CN113377760A - Method and system for establishing low-voltage resident feature portrait based on electric power data and multivariate data - Google Patents
Method and system for establishing low-voltage resident feature portrait based on electric power data and multivariate data Download PDFInfo
- Publication number
- CN113377760A CN113377760A CN202110763167.3A CN202110763167A CN113377760A CN 113377760 A CN113377760 A CN 113377760A CN 202110763167 A CN202110763167 A CN 202110763167A CN 113377760 A CN113377760 A CN 113377760A
- Authority
- CN
- China
- Prior art keywords
- data
- term
- quasi
- real
- low
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 31
- 230000005611 electricity Effects 0.000 claims abstract description 45
- 230000007774 longterm Effects 0.000 claims abstract description 31
- 238000004364 calculation method Methods 0.000 claims abstract description 28
- 238000012821 model calculation Methods 0.000 claims abstract description 23
- 238000012795 verification Methods 0.000 claims abstract description 17
- 238000007781 pre-processing Methods 0.000 claims abstract description 4
- 230000002159 abnormal effect Effects 0.000 claims description 9
- 238000004422 calculation algorithm Methods 0.000 claims description 8
- 238000012512 characterization method Methods 0.000 claims description 8
- 238000004140 cleaning Methods 0.000 claims description 7
- 238000001514 detection method Methods 0.000 claims description 4
- 238000012935 Averaging Methods 0.000 claims description 3
- 238000009499 grossing Methods 0.000 claims description 3
- 239000007787 solid Substances 0.000 abstract description 2
- 238000005516 engineering process Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/23—Updating
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Quality & Reliability (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Development Economics (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a method and a system for establishing a low-voltage resident feature portrait based on electric power data and multivariate data, wherein the method comprises the following steps: acquiring and preprocessing electric power related data of low-voltage residents; establishing a long-term, short-term and quasi-real-time characteristic image model of power consumption of a user; calculating long-term, short-term and quasi-real-time characteristic images of low-voltage residents according to the characteristic image model; verifying the model calculation result; optimizing the feature portrait model according to the verification result until the representation condition of the model calculation result is compared with the actual condition to meet the requirement; and performing feature image calculation on the low-voltage residents by using the optimized feature image model. The invention can accurately grasp the electricity utilization state of the user through the electricity utilization data and the external data, and lays a solid foundation for better service of the user.
Description
Technical Field
The invention belongs to the technical field of electric power data characteristic analysis, and relates to a method and a system for establishing a low-voltage resident characteristic portrait based on electric power data and multivariate data.
Background
At present, user portrait has wide application in the fields of internet services such as recommendation, user growth and the like, and the core technology is to extract characterization data capable of expressing user traits from original data by establishing a portrait system and analyzing large-scale data related to users, and then store the characterization data for use in required services.
At present, in the field of internet big data, a user portrait system and a user portrait technology are mature, and each big internet utilizes accurate user portrait, so that not only can a target customer be better served, but also a good effect on the aspect of increasing income can be achieved.
As a company mastering the big data of the power of social users, the power company can reasonably apply big data technology to establish the user power utilization portrait and make a solid foundation for better serving customers. However, the current portrait of the user's power consumption faces the following problems: one is that the data source is single, only the electricity consumption data is used, and external data such as weather and the like are not reasonably used; another problem is that the image type and timeliness are single, because of the limitation of the device, the national network company does not use the data close to the real-time level to generate the quasi-real-time image characteristic, and with the latest industry development-the promotion of the minute-level electricity consumption data, the quasi-real-time image characteristic lays a foundation for the quasi-real-time user image.
Disclosure of Invention
In order to solve the defects in the prior art, the method and the system for establishing the low-voltage resident feature portrait based on the electric power data and the multivariate data are provided, the offline portrait and the quasi-real-time portrait features of the user under different external conditions can be effectively generated through analyzing the multivariate data and the quasi-real-time minute-level data, and the problems that the dimensionality of the portrait of the user is not clear and the real-time performance of the portrait of the user is not enough are solved.
In order to achieve the above purpose, the invention adopts the following technical scheme:
the method for establishing the low-voltage resident characteristic portrait based on the electric power data and the multivariate data comprises the following steps:
step 1: acquiring power related data of low-voltage residents;
step 2: carrying out data cleaning on the power related data in the step 1;
and step 3: completing the data obtained in the step 2;
and 4, step 4: establishing a long-term, short-term and quasi-real-time characteristic image model of power consumption of a user;
and 5: calculating long-term, short-term and quasi-real-time characteristic images of the low-voltage residents according to the characteristic image model by using the data obtained in the step (3);
step 6: verifying the model calculation result of the step 5;
and 7: optimizing the characteristic image model according to the verification result in the step 6, and returning to the step 5 until the representation condition of the model calculation result meets the requirement compared with the actual condition;
and 8: and (7) performing feature image calculation on the low-voltage residents by using the optimized feature image model in the step 7.
The invention further comprises the following preferred embodiments:
preferably, in step 1, the relevant data of the electric power of the low-voltage residents is selected according to the region, wherein the relevant data comprises electricity consumption data, user profile data, holidays, temperature and weather condition data;
the power utilization data comprises quasi-real-time power utilization data and offline power utilization data;
the quasi-real-time electricity utilization data refers to electricity utilization data updated in a minute level, and the offline electricity utilization data refers to day-level electricity utilization data.
Preferably, in step 2, the usage conditions of the quasi-real-time power consumption data in step 1 are judged to detect negative values and null values;
and (3) detecting abnormal values, negative values and null values by using quartile detection and condition judgment on the offline electricity utilization data in the step (1).
Preferably, in step 3, the quasi-real-time power utilization data is completed by using an adjacent data averaging algorithm;
and the offline electricity utilization data is complemented by using an algorithm which simultaneously meets the historical numerical values of the same user, the same weather condition, the same temperature and the same holiday condition and the weighted average of the adjacent electricity consumption.
Preferably, in step 4, the long-term image model includes stable image features: the age, sex, address and four-season electricity consumption habit characteristics of the user;
the short-term portrait model comprises the following sky-level portrait characteristics: the time characteristic of the electricity utilization time starting in the morning and ending in the evening in the near term;
the quasi-real-time feature image model comprises image features updated at the minute level: the method comprises the following steps of minute-level electricity utilization condition, instantaneous maximum current characteristic and characteristic of judging whether a person is at home.
Preferably, in step 5, long-term, short-term and quasi-real-time feature images of the low-voltage residents are respectively calculated from the dimension of weather conditions, the dimension of temperature and the dimension of holidays.
Preferably, in step 5, the calculated result is stored in a user database and the long-term, short-term and quasi-real-time characteristics are updated periodically according to different time dimensions.
Preferably, in step 6 and step 7, the accuracy of the model calculation features is verified by adopting a field verification and sample-to-sample mutual verification mode.
Preferably, in step 6 and step 7, specifically:
carrying out smooth calculation on the feature data, and carrying out smooth calculation on the features with the feature value deviation larger than the threshold value by using a Wilson smoothing method for alignment; or the like, or, alternatively,
carrying out feature distribution statistics, and reevaluating and calculating features which are not distributed enough to distinguish individual users; or the like, or, alternatively,
setting an error function, comparing and calculating with the actual situation, and if the actual situation is not consistent with the representation situation of the image calculation result, adjusting the model calculation method according to the error;
and returning to the step 5 until the model calculation result characterization situation meets the requirements compared with the actual situation.
The invention also discloses a system for establishing the low-voltage resident characteristic portrait based on the electric power data and the multivariate data, which comprises the following steps:
the initial data acquisition module is used for acquiring the electric power related data of the low-voltage residents and carrying out data preprocessing, including data cleaning and completion;
the characteristic image model building module is used for building a long-term, short-term and quasi-real-time characteristic image model of the power consumption of a user;
the long-term, short-term and quasi-real-time feature calculation module is used for calculating the long-term, short-term and quasi-real-time feature images of the low-voltage residents according to the feature image model by utilizing the data obtained by the initial data acquisition module;
the verification module is used for verifying the model calculation result, optimizing the feature image model and returning to the long-term, short-term and quasi-real-time feature calculation module until the representation condition of the model calculation result meets the requirement compared with the actual condition;
and the characteristic image calculation module is used for calculating the characteristic image of the low-voltage residents by using the optimized characteristic image model.
The beneficial effect that this application reached:
1. by means of the minute-level electricity utilization data newly introduced by the power industry, the method improves the real-time performance of the quasi-real-time characteristics of the user, and greatly increases the usability of the user portrait.
2. The invention improves the calculation dimension and accuracy of the user portrait by adding the multivariate data into the calculation, and enables the characterization data to be more accurate.
3. The invention can effectively improve the accuracy of the algorithm and the representation capability of the portrait characteristic data by the mutual verification between the field verification and the samples, so that the portrait of the user is more accurate.
Drawings
FIG. 1 is a flow chart of a method for creating a low-voltage resident feature representation based on electric power data and multivariate data according to the present invention.
Detailed Description
The present application is further described below with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and the protection scope of the present application is not limited thereby.
As shown in FIG. 1, the method for creating a low-voltage resident feature portrait based on electric power data and multivariate data of the invention comprises the following steps:
step 1: acquiring power related data of low-voltage residents;
in specific implementation, relevant electric power data of 5000-family low-voltage residents are selected according to regions, wherein the relevant electric power data comprise external data such as electricity consumption data, user file data, holidays, temperature and weather conditions;
data sources include mining systems and internet public channels.
The power utilization data comprises quasi-real-time power utilization data and offline power utilization data;
the quasi-real-time electricity utilization data refers to electricity utilization data updated in a minute level, and the data has no abnormal value but has null values and negative values which need to be detected and removed;
the off-line electricity consumption data refers to day-level electricity consumption data, the data have electricity consumption abnormal values which do not accord with logic, abnormal values need to be judged by using statistic quantile abnormal detection, and null values and negative values are detected by using conditions to be removed.
Step 2: and (3) performing data cleaning on the power related data in the step (1), wherein the data cleaning comprises the following steps:
judging the use conditions of the quasi-real-time electricity consumption data (without abnormal values) in the step 1 to be less than 0 and no value, and detecting a negative value and a null value;
and (3) detecting abnormal values, negative values and null values of the offline power utilization data in the step (1) by using quartile detection (a numerical value which exceeds the average value and is 10 times of the absolute value of the difference value between the quartile and the quartile is an abnormal value) and condition judgment.
And step 3: and (3) completing the data obtained in the step (2), specifically:
the quasi-real-time electricity utilization data is completed by using an adjacent data averaging algorithm;
and the offline electricity utilization data is complemented by using an algorithm which simultaneously meets the historical numerical values of the same user, the same weather condition, the same temperature and the same holiday condition and the weighted average of the adjacent electricity consumption.
And 4, step 4: establishing a long-term, short-term and quasi-real-time characteristic image model of power consumption of a user;
long-term portrayal refers to portrayal features that are not always required to be updated, such as age and sex of a user;
short-term portraits refer to portraits features that require updating at the antenna level, such as antenna level electrical conditions;
quasi-real time imagery refers to imagery features that are updated on a minute level.
In particular, the long-term portrait model includes stable portrait features: the age, sex, address and long-term electricity consumption habit characteristics of the user, such as electricity consumption habits in four seasons, electricity consumption habits at different temperatures and other characteristics;
wherein, the age and the gender can be obtained by analyzing the certificate number information, and the address is intercepted and stored from the registration file data, etc.
The short-term portrait model comprises the following sky-level portrait characteristics: the time of starting electricity utilization in the morning, the time of finishing electricity utilization in the evening, the recent electricity utilization habit and the like;
the quasi-real-time feature image model comprises image features updated at the minute level: the electricity consumption condition is accurate to hour or even minute level, the instantaneous maximum current characteristic, whether a person is at home or not is judged, and the like.
The calculation mode is mainly to directly acquire or deduce the quasi-real-time data to carry out statistical calculation. For example, the instantaneous maximum current characteristic may be directly assigned to a value in the push data.
And 5: calculating long-term, short-term and quasi-real-time characteristic images of the low-voltage residents according to the characteristic image model by using the data obtained in the step (3);
in specific implementation, long-term, short-term and quasi-real-time characteristic images of low-voltage residents are respectively calculated from a weather condition dimension, a temperature dimension and a holiday dimension.
The dimension-based statistical characteristics can enable the characteristics to be more refined, and the characteristics of the corresponding dimension can be selected for use according to the conditions of the day when the device is used, so that the characteristics can be more accurately used.
And storing the calculated result in a user database and updating various long-term, short-term and quasi-real-time characteristics according to different time dimensions in a timing mode.
Step 6: verifying the model calculation result in the step 5, specifically:
and 7: optimizing the characteristic image model according to the verification result in the step 6, and returning to the step 5 until the representation condition of the model calculation result meets the requirement compared with the actual condition;
the method for verifying the model calculation feature accuracy by adopting the modes of field verification, mutual verification among samples and the like specifically comprises the following steps:
carrying out smooth calculation on the feature data, and carrying out smooth calculation on the features with the feature value deviation larger than the threshold value by using a Wilson smoothing method for alignment; or the like, or, alternatively,
carrying out feature distribution statistics, and reevaluating and calculating features which are not distributed enough to distinguish individual users; or the like, or, alternatively,
setting an error function, comparing and calculating with the actual situation, and if the actual situation is not consistent with the representation situation of the image calculation result, adjusting the model calculation method according to the error;
and returning to the step 5 until the model calculation result characterization situation meets the requirements compared with the actual situation.
And 8: and (7) performing feature image calculation on the low-voltage residents by using the optimized feature image model in the step 7.
The invention relates to a system for establishing a low-voltage resident characteristic portrait based on electric power data and multivariate data, which comprises:
the initial data acquisition module is used for acquiring the electric power related data of the low-voltage residents and carrying out data preprocessing, including data cleaning and completion;
the characteristic image model building module is used for building a long-term, short-term and quasi-real-time characteristic image model of the power consumption of a user;
the long-term, short-term and quasi-real-time feature calculation module is used for calculating the long-term, short-term and quasi-real-time feature images of the low-voltage residents according to the feature image model by utilizing the data obtained by the initial data acquisition module;
the verification module is used for verifying the model calculation result, optimizing the feature image model and returning to the long-term, short-term and quasi-real-time feature calculation module until the representation condition of the model calculation result meets the requirement compared with the actual condition;
and the characteristic image calculation module is used for calculating the characteristic image of the low-voltage residents by using the optimized characteristic image model.
In conclusion, by means of the minute-level electricity utilization data newly introduced by the power industry, the method improves the real-time performance of the quasi-real-time characteristics of the user, and greatly increases the usability of the user portrait; by adding multivariate data into calculation, the calculation dimension and accuracy of the user portrait are improved, and the characterization data are more accurate; through mutual verification between the field verification and the samples, the accuracy of the algorithm can be effectively improved, the characterization capability of the portrait characteristic data is improved, and the portrait of a user is more accurate.
The present applicant has described and illustrated embodiments of the present invention in detail with reference to the accompanying drawings, but it should be understood by those skilled in the art that the above embodiments are merely preferred embodiments of the present invention, and the detailed description is only for the purpose of helping the reader to better understand the spirit of the present invention, and not for limiting the scope of the present invention, and on the contrary, any improvement or modification made based on the spirit of the present invention should fall within the scope of the present invention.
Claims (10)
1. The method for establishing the low-voltage resident characteristic portrait based on the electric power data and the multivariate data is characterized in that:
the method comprises the following steps:
step 1: acquiring power related data of low-voltage residents;
step 2: carrying out data cleaning on the power related data in the step 1;
and step 3: completing the data obtained in the step 2;
and 4, step 4: establishing a long-term, short-term and quasi-real-time characteristic image model of power consumption of a user;
and 5: calculating long-term, short-term and quasi-real-time characteristic images of the low-voltage residents according to the characteristic image model by using the data obtained in the step (3);
step 6: verifying the model calculation result of the step 5;
and 7: optimizing the characteristic image model according to the verification result in the step 6, and returning to the step 5 until the representation condition of the model calculation result meets the requirement compared with the actual condition;
and 8: and (7) performing feature image calculation on the low-voltage residents by using the optimized feature image model in the step 7.
2. A method of building a low voltage resident characteristic map based on power data and multivariate data as claimed in claim 1, wherein:
in the step 1, selecting power related data of low-voltage residents according to regions, wherein the power related data comprises power consumption data, user profile data, holidays, temperature and weather condition data;
the power utilization data comprises quasi-real-time power utilization data and offline power utilization data;
the quasi-real-time electricity utilization data refers to electricity utilization data updated in a minute level, and the offline electricity utilization data refers to day-level electricity utilization data.
3. A method of building a low voltage resident characteristic map based on power data and multivariate data as claimed in claim 2, wherein:
in step 2, judging the use conditions of the quasi-real-time electricity consumption data in the step 1 to detect negative values and null values;
and (3) detecting abnormal values, negative values and null values by using quartile detection and condition judgment on the offline electricity utilization data in the step (1).
4. A method of building a low voltage resident characteristic map based on power data and multivariate data as claimed in claim 2, wherein:
in step 3, the quasi-real-time power utilization data are complemented by using an adjacent data averaging algorithm;
and the offline electricity utilization data is complemented by using an algorithm which simultaneously meets the historical numerical values of the same user, the same weather condition, the same temperature and the same holiday condition and the weighted average of the adjacent electricity consumption.
5. A method of building a low voltage resident characteristic map based on power data and multivariate data as claimed in claim 1, wherein:
in step 4, the long-term portrait model includes stable portrait features: the age, sex, address and four-season electricity consumption habit characteristics of the user;
the short-term portrait model comprises the following sky-level portrait characteristics: the time characteristic of the electricity utilization time starting in the morning and ending in the evening in the near term;
the quasi-real-time feature image model comprises image features updated at the minute level: the method comprises the following steps of minute-level electricity utilization condition, instantaneous maximum current characteristic and characteristic of judging whether a person is at home.
6. A method of building a low voltage resident characteristic map based on power data and multivariate data as claimed in claim 1, wherein:
and 5, respectively calculating long-term, short-term and quasi-real-time characteristic images of the low-voltage residents from the dimension of the weather condition, the dimension of the temperature and the dimension of the holidays.
7. A method of building a low voltage resident characteristic map based on power data and multivariate data as claimed in claim 1, wherein:
and step 5, storing the calculated result in a user database and updating various long-term, short-term and quasi-real-time characteristics according to different time dimensions in a timing mode.
8. A method of building a low voltage resident characteristic map based on power data and multivariate data as claimed in claim 1, wherein:
in the step 6 and the step 7, the accuracy of model calculation features is verified by adopting a field verification mode and a mutual verification mode among samples.
9. The method for building a low voltage resident characteristic figure based on electric power data and multivariate data according to claim 1 or 8, wherein:
in the step 6 and the step 7, the method specifically comprises the following steps:
carrying out smooth calculation on the feature data, and carrying out smooth calculation on the features with the feature value deviation larger than the threshold value by using a Wilson smoothing method for alignment; or the like, or, alternatively,
carrying out feature distribution statistics, and reevaluating and calculating features which are not distributed enough to distinguish individual users; or the like, or, alternatively,
setting an error function, comparing and calculating with the actual situation, and if the actual situation is not consistent with the representation situation of the image calculation result, adjusting the model calculation method according to the error;
and returning to the step 5 until the model calculation result characterization situation meets the requirements compared with the actual situation.
10. System based on electric power data and multivariate data establish low pressure resident's characteristic portrait, its characterized in that:
the system comprises:
the initial data acquisition module is used for acquiring the electric power related data of the low-voltage residents and carrying out data preprocessing, including data cleaning and completion;
the characteristic image model building module is used for building a long-term, short-term and quasi-real-time characteristic image model of the power consumption of a user;
the long-term, short-term and quasi-real-time feature calculation module is used for calculating the long-term, short-term and quasi-real-time feature images of the low-voltage residents according to the feature image model by utilizing the data obtained by the initial data acquisition module;
the verification module is used for verifying the model calculation result, optimizing the feature image model and returning to the long-term, short-term and quasi-real-time feature calculation module until the representation condition of the model calculation result meets the requirement compared with the actual condition;
and the characteristic image calculation module is used for calculating the characteristic image of the low-voltage residents by using the optimized characteristic image model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110763167.3A CN113377760A (en) | 2021-07-06 | 2021-07-06 | Method and system for establishing low-voltage resident feature portrait based on electric power data and multivariate data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110763167.3A CN113377760A (en) | 2021-07-06 | 2021-07-06 | Method and system for establishing low-voltage resident feature portrait based on electric power data and multivariate data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113377760A true CN113377760A (en) | 2021-09-10 |
Family
ID=77581126
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110763167.3A Pending CN113377760A (en) | 2021-07-06 | 2021-07-06 | Method and system for establishing low-voltage resident feature portrait based on electric power data and multivariate data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113377760A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113779109A (en) * | 2021-09-15 | 2021-12-10 | 南京才华智能科技有限公司 | Power data preprocessing method based on context environment |
| CN114417955A (en) * | 2021-12-02 | 2022-04-29 | 国网浙江省电力有限公司 | Power index portrait real-time generation method and device suitable for villages and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106651424A (en) * | 2016-09-28 | 2017-05-10 | 国网山东省电力公司电力科学研究院 | Electric power user figure establishment and analysis method based on big data technology |
| CN110766438A (en) * | 2019-08-22 | 2020-02-07 | 深圳供电局有限公司 | Method for analyzing user behaviors of power grid users through artificial intelligence |
| CN110826641A (en) * | 2019-11-13 | 2020-02-21 | 上海积成能源科技有限公司 | System and method for classifying electricity consumption condition of residents based on cluster analysis |
| WO2020098308A1 (en) * | 2018-11-12 | 2020-05-22 | 平安科技（深圳）有限公司 | Method, device and equipment for establishing crowd portrait classification medel and storage medium |
| CN111461761A (en) * | 2020-02-29 | 2020-07-28 | 国网江苏省电力有限公司苏州供电分公司 | Resident user portrait method based on multi-dimensional fine-grained behavior data |
| CN111612228A (en) * | 2020-05-12 | 2020-09-01 | 国网河北省电力有限公司电力科学研究院 | User electricity consumption behavior analysis method based on electricity consumption information |
| CN112101635A (en) * | 2020-08-25 | 2020-12-18 | 南方电网深圳数字电网研究院有限公司 | Method and system for monitoring electricity utilization abnormity |
| CN112417308A (en) * | 2020-12-17 | 2021-02-26 | 国网河北省电力有限公司营销服务中心 | User portrait label generation method based on electric power big data |
-
2021
- 2021-07-06 CN CN202110763167.3A patent/CN113377760A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106651424A (en) * | 2016-09-28 | 2017-05-10 | 国网山东省电力公司电力科学研究院 | Electric power user figure establishment and analysis method based on big data technology |
| WO2020098308A1 (en) * | 2018-11-12 | 2020-05-22 | 平安科技（深圳）有限公司 | Method, device and equipment for establishing crowd portrait classification medel and storage medium |
| CN110766438A (en) * | 2019-08-22 | 2020-02-07 | 深圳供电局有限公司 | Method for analyzing user behaviors of power grid users through artificial intelligence |
| CN110826641A (en) * | 2019-11-13 | 2020-02-21 | 上海积成能源科技有限公司 | System and method for classifying electricity consumption condition of residents based on cluster analysis |
| CN111461761A (en) * | 2020-02-29 | 2020-07-28 | 国网江苏省电力有限公司苏州供电分公司 | Resident user portrait method based on multi-dimensional fine-grained behavior data |
| CN111612228A (en) * | 2020-05-12 | 2020-09-01 | 国网河北省电力有限公司电力科学研究院 | User electricity consumption behavior analysis method based on electricity consumption information |
| CN112101635A (en) * | 2020-08-25 | 2020-12-18 | 南方电网深圳数字电网研究院有限公司 | Method and system for monitoring electricity utilization abnormity |
| CN112417308A (en) * | 2020-12-17 | 2021-02-26 | 国网河北省电力有限公司营销服务中心 | User portrait label generation method based on electric power big data |
Non-Patent Citations (4)
| Title |
|---|
| 余文辉;吴争荣;: "基于电力大数据的客户立体画像构建及应用研究", 计算技术与自动化, no. 02 * |
| 姜红玉;汪朋;封雷;: "基于流式计算的实时用户画像***研究", 计算机技术与发展, no. 07 * |
| 王成亮;郑海雁;: "基于模糊聚类的电力客户用电行为模式画像", 电测与仪表, no. 18 * |
| 裘华东;涂莹;丁麒;: "基于标签库***的电力企业客户画像构建与信用评估及电费风险防控应用", 电信科学, no. 1 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113779109A (en) * | 2021-09-15 | 2021-12-10 | 南京才华智能科技有限公司 | Power data preprocessing method based on context environment |
| CN113779109B (en) * | 2021-09-15 | 2024-05-24 | 南京才华智能科技有限公司 | Electric power data preprocessing method based on context environment |
| CN114417955A (en) * | 2021-12-02 | 2022-04-29 | 国网浙江省电力有限公司 | Power index portrait real-time generation method and device suitable for villages and storage medium |
| CN114417955B (en) * | 2021-12-02 | 2023-10-31 | 国网浙江省电力有限公司 | Method, device and storage medium for generating power index image suitable for village in real time |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110350528B (en) | Low-voltage distribution area topology automatic identification method | |
| Mutanen et al. | Customer classification and load profiling method for distribution systems | |
| CN109799474B (en) | Multi-epitope meter box electric energy meter phase identification method and system based on data correlation | |
| CN113377760A (en) | Method and system for establishing low-voltage resident feature portrait based on electric power data and multivariate data | |
| WO2020252785A1 (en) | Abnormal electricity use recognition method and device, and computer readable storage medium | |
| CN111160791A (en) | Abnormal user identification method based on GBDT algorithm and factor fusion | |
| CN111476427A (en) | Low-voltage distribution area topology identification method and identification device | |
| CN117411189B (en) | Monitoring data enhancement method of micro-grid coordination controller | |
| CN113435610B (en) | Method for determining classified line loss based on low-voltage internet of things sensing terminal | |
| CN112198375B (en) | Phase identification method, device, equipment and storage medium for single-phase user | |
| CN111046913A (en) | Load abnormal value identification method | |
| Hartmann et al. | Suspicious electric consumption detection based on multi-profiling using live machine learning | |
| CN116523140A (en) | Method and device for detecting electricity theft, electronic equipment and storage medium | |
| CN105260792A (en) | Air conditioner electricity reference value prediction system and method | |
| Ding et al. | Individual nonparametric load estimation model for power distribution network planning | |
| CN112636335B (en) | Low-voltage distribution network user transformer relation verification method and system based on voltage data decorrelation selection and correlation analysis | |
| CN117154716B (en) | Planning method and system for accessing distributed power supply into power distribution network | |
| CN113780717A (en) | Method and device for analyzing electricity stealing and leakage behaviors based on gateway, intelligent gateway and medium | |
| CN110288383A (en) | Group behavior power distribution network multiplexing electric abnormality detection method based on user property label | |
| CN113420728B (en) | Non-invasive air conditioner load identification method and system integrating multi-time scale information | |
| CN114722971A (en) | Low-voltage transformer area phase identification method | |
| CN111880121B (en) | Low-voltage transformer area topology system based on operation disturbance data analysis and topology identification method | |
| CN114638284A (en) | Power utilization behavior characterization method considering external influence factors | |
| Xiaoman et al. | Analysis of power large user segmentation based on affinity propagation and K-means algorithm | |
| CN113075468A (en) | Phase determination method based on low-voltage user |
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 |