Power marketing data management and operation efficiency improvement method and related equipment

Abstract

The invention discloses a power marketing data management and operation efficiency improvement method and related equipment, and relates to the field of power data, and the method comprises the steps: obtaining household power consumption information and social power consumption information of a plurality of target users in a target region; performing data cleaning operation on the household electricity consumption information and the social electricity consumption information of each target user to obtain cleaned household electricity consumption information and cleaned social electricity consumption information; describing a target user portrait of each target user according to each cleaned household electricity consumption information and each cleaned social electricity consumption information; according to the geographic position information and the power utilization characteristic information of all target user portraits in the target area, generating a target power utilization package and target power utilization equipment recommendation information, the target power utilization equipment including household power utilization equipment and social power utilization equipment, and when the target power utilization equipment is the social power utilization equipment, recommending the target power utilization package to the target power utilization equipment. The target electric equipment recommendation information further comprises suggested installation places of the social electric equipment.

Description

Technical Field

[0001] This specification relates to the field of power data. More specifically, this application relates to a method for power marketing data governance and operation efficiency improvement and related devices. Background Art

[0002] In the wave of the development of smart cities, the power industry's demand for the collection and analysis of user electricity consumption data is increasing continuously. However, the current power management system mainly focuses on load scheduling and electricity bill settlement at the macro level, lacking in-depth analysis of users' electricity consumption behaviors. Although smart meters and power monitoring systems have been gradually popularized, the following problems still exist:

[0003] 1. Most systems only focus on household electricity consumption data and ignore the electricity consumption information in public places, making it difficult to accurately evaluate users' electricity consumption contributions or demands in social scenarios.

[0004] 2. The correlation between mobile terminal location information and social electricity consumption data is not high, and users' electricity consumption behaviors in public areas cannot be accurately characterized.

[0005] 3. Traditional systems tend to provide unified electricity price strategies and energy consumption suggestions, lacking differentiated recommendations for different users' electricity consumption characteristics and living habits.

[0006] 4. Most platforms only provide electricity consumption monitoring and simple energy-saving suggestions, lacking systematic package and equipment recommendation schemes. They cannot combine geographical location and population distribution, resulting in difficulties in the scientific deployment of public electricity-consuming equipment (such as charging piles, street lights, energy storage equipment).

[0007] Therefore, it is necessary to propose a method for power marketing data governance and operation efficiency improvement and related devices to solve at least some of the above problems. Summary of the Invention

[0008] A series of simplified concepts are introduced in the Summary of the Invention section, which will be further elaborated in detail in the Detailed Description section. The Summary of the Invention section of this application does not mean to attempt to define the key features and essential technical features of the claimed technical solution, nor does it mean to attempt to determine the protection scope of the claimed technical solution.

[0009] In a first aspect, this application proposes a method for power marketing data governance and operation efficiency improvement, including:

[0010] Obtain the household electricity consumption information and social electricity consumption information of multiple target users in a target area;

[0011] Perform data cleaning operations on the above-mentioned household electricity consumption information and social electricity consumption information of each target user to obtain the cleaned household electricity consumption information and the cleaned social electricity consumption information;

[0012] Characterize the target user portrait of each of the above target users according to each of the above cleaned household electricity consumption information and the above cleaned social electricity consumption information;

[0013] Generate a target electricity consumption package and target electricity consumption equipment recommendation information based on the geographical location information and electricity consumption characteristic information of all the target user portraits in the above target area, wherein the target electricity consumption equipment includes household electricity consumption equipment and social electricity consumption equipment. In the case where the above target electricity consumption equipment is social electricity consumption equipment, the above target electricity consumption equipment recommendation information further includes the recommended installation location of the social electricity consumption equipment.

[0014] In a feasible implementation manner, the above obtaining the household electricity consumption information and social electricity consumption information of multiple target users in the target area includes:

[0015] Obtain the data information of the intelligent electrical appliance control client of the target user and the electricity consumption information of the intelligent electricity meter of the target user;

[0016] Determine the above household electricity consumption information according to the data information of the intelligent electrical appliance control client and the electricity consumption information of the intelligent electricity meter;

[0017] Obtain the mobile terminal location information of the above target user;

[0018] In the case where the above mobile terminal location information represents being in a social public area, associate the above mobile terminal location information with the social electricity consumption information to obtain the above social electricity consumption information.

[0019] In a feasible implementation manner, the above social public area includes commercial areas, industrial areas, and transportation infrastructure,

[0020] The above associating the above mobile terminal location information with the social electricity consumption information to obtain the above social electricity consumption information includes:

[0021] In the case where the residence time of the above mobile terminal location information is greater than a preset duration, obtain the social electricity consumption behavior of the target user;

[0022] Obtain the electricity consumption type weight information of the above social electricity consumption behavior;

[0023] Determine the residence time weight information according to the residence time information;

[0024] Determine the above social electricity consumption information according to the above electricity consumption type weight information, residence time weight information, and social electricity consumption total information.

[0025] In a feasible implementation manner, the above characterizing the target user portrait of each of the above target users according to each of the above cleaned household electricity consumption information and the above cleaned social electricity consumption information includes:

[0026] Extract household electricity consumption characteristics based on the above-mentioned cleaned household electricity consumption information. Among them, the above-mentioned household electricity consumption characteristics include daily average household electricity consumption characteristics, peak-valley electricity consumption ratio characteristics of households, household equipment usage characteristics, seasonal electricity consumption characteristics, and electricity consumption behavior pattern characteristics;

[0027] Extract social electricity consumption characteristics based on the above-mentioned cleaned social electricity consumption information. Among them, the above-mentioned social electricity consumption characteristics include social contribution electricity consumption, residence time characteristics, activity types and social equipment usage characteristics, and regional electricity consumption ratio characteristics;

[0028] Obtain the user role information of the target user;

[0029] Perform data fusion based on the above-mentioned user role information, the above-mentioned household electricity consumption characteristics, and the above-mentioned social electricity consumption characteristics to depict the target user portraits of each of the above-mentioned target users.

[0030] In a feasible implementation manner, the above-mentioned user role information includes household users, social users, and hybrid users.

[0031] The above-mentioned performing data fusion based on the above-mentioned user role information, the above-mentioned household electricity consumption characteristics, and the above-mentioned social electricity consumption characteristics to depict the target user portraits of each of the above-mentioned target users includes:

[0032] Determine the target weight information corresponding to the above-mentioned user role information according to the above-mentioned user role information and the weight matching table;

[0033] Determine the features to be fused according to the above-mentioned user role information;

[0034] Among them, when the above-mentioned user role information is a household user, the above-mentioned features to be fused are obtained based on a feature priority screening operation; when the above-mentioned user role information is a social user, the above-mentioned features to be fused are obtained based on a behavior feature matching operation; when the above-mentioned user role information is a hybrid user, the above-mentioned features to be fused are obtained based on a multi-layer feature fusion operation.

[0035] In a feasible implementation manner, the above-mentioned target electricity consumption package is a combined household and social electricity consumption package.

[0036] The specific steps for determining the above-mentioned target electricity consumption package include:

[0037] Construct a state space S according to the above-mentioned household electricity consumption characteristics, social electricity consumption characteristics, the above-mentioned geographical location information, and historical feedback information;

[0038] Construct an action space A according to the combined household and social electricity consumption package;

[0039] Construct a reward function R based on the rewards for package ordering, user feedback and evaluation, power grid load optimization, electricity consumption behavior patterns, and long-term power sustainability rewards;

[0040] Initialize the Q-table according to the above state space S and action space A;

[0041] Set the initial state S0;

[0042] According to the current state St, select the action At using the greedy strategy;

[0043] Execute the above-selected action At in the current state St;

[0044] After executing the action At, update the reward Rt according to the user feedback and the change in the power grid load, and transfer the environmental state to St+1;

[0045] Update the Q value of the current state-action pair;

[0046] When the change in the Q value of all state-action pairs is less than the set threshold or the number of training steps reaches the maximum number of training steps, obtain the optimized Q-table;

[0047] Select the optimized action A* according to the above target user profile and the above optimized Q-table;

[0048] Generate a combined household and social electricity consumption package according to the above optimized action A*;

[0049] In a feasible implementation manner, the above target electrical equipment recommendation information includes social electrical equipment recommendation information.

[0050] The specific steps for determining the above social electrical equipment recommendation information include:

[0051] Determine the equipment demand rate of the target sub-region according to all the above target user profiles in the above target region;

[0052] Obtain the equipment coverage rate of each target sub-region;

[0053] Determine the number of new devices and the types of new devices according to the above equipment coverage rate, the above equipment demand rate, and the equipment demand priority;

[0054] Determine the objective function according to the package benefit, equipment installation cost, equipment installation cost, equipment operation cost, and equipment coverage benefit;

[0055] Define the constraint conditions according to the user package selection constraints, user package selection constraints, total budget constraint, and power grid load limit;

[0056] Perform objective optimization according to the above objective function and the above constraint conditions to obtain social electrical equipment recommendation information.

[0057] Second aspect, the present application proposes a device for power marketing data governance and operation efficiency improvement, including:

[0058] A first acquisition unit, configured to acquire the household electricity consumption information and social electricity consumption information of a plurality of target users in a target area;

[0059] A second acquisition unit, configured to perform data cleaning operations on the household electricity consumption information and the social electricity consumption information of each target user to obtain the cleaned household electricity consumption information and the cleaned social electricity consumption information;

[0060] A characterization unit, configured to characterize a target user portrait of each target user according to the cleaned household electricity consumption information and the cleaned social electricity consumption information of each;

[0061] A generation unit, configured to generate a target electricity package and target electricity equipment recommendation information according to the geographical location information and electricity consumption feature information of all target user portraits in the target area, wherein the target electricity equipment includes household electricity equipment and social electricity equipment, and when the target electricity equipment is social electricity equipment, the target electricity equipment recommendation information further includes the recommended installation location of the social electricity equipment.

[0062] Third aspect, an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor is configured to implement the steps of the power marketing data governance and operation efficiency improvement method according to any one of the first aspects when executing the computer program stored in the memory.

[0063] Fourth aspect, the present application also proposes a computer-readable storage medium, on which a computer program is stored, and the computer program, when executed by a processor, implements the power marketing data governance and operation efficiency improvement method according to any one of the first aspects.

[0064] In summary, the present application provides a method for integrated analysis based on household electricity consumption information and social electricity consumption information. Combining the concept of user portraits, it recommends target electricity consumption packages and target electricity-consuming devices for users and public facilities in the target area, and provides recommended installation locations for social electricity-consuming devices in the scenario of social electricity-consuming devices. The present application not only integrates household electricity consumption information generated by user smart meters, smart appliance control clients, etc., but also includes the electricity consumption of users in social public areas (such as the use of charging piles or public facilities in shopping malls and office areas) in the analysis scope. By leveraging the location information of user mobile terminals, the electricity consumption data in public places is associated with specific user behaviors to form a more detailed electricity consumption portrait, thereby accurately depicting the overall electricity consumption pattern of users. By deeply analyzing the user electricity consumption characteristic information (such as peak electricity consumption preferences, the proportion of night electricity consumption, the ownership of electric vehicles, etc.), the present application can generate highly targeted target electricity consumption packages according to each user portrait. On this basis, different electricity price strategies (such as peak-valley electricity price, ladder electricity price, etc.) can be matched for different users to achieve personalized power saving and load optimization, effectively guiding users to adjust their electricity consumption behaviors. The system not only provides energy-saving and efficient household electricity-consuming devices for the household scenario (such as high-efficiency air conditioners, smart lighting), but also can propose optimal installation location suggestions for the social scenario (such as public charging piles, street lamps, energy storage facilities). By comprehensively analyzing the distribution and electricity consumption characteristic information of all target user portraits in the target area, the system can find the aggregation areas of electricity consumption demand, and preferentially deploy charging piles or energy-saving devices in places with high electricity consumption peaks or large new energy charging demands to improve the rational allocation of public electricity resources. After obtaining the user electricity consumption data, the present application will perform unified format conversion, missing value filling, and outlier processing on data from different sources to ensure the accuracy and reliability of the cleaned household electricity consumption information and social electricity consumption information. Through data standardization, subsequent portrait characterization and recommendation decisions are more stable and reliable, avoiding deviation suggestions caused by data errors. For urban power departments or public management agencies, the recommended installation locations of social electricity-consuming devices provided by the present application can be used to deploy public charging piles, smart street lamps, or energy storage systems in key areas to achieve overall energy consumption regulation and load optimization. Combining big data with geographic information system (GIS), urban managers can more effectively plan the locations of public electricity facilities, thereby reducing peak loads, improving energy utilization efficiency, and enhancing user satisfaction. By integrating multi-source electricity consumption data, deeply analyzing user portraits, matching personalized electricity consumption packages, and optimizing device deployment, the present application establishes a complete intelligent electricity consumption ecosystem at the user end and the public level, which can not only meet the differentiated electricity consumption needs of users, but also contribute to the efficient allocation of urban-level electricity resources, realizing the real three-dimensional electricity consumption collaborative management of household - society - city. Brief Description of the Drawings

[0065] Various other advantages and benefits will become clear to those of ordinary skill in the art by reading the following detailed description of the preferred embodiments. The drawings are only for the purpose of showing the preferred embodiments and are not considered to be a limitation of this specification. Moreover, throughout the drawings, the same reference numerals are used to denote the same components. In the drawings:

[0066] Figure 1 It is a schematic flowchart of a method for power marketing data governance and operation efficiency improvement provided by an embodiment of the present application;

[0067] Figure 2 It is a schematic structural diagram of a device for power marketing data governance and operation efficiency improvement provided by an embodiment of the present application;

[0068] Figure 3 It is a schematic structural diagram of an electronic device for power marketing data governance and operation efficiency improvement provided by an embodiment of the present application. Specific Embodiments

[0069] The terms "first", "second", "third", "fourth", etc. (if any) in the specification, claims and above-mentioned drawings of the present application are used to distinguish similar objects and do not necessarily need to be used to describe a specific order or sequence. It should be understood that such used data may be interchanged under appropriate circumstances so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices. The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments.

[0070] Figure 1 It is a schematic flowchart of a method for power marketing data governance and operation efficiency improvement provided by an embodiment of the present application. The method may specifically include:

[0071] S110. Obtain the household electricity consumption information and social electricity consumption information of multiple target users in the target area;

[0072] Exemplarily, first, obtain the household electricity consumption and social electricity consumption information of users in the target area through various channels. The household electricity consumption information can obtain the electricity consumption data through the user's smart meter, including the daily average electricity consumption, the peak-valley electricity consumption ratio, and the power consumption of the main household electrical appliances. For example: The daily average electricity consumption of a certain user's family is 15 kWh, and the peak-valley electricity consumption ratio is 40% (peak) and 60% (valley). The social electricity consumption information can obtain the user's electricity consumption in the social scenario by combining the location information of the user's mobile terminal with the public place electricity consumption data. For example: A certain user charges at the charging pile in the shopping mall parking lot for 3 hours, and the total electricity contribution to the area is 10 kWh. The data acquisition sources include smart meters, smart home devices, public electricity monitoring systems, and the location information of user mobile terminals.

[0073] S120. Perform data cleaning operations on the above-mentioned household electricity consumption information and the above-mentioned social electricity consumption information of each target user to obtain the cleaned household electricity consumption information and the cleaned social electricity consumption information;

[0074] Exemplarily, in order to ensure the accuracy and integrity of the data, perform data cleaning operations on the collected electricity consumption information. The data cleaning operations include missing value processing, outlier processing, and data standardization. Missing value processing can fill the blank data in the electricity consumption records through interpolation or default values; for example, the missing daily electricity consumption data can be interpolated and completed according to historical records. Outlier processing screens and eliminates abnormal electricity consumption data, such as unreasonable peak electricity consumption that appears in a short period of time. Data standardization includes unifying the data formats and units of different sources (such as unifying the electricity consumption as kWh). After cleaning, accurate household and social electricity consumption information is obtained, providing reliable basic data for subsequent analysis.

[0075] S130. Characterize the target user portraits of each of the above-mentioned target users according to the above-mentioned cleaned household electricity consumption information and the above-mentioned cleaned social electricity consumption information;

[0076] Exemplarily, generate a detailed user portrait for each user by analyzing the cleaned electricity consumption information. The household electricity consumption characteristics are obtained by extracting the user's daily average electricity consumption, peak-valley electricity consumption ratio, seasonal electricity consumption characteristics (such as higher electricity consumption in winter than in summer), and high-energy-consuming device usage characteristics (such as air conditioners or electric vehicle charging devices). For example: The household electricity consumption portrait of a certain user is "daily average electricity consumption 14.8 kWh, higher low-valley electricity consumption ratio, electric vehicle user".

[0077] The social electricity consumption characteristics are obtained by analyzing the activity types, electricity consumption contributions, and residence times of users in social scenarios. For example: A certain user often uses a charging pile in a shopping mall parking lot, contributes 30 kWh of social electricity consumption per week, and has a residence time of 3 hours each time. Users are classified into different types according to their characteristics, such as "low-valley electricity preference users", "social-scenario dominant users", "high-energy-consuming household users", etc.

[0078] S140. Generate a target electricity consumption package and target electricity equipment recommendation information based on the geographical location information and electricity consumption characteristics information of all target user portraits in the above target area. Among them, the target electricity equipment includes household electricity equipment and social electricity equipment. When the above target electricity equipment is social electricity equipment, the above target electricity equipment recommendation information also includes the recommended installation locations of social electricity equipment.

[0079] Exemplarily, the system collects and integrates all target user portraits in the target area, and extracts geographical location information and corresponding electricity consumption characteristics information from them. The geographical location information is used to determine the specific location of each target user (such as residential area, commercial area, or industrial area), as well as the distributable locations of social electricity equipment in the target area. The electricity consumption characteristics information includes the electricity consumption peaks, electricity consumption intervals, and potential energy-saving needs of each target user, and is used to assist in matching suitable target electricity consumption packages and target electricity equipment.

[0080] Based on the electricity consumption characteristics information extracted in the previous step, the system combines different electricity price strategies (such as peak-valley electricity price, ladder electricity price, etc.) to recommend a specific target electricity consumption package for each target user. For example: For a target user portrait with a large electricity consumption during peak hours, a target electricity consumption package that can better "cut peaks and fill valleys" can be matched; for a target user portrait with a large electricity consumption at night, a target electricity consumption package more suitable for night preferential electricity prices may be matched.

[0081] After determining the target electricity consumption package, the system can also generate corresponding target electricity equipment recommendation information according to the actual electricity consumption scenarios of each target user. When the target electricity equipment is household electricity equipment, the system will recommend more energy-saving or more efficient household appliances (such as more energy-saving air conditioners, lighting equipment, etc.) according to the electricity consumption patterns of the user's family to match the user's electricity consumption characteristics information.

[0082] When the target electricity equipment is social electricity equipment, the system needs to analyze from all target user portraits in the target area whether there are social electricity equipment (such as public charging piles, street lights, public grid energy storage equipment, etc.) that need to be configured in public places or public facilities, and determine the recommended installation locations of its social electricity equipment according to the geographical location information summarized in the target user portraits.

[0083] If the target power-consuming equipment determined in the previous step is a social power-consuming equipment, the system will derive the recommended installation location for the social power-consuming equipment based on the distribution of all target user portraits, combined with the geographical location information and power consumption characteristics information. For example, if a large number of target user portraits show that a certain area has a high number of electric vehicles and a large demand for charging, the system will list the area as a recommended installation location for charging piles in social power-consuming equipment; or in areas with insufficient public lighting and more nighttime activities, it is recommended to add energy-saving street lights.

[0084] In summary, the present application provides a fusion analysis method based on household electricity consumption information and social electricity consumption information. Combining the concept of user portraits, it recommends target electricity consumption packages and target electricity-consuming devices for users and public facilities within a target area, and provides recommended installation locations for social electricity-consuming devices in the scenario of social electricity-consuming devices. The present application not only integrates household electricity consumption information generated by user smart electricity meters, smart appliance control clients, etc., but also includes the electricity consumption situation of users in social public areas (such as the use of charging piles or public facilities in shopping malls and office areas) in the analysis scope. By means of the user mobile terminal location information, the electricity consumption data in public places is associated with specific user behaviors to form a more detailed electricity consumption portrait, so as to accurately depict the overall electricity consumption pattern of users. By deeply analyzing the user electricity consumption characteristic information (such as peak electricity consumption preference, proportion of night electricity consumption, ownership of electric vehicles, etc.), the present application can generate highly targeted target electricity consumption packages according to each user portrait. On this basis, different electricity price strategies (such as peak-valley electricity price, ladder electricity price, etc.) can be matched for different users to achieve personalized power saving and load optimization, and effectively guide users to adjust their electricity consumption behaviors. The system not only provides energy-saving and efficient household electricity-consuming devices (such as high-efficiency air conditioners, smart lighting) for the household scenario, but also can propose optimal installation location suggestions for the social scenario (such as public charging piles, street lamps, energy storage facilities). By comprehensively analyzing the distribution and electricity consumption characteristic information of all target user portraits within the target area, the system can find the aggregation areas of electricity consumption demand, and preferentially deploy charging piles or energy-saving devices in places with high electricity consumption peaks or large new energy charging demands to improve the rational allocation of public electricity resources. After obtaining the user electricity consumption data, the present application will perform unified format conversion, missing value filling and outlier processing on data from different sources to ensure the accuracy and reliability of the cleaned household electricity consumption information and social electricity consumption information. Through data standardization, subsequent portrait characterization and recommendation decisions are more stable and reliable, avoiding deviation suggestions caused by data errors. For urban power departments or public management agencies, the recommended installation locations of social electricity-consuming devices provided by the present application can be used to deploy public charging piles, smart street lamps or energy storage systems in key areas to achieve overall energy consumption regulation and load optimization. Combining big data and geographic information system (GIS), urban managers can more effectively plan the locations of public electricity facilities, thereby reducing peak loads, improving energy utilization efficiency, and enhancing user satisfaction. The present application establishes a complete intelligent electricity consumption ecosystem at the user end and the public level by integrating multi-source electricity consumption data, deeply analyzing user portraits, matching personalized electricity consumption packages, and optimizing device deployment, which can not only meet the differentiated electricity consumption needs of users, but also help the efficient allocation of urban-level electricity resources, realizing the real three-dimensional electricity consumption collaborative management of household - society - city.

[0085] In some examples, the obtaining of the household electricity consumption information and social electricity consumption information of multiple target users within the target area includes:

[0086] Obtain the data information of the intelligent electrical appliance control client of the target user and the electricity consumption information of the intelligent electricity meter of the target user;

[0087] Determine the above household electricity consumption information according to the data information of the intelligent electrical appliance control client and the electricity consumption information of the intelligent electricity meter;

[0088] Obtain the location information of the mobile terminal of the above target user;

[0089] When the above mobile terminal location information represents being in a social public area, associate the above mobile terminal location information with social electricity consumption information to obtain the above social electricity consumption information.

[0090] Exemplarily, the system collects the operation records of the target user on household appliances from the intelligent electrical appliance control client, including operations such as on / off time, power adjustment or mode adjustment. These data information can reflect the usage status of the target user's household appliances in a fine dimension and provide support for subsequent identification of the household electricity consumption characteristics of the user. The system simultaneously obtains the electricity consumption data from the intelligent electricity meter of the target user, such as the peak-valley electricity consumption ratio, daily average electricity consumption, and electricity consumption fluctuation curve. These information lay the overall energy consumption data foundation for subsequent determination of the "household electricity consumption information" of the target user.

[0091] Associate and analyze the electrical appliance switches and power changes recorded in the intelligent electrical appliance control client with the overall power curve in the electricity consumption information of the intelligent electricity meter. Through the power changes in the same time period, match the actual electricity consumption and electricity consumption time period of each household appliance. Combining the above analysis, the household electricity consumption characteristics of the user can be accurately characterized, including the daily electricity consumption peak, the proportion of night-time electricity consumption, the usage situation of high-energy-consuming equipment, etc. Thus, household electricity consumption information is formed, such as "the proportion of electricity consumption of the user from 22:00 at night to 6:00 the next day reaches 60%", or "the charging equipment of the electric vehicle accounts for 20% of the electricity consumption in the home", etc.

[0092] After obtaining the user's authorization, the system collects the location information in real time or regularly through the mobile terminal (such as a smart phone) of the target user, including longitude and latitude or positioning point ID. After comparing this location information with the user's home address, it is judged whether the current location of the user is at home or in a social public area. If the mobile terminal location information represents that the target user is still within the residential range, it is continuously associated with the household electricity consumption information and not included in the scope of social electricity consumption. If the mobile terminal location information represents being in a social public area, preparations are made for the association operation with social electricity consumption information.

[0093] When the location information of the mobile terminal has been confirmed to be in a social public area (such as a shopping mall, a public parking lot, an office building, etc.), the system will call relevant social electricity consumption information, such as the smart meter data in the public area or the records of public charging piles. The system will match the location information of the mobile terminal with the corresponding social electricity consumption monitoring data to identify the possible electricity consumption contribution or demand of the target user in this public area. For example: If the user uses the charging pile in the shopping mall parking lot for 2 hours, the system will record the electricity consumption of the user for the public charging pile during this period and include it in the user's "social electricity consumption information".

[0094] Through the above matching, the system can determine the electricity consumption behavior of the target user in the public scenario, such as the power consumption of using the public charging pile, the usage period in the night public lighting system, etc. These data finally generate "social electricity consumption information" to form a more complete user electricity consumption profile. This embodiment makes full use of the data information of the intelligent electrical control client, the electricity consumption information of the smart meter, and the location information of the mobile terminal to ensure that the electricity consumption of the target user can be accurately recorded in any scenario. Whether it is the electricity consumption within the home or the electricity consumption behavior in the public area, a unified closed-loop data monitoring and analysis system can be formed.

[0095] In some examples, the above social public areas include commercial areas, industrial areas, and transportation infrastructure.

[0096] The above-mentioned associating the location information of the mobile terminal with the social electricity consumption information to obtain the above-mentioned social electricity consumption information includes:

[0097] When the residence time of the above-mentioned mobile terminal location information is greater than the preset duration, obtain the social electricity consumption behavior of the target user;

[0098] Obtain the weight information of the electricity consumption type of the above-mentioned social electricity consumption behavior;

[0099] Determine the residence time weight information according to the residence time information;

[0100] Determine the above-mentioned social electricity consumption information according to the above-mentioned weight information of the electricity consumption type, the residence time weight information, and the total social electricity consumption information.

[0101] Exemplarily, the system first determines whether the stay time of the target user in a certain social public area exceeds a set threshold based on the location information of the mobile terminal of the user (for example, the stay time > 30 minutes). If the stay time does not reach this preset duration, the in-depth association of social electricity consumption information is not carried out; if it exceeds the preset duration, it is considered that the target user may have social electricity consumption behavior in this social public area. After the stay time is greater than the preset duration, the system identifies the type of social electricity consumption behavior of the user according to the attributes of the area where the user is located (commercial area, industrial area or transportation infrastructure) (such as shopping in a mall or vehicle charging, equipment use in an industrial area, charging of transportation facilities, etc.). By associating with the social electricity consumption monitoring system of this area, the electricity consumption contribution of the user in the public scenario can be initially determined.

[0102] The system classifies social electricity consumption behaviors, such as charging pile use, public lighting use, cooling / heating equipment use, industrial equipment use, etc. The proportion of the total electricity consumption of different electricity consumption types in the social public area may vary. For the determined electricity consumption type (such as "mall charging pile" or "industrial equipment"), the system assigns a corresponding electricity consumption type weight to quantify the influence degree of this behavior in the total social electricity consumption. For example, the fast charging of electric vehicles in transportation infrastructure may have a relatively high electricity consumption type weight, while only using Wi-Fi in a mall may have a relatively low weight.

[0103] The system extracts the stay duration of the target user in this social public area (such as 2 hours, 3 hours, etc.). According to the stay duration in different intervals, the system can set corresponding weight factors (such as the electricity consumption contribution degrees of staying for 1 hour and staying for 3 hours are different). If the stay time is longer, it indicates that the user may generate higher electricity consumption in this scenario and account for a larger share of social electricity consumption.

[0104] After obtaining the "electricity consumption type weight information" and "stay time weight information", the system also needs to call the total social electricity consumption information of the current area. The "total social electricity consumption information" can be obtained from the public power monitoring system, which reflects the overall electricity consumption level of the mall, industrial area or transportation infrastructure. The system calculates the electricity consumption type weight, stay time weight and total social electricity consumption information to form the social electricity consumption information of the target user in this public area. Example: If the user stays in the industrial area for a long time (the stay time weight is relatively high) and mainly participates in the use of high-energy-consuming equipment (the electricity consumption type weight is relatively high), the proportion of the user's social electricity consumption information will increase accordingly.

[0105] Finally, this calculation result will be recorded in the social electricity consumption behavior file of the target user and used as the basis for subsequent analysis (such as user profiling and electricity consumption recommendations). For example, if a user stays in a commercial area for 3 hours and uses a high-power charging pile, the user's social electricity consumption will be calculated according to the corresponding "stay time weight" and "electricity consumption type weight" and then incorporated into the social electricity consumption information database.

[0106] Through the method provided in this embodiment, it is possible to determine the social electricity consumption information of the target user in public places by combining multi-faceted data such as "stay time", "electricity consumption type weight", and "total social electricity consumption information" in social public areas such as commercial areas, industrial areas, or transportation infrastructure. This can more accurately measure the actual consumption or contribution of users to public power resources, improve the electricity consumption profile of users in social scenarios, and lay a data foundation for subsequent electricity consumption package formulation and equipment recommendation.

[0107] In some examples, the above-mentioned target user profiling of each of the above-mentioned target users based on each of the above-mentioned cleaned household electricity consumption information and the above-mentioned cleaned social electricity consumption information includes:

[0108] Extracting household electricity consumption characteristics based on the above-mentioned cleaned household electricity consumption information, where the above-mentioned household electricity consumption characteristics include household daily average electricity consumption characteristics, household peak-valley electricity consumption ratio characteristics, household equipment usage characteristics, seasonal electricity consumption characteristics, and electricity consumption behavior pattern characteristics;

[0109] Extracting social electricity consumption characteristics based on the above-mentioned cleaned social electricity consumption information, where the above-mentioned social electricity consumption characteristics include social contribution electricity consumption, stay time characteristics, activity type and social equipment usage characteristics, and regional electricity consumption ratio characteristics;

[0110] Obtaining the user role information of the target user;

[0111] Performing data fusion based on the above-mentioned user role information, the above-mentioned household electricity consumption characteristics, and the above-mentioned social electricity consumption characteristics to profile the target user portrait of each of the above-mentioned target users.

[0112] Exemplarily, extracting household electricity consumption characteristics based on the above-mentioned cleaned household electricity consumption information, the system calculates the daily average electricity consumption of the target user from the cleaned household electricity consumption information, such as "15 kWh per day" or "8 kWh per day", etc. This characteristic can reflect the average power consumption level of the user in daily life.

[0113] The system can count the proportion of electricity consumption of the user during peak hours and valley hours to extract the household peak-valley electricity consumption ratio characteristic. For example, the user accounts for 40% during peak hours and 60% during valley hours. This characteristic can be used to determine whether the user has the potential or preference for "peak shaving and valley filling".

[0114] The system can extract the usage characteristics of household devices based on the user's intelligent appliance control client and electricity meter records, and analyze the usage duration and power consumption of common high-energy-consuming devices (such as air conditioners, electric vehicle charging devices, washing machines, etc.). For example, if a user has a high frequency of using the air conditioner and the power consumption accounts for 30%, it will be reflected as "high air conditioner usage rate" in the household device usage characteristics.

[0115] The system can analyze the amplitude of electricity consumption changes of users in different seasons (such as summer and winter) to extract seasonal electricity consumption characteristics. For example, the power consumption of heating equipment increases significantly in winter, and the power consumption of air conditioners increases in summer. This analysis can discover the sensitivity of users to seasonal temperature changes.

[0116] The system can also refine the user's electricity consumption behavior patterns based on the daily electricity consumption time distribution of the user (such as a large proportion at night, a high proportion on weekends, etc.) to extract electricity consumption behavior pattern characteristics. These patterns can be used to predict the user's electricity consumption peak or out-of-home period.

[0117] The system can identify the electricity consumption generated by users in public places (such as shopping malls, industrial areas, transportation infrastructure) from the cleaned social electricity consumption information to extract the social contribution electricity consumption. For example, a user contributes 30 kWh of social electricity consumption to the public charging pile every week.

[0118] Through the user's mobile terminal location information, the system can infer the stay duration of the user in different social public areas to extract the stay time characteristics. Combining the stay duration and the electricity consumption situation in this area, the electricity consumption distribution of the user in the social scenario can be further judged.

[0119] The system distinguishes the activity types of users in the social scenario (such as shopping, working, charging) and the corresponding social electricity-consuming devices (such as shopping mall charging piles, public lighting, industrial equipment) to extract the activity type and social device usage characteristics. For example, if a user frequently uses the charging pile in the shopping mall parking lot, the social device usage characteristics will highlight "public charging pile dependence".

[0120] The system calculates the proportion of electricity consumption of users in different social public areas (commercial areas, industrial areas, transportation infrastructure) to form the regional electricity consumption proportion characteristics and extracts the regional electricity consumption proportion characteristics. For example, a user's social electricity consumption accounts for 70% in the commercial area, 20% in the industrial area, and 10% in the transportation infrastructure.

[0121] The system can pre-define or obtain the user's role information provided by the user, such as "ordinary household user", "electric vehicle user", "industrial employee" or "commercial area consumer", etc. This role information can be combined with the aforementioned electricity consumption characteristics to help accurately distinguish different needs (such as electric vehicle users being more concerned about charging piles, and industrial employees being more concerned about industrial equipment electricity consumption).

[0122] The system integrates the obtained user role information, household electricity consumption characteristics, and social electricity consumption characteristics in multiple dimensions. For example, it combines "daily household electricity consumption of 15 kWh + high-frequency use of electric vehicles + 50% utilization rate of shopping mall charging piles + user role as an electric vehicle driver".

[0123] With the integrated multi-dimensional data, the system forms a target user portrait for each target user, such as: "high-energy-consuming household, 60% of electricity consumption at night, electric vehicle user, high utilization rate of social charging piles". This portrait can highlight the electricity consumption characteristics of users in household and social scenarios, and combined with user role information, show users' preferences for certain devices or packages.

[0124] Based on clustering or classification algorithms, the target user portraits are grouped, such as "household electricity energy-saving type", "social scenario-dominated type", "heavy electric vehicle usage type", etc. Different types of users will receive differentiated services in subsequent electricity package recommendations and electricity equipment deployment suggestions.

[0125] Through the above steps, this embodiment can, on the basis of "household electricity information" and "social electricity information", combine "user role information" to deeply depict the portraits of users. Household electricity consumption characteristics focus on users' daily electricity consumption at home, peak-valley distribution, equipment preferences, seasonal impacts, and behavior patterns. Social electricity consumption characteristics analyze users' electricity consumption contribution, stay time, and specific equipment usage in public areas. User role information adds user identity attributes to make the portrait more accurate. The finally formed target user portrait can fully reflect users' electricity consumption habits and preferences in different scenarios, providing reliable and refined data support for subsequent (such as target electricity package recommendations, suggestions on the installation locations of target electricity equipment, etc.).

[0126] In some examples, the above user role information includes household users, social users, and hybrid users.

[0127] The above data fusion based on the above user role information, the above household electricity consumption characteristics, and the above social electricity consumption characteristics to depict the target user portrait of each of the above target users includes:

[0128] According to the above user role information and the weight matching table, determine the target weight information corresponding to the above user role information;

[0129] Determine the features to be fused according to the above user role information;

[0130] Among them, when the above user role information is that of a family-type user, the above features to be fused are obtained based on a feature priority screening operation; when the above user role information is that of a social-type user, the above features to be fused are obtained based on a behavioral feature matching operation; when the above user role information is that of a hybrid-type user, the above features to be fused are obtained based on a multi-layer feature fusion operation.

[0131] Exemplarily, data fusion is performed according to user role information (family-type user, social-type user, and hybrid-type user), as well as household electricity consumption characteristics and social electricity consumption characteristics, to depict the target user portrait of the target user.

[0132] According to the user role information and the weight matching table, determine the target weight information corresponding to the user role information. The user role information can be divided into three categories: family-type user, social-type user, and hybrid-type user. Family-type users mainly rely on household electricity consumption characteristics, and the weight of social electricity consumption characteristics is relatively low. Social-type users mainly rely on social electricity consumption characteristics, and the weight of household electricity consumption characteristics is relatively low. Hybrid-type users combine both household electricity consumption characteristics and social electricity consumption characteristics.

[0133] The weight matching table is used to assign different target weight information to users with different role information:

[0134] W 家庭 +W 社会 = 1

[0135] Family-type user: W 家庭 >W 社会， W 家庭 = 0.8, W 社会 = 0.2.

[0136] Social-type user: W 社会 >W 家庭， W 家庭 = 0.3, W 社会 = 0.7.

[0137] Hybrid-type user: W 社会 ≈W 家庭， W 家庭 = 0.3, W 社会 = 0.7.

[0138] Family-type users obtain the features to be fused based on the feature priority screening operation. Since family-type users mainly rely on household electricity consumption characteristics, the system will screen the most representative features in the household electricity consumption data. The feature priority screening operation sorts the features according to their importance and selects the features with higher weights. The main features can include the average daily household electricity consumption feature (E dai ly ), the household peak-valley electricity consumption ratio feature (R peak－valley), household device usage characteristics (U device ) and seasonal electricity consumption characteristics (S scasonal ).

[0139] Household feature vector = [E daily , R peak-val ley , U device , S seasona

[0140] Since social users mainly rely on social electricity consumption characteristics, the system will identify the main behavior patterns of users in social public areas and match the corresponding characteristics. Appropriate characteristics are selected based on the user's behavior patterns (such as stay time, device usage type, etc.). The main characteristics can include social contribution electricity consumption (E social ), stay time characteristics (T stay ), activity type and social device usage characteristics (U social－device ) and regional electricity consumption ratio characteristics (R region ).

[0141] Social feature vector = [E social , T stay , U social-device , R region

[0142] Hybrid users rely on both household electricity consumption characteristics and social electricity consumption characteristics, and multi-layer feature fusion is required to ensure that both types of feature information can effectively participate in the construction of the user portrait. Multi-layer feature fusion operation: weighted average or deep learning modeling is performed at the data level to achieve the comprehensive utilization of the two types of features.

[0143] Fusion feature vector = W 家庭 × household feature vector + W 社会 × social feature vector

[0144] If W 家庭 = 0.6, W 社会 = 0.4, then:

[0145] Fusion feature vector = 0.6 × [E daily , R peak－valley , U device , S seasonal + 0.4 ×

[0146] [E social , T stay , U social－device , R region

[0147] Finally, the system combines the user role information, target weight information, and features to be fused to generate a user portrait. The calculation formula for the user portrait can be:​​​

[0148] U profi le = W 家庭 × F 家庭 + W 社会 × F 社会

[0149] Where: U profile represents the target user profile, F 家庭 is the household electricity consumption characteristic, F 社会 is the social electricity consumption characteristic, W 家庭 and W 社会 are role weights.

[0150] In some examples, the above target electricity package is a combined household and social electricity package,

[0151] The specific steps for determining the above target electricity package include:

[0152] Construct a state space S based on the above household electricity consumption characteristics, social electricity consumption characteristics, the above geographical location information, and historical feedback information;

[0153] Construct an action space A based on the combined household and social electricity package;

[0154] Construct a reward function R based on the package subscription reward, user feedback evaluation reward, power grid load optimization reward, electricity consumption behavior pattern reward, and long-term power sustainability reward;

[0155] Initialize the Q-table based on the above state space S and action space A;

[0156] Set the initial state S0;

[0157] Based on the current state St, select an action At using the greedy strategy;

[0158] Execute the above selected action At in the current state St;

[0159] After executing the action At, update the reward Rt according to the user feedback and the change in the power grid load, and transfer the environmental state to St+1;

[0160] Update the Q value of the current state-action pair;

[0161] In the case where the change in the Q value of all state-action pairs is less than the set threshold or the number of training steps reaches the maximum number of training steps, obtain the optimized Q-table;

[0162] Select an optimized action A* based on the above target user profile and the above optimized Q-table;

[0163] Generate a combined household and social electricity package based on the above optimized action A*.

[0164] Exemplarily, a state space S is constructed, and the state space S includes home electricity consumption characteristics F H , social electricity consumption characteristics F S and geographical location information L. The home electricity consumption characteristics F H include the average daily electricity consumption E of the home dai ly , the peak-valley electricity consumption ratio R peak－val ley , the home equipment usage characteristics U device and the seasonal electricity consumption characteristics S seasonal The social electricity consumption characteristics F S include the electricity consumption E contributed to society social , the social activity stay time T stay , the social equipment usage characteristics U social－device and the regional electricity consumption ratio R region The geographical location information L includes residential areas, commercial areas, industrial areas, transportation infrastructure, user movement range, charging piles, and public facility density, etc. The historical feedback information H includes the satisfaction of users' previous subscribed packages, the matching degree between the actual electricity consumption of the subscribed packages and the packages, and the grid load and user behavior data.

[0165] The state space can be expressed as:

[0166] S = {F H , F S , L, H}

[0167] The action space A represents different combined home and social electricity consumption packages, that is, the types of packages that users can choose, such as: standard home package + night social charging package, tiered home package + mall charging discount package, intelligent home management package + industrial area work electricity package, and time-of-use home package + low-price social electricity consumption package during peak periods.

[0168] The action space can be defined as: A = {A 1 , A 2 , …, A n}

[0169] Among them, each action A i represents a configuration of a combined home and social electricity consumption package.

[0170] The reward function R is composed of several factors such as package subscription reward, user feedback evaluation reward, grid load optimization reward, electricity consumption behavior pattern reward, and long-term power sustainability reward.

[0171] If the package selected by the user conforms to the historical package preference, a package subscription reward R is given package :

[0172] Rpackage = αP(A i )

[0173] where P(A i ) is the historical subscription probability of Package A for the user, and α is the weight. i

[0174] If the user has a high evaluation of the package, give the customer feedback evaluation reward R feedback :

[0175] R feedback = βF(A i )

[0176] where F(A i ) is the feedback score of Package A by the user, and β is the weight. i

[0177] If the package optimizes the grid load distribution, give the grid load optimization reward R grid :

[0178] R grid = -γ|D grid -T optimal |

[0179] where D grid is the load demand of the current package, T optimal is the optimal grid load target, and γ is the load balancing weight.

[0180] If the package conforms to the user behavior pattern, give the electricity consumption behavior pattern reward R behavior :

[0181] R behavior = δB(A i )

[0182] where B(A i ) represents the matching degree of the package to the user behavior pattern, and δ is the weight.

[0183] If the package contributes to long-term power sustainability, give the long-term power sustainability reward R sustain :

[0184] R sustain = η×S(A i )

[0185] where S(A i ) represents the degree of promotion of the package to the use of renewable energy, and η is the weight.

[0186] The final total reward function:

[0187] R = R package + Rfeedback +R grid +R behavior +R sustain

[0188] Initialize the Q-learning training. First, initialize the Q-table:

[0189]

[0190] Then set the initial state S 0 :

[0191]

[0192] The Q-learning training process is as follows:

[0193] 1. Based on the current state S t Select an action A t , using the ε-greedy strategy:

[0194]

[0195] 2. Execute the selected action A t , and update the environmental state. Calculate the user feedback and the impact on the grid load after executing package A t , and calculate the reward R t :

[0196] S t+1 = f(S t , A t )

[0197] R t = R(S t , A t )

[0198] 3. Update the Q value, using the Bellman equation to update the Q value:

[0199]

[0200] where: α is the learning rate, γ is the discount factor, and max A′ Q(S t+1 , A′) represents the optimal Q value for the next step.

[0201] 4. Termination training condition. If all Q value changes are less than the set threshold δQ < ∈ or the number of training steps reaches the maximum number of steps, the training terminates.

[0202] Select the optimal action through the optimized Q-table:

[0203] A * = argmaxQ(S, A)

[0204] The argmax is to find the optimal option among multiple possible options.

[0205] Generate the final combined household and social electricity consumption package:

[0206] Optimal package = A *

[0207] In this embodiment, through reinforcement learning (Q-learning) and a multi-factor reward mechanism, the intelligent optimization of the combined household and social electricity consumption package is achieved. It can achieve accurate matching of user portraits, improve the recommendation accuracy, optimize the grid load distribution, and reduce the grid pressure. Based on feedback dynamic optimization, the user experience can be improved, and through adaptive adjustment of reinforcement learning, the system becomes more intelligent. The method proposed in this embodiment can reduce the user's electricity consumption cost, optimize the grid load, and improve the utilization rate of green energy.

[0208] In some examples, the above-mentioned target electrical equipment recommendation information includes social electrical equipment recommendation information.

[0209] The specific steps to determine the above-mentioned social electrical equipment recommendation information include:

[0210] Determine the equipment demand rate of the target sub-region according to all the above-mentioned target user portraits in the above-mentioned target region;

[0211] Obtain the equipment coverage rate of each target sub-region;

[0212] Determine the number of new devices and the types of new devices according to the above-mentioned equipment coverage rate, the above-mentioned equipment demand rate, and the equipment demand priority;

[0213] Determine the objective function according to the package benefit, equipment installation cost, equipment installation cost, equipment operation cost, and equipment coverage benefit;

[0214] Define the constraint conditions according to the user package selection constraint, the user package selection constraint, the total budget constraint, and the grid load limit;

[0215] Perform objective optimization according to the above-mentioned objective function and the above-mentioned constraint conditions to obtain the social electrical equipment recommendation information.

[0216] Exemplarily, determine the equipment demand rate of the target sub-region according to all the target user portraits in the target region. Divide the target region into several sub-regions (such as residential areas, commercial areas, industrial areas, transportation hubs).

[0217] Count the target user portraits in each sub-region k and analyze the equipment usage requirements in that region.

[0218] The formula for calculating the equipment demand rate can be:

[0219]

[0220] D k is the equipment demand rate for the target sub - region k, N active is the number of target users using this type of equipment within sub - region k, N total is the total number of target users within sub - region k, W i is the electricity consumption weight of user i in this area (such as activity weight), f i is the usage frequency of user i for this equipment (such as the number of times used per week). α i is the equipment availability coefficient of user i (if there is less of this equipment, the demand rate should be higher), β k is the geographical influence factor of sub - region k (for example, the demand for equipment in commercial areas and residential areas is different).

[0221] The equipment coverage rate C can be calculated based on the following formula k :

[0222]

[0223] C k is the equipment coverage rate for the target sub - region k, N existing is the number of existing such equipment within sub - region k, N active is the number of users with demand for this equipment within sub - region k, U i is the utilization rate of equipment i (reflecting the load situation of the equipment, such as whether it is fully loaded for a long time). λ i is the service capacity coefficient of equipment i (such as the power of a charging pile and the single - charge duration). W j is the demand weight of user j for this type of equipment in this area (for example, users who use it frequently are more important than those who use it occasionally). α j is the availability demand coefficient of user j (whether the user often uses this equipment in this area). β k is the regional equipment accessibility adjustment coefficient (for example, for correction when the equipment is unevenly distributed).

[0224] The new equipment demand N add,k can be calculated based on the following formula:

[0225] N add,k =(D k -C k )×N active

[0226] Among them, (D k -C k ) represents the gap between equipment demand and the current coverage rate, N active is the number of users with demand

[0227] According to the equipment demand priority P k (such as the priority of charging piles is higher than that of smart street lights), give priority to adding high-priority equipment:

[0228]

[0229] The equipment priority is set by the government and the power grid company. For example: public charging pile P k = 0.8, smart street light P k = 0.6, energy storage equipment P k = 0.7.

[0230] Determine the objective function according to the package benefit, equipment installation cost, equipment operation cost and equipment coverage benefit. The objective function can be defined as maximizing the overall benefit of social electricity-consuming equipment, that is:

[0231]

[0232] Where: R k (package benefit) is the income from the electricity consumption packages subscribed by users, C install,k (equipment installation cost) is the equipment construction cost, such as the installation of charging piles or smart street lights, C operate，k (equipment operation cost) is the long-term operation and maintenance cost, such as maintenance, power supply, etc.

[0233] For example: charging pile package income: R charging = 5000 yuan / year, charging pile installation cost: C instal l，charging = 3000 yuan, charging pile operation cost: C operate，charging = 1000 yuan / year.

[0234] Then the contribution value of the objective function:

[0235] Z charging = 5000 - 3000 - 1000 = 1000

[0236] To ensure the rationality of the recommended equipment, the following user package selection constraints, user package selection constraints, total budget constraints and power grid load limit definition constraints need to be satisfied.

[0237] 1. The user package selection constraint can be: ∑ k R k ≥ the user's minimum income requirement to ensure that the income brought by the equipment meets the minimum expectation.

[0238] 2. The total budget constraint can be: ∑ k (C install,k + C operate,k ) ≤ B max , so that the equipment investment cost does not exceed the budget Bmax

[0239] 3. The grid load limit can be: ∑ k L k ≤L grid-max ,L k represents the load increment brought by the newly added equipment, ensuring that it does not exceed the grid carrying capacity L grid－max

[0240] By solving the objective function:

[0241]

[0242] to make it satisfy the constraint conditions:

[0243]

[0244] Linear Programming (LP) or Integer Programming (IP) can be used to calculate the optimal equipment deployment plan under constraint conditions such as budget load limit.

[0245] The method provided in this embodiment realizes the scientific planning of social electricity-consuming equipment through data analysis and optimization algorithms. By combining user portraits and equipment demand priorities, it ensures the balance between equipment supply and demand. Under budget constraints, the overall revenue is improved through the optimal combination plan. The number of equipment can be reasonably planned to avoid overloading of the power grid. It can guide the reasonable deployment of new energy equipment (such as energy storage systems) and improve the utilization rate of renewable energy.

[0246] Such as Figure 2 shown, this application proposes a device for power marketing data governance and operation efficiency improvement, including:

[0247] The first acquisition unit 21 is used to acquire the household electricity consumption information and social electricity consumption information of multiple target users in the target area;

[0248] The second acquisition unit 22 is used to perform data cleaning operations on the household electricity consumption information and the social electricity consumption information of each target user to obtain the cleaned household electricity consumption information and the cleaned social electricity consumption information;

[0249] The characterization unit 23 is used to characterize the target user portraits of each target user according to the cleaned household electricity consumption information and the cleaned social electricity consumption information of each;

[0250] A generating unit 24 is configured to generate a target power consumption package and target power consumption device recommendation information according to the geographical location information and power consumption characteristic information of all target user portraits in the target area, where the target power consumption devices include household power consumption devices and social power consumption devices. In the case where the target power consumption device is a social power consumption device, the target power consumption device recommendation information further includes a recommended installation location for the social power consumption device.

[0251] As Figure 3 shown in the figure, an embodiment of the present application further provides an electronic device 300, including a memory 310, a processor 320, and a computer program 311 stored on the memory 310 and executable on the processor. When the processor 320 executes the computer program 311, it implements the steps of any of the methods for power marketing data governance and operation efficiency improvement described above.

[0252] Since the electronic device introduced in this embodiment is the device used to implement a power marketing data governance and operation efficiency improvement device in an embodiment of the present application, based on the method introduced in the embodiment of the present application, those skilled in the art can understand the specific implementation manners and various forms of change of the electronic device in this embodiment. Therefore, the specific implementation of how this electronic device implements the method in the embodiment of the present application will not be described in detail here. As long as the device used by those skilled in the art to implement the method in the embodiment of the present application belongs to the scope of protection of the present application.

[0253] In the specific implementation process, when the computer program 311 is executed by the processor, it can implement any implementation manner in the corresponding embodiment of the first aspect.

[0254] It should be noted that in the above embodiments, the descriptions of the various embodiments have their own emphases. For the parts not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0255] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0256] This application is described with reference to the flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, as well as the combination of flows and / or blocks in the flowchart and / or block diagram. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate a means for implementing the functions specified in the Figure 1 one or more flows and / or blocks Figure 1 one or more blocks.

[0257] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including an instruction means that implements the functions specified in the Figure 1 one or more flows and / or blocks Figure 1 one or more blocks.

[0258] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in the Figure 1 one or more flows and / or blocks Figure 1 one or more blocks.

[0259] Embodiments of the present application also provide a computer program product that includes computer software instructions. When the computer software instructions run on a processing device, the processing device is caused to execute the process of power marketing data governance and operation efficiency improvement in the corresponding embodiments.

[0260] A computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, the processes or functions according to the embodiments of the present application are generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from a website, computer, server, or data center to another website, computer, server, or data center by wire (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wirelessly (such as infrared, wireless, microwave, etc.). The computer-readable storage medium may be any available medium that can be stored by a computer or a data storage device such as a server or data center that includes one or more integrated available media. The available medium may be a magnetic medium (such as a floppy disk, hard disk, magnetic tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid state disk (SSD)), etc.

[0261] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0262] In several embodiments provided in the present application, it should be understood that the disclosed systems, devices, and methods may be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Another point is that the couplings, direct couplings, or communication connections shown or discussed with each other may be indirect couplings or communication connections through some interfaces, devices, or units, and may be in electrical, mechanical, or other forms.

[0263] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0264] In addition, in each embodiment of the present application, each functional unit can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0265] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in the various embodiments of the present application. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0266] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the various embodiments of the present application.

Claims

1. A method for improving power marketing data management and operational efficiency, characterized in that: include: Acquire household electricity consumption information and social electricity consumption information of multiple target users in the target area; Performing data cleaning operations on the household electricity usage information and the social electricity usage information of each target user to obtain cleaned household electricity usage information and cleaned social electricity usage information; Characterize a target user portrait of each target user according to each of the cleaned household electricity usage information and the cleaned social electricity usage information; A target electricity package and target electricity equipment recommendation information are generated based on the geographic location information and electricity usage characteristic information of all target user portraits in the target area, wherein the target electricity equipment includes household electricity equipment and social electricity equipment. When the target electricity equipment is a social electricity equipment, the target electricity equipment recommendation information also includes a recommended installation location for the social electricity equipment.

2. The method for improving power marketing data management and operational efficiency according to claim 1, characterized in that: The step of obtaining household electricity consumption information and social electricity consumption information of multiple target users in the target area includes: Obtain data information of the target user's smart appliance control client and the target user's smart meter electricity usage information; Determine the household electricity usage information according to the data information of the smart appliance control client and the electricity usage information of the smart meter; Obtaining the mobile terminal location information of the target user; In the case where the mobile terminal location information indicates that the mobile terminal is in a social public area, the mobile terminal location information is associated with social electricity usage information to obtain the social electricity usage information.

3. The method for improving power marketing data management and operational efficiency according to claim 2, characterized in that: The social public areas include commercial areas, industrial areas and transportation infrastructure. The associating the mobile terminal location information with social electricity usage information to obtain the social electricity usage information includes: When the mobile terminal location information stays for a time greater than a preset time, obtaining the target user's social electricity usage behavior; Obtaining electricity consumption type weight information of the social electricity consumption behavior; Determine the residence time weight information according to the residence time information; The social electricity consumption information is determined according to the electricity consumption type weight information, the residence time weight information and the total social electricity consumption information.

4. The method for improving power marketing data management and operational efficiency according to claim 1, characterized in that: The target user portrait of each target user is depicted based on each cleaned household electricity usage information and the cleaned social electricity usage information, including: Extracting household electricity usage characteristics based on the cleaned household electricity usage information, wherein the household electricity usage characteristics include household daily average electricity usage characteristics, household peak-valley electricity usage ratio characteristics, household equipment usage characteristics, seasonal electricity usage characteristics, and electricity usage behavior pattern characteristics; Extracting social electricity consumption characteristics based on the cleaned social electricity consumption information, wherein the social electricity consumption characteristics include social contribution electricity consumption, residence time characteristics, activity type and social equipment use characteristics, and regional electricity consumption ratio characteristics; Get the user role information of the target user; Data fusion is performed according to the user role information, the household electricity usage characteristics and the social electricity usage characteristics to characterize a target user portrait of each target user.

5. The method for improving power marketing data management and operational efficiency according to claim 4 is characterized in that: The user role information includes family users, social users and mixed users. The data fusion is performed according to the user role information, the household electricity usage characteristics and the social electricity usage characteristics to characterize the target user portrait of each target user, including: Determine target weight information corresponding to the user role information according to the user role information and the weight matching table; Determining features to be fused according to the user role information; Among them, when the user role information is a family user, the features to be fused are obtained based on a feature priority screening operation; when the user role information is a social user, the features to be fused are obtained based on a behavioral feature matching operation; when the user role information is a mixed user, the features to be fused are obtained based on a multi-layer feature fusion operation.

6. The method for improving power marketing data management and operational efficiency according to claim 4, characterized in that: The target electricity package is a combined household and social electricity package. The specific steps of determining the target electricity package include: Constructing a state space S according to the household electricity consumption characteristics, social electricity consumption characteristics, the geographic location information and historical feedback information; Construct action space A based on household and social combined electricity packages; Construct a reward function R based on package subscription rewards, user feedback evaluation rewards, grid load optimization rewards, electricity consumption behavior pattern rewards, and long-term electricity sustainability rewards; Initialize the Q table according to the state space S and the action space A; Set the initial state S0; According to the current state St, use the greedy strategy to select action At; Execute the selection action At in the current state St; After executing action At, the reward Rt will be updated according to user feedback and grid load changes, and the environmental state will be transferred to St+1; Update the Q value of the current state-action pair; When the Q value change of all state-action pairs is less than the set threshold or the number of training steps reaches the maximum number of training steps, the optimized Q table is obtained; Selecting an optimization action A* according to the target user portrait and the optimized Q table; A household and society combined electricity consumption package is generated according to the optimization action A*.

7. The method for improving power marketing data management and operational efficiency according to claim 4, characterized in that: The target electric equipment recommendation information includes social electric equipment recommendation information, The specific steps of determining the recommended information of the social electrical equipment include: Determine the equipment demand rate of the target sub-area according to all the target user portraits in the target area; Get the device coverage of each target sub-area; Determine the number and type of new equipment according to the equipment coverage rate, the equipment demand rate and the equipment demand priority; Determine the objective function based on package benefits, equipment installation costs, equipment installation costs, equipment operating costs, and equipment coverage benefits; Define constraints based on user package selection constraints, user package selection constraints, total budget constraints, and grid load limits; Target optimization is performed according to the objective function and the constraint conditions to obtain recommended information on social electrical equipment.

8. A device for managing power marketing data and improving operational efficiency, characterized in that: include: A first acquisition unit is used to acquire household electricity consumption information and social electricity consumption information of multiple target users in a target area; A second acquisition unit is used to perform a data cleaning operation on the household electricity usage information and the social electricity usage information of each target user to obtain cleaned household electricity usage information and cleaned social electricity usage information; A characterization unit, used for characterizing a target user portrait of each target user according to each of the cleaned household electricity usage information and the cleaned social electricity usage information; A generation unit is used to generate target electricity packages and target electricity equipment recommendation information based on the geographic location information and electricity consumption characteristic information of all target user portraits in the target area, wherein the target electricity equipment includes household electricity equipment and social electricity equipment. When the target electricity equipment is a social electricity equipment, the target electricity equipment recommendation information also includes a recommended installation location for the social electricity equipment.

9. An electronic device, comprising: A memory and a processor, characterized in that the processor is used to implement the steps of the method for improving power marketing data governance and operational efficiency as described in any one of claims 1 to 7 when executing the computer program stored in the memory.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for improving power marketing data governance and operational efficiency as described in any one of claims 1-7 are implemented.

Images