CN112906790A - Method and system for identifying solitary old people based on electricity consumption data - Google Patents
Method and system for identifying solitary old people based on electricity consumption data Download PDFInfo
- Publication number
- CN112906790A CN112906790A CN202110192708.1A CN202110192708A CN112906790A CN 112906790 A CN112906790 A CN 112906790A CN 202110192708 A CN202110192708 A CN 202110192708A CN 112906790 A CN112906790 A CN 112906790A
- Authority
- CN
- China
- Prior art keywords
- data
- electricity consumption
- living alone
- elderly
- elderly living
- 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
- 230000005611 electricity Effects 0.000 title claims abstract description 71
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000012549 training Methods 0.000 claims abstract description 25
- 238000007621 cluster analysis Methods 0.000 claims abstract description 8
- 238000003066 decision tree Methods 0.000 claims description 18
- 239000013598 vector Substances 0.000 claims description 10
- 230000002159 abnormal effect Effects 0.000 claims description 9
- 238000004458 analytical method Methods 0.000 claims description 9
- 238000004422 calculation algorithm Methods 0.000 claims description 8
- 238000007637 random forest analysis Methods 0.000 claims description 8
- 238000012795 verification Methods 0.000 claims description 8
- 238000012216 screening Methods 0.000 claims description 7
- 238000005070 sampling Methods 0.000 claims description 6
- 238000011002 quantification Methods 0.000 claims 2
- 238000004364 calculation method Methods 0.000 claims 1
- 238000004140 cleaning Methods 0.000 abstract description 5
- 238000012544 monitoring process Methods 0.000 abstract description 5
- 238000013139 quantization Methods 0.000 abstract description 3
- 238000002372 labelling Methods 0.000 description 2
- 241000253999 Phasmatodea Species 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Medical Treatment And Welfare Office Work (AREA)
- Alarm Systems (AREA)
Abstract
本申请公开了一种基于用电数据的独居老人识别方法和系统，所述方法包括：随机选取批量低压用户用电数据，对选取数据进行清洗；对数据进行特征选择并向量化；对向量化的数据进行聚类分析；聚类分析结果结合电力营销数据，筛选疑似独居老人群体样本数据；对疑似独居老人群体样本数据进行随机验证，确定模型训练用正样本和负样本；构建独居老人识别模型，并利用正样本、负样本进行模型训练；获取全量用户用电数据，利用独居老人识别模型识别独居老人。本发明可借助电表等电力采集设备获得数据，无需投入大量资金安装监控设备；可以在缺少训练样本的情况下，利用原始用电数据，构建独居老人识别模型，快速定位独居老人用户。
The present application discloses a method and system for identifying elderly people living alone based on electricity consumption data. The method includes: randomly selecting a batch of low-voltage user electricity consumption data, cleaning the selected data; performing feature selection and quantization on the data; The cluster analysis results are combined with the power marketing data, and the sample data of the suspected elderly living alone is screened; the sample data of the suspected elderly living alone is randomly verified to determine the positive and negative samples for model training; the identification model of the elderly living alone is constructed. , and use positive samples and negative samples for model training; obtain the full amount of user electricity consumption data, and use the identification model for the elderly living alone to identify the elderly living alone. The invention can obtain data by means of electric power acquisition equipment such as electricity meters, without investing a lot of money to install monitoring equipment; in the absence of training samples, the invention can use the original electricity consumption data to construct a recognition model for the elderly living alone, and quickly locate the elderly living alone users.
Description
Technical Field
The invention belongs to the technical field of power consumption data analysis and application, and relates to a method and a system for identifying solitary old people based on power consumption data.
Background
At present, the monitoring method for the elderly living alone is more, if the elderly living alone is detected through intelligent equipment, the elderly are prevented from encountering dangers and being unable to be rescued timely, such as intelligent walking sticks, intelligent hand rings and the like, or behaviors, expressions and the like of the elderly are identified and monitored through video monitoring and artificial intelligence technology.
However, many solitary old people often live at the edge of the society, especially solitary old people who urgently need help, how to find the solitary old people to provide necessary help for the solitary old people, and at present, no good method exists. The list of solitary old people is often obtained only by the basic community visit survey. The method consumes huge manpower and material resources and completely depends on community management level and work efficiency. In some huge communities with large and complex population, the list information of the elderly people living alone is difficult to update in time. Although the intensity of community work can be reduced by installing monitoring equipment and the like, a large amount of capital investment is required in the early stage, and special maintenance is required in the later stage.
Disclosure of Invention
In order to overcome the defects in the prior art, the application provides a solitary old man identification method and system based on electricity consumption data.
In order to achieve the above purpose, the invention adopts the following technical scheme:
the method for identifying the old people living alone based on the electricity consumption data is characterized by comprising the following steps:
the method comprises the following steps:
step 1: randomly selecting batch low-voltage user electricity utilization data, cleaning the selected data, and removing abnormal values and null values of electricity utilization;
step 2: carrying out feature selection and vectorization on the data in the step 1;
and step 3: performing clustering analysis on the vectorized data in the step 2 by using a clustering algorithm;
and 4, step 4: step 3, combining the clustering analysis result with the power marketing data, and screening sample data of suspected solitary old people;
and 5: randomly verifying the sample data of the suspected solitary old people group in the step 4, and determining a positive sample and a negative sample for model training;
step 6: constructing a solitary old man identification model, and respectively labeling and combining the positive sample and the negative sample determined in the step (5) to be used as training data of the model to train the solitary old man identification model;
and 7: and acquiring full user power consumption data, and identifying the elderly people living alone by using the elderly people living alone identification model.
The invention further comprises the following preferred embodiments:
preferably, the low-voltage user in the step 1 is a user with an access voltage lower than 380V;
the used electricity consumption data is randomly selected 50 universal users of the daily electricity consumption in the last two years;
the abnormal value includes that the daily electricity consumption is a negative value or the daily electricity consumption is larger than a daily electricity consumption set threshold.
Preferably, in step 2, the electricity consumption statistical characteristics are selected and calculated for each user, and the electricity consumption statistical characteristics of each user are stored in a vector form.
Preferably, the electricity utilization statistical characteristics comprise average electricity utilization ratio of summer to winter, average level ratio of working days to non-working days, average electricity utilization and variance of holidays over three days and holidays over three days.
Preferably, the specific steps of step 3 are as follows:
step 301: taking each user feature vector as a class, and calculating the minimum Euclidean distance between every two users;
step 302: combining the two classes with the minimum Euclidean distance into a new class;
step 303: repeatedly calculating the distances between the new class and all classes;
step 304: step 302 and step 303 are repeated until all classes are merged into one class.
Preferably, the electric marketing data of step 4 comprises a user basic file and a payment channel.
Preferably, in step 5, random sampling is performed from sample data of the suspected solitary old people group, field verification is performed, if the accuracy reaches a set threshold, the sample data of the suspected solitary old people group in step 4 is used as a negative sample, the data group which is the farthest in the euclidean distance from the negative sample in the clustering result in step 3 is used as a positive sample, and if the accuracy does not reach the set threshold, the step 2 is returned, and feature selection and vectorization processing are performed again.
Preferably, in step 6, a random forest model is adopted to construct the elderly people living alone recognition model, the number of samples is assumed to be N, each sample has M characteristics, and the specific training steps are as follows:
step 601: sampling is carried out on samples for N times, 1 sample is obtained each time, N samples are formed, and a decision tree is trained by utilizing the randomly selected N samples to serve as samples at the root node of the decision tree;
step 602: when each node of the decision tree in the step 601 is split, randomly selecting M features from the M features, ensuring that M < < M, and then selecting one feature from the M features as the splitting feature of the node by using an information gain strategy;
step 603: repeating step 602 until the decision tree node cannot be split;
step 604: establishing a batch decision tree according to the sequence of the step 601, the step 602 and the step 603;
step 605: and (4) forming a random forest by the decision tree formed in the step 604 and using the random forest as a solitary old man identification model.
Preferably, in step 7, feature selection and vectorization are carried out on the full-amount user electricity consumption data according to the mode in step 2, and the feature selection and vectorization are input into the solitary old man recognition model trained in step 6 to obtain a solitary old man list;
the electricity consumption data of the full-quantity users refers to the daily electricity consumption of all low-voltage users in the whole province in the last two years.
The present application also discloses another invention, namely, a solitary old man identification system based on electricity consumption data, the system comprising:
the initial data acquisition module is used for randomly selecting batch low-voltage user electricity utilization data, cleaning the selected data and removing abnormal values and null values of electricity utilization;
the characteristic selection and vectorization module is used for carrying out characteristic selection and vectorization on the data of the initial data acquisition module;
the cluster analysis module is used for carrying out cluster analysis on the data of the opposite quantization by utilizing a clustering algorithm based on a hierarchy from bottom to top;
the sample data screening module is used for screening sample data of suspected solitary old people groups by utilizing the clustering analysis result in combination with the electric power marketing data;
the training sample verification module is used for randomly verifying the sample data of the suspected solitary old people group and determining a positive sample and a negative sample for model training;
the model building module is used for building a recognition model of the elderly living alone and performing model training by using a positive sample and a negative sample;
and the identification module is used for acquiring the full-scale electricity utilization data of the user and identifying the solitary old people by utilizing the solitary old people identification model.
The beneficial effect that this application reached:
1. according to the method, through analysis of power consumption data and auxiliary verification of other power marketing data, a list of high-probability solitary old people is rapidly found out, investigation work of communities and the like is reduced, and a precondition is provided for the follow-up care of the work of the solitary old people;
2. the invention can obtain data by means of electric power acquisition equipment such as an ammeter and the like, and does not need to invest a large amount of capital to install monitoring equipment; the old people living alone identification model can be constructed by utilizing original power utilization data under the condition of lacking a training sample, and the old people living alone can be quickly positioned.
Drawings
Fig. 1 is a flow chart of a solitary old man identification method based on electricity consumption 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.
The method utilizes the electricity consumption data of the users to quickly position the users of the elderly living alone, and obtains the labels and the characteristic information of the positive and negative samples for model training in the modes of clustering algorithm, electric power marketing data auxiliary verification and the like under the condition of lacking of training samples.
Specifically, as shown in fig. 1, the method for identifying the elderly living alone based on the electricity consumption data of the present invention includes the following steps:
step 1: randomly selecting batch low-voltage user electricity utilization data, cleaning the selected data, and removing abnormal values, null values and the like of electricity utilization, wherein the low-voltage users are users with access voltage lower than 380V;
the used electricity consumption data is randomly selected 50 universal users of the daily electricity consumption in the last two years;
the abnormal value comprises that the daily electricity consumption is a negative value or the daily electricity consumption is too large;
step 2: and (4) performing feature selection and vectorization on the data in the step 1.
Selecting power utilization statistical characteristics, calculating the power utilization statistical characteristics of each user, and storing the power utilization statistical characteristics of each user in a vector form;
the user electricity utilization statistical characteristics comprise average power consumption ratio in summer and winter, level average ratio between working days and non-working days, average power consumption and variance in holidays over three days and in holidays over non-three days and the like.
And step 3: and (3) carrying out clustering analysis on the vectorized data in the step (2) by using a clustering algorithm, wherein the specific clustering algorithm comprises the following steps:
step 301: taking each user feature vector as a class, and calculating the minimum Euclidean distance between every two users, if the feature vector of the user a is A ═ a (a)1,a2,a3…), the feature vector of user B is B ═ B (B)1,b2,b3…), the feature vector of user C is C ═ C (C)1,c2,c3…), euclidean distance L of user a from user b feature vectorsabIs composed of
The Euclidean distance L between the user a and the user c can be obtained by the same methodacAnd Euclidean distance L between user b and user cbc。
Step 302: merging two classes with the minimum Euclidean distance into a new class, such as Lab、Lbc、LacAmong three distances, LabIf the minimum, combining the user a and the user b into a new class;
step 303: repeatedly calculating the distances between the new class and all classes;
step 304: step 302 and step 303 are repeated until all classes are merged into one class.
Through the clustering, users with similar electricity utilization characteristics can be classified into the same group.
And 4, step 4: step 3, screening sample data of suspected solitary old people group by combining the clustering analysis result with the modes of electric power marketing data and the like;
the electric power marketing data comprises a user basic file, a payment channel and the like;
for example, information such as the age of the user and whether the user is paying off-line may be used as a condition, and a clustering group meeting the condition in the clustering result may be screened out.
And 5: randomly verifying the sample data of the suspected solitary old people group in the step 4, and determining a positive sample and a negative sample for model training;
and (3) randomly sampling from the sample data of the suspected solitary old people group, carrying out on-site verification, and if the accuracy reaches a set threshold value such as 80%, taking the sample data of the suspected solitary old people group in the step (4) as a negative sample, and taking the data group which is the farthest Euclidean distance from the negative sample in the clustering result in the step (3) as a positive sample. If the accuracy rate does not reach 80%, returning to the step 2, and performing feature selection and vectorization again;
step 6: constructing a solitary old man identification model, and respectively labeling and combining the positive sample and the negative sample determined in the step (5) to be used as training data of the model to train the solitary old man identification model, wherein the model is a two-class model and needs to judge whether input data is solitary old man, so that samples for training need two types, namely the positive sample and the negative sample determined in the step (5);
a random forest model is adopted to construct a solitary old man identification model, the number of samples is assumed to be N, each sample has M characteristics, and the specific training steps are as follows:
step 601: sampling is carried out on samples for N times, 1 sample is obtained each time, N samples are formed, and a decision tree is trained by utilizing the randomly selected N samples to serve as samples at the root node of the decision tree;
step 602: when each node of the decision tree in the step 601 is split, randomly selecting M features from the M features, ensuring that M < < M, and then selecting one feature from the M features as the splitting feature of the node by using an information gain strategy;
step 603: repeating step 602 until the decision tree node cannot be split;
step 604: establishing a batch decision tree according to the sequence of the step 601, the step 602 and the step 603;
step 605: and (4) forming a random forest by the decision tree formed in the step 604 and using the random forest as a solitary old man identification model.
And 7: and acquiring full user power consumption data, and identifying the elderly people living alone by using the elderly people living alone identification model.
Selecting and vectorizing characteristics of the full-user electricity consumption data according to the mode of the step 2, inputting the characteristics into the solitary old man identification model trained in the step 6, and obtaining a solitary old man list;
the electricity consumption data of the full-quantity users refers to the daily electricity consumption of all low-voltage users in the whole province in the last two years.
An elderly people solitary identification system based on power consumption data, the system comprising:
the initial data acquisition module is used for randomly selecting batch low-voltage user electricity utilization data, cleaning the selected data and removing abnormal values and null values of electricity utilization;
the characteristic selection and vectorization module is used for carrying out characteristic selection and vectorization on the data of the initial data acquisition module;
the cluster analysis module is used for carrying out cluster analysis on the data of the opposite quantization by utilizing a clustering algorithm based on a hierarchy from bottom to top;
the sample data screening module is used for screening sample data of suspected solitary old people groups by utilizing the clustering analysis result in combination with the electric power marketing data;
the training sample verification module is used for randomly verifying the sample data of the suspected solitary old people group and determining a positive sample and a negative sample for model training;
the model building module is used for building a recognition model of the elderly living alone and performing model training by using a positive sample and a negative sample;
and the identification module is used for acquiring the full-scale electricity utilization data of the user and identifying the solitary old people by utilizing the solitary old people identification model.
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)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110192708.1A CN112906790B (en) | 2021-02-20 | 2021-02-20 | A method and system for identifying elderly people living alone based on electricity consumption data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110192708.1A CN112906790B (en) | 2021-02-20 | 2021-02-20 | A method and system for identifying elderly people living alone based on electricity consumption data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112906790A true CN112906790A (en) | 2021-06-04 |
| CN112906790B CN112906790B (en) | 2023-08-18 |
Family
ID=76124115
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110192708.1A Active CN112906790B (en) | 2021-02-20 | 2021-02-20 | A method and system for identifying elderly people living alone based on electricity consumption data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112906790B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113298175A (en) * | 2021-06-10 | 2021-08-24 | 国网江苏省电力有限公司营销服务中心 | Method and system for monitoring power consumption of old people living alone based on multiple scenes and multivariate data |
| CN113447711A (en) * | 2021-08-02 | 2021-09-28 | 宁夏隆基宁光仪表股份有限公司 | Intelligent ammeter with old people electricity utilization abnormity warning function and warning method thereof |
| CN113780452A (en) * | 2021-09-16 | 2021-12-10 | 国网北京市电力公司 | Monitoring method and monitoring device for solitary group and electronic equipment |
| CN114970672A (en) * | 2022-04-13 | 2022-08-30 | 广东以诺通讯有限公司 | Safe household system and use method thereof |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120134532A1 (en) * | 2010-06-08 | 2012-05-31 | Gorilla Technology Inc. | Abnormal behavior detection system and method using automatic classification of multiple features |
| US20130346346A1 (en) * | 2012-06-21 | 2013-12-26 | Microsoft Corporation | Semi-supervised random decision forests for machine learning |
| WO2015133635A1 (en) * | 2014-03-07 | 2015-09-11 | 株式会社日立製作所 | Data analysis system and method |
| CN105184084A (en) * | 2015-09-14 | 2015-12-23 | 深圳供电局有限公司 | Method and system for predicting fault type of electric power metering automation terminal |
| CN109753989A (en) * | 2018-11-18 | 2019-05-14 | 韩霞 | Analysis method of electricity stealing behavior of power users based on big data and machine learning |
| CN110634080A (en) * | 2018-06-25 | 2019-12-31 | 中兴通讯股份有限公司 | Abnormal electricity utilization detection method, device, equipment and computer readable storage medium |
| KR102060301B1 (en) * | 2019-04-19 | 2020-02-11 | 한국전력공사 | Apparatus and method for analysing living pattern based on power data |
| 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 |
| CN111126820A (en) * | 2019-12-17 | 2020-05-08 | 国网山东省电力公司电力科学研究院 | Anti-stealing method and system |
| CN111861781A (en) * | 2020-02-29 | 2020-10-30 | 上海电力大学 | A method and system for feature selection in clustering of residential electricity consumption behavior |
| WO2020238631A1 (en) * | 2019-05-31 | 2020-12-03 | 南京瑞栖智能交通技术产业研究院有限公司 | Population type recognition method based on mobile phone signaling data |
| CN112200209A (en) * | 2020-06-28 | 2021-01-08 | 国网浙江省电力有限公司金华供电公司 | Poor user identification method based on day-to-day power consumption |
-
2021
- 2021-02-20 CN CN202110192708.1A patent/CN112906790B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120134532A1 (en) * | 2010-06-08 | 2012-05-31 | Gorilla Technology Inc. | Abnormal behavior detection system and method using automatic classification of multiple features |
| US20130346346A1 (en) * | 2012-06-21 | 2013-12-26 | Microsoft Corporation | Semi-supervised random decision forests for machine learning |
| WO2015133635A1 (en) * | 2014-03-07 | 2015-09-11 | 株式会社日立製作所 | Data analysis system and method |
| CN105184084A (en) * | 2015-09-14 | 2015-12-23 | 深圳供电局有限公司 | Method and system for predicting fault type of electric power metering automation terminal |
| CN110634080A (en) * | 2018-06-25 | 2019-12-31 | 中兴通讯股份有限公司 | Abnormal electricity utilization detection method, device, equipment and computer readable storage medium |
| CN109753989A (en) * | 2018-11-18 | 2019-05-14 | 韩霞 | Analysis method of electricity stealing behavior of power users based on big data and machine learning |
| KR102060301B1 (en) * | 2019-04-19 | 2020-02-11 | 한국전력공사 | Apparatus and method for analysing living pattern based on power data |
| WO2020238631A1 (en) * | 2019-05-31 | 2020-12-03 | 南京瑞栖智能交通技术产业研究院有限公司 | Population type recognition method based on mobile phone signaling data |
| 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 |
| CN111126820A (en) * | 2019-12-17 | 2020-05-08 | 国网山东省电力公司电力科学研究院 | Anti-stealing method and system |
| CN111861781A (en) * | 2020-02-29 | 2020-10-30 | 上海电力大学 | A method and system for feature selection in clustering of residential electricity consumption behavior |
| CN112200209A (en) * | 2020-06-28 | 2021-01-08 | 国网浙江省电力有限公司金华供电公司 | Poor user identification method based on day-to-day power consumption |
Non-Patent Citations (2)
| Title |
|---|
| 卢子萌;陈佳怡;李?;谢岳;蒋欣利;韩蕾;郭倩;: "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, no. 08 * |
| 庄绪强;: "基于云计算技术的用户用电智能分析技术研究", 自动化与仪器仪表, no. 02 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113298175A (en) * | 2021-06-10 | 2021-08-24 | 国网江苏省电力有限公司营销服务中心 | Method and system for monitoring power consumption of old people living alone based on multiple scenes and multivariate data |
| CN113298175B (en) * | 2021-06-10 | 2023-09-12 | 国网江苏省电力有限公司营销服务中心 | Method and system for monitoring electricity consumption of elderly people living alone based on multiple scenarios and multiple data |
| CN113447711A (en) * | 2021-08-02 | 2021-09-28 | 宁夏隆基宁光仪表股份有限公司 | Intelligent ammeter with old people electricity utilization abnormity warning function and warning method thereof |
| CN113780452A (en) * | 2021-09-16 | 2021-12-10 | 国网北京市电力公司 | Monitoring method and monitoring device for solitary group and electronic equipment |
| CN114970672A (en) * | 2022-04-13 | 2022-08-30 | 广东以诺通讯有限公司 | Safe household system and use method thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112906790B (en) | 2023-08-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112906790A (en) | Method and system for identifying solitary old people based on electricity consumption data | |
| CN112383052B (en) | Power grid fault repairing method and device based on power internet of things | |
| Singh et al. | A review of studies on machine learning techniques | |
| CN109614488B (en) | Discrimination method of live working conditions in distribution network based on text classification and image recognition | |
| CN108985632A (en) | A kind of electricity consumption data abnormality detection model based on isolated forest algorithm | |
| CN110909224B (en) | A method and system for automatic classification and identification of sensitive data based on artificial intelligence | |
| CN113496440B (en) | User abnormal electricity consumption detection method and system | |
| CN111126820A (en) | Anti-stealing method and system | |
| CN114091549B (en) | A device fault diagnosis method based on deep residual network | |
| CN110472671A (en) | Based on multistage oil-immersed transformer fault data preprocess method | |
| CN117131449A (en) | Data management-oriented anomaly identification method and system with propagation learning capability | |
| CN111506635A (en) | System and method for analyzing residential electricity consumption behavior based on autoregressive naive Bayes algorithm | |
| CN112836809A (en) | Device characteristic extraction method and fault prediction method of convolutional neural network based on differential feature fusion | |
| CN113989544A (en) | Group discovery method based on deep map convolution network | |
| CN113641906A (en) | System, method, device, processor and medium for realizing similar target person identification processing based on fund transaction relation data | |
| CN114626433A (en) | Fault prediction and classification method, device and system for intelligent electric energy meter | |
| CN114611738A (en) | A Load Forecasting Method Based on User's Electricity Behavior Analysis | |
| CN104778250B (en) | Information physical emerging system data classification method based on genetic planning decision tree | |
| CN110334767A (en) | An Improved Random Forest Method for Air Quality Classification | |
| CN112001436A (en) | Water quality classification method based on improved extreme learning machine | |
| CN116796894A (en) | An efficient deep learning weather prediction model construction method | |
| CN114399407B (en) | Power dispatching monitoring data anomaly detection method based on dynamic and static selection integration | |
| CN113807462B (en) | Network equipment fault cause positioning method and system based on AI | |
| CN116611729A (en) | A community resilience assessment method based on multi-task neural network | |
| CN114490645A (en) | An automated machine learning approach for grid structured 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 |