5 The present invention will now be described in the form of a structural block diagram of an electronic device 500 that can serve as a server or client of the present invention, which is an example of a hardware device that can be applied to various aspects of the present invention. The electronic device is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0056] like Figure 5 As shown, the electronic device 500 includes a computing unit 501, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 502 or a computer program loaded from a storage unit 508 into a random access memory (RAM) 503. The RAM 503 may also store various programs and data required for the operation of the electronic device 500. The computing unit 501, ROM 502, and RAM 503 are interconnected via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0057] Multiple components in electronic device 500 are connected to I / O interface 505, including: input unit 506, output unit 507, storage unit 508, and communication unit 509. Input unit 506 can be any type of device capable of inputting information to electronic device 500. Input unit 506 can receive input digital or character information and generate key signal inputs related to user settings and / or function control of electronic device. Output unit 507 can be any type of device capable of presenting information and may include, but is not limited to, a display, speaker, video / audio output terminal, vibrator, and / or printer. Storage unit 508 may include, but is not limited to, disk and optical disk. Communication unit 509 allows electronic device 500 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks, and may include, but is not limited to, modems, network cards, infrared communication devices, wireless communication transceivers, and / or chipsets, such as Bluetooth™ devices, WiFi devices, WiMax devices, cellular communication devices, and / or the like.

[0058] The computing unit 501 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 501 performs the various methods and processes described above. For example, in some embodiments, any of the cost management methods described above can be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 508. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 500 via ROM 502 and / or communication unit 509. In some embodiments, the computing unit 501 can be configured to perform any of the cost management methods described above by any other suitable means (e.g., by means of firmware).

[0059] The program code used to implement the methods of the present invention can be written in any combination of one or more programming languages. This program code can be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing device, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code can be executed entirely on the machine, partially on the machine, as a standalone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0060] In the context of this invention, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media can include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0061] As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, device, and / or apparatus (e.g., disk, optical disk, memory, programmable logic device (PLD)) for providing machine instructions and / or data to a programmable processor, including machine-readable media that receive machine instructions as machine-readable signals. The term "machine-readable signal" refers to any signal for providing machine instructions and / or data to a programmable processor.

[0062] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0063] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0064] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other.

Claims

1. A cost management method, characterized in that, The method includes: Acquire multi-source cost data, including cloud billing data, budget data, and monitoring data; The multi-source cost data is input into the AI ​​big model so that the AI ​​big model outputs cost trend prediction results and anomaly detection results based on the multi-source cost data; By comparing the cost trend forecast results with the budget data, an alert is triggered if the cost trend forecast results exceed the budget data.

2. The method according to claim 1, characterized in that, The method further includes: The multi-source cost data is cleaned and filtered to obtain filtered multi-source cost data; The multi-source cost data is converted to a unified format based on the target format.

3. The method according to claim 1, characterized in that, The AI ​​big data model outputs cost trend prediction results based on the multi-source cost data, including: The AI ​​big data model outputs cost trend prediction results for various cost types based on the multi-source cost data. The cost types include at least user groups and products. The cost trend prediction results include cost trends and cost risk scores.

4. The method according to claim 1, characterized in that, The method further includes: When an alert is triggered, the AI ​​big data model outputs optimization suggestions based on the multi-source cost data. These optimization suggestions include instance scaling up / down and / or budget adjustments.

5. The method according to claim 4, characterized in that, The method further includes: The cost trend prediction results and optimization suggestions are displayed using a preset display format.

6. A cost management device, characterized in that, The device includes: The acquisition module is used to acquire multi-source cost data, wherein the multi-source cost data includes cloud billing data, budget data, and monitoring data; The prediction module is used to input the multi-source cost data into the AI ​​big model, so that the AI ​​big model outputs cost trend prediction results and anomaly detection results based on the multi-source cost data; The comparison module is used to compare the cost trend prediction result with the budget data, and to trigger an early warning if the cost trend prediction result exceeds the budget data.

7. The apparatus according to claim 6, characterized in that, The device further includes: The filtering module is used to clean and filter the multi-source cost data to obtain filtered multi-source cost data. The multi-source cost data is converted to a unified format based on the target format.

8. The apparatus according to claim 7, characterized in that, The AI ​​big data model outputs cost trend prediction results based on the multi-source cost data, including: The AI ​​big data model outputs cost trend prediction results for various cost types based on the multi-source cost data. The cost types include at least user groups and products. The cost trend prediction results include cost trends and cost risk scores. The device further includes: The optimization module is used to output optimization suggestions based on the multi-source cost data through the AI ​​big model when an early warning is triggered. The optimization suggestions include instance scaling up or down and / or budget adjustment. The display module is used to display the cost trend prediction results and the optimization suggestions in a preset display format.

9. An electronic device, comprising: processor; as well as Stored program memory, The program includes instructions that, when executed by the processor, cause the processor to perform the method according to any one of claims 1-5.

10. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-5.

Images