Electricity stealing user identification system and method based on big data analysis

Abstract

The invention discloses an electricity stealing user identification system and method based on big data analysis, and relates to the technical field of user power data analysis, and the system comprises a data collection module, a data processing module, an anomaly detection module, an intelligent identification module and an alarm module. The information acquisition module is used for acquiring power utilization information of a user in real time and sending the power utilization information of the user to the data processing module; the information acquisition module comprises a current sensor, a voltage sensor and a power sensor, and is used for acquiring performance information of power utilization of a user in real time, comprehensively analyzing the data by using the intelligent identification module, confirming an electricity stealing behavior by using a machine learning algorithm or a statistical model, and sending early warning information to a manager; the system is convenient for management personnel to carry out further verification and processing, measures for preventing electricity stealing are taken in time, and the screening accuracy is improved by collecting electricity utilization, power supply, loss and environment information in the power system and carrying out preprocessing and analysis by using the artificial intelligence module.

Description

Technical Field

[0001] The present invention relates to the technical field of user power data analysis, and in particular to a system and method for identifying electricity theft users based on big data analysis. Background Art

[0002] There are many users in the power grid and a lot of electricity consumption data, so it is necessary to use the big data platform to analyze the massive historical electricity consumption data to see if there is electricity theft by users, in order to maintain the safe operation of the power grid. At present, there are many anomaly detection algorithms that mainly observe the historical data of voltage, electricity, and power. These methods all rely on the historical electricity consumption data collected by the power system;

[0003] During the normal operation of the power system, power equipment, power lines, and power-consuming equipment will generate certain power losses, causing the power supply to be greater than the actual power consumption. Big data is used to increase the normal range of the difference between the power supply and the actual power consumption. People determine whether there is power theft by calculating whether the difference between the actual power consumption data and the actual power supply data exceeds the normal range recorded in big data, thereby conducting power theft screening.

[0004] On this basis, after searching the patent website, the Chinese patent publication number CN115510781A discloses an anti-electricity theft warning model verification method based on an anti-electricity theft simulation experimental platform. A public transformer area or line is selected, and the corresponding electricity users are extracted and reproduced on the anti-electricity theft simulation experimental platform. Each group of historical electricity theft users and normal electricity users are retrieved from different areas, and all their electricity consumption data during the electricity theft period and the corresponding line loss data are extracted. The anti-electricity theft warning model verification method can verify the anti-electricity theft warning model in terms of completeness, accuracy, targeted users and detection timeliness, so as to achieve evaluation of scalability and universality.

[0005] However, the above patent has the following defects in actual use: the traditional anti-electricity theft inspection method is mainly based on on-site inspection of all users in the substation, which has certain limitations and slowness, and the efficiency of screening electricity theft users is low. At the same time, the existing anti-electricity theft inspection method cannot intelligently identify and control electricity theft users, resulting in poor management of electricity theft users and the inability to quickly detect electricity theft and take measures.

[0006] In order to solve the above problems, a system and method for identifying electricity theft users based on big data analysis is proposed. Summary of the invention

[0007] The purpose of the present invention is to provide a system and method for identifying electricity theft users based on big data analysis. The present device is used to work, thereby solving the problem that the traditional anti-electricity theft inspection method in the above background is mainly based on on-site inspection of all users in the substation area, which has certain limitations and slowness, and the efficiency of screening electricity theft users is low. At the same time, the existing anti-electricity theft inspection method cannot intelligently identify and control electricity theft users, resulting in poor management of electricity theft users and the inability to quickly discover electricity theft behavior and take measures.

[0008] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: A system for identifying electricity theft users based on big data analysis, characterized in that it comprises: a data acquisition module, a data processing module, an abnormality detection module, an intelligent recognition module and an alarm module;

[0009] The information collection module is used to collect the user's electricity usage information in real time and send the user's electricity usage information to the data processing module; the information collection module includes:

[0010] Current sensor, used to collect current information of users' electricity consumption in real time;

[0011] Voltage sensor, used to collect voltage information of users' electricity consumption in real time;

[0012] Power sensors are used to collect real-time information on the power consumption of users.

[0013] Preferably, the information acquisition module includes power consumption information, power supply information, consumption information and environmental information, and the acquisition module is used to comprehensively collect the power consumption information, power supply information, consumption information and environmental information of the power system; and the transmission module includes a wireless local area network or a data network, and the transmission module is used to transmit the collected power consumption information, power supply information, consumption information and environmental information through a wireless local area network or a data network.

[0014] Preferably, the data processing module can be used to pre-process the received user electricity usage information, obtain the user electricity usage information collected in real time, classify and analyze the user electricity usage information, and determine the user electricity usage characterization data and historical data based on big data. The data processing module includes:

[0015] A data retrieval unit is used to retrieve the user electricity usage information collected in real time, obtain the user electricity usage information collected in real time, filter the user electricity usage information collected in real time, filter out the user electricity usage information that is useless for intelligent identification of electricity theft users, and determine the user electricity usage information that is useful for identification;

[0016] The electricity theft identification module is used to identify electricity theft based on user electricity usage characterization data, obtain user electricity usage characterization data based on big data, analyze user electricity usage standard data and historical data, identify electricity theft based on user electricity usage characterization data, and determine the intelligent identification results of electricity theft users based on big data.

[0017] Preferably, the alarm module includes an automatic alarm, which is electrically connected to the data processing module. When the intelligent identification module determines that the user is stealing electricity, there are a series of possible electricity theft behaviors such as sudden increase or decrease in electricity volume, abnormal voltage and current, etc., the automatic alarm sounds an alarm to remind supervisors to conduct safety checks and take relevant measures to prevent electricity theft.

[0018] Preferably, the data processing module also includes a data grouping unit, which is used to group the retrieved user electricity usage information, obtain useful electricity information for intelligent identification of electricity theft users, group the user electricity usage information, and determine user electricity usage information groups with different categories, wherein the user electricity usage information groups store user electricity usage information with the same attributes.

[0019] Preferably, the intelligent identification module is used to intelligently manage and control the electricity theft users intelligently identified, obtain the intelligent identification results of the electricity theft users based on big data, and send early warning information to the electricity management party in the first time based on the intelligent identification results of the electricity theft users to determine whether the electricity theft phenomenon actually exists;

[0020] The intelligent identification module comprehensively analyzes these data, uses machine learning algorithms or statistical models to confirm the electricity theft behavior, and sends early warning information to managers for further verification and processing.

[0021] Preferably, the machine learning algorithm is a mapping function from input to output, which can adjust its own parameters according to a given electricity consumption data set so that the output can conform to the expected result as much as possible. The machine learning algorithm includes a model, an objective function, an optimization algorithm and hyperparameters.

[0022] The machine learning algorithm also includes linear regression and a supervised algorithm for predicting continuous power consumption numerical output. The machine learning algorithm also includes a KNN algorithm and a parameter-free supervised learning algorithm for classification and regression tasks.

[0023] Preferably, a method for identifying electricity theft users based on big data analysis comprises the following steps:

[0024] Step 1: The user uses the information collection module to collect the power consumption data of each group of users in real time, collects the power consumption, power supply, loss and environmental information in the power system, and sends the real-time collected user power consumption data to the data processing module. After receiving the user power consumption information, the processing module can classify and analyze the information to determine the user power consumption characterization data based on big data;

[0025] Step 2: The collected electricity consumption, power supply, loss and environmental information are transmitted through a wireless LAN or data network, and the electricity theft identification module is used to identify the electricity theft of the user's electricity consumption data, index the stored user electricity consumption standard data, and analyze it with the historical data. According to whether the actual power consumption and power supply are within the standard range, the user's electricity consumption characterization data is used to identify the electricity theft, and the intelligent identification result of the electricity theft user based on big data is determined;

[0026] Based on the user's electricity usage characterization data, the stored user standard electricity usage data that matches the user's electricity usage characterization data is indexed; in the case where the user's electricity usage characterization data is within the range of the user's electricity usage standard data, (1) the intelligent identification result of the electricity theft user based on big data is that the electricity user's electricity usage is normal and there is no electricity theft behavior; (2) in the case where the user's electricity usage characterization data is not within the range of the user's electricity usage standard data, the intelligent identification result of the electricity theft user based on big data is that the electricity user's electricity usage is abnormal and there is electricity theft behavior;

[0027] Step 3: Screen the information collected from the actual electricity theft screening area, and integrate the information of the target electricity theft screening area after screening. According to the information processed by the pre-processing unit, the area with the risk of electricity theft is obtained, and the risk level is comprehensively obtained. According to the analyzed information, the area with the risk of electricity theft is screened on the spot, and the information obtained from the on-site screening is fed back in a timely manner;

[0028] Step 4: Use the intelligent management and control module to perform intelligent management on the identified electricity theft users. Based on the intelligent identification results of the electricity theft users, if it is judged and confirmed that the user has committed electricity theft, the early warning information will be sent to the alarm module to prompt the supervisors and guide the management personnel to take anti-electricity theft measures in time.

[0029] Compared with the prior art, the present invention has the following beneficial effects:

[0030] 1. The present invention proposes a system and method for identifying electricity theft users based on big data analysis. The core of the system is to identify abnormal electricity usage behaviors by collecting, processing and analyzing a large amount of electricity usage data, so as to discover electricity theft users. The system collects users' electricity usage information in real time through a data acquisition module, including current, voltage, power and location information, and then the data processing module pre-processes these data to remove noise and abnormal values ​​to ensure the accuracy and reliability of the data; the abnormal detection module identifies possible electricity theft behaviors by analyzing abnormal changes in electricity usage data, such as sudden increases and decreases in electricity volume, abnormal voltage and current, etc.; finally, the intelligent recognition module comprehensively analyzes these data, confirms the electricity theft behaviors by using machine learning algorithms or statistical models, and sends early warning information to management personnel so that management personnel can further verify and handle them, and take measures to prevent electricity theft in time. By collecting electricity usage, power supply, loss and environmental information in the power system, and using artificial intelligence modules for pre-processing and analysis, the electricity theft users are finally determined, thereby improving the accuracy of screening.

[0031] 2. The intelligent identification system and method of electricity theft users based on big data of the present invention collects user electricity usage information in real time, and performs data retrieval, grouping and feature extraction on the user electricity usage information collected in real time, indexes the stored user electricity usage standard data, identifies electricity theft based on the user electricity usage characterization data, determines the intelligent identification results of electricity theft users based on big data, and issues warning information, and sends warning information based on the intelligent identification results of electricity theft users to the electricity theft power supply management party, guides the management personnel to carry out on-site verification in time, and can perform additional calculation of electricity according to the verification results, and can intelligently identify and control electricity theft users, which can improve the management effect of electricity theft users, and compare the information obtained by on-site screening with the risk level information of different locations in the target area obtained by analysis, so as to facilitate subsequent improvement of preprocessing and long-term use, and timely and accurately eliminate the electricity theft behaviors that meet the data characteristics in the bud without additional investment. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 This is a structural diagram of the electricity theft user identification system based on big data analysis of the present invention. DETAILED DESCRIPTION

[0033] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0034] In order to further understand the content of the present invention, the present invention is described in detail in conjunction with the accompanying drawings.

[0035] Example

[0036] Combination Figure 1 , a system for identifying electricity theft users based on big data analysis, including: a data acquisition module, a data processing module, an abnormality detection module, an intelligent recognition module and an alarm module;

[0037] The information collection module is used to collect the user's electricity usage information in real time and send the user's electricity usage information to the data processing module; the information collection module includes: a current sensor, which is used to collect the user's current information in real time; a voltage sensor, which is used to collect the user's voltage information in real time; and a power sensor, which is used to collect the user's power information in real time.

[0038] The information collection module acquisition module includes power consumption information, power supply information, consumption information and environmental information. The acquisition module is used to comprehensively collect the power consumption information, power supply information, consumption information and environmental information of the power system; and the transmission module includes a wireless local area network or a data network. The transmission module is used to transmit the collected power consumption information, power supply information, consumption information and environmental information through a wireless local area network or a data network.

[0039] The data processing module can be used to pre-process the received user electricity usage information, obtain the user electricity usage information collected in real time, classify and analyze the user electricity usage information, and determine the user electricity usage characterization data and historical data based on big data. The data processing module includes: a data retrieval unit, which is used to retrieve the user electricity usage information collected in real time, obtain the user electricity usage information collected in real time, filter the user electricity usage information collected in real time, filter out the user electricity usage information that is useless for intelligent identification of electricity theft users, and determine the user electricity usage information that is useful for identification; an electricity theft identification module: used to identify electricity theft on the user electricity usage characterization data, obtain the user electricity usage characterization data based on big data, analyze the user electricity usage standard data and historical data, identify electricity theft on the user electricity usage characterization data, and determine the intelligent identification result of electricity theft users based on big data.

[0040] The alarm module includes an automatic alarm, which is electrically connected to the data processing module. When the intelligent identification module determines that the user is stealing electricity, there are a series of possible electricity theft behaviors such as sudden increase or decrease in electricity volume, abnormal voltage and current, etc., the automatic alarm will sound an alarm to remind supervisors to conduct safety inspections and take relevant measures to prevent electricity theft.

[0041] The data processing module also includes a data grouping unit, which is used to group the retrieved user electricity usage information, obtain electricity information useful for intelligent identification of electricity theft users, group the user electricity usage information, and determine user electricity usage information groups with different categories, wherein the user electricity usage information groups store user electricity usage information with the same attributes.

[0042] The intelligent identification module is used to carry out intelligent management and control of the electricity theft users who have been intelligently identified, obtain the intelligent identification results of the electricity theft users based on big data, and send early warning information to the electricity management party as soon as possible based on the intelligent identification results of the electricity theft users to determine whether the electricity theft phenomenon actually exists; the intelligent identification module comprehensively analyzes these data, uses machine learning algorithms or statistical models to confirm the electricity theft behavior, and sends early warning information to the management personnel for further verification and processing.

[0043] A machine learning algorithm is a mapping function from input to output. It can adjust its own parameters according to a given electricity consumption data set so that the output can be as close to the expected result as possible. The machine learning algorithm includes models, objective functions, optimization algorithms, and hyperparameters. The machine learning algorithm also includes linear regression and supervised algorithms for predicting continuous electricity consumption numerical outputs. The machine learning algorithm also includes the KNN algorithm and parameter-free supervised learning algorithms for classification and regression tasks.

[0044] The present invention provides a method for identifying electricity theft users based on big data analysis, comprising the following steps:

[0045] Step 1: The user uses the information collection module to collect the power consumption data of each group of users in real time, collects the power consumption, power supply, loss and environmental information in the power system, and sends the real-time collected user power consumption data to the data processing module. After receiving the user power consumption information, the processing module can classify and analyze the information to determine the user power consumption characterization data based on big data;

[0046] Step 2: The collected electricity consumption, power supply, loss and environmental information are transmitted through a wireless LAN or data network, and the electricity theft identification module is used to identify the electricity theft of the user's electricity consumption data, index the stored user electricity consumption standard data, and analyze it with the historical data. According to whether the actual power consumption and power supply are within the standard range, the user's electricity consumption characterization data is used to identify the electricity theft, and the intelligent identification result of the electricity theft user based on big data is determined;

[0047] Based on the user's electricity usage characterization data, the stored user standard electricity usage data that matches the user's electricity usage characterization data is indexed; in the case where the user's electricity usage characterization data is within the range of the user's electricity usage standard data, (1) the intelligent identification result of the electricity theft user based on big data is that the electricity user's electricity usage is normal and there is no electricity theft behavior; (2) in the case where the user's electricity usage characterization data is not within the range of the user's electricity usage standard data, the intelligent identification result of the electricity theft user based on big data is that the electricity user's electricity usage is abnormal and there is electricity theft behavior;

[0048] Step 3: Screen the information collected from the actual electricity theft screening area, and integrate the information of the target electricity theft screening area after screening. According to the information processed by the pre-processing unit, the area with the risk of electricity theft is obtained, and the risk level is comprehensively obtained. According to the analyzed information, the area with the risk of electricity theft is screened on the spot, and the information obtained from the on-site screening is fed back in a timely manner;

[0049] Step 4: Use the intelligent management and control module to perform intelligent management on the identified electricity theft users. Based on the intelligent identification results of the electricity theft users, if it is judged and confirmed that the user has committed electricity theft, the early warning information will be sent to the alarm module to prompt the supervisors and guide the management personnel to take anti-electricity theft measures in time.

[0050] In summary, the invention proposes a system and method for identifying electricity theft users based on big data analysis: The invention proposes a system and method for identifying electricity theft users based on big data analysis, the core of which is to identify abnormal electricity usage behaviors by collecting, processing and analyzing a large amount of electricity usage data, so as to discover electricity theft users. The system collects users' electricity usage information in real time through a data acquisition module, including current, voltage, power and location information, and then the data processing module pre-processes these data to remove noise and abnormal values ​​to ensure the accuracy and reliability of the data; the abnormal detection module identifies possible electricity theft behaviors by analyzing abnormal changes in electricity usage data, such as sudden increases and decreases in electricity consumption, abnormal voltage and current, etc.; finally, the intelligent identification module comprehensively analyzes these data, confirms the electricity theft behaviors by using machine learning algorithms or statistical models, and sends early warning information to management personnel so that management personnel can further verify and handle them, and take measures to prevent electricity theft in time, and finally determine electricity theft users by collecting electricity usage, power supply, loss and environmental information in the power system, and using artificial intelligence modules for pre-processing and analysis, thereby improving the accuracy of screening;

[0051] The big data-based intelligent identification system and method for electricity theft users of the present invention collects electricity usage information of users in real time, and performs data retrieval, grouping and feature extraction on the electricity usage information of users collected in real time, indexes the stored standard electricity usage data of users, identifies electricity theft based on the electricity usage characterization data of users, determines the intelligent identification results of electricity theft users based on big data, issues warning information, and sends warning information based on the intelligent identification results of electricity theft users to the electricity theft power supply management party, guides the management personnel to carry out on-site verification in a timely manner, and can perform additional calculation of electricity according to the verification results, and can intelligently identify and control electricity theft users, which can improve the management effect of electricity theft users, and compare the information obtained by on-site screening with the risk level information of different locations in the target area obtained by analysis, so as to facilitate subsequent improvement of preprocessing and long-term use, and timely and accurately eliminate the electricity theft behavior that meets the data characteristics in the bud without additional investment.

[0052] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0053] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A system for identifying electricity theft users based on big data analysis, characterized in that: include: Data acquisition module, data processing module, anomaly detection module, intelligent recognition module and alarm module; An information collection module is used to collect user power consumption information in real time and send the user power consumption information to a data processing module; The information collection module includes: Current sensor, used to collect current information of users' electricity consumption in real time; Voltage sensor, used to collect voltage information of users' electricity consumption in real time; Power sensors are used to collect real-time information on the power consumption of users. The information acquisition module includes power consumption information, power supply information, consumption information and environmental information. The acquisition module is used to comprehensively collect the power consumption information, power supply information, consumption information and environmental information of the power system; and the transmission module includes a wireless local area network or a data network. The transmission module is used to transmit the collected power consumption information, power supply information, consumption information and environmental information through a wireless local area network or a data network. The data processing module can be used to pre-process the received user electricity usage information, obtain the user electricity usage information collected in real time, classify and analyze the user electricity usage information, and determine the user electricity usage characterization data and historical data based on big data. The data processing module includes: A data retrieval unit is used to retrieve the user electricity usage information collected in real time, obtain the user electricity usage information collected in real time, filter the user electricity usage information collected in real time, filter out the user electricity usage information that is useless for intelligent identification of electricity theft users, and determine the user electricity usage information that is useful for identification; The electricity theft identification module is used to identify electricity theft based on user electricity usage characterization data, obtain user electricity usage characterization data based on big data, analyze user electricity usage standard data and historical data, identify electricity theft based on user electricity usage characterization data, and determine the intelligent identification results of electricity theft users based on big data. The alarm module includes an automatic alarm, which is electrically connected to the data processing module. When the intelligent identification module determines that the user is stealing electricity, there are a series of possible electricity theft behaviors such as sudden increase or decrease in electricity volume, abnormal voltage and current, etc., the automatic alarm sounds an alarm to remind supervisors to conduct safety inspections and take relevant measures to prevent electricity theft.

2. The electricity theft user identification system based on big data analysis according to claim 1 is characterized by: The data processing module also includes a data grouping unit, which is used to group the retrieved user electricity usage information, obtain electricity information useful for intelligent identification of electricity theft users, group the user electricity usage information, and determine user electricity usage information groups with different categories, wherein the user electricity usage information groups store user electricity usage information with the same attributes.

3. The electricity theft user identification system based on big data analysis according to claim 2 is characterized by: The intelligent identification module is used to intelligently manage and control the electricity theft users intelligently identified, obtain the intelligent identification results of electricity theft users based on big data, and send early warning information to the electricity management party in the first time based on the intelligent identification results of electricity theft users to determine whether the electricity theft phenomenon actually exists; The intelligent identification module comprehensively analyzes these data, uses machine learning algorithms or statistical models to confirm the electricity theft behavior, and sends early warning information to managers for further verification and processing.

4. The system for identifying electricity theft users based on big data analysis according to claim 3 is characterized by: The machine learning algorithm is a mapping function from input to output. It can adjust its own parameters according to a given electricity consumption data set so that the output can conform to the expected result as much as possible. The machine learning algorithm includes a model, an objective function, an optimization algorithm and hyperparameters.

5. The system for identifying electricity theft users based on big data analysis according to claim 4 is characterized by: The machine learning algorithm also includes linear regression and a supervised algorithm for predicting continuous power consumption numerical output. The machine learning algorithm also includes a KNN algorithm and a parameter-free supervised learning algorithm for classification and regression tasks.

6. A method for identifying electricity theft users based on big data analysis, characterized in that: It is implemented by using the electricity theft user identification system based on big data analysis as described in any one of claims 1 to 5, and the electricity theft user identification method comprises the following steps: Step 1: The user uses the information collection module to collect the power consumption data of each group of users in real time, collects the power consumption, power supply, loss and environmental information in the power system, and sends the real-time collected user power consumption data to the data processing module. After receiving the user power consumption information, the processing module can classify and analyze the information to determine the user power consumption characterization data based on big data; Step 2: The collected electricity consumption, power supply, loss and environmental information are transmitted through a wireless LAN or data network, and the electricity theft identification module is used to identify the electricity theft of the user's electricity consumption data, index the stored user electricity consumption standard data, and analyze it with the historical data. According to whether the actual power consumption and power supply are within the standard range, the user's electricity consumption characterization data is used to identify the electricity theft, and the intelligent identification result of the electricity theft user based on big data is determined; Based on the user's electricity usage characterization data, the stored user standard electricity usage data that matches the user's electricity usage characterization data is indexed; in the case where the user's electricity usage characterization data is within the range of the user's electricity usage standard data, (1) the intelligent identification result of the electricity theft user based on big data is that the electricity user's electricity usage is normal and there is no electricity theft behavior; (2) in the case where the user's electricity usage characterization data is not within the range of the user's electricity usage standard data, the intelligent identification result of the electricity theft user based on big data is that the electricity user's electricity usage is abnormal and there is electricity theft behavior; Step 3: Screen the information collected from the actual electricity theft screening area, and integrate the information of the target electricity theft screening area after screening. According to the information processed by the pre-processing unit, the area with the risk of electricity theft is obtained, and the risk level is comprehensively obtained. According to the analyzed information, the area with the risk of electricity theft is screened on the spot, and the information obtained from the on-site screening is fed back in a timely manner; Step 4: Use the intelligent management and control module to perform intelligent management on the identified electricity theft users. Based on the intelligent identification results of the electricity theft users, if it is judged and confirmed that the user has committed electricity theft, the early warning information will be sent to the alarm module to prompt the supervisors and guide the management personnel to take anti-electricity theft measures in time.

Images