User portrait construction method, system and equipment based on user feature fusion analysis

Abstract

The invention discloses a user portrait construction method, system and device based on user feature fusion analysis, and the method comprises the steps: responding to a received user portrait construction request, and obtaining a user list corresponding to the user portrait construction request; according to the user list, first basic information and first electricity utilization information of a first user are obtained, and the first user belongs to users in the user list; according to the first basic information, based on a preset first portrait generation model, obtaining a basic portrait of the first user; when the first user does not belong to the insurance supply user, obtaining an adjustment portrait of the first user based on a preset second portrait generation model according to the first electricity consumption information; and generating a user portrait of the first user according to the basic portrait and the adjustment portrait of the first user. At least the problems that refined load adjustment is not carried out according to the actual situation of a user when the power utilization load is insufficient at present, and the influence on production and life is large when the power supply needs to be limited are solved.

Description

Technical Field

[0001] The present application relates to the field of power management technology, and in particular to a method, system and device for constructing a user portrait based on user feature fusion analysis. Background Art

[0002] Power rationing and blackouts are usually taken as a response measure when the contradiction between power supply and demand intensifies and the power system faces pressure. In recent years, with the rapid development of the economy and the improvement of people's living standards, the demand for electricity has continued to grow, while the power supply is affected by many factors, such as weather, energy prices, equipment failures, etc., resulting in the imbalance between power supply and demand. Especially during peak periods of electricity consumption such as high temperatures in summer and cold winter, the pressure on power supply is greater, which is prone to cause power rationing and blackouts.

[0003] According to the provisions of DL / T836-2012 "Regulations on Power Supply Reliability Evaluation for Power Supply System Users", power rationing refers to the limited supply of electricity to the part where demand exceeds supply based on the supply and demand relationship of electricity under the planned operation mode of the power system. In other words, there is generally a power shortage when power rationing occurs.

[0004] At present, when electricity load is tight, the granularity of load management is large due to the lack of precision in the portrait of electricity users, and a "one-size-fits-all model" is often adopted. When power rationing is needed, it has a great impact on production and life. Summary of the invention

[0005] The present invention provides a method, system and device for constructing a user portrait based on user feature fusion analysis, and provides a refined electricity user portrait construction solution, which at least solves the current problem that when the electricity load is tight, the electricity user portrait is not refined enough, resulting in a large granularity of load management and often adopting a "one-size-fits-all model", which has a great impact on production and life when power rationing is needed.

[0006] This application provides a method for constructing a user profile based on user feature fusion analysis, including:

[0007] In response to receiving the user portrait building request, obtaining a user list corresponding to the user portrait building request;

[0008] According to the user list, first basic information and first power usage information of a first user are obtained, where the first user belongs to the users in the user list;

[0009] According to the first basic information, based on a preset first portrait generation model, a basic portrait of the first user is obtained;

[0010] Determining whether the first user is a guaranteed supply user according to at least one tag in the basic portrait of the first user;

[0011] When the first user is not a guaranteed supply user:

[0012] According to the first electricity usage information, based on a preset second portrait generation model, obtaining an adjustment portrait of the first user;

[0013] A user portrait of the first user is generated according to the basic portrait and the adjusted portrait of the first user.

[0014] Optionally, the step of responding to receiving a user profile building request and obtaining a user list corresponding to the user profile building request includes:

[0015] In response to receiving the user portrait building request, obtaining administrator information of a first administrator who sent the user portrait building request;

[0016] According to the administrator information, obtaining a first area corresponding to the first administrator;

[0017] According to the first area, a user list of the first area is obtained, which is a user list corresponding to the user portrait building request.

[0018] Optionally, obtaining first basic information and first power usage information of a first user according to the user list includes:

[0019] Obtaining a unique identifier of the first user according to the user list;

[0020] Acquire at least one basic information of the first user from a user information database according to the unique identifier of the first user, where the at least one basic information belongs to the first basic information;

[0021] According to the unique identifier of the first user, first electricity usage information of the first user is obtained from an electricity usage database.

[0022] Optionally, before obtaining the basic portrait of the first user according to the first basic information based on a preset first portrait generation model, the method further includes:

[0023] Establishing a user tag system, wherein the user tag system includes at least one basic tag;

[0024] A basic mapping between user information and basic tags is established according to the user tag system to obtain a first portrait generation model.

[0025] Optionally, obtaining the adjustment portrait of the first user according to the first electricity usage information and based on a preset second portrait generation model includes:

[0026] According to the first power usage information, first time series data and second time series data are obtained, wherein the first time series data is configured as power usage time series data of the first user when power supply is normal, and the second time series data is configured as power usage time series data of the first user when power supply is short;

[0027] Obtaining third time series data according to the first time series data, wherein the third time series data is configured as theoretical power consumption time series data of the first user when power supply is short;

[0028] According to the second time series data and the third time series data, based on a preset second portrait generation model, an adjustment portrait of the first user is obtained.

[0029] Optionally, obtaining the adjustment portrait of the first user according to the second time series data and the third time series data includes:

[0030] Obtaining first load adjustment data of the first user according to the second time series data and the third time series data;

[0031] According to the first load adjustment data, based on a preset second portrait generation model, an adjustment portrait of the first user is obtained, and the adjustment portrait is used to characterize the conditions for the user to perform load adjustment.

[0032] Optionally, obtaining the adjustment portrait of the first user according to the first load adjustment data based on a preset second portrait generation model includes:

[0033] Acquire power supply shortage time series data of the area where the first user is located, where the power supply shortage time series data is configured to represent the ratio and / or difference between the actual power supply and the predicted power consumption of the corresponding area;

[0034] Dividing the power supply shortage time series data into at least two time periods according to the ratio and / or difference between the actual power supply and the predicted power consumption of the corresponding area;

[0035] According to the at least two time periods, dividing the first load adjustment data into at least two load adjustment sub-data matching the time periods;

[0036] According to the at least two load adjustment data, based on a preset second portrait generation model, an adjustment portrait of the first user is obtained, and the adjustment portrait is used to characterize the conditions for the user to perform load adjustment under different power supply shortage situations in the corresponding area.

[0037] On the other hand, a user portrait construction system based on user feature fusion analysis includes a user portrait generation platform and a power data management platform:

[0038] The user portrait generation platform is configured as follows:

[0039] In response to receiving the user portrait building request, obtaining a user list corresponding to the user portrait building request;

[0040] According to the user list, first basic information and first power usage information of a first user are obtained, where the first user belongs to the users in the user list;

[0041] According to the first basic information, based on a preset first portrait generation model, a basic portrait of the first user is obtained;

[0042] Determining whether the first user is a guaranteed supply user according to at least one tag in the basic portrait of the first user;

[0043] When the first user is not a guaranteed supply user:

[0044] According to the first electricity usage information, based on a preset second portrait generation model, obtaining an adjustment portrait of the first user;

[0045] generating a user profile of the first user according to the basic profile and the adjusted profile of the first user;

[0046] The power data management platform is configured as follows:

[0047] In response to the request of the user portrait generation platform, the first basic information and the first electricity usage information of the first user are sent to the user portrait generation platform.

[0048] Optionally, obtaining the adjustment portrait of the first user according to the first electricity usage information and based on a preset second portrait generation model includes:

[0049] According to the first power usage information, first time series data and second time series data are obtained, wherein the first time series data is configured as power usage time series data of the first user when power supply is normal, and the second time series data is configured as power usage time series data of the first user when power supply is short;

[0050] Obtaining third time series data according to the first time series data, wherein the third time series data is configured as theoretical power consumption time series data of the first user when power supply is short;

[0051] According to the second time series data and the third time series data, based on a preset second portrait generation model, an adjustment portrait of the first user is obtained.

[0052] On the other hand, an embodiment of the present application further provides a computer device, which includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the above method.

[0053] On the other hand, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, and a processor executes the computer program to implement the above method.

[0054] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0055] The present invention provides a method, system and device for constructing a user portrait based on user feature fusion analysis, including: in response to receiving a user portrait construction request, obtaining a user list corresponding to the user portrait construction request; obtaining first basic information and first power consumption information of a first user according to the user list, wherein the first user belongs to the users in the user list; obtaining a basic portrait of the first user according to the first basic information based on a preset first portrait generation model; judging whether the first user belongs to a guaranteed supply user according to at least one label in the basic portrait of the first user; when the first user does not belong to a guaranteed supply user: obtaining an adjustment portrait of the first user according to the first power consumption information based on a preset second portrait generation model; generating a user portrait of the first user according to the basic portrait and the adjustment portrait of the first user. The present invention provides a refined power user portrait construction scheme, which at least solves the problem that when the power load is tight, the power user portrait is not refined enough, resulting in a large granularity of load management, and often adopts a "one-size-fits-all model", which has a greater impact on production and life when power restriction is required. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the specific implementation of the present application or the technical solution in the prior art, the following is a brief introduction to the drawings required for the specific implementation or the prior art description. In all drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, each element or part is not necessarily drawn according to the actual scale.

[0057] Figure 1 A flowchart of a method for constructing a user portrait based on user feature fusion analysis in this application;

[0058] Figure 2 This is a schematic diagram of the structure of a computer device in this application.

[0059] Markings in the figure: 101 - processor, 102 - communication bus, 103 - network interface, 104 - user interface, 105 - memory.

[0060] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0061] In order to enable those skilled in the art to better understand the scheme of the present disclosure, the technical scheme in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in the field without creative work should fall within the scope of protection of the present disclosure.

[0062] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products, or devices.

[0063] Example 1

[0064] like Figure 1 As shown, a method for constructing a user portrait based on user feature fusion analysis includes:

[0065] S1. In response to receiving a user portrait building request, obtain a user list corresponding to the user portrait building request.

[0066] Optionally, the user profile building request may be a request actively initiated by a system operator or system administrator, or automatically initiated by a system operator, system administrator or system according to a preset cycle, or automatically initiated by a system operator, system administrator or system according to a predicted power outage or power restriction;

[0067] Optionally, the user in the user list is a system operator, a system administrator, or a user in the electricity consumption area corresponding to the system who made the user portrait construction request. If a user subject corresponds to multiple electricity meters in the area, each electricity meter is a user.

[0068] S2. Obtain first basic information and first electricity usage information of the first user according to the user list.

[0069] Optionally, the first user is a user in a user list.

[0070] Optionally, the first basic information includes at least information declared or collected when the first user opens an account.

[0071] Optionally, the first electricity usage information at least includes electricity usage timing data of the first user.

[0072] S3. According to the first basic information, based on a preset first portrait generation model, obtain a basic portrait of the first user.

[0073] Optionally, according to the first basic information, based on a preset first portrait generation model, a method for obtaining a basic portrait of the first user includes: obtaining basic information data of the first user; performing data cleaning and preprocessing on the basic information data; using a preset value or a pre-trained first portrait generation model or a mapping relationship model; and performing feature extraction and evaluation on the preprocessed basic information data through a talent portrait model to obtain a basic portrait of the first user.

[0074] Specifically, the labels of the basic portrait include: one or more of the following: voltage level information, electricity consumption category information, industrial information, sector information, temporary power sign information, important user sign information, five-limit sign information, six-guarantee sign information, two-high sign information, area information, street and town information, etc.

[0075] S4. Determine whether the first user is a guaranteed user based on at least one label in the basic portrait of the first user.

[0076] When the first user is not a guaranteed supply user:

[0077] S5. According to the first electricity usage information, based on a preset second portrait generation model, an adjustment portrait of the first user is obtained.

[0078] Optionally, the adjustment portrait label of the first user includes: adjustable on holidays, adjustable on weekdays, electricity consumption can be reduced by 50% on holidays, electricity consumption can be reduced by 30% on weekdays, etc. Adjustable includes adjustable at will or adjustable to a certain proportion or a certain value.

[0079] It can also include: adjustable in specific seasons, adjustable in specific months, etc.

[0080] It can also include: high temperature adjustable, low temperature adjustable, etc.

[0081] It can also include: adjustable from 6 to 8 o'clock, adjustable from 8 to 11 o'clock, adjustable from 11 to 12 o'clock, adjustable from 12 to 14 o'clock, adjustable from 14 to 15 o'clock, adjustable from 15 to 18 o'clock, adjustable from 18 to 19 o'clock, adjustable from 19 to 21 o'clock, adjustable from 21 to 22 o'clock, adjustable during valley hours, etc.

[0082] S6. Generate a user portrait of the first user based on the basic portrait and the adjusted portrait of the first user.

[0083] Optionally, the basic portrait of the first user and the adjusted portrait of the first user may be stored separately; further, before step S3, it also includes: searching according to the first user to determine whether there is a historical basic portrait of the first user; if there is a historical basic portrait of the first user, determining whether there is a change application or change information associated with the first user; if not, using the historical basic portrait as the basic portrait, otherwise executing step S3.

[0084] Through the above scheme, user portraits are generated according to the user's basic information and electricity consumption information. The user portraits are highly refined, and users who are less affected by power restrictions or who are given priority for power restrictions can be quickly screened out when power restrictions are needed. This at least solves the current problem that when the electricity load is tight, the granularity of load management is large, and a "one-size-fits-all model" is often adopted due to the lack of refinement in the electricity user portraits, which leads to a large impact on production and life when power restrictions are needed.

[0085] Example 2

[0086] This embodiment, based on Embodiment 1, provides a method for constructing a user portrait based on user feature fusion analysis, including:

[0087] S1. In response to receiving a user portrait building request, obtain a user list corresponding to the user portrait building request.

[0088] Optionally, the user profile building request may be a request actively initiated by a system operator or system administrator, or automatically initiated by a system operator, system administrator or system according to a preset cycle, or automatically initiated by a system operator, system administrator or system according to a predicted power outage or power restriction;

[0089] Optionally, the user in the user list is a system operator, a system administrator, or a user in the electricity consumption area corresponding to the system who made the user portrait construction request. If a user subject corresponds to multiple electricity meters in the area, each electricity meter is a user.

[0090] Optionally, in response to receiving the user profile building request, obtaining a user list corresponding to the user profile building request includes:

[0091] In response to receiving the user portrait building request, obtaining administrator information of a first administrator who sent the user portrait building request;

[0092] According to the administrator information, a first region corresponding to the first administrator is obtained;

[0093] According to the first region, a user list of the first region is obtained as a user list corresponding to the user portrait building request.

[0094] Optionally, the first administrator may be a system operator, a system administrator or the system itself of a regional power grid system.

[0095] S2. Obtain first basic information and first power usage information of a first user according to the user list, where the first user is a user in the user list.

[0096] Optionally, the first basic information includes at least information declared or collected when the first user opens an account.

[0097] Optionally, the first electricity usage information at least includes electricity usage timing data of the first user.

[0098] Optionally, obtaining first basic information and first electricity usage information of a first user according to the user list includes:

[0099] Obtaining a unique identifier of the first user according to the user list;

[0100] Acquire at least one basic information of the first user from a user information database according to the unique identifier of the first user, wherein the at least one basic information belongs to the first basic information;

[0101] According to the unique identifier of the first user, first power usage information of the first user is obtained from the power usage database.

[0102] Optionally, the unique identifier of the first user may be a UID of the first user or other parameters that may be used to indicate the first user.

[0103] S3. According to the first basic information, based on a preset first portrait generation model, obtain a basic portrait of the first user.

[0104] Optionally, according to the first basic information, based on a preset first portrait generation model, a method for obtaining a basic portrait of the first user includes: obtaining basic information data of the first user; performing data cleaning and preprocessing on the basic information data; using a preset value or a pre-trained first portrait generation model or a mapping relationship model; and performing feature extraction and evaluation on the preprocessed basic information data through a talent portrait model to obtain a basic portrait of the first user.

[0105] Specifically, the labels of the basic portrait include: one or more of the following: voltage level information, electricity consumption category information, industrial information, sector information, temporary power sign information, important user sign information, five-limit sign information, six-guarantee sign information, two-high sign information, area information, street and town information, etc.

[0106] Optionally, before obtaining the basic portrait of the first user according to the first basic information and based on a preset first portrait generation model, the method further includes:

[0107] Establishing a user tag system, wherein the user tag system includes at least one basic tag;

[0108] A basic mapping between user information and basic tags is established according to the user tag system to obtain a first portrait generation model.

[0109] S4. Determine whether the first user is a guaranteed user based on at least one label in the basic portrait of the first user.

[0110] Optionally, the method for determining whether the first user is a guaranteed supply user further includes:

[0111] Acquire power restriction data of the first user in at least one cycle;

[0112] Determining whether the load reduction of the power-limiting data of the first user in at least one cycle is not greater than a preset threshold;

[0113] When the reduced load of the power-limiting data of the first user in at least one cycle is not greater than a preset threshold, the first user is a guaranteed-supply user.

[0114] When the first user is not a guaranteed supply user:

[0115] S5. According to the first electricity usage information, based on a preset second portrait generation model, an adjustment portrait of the first user is obtained.

[0116] Optionally, obtaining an adjustment portrait of the first user based on the first power usage information and a preset second portrait generation model includes:

[0117] According to the first power consumption information, first time series data and second time series data are obtained, wherein the first time series data is configured as the power consumption time series data of the first user when power supply is normal, and the second time series data is configured as the power consumption time series data of the first user when power supply is short;

[0118] According to the first time series data, third time series data is obtained, where the third time series data is configured as theoretical power consumption time series data of the first user when power supply is short;

[0119] According to the second time series data and the third time series data, based on a preset second portrait generation model, an adjustment portrait of the first user is obtained.

[0120] Specifically, according to the first time series data, the method for obtaining the third time series data includes:

[0121] Establishing a basic model for predicting electricity consumption time series data, which is configured to take time, weather and other data as input and electricity consumption time series data as output;

[0122] The basic model for predicting power consumption time series data is trained by using the first time series data or other power consumption data of the first user to obtain a power consumption time series data prediction model;

[0123] The time, weather and other data corresponding to the second time series data are input into the electricity consumption time series data prediction model to obtain the third time series data.

[0124] The following is a Python example that provides an example of using a linear regression model to predict electricity time series data. In actual applications, more complex models such as neural networks and decision trees can be selected according to needs;

[0125] Python

[0126] import numpy as np

[0127] from sklearn.linear_model import LinearRegression

[0128] #Sample data: Assume that time and weather are input features and electricity consumption is output feature

[0129] #Time feature (0 to 23 in the example represents the time of day), weather feature (0 to 1 represents the weather)

[0130] #Power consumption (randomly generated in the example)

[0131] time_weather_data=np.array([[0,0.1],[1,0.3],[2,0.2],[3,0.4],[4,0.5]])

[0132] electricity_data=np.array([10,12,11,14,15])

[0133] #Create a linear regression model

[0134] model=LinearRegression()

[0135] #Train the model using the first time series data for training

[0136] model.fit(time_weather_data,electricity_data)

[0137] #Use the trained model for prediction. Here, we assume that the second time series data is [5,0.6]

[0138] second_time_weather_data=np.array([[5,0.6]])

[0139] predicted_electricity=model.predict(second_time_weather_data)

[0140] print("Predicted third time series data (electricity consumption):",predicted_electricity)

[0141] The example uses simplified time features, where 0 to 23 represents the time of day, and weather features, where 0 to 1 represents good or bad weather, as well as randomly generated electricity consumption as example data.

[0142] The example uses the model.fit() method to train the model, taking time and weather data (time_weather_data) as input features and electricity consumption data (electricity_data) as output features.

[0143] Use the trained model (model.predict()) to predict the second time series data (second_time_weather_data) to obtain the predicted third time series data (electricity consumption).

[0144] Optionally, obtaining an adjustment portrait of the first user according to the second time series data and the third time series data includes:

[0145] Obtaining first load adjustment data of a first user according to the second time series data and the third time series data;

[0146] According to the first load adjustment data, based on a preset second portrait generation model, an adjustment portrait of the first user is obtained, and the adjustment portrait is used to characterize the conditions for the user to perform load adjustment.

[0147] Optionally, obtaining the adjustment portrait of the first user according to the first load adjustment data and based on a preset second portrait generation model includes:

[0148] Acquire power supply shortage time series data of the area where the first user is located, where the power supply shortage time series data is configured to represent the ratio and / or difference between the actual power supply and the predicted power consumption of the corresponding area;

[0149] The power supply shortage time series data is divided into at least two time periods according to the ratio and / or difference between the actual power supply and the predicted power consumption in the corresponding area; specifically, the division can be based on the ratio of the actual power supply and the predicted power consumption in the corresponding area, such as the actual power supply is greater than 95% of the predicted power consumption, the actual power supply is greater than 90% of the predicted power consumption and not greater than 95% of the predicted power consumption, etc.; the division can also be based on the difference between the actual power supply and the predicted power consumption in the corresponding area, where the actual power supply power and the predicted power consumption need to be used to replace the actual power supply and the predicted power consumption, such as the difference between the actual power supply power and the predicted power consumption is less than 5000KW, the difference between the actual power supply power and the predicted power consumption is less than 10000KW and not less than 5000KW, the difference between the actual power supply power and the predicted power consumption is less than 100000KW and not less than 10000KW, etc.;

[0150] According to at least two time periods, dividing the first load adjustment data into at least two load adjustment sub-data matching the time periods;

[0151] According to at least two load adjustment data, based on a preset second portrait generation model, an adjustment portrait of the first user is obtained, and the adjustment portrait is used to characterize the conditions for the user to perform load adjustment under different power supply shortage situations in the corresponding area.

[0152] Using the above method, the label in the obtained adjustment portrait can be "5000-10; 10000-1000", that is, when the difference between the actual power supply power and the predicted power consumption is less than 5000KW, the load that the first user can adjust is 10KW; when the difference between the actual power supply power and the predicted power consumption is less than 10000KW and not less than 5000KW, the load that the first user can adjust is 1000KW, etc. This can help the power grid system generate load adjustment plans faster when performing load adjustment.

[0153] S6. Generate a user portrait of the first user based on the basic portrait and the adjusted portrait of the first user.

[0154] Optionally, the basic portrait of the first user and the adjusted portrait of the first user may be stored separately; further, before step S3, it also includes: searching according to the first user to determine whether there is a historical basic portrait of the first user; if there is a historical basic portrait of the first user, determining whether there is a change application or change information associated with the first user; if not, using the historical basic portrait as the basic portrait, otherwise executing step S3.

[0155] When the first user is a guaranteed supply user:

[0156] S7. Generate a user portrait of the first user based on the basic portrait of the first user.

[0157] When the first user is a guaranteed supply user, the user generally does not participate in load regulation, so there is no need to obtain the regulation profile of the guaranteed supply user.

[0158] Through the above method, a more refined user portrait can be obtained. When power restrictions are implemented, users who can adjust the load and obtain the load that users can transfer can be intelligently screened out according to the actual situation.

[0159] Example 3

[0160] A user portrait construction system based on user feature fusion analysis, including a user portrait generation platform and a power data management platform:

[0161] The user portrait generation platform is configured as follows:

[0162] In response to receiving the user portrait building request, obtaining a user list corresponding to the user portrait building request;

[0163] According to the user list, first basic information and first power usage information of a first user are obtained, where the first user belongs to the users in the user list;

[0164] According to the first basic information, based on a preset first portrait generation model, a basic portrait of the first user is obtained;

[0165] Determining whether the first user is a guaranteed supply user according to at least one tag in the basic portrait of the first user;

[0166] When the first user is not a guaranteed supply user:

[0167] According to the first power usage information, based on a preset second portrait generation model, an adjustment portrait of the first user is obtained;

[0168] Generate a user profile of the first user according to the basic profile and the adjusted profile of the first user;

[0169] The power data management platform is configured to:

[0170] In response to a request from the user portrait generation platform, the first basic information and the first electricity usage information of the first user are sent to the user portrait generation platform.

[0171] Optionally, in response to receiving the user profile building request, obtaining a user list corresponding to the user profile building request includes:

[0172] In response to receiving the user portrait building request, obtaining administrator information of a first administrator who sent the user portrait building request;

[0173] According to the administrator information, a first region corresponding to the first administrator is obtained;

[0174] According to the first region, a user list of the first region is obtained as a user list corresponding to the user portrait building request.

[0175] Optionally, obtaining first basic information and first electricity usage information of a first user according to the user list includes:

[0176] Obtaining a unique identifier of the first user according to the user list;

[0177] Acquire at least one basic information of the first user from a user information database according to the unique identifier of the first user, wherein the at least one basic information belongs to the first basic information;

[0178] According to the unique identifier of the first user, first power usage information of the first user is obtained from the power usage database.

[0179] Optionally, before obtaining the basic portrait of the first user according to the first basic information and based on a preset first portrait generation model, the method further includes:

[0180] Establishing a user tag system, wherein the user tag system includes at least one basic tag;

[0181] A basic mapping between user information and basic tags is established according to the user tag system to obtain a first portrait generation model.

[0182] Optionally, obtaining an adjustment portrait of the first user based on the first power usage information and a preset second portrait generation model includes:

[0183] According to the first power consumption information, first time series data and second time series data are obtained, wherein the first time series data is configured as the power consumption time series data of the first user when power supply is normal, and the second time series data is configured as the power consumption time series data of the first user when power supply is short;

[0184] According to the first time series data, third time series data is obtained, where the third time series data is configured as theoretical power consumption time series data of the first user when power supply is short;

[0185] According to the second time series data and the third time series data, based on a preset second portrait generation model, an adjustment portrait of the first user is obtained.

[0186] Optionally, obtaining an adjustment portrait of the first user according to the second time series data and the third time series data includes:

[0187] Obtaining first load adjustment data of a first user according to the second time series data and the third time series data;

[0188] According to the first load adjustment data, based on a preset second portrait generation model, an adjustment portrait of the first user is obtained, and the adjustment portrait is used to characterize the conditions for the user to perform load adjustment.

[0189] Optionally, obtaining the adjustment portrait of the first user according to the first load adjustment data and based on a preset second portrait generation model includes:

[0190] Acquire power supply shortage time series data of the area where the first user is located, where the power supply shortage time series data is configured to represent the ratio and / or difference between the actual power supply and the predicted power consumption of the corresponding area;

[0191] Divide the power supply shortage time series data into at least two time periods according to the ratio and / or difference between the actual power supply and the predicted power consumption in the corresponding area;

[0192] According to at least two time periods, dividing the first load adjustment data into at least two load adjustment sub-data matching the time periods;

[0193] According to at least two load adjustment data, based on a preset second portrait generation model, an adjustment portrait of the first user is obtained, and the adjustment portrait is used to characterize the conditions for the user to perform load adjustment under different power supply shortage situations in the corresponding area.

[0194] Example 4

[0195] This embodiment provides a computer device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement any of the above methods.

[0196] Specifically, Figure 2 As shown, Figure 2This is a schematic diagram of the computer device structure of the hardware operating environment involved in the embodiment of the present application. The computer device may include: a processor 101, such as a central processing unit (CPU), a communication bus 102, a user interface 104, a network interface 103, and a memory 105. Among them, the communication bus 102 is used to realize the connection and communication between these components. The user interface 104 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the user interface 104 may also include a standard wired interface and a wireless interface. The network interface 103 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (WIreless-FIdelity, WI-FI) interface). The memory 105 may optionally be a storage device independent of the aforementioned processor 101. The memory 105 may be a high-speed random access memory (RAM) memory, or it may be a stable non-volatile memory (NVM), such as at least one disk storage; the processor 101 may be a general-purpose processor, including a central processing unit, a network processor, etc., or it may be a digital signal processor, an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component.

[0197] Those skilled in the art will understand that Figure 2 The structure shown in the figure does not constitute a limitation on the electronic device, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0198] like Figure 2 As shown, the memory 105 as a storage medium may include an operating system, a network communication module, a user interface module, and an application program for implementing a method for constructing a user portrait based on user feature fusion analysis.

[0199] exist Figure 2 In the electronic device shown, the network interface 103 is mainly used for data communication with the network server; the user interface 104 is mainly used for data interaction with the user; the processor 101 and the memory 105 in the present application can be set in the electronic device, and the electronic device calls the application stored in the memory 105 for implementing a user portrait construction method based on user feature fusion analysis through the processor 101 to implement the above method.

[0200] Example 5

[0201] This embodiment provides a computer-readable storage medium, on which a computer program is stored, and a processor executes the computer program to implement any of the above methods.

[0202] In some embodiments, the computer readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface memory, optical disk, or CD-ROM; or various devices including one or any combination of the above memories. The computer may be various computing devices including intelligent terminals and servers.

[0203] In the above embodiments of the present disclosure, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0204] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0205] 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 over multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0206] In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0207] 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 non-volatile storage medium. Based on this understanding, the technical solution of the present disclosure is essentially 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, and the computer software product is stored in a non-volatile storage medium, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the various embodiments of the present disclosure. The aforementioned non-volatile storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0208] The above are only preferred embodiments of the present disclosure. It should be pointed out that, for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present disclosure. These improvements and modifications should also be regarded as the protection scope of the present disclosure.

Claims

1. A method for constructing a user portrait based on user feature fusion analysis, characterized in that: include: In response to receiving the user portrait building request, obtaining a user list corresponding to the user portrait building request; According to the user list, first basic information and first power usage information of a first user are obtained, where the first user belongs to the users in the user list; According to the first basic information, based on a preset first portrait generation model, a basic portrait of the first user is obtained; Determining whether the first user is a guaranteed supply user according to at least one tag in the basic portrait of the first user; When the first user is not a guaranteed supply user: According to the first electricity usage information, based on a preset second portrait generation model, obtaining an adjustment portrait of the first user; A user portrait of the first user is generated according to the basic portrait and the adjusted portrait of the first user.

2. A method for constructing a user portrait based on user feature fusion analysis according to claim 1, characterized in that: The responding to receiving the user portrait building request and obtaining a user list corresponding to the user portrait building request includes: In response to receiving the user portrait building request, obtaining administrator information of a first administrator who sent the user portrait building request; According to the administrator information, obtaining a first area corresponding to the first administrator; According to the first area, a user list of the first area is obtained, which is a user list corresponding to the user portrait building request.

3. The method for constructing a user portrait based on user feature fusion analysis according to claim 1, characterized in that: The obtaining, according to the user list, first basic information and first electricity usage information of the first user includes: Obtaining a unique identifier of the first user according to the user list; Acquire at least one basic information of the first user from a user information database according to the unique identifier of the first user, where the at least one basic information belongs to the first basic information; According to the unique identifier of the first user, first electricity usage information of the first user is obtained from an electricity usage database.

4. The method for constructing a user portrait based on user feature fusion analysis according to claim 1, characterized in that: Before obtaining the basic portrait of the first user according to the first basic information based on a preset first portrait generation model, the method further includes: Establishing a user tag system, wherein the user tag system includes at least one basic tag; A basic mapping between user information and basic tags is established according to the user tag system to obtain a first portrait generation model.

5. The method for constructing a user portrait based on user feature fusion analysis according to claim 1, characterized in that: The obtaining, according to the first electricity usage information and based on a preset second portrait generation model, an adjustment portrait of the first user includes: According to the first power usage information, first time series data and second time series data are obtained, wherein the first time series data is configured as power usage time series data of the first user when power supply is normal, and the second time series data is configured as power usage time series data of the first user when power supply is short; Obtaining third time series data according to the first time series data, wherein the third time series data is configured as theoretical power consumption time series data of the first user when power supply is short; According to the second time series data and the third time series data, based on a preset second portrait generation model, an adjustment portrait of the first user is obtained.

6. A method for constructing a user portrait based on user feature fusion analysis according to claim 5, characterized in that: The obtaining, according to the second time series data and the third time series data, an adjustment portrait of the first user includes: Obtaining first load adjustment data of the first user according to the second time series data and the third time series data; According to the first load adjustment data, based on a preset second portrait generation model, an adjustment portrait of the first user is obtained, and the adjustment portrait is used to characterize the conditions for the user to perform load adjustment.

7. The method for constructing a user portrait based on user feature fusion analysis according to claim 6, characterized in that: The obtaining, according to the first load adjustment data and based on a preset second portrait generation model, an adjustment portrait of the first user includes: Acquire power supply shortage time series data of the area where the first user is located, where the power supply shortage time series data is configured to represent the ratio and / or difference between the actual power supply and the predicted power consumption of the corresponding area; Dividing the power supply shortage time series data into at least two time periods according to the ratio and / or difference between the actual power supply and the predicted power consumption of the corresponding area; According to the at least two time periods, dividing the first load adjustment data into at least two load adjustment sub-data matching the time periods; According to the at least two load adjustment data, based on a preset second portrait generation model, an adjustment portrait of the first user is obtained, and the adjustment portrait is used to characterize the conditions for the user to perform load adjustment under different power supply shortage situations in the corresponding area.

8. A user portrait construction system based on user feature fusion analysis, characterized in that: Including user portrait generation platform and power data management platform: The user portrait generation platform is configured as follows: In response to receiving the user portrait building request, obtaining a user list corresponding to the user portrait building request; According to the user list, first basic information and first power usage information of a first user are obtained, where the first user belongs to the users in the user list; According to the first basic information, based on a preset first portrait generation model, a basic portrait of the first user is obtained; Determining whether the first user is a guaranteed supply user according to at least one tag in the basic portrait of the first user; When the first user is not a guaranteed supply user: According to the first electricity usage information, based on a preset second portrait generation model, obtaining an adjustment portrait of the first user; generating a user profile of the first user according to the basic profile and the adjusted profile of the first user; The power data management platform is configured as follows: In response to the request of the user portrait generation platform, the first basic information and the first electricity usage information of the first user are sent to the user portrait generation platform.

9. A user portrait construction system based on user feature fusion analysis according to claim 8, characterized in that: The obtaining, according to the first electricity usage information and based on a preset second portrait generation model, an adjustment portrait of the first user includes: According to the first power usage information, first time series data and second time series data are obtained, wherein the first time series data is configured as power usage time series data of the first user when power supply is normal, and the second time series data is configured as power usage time series data of the first user when power supply is short; Obtaining third time series data according to the first time series data, wherein the third time series data is configured as theoretical power consumption time series data of the first user when power supply is short; According to the second time series data and the third time series data, based on a preset second portrait generation model, an adjustment portrait of the first user is obtained.

10. A computer device, characterized in that: The computer device comprises a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method according to any one of claims 1 to 7.

Images