A data processing system for determining abnormal power consumption state of a target area

Abstract

This invention relates to a data processing system for determining abnormal power consumption status in a target area, comprising: a processor and a memory storing a computer program. When the computer program is executed by the processor, the following steps are implemented: obtaining a list of candidate device IDs, obtaining a list of target feature values, obtaining a list of candidate feature vectors, obtaining a list of key feature values, obtaining a list of candidate priorities, training a target function to obtain a target prediction model, inputting the target feature vector corresponding to the target area into the target prediction model to obtain the target priority, and determining the abnormal power consumption status based on the target priority. This embodiment combines the power consumption characteristics of the area with the behavioral characteristics of the corresponding devices to obtain the target prediction model, and performs feature filtering on the behavioral characteristic data corresponding to the devices based on historical data, reducing the dimensionality of data features and the variability of data, thus making the determination of abnormal power consumption status in the target area more accurate.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a data processing system for determining abnormal power consumption status in a target area. Background Technology

[0002] Electricity plays a vital role in socio-economic development, and various studies and surveys directly link electricity consumption to national economic, technological, and social progress. On the one hand, electricity demand is growing exponentially, and available resources are being consumed at an alarming rate; on the other hand, electricity is still in short supply, making energy conservation a basic requirement. Therefore, it is essential to strengthen electricity management and optimize electricity use to reduce production costs and environmental hazards. Electricity consumption forecasting and analysis are crucial means to achieve this goal.

[0003] In the existing technology, the method for determining the abnormal power consumption status of a target area is as follows: real-time capture of the power consumption characteristic data (such as current change and cable temperature change) corresponding to the target area, and inputting these data into the power consumption anomaly identification model for identification processing to determine the abnormal power consumption status corresponding to the target area.

[0004] In summary, the methods for determining abnormal power consumption in target areas have the following problems: they are limited to power consumption characteristics, fail to combine power consumption characteristics with the corresponding behavioral characteristics of equipment, and do not perform feature filtering on the data, resulting in large data feature dimensions and large data differences, which leads to low accuracy in determining abnormal power consumption in target areas. Summary of the Invention

[0005] To address the aforementioned technical problems, the technical solution adopted by this invention is as follows: S100, obtaining a list set A = {A1, ..., A...} of candidate device IDs corresponding to the sample region list. i , ..., A n},A i ={A i1 , ..., A ij , ..., A im(i)}, A ij Let j be the j-th candidate device ID in the candidate device ID list corresponding to the i-th sample region, j = 1...m(i), m(i) is the number of candidate device IDs in the candidate device ID list corresponding to the i-th sample region, i = 1...n, n is the number of sample regions.

[0006] S200, Obtain the target feature value list set G = {G1, ..., G2} corresponding to the sample region list. i , ..., G n},G i ={G i1 , ..., G ij , ..., G im(i)}, G ij={G 1 ij , ..., G e ij , ..., G f ij}, G e ij For A ij The corresponding target feature value in the target feature value list, e = 1...f, where f is the number of target feature values ​​in the target feature value list.

[0007] S300, Based on G, obtain the candidate feature vector list J = {J1, ..., J2} corresponding to the sample region list. i , ..., J n}, J i Let J be the candidate feature vector corresponding to the i-th sample region, where J i =(J i1 , ..., J ie , ..., J if ), J ie Meets the following conditions:

[0008] J ie =∑ m(i) j＝1 G e ij .

[0009] S400, Obtain the list of key feature values ​​H = {H1, ..., H2} corresponding to the sample region list. i H n}, H i Let be the key feature value corresponding to the i-th sample region, where the key feature value is the amount of electricity consumed by the sample region within a specified time period.

[0010] S500, Based on H, obtain the candidate priority list P = {P1, ..., P2} corresponding to the sample region list. i ..., P n}, P i Let P be the priority of the candidate features corresponding to the i-th sample region. i Meets the following conditions:

[0011] P i =1-(H i / T 0 ) / max{H i / T 0 ,β i}+1,T 0 β represents the time span corresponding to the specified time period. i This represents the average electricity consumption during the normal working time period of the i-th sample area.

[0012] S600 inputs J and P into the objective function for training, obtains the parameters corresponding to the objective function, and obtains the target prediction model.

[0013] S700: Input the target feature vector corresponding to the target region into the target prediction model to obtain the target priority η corresponding to the target region.

[0014] S800, when η < η 0 When it is determined that the target area is in an abnormal power consumption state during a specified time period, η 0 This is the preset priority threshold.

[0015] Compared with the prior art, the present invention has significant advantages. Through the above technical solution, the data processing system for determining abnormal power consumption status in a target area provided by the present invention achieves considerable technological advancement and practicality, and has broad industrial application value. It has at least the following advantages:

[0016] A data processing system for determining abnormal power consumption status in a target area includes a processor and a memory storing a computer program. When the computer program is executed by the processor, it performs the following steps: obtaining a list of candidate device IDs corresponding to a sample area list; obtaining a list of target feature values ​​corresponding to the sample area list; obtaining a list of candidate feature vectors corresponding to the sample area list based on the list of target feature values; obtaining a list of key feature values ​​corresponding to the sample area list; obtaining a list of candidate priorities corresponding to the sample area list based on the list of key feature values; inputting the list of candidate feature vectors and the list of candidate priorities into a target function for training; obtaining the parameters corresponding to the target function to obtain a target prediction model; inputting the target feature vectors corresponding to the target area into the target prediction model; obtaining the target priority corresponding to the target area; determining that the target area is in an abnormal power consumption state within a specified time period when the target priority is less than a preset priority threshold; not limited to the power consumption characteristics of the area, but also considering the behavioral characteristics of the devices in the area; combining the power consumption characteristics of the area and the behavioral characteristics of the devices to obtain a target prediction model; and performing feature filtering on the behavioral characteristic data of the devices based on historical data, thereby reducing the dimensionality and variability of the data features and making the determination of abnormal power consumption status in the target area more accurate.

[0017] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0018] Figure 1 This is a flowchart of the execution computer program for a data processing system that determines abnormal power consumption status in a target area, as provided in an embodiment of the present invention. Detailed Implementation

[0019] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or server that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0021] Example

[0022] This embodiment provides a data processing system for determining abnormal power consumption in a target area. The system includes a processor and a memory storing a computer program. When the computer program is executed by the processor, it performs the following steps, such as... Figure 1 As shown:

[0023] S100, Obtain the candidate device ID list set A = {A1, ..., A2} corresponding to the sample area list. i , ..., A n},A i ={A i1 , ..., A ij , ..., A im(i)}, A ij Let j be the j-th candidate device ID in the candidate device ID list corresponding to the i-th sample region, j = 1...m(i), m(i) is the number of candidate device IDs in the candidate device ID list corresponding to the i-th sample region, i = 1...n, n is the number of sample regions.

[0024] Specifically, the sample area list includes several sample areas, wherein each sample area is an area that gathers several target objects and provides office space for the target objects, such as: company office space, a department of a company, etc.

[0025] Furthermore, the target object is the user using the candidate device.

[0026] The candidate device ID is a unique identifier representing a candidate device, where the candidate device is a user connected to Wi-Fi in the sample area.

[0027] S200, Obtain the target feature value list set G = {G1, ..., G2} corresponding to the sample region list. i , ..., G n},G i ={G i1 , ..., G ij , ..., G im(i)}, G ij ={G 1 ij , ..., G e ij , ..., G f ij}, G e ij For A ij The corresponding target feature value in the target feature value list, e = 1...f, where f is the number of target feature values ​​in the target feature value list.

[0028] Specifically, the target feature value is the numerical value of the candidate device under the target feature within a preset time period.

[0029] Specifically, in S200, target features are obtained through the following steps:

[0030] S201, Obtain the candidate feature list D = {D1, ..., D2} r , ..., D s}, D r Let be the r-th candidate feature, where r = 1...s, and s is the number of candidate features.

[0031] Specifically, the candidate features are the behavioral features of the target objects corresponding to the candidate devices within the sample area, such as the number of times the APP is opened, the duration of APP use, and the duration of work.

[0032] S202, Obtain the first candidate feature value list set F = {F1, ..., F2} corresponding to D. r , ..., F s}, F r ={F r1, ..., F ri , ..., F rn}, F ri D r The corresponding first candidate feature value in the first candidate feature value list, where F ri Meets the following conditions:

[0033] F ri =(1 / m(i))×∑ m(i) j＝1 C r ij / m(i), C r ij For A ij The corresponding candidate device's value under the corresponding candidate feature within a preset time period.

[0034] Specifically, the end time of the preset time period is earlier than the current time. As those skilled in the art know, the span of the preset time period can be selected according to actual needs, and all of these fall within the protection scope of this invention, which will not be elaborated here.

[0035] S203, Obtain the second candidate feature value list E = {E1, ..., E2} corresponding to the sample region list. i , ..., E n}, E i Let be the second candidate feature value corresponding to the i-th sample region, where the second candidate feature value is the amount of electricity consumed by the sample region within a preset time period.

[0036] S204, Based on F and E, obtain the specified priority list Q = {Q1, ..., Q...} corresponding to D. r Q s}, Q r D r The corresponding specified priority, where Q r Meets the following conditions:

[0037]

[0038] S205, based on Q, f target features are obtained, where, when |Q r |<Q 0 At that time, determine D r For the target feature, Q 0 For the preset priority threshold, |Q r |For Q r The absolute value of.

[0039] Specifically, Q 0The value range is 0.3 to 0.4. As those skilled in the art know, any selection made according to actual needs falls within the protection scope of this invention, and will not be elaborated further here.

[0040] The above-mentioned method involves obtaining a list of candidate features corresponding to a specified priority list, filtering candidate features based on the specified priority, obtaining target features, and filtering the behavioral feature data of the device based on historical data. This reduces the dimensionality of data features and the variability of data, resulting in higher accuracy in determining abnormal power consumption status in the target area.

[0041] S300, Based on G, obtain the candidate feature vector list J = {J1, ..., J2} corresponding to the sample region list. i , ..., J n}, J i Let J be the candidate feature vector corresponding to the i-th sample region, where J i =(J i1 , ..., J ie , ..., J if ), J ie Meets the following conditions:

[0042] J ie =∑ m(i) j＝1 G e ij .

[0043] S400, Obtain the list of key feature values ​​H = {H1, ..., H2} corresponding to the sample region list. i H n}, H i Let be the key feature value corresponding to the i-th sample region, where the key feature value is the amount of electricity consumed by the sample region within a specified time period.

[0044] Specifically, the start time of the specified time period is later than the end time of the preset time period. As those skilled in the art know, the time span corresponding to the specified time period can be selected according to actual needs, and all of these fall within the protection scope of this invention, which will not be elaborated here.

[0045] S500, Based on H, obtain the candidate priority list P = {P1, ..., P2} corresponding to the sample region list. i ..., P n}, P i Let P be the priority of the candidate features corresponding to the i-th sample region. i Meets the following conditions:

[0046] P i =1-(H i / T0 ) / max{H i / T 0 ,β i}+1,T 0 β represents the time span corresponding to the specified time period. i This represents the average electricity consumption during the normal working time period of the i-th sample area.

[0047] S600 inputs J and P into the objective function for training, obtains the parameters corresponding to the objective function, and obtains the target prediction model.

[0048] Preferably, the objective function is the Sigmoid function.

[0049] S700: Input the target feature vector corresponding to the target region into the target prediction model to obtain the target priority η corresponding to the target region.

[0050] Specifically, the target area is the area where it is to be confirmed whether it is in an abnormal power consumption state.

[0051] Furthermore, the properties of the target region are consistent with the properties of the sample region.

[0052] Specifically, the target feature vector is a feature vector obtained based on several undetermined feature values ​​corresponding to several devices in the target area, wherein the undetermined feature values ​​are the values ​​of the target features corresponding to the devices in the target area within an undetermined time period.

[0053] Furthermore, the method for obtaining the target feature vector is consistent with the method for obtaining the candidate feature vector.

[0054] Furthermore, the end time of the pending time period is earlier than the current time. As those skilled in the art know, the time span corresponding to the pending time period can be selected according to actual needs, all of which fall within the protection scope of this invention, and will not be elaborated further here.

[0055] Specifically, the target priority η is the value obtained by inputting the target feature vector corresponding to the target region into the target prediction model.

[0056] S800, when η < η 0 When it is determined that the target area is in an abnormal power consumption state during a specified time period, η 0 This is the preset priority threshold.

[0057] Specifically, the smaller η is, the more abnormal the power consumption of the target area is within the specified time period. As those skilled in the art know, the selection can be made according to actual needs and all of these fall within the protection scope of this invention, and will not be elaborated further here.

[0058] In summary, the process involves obtaining a list of candidate feature vectors and a list of key feature values ​​corresponding to the sample region list, then using these lists to obtain a target prediction model. This model is then used to determine the abnormal power consumption status of the target region. Furthermore, it is not limited to the power consumption characteristics of the region but also considers the behavioral characteristics of the devices within the region. Combining the power consumption characteristics of the region with the behavioral characteristics of the devices yields a highly accurate target prediction model.

[0059] This embodiment provides a data processing system for determining abnormal power consumption status in a target area. The system includes a processor and a memory storing a computer program. When the computer program is executed by the processor, the following steps are implemented: obtaining a list of candidate device IDs corresponding to a sample area list; obtaining a list of target feature values ​​corresponding to the sample area list; obtaining a list of candidate feature vectors corresponding to the sample area list based on the list of target feature values; obtaining a list of key feature values ​​corresponding to the sample area list; obtaining a list of candidate priorities corresponding to the sample area list based on the list of key feature values; inputting the list of candidate feature vectors and the list of candidate priorities into a target function for training; obtaining the parameters corresponding to the target function to obtain a target prediction model; inputting the target feature vectors corresponding to the target area into the target prediction model; obtaining the target priority corresponding to the target area; when the target priority is less than a preset priority threshold, it is determined that the target area is in an abnormal power consumption state within a certain time period. This embodiment is not limited to the power consumption characteristics of the area, but also considers the behavioral characteristics of the devices in the area. The power consumption characteristics of the area and the behavioral characteristics of the devices are combined to obtain a target prediction model. Based on historical data, the behavioral characteristic data of the devices are filtered to reduce the dimensionality and variability of the data features, resulting in higher accuracy in determining the abnormal power consumption status of the target area.

[0060] While specific embodiments of the invention have been described in detail by way of example, those skilled in the art should understand that the above examples are for illustrative purposes only and are not intended to limit the scope of the invention. Those skilled in the art should also understand that various modifications can be made to the embodiments without departing from the scope and spirit of the invention. The scope of the invention is defined by the appended claims.

Claims

1. A data processing system for determining abnormal power consumption status in a target area, characterized in that, The system includes a processor and a memory storing a computer program, which, when executed by the processor, performs the following steps: S100, Obtain the candidate device ID list set A = {A1, ..., A2} corresponding to the sample area list. i , ..., A n },A i ={A i1 , ..., A ij , ..., A im(i) }, A ij Let j be the j-th candidate device ID in the candidate device ID list corresponding to the i-th sample region, j = 1...m(i), m(i) is the number of candidate device IDs in the candidate device ID list corresponding to the i-th sample region, i = 1...n, n is the number of sample regions; S200, Obtain the target feature value list set G = {G1, ..., G2} corresponding to the sample region list. i , ..., G n },G i ={G i1 , ..., G ij , ..., G im(i) }, G ij ={G 1 ij , ..., G e ij , ..., G f ij }, G e ij For A ij The e-th target feature value in the corresponding list of target feature values, where e = 1...f, and f is the number of target feature values ​​in the list of target feature values; S300, Based on G, obtain the candidate feature vector list J = {J1, ..., J2} corresponding to the sample region list. i , ..., J n }, J i Let J be the candidate feature vector corresponding to the i-th sample region, where J i =(J i1 , ..., J ie , ..., J if ), J ie The following conditions must be met: J ie =∑ m(i) j＝1 G e ij ; S400, Obtain the list of key feature values ​​H = {H1, ..., H2} corresponding to the sample region list. i H n }, H i Let be the key feature value corresponding to the i-th sample region, where the key feature value is the amount of electricity consumed by the sample region within a specified time period; S500, Based on H, obtain the candidate priority list P = {P1, ..., P2} corresponding to the sample region list. i ..., P n }, P i Let P be the priority of the candidate features corresponding to the i-th sample region. i The following conditions must be met: P i =1-(H) i / T 0 ) / max{H i / T 0 ,β i }+1,T 0 β represents the time span corresponding to a specified time period. i This represents the average electricity consumption during the normal working time period of the i-th sample area. S600, input J and P into the objective function for training, obtain the parameters corresponding to the objective function to obtain the target prediction model; S700, input the target feature vector corresponding to the target region into the target prediction model to obtain the target priority η corresponding to the target region; S800, when η < η 0 When it is determined that the target area is in an abnormal power consumption state during a specified time period, η 0 This is the preset priority threshold.

2. The data processing system for determining abnormal power consumption status in a target area according to claim 1, characterized in that, The sample area list includes several sample areas, wherein each sample area is an area that gathers several target objects and provides office space for the target objects.

3. The data processing system for determining abnormal power consumption status in a target area according to claim 1, characterized in that, The target feature value is the numerical value of the candidate device under the target feature within a preset time period.

4. The data processing system for determining abnormal power consumption status in a target area according to claim 3, characterized in that, In S200, target features are obtained through the following steps: S201, Obtain the candidate feature list D = {D1, ..., D2} r , ..., D s }, D r Let be the r-th candidate feature, where r = 1...s, and s is the number of candidate features; S202, Obtain the first candidate feature value list set F = {F1, ..., F2} corresponding to D. r , ..., F s }, F r ={F r1 , ..., F ri , ..., F rn }, F ri D r The corresponding first candidate feature value in the first candidate feature value list, where F ri The following conditions must be met: F ri =(1 / m(i))×∑ m(i) j＝1 C r ij / m(i), C r ij For A ij The value of the corresponding candidate device under the corresponding candidate feature within a preset time period; S203, Obtain the second candidate feature value list E = {E1, ..., E2} corresponding to the sample region list. i , ..., E n }, E i Let be the second candidate feature value corresponding to the i-th sample region, where the second candidate feature value is the electricity consumed by the sample region within a preset time period; S204, Based on F and E, obtain the specified priority list Q = {Q1, ..., Q...} corresponding to D. r Q s }, Q r D r The corresponding specified priority, where Q r The following conditions must be met: S205, based on Q, f target features are obtained, where, when |Q r |<Q 0 At that time, determine D r For the target feature, Q 0 For the preset priority threshold, |Q r |For Q r The absolute value of.

5. The data processing system for determining abnormal power consumption status in a target area according to claim 4, characterized in that, The candidate features are the behavioral features of the target objects corresponding to the candidate devices within the sample area.

6. The data processing system for determining abnormal power consumption status in a target area according to claim 4, characterized in that, Q 0 The value range is 0.3 to 0.

4.

7. The data processing system for determining abnormal power consumption status in a target area according to claim 1, characterized in that, The target feature vector is a feature vector obtained based on several undetermined feature values ​​corresponding to several devices in the target area, wherein the undetermined feature values ​​are the values ​​of the target features corresponding to the devices in the target area within an undetermined time period.

8. The data processing system for determining abnormal power consumption status in a target area according to claim 1, characterized in that, The target priority η is the value obtained by inputting the target feature vector corresponding to the target region into the target prediction model.

Images