CN112488738A - Method and equipment for identifying resident vacant residents based on electric power big data - Google Patents
Method and equipment for identifying resident vacant residents based on electric power big data Download PDFInfo
- Publication number
- CN112488738A CN112488738A CN202011487987.6A CN202011487987A CN112488738A CN 112488738 A CN112488738 A CN 112488738A CN 202011487987 A CN202011487987 A CN 202011487987A CN 112488738 A CN112488738 A CN 112488738A
- Authority
- CN
- China
- Prior art keywords
- week
- average value
- residents
- unoccupied
- resident
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 53
- 230000005611 electricity Effects 0.000 claims abstract description 109
- 230000003442 weekly effect Effects 0.000 claims abstract description 77
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 4
- 238000012360 testing method Methods 0.000 claims description 4
- 230000006399 behavior Effects 0.000 abstract description 3
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 5
- 238000011835 investigation Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Finance (AREA)
- Marketing (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Primary Health Care (AREA)
- Tourism & Hospitality (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
One or more embodiments of the present specification provide a resident unoccupied residents identification method and apparatus based on big electric power data, construct an unoccupied resident identification model based on the electric power consumption of the resident, analyze the unoccupied resident residents according to the electricity consumption data, behaviors and rules of the average weekly electricity consumption, the average monthly electricity consumption and the average half-year electricity consumption of the users, and fully consider two electricity consumption characteristic factors, namely average weekly electricity consumption and variation coefficient, so as to realize accurate identification of the unoccupied resident residents by a mathematical statistics method; and determining the threshold parameters, and searching the judgment threshold of the user by referring to the power and the service time of each type of electric appliance. The method is beneficial to classifying various vacant scenes in life by combining services, and the constructed model effectively covers the vacant scenes.
Description
Technical Field
One or more embodiments of the present disclosure relate to the technical field of identification of unoccupied residents, and in particular, to a method and an apparatus for identifying unoccupied residents based on big electric power data.
Background
The seventh national census job is started completely in the beginning of the year, and because the census job requires full coverage, the biggest pain point of census is difficult to enter the home, and people cannot be found, so that the census efficiency and the census quality are influenced. The method mainly comprises the following aspects that firstly, the multiple entrepreneurs are caused because no person can be found by the entrepreneur, and the general investigation efficiency is influenced; secondly, people can not be found by entering the house for many times, which is usually defined as 'empty house', but general survey omission can be caused, and the general survey quality is influenced; thirdly, the responsibility of the general investigators is not strong, and the general investigators can not find people at a time and directly report the people as empty users, so that the general investigation quality is also influenced. And accurate judgment of "empty" is an important factor for solving the above problems.
At present, no standard residential vacancy recognition method exists at home and abroad, the commonly used method is mainly to judge the vacancy rate of a house according to the ratio of the vacancy area to the total area of the house at a certain moment, and the vacancy rate analysis is mainly developed for commercial buildings, so that the technology is generally not suitable for the vacancy recognition of residents. It is not suitable for judging whether the resident residents are vacant in the week, month and half year.
Disclosure of Invention
In view of the above, one or more embodiments of the present disclosure are directed to a method and an apparatus for identifying an unoccupied resident based on big power data, so as to solve the problem in the prior art that the unoccupied resident cannot be identified accurately.
In view of the above objects, one or more embodiments of the present specification provide a resident vacant resident identification method based on electric power big data, including:
acquiring daily electricity quantity data of a resident, and removing the acquired data;
calculating the average value of the electricity consumption of the residents in week, the average value of the electricity consumption of the residents in month and the average value of the electricity consumption of the residents in half year based on the processed data;
constructing an unoccupied resident identification model based on the processed data, and determining a parameter threshold of the unoccupied resident identification model;
and sequentially inputting the average value of the weekly power consumption, the average value of the monthly power consumption and the average value of the half-year power consumption into the vacant resident identification model to identify the vacant residents of the residents.
Optionally, the removing the acquired data includes: values less than 0 and values greater than 2500 in the culled data.
Optionally, the constructing an unoccupied-resident identification model based on the processed data, and determining a parameter threshold of the unoccupied-resident identification model includes:
constructing an unoccupied resident identification model based on the processed data, wherein the unoccupied resident identification model comprises the following parameters: the method comprises the following steps of (1) weekly average power consumption and weekly variation coefficient, wherein the weekly average power consumption comprises a threshold value 1 and a threshold value 3, and the weekly variation coefficient comprises a threshold value 2 and a threshold value 4;
calculating the average power consumption and the week variation coefficient of the power consumption of the residents;
according to a quantile method, taking the A quantiles of the week average power consumption and the week variation coefficient of all residents; adjusting the value of A to ensure that the percentage of the number of the users which is less than the weekly average power consumption and less than the weekly variation coefficient is less than or equal to 5 percent;
at this time, the average value of the electricity consumption in the week and the week variation coefficient corresponding to the value A are respectively the threshold value 1 of the average value of the electricity consumption in the week and the threshold value 2 of the week variation coefficient;
taking the A quantiles of the average value of the weekly electricity consumption of all the residents and the 2A quantile of the weekly variation coefficient; adjusting the value of A to enable the percentage of the number of the users smaller than the average value of the weekly power consumption and smaller than the weekly variation coefficient to be less than or equal to 1%;
in this case, the average value of the electricity consumption in the week and the coefficient of variation in the week corresponding to the value a are the threshold value 3 of the average value of the electricity consumption in the week and the threshold value 4 of the coefficient of variation in the week, respectively.
Optionally, the average value of the weekly power consumption, the average value of the monthly power consumption and the average value of the half-year power consumption are sequentially input into the unoccupied resident identification model for identifying the unoccupied residents, and the method includes the following steps:
sequentially inputting the average value of the weekly power consumption, the average value of the monthly power consumption and the average value of the half-year power consumption into an empty resident identification model, and comparing the average value with a parameter threshold value in the model;
when the average electricity consumption of the household week meets one of the following relations, the household is output to be vacant in the week:
(1) the average value of the weekly electricity consumption is less than the threshold value 1,
(2) the average value of the weekly power consumption is more than or equal to a threshold value 1, the weekly variation coefficient is less than a threshold value 2,
(3) the week variation coefficient is more than or equal to a threshold value 2, the average value of the week electricity consumption is less than a threshold value 3, and the week variation coefficient is less than a threshold value 4;
judging the continuous two-week vacancy condition of the resident according to the one-week vacancy condition of the resident, and if the resident is continuously vacant for two weeks, judging that the resident is vacant for the two weeks;
the monthly vacancy and the semi-annual vacancy are analogized according to the method.
Optionally, the determining a parameter threshold of the unoccupied-resident identification model includes:
setting daily electricity level thresholds N of a plurality of vacant residents by referring to the power and the service time of each type of electric appliance;
and calculating and testing the vacancy condition of the residents in the area, and analyzing and determining the judgment threshold of the vacant residents.
Optionally, the electrical appliances of different types include at least one of a radio, a power-saving light bulb, a fluorescent lamp, a 40W light bulb, a 60W light bulb and a refrigerator.
Optionally, the calculation formula of the week variation coefficient is as follows:
the week variation coefficient is the standard deviation of the week electricity consumption/the average value of the week electricity consumption.
An apparatus for performing a resident vacant resident identification method based on electric power big data, comprising:
the data acquisition and removal module is used for acquiring daily electricity quantity data of the household and removing the acquired data;
the data calculation module is used for calculating the average value of the electricity consumption of the residents in the week, the average value of the electricity consumption of the residents in the month and the average value of the electricity consumption of the residents in the half year based on the processed data;
the model construction module is used for constructing an unoccupied resident identification model based on the processed data and determining a parameter threshold of the unoccupied resident identification model;
and the judgment output module is used for sequentially inputting the average value of the weekly power consumption, the average value of the monthly power consumption and the average value of the half-year power consumption into the vacant resident identification model to identify the vacant residents of the residents.
As can be seen from the above, according to the method and the device for identifying the unoccupied residents based on the big electric power data, an unoccupied resident identification model is constructed through the electricity consumption of the residents, the analysis of the unoccupied residents is performed according to the electricity consumption data, behaviors and rules of the electricity consumption data, such as the average electricity consumption of the residents, the average monthly electricity consumption and the average electricity consumption of the residents, and two electricity consumption characteristic factors, namely the average electricity consumption of the residents and the variation coefficient, are fully considered through a mathematical statistics method, so that the accurate identification of the unoccupied residents can be realized. And determining the threshold parameters, and searching the judgment threshold of the user by referring to the power and the service time of each type of electric appliance. The method is beneficial to classifying various vacant scenes in life by combining services, and the constructed model effectively covers the vacant scenes.
Drawings
In order to more clearly illustrate one or more embodiments or prior art solutions of the present specification, the drawings that are needed in the description of the embodiments or prior art will be briefly described below, and it is obvious that the drawings in the following description are only one or more embodiments of the present specification, and that other drawings may be obtained by those skilled in the art without inventive effort from these drawings.
Fig. 1 is a flow diagram of a method for identifying unoccupied subscribers in accordance with one or more embodiments of the present disclosure;
FIG. 2 is a flow diagram of identifying unoccupied residents in one or more embodiments of the present disclosure;
FIG. 3 is a flow diagram illustrating identification of unoccupied residents in two weeks, months, or half a year in accordance with one or more embodiments of the present disclosure;
fig. 4 is a block diagram of modules within a device that performs a method for identifying an unoccupied subscriber in one or more embodiments of the present disclosure.
Detailed Description
To make the objects, technical solutions and advantages of the present disclosure more apparent, the present disclosure is further described in detail below with reference to specific embodiments.
In the technical field of judging the vacancy of residents, a standard residential vacancy recognition method is not available at home and abroad, a common method mainly judges the vacancy rate of a house according to the ratio of the area of the vacant house to the total area of the house at a certain moment, and mainly analyzes the vacancy rate developed by commercial buildings, so that the technology is generally not suitable for the vacancy recognition of the residents. It is not suitable for judging whether the resident residents are vacant in the week, month and half year.
In order to solve the above problems, one or more embodiments of the present specification provide a resident unoccupied residence identification method based on power big data, including:
acquiring daily electricity quantity data of a resident, and removing the acquired data;
calculating the average value of the electricity consumption of the residents in week, the average value of the electricity consumption of the residents in month and the average value of the electricity consumption of the residents in half year based on the processed data;
constructing an unoccupied resident identification model based on the processed data, and determining a parameter threshold of the unoccupied resident identification model;
and sequentially inputting the average value of the weekly power consumption, the average value of the monthly power consumption and the average value of the half-year power consumption into the vacant resident identification model to identify the vacant residents of the residents.
Meanwhile, one or more embodiments of the present specification provide an apparatus for performing a resident vacant resident identification method based on power big data, including:
the data acquisition and removal module is used for acquiring daily electricity quantity data of the household and removing the acquired data;
the data calculation module is used for calculating the average value of the electricity consumption of the residents in the week, the average value of the electricity consumption of the residents in the month and the average value of the electricity consumption of the residents in the half year based on the processed data;
the model construction module is used for constructing an unoccupied resident identification model based on the processed data and determining a parameter threshold of the unoccupied resident identification model;
and the judgment output module is used for sequentially inputting the average value of the weekly power consumption, the average value of the monthly power consumption and the average value of the half-year power consumption into the vacant resident identification model to identify the vacant residents of the residents.
The method comprises the steps of constructing an empty resident identification model through the electricity consumption of residents, analyzing the empty resident residents according to electricity consumption data, behaviors and rules of the average electricity consumption of the residents, the.
One or more embodiments of the present specification provide a method for identifying a resident vacant resident based on big electric power data, and a flowchart is shown in fig. 1, and includes:
step 101: and acquiring daily electricity quantity data of the household, and removing the acquired data.
Specifically, data preparation is carried out, daily electricity consumption data of the resident households in the last three years in a certain area are obtained, and values smaller than 0 and values larger than 2500 in the data are removed.
For example, the daily electricity consumption of all households in a certain area of the Heilongjiang province in the last three years is used as statistical data, the data characteristics are obtained by processing and calculating sample data of three cells in the area, and values smaller than 0 and values larger than 2500 in the data are removed.
Step 102: and calculating the average value of the weekly power consumption, the average value of the monthly power consumption and the average value of the half-year power consumption of the resident based on the processed data.
Step 103: and constructing an empty resident identification model based on the processed data, and determining a parameter threshold of the empty resident identification model.
Specifically, an unoccupied resident identification model is constructed based on the processed data, and the unoccupied resident identification model comprises the following parameters: the method comprises the following steps of (1) weekly average power consumption and weekly variation coefficient, wherein the weekly average power consumption comprises a threshold value 1 and a threshold value 3, and the weekly variation coefficient comprises a threshold value 2 and a threshold value 4;
calculating the average power consumption and the week variation coefficient of the power consumption of the residents;
according to a quantile method, taking the A quantiles of the week average power consumption and the week variation coefficient of all residents; adjusting the value of A to ensure that the percentage of the number of the users which is less than the weekly average power consumption and less than the weekly variation coefficient is less than or equal to 5 percent;
at this time, the average value of the electricity consumption in the week and the week variation coefficient corresponding to the value A are respectively the threshold value 1 of the average value of the electricity consumption in the week and the threshold value 2 of the week variation coefficient;
taking the A quantiles of the average value of the weekly electricity consumption of all the residents and the 2A quantile of the weekly variation coefficient; adjusting the value of A to enable the percentage of the number of the users smaller than the average value of the weekly power consumption and smaller than the weekly variation coefficient to be less than or equal to 1%;
in this case, the average value of the electricity consumption in the week and the coefficient of variation in the week corresponding to the value a are the threshold value 3 of the average value of the electricity consumption in the week and the threshold value 4 of the coefficient of variation in the week, respectively.
In the determination of the parameter threshold of the empty resident identification model, the method comprises the following steps: setting daily electricity level thresholds N of a plurality of vacant residents by referring to the power and the service time of each type of electric appliance;
and calculating and testing the vacancy condition of the residents in the area, and analyzing and determining the judgment threshold of the vacant residents.
The week variation coefficient is calculated as follows:
the week variation coefficient is the standard deviation of the week electricity consumption/the average value of the week electricity consumption.
For example: and (4) calculating the average value of the electricity consumption per week and the week variation coefficient of each household in the cell by using the data processed in the step 101. Taking the week average power consumption and the A quantiles of the week variation coefficient of all residents; and adjusting the value of A to ensure that the percentage of the number of the users is less than or equal to 5 percent, wherein the average value of the weekly electricity consumption and the weekly variation coefficient corresponding to the value A are respectively a threshold value 1 of the average value of the weekly electricity consumption and a threshold value 2 of the weekly variation coefficient (A is about 25 percent).
Considering that the main purpose of setting the threshold 3 and the threshold 4 is to find that there are empty houses that are used once by once, the value should be such that the quantile of the coefficient of variation is larger than the average.
Taking the A quantiles of the average value of the weekly electricity consumption of all the residents and the 2A quantile of the weekly variation coefficient; adjusting the value of A to enable the percentage of the number of the users smaller than the average value of the weekly power consumption and smaller than the weekly variation coefficient to be less than or equal to 1%;
in this case, the average value of the electricity consumption in the week and the coefficient of variation in the week corresponding to the value a are the threshold value 3 of the average value of the electricity consumption in the week and the threshold value 4 of the coefficient of variation in the week, respectively, (a is about 30%, and 2A is about 60%).
The power consumption level of the vacant users is generally in a lower level, the current threshold is determined by referring to the power and the service time (shown in table 1) of each type of electric appliance, a plurality of daily power level thresholds N of the vacant users are set, the vacant conditions of the users in the area are calculated and observed, and the vacant user judgment threshold is analyzed and determined.
TABLE 1 Power and service time of type appliances
Through the above steps, the parameter threshold values of the determined unoccupied-resident recognition model are shown in table 2.
Table 2 empty resident identification model parameter threshold table
Step 104: and sequentially inputting the average value of the weekly power consumption, the average value of the monthly power consumption and the average value of the half-year power consumption into the vacant resident identification model to identify the vacant residents of the residents.
Specifically, as shown in fig. 2 and 3, the average value of the weekly power consumption, the average value of the monthly power consumption and the average value of the half-year power consumption are sequentially input into the vacant household identification model and compared with the parameter threshold in the model;
when the average electricity consumption of the household week meets one of the following relations, the household is output to be vacant in the week:
(1) the average value of the weekly electricity consumption is less than the threshold value 1,
(2) the average value of the weekly power consumption is more than or equal to a threshold value 1, the weekly variation coefficient is less than a threshold value 2,
(3) the week variation coefficient is more than or equal to a threshold value 2, the average value of the week electricity consumption is less than a threshold value 3, and the week variation coefficient is less than a threshold value 4;
judging the continuous two-week vacancy condition of the resident according to the one-week vacancy condition of the resident, and if the resident is continuously vacant for two weeks, judging that the resident is vacant for the two weeks;
the monthly vacancy and the semi-annual vacancy are analogized according to the method.
For example, taking a week as an example, inputting the average value of the electricity consumption of the household in the week calculated in step 102 into the empty household identification model determined in step 103, firstly adopting a daily electricity consumption balance method, when the average value of the electricity consumption of the household in the week is less than a threshold value 1, judging that the household is empty in the week, when the average value of the electricity consumption of the household in the week is greater than or equal to the threshold value 1, adopting an electricity fluctuation amplitude (variation coefficient) measurement method to continuously judge the week variation coefficient, if the week variation coefficient is less than a threshold value 2, judging that the household is empty in the week, if the week variation coefficient is greater than or equal to the threshold value 2, adopting an electricity consumption balance-less method, simultaneously judging the average electricity consumption of the household in the week and the variation coefficient of the electricity consumption of the household, if the average value of the electricity consumption of the week is less than the threshold value 3 and the week variation coefficient is less than the threshold value 4, judging that the household is empty in the week, judging that the household is empty, and if the resident is vacant for two consecutive weeks, judging that the resident is vacant for the two weeks.
The monthly vacancy and the semi-annual vacancy are analogized according to the method.
Through the vacant resident identification model and classification of various vacant scenes in life, whether the vacant scenes are effectively covered by the model is judged. The results are shown in Table 3.
TABLE 3 vacant model scene Classification and decision results
The vacant resident identification model is divided into four types of one-week vacant, two-week vacant, one-month vacant and half-year vacant according to the vacant time. And (4) judging the vacant resident, and identifying the vacant resident by a data analysis method.
One or more embodiments of the present specification provide an apparatus for performing a method for identifying unoccupied residents based on big power data, and a block diagram of internal modules is shown in fig. 4, and includes: the system comprises a data obtaining and eliminating module 401, a data calculating module 402, a model constructing module 403 and a judgment output module.
And the data acquiring and removing module 401 is configured to acquire daily electricity consumption data of the household and remove the acquired data.
Specifically, the method is used for data preparation, daily electricity consumption data of the resident households in the last three years of a certain area are obtained, and values smaller than 0 and values larger than 2500 in the data are removed.
And the data calculation module 402 is configured to calculate an average value of the electricity consumption of the household in the week, an average value of the electricity consumption in the month, and an average value of the electricity consumption in the half year based on the processed data.
And a model construction module 403, configured to construct an unoccupied-resident identification model based on the processed data, and determine a parameter threshold of the unoccupied-resident identification model.
Specifically, an unoccupied resident identification model is constructed based on the processed data, and the unoccupied resident identification model comprises the following parameters: the method comprises the following steps of (1) weekly average power consumption and weekly variation coefficient, wherein the weekly average power consumption comprises a threshold value 1 and a threshold value 3, and the weekly variation coefficient comprises a threshold value 2 and a threshold value 4;
calculating the average power consumption and the variation coefficient of the electricity consumption of the residents,
according to a quantile method, taking the A quantiles of the week average power consumption and the week variation coefficient of all residents; adjusting the value of A to ensure that the percentage of the number of the users which is less than the weekly average power consumption and less than the weekly variation coefficient is less than or equal to 5 percent;
at this time, the average value of the electricity consumption in the week and the week variation coefficient corresponding to the value A are respectively the threshold value 1 of the average value of the electricity consumption in the week and the threshold value 2 of the week variation coefficient;
taking the A quantiles of the average value of the weekly electricity consumption of all the residents and the 2A quantile of the weekly variation coefficient; adjusting the value of A to enable the percentage of the number of the users smaller than the average value of the weekly power consumption and smaller than the weekly variation coefficient to be less than or equal to 1%;
in this case, the average value of the electricity consumption in the week and the coefficient of variation in the week corresponding to the value a are the threshold value 3 of the average value of the electricity consumption in the week and the threshold value 4 of the coefficient of variation in the week, respectively.
In the determination of the parameter threshold of the empty resident identification model, the method comprises the following steps: setting daily electricity level thresholds N of a plurality of vacant residents by referring to the power and the service time of each type of electric appliance;
and calculating and testing the vacancy condition of the residents in the area, and analyzing and determining the judgment threshold of the vacant residents.
The week variation coefficient is calculated as follows:
the week variation coefficient is the standard deviation of the week electricity consumption/the average value of the week electricity consumption.
And the judgment output module 404 is configured to sequentially input the average value of the weekly power consumption, the average value of the monthly power consumption, and the average value of the half-year power consumption into the unoccupied resident identification model for identifying the unoccupied residents.
Specifically, the average value of the weekly power consumption, the average value of the monthly power consumption and the average value of the half-year power consumption are sequentially input into an unoccupied household identification model and are compared with a parameter threshold value in the model;
when the average electricity consumption of the household week meets one of the following relations, the household is output to be vacant in the week:
(1) the average value of the weekly electricity consumption is less than the threshold value 1,
(2) the average value of the weekly power consumption is more than or equal to a threshold value 1, the weekly variation coefficient is less than a threshold value 2,
(3) the week variation coefficient is more than or equal to a threshold value 2, the average value of the week electricity consumption is less than a threshold value 3, and the week variation coefficient is less than a threshold value 4;
judging the continuous two-week vacancy condition of the resident according to the one-week vacancy condition of the resident, and if the resident is continuously vacant for two weeks, judging that the resident is vacant for the two weeks;
the monthly vacancy and the semi-annual vacancy are analogized according to the method.
The vacant resident houses identified by the vacant resident identification model can help an investigator to judge whether one house is vacant. And the method can also be used for verifying whether the investigation result of an investigator is true, and the census efficiency and census quality are improved.
Those of ordinary skill in the art will understand that: the discussion of any embodiment above is meant to be exemplary only, and is not intended to intimate that the scope of the disclosure, including the claims, is limited to these examples; within the spirit of the present disclosure, features from the above embodiments or from different embodiments may also be combined, steps may be implemented in any order, and there are many other variations of different aspects of one or more embodiments of the present description as described above, which are not provided in detail for the sake of brevity.
It is intended that the one or more embodiments of the present specification embrace all such alternatives, modifications and variations as fall within the broad scope of the appended claims. Therefore, any omissions, modifications, substitutions, improvements, and the like that may be made without departing from the spirit and principles of one or more embodiments of the present disclosure are intended to be included within the scope of the present disclosure.
Claims (8)
1. The method for identifying the unoccupied residents based on the electric power big data is characterized by comprising the following steps:
acquiring daily electricity quantity data of a resident, and removing the acquired data;
calculating the average value of the electricity consumption of the residents in week, the average value of the electricity consumption of the residents in month and the average value of the electricity consumption of the residents in half year based on the processed data;
constructing an unoccupied resident identification model based on the processed data, and determining a parameter threshold of the unoccupied resident identification model;
and sequentially inputting the average value of the weekly power consumption, the average value of the monthly power consumption and the average value of the half-year power consumption into the vacant resident identification model to identify the vacant residents of the residents.
2. The method for identifying the unoccupied residents based on the electric power big data as claimed in claim 1, wherein the removing the acquired data comprises: values less than 0 and values greater than 2500 in the culled data.
3. The method for identifying unoccupied residents according to claim 1, wherein the step of building an unoccupied resident identification model based on the processed data and determining the parameter threshold of the unoccupied resident identification model comprises the steps of:
constructing an unoccupied resident identification model based on the processed data, wherein the unoccupied resident identification model comprises the following parameters: the method comprises the following steps of (1) weekly average power consumption and weekly variation coefficient, wherein the weekly average power consumption comprises a threshold value 1 and a threshold value 3, and the weekly variation coefficient comprises a threshold value 2 and a threshold value 4;
calculating the average power consumption and the week variation coefficient of the power consumption of the residents;
according to a quantile method, taking the A quantiles of the week average power consumption and the week variation coefficient of all residents; adjusting the value of A to ensure that the percentage of the number of the users which is less than the weekly average power consumption and less than the weekly variation coefficient is less than or equal to 5 percent;
at this time, the average value of the electricity consumption in the week and the week variation coefficient corresponding to the value A are respectively the threshold value 1 of the average value of the electricity consumption in the week and the threshold value 2 of the week variation coefficient;
taking the A quantiles of the average value of the weekly electricity consumption of all the residents and the 2A quantile of the weekly variation coefficient; adjusting the value of A to enable the percentage of the number of the users smaller than the average value of the weekly power consumption and smaller than the weekly variation coefficient to be less than or equal to 1%;
in this case, the average value of the electricity consumption in the week and the coefficient of variation in the week corresponding to the value a are the threshold value 3 of the average value of the electricity consumption in the week and the threshold value 4 of the coefficient of variation in the week, respectively.
4. The method for identifying the unoccupied residences based on the big electric power data as claimed in claim 1, wherein the step of sequentially inputting the average value of the weekly power consumption, the average value of the monthly power consumption and the average value of the semi-annual power consumption into the unoccupied residences identification model for identifying the unoccupied residences comprises the following steps:
sequentially inputting the average value of the weekly power consumption, the average value of the monthly power consumption and the average value of the half-year power consumption into an empty resident identification model, and comparing the average value with a parameter threshold value in the model;
when the average electricity consumption of the household week meets one of the following relations, the household is output to be vacant in the week:
(1) the average value of the weekly electricity consumption is less than the threshold value 1,
(2) the average value of the weekly power consumption is more than or equal to a threshold value 1, the weekly variation coefficient is less than a threshold value 2,
(3) the week variation coefficient is more than or equal to a threshold value 2, the average value of the week electricity consumption is less than a threshold value 3, and the week variation coefficient is less than a threshold value 4;
judging the continuous two-week vacancy condition of the resident according to the one-week vacancy condition of the resident, and if the resident is continuously vacant for two weeks, judging that the resident is vacant for the two weeks;
the monthly vacancy and the semi-annual vacancy are analogized according to the method.
5. The electric power big data-based resident unoccupied subscriber identification method according to claim 1 or 3, wherein the determining the parameter threshold values of the unoccupied subscriber identification model comprises:
setting daily electricity level thresholds N of a plurality of vacant residents by referring to the power and the service time of each type of electric appliance;
and calculating and testing the vacancy condition of the residents in the area, and analyzing and determining the judgment threshold of the vacant residents.
6. The method for identifying residents who are unoccupied according to claim 5, wherein the electrical appliances include at least one of a radio, a power saving light bulb, a fluorescent lamp, a 40W light bulb, a 60W light bulb, and a refrigerator.
7. The method for identifying unoccupied residents based on electric power big data as claimed in claim 3, wherein the week variation coefficient is calculated as follows:
the week variation coefficient is the standard deviation of the week electricity consumption/the average value of the week electricity consumption.
8. An apparatus for performing the method for identifying unoccupied residents based on big electric power data as claimed in any one of claims 1 to 7, comprising:
the data acquisition and removal module is used for acquiring daily electricity quantity data of the household and removing the acquired data;
the data calculation module is used for calculating the average value of the electricity consumption of the residents in the week, the average value of the electricity consumption of the residents in the month and the average value of the electricity consumption of the residents in the half year based on the processed data;
the model construction module is used for constructing an unoccupied resident identification model based on the processed data and determining a parameter threshold of the unoccupied resident identification model;
and the judgment output module is used for sequentially inputting the average value of the weekly power consumption, the average value of the monthly power consumption and the average value of the half-year power consumption into the vacant resident identification model to identify the vacant residents of the residents.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011487987.6A CN112488738B (en) | 2020-12-16 | 2020-12-16 | Resident vacant resident identification method and equipment based on electric power big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011487987.6A CN112488738B (en) | 2020-12-16 | 2020-12-16 | Resident vacant resident identification method and equipment based on electric power big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112488738A true CN112488738A (en) | 2021-03-12 |
| CN112488738B CN112488738B (en) | 2024-02-27 |
Family
ID=74917304
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011487987.6A Active CN112488738B (en) | 2020-12-16 | 2020-12-16 | Resident vacant resident identification method and equipment based on electric power big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112488738B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113657727A (en) * | 2021-07-30 | 2021-11-16 | 国网湖北省电力有限公司电力科学研究院 | Household personnel household state judgment method based on electric power big data |
| CN113780769A (en) * | 2021-08-26 | 2021-12-10 | 国网湖北省电力有限公司电力科学研究院 | Population mobility index calculation method based on electric power big data |
| CN113919741A (en) * | 2021-11-02 | 2022-01-11 | 南方电网大数据服务有限公司 | Vacant house determining method and device, computer equipment and storage medium |
| CN114639484A (en) * | 2021-11-30 | 2022-06-17 | 国网辽宁省电力有限公司电力科学研究院 | System and method for analyzing community population mobility condition based on electric power big data |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120035057A1 (en) * | 2010-08-03 | 2012-02-09 | Alexandre Bratkovski | Room-temperature superconductive-like diode device |
| CN103577881A (en) * | 2013-11-12 | 2014-02-12 | 国家电网公司 | Client peak alternating and avoiding power limiting effect evaluation method based on orderly power utilization |
| CN103745291A (en) * | 2013-11-12 | 2014-04-23 | 国家电网公司 | Multi-target orderly power utility ordering method based on power utility characteristics |
| CN105225026A (en) * | 2015-08-26 | 2016-01-06 | 中国电力科学研究院 | A kind of Research on Housing Vacancy Rate appraisal procedure based on electric energy service management platform |
| CN105719198A (en) * | 2016-01-22 | 2016-06-29 | 江苏省电力公司电力经济技术研究院 | Method for calculating housing vacancy rate based on resident power consumption behaviors |
| CN108022043A (en) * | 2017-11-30 | 2018-05-11 | 北京汇通金财信息科技有限公司 | Abnormal electricity consumption behavior identification method and device and central server |
| CN109447404A (en) * | 2018-09-20 | 2019-03-08 | 深圳供电局有限公司 | Method and device for evaluating housing vacancy rate, computer equipment and storage medium |
| CN111209534A (en) * | 2019-12-23 | 2020-05-29 | 广西电网有限责任公司 | Method for dividing electricity using state of customer based on electricity consumption data of resident customer |
| CN111667144A (en) * | 2020-04-30 | 2020-09-15 | 北京中电普华信息技术有限公司 | User identification method and device |
-
2020
- 2020-12-16 CN CN202011487987.6A patent/CN112488738B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120035057A1 (en) * | 2010-08-03 | 2012-02-09 | Alexandre Bratkovski | Room-temperature superconductive-like diode device |
| CN103577881A (en) * | 2013-11-12 | 2014-02-12 | 国家电网公司 | Client peak alternating and avoiding power limiting effect evaluation method based on orderly power utilization |
| CN103745291A (en) * | 2013-11-12 | 2014-04-23 | 国家电网公司 | Multi-target orderly power utility ordering method based on power utility characteristics |
| CN105225026A (en) * | 2015-08-26 | 2016-01-06 | 中国电力科学研究院 | A kind of Research on Housing Vacancy Rate appraisal procedure based on electric energy service management platform |
| CN105719198A (en) * | 2016-01-22 | 2016-06-29 | 江苏省电力公司电力经济技术研究院 | Method for calculating housing vacancy rate based on resident power consumption behaviors |
| CN108022043A (en) * | 2017-11-30 | 2018-05-11 | 北京汇通金财信息科技有限公司 | Abnormal electricity consumption behavior identification method and device and central server |
| CN109447404A (en) * | 2018-09-20 | 2019-03-08 | 深圳供电局有限公司 | Method and device for evaluating housing vacancy rate, computer equipment and storage medium |
| CN111209534A (en) * | 2019-12-23 | 2020-05-29 | 广西电网有限责任公司 | Method for dividing electricity using state of customer based on electricity consumption data of resident customer |
| CN111667144A (en) * | 2020-04-30 | 2020-09-15 | 北京中电普华信息技术有限公司 | User identification method and device |
Non-Patent Citations (2)
| Title |
|---|
| 卢子萌 等: "基于加权随机森林算法的空巢电力用户识别方法", 《电信科学》, vol. 36, no. 8, 17 August 2020 (2020-08-17), pages 112 - 121 * |
| 康旭源 等: "居住建筑用电数据分析与随机模型构建", 《建筑科学》, vol. 35, no. 12, 31 December 2019 (2019-12-31), pages 1 - 11 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113657727A (en) * | 2021-07-30 | 2021-11-16 | 国网湖北省电力有限公司电力科学研究院 | Household personnel household state judgment method based on electric power big data |
| CN113780769A (en) * | 2021-08-26 | 2021-12-10 | 国网湖北省电力有限公司电力科学研究院 | Population mobility index calculation method based on electric power big data |
| CN113919741A (en) * | 2021-11-02 | 2022-01-11 | 南方电网大数据服务有限公司 | Vacant house determining method and device, computer equipment and storage medium |
| CN114639484A (en) * | 2021-11-30 | 2022-06-17 | 国网辽宁省电力有限公司电力科学研究院 | System and method for analyzing community population mobility condition based on electric power big data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112488738B (en) | 2024-02-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112488738B (en) | Resident vacant resident identification method and equipment based on electric power big data | |
| CN107609783B (en) | Method and system for evaluating comprehensive performance of intelligent electric energy meter based on data mining | |
| CN103135009B (en) | Electric appliance detection method and system based on user feedback information | |
| CN110991786A (en) | 10kV static load model parameter identification method based on similar daily load curve | |
| CN111680764B (en) | Industry reworking and production-resuming degree monitoring method | |
| CN111027872B (en) | Method and system for determining electricity utilization maturity of regional users | |
| CN103778567A (en) | Method and system for discriminating abnormal electricity utilization of user | |
| CN115081795A (en) | Enterprise energy consumption abnormity cause analysis method and system under multidimensional scene | |
| CN107478997B (en) | Base station storage battery evaluation method and device | |
| CN116203351A (en) | Method and system for detecting abnormal line impedance | |
| CN113705710A (en) | Method and device for identifying default electricity consumption of electric vehicle charging facility | |
| CN116307092A (en) | Power consumption information acquisition-based electricity larceny prevention analysis method for transformer area | |
| CN113947504A (en) | Electricity stealing analysis method and system based on random forest method | |
| CN107274025B (en) | System and method for realizing intelligent identification and management of power consumption mode | |
| CN111861141A (en) | Power distribution network reliability assessment method based on fuzzy fault rate prediction | |
| CN115378143B (en) | Intelligent inspection system for electric power marketing | |
| CN116910655A (en) | Intelligent ammeter fault prediction method based on device measurement data | |
| CN110209260A (en) | Power consumption method for detecting abnormality, device, equipment and computer readable storage medium | |
| CN115545240A (en) | Method, system, equipment and medium for diagnosing abnormal line loss of low-voltage distribution network transformer area | |
| CN112925827A (en) | User property abnormity analysis method based on power acquisition Internet of things data | |
| CN106711998A (en) | Calculation method of emergency degree of acquisition abnormity based on abnormity lasting time | |
| CN113627452A (en) | Electricity stealing behavior detection method based on machine learning random forest algorithm | |
| CN110297145B (en) | Voltage sag detection method based on multi-user electric energy data deep analysis | |
| CN117792806B (en) | Power consumption information acquisition terminal based on POE power supply | |
| CN115576936B (en) | Intelligent calibration method and system for electricity consumption data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |