Method and device for monitoring abnormity of elderly living alone based on power consumption data

Abstract

The invention provides a method and a device for monitoring abnormity of elderly people living alone based on power consumption data, and belongs to the technical field of power data. The method comprises the following steps: acquiring first historical power consumption data and current power consumption data of a target elderly living alone; determining a power consumption behavior type of the target elderly living alone according to the first historical power consumption data; according to a power utilization threshold value corresponding to the power utilization behavior type of the target elderly living alone and the current power utilization data, determining whether the target elderly living alone has a power utilization abnormal risk at present; if the target elderly people living alone currently have the risk of abnormal electricity utilization, predicting the electricity utilization data of the target elderly people living alone at the next moment to obtain target electricity utilization data; and according to the target power consumption data and the corresponding power consumption threshold, determining an abnormal monitoring result of the target elderly living alone. According to the invention, abnormity monitoring of the elderly living alone can be timely and effectively realized.

Description

Technical Field

[0001] The present invention relates to the technical field of power data, and in particular to a method and device for abnormal monitoring of elderly people living alone based on electricity consumption data. Background Art

[0002] With the continuous deepening of the aging degree of the population in our country, the number of elderly people living alone is also increasing. Considering that elderly people living alone are prone to accidents at home, it is necessary to provide timely health monitoring for them to provide real-time guarantee for their lives.

[0003] Currently, the monitoring of elderly people living alone mostly uses technologies such as wearing smart devices like smart bracelets, installing surveillance videos or artificial intelligence to identify and monitor the behaviors of elderly people living alone to achieve abnormal monitoring. However, the cost of abnormal monitoring of elderly people living alone through these methods is relatively high, and the usage of smart devices by elderly people living alone is relatively low, making it difficult to achieve timely and effective abnormal monitoring of elderly people living alone. Summary of the Invention

[0004] Embodiments of the present invention provide a method and device for abnormal monitoring of elderly people living alone based on electricity consumption data to achieve timely and effective abnormal monitoring of elderly people living alone.

[0005] In a first aspect, embodiments of the present invention provide a method for abnormal monitoring of elderly people living alone based on electricity consumption data, including:

[0006] Obtain the first historical electricity consumption data and current electricity consumption data of the target elderly person living alone;

[0007] Determine the electricity consumption behavior type of the target elderly person living alone according to the first historical electricity consumption data;

[0008] Determine whether there is a risk of abnormal electricity consumption for the target elderly person living alone currently according to the electricity consumption threshold corresponding to the electricity consumption behavior type of the target elderly person living alone and the current electricity consumption data;

[0009] If there is a risk of abnormal electricity consumption for the target elderly person living alone currently, predict the electricity consumption data of the next moment of the target elderly person living alone to obtain target electricity consumption data; and determine the abnormal monitoring result of the target elderly person living alone according to the target electricity consumption data and the corresponding electricity consumption threshold.

[0010] In a possible implementation manner, the electricity consumption threshold includes a lower limit threshold and an upper limit threshold;

[0011] The determining whether there is a risk of abnormal electricity consumption for the target elderly person living alone currently according to the electricity consumption threshold corresponding to the electricity consumption behavior type of the target elderly person living alone and the current electricity consumption data includes:

[0012] Determine whether the current electricity consumption data is between the upper threshold and the lower threshold;

[0013] If the current electricity consumption data is not between the upper threshold and the lower threshold, determine that the target elderly person living alone currently has a risk of abnormal electricity consumption;

[0014] If the current electricity consumption data is between the upper threshold and the lower threshold, determine that the target elderly person living alone currently has no risk of abnormal electricity consumption.

[0015] In a possible implementation, the determining the abnormal monitoring result of the target elderly person living alone according to the target electricity consumption data and the corresponding electricity consumption threshold includes:

[0016] Determine whether the target electricity consumption data is between the upper threshold and the lower threshold;

[0017] If the target electricity consumption data is not between the upper threshold and the lower threshold, determine that the abnormal monitoring result of the target elderly person living alone is abnormal electricity consumption;

[0018] If the target electricity consumption data is between the upper threshold and the lower threshold, determine that the abnormal monitoring result of the target elderly person living alone is no abnormal electricity consumption.

[0019] In a possible implementation, the electricity consumption threshold includes a lower threshold and an upper threshold;

[0020] The determining whether the target elderly person living alone currently has a risk of abnormal electricity consumption according to the electricity consumption threshold corresponding to the electricity consumption behavior type of the target elderly person living alone and the current electricity consumption data includes:

[0021] Determine whether the difference between the current electricity consumption data and the lower threshold is greater than a first preset threshold, and whether the difference between the current electricity consumption data and the upper threshold is greater than a second preset threshold;

[0022] If the difference between the current electricity consumption data and the lower threshold is not greater than the first preset threshold, or the difference between the current electricity consumption data and the upper threshold is not greater than the second preset threshold, determine that the target elderly person living alone currently has a risk of abnormal electricity consumption;

[0023] If the difference between the current electricity consumption data and the lower threshold is greater than the first preset threshold, and the difference between the current electricity consumption data and the upper threshold is greater than the second preset threshold, then determine whether the current electricity consumption data is less than the lower threshold and whether the current electricity consumption data is greater than the upper threshold; if the current electricity consumption data is not less than the lower threshold and the current electricity consumption data is not greater than the upper threshold, then determine that there is no current electricity consumption anomaly risk for the target elderly living alone.

[0024] In a possible implementation manner, the determining the abnormal monitoring result of the target elderly living alone according to the target electricity consumption data and the corresponding electricity consumption threshold includes:

[0025] Determine whether the target electricity consumption data is less than the difference between the lower threshold and the first preset threshold, and whether the target electricity consumption data is greater than the sum of the upper threshold and the second preset threshold;

[0026] If the target electricity consumption data is less than the difference between the lower threshold and the first preset threshold, or the target electricity consumption data is greater than the sum of the upper threshold and the second preset threshold, then determine that the abnormal monitoring result of the target elderly living alone is abnormal electricity consumption;

[0027] If the target electricity consumption data is not less than the difference between the lower threshold and the first preset threshold, and the target electricity consumption data is not greater than the sum of the upper threshold and the second preset threshold, then determine that the abnormal monitoring result of the target elderly living alone is no abnormal electricity consumption.

[0028] In a possible implementation manner, after determining whether the current electricity consumption data is less than the lower threshold and whether the current electricity consumption data is greater than the upper threshold, it further includes:

[0029] If the current electricity consumption data is less than the lower threshold, or the current electricity consumption data is greater than the upper threshold, then determine that the target elderly living alone currently has an electricity consumption anomaly.

[0030] In a possible implementation manner, before obtaining the first historical electricity consumption data and the current electricity consumption data of the target elderly living alone, it further includes:

[0031] Obtain the second historical electricity consumption data of the user to be identified;

[0032] According to the second historical electricity consumption data, calculate the electricity consumption characteristics of the user to be identified; wherein, the electricity consumption characteristics include day-night electricity consumption fluctuations, a first ratio of the average electricity consumption on weekdays to the average electricity consumption on rest days within a first preset duration, a second ratio of the average electricity consumption on holidays to the average electricity consumption on non-holidays within a second preset duration, and the average daily electricity consumption.

[0033] Input the electricity consumption characteristics of the user to be identified into a preset identification model for elderly living alone, and obtain the category label of the user to be identified output by the identification model for elderly living alone; wherein, the category label is an elderly living alone or a non-elderly living alone; the identification model for elderly living alone is trained based on the electricity consumption characteristics calculated from historical electricity consumption data of different categories and the category labels corresponding to the electricity consumption characteristics.

[0034] If the category label of the user to be identified is an elderly living alone, then regard the user to be identified as the target elderly living alone.

[0035] In a possible implementation manner, determining the electricity consumption behavior type of the target elderly living alone according to the first historical electricity consumption data includes:

[0036] Cluster the sample electricity consumption data of the elderly living alone with different electricity consumption behavior types to obtain the characteristic clustering centers of each electricity consumption behavior type.

[0037] According to the first historical electricity consumption data and the characteristic clustering centers, determine the similarities between the first historical electricity consumption data and each electricity consumption behavior type respectively.

[0038] Determine the electricity consumption behavior type corresponding to the maximum similarity as the electricity consumption behavior type of the target elderly living alone.

[0039] In a possible implementation manner, clustering the sample electricity consumption data of the elderly living alone with different electricity consumption behavior types to obtain the characteristic clustering centers of each electricity consumption behavior type includes:

[0040] Obtain the sample electricity consumption data of multiple elderly living alone.

[0041] Set the relevant parameters for clustering the sample electricity consumption data, and the relevant parameters include clustering centers, number of iterations, and maximum number of iterations.

[0042] Calculate the similarities between the sample electricity consumption data of each elderly living alone and each clustering center respectively, and cluster each elderly living alone to the nearest clustering center; calculate the average value of the sample electricity consumption data of all elderly living alone in each clustering center respectively, and regard the average value as the new clustering center; complete one iteration calculation of the clustering center.

[0043] Keep iterating until the maximum number of iterations is reached, and regard each clustering center corresponding to the maximum number of iterations as the characteristic clustering centers of different electricity consumption behavior types.

[0044] In a second aspect, an embodiment of the present invention provides a monitoring device for abnormal situations of the elderly living alone based on electricity consumption data, including:

[0045] An acquisition module, configured to acquire first historical power consumption data and current power consumption data of a target elderly person living alone;

[0046] A classification module, configured to determine the power consumption behavior type of the target elderly person living alone according to the first historical power consumption data;

[0047] A first determination module, configured to determine whether there is a risk of abnormal power consumption for the target elderly person living alone according to the power consumption threshold corresponding to the power consumption behavior type of the target elderly person living alone and the current power consumption data;

[0048] A second determination module, configured to, if there is a risk of abnormal power consumption for the target elderly person living alone currently, predict the power consumption data of the target elderly person at the next moment to obtain target power consumption data; and determine the abnormal monitoring result of the target elderly person living alone according to the target power consumption data and the corresponding power consumption threshold.

[0049] The beneficial effects of the embodiments of the present invention compared with the prior art are as follows:

[0050] In the embodiments of the present invention, the power consumption behavior type of the target elderly person living alone is determined through the first historical power consumption data of the target elderly person living alone, so as to clarify the power consumption characteristics of the target elderly person living alone, so as to analyze the power consumption situation of the target elderly person living alone; then, through the current power consumption data of the target elderly person living alone and the power consumption threshold corresponding to the power consumption behavior type, it can be judged whether there is a risk of abnormal power consumption for the elderly person living alone currently, and a preliminary judgment on the behavior of the elderly person living alone can be made; if there is a risk of abnormal power consumption for the elderly person living alone currently, it may indicate that there is an abnormality in the health of the elderly person living alone, or it may be caused by the normal power consumption operation of the elderly person living alone. Therefore, the power consumption data of the target elderly person living alone at the next moment is predicted to obtain target power consumption data, and then the abnormal monitoring result of the target elderly person living alone is further judged through the target power consumption data, accurately obtaining whether the power consumption of the elderly person living alone is abnormal, thereby judging the health condition of the elderly person living alone, being able to rescue the elderly person living alone in time, without setting additional intelligent devices or monitoring video devices, etc., and being able to quickly and efficiently realize the abnormal monitoring of the elderly person living alone, reducing the cost of abnormal monitoring. Description of the Drawings

[0051] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0052] Figure 1 It is the first implementation flowchart of the method for abnormal monitoring of the elderly person living alone based on power consumption data provided by the embodiments of the present invention;

[0053] Figure 2 It is a schematic diagram of the power consumption threshold provided by an embodiment of the present invention;

[0054] Figure 3 It is the second implementation flowchart of the method for monitoring the abnormality of the elderly living alone based on power consumption data provided by an embodiment of the present invention;

[0055] Figure 4 It is a schematic structural diagram of the device for monitoring the abnormality of the elderly living alone based on power consumption data provided by an embodiment of the present invention. Detailed implementation manners

[0056] In the following description, specific details such as specific system structures and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present invention. However, those skilled in the art should clearly understand that the present invention can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present invention.

[0057] To make the objectives, technical solutions, and advantages of the present invention clearer, the following will be described through specific embodiments with reference to the accompanying drawings.

[0058] Figure 1 The implementation flowchart of the method for monitoring the abnormality of the elderly living alone based on power consumption data provided by an embodiment of the present invention is described in detail as follows:

[0059] Step S101: Obtain the first historical power consumption data and the current power consumption data of the target elderly person living alone.

[0060] Here, the first historical power consumption data may be the online load data of the elderly person living alone. For example, the load data of 96 sampling points at intervals of 15 minutes. The current power consumption data may be the load data corresponding to the current sampling point.

[0061] Optionally, after obtaining the first historical power consumption data and the current power consumption data of the target elderly person living alone, the missing value filling of the first historical power consumption data can also be performed.

[0062] The formula for missing value filling can be: In the formula, represents the data corresponding to the missing value at time t calculated for the target elderly person i, represents the measured value of the target elderly person i at time t within date j, that is, the power consumption data, Ω represents the set of all measured values at time t, and N represents the number of dates included in Ω.

[0063] Step S102: Determine the type of power consumption behavior of the target elderly person living alone according to the first historical power consumption data.

[0064] In this embodiment, considering the different lifestyles of the elderly living alone, there are generally three types of electricity consumption behaviors: for the elderly living alone with the first type of electricity consumption behavior, their electricity consumption data is relatively flat, the overall electricity consumption is small, and electricity consumption peaks occur in the morning and at night; for the elderly living alone with the second type of electricity consumption behavior, electricity consumption peaks occur in the morning and at noon, especially with large fluctuations in electricity consumption at noon; for the elderly living alone with the third type of electricity consumption behavior, the electricity consumption increases compared with other periods in the morning, at noon, and in the evening, and the overall electricity consumption is larger than that of the above two types.

[0065] Due to the different types of electricity consumption behaviors of the elderly living alone, when detecting abnormalities in the elderly living alone, it is also necessary to classify them in order to accurately monitor.

[0066] Step S103, determine whether there is a risk of abnormal electricity consumption for the target elderly living alone currently according to the electricity consumption threshold corresponding to the electricity consumption behavior type of the target elderly living alone and the current electricity consumption data.

[0067] In this embodiment, each type of electricity consumption behavior corresponds to an electricity consumption threshold, and the electricity consumption threshold corresponding to the target elderly living alone is selected to judge the electricity consumption situation of the elderly living alone.

[0068] Here, first, a preliminary judgment of abnormal electricity consumption is made through the current electricity consumption data and the electricity consumption threshold corresponding to the target elderly living alone.

[0069] Step S104, if there is a risk of abnormal electricity consumption for the target elderly living alone currently, then predict the electricity consumption data of the target elderly living alone at the next moment to obtain the target electricity consumption data; and determine the abnormal monitoring result of the target elderly living alone according to the target electricity consumption data and the corresponding electricity consumption threshold.

[0070] In this embodiment, if it is preliminarily determined that there is a risk of abnormal electricity consumption for the target elderly living alone, it means that the current electricity consumption of the target elderly living alone is abnormal. This may be caused by the actual abnormal electricity consumption of the target elderly living alone, or may be caused by data collection errors or other reasons. Therefore, predict the electricity consumption data at the next moment, and then use the predicted target electricity consumption data and the corresponding electricity consumption threshold to make a judgment to accurately obtain the abnormal monitoring result of the target elderly living alone.

[0071] In the embodiments of the present invention, the type of electricity consumption behavior of the target elderly living alone is determined through the first historical electricity consumption data of the target elderly living alone, so as to clarify the electricity consumption characteristics of the target elderly living alone, so as to analyze the electricity consumption situation of the target elderly living alone; then, through the current electricity consumption data of the target elderly living alone and the electricity consumption threshold corresponding to the type of electricity consumption behavior, it can be judged whether there is a risk of abnormal electricity consumption for the elderly living alone at present, and a preliminary judgment on the behavior of the elderly living alone can be made; if there is a risk of abnormal electricity consumption for the elderly living alone at present, it may indicate that there is an abnormality in the health of the elderly living alone, or it may be caused by the normal electricity consumption operation of the elderly living alone. Therefore, the electricity consumption data of the target elderly living alone at the next moment is predicted to obtain the target electricity consumption data, and then the abnormal monitoring result of the target elderly living alone is further judged through the target electricity consumption data, and it is accurately obtained whether the electricity consumption of the elderly living alone is abnormal, so as to judge the health status of the elderly living alone, and the elderly living alone can be rescued in time without setting up additional intelligent devices or monitoring video devices, etc., and the abnormal monitoring of the elderly living alone can be realized quickly and efficiently, and the cost of abnormal monitoring can be reduced.

[0072] In some embodiments, the electricity consumption threshold includes a lower limit threshold and an upper limit threshold.

[0073] In this embodiment, according to the electricity consumption threshold corresponding to the type of electricity consumption behavior of the target elderly living alone and the current electricity consumption data, it is determined whether there is a risk of abnormal electricity consumption for the target elderly living alone at present, which may be: judging whether the current electricity consumption data is between the upper limit threshold and the lower limit threshold; if the current electricity consumption data is not between the upper limit threshold and the lower limit threshold, it is determined that there is a risk of abnormal electricity consumption for the target elderly living alone at present; if the current electricity consumption data is between the upper limit threshold and the lower limit threshold, it is determined that there is no risk of abnormal electricity consumption for the target elderly living alone at present.

[0074] In this embodiment, if the current electricity consumption data is between the upper limit threshold and the lower limit threshold, it means that the current electricity consumption data of the target elderly living alone is within the normal range, that is, there is no risk of abnormal electricity consumption.

[0075] If the current electricity consumption data is not between the upper limit threshold and the lower limit threshold, it means that the current electricity consumption data of the target elderly living alone is outside the normal range, and there is a risk of abnormal electricity consumption.

[0076] Optionally, in this embodiment, according to the target electricity consumption data and the corresponding electricity consumption threshold, the abnormal monitoring result of the target elderly living alone is determined, which may be: judging whether the target electricity consumption data is between the upper limit threshold and the lower limit threshold; if the target electricity consumption data is not between the upper limit threshold and the lower limit threshold, it is determined that the abnormal monitoring result of the target elderly living alone is abnormal electricity consumption; if the target electricity consumption data is between the upper limit threshold and the lower limit threshold, it is determined that the abnormal monitoring result of the target elderly living alone is no abnormal electricity consumption.

[0077] In this embodiment, after predicting the target power consumption data of the target elderly living alone at the next moment, if the target power consumption data is between the upper threshold and the lower threshold, it indicates that the current power consumption data may be affected by data acquisition errors or other reasons, resulting in being outside the normal range, rather than there being abnormal power consumption.

[0078] If the target power consumption data is still not between the upper threshold and the lower threshold, it means that the target power consumption data is also outside the normal range. It can be considered that there is a risk of abnormal power consumption for the target elderly living alone, that is, there may be abnormalities in the life of the target elderly living alone. Accordingly, an alarm message can be sent to relevant personnel to remind them to check or make a home visit to help the target elderly living alone.

[0079] In some other embodiments, the power consumption threshold includes a lower threshold and an upper threshold.

[0080] In this embodiment, determining whether there is a risk of abnormal power consumption for the target elderly living alone based on the power consumption threshold corresponding to the power consumption behavior type of the target elderly living alone and the current power consumption data may be:

[0081] First, determine whether the difference between the current power consumption data and the lower threshold is greater than a first preset threshold, and whether the difference between the current power consumption data and the upper threshold is greater than a second preset threshold.

[0082] See Figure 2 the schematic diagram of the power consumption threshold shown in, where it is considered the normal power consumption range between the upper threshold λ2 and the lower threshold λ1. Considering the fluctuations in the daily power consumption data of the elderly living alone, a fluctuation range is set at the upper and lower thresholds respectively, that is, the first preset threshold (the corresponding fluctuation range is such as Figure 2 the area between the midpoints A1 and A2) and the second preset threshold (the corresponding fluctuation range is such as Figure 2 the area between the midpoints B1 and B2).

[0083] If the difference between the current power consumption data and the lower threshold λ1 is not greater than the first preset threshold, or the difference between the current power consumption data and the upper threshold is not greater than the second preset threshold, it is determined that there is a risk of abnormal power consumption for the target elderly living alone at present. Here, the current power consumption data is within the above-mentioned fluctuation range, indicating that the current power consumption data has approached the boundaries of the normal power consumption range, that is, the lower threshold λ1 and the upper threshold λ2, and there may be a possibility of abnormal power consumption beyond the fluctuation range at the next moment, that is, there is a risk of abnormal power consumption.

[0084] If the difference between the current electricity consumption data and the lower threshold λ1 is greater than the first preset threshold, and the difference between the current electricity consumption data and the upper threshold is greater than the second preset threshold, then determine whether the current electricity consumption data is less than the lower threshold λ1 and whether the current electricity consumption data is greater than the upper threshold λ2; if the current electricity consumption data is not less than the lower threshold λ1 and the current electricity consumption data is not greater than the upper threshold λ2, it is determined that there is no current risk of abnormal electricity consumption for the target elderly living alone.

[0085] Here, since the current electricity consumption data is not within the above-mentioned fluctuation range, it indicates that the current electricity consumption data may be within the safe electricity consumption range or has seriously exceeded the normal electricity consumption range. Therefore, it is further determined which situation it belongs to. If the current electricity consumption data is not less than the lower threshold λ1 and the current electricity consumption data is not greater than the upper threshold λ2, that is, the current electricity consumption data is between the lower threshold λ1 and the upper threshold λ2, it means that the current electricity consumption data is within the safe electricity consumption range, that is, there is no current risk of abnormal electricity consumption.

[0086] Exemplarily, the first preset threshold can be 0.05λ1, and the second preset threshold can be 0.05λ2.

[0087] Optionally, after this embodiment determines whether the current electricity consumption data is less than the lower threshold λ1 and whether the current electricity consumption data is greater than the upper threshold λ2, it further includes: if the current electricity consumption data is less than the lower threshold λ1, or the current electricity consumption data is greater than the upper threshold λ2, it is determined that there is current abnormal electricity consumption for the target elderly living alone.

[0088] Here, if the current electricity consumption data is less than the lower threshold λ1, or the current electricity consumption data is greater than the upper threshold λ2, it means that the current electricity consumption data has seriously exceeded the normal electricity consumption range, and it can be directly considered that there is current abnormal electricity consumption for the target elderly living alone, and an alarm message can be sent to relevant personnel to remind them to check or visit the home to help the target elderly living alone.

[0089] Optionally, according to the target electricity consumption data and the corresponding electricity consumption threshold, the abnormal monitoring result of the target elderly living alone determined by this embodiment may be:

[0090] Judge whether the target electricity consumption data is less than the difference between the lower threshold and the first preset threshold, and whether the target electricity consumption data is greater than the sum of the upper threshold and the second preset threshold. As Figure 2 shown, that is, judge whether the target electricity consumption data is to the left of point A1 and whether the target electricity consumption data is to the right of point B2.

[0091] If the target electricity consumption data is less than the difference between the lower threshold and the first preset threshold, or the target electricity consumption data is greater than the sum of the upper threshold and the second preset threshold, it is determined that the abnormal monitoring result of the target elderly living alone is abnormal electricity consumption.

[0092] Here, if the target electricity consumption data is to the left of point A1 or to the right of point B2, it indicates that the predicted target electricity consumption data for the next moment of the target elderly living alone has seriously exceeded the normal electricity consumption range, which is abnormal electricity consumption data. It can be considered that there is current abnormal electricity consumption for the target elderly living alone. Accordingly, an alarm message can be sent to relevant personnel to remind them to check or make a home visit to assist the target elderly living alone.

[0093] Exemplarily, if the fluctuation range is divided by 0.05, then point A1 is 0.95λ1 and point B2 is 1.05λ2.

[0094] If the target electricity consumption data is not less than the difference between the lower limit threshold and the first preset threshold, and the target electricity consumption data is not greater than the sum of the upper limit threshold and the second preset threshold, then it is determined that the abnormal monitoring result of the target elderly living alone is that there is no abnormal electricity consumption.

[0095] Here, if the target electricity consumption data is between point A1 and point B2, it indicates that the predicted target electricity consumption data for the next moment of the target elderly living alone has not seriously exceeded the normal electricity consumption range and still belongs to the normal electricity consumption situation. Then, the target elderly living alone can be continuously monitored.

[0096] In some embodiments, according to the first historical electricity consumption data, the electricity consumption behavior type of the target elderly living alone can be determined as follows:

[0097] First, cluster the sample electricity consumption data of the elderly living alone with different electricity consumption behavior types to obtain the characteristic clustering centers of each electricity consumption behavior type.

[0098] Then, according to the first historical electricity consumption data and the characteristic clustering centers, determine the similarity between the first historical electricity consumption data and each electricity consumption behavior type respectively.

[0099] Finally, determine the electricity consumption behavior type corresponding to the maximum similarity as the electricity consumption behavior type of the target elderly living alone.

[0100] In this embodiment, by clustering the sample electricity consumption data of the elderly living alone with different electricity consumption behavior types, the elderly living alone with different electricity consumption behavior types can be classified to obtain the clustering clusters of each electricity consumption behavior type. Accordingly, the clustering centers of each clustering cluster, that is, the characteristic clustering centers, can be obtained.

[0101] By determining the similarity between the first historical electricity consumption data and each characteristic clustering center, the similarity between the first historical electricity consumption data and each clustering cluster can be determined, so as to determine the clustering cluster to which the first historical electricity consumption data belongs and obtain the electricity consumption behavior type of the target elderly living alone, that is, the electricity consumption behavior type corresponding to the maximum similarity.

[0102] Here, the calculation formula for similarity can be:

[0103]

[0104] In the formula, cos(ψ, C r ) represents the similarity between the first historical electricity consumption data ψ and the characteristic clustering center C r , ψ represents the first historical electricity consumption data, and C r represents the r-th characteristic clustering center, X i represents the i-th data in the first historical electricity consumption data ψ, and C ri represents the i-th data in the r-th characteristic clustering center, and N represents the total number of data in the first historical electricity consumption data ψ or the r-th characteristic clustering center.

[0105] Optionally, in this embodiment, the sample electricity consumption data of the elderly living alone with different electricity consumption behavior types is clustered to obtain the characteristic clustering centers of each electricity consumption behavior type, which may be:

[0106] First, obtain the sample electricity consumption data of multiple elderly living alone.

[0107] Then, set the relevant parameters for clustering the sample electricity consumption data. The relevant parameters include the clustering center, the number of iterations, and the maximum number of iterations.

[0108] Calculate the similarity between the sample electricity consumption data of each elderly living alone and each clustering center respectively, and cluster each elderly living alone to the nearest clustering center; calculate the average value of the sample electricity consumption data of all elderly living alone in each clustering center respectively, and use the average value as the new clustering center; complete one iteration calculation of the clustering center.

[0109] Finally, continuously iterate until the maximum number of iterations is reached, and use each clustering center corresponding to the maximum number of iterations as the characteristic clustering centers of different electricity consumption behavior types.

[0110] In this embodiment, the K-means clustering algorithm can be used to cluster the sample electricity consumption data of multiple elderly living alone, and among them, the number of clustering centers can be set to 3.

[0111] Here, by continuously iterating to calculate the new clustering center, the sample electricity consumption data of multiple elderly living alone can be divided into three types, that is, three final clustering clusters are obtained.

[0112] In some embodiments, the inventor of the present invention considers that the relevant elderly living alone are mainly identified and confirmed through the way of manual visits by community personnel. This way requires manual identification, and moreover, the visits are difficult to be carried out in a timely manner, resulting in the problems of high cost and low efficiency.

[0113] Based on this, in this embodiment, before performing anomaly detection on the elderly living alone, the power data is used to identify the elderly living alone, so as to quickly and comprehensively identify the elderly living alone and perform anomaly monitoring.

[0114] As Figure 3 shown, in this embodiment, before obtaining the first historical power consumption data and the current power consumption data of the target elderly living alone, the following steps can also be performed:

[0115] First, obtain the second historical power consumption data of the user to be identified.

[0116] In this embodiment, considering that there are differences in the power consumption behaviors of the elderly living alone and the elderly not living alone, the elderly living alone can be identified through power consumption data. Here, the second historical power consumption data can be the power consumption data of the user to be identified in the past year.

[0117] Then, according to the second historical power consumption data, calculate the power consumption characteristics of the user to be identified; among them, the power consumption characteristics include the day-night power consumption fluctuation, the first ratio of the average power consumption on weekdays to the average power consumption on rest days within the first preset duration, the second ratio of the average power consumption on holidays to the average power consumption on non-holiday days within the second preset duration, and the average daily power consumption.

[0118] In this embodiment, the peak power consumption at night of the elderly not living alone shows a later trend compared to that of the elderly living alone, with a time difference, and the power consumption at night of the elderly living alone is much higher than that during the day, resulting in a large day-night power consumption fluctuation. The power consumption on rest days of the elderly not living alone is much higher than that on weekdays, and they are greatly affected by rest days, while the elderly living alone are less affected by rest days, with more regular living habits and lower power consumption levels.

[0119] Based on this, the day-night power consumption fluctuation, the first ratio of the average power consumption on weekdays to the average power consumption on rest days within the first preset duration, the second ratio of the average power consumption on holidays to the average power consumption on non-holiday days within the second preset duration, and the average daily power consumption are used as power consumption characteristics to distinguish between the elderly living alone and the elderly not living alone.

[0120] Again, input the power consumption characteristics of the user to be identified into the preset elderly living alone recognition model to obtain the category label of the user to be identified output by the elderly living alone recognition model; among them, the category label is the elderly living alone or the elderly not living alone; the elderly living alone recognition model is trained based on the power consumption characteristics calculated from the historical power consumption data of different categories and the corresponding category labels.

[0121] In this embodiment, the elderly living alone recognition model can be trained using a support vector machine.

[0122] Finally, if the category label of the user to be identified is the elderly living alone, then the user to be identified is used as the target elderly living alone.

[0123] In some embodiments, after obtaining the second historical power consumption data of the user to be identified, it further includes filling in missing values for the second historical power consumption data and performing normalization processing.

[0124] Here, the formula for normalization processing can be: In the formula, f(x) represents the normalized power consumption data, x represents the original power consumption data, x min represents the minimum value in the original power consumption data, and x max represents the maximum value in the original power consumption data.

[0125] In the embodiments of the present invention, through the first historical power consumption data of the target solitary elderly, the power consumption behavior type of the target solitary elderly can be determined, and the power consumption characteristics of the target solitary elderly can be clarified, so as to analyze the power consumption situation of the target solitary elderly; then, through the current power consumption data of the target solitary elderly and the power consumption threshold corresponding to its power consumption behavior type, it can be judged whether there is a risk of abnormal power consumption for the solitary elderly at present, and a preliminary judgment on the behavior of the solitary elderly can be made; if there is a risk of abnormal power consumption for the solitary elderly at present, it may indicate that there is an abnormality in the health of the solitary elderly, or it may be caused by the normal power consumption operation of the solitary elderly. Therefore, the power consumption data of the target solitary elderly at the next moment is predicted to obtain the target power consumption data, and then the abnormal monitoring result of the target solitary elderly is further judged through the target power consumption data, and it can be accurately obtained whether the power consumption of the solitary elderly is abnormal, so as to judge the health condition of the solitary elderly, and the solitary elderly can be rescued in time without setting additional intelligent devices or monitoring video devices, etc., and the abnormal monitoring of the solitary elderly can be realized quickly and efficiently, and the cost of abnormal monitoring can be reduced. Among them, through the second historical power consumption data of the user to be identified and using the solitary elderly identification model, the solitary elderly residents can be quickly identified with high identification accuracy, and the labor cost can be reduced.

[0126] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not mean the order of execution. The execution order of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0127] The following is the device embodiment of the present invention. For the details not described in detail, reference can be made to the corresponding method embodiments above.

[0128] Figure 4 The structural schematic diagram of the solitary elderly abnormal monitoring device based on power consumption data provided by the embodiments of the present invention is shown. For the sake of convenience of description, only the parts related to the embodiments of the present invention are shown and are described in detail as follows:

[0129] As Figure 4 shown, the solitary elderly abnormal monitoring device 40 based on power consumption data includes:

[0130] An acquisition module 41, configured to acquire first historical power consumption data and current power consumption data of a target elderly person living alone;

[0131] A classification module 42, configured to determine the type of power consumption behavior of the target elderly person living alone according to the first historical power consumption data;

[0132] A first determination module 43, configured to determine whether there is a risk of abnormal power consumption for the target elderly person living alone currently according to the power consumption threshold corresponding to the type of power consumption behavior of the target elderly person living alone and the current power consumption data;

[0133] A second determination module 44, configured to, if there is a risk of abnormal power consumption for the target elderly person living alone currently, predict the power consumption data of the target elderly person at the next moment to obtain target power consumption data; and determine the abnormal monitoring result of the target elderly person living alone according to the target power consumption data and the corresponding power consumption threshold.

[0134] In a possible implementation manner, the power consumption threshold includes a lower limit threshold and an upper limit threshold;

[0135] The first determination module 43 is specifically configured to:

[0136] Determine whether the current power consumption data is between the upper limit threshold and the lower limit threshold;

[0137] If the current power consumption data is not between the upper limit threshold and the lower limit threshold, it is determined that there is a risk of abnormal power consumption for the target elderly person living alone currently;

[0138] If the current power consumption data is between the upper limit threshold and the lower limit threshold, it is determined that there is no risk of abnormal power consumption for the target elderly person living alone currently.

[0139] In a possible implementation manner, the second determination module 44 is specifically configured to:

[0140] Determine whether the target power consumption data is between the upper limit threshold and the lower limit threshold;

[0141] If the target power consumption data is not between the upper limit threshold and the lower limit threshold, it is determined that the abnormal monitoring result of the target elderly person living alone is that there is abnormal power consumption;

[0142] If the target power consumption data is between the upper limit threshold and the lower limit threshold, it is determined that the abnormal monitoring result of the target elderly person living alone is that there is no abnormal power consumption.

[0143] In a possible implementation manner, the power consumption threshold includes a lower limit threshold and an upper limit threshold;

[0144] The first determination module 43 is specifically configured to:

[0145] Determine whether the difference between the current electricity consumption data and the lower threshold is greater than the first preset threshold, and whether the difference between the current electricity consumption data and the upper threshold is greater than the second preset threshold;

[0146] If the difference between the current electricity consumption data and the lower threshold is not greater than the first preset threshold, or the difference between the current electricity consumption data and the upper threshold is not greater than the second preset threshold, it is determined that there is a current risk of abnormal electricity consumption for the target elderly living alone;

[0147] If the difference between the current electricity consumption data and the lower threshold is greater than the first preset threshold, and the difference between the current electricity consumption data and the upper threshold is greater than the second preset threshold, then determine whether the current electricity consumption data is less than the lower threshold, and whether the current electricity consumption data is greater than the upper threshold; if the current electricity consumption data is not less than the lower threshold and the current electricity consumption data is not greater than the upper threshold, it is determined that there is no current risk of abnormal electricity consumption for the target elderly living alone.

[0148] In a possible implementation manner, the second determination module 44 is specifically configured to:

[0149] Determine whether the target electricity consumption data is less than the difference between the lower threshold and the first preset threshold, and whether the target electricity consumption data is greater than the sum of the upper threshold and the second preset threshold;

[0150] If the target electricity consumption data is less than the difference between the lower threshold and the first preset threshold, or the target electricity consumption data is greater than the sum of the upper threshold and the second preset threshold, it is determined that the abnormal monitoring result of the target elderly living alone is abnormal electricity consumption;

[0151] If the target electricity consumption data is not less than the difference between the lower threshold and the first preset threshold, and the target electricity consumption data is not greater than the sum of the upper threshold and the second preset threshold, it is determined that the abnormal monitoring result of the target elderly living alone is no abnormal electricity consumption.

[0152] In a possible implementation manner, the first determination module 43 is further configured to:

[0153] If the current electricity consumption data is less than the lower threshold, or the current electricity consumption data is greater than the upper threshold, it is determined that there is current abnormal electricity consumption for the target elderly living alone.

[0154] In a possible implementation manner, the abnormal monitoring device 40 for the elderly living alone based on electricity consumption data further includes an identification module, and the identification module is used to:

[0155] Obtain the second historical electricity consumption data of the user to be identified;

[0156] Calculate the electricity consumption characteristics of the user to be identified according to the second historical electricity consumption data; wherein, the electricity consumption characteristics include the day-night electricity consumption fluctuation, the first ratio of the average electricity consumption on weekdays to the average electricity consumption on rest days within the first preset duration, the second ratio of the average electricity consumption on holidays to the average electricity consumption on non-holiday days within the second preset duration, and the average daily electricity consumption.

[0157] Input the electricity consumption characteristics of the user to be identified into a preset recognition model for elderly living alone to obtain the category label of the user to be identified output by the recognition model for elderly living alone; wherein, the category label is elderly living alone or non-elderly living alone; the recognition model for elderly living alone is trained based on the electricity consumption characteristics calculated from the historical electricity consumption data of different categories and the corresponding category labels.

[0158] If the category label of the user to be identified is elderly living alone, then regard the user to be identified as the target elderly living alone.

[0159] In a possible implementation manner, the classification module 42 is specifically configured to:

[0160] Cluster the sample electricity consumption data of the elderly living alone with different electricity consumption behavior types to obtain the characteristic clustering centers of each electricity consumption behavior type.

[0161] Determine the similarity between the first historical electricity consumption data and each electricity consumption behavior type respectively according to the first historical electricity consumption data and the characteristic clustering centers.

[0162] Determine the electricity consumption behavior type corresponding to the maximum similarity as the electricity consumption behavior type of the target elderly living alone.

[0163] In a possible implementation manner, the classification module 42 is specifically configured to:

[0164] Obtain the sample electricity consumption data of multiple elderly living alone.

[0165] Set the relevant parameters for clustering the sample electricity consumption data, and the relevant parameters include the clustering centers, the number of iterations, and the maximum number of iterations.

[0166] Calculate the similarity between the sample electricity consumption data of each elderly living alone and each clustering center respectively, and cluster each elderly living alone to the nearest clustering center; calculate the average value of the sample electricity consumption data of all elderly living alone in each clustering center respectively, and use the average value as the new clustering center; complete one iteration calculation of the clustering center.

[0167] Keep iterating until the maximum number of iterations is reached, and use each clustering center corresponding to the maximum number of iterations as the characteristic clustering centers of different electricity consumption behavior types.

[0168] In the above embodiments, the descriptions of the various embodiments have their respective emphases. For parts not detailed or recorded in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

[0169] Those of ordinary skill in the art can realize that the templates, units, and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. A professional technician can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0170] If a module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, to implement all or part of the processes in the above-described embodiment methods of the present invention, it can also be completed by a computer program instructing the relevant hardware. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-described method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory, random access memory, electrical carrier signal, telecommunication signal, and software distribution medium, etc.

[0171] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for monitoring abnormalities of elderly people living alone based on electricity consumption data, characterized in that: include: Obtain the first historical electricity consumption data and current electricity consumption data of the target elderly person living alone; Determining the electricity usage behavior type of the target elderly person living alone according to the first historical electricity usage data; Determine whether the target elderly person living alone currently has a risk of abnormal electricity usage based on the electricity usage threshold corresponding to the electricity usage behavior type of the target elderly person living alone and the current electricity usage data; If the target elderly person living alone currently has a risk of abnormal electricity usage, the electricity usage data of the target elderly person living alone at the next moment is predicted to obtain the target electricity usage data; and based on the target electricity usage data and the corresponding electricity usage threshold, the abnormal monitoring result of the target elderly person living alone is determined.

2. The abnormal monitoring method for elderly people living alone based on electricity consumption data according to claim 1 is characterized in that: The power consumption threshold includes a lower threshold and an upper threshold; The determining, based on the power usage threshold corresponding to the power usage behavior type of the target elderly person living alone and the current power usage data, whether the target elderly person living alone currently has a risk of abnormal power usage includes: Determining whether the current power consumption data is between the upper threshold and the lower threshold; If the current electricity consumption data is not between the upper threshold and the lower threshold, it is determined that the target elderly person living alone currently has a risk of abnormal electricity consumption; If the current electricity usage data is between the upper threshold and the lower threshold, it is determined that the target elderly person living alone currently does not have a risk of abnormal electricity usage.

3. The abnormal monitoring method for elderly people living alone based on electricity consumption data according to claim 2 is characterized in that: The determining, according to the target power consumption data and the corresponding power consumption threshold, the abnormal monitoring result of the target elderly person living alone includes: Determining whether the target power consumption data is between the upper threshold and the lower threshold; If the target power consumption data is not between the upper threshold and the lower threshold, determining that the abnormal monitoring result of the target elderly person living alone has abnormal power consumption; If the target power consumption data is between the upper threshold and the lower threshold, it is determined that the abnormal monitoring result of the target elderly person living alone does not contain abnormal power consumption.

4. The abnormal monitoring method for elderly people living alone based on electricity consumption data according to claim 1 is characterized in that: The power consumption threshold includes a lower threshold and an upper threshold; The determining, based on the power usage threshold corresponding to the power usage behavior type of the target elderly person living alone and the current power usage data, whether the target elderly person living alone currently has a risk of abnormal power usage includes: Determine whether the difference between the current power consumption data and the lower threshold is greater than a first preset threshold, and whether the difference between the current power consumption data and the upper threshold is greater than a second preset threshold; If the difference between the current power consumption data and the lower threshold is not greater than the first preset threshold, or the difference between the current power consumption data and the upper threshold is not greater than the second preset threshold, it is determined that the target elderly person living alone currently has a risk of abnormal power consumption; If the difference between the current electricity consumption data and the lower limit threshold is greater than a first preset threshold, and the difference between the current electricity consumption data and the upper limit threshold is greater than a second preset threshold, then determine whether the current electricity consumption data is less than the lower limit threshold, and whether the current electricity consumption data is greater than the upper limit threshold; if the current electricity consumption data is not less than the lower limit threshold, and the current electricity consumption data is not greater than the upper limit threshold, then determine that the target elderly person living alone currently does not have any risk of abnormal electricity consumption.

5. The abnormal monitoring method for elderly people living alone based on electricity consumption data according to claim 4 is characterized in that: The determining, according to the target power consumption data and the corresponding power consumption threshold, the abnormal monitoring result of the target elderly person living alone includes: Determine whether the target power consumption data is less than the difference between the lower threshold and the first preset threshold, and whether the target power consumption data is greater than the sum of the upper threshold and the second preset threshold; If the target power consumption data is less than the difference between the lower threshold and the first preset threshold, or the target power consumption data is greater than the sum of the upper threshold and the second preset threshold, it is determined that the abnormal monitoring result of the target elderly person living alone has abnormal power consumption; If the target electricity consumption data is not less than the difference between the lower limit threshold and the first preset threshold, and the target electricity consumption data is not greater than the sum of the upper limit threshold and the second preset threshold, it is determined that the abnormal monitoring result of the target elderly person living alone does not contain abnormal electricity consumption.

6. The abnormal monitoring method for elderly people living alone based on electricity consumption data according to claim 4 is characterized in that: After determining whether the current power usage data is less than the lower threshold and whether the current power usage data is greater than the upper threshold, the method further includes: If the current electricity usage data is less than the lower threshold value, or the current electricity usage data is greater than the upper threshold value, it is determined that the target elderly person living alone currently has abnormal electricity usage.

7. The abnormal monitoring method for elderly people living alone based on electricity consumption data according to any one of claims 1 to 6, characterized in that: Before obtaining the first historical electricity usage data and current electricity usage data of the target elderly person living alone, the method further includes: Acquire second historical electricity consumption data of the user to be identified; Calculate the power consumption characteristics of the user to be identified based on the second historical power consumption data; wherein the power consumption characteristics include fluctuations in power consumption during the day and night, a first ratio of average power consumption on working days to average power consumption on holidays within a first preset time period, a second ratio of average power consumption on holidays to average power consumption on non-holidays within a second preset time period, and average daily power consumption; Input the power consumption characteristics of the user to be identified into a preset single-elderly identification model, and obtain the category label of the user to be identified output by the single-elderly identification model; wherein the category label is single-elderly or non-single-elderly; the single-elderly identification model is trained based on power consumption characteristics calculated from historical power consumption data of different categories and category labels corresponding to the power consumption characteristics; If the category label of the user to be identified is an elderly person living alone, the user to be identified is taken as a target elderly person living alone.

8. The abnormal monitoring method for elderly people living alone based on electricity consumption data according to any one of claims 1 to 6, characterized in that: The step of determining the electricity usage behavior type of the target elderly person living alone according to the first historical electricity usage data includes: Cluster the sample electricity consumption data of elderly people living alone with different electricity consumption behavior types to obtain the characteristic cluster center of each electricity consumption behavior type; Determining, according to the first historical electricity usage data and the characteristic cluster center, the similarity between the first historical electricity usage data and each type of electricity usage behavior; The electricity usage behavior type corresponding to the greatest similarity is determined as the electricity usage behavior type of the target elderly person living alone.

9. The abnormal monitoring method for elderly people living alone based on electricity consumption data according to claim 8 is characterized in that: The sample electricity consumption data of elderly people living alone with different electricity consumption behavior types are clustered to obtain the characteristic cluster center of each electricity consumption behavior type, including: Obtain sample electricity consumption data of multiple elderly people living alone; Setting relevant parameters for clustering the sample electricity consumption data, wherein the relevant parameters include a cluster center, a number of iterations, and a maximum number of iterations; Calculate the similarity between the sample electricity consumption data of each elderly person living alone and each cluster center, and cluster each elderly person living alone to the nearest cluster center; calculate the average value of the sample electricity consumption data of all elderly people living alone in each cluster center, and use the average value as the new cluster center; complete an iterative calculation of the cluster center; Iterate continuously until the maximum number of iterations is reached, and each cluster center corresponding to the maximum number of iterations is used as a feature cluster center of different types of electricity consumption behaviors.

10. A device for monitoring abnormalities of elderly people living alone based on electricity consumption data, characterized in that: include: An acquisition module is used to acquire the first historical electricity consumption data and the current electricity consumption data of the target elderly person living alone; a classification module, configured to determine the type of electricity usage behavior of the target elderly person living alone according to the first historical electricity usage data; A first determination module is used to determine whether the target elderly person living alone currently has a risk of abnormal electricity usage according to the electricity usage threshold corresponding to the electricity usage behavior type of the target elderly person living alone and the current electricity usage data; The second determination module is used to predict the electricity consumption data of the target elderly person living alone at the next moment to obtain the target electricity consumption data if the target elderly person living alone currently has a risk of abnormal electricity consumption; and determine the abnormal monitoring result of the target elderly person living alone based on the target electricity consumption data and the corresponding electricity consumption threshold.

Images