Energy consumption analysis report generation method and device, equipment, medium and program product

Abstract

The embodiment of the invention discloses an energy consumption analysis report generation method and device, equipment, a medium and a program product. The method comprises the following steps: in response to a received energy consumption analysis request sent by a user terminal, obtaining subject portrait data of a target energy consumption subject corresponding to the energy consumption analysis request, and obtaining energy consumption feature data of the target energy consumption subject; performing data analysis processing on the energy consumption analysis request, the subject portrait data and the energy consumption characteristic data to obtain an energy consumption analysis result and interpretation information corresponding to the energy consumption analysis result; performing fusion processing on the energy consumption analysis result and the interpretation information to generate energy consumption analysis report data; and sending the energy consumption analysis report data to the user terminal, so that the user terminal displays the energy consumption analysis report data based on the energy consumption analysis report data. According to the embodiment of the invention, the generation efficiency of the energy consumption analysis report and the reliability of the report content can be improved.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and in particular to a method, apparatus, device, medium, and program product for generating energy analysis reports. Background Technology

[0002] With the increasing popularity of smart home devices, home energy management systems face the challenge of processing multi-source, heterogeneous data in a unified manner. Because different brands and types of devices use their own independent energy consumption data collection formats, the lack of data format consistency between devices makes cross-device data fusion and unified analysis difficult.

[0003] Electricity analysis systems in related technologies often rely on batch processing, lacking real-time monitoring and dynamic report generation capabilities. In high-concurrency scenarios, data processing delays can easily occur, potentially leading to low efficiency in report generation and low reliability of report content. Summary of the Invention

[0004] This application provides a method, apparatus, device, medium, and program product for generating energy consumption analysis reports, which can improve the generation efficiency and reliability of report content. The above technical solution is as follows: In a first aspect, embodiments of this application provide a method for generating an energy consumption analysis report, applied to a cloud device, including: In response to receiving an energy consumption analysis request from a user terminal, the system obtains the subject profile data of the target energy-consuming subject corresponding to the energy consumption analysis request, as well as the energy consumption characteristic data of the target energy-consuming subject; Data analysis and processing are performed on energy consumption analysis requests, subject profile data, and energy consumption characteristic data to obtain energy consumption analysis results and corresponding explanatory information. The energy consumption analysis results and explanatory information are integrated and processed to generate energy consumption analysis report data; The energy consumption analysis report data is sent to the user terminal so that the user terminal can display the data based on the energy consumption analysis report data.

[0005] In one possible implementation, the cloud device deploys multiple pre-defined intelligent agents, including a scheduling agent and multiple working agents, to perform data analysis processing on energy consumption analysis requests, subject profile data, and energy consumption characteristic data, obtaining energy consumption analysis results and corresponding explanatory information, including: Through a pre-set scheduling agent, task data generation and processing are performed based on energy consumption analysis requests, subject profile data, and energy consumption characteristic data to obtain multiple task data corresponding to multiple working agents; Energy consumption analysis results are obtained by performing task execution processing based on multiple task data by multiple working intelligent agents. The result interpretation agent performs interpretation generation processing based on subject profile data, energy consumption feature data, and energy consumption analysis results to generate interpretation information corresponding to the energy consumption analysis results. The interpretation information is used to provide interpretive output related to the energy consumption analysis results.

[0006] In one possible implementation, a pre-defined scheduling agent performs task data generation processing based on energy consumption analysis requests, subject profile data, and energy consumption characteristic data to obtain multiple task data corresponding to the working agent, including: The system loads the multi-agent registration list through a pre-defined scheduling agent and obtains multiple work attribute information corresponding to multiple working agents. The pre-defined scheduling agent generates the analysis task objective based on the energy consumption analysis request, subject profile data, and energy consumption characteristic data. By scheduling intelligent agents to generate and process task data based on the analysis of task objectives and multiple work attribute information, multiple task data corresponding to the working intelligent agents are obtained.

[0007] In one possible implementation, the multiple working intelligent agents include a device analysis intelligent agent and a profile analysis intelligent agent, and the multiple task data include device analysis task data corresponding to the device analysis intelligent agent and profile analysis data corresponding to the profile analysis intelligent agent. By having multiple working agents perform task execution processing based on multiple task data, energy consumption analysis results are obtained, including: The device analysis agent performs device energy consumption analysis based on the corresponding device analysis task data and the preset device knowledge base to obtain device analysis results. The device analysis task data includes at least one of the following: device function information, device energy consumption data, and device status log. The profiling analysis agent performs profiling reasoning based on the corresponding profiling analysis task data and the preset profiling knowledge base to obtain profiling analysis results. The profiling analysis task data includes at least one of the following: equipment environmental parameters, user historical operation information, and energy price parameters. The energy consumption analysis results are determined based on the equipment analysis results and the profile analysis results.

[0008] In one possible implementation, the result interpretation agent performs interpretation generation processing based on the subject profile data, energy consumption feature data, and energy consumption analysis results to generate interpretation information corresponding to the energy consumption analysis results, including: The result interpretation agent performs interpretation generation processing based on a preset interpretation knowledge base, subject profile data, energy consumption feature data and energy consumption analysis results, and generates interpretation information corresponding to the energy consumption analysis results; The interpretation knowledge base includes at least one of the following: case knowledge, rule knowledge, template knowledge, strategy knowledge, and security constraint knowledge used to interpret the generated information.

[0009] In one possible implementation, the energy consumption analysis results and explanatory information are fused together to generate energy consumption analysis report data, including: The pre-set scheduling agent organizes energy consumption analysis results and interpretation information in a structured manner to generate energy consumption description information and energy consumption suggestion information. By scheduling intelligent agents to generate display content based on preset report templates, energy consumption description information, and energy consumption suggestion information, graphical element information is obtained; By scheduling intelligent agents based on graphical element information and preset rendering templates, corresponding energy consumption analysis report data is generated.

[0010] In one possible implementation, the multiple agents also include an optimization agent, and after sending the energy consumption analysis report data to the user terminal, the method further includes: Receive user feedback information sent from user terminals; By optimizing the energy consumption analysis report data based on user feedback information using an intelligent agent, optimized energy consumption analysis report data is obtained. The optimized energy consumption analysis report data is sent to the user terminal, so that the user terminal can render and generate an optimized energy consumption analysis report for presentation based on the optimized energy consumption analysis report data.

[0011] In one possible implementation, acquiring the energy consumption characteristic data of the target energy-consuming entity includes: Obtain the list of energy-consuming devices for the target energy-consuming entity corresponding to the energy consumption analysis request. The list of energy-consuming devices includes at least one energy-consuming device corresponding to the target energy-consuming entity. Obtain the structured operation data corresponding to each energy-consuming device based on the energy-consuming equipment list; The structured operational data is processed to generate energy consumption characteristic data of the target energy-consuming entity.

[0012] In one possible implementation, structured operational data for each energy-consuming device is obtained from a list of energy-consuming devices, including: Based on the list of energy-consuming equipment, obtain the structured operation data corresponding to each energy-consuming equipment from the preset data platform; The pre-set data platform is used to receive the raw operating data of each energy-consuming device, and to process the raw operating data of each energy-consuming device to generate and store the structured operating data corresponding to each energy-consuming device.

[0013] Secondly, embodiments of this application provide an energy consumption analysis report display system, including a cloud device and a user terminal; The user terminal is used to send energy consumption analysis requests to cloud devices; The cloud-based device is used to respond to a user terminal's energy consumption analysis request, obtain the target energy-consuming entity's profile data corresponding to the energy consumption analysis request, and obtain the target energy-consuming entity's energy consumption characteristic data; perform data analysis and processing on the energy consumption analysis request, entity profile data, and energy consumption characteristic data to obtain energy consumption analysis results and corresponding explanatory information; perform fusion processing on the energy consumption analysis results and explanatory information to generate energy consumption analysis report data; and send the energy consumption analysis report data to the user terminal. The user terminal is also used to receive energy consumption analysis report data returned by cloud devices, and to perform rendering processing based on the energy consumption analysis report data to generate a display page to present the energy consumption analysis report data.

[0014] Thirdly, embodiments of this application provide an energy consumption analysis report generation device, applied to cloud devices, including: The acquisition module is used to respond to receiving an energy consumption analysis request sent by a user terminal, acquire the subject profile data of the target energy consumption subject corresponding to the energy consumption analysis request, and acquire the energy consumption characteristic data of the target energy consumption subject; The processing module is used to perform data analysis and processing on energy consumption analysis requests, subject profile data and energy consumption characteristic data to obtain energy consumption analysis results and corresponding explanatory information. The generation module is used to integrate and process energy consumption analysis results and explanatory information to generate energy consumption analysis report data; The first sending module is used to send energy consumption analysis report data to the user terminal so that the user terminal can display the data based on the energy consumption analysis report.

[0015] Fourthly, embodiments of this application provide an electronic device, including: a processor and a memory; wherein the memory stores a computer program, and the processor executes the computer program to implement the method steps provided in the first aspect of embodiments of this application.

[0016] Fifthly, embodiments of this application provide a computer storage medium storing a plurality of instructions adapted for loading by a processor and executing the method steps provided in the first aspect of embodiments of this application.

[0017] In a sixth aspect, embodiments of this application provide a computer program product containing instructions that, when run on a computer or processor, cause the computer or processor to execute the method provided in the first aspect of embodiments of this application.

[0018] This application embodiment responds to an energy consumption analysis request sent by a user terminal via a cloud device, acquiring the subject profile data and energy consumption characteristic data of the target energy-consuming entity corresponding to the energy consumption analysis request. Subsequently, data analysis processing is performed on the energy consumption analysis request, subject profile data, and energy consumption characteristic data to obtain energy consumption analysis results and corresponding explanatory information. Furthermore, the energy consumption analysis results and explanatory information are fused to generate an energy consumption analysis report, which is then sent to the user terminal for display. Thus, by integrating subject profile modeling, energy consumption feature extraction, analysis and reasoning, and explanation generation capabilities into the cloud device, automated and intelligent overall analysis of the energy consumption behavior of the target energy-consuming entity is achieved. Moreover, by fusing the energy consumption analysis results and explanatory information to generate structured and visualized energy consumption analysis report data and sending it to the user terminal, users can obtain information such as energy consumption composition, abnormal situations, and energy-saving suggestions in a more intuitive and easily understandable way. The embodiments of this application not only improve the efficiency of energy consumption analysis report generation and the accuracy and interpretability of energy consumption analysis results, but also enhance the completeness of energy consumption analysis report display and user experience. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 An exemplary system architecture diagram of an energy consumption analysis report generation method provided in this application embodiment; Figure 2 A flowchart illustrating a method for generating an energy consumption analysis report provided in an embodiment of this application; Figure 3 A flowchart illustrating a method for generating energy analysis results and interpretation information, provided in an embodiment of this application; Figure 4 A flowchart illustrating an energy consumption analysis report optimization method provided in this application embodiment; Figure 5 A schematic diagram of the architecture of an energy consumption analysis report generation system provided in this application embodiment; Figure 6 A schematic diagram illustrating the specific process of an energy consumption analysis report generation method provided in this application embodiment; Figure 7 A schematic diagram of an energy consumption analysis report generation device provided in this application embodiment; Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0021] To make the features and advantages of the embodiments of this application more apparent and understandable, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the protection scope of the embodiments of this application.

[0022] In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the embodiments of this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this application as detailed in the appended claims. Furthermore, in the description of the embodiments of this application, unless otherwise stated, " / " means "or," for example, A / B can mean A or B; the word "and / or" in the text is merely a description of the association relationship between related objects, indicating that three relationships can exist, for example, A and / or B can represent: A alone, A and B simultaneously, and B alone. Additionally, in the description of the embodiments of this application, "multiple" refers to two or more.

[0023] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as implying or suggesting relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature.

[0024] With the widespread adoption of smart home devices, home energy management systems face the challenge of processing multi-source, heterogeneous data in a unified manner. Different brands and types of devices use their own independent energy consumption data collection formats, leading to inconsistent data formats and difficulties in cross-device data fusion and unified analysis. Existing power consumption analysis systems often rely on batch processing, lacking real-time monitoring and dynamic report generation capabilities. In high-concurrency scenarios, data processing delays can easily occur, potentially resulting in low report generation efficiency and low report reliability.

[0025] Therefore, embodiments of this application provide a method, apparatus, device, medium, and program product for generating energy consumption analysis reports to solve the technical problems of low generation efficiency and low reliability of report content in the aforementioned energy consumption analysis reports.

[0026] Please see Figure 1 , Figure 1 An exemplary system architecture diagram of an energy consumption analysis report generation method provided in this application embodiment.

[0027] like Figure 1 As shown, the system architecture may include a cloud device 110, a user terminal 120, and a network 130. The network 130 provides a communication link between the cloud device 110 and the user terminal 120. The network 130 may include various types of wired or wireless communication links, such as wired communication links including fiber optic cables, twisted-pair cables, or coaxial cables, and wireless communication links including Bluetooth communication links, Wireless-Fidelity (Wi-Fi) communication links, or microwave communication links, etc.

[0028] The cloud device 110 can interact with the user terminal 120 via the network 130 to receive or send messages to the user terminal 120. The user terminal 120 can be either hardware or software. When the user terminal 120 is hardware, it can be various electronic devices or smart home devices with voice or graphical interaction capabilities, including but not limited to smart speakers, smart central control screens, smart TVs, voice-activated home appliances, robot vacuum cleaners, air conditioner remote control panels, smart door lock panels, and gateway devices with displays. When the user terminal 120 is software, it can be an application installed on a mobile terminal, such as a smart home application (App), a mini-program, or other client applications with voice input capabilities, used to receive the user's voice or text input and send it to the cloud device 110 for processing.

[0029] In this embodiment, the user terminal 120 first sends an energy consumption analysis request to the cloud device 110 via the network 130. The cloud device 110, in response to receiving the energy consumption analysis request from the user terminal 120, obtains the subject profile data of the target energy-consuming entity corresponding to the energy consumption analysis request, and obtains the energy consumption characteristic data of the target energy-consuming entity. Subsequently, it performs data analysis processing on the energy consumption analysis request, the subject profile data, and the energy consumption characteristic data to obtain the energy consumption analysis results and the corresponding explanatory information. Then, it performs fusion processing on the energy consumption analysis results and the explanatory information to generate energy consumption analysis report data, and sends the energy consumption analysis report data to the user terminal 120 via the network 130. After receiving the energy consumption analysis report data returned by the cloud device 110, the user terminal 120 performs rendering processing based on the energy consumption analysis report data to generate a display page to present the energy consumption analysis report data.

[0030] Cloud device 110 can be a server component that provides functions such as information processing, model inference, data querying, or service orchestration. It should be noted that cloud device 110 can be in hardware or software form. When cloud device 110 is hardware, it can be implemented by a distributed server cluster consisting of multiple physical servers, or by a single physical server. When cloud device 110 is software, it can consist of multiple software programs or software modules (e.g., a software framework for providing distributed services), or by a single software program or software module; no specific limitation is made here. For example, cloud device 110 can be deployed in a cloud, public cloud, or private cloud environment, or it can be deployed on a local edge computing device to achieve unified processing and management of power-consuming devices.

[0031] It should be noted that the energy consumption scenario may include multiple energy-consuming devices or applications. The user terminal 120 can be any device or application in the energy consumption scenario that can interact with the cloud device 110. The user terminal 120 can receive user interaction commands through voice, touch, or text, and send the commands to the cloud device 110 to trigger the energy consumption analysis report generation service of the cloud device 110. The specific type of the user terminal 120 is not limited here.

[0032] It should be understood that Figure 1 The number of cloud devices, user terminals, and networks shown is only illustrative; it can be any number of cloud devices, user terminals, and networks depending on the implementation needs.

[0033] Please see Figure 2 , Figure 2 This is a flowchart illustrating a method for generating an energy consumption analysis report, provided as an embodiment of this application. Figure 2 As shown, the energy consumption analysis report generation method can be applied to the aforementioned cloud devices, and the energy consumption analysis report generation method can include at least: S210: In response to receiving an energy consumption analysis request sent by a user terminal, obtain the subject profile data of the target energy consumption subject corresponding to the energy consumption analysis request, and obtain the energy consumption characteristic data of the target energy consumption subject.

[0034] The energy consumption analysis request can be a request sent by the user terminal to trigger the system to perform energy consumption analysis. Specifically, it can be initiated in the form of natural language, button commands, or preset tasks. For example, the user can click on buttons such as "View Energy Consumption Analysis" or "Generate Energy Consumption Report" on the relevant interface of the App or system to trigger the user terminal to send an energy consumption analysis request to the cloud device.

[0035] Optionally, the energy consumption analysis request may include information such as request type and analysis scope. The request type indicates the specific type of analysis to be performed, such as a trend analysis to characterize the overall energy consumption trend the user wants to view, a device comparison analysis to compare the energy consumption differences of different energy-consuming devices, an anomaly detection analysis to identify energy consumption anomalies, or an energy-saving suggestion analysis to obtain energy-saving strategies. The analysis scope may include range parameters to define the boundaries of the energy consumption analysis target, such as range information indicating the type of analysis object, the spatial range of the analysis, or the time range of the analysis.

[0036] Optionally, the target energy user can refer to the object for which energy consumption analysis needs to be performed, specifically entities with independent energy usage behaviors such as households, shops, schools, offices, and factories. Specifically, the analysis object can be determined based on the user account or request parameters that sent the energy consumption analysis request, such as the household identification document (ID), user household configuration, building ID, and energy consumption area (e.g., dormitory building 1, workshop A).

[0037] In one embodiment, the subject profile data can be multi-dimensional profile data used to characterize the features of the target energy user. This includes, but is not limited to: equipment environmental parameters (such as temperature, humidity, lighting conditions, CO2 content, PM2.5 content with a diameter of 2.5 micrometers or less), and user historical operation information (such as the daily routines of family members, power on / off preferences, seasonal patterns, etc.). Specifically, relevant features can be automatically extracted from related user profiles, historical usage logs, environmental sensor data, and cloud-based knowledge bases to form a structured profile, which serves as the subject profile data.

[0038] In one embodiment, energy consumption characteristic data can be a feature set formed by processing the operating data of energy-consuming equipment in the target energy-consuming entity. Energy consumption characteristic data can include at least one of the following: equipment energy consumption data, equipment status logs, and energy price parameters. Specifically, equipment energy consumption data can be structured data used to characterize the energy consumption behavior of energy-consuming equipment, such as instantaneous power, cumulative energy consumption, running time, start-up frequency, and load level of the equipment at different times, which can be used to reflect the energy consumption contribution and operating characteristics of the equipment. Equipment status logs can be status records reported by energy-consuming equipment during operation, used to describe changes in the equipment's operating status, switching of working modes, fault events, abnormal alarms, operating temperature, or environmental feedback, which can be used to identify whether the equipment has abnormal energy consumption behavior or low operating efficiency. Energy price parameters can be price information used to describe energy billing models, such as time-of-use pricing, peak-valley pricing, tiered pricing, and fee rules for different billing periods, used to analyze the user's energy consumption behavior in different electricity price ranges and provide a basis for energy-saving strategies.

[0039] Optionally, the subject profile data and energy consumption characteristic data can be obtained from a relevant data platform, which can be a cloud data platform, an edge data platform, or a local data platform.

[0040] It should be noted that in the energy consumption scenario provided in the embodiments of this application, energy consumption can be the total amount of energy consumed by the target energy user during operation, and the energy can include, but is not limited to, electrical energy, thermal energy, gas energy, cooling energy or other forms of energy.

[0041] S220: Perform data analysis and processing on the energy consumption analysis request, subject profile data, and energy consumption characteristic data to obtain energy consumption analysis results and corresponding explanatory information.

[0042] The energy consumption analysis results can be data on energy consumption behavior generated based on model analysis or multi-agent reasoning. For example, the energy consumption analysis results can include multiple energy consumption analysis sub-results output by multiple agents or multiple models. Each energy consumption analysis sub-result can reflect the energy consumption characteristics of the target energy-consuming subject in different dimensions. Different energy consumption analysis sub-results can complement each other and be used together to describe the overall energy consumption behavior characteristics of the target energy-consuming subject.

[0043] Optionally, the explanatory information is used to provide explanatory output related to the energy consumption analysis results. For example, the explanatory information may provide explanations of the causes, reasoning, and actionable suggestions for the energy consumption analysis results.

[0044] In one specific embodiment, a pre-defined analysis model or multi-agent inference framework can be invoked to jointly analyze data such as energy consumption analysis requests, subject profile data, and energy consumption characteristic data. Specifically, the analysis model or multi-agent inference framework can identify the behavioral patterns and environmental characteristics of the target energy-consuming subject based on the subject profile data, identify the energy consumption composition, operating status, and potential anomalies of equipment based on the energy consumption characteristic data, and generate corresponding energy consumption analysis results by combining the analysis type specified in the energy consumption analysis request. Furthermore, an interpreting agent can be used to interpret and generate explanations for the energy consumption analysis results, providing causal explanations, reasoning basis, and actionable energy-saving or optimization suggestions to generate corresponding explanatory information.

[0045] S230: Integrate and process the energy consumption analysis results and interpretation information to generate energy consumption analysis report data.

[0046] Among them, the energy analysis report data can be the final output data organized according to the preset report template, which can be used for terminal rendering.

[0047] Optionally, the content of the energy consumption analysis report may include, but is not limited to: energy consumption description information (such as energy consumption analysis or conclusions), energy consumption recommendation information, graphical elements (such as equipment proportion charts and cost comparison charts), and structured display data (such as chart data).

[0048] Specifically, based on a preset report template, energy consumption analysis results and explanatory information can be filtered, classified, and structured to obtain energy consumption description information to describe the current energy consumption status and energy consumption suggestion information to provide guidance for energy-saving actions. Furthermore, graphical element information related to energy consumption can be generated based on various indicators in the energy consumption analysis results. This graphical element information, along with the energy consumption description information and energy consumption suggestion information, can be combined according to a preset format to form structured display data. Finally, the energy consumption description information, energy consumption suggestion information, graphical element information, and structured display data are merged and output to generate an energy consumption analysis report that meets the requirements of the report template, for rendering and display on user terminals.

[0049] S240: Send the energy consumption analysis report data to the user terminal so that the user terminal can display the data based on the energy consumption analysis report.

[0050] Specifically, energy consumption analysis report data can be transmitted to the user terminal in structured data format via a communication connection. Upon receiving the energy consumption analysis report data, the user terminal can parse and visualize the specific content of the data according to a preset rendering template, and display the final energy consumption analysis report on the interface in a combination of text and graphics. The user terminal can also adopt appropriate adaptive layout strategies based on device type (such as mobile phone, tablet, or browser) to improve the readability and interactive experience of the report.

[0051] In this embodiment, the cloud device responds to an energy consumption analysis request sent by a user terminal, acquires the subject profile data of the target energy-consuming entity corresponding to the energy consumption analysis request, and acquires the energy consumption characteristic data of the target energy-consuming entity. Subsequently, it performs data analysis processing on the energy consumption analysis request, subject profile data, and energy consumption characteristic data to obtain energy consumption analysis results and corresponding explanatory information. Then, it fuses the energy consumption analysis results and explanatory information to generate energy consumption analysis report data, which is sent to the user terminal for display. Thus, by integrating subject profile modeling, energy consumption feature extraction, analysis and reasoning, and explanation generation capabilities into the cloud device, it achieves automated and intelligent overall analysis of the energy consumption behavior of the target energy-consuming entity. Furthermore, by fusing the energy consumption analysis results and explanatory information to generate structured and visualized energy consumption analysis report data and sending it to the user terminal, users can obtain information such as energy consumption composition, abnormal situations, and energy-saving suggestions in a more intuitive and easily understandable way. The embodiments of this application not only improve the efficiency of energy consumption analysis report generation and the accuracy and interpretability of energy consumption analysis results, but also enhance the completeness of energy consumption analysis report display and user experience.

[0052] In one embodiment, obtaining the energy consumption characteristic data of the target energy-consuming entity in S210 above may include the following steps: S211: Obtain the list of energy-consuming devices corresponding to the target energy-consuming entity in the energy consumption analysis request. The list of energy-consuming devices includes at least one energy-consuming device corresponding to the target energy-consuming entity.

[0053] The energy-consuming equipment list can be a list of at least one energy-consuming equipment associated with the target energy-consuming entity, used to indicate the scope of equipment to be included in the analysis. The energy-consuming equipment list can include information such as the equipment type, equipment identification, and equipment installation location of each energy-consuming equipment. Energy-consuming equipment can be physical devices that consume energy (such as electrical energy, heat energy, or gas energy), such as air conditioners, refrigerators, washing machines, water heaters, lighting equipment, etc., and can also include high-power industrial and commercial equipment.

[0054] Specifically, the list of energy-consuming devices can be obtained by parsing energy consumption analysis requests. For example, when a user initiates an analysis request on the terminal, the set of devices to be analyzed can be automatically derived from the analysis object selected by the user (such as whole-house energy consumption); in addition, when the energy consumption analysis request does not explicitly specify the range of devices, the list of energy-consuming devices can also be automatically generated based on the registered device list of the target energy-consuming entity or historical analysis scenarios.

[0055] S212: Obtain the structured operation data corresponding to each energy-consuming device based on the energy-consuming device list.

[0056] Structured operational data can be data with a unified field format, unified time granularity, and unified statistical caliber.

[0057] Optionally, the structured operation data corresponding to each energy-consuming device is obtained according to the energy-consuming device list, including: obtaining the structured operation data corresponding to each energy-consuming device from a preset data platform according to the energy-consuming device list; the preset data platform is used to receive the raw operation data of each energy-consuming device and process the raw operation data of each energy-consuming device to generate and store the structured operation data corresponding to each energy-consuming device.

[0058] Raw operating data can be unprocessed operating information reported in real time by energy-consuming equipment, such as raw indicators like equipment power, current, voltage, operating mode, start-up and shutdown events, fault events, and working hours. The structure of raw operating data varies depending on the type of equipment.

[0059] Optionally, the pre-defined data platform can be a big data platform for receiving, storing, and processing operational data from various energy-consuming devices. This platform may include components such as a data lake, a data cleaning module, a data processing module, and a data tag extraction module to achieve standardized processing and structured storage of device data. For example, the data lake can access raw operational data reported by different types of devices in real time through a message middleware; the data cleaning module can perform anomaly removal, time zone alignment, and data standardization on the raw operational data based on pre-defined specifications; the data processing module can uniformly process data at different time granularities, such as aggregating calculations by hour, day, or month; and the data tagging module can generate tag indicators related to device status, energy consumption patterns, etc., on the processed data. The message middleware can be a distributed messaging system like Kafka.

[0060] In one embodiment, data processing may include format standardization, outlier removal, missing value handling, time zone unification, time granularity alignment (e.g., unification to hour / day / month dimensions), and statistical aggregation of raw operational data to generate structured data that can be used for analysis.

[0061] By employing a pre-defined data platform to centrally access, clean, process, and extract tags from the raw operational data reported by various energy-consuming devices, this embodiment of the application can uniformly convert heterogeneous data from different device sources, with different data structures, and different time granularities into structured operational data, and further generate energy consumption characteristic data with stable quality and consistent semantics. This not only improves the usability and accuracy of the data in subsequent analysis tasks, but also automates and standardizes the device data processing workflow.

[0062] S213: Perform feature generation processing on the structured operational data to generate energy consumption characteristic data for the target energy-consuming entity. The energy consumption characteristic data includes at least one of the following: equipment energy consumption data, equipment status logs, and energy price parameters.

[0063] In one specific embodiment, feature generation processing of structured operational data may include parsing, aggregating, and tagging the structured operational data of each energy-consuming device to form energy consumption feature data that can be used by analysis models or working intelligent agents to perform inference tasks.

[0064] Specifically, features related to energy consumption behavior can be extracted from structured operational data. In addition, based on preset feature engineering rules, the structured operational data can be denoised, missing data filled, time aligned, and normalized, and corresponding tag features can be generated according to different types of energy-consuming equipment (such as high-energy-consuming equipment tags, periodic energy consumption pattern tags, abnormal fluctuation tags, etc.).

[0065] In this embodiment, by automatically parsing the energy-consuming equipment list of the target energy-consuming entity, acquiring structured operational data based on a preset data platform, and further performing feature generation processing on the structured operational data, the entire process from raw equipment data to analytically usable feature data can be automated and standardized. This not only enables the system to effectively handle heterogeneous data from different equipment sources, with different data structures and time granularities, but also outputs semantically consistent, high-quality, and adaptable energy consumption feature data for subsequent analysis models or intelligent agent reasoning, thereby improving the accuracy and robustness of energy consumption analysis while reducing the complexity of data preprocessing.

[0066] In one embodiment, a cloud device deploys multiple intelligent agents, including a scheduling agent, multiple working agents, a result interpretation agent, and an optimization agent. These agents collaborate to complete energy consumption analysis tasks and generate energy consumption analysis reports. The scheduling agent, based on energy consumption analysis requests, subject profile data, and energy consumption characteristic data, combined with the working attribute information of each working agent, formulates task objectives and generates corresponding task data, allocating tasks to suitable working agents as needed. The multiple working agents may include a device analysis agent for performing device-level energy consumption analysis and a profile analysis agent for performing profile inference. The result interpretation agent generates corresponding explanatory outputs based on the energy consumption analysis results from the multiple working agents. The optimization agent optimizes the energy consumption analysis report data to obtain optimized energy consumption analysis report data. During the energy consumption analysis process, the scheduling agent can automatically select the execution order and priority of each working agent based on the task content and agent capabilities. Each working agent independently or collaboratively completes data analysis, inference judgment, or result generation based on the task data issued by the scheduling agent, and returns interim results to the scheduling agent or the interpretation agent. Through the division of labor and coordination among the aforementioned intelligent agents, efficient processing and intelligent reasoning of multi-dimensional energy consumption data can be achieved, improving the accuracy, interpretability, and executability of energy consumption analysis results.

[0067] The following will describe the functional positioning of each intelligent agent and its collaborative working mechanism in this application, with reference to specific embodiments.

[0068] Please see Figure 3 In step S210 above, data analysis and processing are performed on the energy consumption analysis request, the main profile data, and the energy consumption characteristic data to obtain the energy consumption analysis results and the corresponding explanatory information. This may include the following steps: S310: Through a pre-set scheduling agent, task data generation and processing are performed based on energy consumption analysis requests, subject profile data, and energy consumption characteristic data to obtain multiple task data corresponding to multiple working agents.

[0069] In this context, there is a one-to-one correspondence between working agents and task data, meaning that different task data can be used to guide different working agents to perform corresponding exclusive analysis tasks.

[0070] Specifically, the multiple task data include device analysis task data corresponding to the device analysis agent and profile analysis data corresponding to the profile analysis agent. Device analysis task data may include, but is not limited to: device functional information (such as device type and device identifier of energy-consuming equipment), device energy consumption data, device status logs, and related operational background information. The operational background information can be auxiliary information describing the external conditions under which the device operates, supplementing the device energy consumption data and device status logs. Operational background information may include at least one of the following: time context information (such as time period, season, holidays), environmental condition information (such as device installation location, temperature, humidity, light intensity), scenario or mode information (such as home / away mode, cooling / heating scenario), energy price or load strategy information (such as peak / valley electricity price periods), and other external influencing factors related to device operation. Optionally, profile analysis task data may include at least a portion of the subject profile data. For example, subject profile data can serve as the basic information input for profile analysis task data to reflect the long-term profile characteristics of the target energy-consuming subject. In addition, the data for profile analysis tasks can also include dynamic contextual information related to the current analysis task, such as device environmental parameters, user historical operation information, and energy price parameters, to support the profile analysis agent in performing more accurate profile reasoning processing.

[0071] Optionally, energy consumption analysis requests, subject profile data, and energy consumption characteristic data can be jointly input into the scheduling agent to generate and process task data, and obtain multiple task data corresponding to multiple working agents output by the scheduling agent.

[0072] S320: Multiple working intelligent agents perform task execution processing based on multiple task data to obtain energy consumption analysis results.

[0073] Optionally, the scheduling agent can use structured messages, such as JavaScript Object Notation (JSON) messages, to send the generated task data to the corresponding worker agents. Further, each worker agent performs task processing based on the received task data. Each worker agent can generate corresponding energy consumption analysis sub-results, and multiple energy consumption analysis sub-results generated by multiple worker agents can be used as the final energy consumption analysis result.

[0074] S330: The result interpretation agent performs interpretation generation processing based on the subject profile data, energy consumption feature data and energy consumption analysis results, and generates interpretation information corresponding to the energy consumption analysis results. The interpretation information is used to provide interpretive output related to the energy consumption analysis results.

[0075] Optionally, the scheduling agent can send subject profile data, energy consumption characteristic data, etc., to the result interpretation agent in the form of structured messages. Furthermore, each working agent can send the generated energy consumption analysis sub-results to the result interpretation agent. Then, the result interpretation agent can perform interpretation generation processing based on the subject profile data, energy consumption characteristic data, and energy consumption analysis results. This interpretation generation processing may include performing rule matching, case retrieval, or counterfactual reasoning based on a preset interpretation knowledge base to generate explanations of the analysis results, key evidence, and executable optimization suggestions, thereby forming explanatory information corresponding to the energy consumption analysis results and providing support for subsequent report generation steps.

[0076] In this embodiment, a multi-agent collaborative data analysis process enables the automatic generation of targeted task data based on different types of data under the unified scheduling of the scheduling agent. Work agents with matching capabilities then execute subdivided tasks such as device analysis and profiling reasoning, achieving efficient analysis of multi-dimensional energy consumption behavior. The sub-analysis results generated by each work agent are aggregated to form the overall energy consumption analysis result. The result interpretation agent then interprets and generates the result based on the subject profiling data and energy consumption characteristic data, providing clear explanations, reasoning bases, and actionable suggestions for the analysis conclusions. This not only improves the accuracy, scalability, and automation of energy consumption analysis but also enhances the interpretability and usability of the analysis results, providing a stable and reliable foundation for subsequent energy consumption report generation.

[0077] In one embodiment, in S310 above, the process of generating task data based on energy consumption analysis requests, subject profile data, and energy consumption characteristic data by a preset scheduling agent to obtain multiple task data corresponding to the working agent may include the following steps: S311: Load the multi-agent registration list through the preset scheduling agent and obtain multiple working attribute information corresponding to multiple working agents.

[0078] The multi-agent registration list can be a pre-configured agent management data structure used to record each deployed agent and its corresponding capability description. This registration list may include, but is not limited to, the following: agent identification information (e.g., unique ID, type label), functional description information (e.g., device analysis, profiling reasoning), input or output data type requirements, execution priority, or adaptation scenario information.

[0079] Optionally, the job attribute information and the job agent can correspond one-to-one. The job attribute information can be a set of attributes related to task generation extracted from the registration list, including the job agent's capability range, processing capability, task adaptability, invocation cost, knowledge base coverage, etc.

[0080] Specifically, the scheduling agent can load a multi-agent registration list according to preset rules and parse the work attribute information corresponding to each working agent to prepare for subsequent task target generation and matching.

[0081] S312: The pre-set scheduling agent generates the task objective based on the energy consumption analysis request, subject profile data and energy consumption characteristic data, and obtains the analysis task objective.

[0082] The analysis task objectives may include, but are not limited to: analysis category (such as total energy consumption analysis, equipment contribution assessment, anomaly detection, behavior pattern analysis, energy saving potential assessment, etc.), analysis scope (such as by equipment, by time period, by scenario, by user behavior, etc.), analysis granularity (such as by hour, by day, by equipment category, etc.), output requirements (such as whether trend prediction needs to be generated, whether visualization elements are needed, etc.).

[0083] Specifically, energy consumption analysis requests, subject profile data, and energy consumption characteristic data can be used as input data for the scheduling agent. The scheduling agent can parse the input data based on a preset task reasoning model or rule engine and automatically generate corresponding analysis task objectives to clarify the subsequent task allocation content.

[0084] S313: By scheduling intelligent agents to generate and process task data based on the analysis of task objectives and multiple work attribute information, multiple task data corresponding to the working intelligent agents are obtained.

[0085] Specifically, the scheduling agent can divide the analysis task objective into multiple task sub-objectives through task decomposition and task matching algorithms, select appropriate working agents to execute the corresponding tasks based on agent attribute information, and generate structured task data for each working agent.

[0086] In this embodiment, the scheduling agent utilizes a pre-defined multi-agent registration list and work attribute information to rationally decompose and match different types of analysis tasks. This ensures that each working agent can receive task data that matches its capabilities, thereby significantly improving the efficiency and accuracy of multi-agent collaborative analysis. This not only effectively reduces manual configuration costs and enhances adaptability to different analysis needs, but also enables analysis tasks to maintain good scalability and stability even in complex scenarios, providing a reliable foundation for subsequent analysis result generation and interpretation information generation.

[0087] In one embodiment, in step S320 above, obtaining energy analysis results by having multiple working agents perform task execution processing based on multiple task data may include the following steps: S321: The device analysis agent performs device energy consumption analysis based on the corresponding device analysis task data and the preset device knowledge base to obtain device analysis results. The device analysis task data includes at least one of the following: device function information, device energy consumption data, and device status log.

[0088] The equipment knowledge base can be a pre-defined set of structured or semi-structured knowledge, used to store attribute information, energy efficiency ratings, typical operating characteristics, historical operating cases, failure modes, equipment usage specifications, and other knowledge related to various energy-consuming equipment. This equipment knowledge base can be used to assist equipment analysis agents in inferring and evaluating equipment operating behavior.

[0089] Optionally, the equipment analysis results can be the equipment-level energy consumption analysis output obtained by the equipment analysis agent based on the corresponding task data, including equipment energy consumption contribution, operating cycle, abnormal mode, load change, energy saving space estimation, etc.

[0090] Specifically, the equipment analysis agent can identify equipment type and operational capabilities based on equipment functional information, calculate equipment energy consumption and energy consumption ratio based on equipment energy consumption data, and identify equipment operational anomalies, mode switching patterns, or load fluctuations based on equipment status logs. Combined with equipment energy efficiency models or operational cases in the equipment knowledge base, the equipment analysis agent can generate corresponding equipment analysis results.

[0091] S322: The profile analysis agent performs profile reasoning processing based on the corresponding profile analysis task data and the preset profile knowledge base to obtain the profile analysis result. The profile analysis task data includes at least one of the following: equipment environmental parameters, user historical operation information, and energy price parameters.

[0092] The profile knowledge base is a collection of knowledge storing information such as user behavior patterns, household profile types, environmental influencing factors, lifestyle habit models, and time-of-use electricity pricing strategies. This knowledge base supports the profile analysis agent in inferring the energy consumption behavior characteristics of users or households. The profile analysis results are the profile-level inference output obtained by the profile analysis agent by combining the corresponding profile analysis task data with the profile knowledge base. Examples include user behavior patterns, the degree of influence of environmental parameters on energy consumption, and the impact of energy price changes on energy consumption behavior.

[0093] Specifically, the profiling analysis agent can identify the impact trends of the external environment on energy consumption based on device environmental parameters, determine users' energy consumption habits and behavior patterns based on users' historical operation information, and infer the impact of different electricity price ranges on users' energy consumption behavior based on energy price parameters. Combining behavioral models and strategy templates in the profiling knowledge base, the profiling analysis agent can generate profiling analysis results including user profile features, behavioral pattern classification, and environmental impact factor assessment.

[0094] S323: Determine the energy consumption analysis results based on the equipment analysis results and the profile analysis results.

[0095] Optionally, the equipment analysis results and user profile analysis results can be used as the energy consumption analysis results. Alternatively, the equipment analysis results and user profile analysis results can be correlated and matched to obtain the final energy consumption analysis results. For example, based on the matching relationship between equipment energy consumption contribution and user behavior patterns, the specific causes of abnormal energy consumption can be identified; alternatively, by combining environmental factors and equipment operating load, the energy consumption change trends of different devices can be inferred, thus obtaining the final energy consumption analysis results.

[0096] This embodiment introduces a device analysis agent and a profile analysis agent, and performs independent analysis and reasoning based on device analysis task data and profile analysis task data respectively. This enables a comprehensive analysis of the energy consumption characteristics of the target energy user from at least two dimensions: the device level and the user behavior level. The device analysis agent uses a device knowledge base to identify device operating status, energy consumption contribution, and abnormal patterns, providing accurate device-level energy consumption insights. The profile analysis agent combines a profile knowledge base to reason about user behavior patterns, environmental influencing factors, and energy price sensitivity, obtaining more scenario-specific behavior-level analysis results. Therefore, this not only improves the accuracy and reliability of energy consumption analysis results but also enhances the system's ability to understand complex energy consumption behaviors.

[0097] In one embodiment, in the above S330, the process of generating explanation information corresponding to the energy analysis results by having the result explanation agent perform explanation generation processing based on the subject profile data, energy consumption feature data, and energy consumption analysis results may include the following steps: generating explanation information corresponding to the energy analysis results by having the result explanation agent perform explanation generation processing based on a preset explanation knowledge base, subject profile data, energy consumption feature data, and energy consumption analysis results; wherein, the explanation knowledge base includes at least one of case knowledge, rule knowledge, template knowledge, strategy knowledge, and security constraint knowledge used for explanation generation.

[0098] The explanatory knowledge base can be a collection of knowledge used to support the explanatory generation process, providing causal explanations for analysis results, inferences based on them, and knowledge support for strategy recommendations. This explanatory knowledge base can consist of various types of knowledge.

[0099] For example, case knowledge can be a structured storage of typical energy consumption patterns, energy-saving cases, and abnormal behavior cases, used to provide reference explanations for the current analysis results through analogical reasoning or pattern matching. For instance, the system can generate explanations for similar situations based on historical cases such as "air conditioner running at low temperatures for a long time leads to abnormal energy consumption." Rule knowledge can include logical rules generated from expert experience or long-term statistical analysis to guide the explanation generation process. For instance, rule knowledge can include "If the average power of energy-consuming equipment is consistently higher than the rated power, there may be an abnormal load." Rule knowledge can generate specific cause judgments for energy consumption analysis results through condition matching. Template knowledge can be sentence templates or structural templates used to generate natural language explanations or structured explanations. For example, template knowledge can include the template "Due to [reason], the current energy consumption shows a [trend] in [time period]." Strategy knowledge can be a set of optimization strategies or energy-saving strategies corresponding to different analysis scenarios, such as energy-saving mode adjustment suggestions, user behavior optimization suggestions, and runtime recommendations. Safety constraint knowledge can be a set of knowledge related to the safe operation boundaries of energy-consuming equipment, such as maximum allowable temperature, minimum wind speed limit, compressor protection interval, and defrosting cycle.

[0100] In one specific embodiment, the result interpretation agent can first identify key indicators in the energy consumption analysis results, such as energy consumption anomalies, high equipment energy consumption, and the correlation between behavior patterns and costs. Then, it performs analogical retrieval based on case knowledge in the interpretation knowledge base to find typical cases similar to the current situation. Further, it can perform rule matching on the analysis results based on rule knowledge to determine the possible causes of energy consumption changes. Subsequently, the result interpretation agent can combine template knowledge to fill the inferred causes and evidence into a preset interpretation template, generating structured natural language interpretation content. If the analysis results contain optimizable behaviors or strategies, the agent can select applicable energy-saving strategies or behavioral suggestions from strategy knowledge and verify them in conjunction with safety constraint knowledge to ensure that the generated suggestions meet the requirements for safe equipment operation. Finally, the result interpretation agent outputs interpretation information for use in subsequent report generation steps.

[0101] This embodiment of the application introduces a result-interpreting agent and performs interpretation generation processing based on a preset interpretation knowledge base. This enables the generation of readable, interpretable, and actionable explanatory information based on the obtained energy consumption analysis results. The interpretation knowledge base allows the interpreting agent to achieve a complete reasoning chain from analysis results to causal explanations and then to strategy recommendations, supported by multi-dimensional knowledge. Therefore, this embodiment not only effectively improves the depth of understanding of energy consumption behavior but also provides clear explanations of the causes of phenomena such as abnormal energy consumption and changes in energy consumption patterns, and outputs safe and verifiable, actionable optimization suggestions, thereby enhancing the credibility of the energy consumption analysis results.

[0102] In one embodiment, the process of fusing energy consumption analysis results and explanatory information to generate energy consumption analysis report data in step S230 above may include the following steps: S231: Based on the energy consumption analysis results and interpretation information, the pre-set scheduling agent performs structured organization to generate energy consumption description information and energy consumption suggestion information.

[0103] The energy consumption description information can be textual or structured content describing the current energy consumption behavior of the target energy user. This can include total energy consumption, equipment energy consumption composition, energy consumption trends, abnormal energy consumption patterns, and key influencing factors, clearly presenting the overall energy consumption status to the user. The energy consumption suggestion information can be actionable optimization suggestions, specifically including but not limited to energy-saving strategy suggestions, operating mode adjustment suggestions, behavior optimization suggestions, cost-saving suggestions, and safe operation suggestions, to help users improve their energy consumption behavior.

[0104] Specifically, the scheduling agent can transform the content in the energy consumption analysis results into energy consumption description information based on preset structured rules, and transform the explanatory information generated by the explanation agent into energy consumption suggestion information.

[0105] S232: By scheduling the intelligent agent to generate display content based on the preset report template, energy consumption description information and energy consumption suggestion information, graphical element information is obtained.

[0106] The preset report templates are used to format and organize report content, defining the report's structure, content segmentation, title styles, and the relationship between text and images. These preset report templates can be customized for different display scenarios (mobile / desktop), user roles (home / business), or specific display needs.

[0107] Optionally, the graphical element information can be visual display content, such as equipment energy consumption ratio charts, cost comparison charts, trend line charts, anomaly detection marker charts, energy-saving effect simulation charts, etc., for graphical presentation on user terminals.

[0108] Specifically, the scheduling agent can select the corresponding report template according to different display needs, and map the energy consumption description information into corresponding visualization elements according to the chart structure defined in the template. For example, it can generate a corresponding trend line chart for total energy consumption, generate a pie chart or bar chart for the energy consumption ratio of each energy-consuming device, and generate hotspot prompts or card-style displays for energy-saving suggestions.

[0109] S233: By scheduling intelligent agents, corresponding energy consumption analysis report data is generated based on graphical element information and preset rendering templates.

[0110] The preset rendering template can be used to define the display format of the report on the user's terminal, such as the arrangement of text and images, color scheme, and interactive components. The content of the energy analysis report data may include, but is not limited to: energy description information, energy suggestion information, graphical elements, and structured data presentation.

[0111] Specifically, the scheduling agent can embed graphical element information, energy consumption description information, and energy consumption suggestion information into the corresponding field positions of the rendering template to form structured output data, such as JSON, visual component description data, or other standard formats used for terminal rendering. The final generated energy consumption analysis report data can be displayed on the user terminal.

[0112] This application embodiment introduces a scheduling intelligent agent during the energy consumption analysis report generation process to structurally integrate the energy consumption analysis results and explanatory information. This transforms complex analysis data into clear, easy-to-understand, and actionable user reports. This application embodiment effectively improves the readability, interpretability, and user experience of energy consumption analysis results, enabling users to easily understand their own energy consumption behavior and adopt corresponding optimization strategies, thereby promoting energy conservation, consumption reduction, and energy efficiency improvement.

[0113] In one embodiment, see Figure 4 In cases where multiple agents are involved, including an optimization agent, after sending the energy consumption analysis report data to the user terminal, the method further includes the following steps: S410: Receives user feedback information sent by the user terminal.

[0114] User feedback information can be data submitted by users through their terminals after viewing the energy consumption analysis report, and this feedback may include, but is not limited to: user preferences (e.g., whether they are more concerned about electricity costs or device energy consumption), evaluations of certain analysis conclusions (e.g., likes, dislikes, error corrections), personalized user needs (e.g., requests for additional charts, or requests to focus on specific devices), text-based questions or opinions, and user interaction data (e.g., dwell time, browsing order). User feedback information is used to guide the optimization agent in making personalized adjustments to the report content.

[0115] Specifically, user terminals can provide feedback entry points when users browse the energy consumption analysis report page, such as "more concerned about costs" or "the suggestions are inaccurate," and upload this feedback data to the cloud device in structured or semi-structured form. The cloud device can parse the user feedback information and send it to the optimization agent for further processing.

[0116] S420: The intelligent agent optimizes the energy consumption analysis report data based on user feedback information to obtain optimized energy consumption analysis report data.

[0117] The optimized energy consumption analysis report data can be a new version of the report data generated by the optimization agent after optimizing the initial energy consumption analysis report data based on user feedback. The optimized energy consumption analysis report data may include adjusted energy consumption description information, suggested content with adjusted sorting, additional graphical elements, a simplified report after removing irrelevant content, and different display styles based on user preferences, in order to improve the personalization and readability of the report.

[0118] For example, optimizing energy consumption analysis report data based on user feedback by an intelligent agent can specifically include at least one of the following: adjusting content priorities based on user preferences indicated by user feedback, such as increasing the display weight of cost-related charts or content if the user is more concerned about electricity costs; adjusting report content based on user evaluations indicated by user feedback, such as replacing or deleting corresponding content based on a strategy knowledge base if the user points out that a certain suggestion is not applicable; generating new content based on user needs indicated by user feedback, such as generating trend charts and inserting them into the report if the user wants to view energy consumption trends; and personalizing the sorting based on behavioral data indicated by user feedback, such as determining the order of content presentation based on user reading time and click behavior.

[0119] Understandably, the optimization agent can combine preset optimization rules, user preference models, or recommendation algorithms to generate optimized energy consumption analysis report data, making the report content more in line with users' reading habits and usage needs.

[0120] S430: Send the optimized energy consumption analysis report data to the user terminal so that the user terminal can render and generate an optimized energy consumption analysis report for presentation based on the optimized energy consumption analysis report data.

[0121] Specifically, cloud-based devices can send optimized energy consumption analysis report data to user terminals, enabling the terminals to generate optimized energy consumption analysis reports based on this data. User terminals can then update and display the optimized content according to the rendering template, including adjusting text, replacing or adding graphical elements, and reordering suggested content, thereby presenting a more personalized and user-friendly report interface.

[0122] It should be noted that users can continue to provide feedback on the optimized report, thus forming a closed loop of analysis, display, feedback, and optimization, improving the system's adaptability and user experience.

[0123] This embodiment introduces an optimization agent and dynamically optimizes the energy consumption analysis report based on user feedback, enabling the system to adaptively adjust and continuously improve. This embodiment not only receives user preferences, evaluations, and interaction data in real time, but also automatically adjusts the report's display structure, generates new graphical elements, or provides optimization suggestions based on feedback, thereby achieving personalized customization of the report content and effectively improving its readability, practicality, and strategic value. Furthermore, the closed-loop iterative mechanism of user feedback and report optimization allows for continuous learning of user behavior, constantly improving analysis and display effects, and enhancing sustainable optimization capabilities and user experience.

[0124] Further, please refer to Figure 5 , Figure 5 This is a schematic diagram of the architecture of an energy consumption analysis report generation system provided in an embodiment of this application. Figure 5 As shown, this structure can be used to execute the above-mentioned energy consumption analysis report generation method. Specifically, the energy consumption analysis report generation system may include a terminal device layer, a big data platform layer, a multi-agent layer, and an application layer. The layers are interconnected through data flow and control flow to form a complete closed loop for electricity consumption report generation and feedback.

[0125] In one embodiment, the terminal device layer can be used to collect data from various energy-consuming devices and environmental sensors of the energy-consuming entity. The terminal device layer may include heating, ventilation, and air conditioning (HVAC) systems, refrigerators, washing machines, water heaters, lighting equipment, and environmental sensors such as temperature, humidity, and light intensity sensors. Each energy-consuming device can periodically report its operating status, energy consumption data, and event information, such as start / stop status, setpoint changes, and fault alarms. The energy-consuming devices can perform basic time synchronization and encrypted transmission. The data collection granularity can be primarily hourly, and can be increased to higher frequencies as needed to support refined analysis.

[0126] In one embodiment, the big data platform layer (i.e., the aforementioned preset data platform) can be used to access, store, clean, process, and tag data uploaded from the terminal device layer. The big data platform layer may include a data lake, a data cleaning module, a data processing module, and a data tag extraction module. Specifically, the data lake can access raw energy consumption data from different types of devices in real time via Kafka middleware, and integrate and back up heterogeneous data; the data cleaning module can perform data cleaning, time-series alignment, and anomaly removal; the data processing module can process energy consumption statistics, electricity cost statistics, and electricity price statistics according to a unified time dimension such as hour, day, or month; and the data tag extraction module can generate various tags, including category tags, device tags, and electricity consumption tags, to support subsequent intelligent agent analysis.

[0127] In one embodiment, the multi-agent layer can construct a multi-agent collaborative architecture, including a scheduling agent, a device analysis agent, a profiling analysis agent, a result interpretation agent, and an optimization agent. The scheduling agent can formulate analysis task plans based on a unified feature view and distribute tasks to each working agent via Kafka in JSON format, while simultaneously receiving task status information (in progress, completed, failed) and work results. The device analysis agent can perform device-level energy consumption analysis based on device tags, energy consumption characteristics, and a device knowledge base; the profiling analysis agent can perform user or household profiling inference based on electricity usage tags, environmental parameters, and user behavior data; the result interpretation agent can perform consistency verification, conflict resolution, and cause attribution between device analysis results and profiling analysis results, and generate explanations such as energy saving rate, cost changes, comfort deviations, and adoptability; the optimization agent is used to implement report optimization based on user feedback to achieve continuous iteration. Each agent can construct system prompts, function descriptions, callable tools, and handover agents based on prompt word engineering, and retrieve supplementary knowledge from the corresponding domain knowledge base using a retrieval enhancement generation mechanism to complete higher-quality inference tasks.

[0128] In one embodiment, the application layer (i.e., the user terminal side) can provide user-facing interface functions, including modules for device management, electricity price configuration, preference configuration, energy consumption dashboards, electricity consumption report generation, and report feedback. The application layer can display visual charts such as device percentage graphs and electricity bill cycle comparison graphs, and supports question-and-answer interaction to explain key analysis results. Furthermore, users can bind home devices, create electricity price groups, and configure multiple electricity price groups or different types of electricity prices for devices at the application layer. The system can automatically calculate electricity bills based on the electricity price groups and synchronously back up the processed electricity bill data to the big data platform layer.

[0129] In this embodiment, stable data and control links are formed between the layers: the terminal device layer provides the data acquisition entry point; the big data platform layer realizes data governance and unified feature view construction; the multi-agent layer performs multi-dimensional reasoning, interpretation, and optimization; and the application layer is responsible for display and feedback. User feedback information can flow back to the multi-agent layer and the big data platform layer to update and optimize the model, adjust the strategy template, and improve the task configuration, thereby realizing continuous optimization and closed-loop learning of the electricity consumption report generation system, effectively improving the real-time performance, accuracy, and personalized presentation of energy consumption analysis report data.

[0130] Please refer to the following. Figure 6 , Figure 6 This is a schematic diagram illustrating the specific process of an energy consumption analysis report generation method provided in an embodiment of this application. Figure 6First, the user terminal initiates an energy consumption analysis request to the cloud-based energy consumption analysis report generation service. Upon receiving this request, the service sends an electricity consumption data request to a pre-defined data platform to obtain structured operational data associated with the target energy-consuming entity. Subsequently, the service sends the energy consumption report generation request, entity profile data, and energy consumption characteristic data to the scheduling agent to initiate the analysis task configuration process. The scheduling agent generates the corresponding analysis task objectives and initiates the tasks to the device analysis agent, profile analysis agent, and result interpretation agent, respectively.

[0131] Furthermore, the device analysis agent retrieves relevant knowledge from the device knowledge base and performs device-level analysis in conjunction with the device analysis task data, ultimately sending the device analysis results to the result interpretation agent. Similarly, the profile analysis agent retrieves relevant behavioral patterns and environmental factors from the profile knowledge base and performs profile reasoning processing based on the profile analysis task data to obtain profile analysis results, which are then sent to the result interpretation agent.

[0132] In one embodiment, after receiving the task execution results returned by each working agent, the result interpretation agent can perform interpretation generation processing on the overall energy consumption behavior based on device analysis information and profile analysis information. Specifically, the result interpretation agent first performs correlation modeling on the device analysis results and profile analysis results, constructing an evidence chain containing causal links and a multi-layered interpretation tree. Based on the evidence chain and the multi-layered interpretation tree, it retrieves typical cases matching the current situation from a pre-set case knowledge base to generate explanations and reasoning basis for the analysis results. Simultaneously, the interpretation agent can generate actionable strategy suggestions for users based on a strategy knowledge base and evaluate the potential optimization benefits. The evaluation content may include, but is not limited to, energy saving rate estimation, cost reduction, minimization of user comfort deviation, and the adoptability of the suggestions. Furthermore, before generating the interpretation content, the interpretation agent can perform consistency checks and common-sense checks on the analysis results output by each working agent and the data returned by the data platform. When conflicts arise within the same metric, the interpreting agent can make decisions based on pre-defined conflict resolution rules. These rules include: treating structured data from the data platform as highly reliable information, giving it a higher weight than model inference results; treating equipment safety boundaries as hard constraints, such as minimum / maximum operating temperatures, defrosting cycle limits, and maximum wind speed limits, which must not be violated; prioritizing the cost-optimal strategy while meeting user comfort requirements; and prioritizing strategies with higher historical adoption rates if the differences in returns between recommended strategies are small, thereby improving the stability and rationality of the recommendations. After generating the interpretation, the interpreting agent can uniformly transmit the generated interpretation information, optimization suggestions, and relevant verification logs back to the scheduling agent.

[0133] In one embodiment, after receiving the energy consumption analysis results and explanations, the scheduling agent executes a report generation process. It structures the analysis results and generates energy consumption descriptions and recommendations, while simultaneously generating graphical elements and a data format that can be rendered on the terminal based on preset report and rendering templates. Subsequently, the energy consumption analysis report generation service returns the data to the user terminal for display. After viewing the report, the user can submit feedback through the terminal, which is then forwarded to the optimization agent. The optimization agent performs optimization processing based on the feedback, resulting in an optimized energy consumption analysis report. After the optimization result is returned to the energy consumption analysis report generation service, the service resends the optimized report to the user terminal to present an updated, personalized energy consumption report.

[0134] Furthermore, users can continue to provide feedback on the optimized report, forming a closed-loop iterative mechanism of analysis, display, feedback, and optimization. This allows for the continuous learning of user preferences and drives the continuous improvement of multi-agent collaborative effects, thereby enhancing the readability, accuracy, and personalization of the energy analysis report.

[0135] In one embodiment, both the worker agents and the scheduling agent are built based on a Large Language Model (LLM) and their capabilities and behavioral constraints are defined through prompt engineering. Specifically, each agent adopts a predefined prompt construction paradigm, explicitly defining information such as agent name, description, system prompt, callable tools, and handoff agents in its internal prompt structure. The agent name uniquely identifies the agent, facilitating its invocation or routing by the scheduling agent during task orchestration. The description defines the agent's functional boundaries; for example, a device agent might be used for device energy consumption reasoning, a profiling agent for behavioral profiling inference, and an explanation agent for explanation generation. The system prompt sets global behavioral guidelines for the agent, including output format requirements, reasoning constraints, and the scope of knowledge use, ensuring stable and consistent reasoning behavior during task execution. Furthermore, callable tools are used to indicate the external capability modules that the agent can access, such as knowledge base retrieval tools, data query tools, rule matching tools, or graph generation tools, thereby enhancing the agent's specialized processing capabilities. Handoff agents define which other agents the agent can delegate task processing flows to, forming clear collaborative links between multiple agents and enabling streamlined task processing. Through the above-mentioned prompt-based engineering construction method, different agents can maintain a clear responsibility, stable behavior, and collaborative scheduling operation mode within a unified framework, thereby improving the overall controllability and scalability of the multi-agent system and making subsequent task orchestration, inference link design, and functional expansion more efficient.

[0136] Optionally, the scheduling agent can be fine-tuned based on a pre-defined large language model. Training data may include various energy consumption analysis requests and their corresponding task breakdown results, enabling the model to learn how to identify analysis targets, analysis scope, and task dependencies from input requests. Furthermore, the scheduling agent can be fine-tuned by incorporating data describing the capabilities of working agents, allowing it to automatically select the appropriate agent based on the task type and generate structured task data. Through this training, the scheduling agent can acquire stable task planning and scheduling capabilities.

[0137] Optionally, the device analysis agent can build device-level energy consumption analysis capabilities based on a pre-set large language model through supervised fine-tuning. Training data may include operational data samples from different devices, energy consumption statistics, typical anomaly patterns, and device usage rules, along with corresponding analysis conclusions. The device analysis agent can also be enhanced through retrieval training using a device knowledge base to improve its understanding of device attributes, energy consumption characteristics, and operational patterns. Through the above training, the device analysis agent can output analysis results such as device energy consumption contribution assessment, operational mode judgment, and anomaly identification.

[0138] Optionally, the profiling analysis agent can be fine-tuned under supervision using multi-source behavioral and environmental data, based on a pre-defined large language model. Training data may include user historical operation records, environmental parameters, electricity pricing strategies, and corresponding user profiles or behavioral pattern labels, enabling the model to learn methods for inferring behavioral preferences. Furthermore, the profiling analysis agent can be enhanced through retrieval training using a profiling knowledge base to improve its understanding of the relationship between environmental factors, electricity price changes, and user behavior. Through training, the profiling analysis agent can output information such as behavioral habits, the degree of environmental influence, and profiling features.

[0139] Optionally, the result explanation agent can be fine-tuned based on a pre-defined large language model using supervised data containing analysis results and explanations, enabling the agent to learn typical energy consumption explanation logic. Furthermore, case knowledge, rule knowledge, counterfactual reasoning templates, and energy-saving strategy examples can be constructed for retrieval-enhanced training, allowing the agent to generate explanations, key evidence, and actionable suggestions based on different contexts. Through this training, the result explanation agent can perform consistency verification, conflict identification, and explanation generation processing on the analysis results.

[0140] Optionally, the optimization agent can be based on a pre-defined large language model, using user feedback samples for preference learning and supervised fine-tuning. Training data may include user evaluations of the report content, preference indicators, and corresponding optimized reports, enabling the model to learn how to adjust the content structure, visualization elements, or suggested presentation methods based on feedback. Furthermore, the optimization agent can be trained in conjunction with a recommendation strategy knowledge base to enhance its personalized adjustment capabilities. Through training, the optimization agent can generate optimized report content based on user feedback.

[0141] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps.

[0142] Based on the inventive concept of the above-mentioned energy consumption analysis report generation method, such as Figure 7 As shown, this application also provides an energy consumption analysis report generation apparatus 700 for implementing the energy consumption analysis report generation method described above. The energy consumption analysis report generation apparatus 700 is applied to a cloud device and includes: The acquisition module 710 is used to respond to receiving an energy consumption analysis request sent by a user terminal, acquire the subject profile data of the target energy consumption subject corresponding to the energy consumption analysis request, and acquire the energy consumption characteristic data of the target energy consumption subject; The processing module 720 is used to perform data analysis and processing on the energy consumption analysis request, the main profile data and the energy consumption characteristic data to obtain the energy consumption analysis results and the corresponding explanatory information of the energy consumption analysis results; The generation module 730 is used to integrate and process the energy consumption analysis results and interpretation information to generate energy consumption analysis report data; The first sending module 740 is used to send energy consumption analysis report data to the user terminal so that the user terminal can display the data based on the energy consumption analysis report.

[0143] In one possible implementation, the cloud device deploys multiple pre-defined intelligent agents, including a scheduling intelligent agent and multiple working intelligent agents. The processing module 720 is used for: Through a pre-set scheduling agent, task data generation and processing are performed based on energy consumption analysis requests, subject profile data, and energy consumption characteristic data to obtain multiple task data corresponding to multiple working agents; Energy consumption analysis results are obtained by performing task execution processing based on multiple task data by multiple working intelligent agents. The result interpretation agent performs interpretation generation processing based on subject profile data, energy consumption feature data, and energy consumption analysis results to generate interpretation information corresponding to the energy consumption analysis results. The interpretation information is used to provide interpretive output related to the energy consumption analysis results.

[0144] In one possible implementation, the processing module 720 is specifically used for: The system loads the multi-agent registration list through a pre-defined scheduling agent and obtains multiple work attribute information corresponding to multiple working agents. The pre-defined scheduling agent generates the analysis task objective based on the energy consumption analysis request, subject profile data, and energy consumption characteristic data. By scheduling intelligent agents to generate and process task data based on the analysis of task objectives and multiple work attribute information, multiple task data corresponding to the working intelligent agents are obtained.

[0145] In one possible implementation, the multiple working intelligent agents include a device analysis intelligent agent and a profile analysis intelligent agent, and the multiple task data include device analysis task data corresponding to the device analysis intelligent agent and profile analysis data corresponding to the profile analysis intelligent agent; the processing module 720 is specifically used for: The device analysis agent performs device energy consumption analysis based on the corresponding device analysis task data and the preset device knowledge base to obtain device analysis results. The device analysis task data includes at least one of the following: device function information, device energy consumption data, and device status log. The profiling analysis agent performs profiling reasoning based on the corresponding profiling analysis task data and the preset profiling knowledge base to obtain profiling analysis results. The profiling analysis task data includes at least one of the following: equipment environmental parameters, user historical operation information, and energy price parameters. The energy consumption analysis results are determined based on the equipment analysis results and the profile analysis results.

[0146] In one possible implementation, the processing module 720 is specifically used for: The intelligent agent interprets the results based on the subject profile data, energy consumption characteristic data, and energy consumption analysis results, generating interpretation information corresponding to the energy consumption analysis results, including: The result interpretation agent performs interpretation generation processing based on a preset interpretation knowledge base, subject profile data, energy consumption feature data and energy consumption analysis results, and generates interpretation information corresponding to the energy consumption analysis results; The interpretation knowledge base includes at least one of the following: case knowledge, rule knowledge, template knowledge, strategy knowledge, and security constraint knowledge used to interpret the generated information.

[0147] In one possible implementation, the generation module 730 is used for: The pre-set scheduling agent organizes energy consumption analysis results and interpretation information in a structured manner to generate energy consumption description information and energy consumption suggestion information. By scheduling intelligent agents to generate display content based on preset report templates, energy consumption description information, and energy consumption suggestion information, graphical element information is obtained; By scheduling intelligent agents based on graphical element information and preset rendering templates, corresponding energy consumption analysis report data is generated.

[0148] In one possible implementation, the multiple agents also include an optimization agent, and after sending the energy consumption analysis report data to the user terminal, the device 700 further includes: The receiving module is used to receive user feedback information sent by the user terminal; The optimization module is used to optimize the energy consumption analysis report data based on user feedback information through the optimization agent, so as to obtain the optimized energy consumption analysis report data. The second sending module is used to send the optimized energy consumption analysis report data to the user terminal, so that the user terminal can render and generate an optimized energy consumption analysis report for presentation based on the optimized energy consumption analysis report data.

[0149] In one possible implementation, module 710 is used for: Obtain the list of energy-consuming devices for the target energy-consuming entity corresponding to the energy consumption analysis request. The list of energy-consuming devices includes at least one energy-consuming device corresponding to the target energy-consuming entity. Obtain the structured operation data corresponding to each energy-consuming device based on the energy-consuming equipment list; The structured operational data is processed to generate energy consumption characteristic data of the target energy-consuming entity.

[0150] In one possible implementation, module 710 is used for: Based on the list of energy-consuming equipment, obtain the structured operation data corresponding to each energy-consuming equipment from the preset data platform; The pre-set data platform is used to receive the raw operating data of each energy-consuming device, and to process the raw operating data of each energy-consuming device to generate and store the structured operating data corresponding to each energy-consuming device.

[0151] The division of modules in the above-described energy consumption analysis report generation device is for illustrative purposes only. In other embodiments, the energy consumption analysis report generation device can be divided into different modules as needed to complete all or part of the functions of the above-described energy consumption analysis report generation device. The implementation of each module in the energy consumption analysis report generation device provided in this application embodiment can be in the form of a computer program. This computer program can run on a terminal or server. The program modules constituted by this computer program can be stored in the memory of the terminal or server. When the computer program is executed by a processor, it implements all or part of the steps of the energy consumption analysis report generation method described in this application embodiment.

[0152] This application also provides an electronic device, which can be a server, and its internal structure diagram can be as follows: Figure 8 As shown, this electronic device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network connection. The processor executes a computer program to implement a method for generating energy analysis reports.

[0153] Those skilled in the art will understand that Figure 8 The structures shown are merely block diagrams of some structures related to the embodiments of this application and do not constitute a limitation on the electronic devices to which the embodiments of this application are applied. Specific electronic devices may include more or fewer components than those shown in the figures, or combine certain components, or have different component arrangements.

[0154] In one possible implementation, a computer storage medium is provided that stores instructions, which, when executed on a computer or processor, cause the computer or processor to perform one or more steps in the above embodiments. If the constituent modules of the above-described electronic device are implemented as software functional units and sold or used as independent products, they can be stored in the aforementioned computer-readable storage medium.

[0155] In one possible implementation, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0156] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions. When these computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer storage medium or transmitted through the computer storage medium. The computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The aforementioned available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., Digital Versatile Discs (DVDs)), or semiconductor media (e.g., Solid State Disks (SSDs)).

[0157] It should be noted that the information (including but not limited to the original operating data of the energy-consuming equipment, equipment environmental parameters, user historical operation information, etc.), data (including but not limited to data used for analysis, stored data, displayed data, etc.), and signals involved in the embodiments of this application are all authorized by the user or fully authorized by all parties, and the collection, use, and processing of related data must comply with the relevant laws, regulations, and standards of the relevant countries and regions. For example, the original operating data of the energy-consuming equipment, equipment environmental parameters, user historical operation information, etc. involved in this application were all obtained under full authorization.

[0158] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the methods described above. The aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks. Unless otherwise specified, the technical features of this embodiment and its implementation can be combined arbitrarily.

[0159] The above-described embodiments are merely preferred embodiments of the present application and are not intended to limit the scope of the present application. Any modifications and improvements made by those skilled in the art to the technical solutions of the present application without departing from the design spirit of the present application should fall within the protection scope defined by the claims.

[0160] The foregoing has described specific embodiments of this application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims may be performed in a different order than that shown in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A method for generating an energy analysis report, characterized in that, Applied to cloud devices, including: In response to receiving an energy consumption analysis request sent by a user terminal, the system obtains the subject profile data of the target energy-consuming subject corresponding to the energy consumption analysis request, and obtains the energy consumption characteristic data of the target energy-consuming subject; The energy consumption analysis request, the subject profile data, and the energy consumption characteristic data are processed to obtain the energy consumption analysis results and the corresponding explanatory information. The energy consumption analysis results and the explanatory information are fused together to generate energy consumption analysis report data; The energy consumption analysis report data is sent to the user terminal so that the user terminal can display the data based on the energy consumption analysis report data.

2. The method as described in claim 1, characterized in that, The cloud device is deployed with multiple pre-defined intelligent agents, including a scheduling intelligent agent and multiple working intelligent agents. The data analysis processing of the energy consumption analysis request, the subject profile data, and the energy consumption characteristic data to obtain energy consumption analysis results and corresponding explanatory information includes: Through a pre-set scheduling agent, task data generation processing is performed based on the energy consumption analysis request, the subject profile data, and the energy consumption feature data to obtain multiple task data corresponding to multiple working agents; The energy consumption analysis results are obtained by the multiple working intelligent agents performing task execution processing based on the multiple task data. The result interpretation agent performs interpretation generation processing based on the subject profile data, the energy consumption feature data, and the energy consumption analysis results to generate interpretation information corresponding to the energy consumption analysis results. The interpretation information is used to provide interpretive output related to the energy consumption analysis results.

3. The method as described in claim 2, characterized in that, The process involves a pre-defined scheduling agent that generates task data based on the energy consumption analysis request, the subject profile data, and the energy consumption characteristic data. This generates multiple task data corresponding to the working agent, including: The multi-agent registration list is loaded through the preset scheduling agent, and multiple work attribute information corresponding to the multiple working agents is obtained; The pre-set scheduling agent performs task target generation processing based on the energy consumption analysis request, the subject profile data, and the energy consumption characteristic data to obtain the analysis task target; The scheduling agent generates task data based on the analysis task objective and the multiple work attribute information to obtain multiple task data corresponding to the work agent.

4. The method as described in claim 2, characterized in that, The plurality of working intelligent agents include a device analysis intelligent agent and a profile analysis intelligent agent, and the plurality of task data includes device analysis task data corresponding to the device analysis intelligent agent and profile analysis data corresponding to the profile analysis intelligent agent; The process of obtaining energy consumption analysis results by having multiple working intelligent agents perform task execution processing based on multiple task data includes: The device analysis agent performs device energy consumption analysis based on the corresponding device analysis task data and the preset device knowledge base to obtain device analysis results. The device analysis task data includes at least one of the following: device function information, device energy consumption data, and device status log. The profiling analysis agent performs profiling reasoning based on the corresponding profiling analysis task data and the preset profiling knowledge base to obtain profiling analysis results. The profiling analysis task data includes at least one of the following: equipment environmental parameters, user historical operation information, and energy price parameters. The energy consumption analysis results are determined based on the equipment analysis results and the profile analysis results.

5. The method as described in claim 2, characterized in that, The result interpretation agent performs interpretation generation processing based on the subject profile data, the energy consumption feature data, and the energy consumption analysis results to generate interpretation information corresponding to the energy consumption analysis results, including: The result interpretation agent performs interpretation generation processing based on a preset interpretation knowledge base, the subject profile data, the energy consumption feature data, and the energy consumption analysis results to generate interpretation information corresponding to the energy consumption analysis results; The explanation knowledge base includes at least one of the following: case knowledge, rule knowledge, template knowledge, strategy knowledge, and security constraint knowledge used for explanation and generation.

6. The method as described in claim 1, characterized in that, The process of fusing the energy consumption analysis results and the explanatory information to generate energy consumption analysis report data includes: Based on the energy consumption analysis results and the explanatory information, the pre-set scheduling agent performs structured organization to generate energy consumption description information and energy consumption suggestion information; The scheduling agent generates graphical element information by generating display content based on a preset report template, the energy consumption description information, and the energy consumption suggestion information. The scheduling agent generates corresponding energy consumption analysis report data based on the graphical element information and the preset rendering template.

7. The method as described in claim 3, characterized in that, The plurality of intelligent agents also includes an optimization intelligent agent, and after sending the energy consumption analysis report data to the user terminal, the method further includes: Receive user feedback information sent by the user terminal; The energy consumption analysis report data is optimized by the intelligent agent based on the user feedback information to obtain the optimized energy consumption analysis report data. The optimized energy consumption analysis report data is sent to the user terminal, so that the user terminal can render and generate an optimized energy consumption analysis report for presentation based on the optimized energy consumption analysis report data.

8. The method as described in claim 1, characterized in that, The acquisition of energy consumption characteristic data of the target energy-consuming entity includes: Obtain the list of energy-consuming devices for the target energy-consuming entity corresponding to the energy consumption analysis request, wherein the list of energy-consuming devices includes at least one energy-consuming device corresponding to the target energy-consuming entity; Obtain the structured operation data corresponding to each energy-consuming device based on the energy-consuming device list; The structured operational data is processed to generate feature generation data for the target energy-consuming entity.

9. The method as described in claim 8, characterized in that, The step of obtaining structured operation data corresponding to each energy-consuming device based on the energy-consuming device list includes: According to the energy-consuming equipment list, obtain the structured operation data corresponding to each energy-consuming equipment from the preset data platform; The preset data platform is used to receive the raw operating data of each energy-consuming device, and to process the raw operating data of each energy-consuming device to generate and store the structured operating data corresponding to each energy-consuming device.

10. An energy consumption analysis report display system, characterized in that, This includes cloud devices and user terminals; The user terminal is used to send energy consumption analysis requests to cloud devices; The cloud device is used to respond to receiving an energy consumption analysis request sent by the user terminal, to obtain the subject profile data of the target energy consumption subject corresponding to the energy consumption analysis request, and to obtain the energy consumption characteristic data of the target energy consumption subject; The energy consumption analysis request, the subject profile data, and the energy consumption characteristic data are processed to obtain energy consumption analysis results and corresponding explanatory information; the energy consumption analysis results and the explanatory information are then fused to generate an energy consumption analysis report. The energy consumption analysis report data is sent to the user terminal; The user terminal is also used to receive energy consumption analysis report data returned by the cloud device, and to perform rendering processing based on the energy consumption analysis report data to generate a display page to present the energy consumption analysis report data.

11. An energy analysis report generation device, characterized in that, Applied to cloud devices, including: The acquisition module is used to respond to receiving an energy consumption analysis request sent by a user terminal, acquire the subject profile data of the target energy consumption subject corresponding to the energy consumption analysis request, and acquire the energy consumption characteristic data of the target energy consumption subject; The processing module is used to perform data analysis and processing on the energy consumption analysis request, the subject profile data and the energy consumption characteristic data to obtain energy consumption analysis results and explanatory information corresponding to the energy consumption analysis results; The generation module is used to fuse the energy consumption analysis results and the explanation information to generate energy consumption analysis report data; The first sending module is used to send the energy consumption analysis report data to the user terminal so that the user terminal can display the data based on the energy consumption analysis report data.

12. An electronic device, characterized in that, include: Processor and memory; The processor is connected to the memory; The memory is used to store executable program code; The processor runs a program corresponding to the executable program code stored in the memory to perform the method as described in any one of claims 1-9.

13. A computer storage medium, characterized in that, The computer storage medium stores a plurality of instructions adapted for loading by a processor and executing the method steps as claimed in any one of claims 1-9.

14. A computer program product containing instructions, characterized in that, When the computer program product is run on a computer or processor, it causes the computer or processor to perform the steps of the method as described in any one of claims 1-9.

Images