A smart electricity alarm identification method, device and equipment

Abstract

The present application provides a method, device and equipment for intelligent electricity alarm identification, which belongs to the field of data processing technology. The method determines the operation monitoring information of the power-consuming device end based on a preset threshold update cycle; matches the operation monitoring information with a pre-stored data sequence list to generate a long-short cycle data set corresponding to the operation monitoring information according to the matching result. Based on the long-short cycle data set and the safety margin coefficient set corresponding to the power-consuming device end, determine the threshold update comparison values ​​corresponding to the operation monitoring information; determine whether to update the previous alarm threshold according to the threshold update rules and the threshold update comparison values ​​to obtain the current alarm threshold; based on the current alarm threshold, perform alarm identification on the real-time monitoring data of the next threshold update cycle to determine whether the real-time monitoring data meets the alarm triggering conditions, and generate corresponding alarm prompt information when the alarm triggering conditions are met, and send it to the user terminal.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method, device and equipment for identifying smart electricity alarms. Background Art

[0002] "Smart firefighting" uses the latest technologies such as the Internet of Things, artificial intelligence, virtual reality, mobile Internet+, and cooperates with professional applications such as big data cloud computing platforms and intelligent fire alarm analysis to realize the intelligence of urban firefighting.

[0003] At present, smart fire protection usually monitors the operating status data of the power supply line at the equipment end, and issues alarms for the data monitoring items by setting different alarm thresholds. Such alarm threshold data is fixed, which is very easy to cause false alarms or missed alarms.

[0004] For example, if the abnormal status data is higher than the normal operating state and lower than the alarm threshold for a long time, no alarm can be generated. If the electrical line is in this abnormal working state for a long time, the probability of electrical fire will increase, and the role of smart electricity use in monitoring circuit abnormal status and preventing electrical fire cannot be played. Frequent setting of alarm thresholds means that a lot of manpower is required, which makes it difficult to balance the relationship between user experience and resource investment, and may cause trouble to users in actual use. Summary of the invention

[0005] The embodiments of the present application provide a smart electricity alarm identification method, device and equipment, which are used to solve the technical problems that the current electricity alarm is not sensitive enough, there are false alarms and missed alarms, and it is difficult to identify alarms intelligently and efficiently to ensure user experience.

[0006] On the one hand, an embodiment of the present application provides a smart power usage alarm identification method, which is applied to a smart power usage alarm identification system connected to one or more power-consuming devices; the method includes:

[0007] Based on a preset threshold update cycle, determining the operation monitoring information of the electric device end; the operation monitoring information includes a monitoring data reference value within the threshold update cycle;

[0008] Matching the operation monitoring information with a pre-stored data sequence list to generate a long- and short-cycle data set corresponding to the operation monitoring information according to the matching result; the data sequence list at least includes a corresponding relationship between a time series and a monitoring data sequence; the long- and short-cycle data set includes a long-cycle data subset and a short-cycle data subset;

[0009] Determine, based on the long- and short-cycle data sets and the safety margin coefficient set corresponding to the power-consuming device end, each threshold update comparison value corresponding to the operation monitoring information;

[0010] Determine whether to update the previous alarm threshold according to the threshold update rule and the threshold update comparison value to obtain the current alarm threshold;

[0011] Based on the current alarm threshold, alarm identification is performed on the real-time monitoring data of the next threshold update cycle to determine whether the real-time monitoring data meets the alarm trigger condition, and when the alarm trigger condition is met, corresponding alarm prompt information is generated and sent to the user terminal.

[0012] In one implementation of the present application, the operation monitoring information is matched with a pre-stored data sequence list to generate a long- and short-period data set corresponding to the operation monitoring information according to the matching result, specifically including:

[0013] Matching the monitoring data sequence corresponding to the monitoring data dimension of the operation monitoring information from the pre-stored data sequence list; wherein the monitoring data dimension of the operation monitoring information includes at least one or more of the following: current, voltage, residual current, and line temperature;

[0014] According to the time series, the preset long cycle duration and the preset short cycle duration, the sequence elements in the monitoring data sequence are screened to obtain the sequence element tuples corresponding to the long cycle data subset and the short cycle data subset respectively, so as to generate the long and short cycle data sets according to the sequence element tuples; the preset long cycle duration is greater than the preset short cycle duration; the preset short cycle duration includes multiple threshold update cycles.

[0015] In one implementation of the present application, based on the long and short cycle data sets and the safety margin coefficient set corresponding to the power-consuming device end, determining each threshold update comparison value corresponding to the operation monitoring information specifically includes:

[0016] Determine, according to the device type and monitoring data dimension of the electrical device end, a first safety margin coefficient and a second safety margin coefficient corresponding to the long-period data subset and the short-period data subset in the safety margin coefficient set, respectively;

[0017] Calculate the product of the first monitoring data reference average value corresponding to the long-period data subset and the first safety margin coefficient as the long-period monitoring data reference value;

[0018] Calculate the product of the second monitoring data reference average value corresponding to the short-period data subset and the second safety margin coefficient as the short-period monitoring data reference value;

[0019] The long-period monitoring data reference value and the short-period monitoring data reference value are used as the threshold update comparison value.

[0020] In one implementation of the present application, according to the threshold update rule and each of the threshold update comparison values, determining whether to update the previous alarm threshold to obtain the current alarm threshold specifically includes:

[0021] Comparing the monitoring data reference value with the short-period monitoring data reference value to obtain a first comparison result;

[0022] According to whether the first comparison result and the preset trend of the corresponding monitoring data dimension meet the division condition, determining the power consumption trend compliance result; the preset trend compliance division condition is used to characterize the special degree of different power consumption trends of the corresponding monitoring data dimension; the power consumption trend compliance result includes trend compliance and trend deviation;

[0023] In the case where the power consumption trend conformity result is a trend deviation, the monitoring data reference value is compared with the long-period monitoring data reference value to determine a provisional alarm threshold according to the corresponding second comparison result; the provisional alarm threshold includes at least one of the following: the short-period monitoring data reference value and a third safety margin; the third safety margin is the product value of the monitoring data reference value and a third safety margin coefficient;

[0024] When the power consumption trend compliance result is trend compliance, using the monitoring data reference value as the provisional alarm threshold;

[0025] In the case that the provisional alarm threshold is not equal to the early alarm threshold, the early alarm threshold is updated to use the provisional alarm threshold as the current alarm threshold.

[0026] In one implementation of the present application, the method further includes:

[0027] Acquire the alarm threshold update record and generate an alarm threshold update curve; the abscissa of the alarm threshold update curve is time, and the ordinate is the alarm threshold;

[0028] Generate a first difference curve according to the difference between each ordinate value of the alarm threshold update curve and the corresponding representative value of the monitoring data within the threshold update period; the representative value of the monitoring data is the maximum value of the monitoring data or the minimum value of the monitoring data;

[0029] Generate a second difference curve according to the difference between each ordinate point value of the alarm threshold update curve and the corresponding previous alarm threshold;

[0030] Inputting the first difference curve and the second difference curve into a preset update effectiveness recognition model, determining corresponding update effective alarm coordinate points, and adding the horizontal coordinates of each of the update effective alarm coordinate points to the interval sequence to be updated;

[0031] Based on each adjacent time difference in the interval sequence to be updated and the threshold update period, a threshold update interval operation period is determined; the threshold update interval operation period is used to execute the update of the early warning threshold after a number of threshold update periods corresponding to the threshold update interval operation period.

[0032] In one implementation of the present application, determining the threshold update interval operation period based on each adjacent time difference in the interval sequence to be updated and the threshold update period specifically includes:

[0033] Calculate the division result of each of the adjacent time differences and the threshold update period to obtain a plurality of threshold effective update interval periods;

[0034] Arrange the effective update intervals of the threshold values ​​from large to small to form an interval sequence;

[0035] The median of the interval period sequence is used as the threshold update interval operation period.

[0036] In one implementation of the present application, determining whether the real-time monitoring data meets the alarm triggering condition specifically includes:

[0037] Comparing the real-time monitoring data of the next threshold update cycle with the current alarm threshold to match the third comparison result with the alarm threshold trigger sub-condition in the alarm trigger condition, and judging whether the real-time monitoring data meets the alarm trigger condition according to the first matching result;

[0038] If not, the real-time monitoring data is matched with the alarm triggering additional sub-condition in the alarm triggering condition to determine whether the real-time monitoring data satisfies the alarm triggering condition according to a second matching result.

[0039] In one implementation of the present application, the power-consuming equipment end includes at least one or more of the following: a charging station distribution box, a park distribution box, and a residential power distribution box.

[0040] On the other hand, the embodiment of the present application further provides a smart power usage alarm identification device, the device comprising:

[0041] A first determination module determines operation monitoring information of the electric device end based on a preset threshold update period; the operation monitoring information includes a monitoring data reference value within the threshold update period;

[0042] A matching module, used for matching the operation monitoring information with a pre-stored data sequence list, so as to generate a long-short cycle data set corresponding to the operation monitoring information according to the matching result; the data sequence list at least includes a corresponding relationship between a time series and a monitoring data sequence; the long-short cycle data set includes a long-cycle data subset and a short-cycle data subset;

[0043] A second determination module is used to determine each threshold update comparison value corresponding to the operation monitoring information based on the long and short cycle data set and the safety margin coefficient set corresponding to the power-consuming device end;

[0044] A third determination module is used to determine whether to update the previous alarm threshold according to the threshold update rule and each of the threshold update comparison values ​​to obtain the current alarm threshold;

[0045] The alarm identification module is used to perform alarm identification on the real-time monitoring data of the next threshold update cycle based on the current alarm threshold to determine whether the real-time monitoring data meets the alarm triggering conditions, and generate corresponding alarm prompt information when the alarm triggering conditions are met, and send it to the user terminal.

[0046] On the other hand, the embodiment of the present application further provides a smart power usage alarm identification device, the device comprising:

[0047] At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute a smart electricity alarm identification method as described above.

[0048] Compared with the prior art, the present invention has the following significant effects:

[0049] Through the above scheme, this application can combine short-cycle data and long-cycle data to flexibly determine whether the alarm threshold needs to be updated in each threshold update cycle, so as to obtain an alarm threshold that is more in line with the actual usage conditions. There is no need to invest excessive manpower costs, and the technical problem that the current alarm threshold data is fixed and prone to false alarms or missed alarms is solved. By flexibly updating the alarm threshold, the sensitivity of the power alarm is improved, and the user experience of smart power alarm identification in the smart fire protection process is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0051] Figure 1A flowchart of a smart electricity alarm identification method in an embodiment of the present application;

[0052] Figure 2 This is a structural diagram of a smart electricity usage alarm identification device in an embodiment of the present application.

[0053] Figure 3 This is a structural diagram of a smart electricity alarm identification device in an embodiment of the present application. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0055] The embodiments of the present application provide a smart electricity alarm identification method, device and equipment to solve the technical problems that the current electricity alarm is not sensitive enough, there are false alarms and missed alarms, and it is difficult to intelligently and efficiently identify alarms to ensure user experience.

[0056] The following describes in detail various embodiments of the present application in conjunction with the accompanying drawings.

[0057] The present application embodiment provides a smart power alarm identification method, which is applied to a smart power alarm identification system connected to one or more power-consuming devices. Figure 1 As shown, the method may include steps S101-S105:

[0058] S101, the server determines the operation monitoring information of the electric device based on a preset threshold update cycle.

[0059] The above-mentioned operation monitoring information includes a reference value of monitoring data within a threshold update cycle.

[0060] It should be noted that the server as the execution subject of the smart power alarm identification method is only for example, and the execution subject is not limited to the server, and this application does not make specific restrictions on this. The smart power alarm identification system can be set in the server.

[0061] In the embodiments of the present application, the power-consuming equipment end includes at least one or more of the following: a charging station distribution box, a park distribution box, and a residential power distribution box. The charging station distribution box can be a distribution box in an electric vehicle charging station, and the park distribution box can be understood as a distribution box in an industrial park or a smart park; the residential power distribution box can be a distribution box in a residential building or a community. In addition, the power-consuming equipment end can also be a distribution box in other scenarios. By adopting the smart power alarm identification method of the present application, the number of manual inspections of the distribution box can be reduced, and smart fire protection of the distribution box can be achieved.

[0062] The above-mentioned preset threshold update cycle can be understood as a set of time periods for collecting operation monitoring information pre-specified by the user, for example, 24 hours (i.e., from 00:00:00 to 23:59:59) is a threshold update cycle. One or more sensors for collecting monitoring data can be installed on the electrical equipment end, which are used to collect monitoring data of different monitoring data dimensions, such as current sensors, low voltage sensors, high voltage sensors, residual current sensors, line temperature sensors, etc. Different monitoring data dimensions correspond to different alarm thresholds.

[0063] Each electrical device can be bound to one or more of the above sensors. After receiving the monitoring data collected by the sensor from the electrical device, the server can calculate the reference value of the monitoring data, for example, selecting monitoring data within a preset interval of the monitoring data within the threshold update period, and calculating the average value of the monitoring data within the interval, and obtaining the reference value of the monitoring data based on the product value of the fourth safety margin coefficient of the corresponding monitoring data dimension. The preset interval range is set in advance according to the monitoring data dimension, and is set by the user according to the actual usage scenario, and this application does not make specific restrictions on this.

[0064] In one embodiment of the present application, when the monitoring data dimension is current, the monitoring data is real-time current, and the maximum current peak value is set to I PK , the alarm threshold of current monitoring is set to I CK The threshold update cycle is 24 hours (i.e. 00:00:00-23:59:59), and 80% of the maximum current peak value in the current threshold update cycle is set as the first current reference value I 80 , I 80 =I PK *80%, take 90% of the maximum current peak value in the current threshold update cycle as the second current reference value I 90 , I 90 =I PK *90%, take I 80 with I 90 The average value of all monitoring data within the preset interval is set to I Dx̄, calculate the third current reference value (i.e., monitoring data reference value) of the current threshold update cycle and set it as I DCK , I DCK =I Dx̄ *135%, where 135% is the fourth safety margin coefficient. Different fourth safety margin coefficients can be set by the user according to actual conditions for different scenarios and / or different monitoring data dimensions, and this application does not make specific restrictions on this. The server adds the monitoring data reference value of the current threshold update cycle to the operation monitoring information.

[0065] In another embodiment of the present application, when the monitoring data dimension is the high voltage in the voltage, the monitoring data is the real-time voltage, and the voltage maximum alarm limit threshold is set to U mg (i.e., the maximum value that can be set for the alarm threshold under the high voltage monitoring data dimension). The alarm threshold for high voltage monitoring is set to U mck , the threshold update cycle is 24 hours (i.e. 00:00:00-23:59:59). Take the highest voltage peak value in the current threshold update cycle (i.e. the maximum value of the monitoring data in the threshold update cycle) as the first high voltage reference value U m , set 97.5% of the highest voltage peak value in the current threshold update cycle as the second highest voltage reference value U m97.5 , U m97.5 =U m *97.5%, take U m with U m97.5 The average value of all monitoring data within the preset interval is set as U mx̄ , calculate the third highest voltage reference value (i.e. monitoring data reference value) of the current threshold update cycle and set it as U 1mck , U 1mck =U mx̄ *102.5%. 102.5% is the fourth safety margin factor.

[0066] In another embodiment of the present application, when the monitoring data dimension is the low voltage in the voltage, the monitoring data is the real-time voltage, and the voltage minimum alarm limit threshold is set to U sg (i.e., the minimum value that can be set for the alarm threshold under the low voltage monitoring data dimension), the low voltage monitoring alarm threshold is set to U sck , the threshold update cycle is 24 hours (00:00:00-23:59:59). Set the lowest voltage in the current threshold update cycle to the first low voltage reference value U s , set 102.5% of the lowest voltage value in the current threshold update cycle as the second low voltage reference value U s102.5 , U s102.5 =U s *102.5%, take U s with U s102.5The average value of all monitoring data within the preset interval is set as U sx̄ , calculate the third low voltage reference value (i.e. monitoring data reference value) of the current threshold update cycle and set it as U 1sck , U 1sck =U sx̄ *97.5%, 97.5% is the fourth safety margin factor.

[0067] In another embodiment of the present application, when the monitoring data dimension is residual current, the monitoring data is a real-time residual current value, and the residual current maximum alarm limit threshold is set to I eg (i.e. the maximum value that can be set for the alarm threshold under the residual current monitoring data dimension), the residual current monitoring alarm threshold is set to I eck , the threshold update cycle is 24 hours (00:00:00-23:59:59). Take the highest residual current peak value in the current threshold update cycle as the first residual current reference value I em , set 82% of the highest residual current peak value in the current threshold update cycle as the second residual current reference value I em82 , I em82 =I em *82%, take I em with I em82 The average value of all monitoring data within the preset interval is set to I emx̄ , calculate the third residual current reference value (i.e., monitoring data reference value) of the current threshold update cycle and set it as I e1mck , I e1mck =I emx̄ *115%, 115% is the fourth safety margin factor.

[0068] In another embodiment of the present application, when the monitoring data dimension is line temperature, the line temperature maximum alarm limit threshold is set to C g (i.e., the maximum value that can be set for the alarm threshold under the line temperature monitoring data dimension). The line temperature monitoring alarm threshold is set to C ck The threshold update cycle is 24 hours (00:00:00-23:59:59). The highest line temperature peak value in the current threshold update cycle is set as the first line temperature reference value C m , take 83% of the highest line temperature peak value in the current threshold update cycle as the second line temperature reference value C 83 , C 83 =C ck *83%, choose C ck With C 83 The average value of all monitoring data within the preset interval is set as C 1mx̄ Calculate the third line temperature reference value in the current threshold update cycle and set it to C 1mck , C 1mck =C1mx̄ *128%, 128% is the fourth safety margin factor.

[0069] S102, the server matches the operation monitoring information with a pre-stored data sequence list to generate a long- and short-cycle data set corresponding to the operation monitoring information according to the matching result.

[0070] The data series list includes at least the corresponding relationship between the time series and the monitoring data series. The long-short cycle data set includes a long-cycle data subset and a short-cycle data subset.

[0071] The server may pre-store a data sequence list, which records the correspondence between the time series and the monitoring data series, and can be understood as a list in which the monitoring data are arranged in chronological order.

[0072] In the embodiment of the present application, the operation monitoring information is matched with a pre-stored data sequence list to generate a long-short cycle data set corresponding to the operation monitoring information according to the matching result, specifically including:

[0073] The server matches the monitoring data sequence corresponding to the monitoring data dimension of the operation monitoring information from the pre-stored data sequence list. The monitoring data dimension of the operation monitoring information includes at least one or more of the following: current, voltage, residual current, and line temperature. According to the time series, the preset long cycle duration, and the preset short cycle duration, the sequence elements in the monitoring data sequence are screened to obtain the tuples of sequence elements corresponding to the long cycle data subset and the short cycle data subset, respectively, so as to generate a long and short cycle data set according to each sequence element tuple. The preset long cycle duration is greater than the preset short cycle duration. The preset short cycle duration includes multiple threshold update cycles.

[0074] In other words, after obtaining the operation monitoring information, the server can match the monitoring data sequence corresponding to the monitoring data dimension from the data sequence list, for example, to obtain the monitoring data sequence of the current, which can be generated by the monitoring data corresponding to several threshold update cycles before the current threshold update cycle. The user can pre-specify the preset long cycle duration and the preset short cycle duration, for example, the preset long cycle duration includes 30 threshold update cycles, and the preset short cycle duration includes 7 threshold update cycles. It can be understood that if the threshold update cycle is 1 day, the preset long cycle duration is 30 days from the day corresponding to the corresponding operation monitoring information, and the preset short cycle duration is 7 days in the past. Through the time series, the server can respectively filter the sequence elements corresponding to the preset long cycle duration and the preset short cycle duration, and then add the corresponding sequence elements to the long cycle data subset and the short cycle data subset. The sequence element tuple can be understood as a tuple consisting of time and monitoring data, for example (t1, Ia), t1 represents the first moment, and Ia represents the current value corresponding to the monitoring data.

[0075] In one embodiment of the present application, the time series can be divided in the data series list in the form of time series groups. A time series group includes one or more moments in the time series. If there are multiple moments in the time series group, the multiple moments are continuous. Continuous means that they are continuous in time, and there are no other moments in the middle. The time series group is divided according to certain rules. The rule can be to compare the monitoring data in the monitoring data sequence in chronological order. If the two monitoring data compared before and after are the same, the two moments in the time series corresponding to the two identical monitoring data are added to the same time series group, otherwise they are divided into different time series groups. At the same time, the server also retains one of the two monitoring data and stores it in the corresponding position in the monitoring data sequence.

[0076] Taking the monitoring data dimension of current as an example, the time series group includes {t1, t2}, {t3}, {t4, t5}, and the monitoring data sequence is [Ia, Ib, Ic]. It means that the two tuples of sequence elements corresponding to the two moments {t1, t2} are (t1, Ia), (t2, Ia), respectively. Similarly, other two tuples of sequence elements can be obtained based on the correspondence between the two time series groups and the monitoring data sequences.

[0077] Through the above processing method, storage space is saved and data processing efficiency is improved.

[0078] S103, the server determines the updated comparison values ​​of each threshold value corresponding to the operation monitoring information based on the long and short cycle data sets and the safety margin coefficient set corresponding to the power-consuming equipment end.

[0079] In the embodiment of the present application, based on the long and short cycle data sets and the safety margin coefficient set corresponding to the power consumption equipment end, the threshold update comparison values ​​corresponding to the operation monitoring information are determined, specifically including:

[0080] The server determines the first safety margin coefficient and the second safety margin coefficient corresponding to the long-period data subset and the short-period data subset in the safety margin coefficient set according to the equipment type and monitoring data dimension of the power-consuming equipment. The product value of the first monitoring data reference average value corresponding to the long-period data subset and the first safety margin coefficient is calculated as the long-period monitoring data reference value. The product value of the second monitoring data reference average value corresponding to the short-period data subset and the second safety margin coefficient is calculated as the short-period monitoring data reference value. The long-period monitoring data reference value and the short-period monitoring data reference value are used as the threshold update comparison value.

[0081] That is to say, the server pre-stores different safety margin coefficient sets corresponding to different equipment types and different monitoring data dimensions, and the safety margin coefficient sets contain safety margin coefficients corresponding to long-cycle data subsets and short-cycle data subsets, respectively, so as to perform safety margin calculations corresponding to long cycles and short cycles, respectively.

[0082] For example, equipment type S1 has different safety margin coefficient sets in monitoring data dimensions n1, n2, and n3, and the safety margin coefficient sets of different monitoring data dimensions include at least two parts: a first safety margin coefficient for processing a long-period data subset, and a second safety margin coefficient for processing a short-period data subset. Equipment type S2 can have different safety margin coefficient sets from equipment type S1 in monitoring data dimensions n1, n2, and n3.

[0083] Furthermore, the dependency relationship between the device type, monitoring data dimension and the safety margin coefficient set is set by the user or developer according to actual usage. This application does not make any specific limitations on this. For example, the developer sets several initial safety margin coefficient sets and their dependencies with the device type and monitoring data dimension. At the same time, in actual use, the user can modify or adjust the safety margin coefficient set and the above-mentioned dependencies, such as modifying the first safety margin coefficient and / or the second safety margin coefficient in the safety margin coefficient set associated with a certain device type and monitoring data dimension.

[0084] Developers can pre-specify the above initial safety margin coefficient set for different device types and different monitoring data dimensions, and store the dependency in a preset database connected to the server, so that the server can perform matching calls after obtaining the device type and monitoring data dimension of the power-consuming device. The database can store the specific data of the above dependency in a list data format.

[0085] In other words, the safety margin coefficient set is a pre-set set, and the safety margin coefficients therein are also pre-set. In actual use, the server can match the pre-set safety margin coefficient set in the preset database from several safety margin coefficient sets according to the device type of the power-consuming device, the monitoring data dimension and the dependency relationship between the safety margin coefficient set, so as to perform the determination operation of each threshold update comparison value.

[0086] Furthermore, the server can execute the above calculation method based on the first safety margin coefficient for processing the long-period data subset and the second safety margin coefficient for processing the short-period data subset, calculate the threshold update comparison value, so that the alarm threshold data is no longer fixed.

[0087] This application uses long-term and short-term data to obtain threshold update comparison values, which can comprehensively consider the impact of recent and long-term data on the alarm threshold, thereby reasonably adjusting the alarm threshold, aiming to respond to abnormalities in a timely manner and avoid false alarms. By setting multiple safety margins, the safe operation of electrical equipment and lines under different loads and working conditions is ensured.

[0088] More specifically, when the monitoring data dimension is current, the threshold update cycle is 1 day, the short cycle is 7 days, and the long cycle is 30 days, the first safety margin coefficient is set to 130%, the second safety margin coefficient is set to 110%, and the server sets the average value (i.e., the second monitoring data reference average value) of the third current reference value (i.e., the monitoring data reference value) of the previous 7 days from the current threshold update cycle as I Zx̄ , calculate the 7-day short-term monitoring data reference value and set it as I ZCK , I ZCK =I Zx̄ *110%. The average value of the third current reference value in the first 30 days (i.e., the first monitoring data reference average value) is set as I Yx̄ , calculate the 30-day long-period monitoring data reference value and set it as I YCK , I YCK =I Yx̄ *130%. Then the threshold update comparison value I is obtained YCK and I ZCK .

[0089] In one embodiment, when the monitoring data dimension is high voltage, the threshold update cycle is 1 day, the short cycle is 7 days, and the long cycle is 30 days, the first safety margin coefficient is set to 106%, the second safety margin coefficient is set to 103%, and the server sets the average value (i.e., the second monitoring data reference average value) of the third highest voltage reference value (i.e., the monitoring data reference value) of the previous 7 days from the current threshold update cycle as U 7mx̄ , calculate the 7-day short-term monitoring data reference value and set it as U 7mck, U 7mck =U 7mx̄ *103%. Set the average value of the third highest voltage reference value in the first 30 days (i.e. the first monitoring data reference average value) as U 30mx̄ Calculate the reference value of the 30-day long-term monitoring data and set it as U 30mck , U 30mck =U 30mx̄ *106%. Then we get the threshold update comparison value U 30mck and U 7mck .

[0090] In one embodiment, when the monitoring data dimension is low voltage, the threshold update cycle is 1 day, the short cycle is 7 days, and the long cycle is 30 days, the first safety margin coefficient is set to 94%, the second safety margin coefficient is set to 97%, and the server sets the average value (i.e., the second monitoring data reference average value) of the third low voltage reference value (i.e., the monitoring data reference value) of the previous 7 days from the current threshold update cycle as U 7sx̄ , calculate the 7-day short-term monitoring data reference value and set it as U 7sck , U 7sck =U 7sx̄ *97%. Set the average value of the third lowest voltage reference value in the previous 30 days (i.e. the first monitoring data reference average value) as U 30sx̄ Calculate the reference value of the 30-day long-term monitoring data and set it as U 30sck , U 30sck =U 30sx̄ *94%. Then we get the threshold update comparison value U 30sck and U 7sck .

[0091] In one embodiment, when the monitoring data dimension is residual current, the threshold update cycle is 1 day, the short cycle is 7 days, and the long cycle is 30 days, the first safety margin coefficient is set to 116%, the second safety margin coefficient is set to 110%, and the server sets the average value (i.e., the second monitoring data reference average value) of the third residual current reference value (i.e., the monitoring data reference value) of the previous 7 days from the current threshold update cycle to I e7mx̄ , calculate the 7-day short-term monitoring data reference value and set it as I e7mck , I e7mck =I e7mx̄ *110%. Set the average value of the third residual current reference value (i.e. the first monitoring data reference average value) of the first 30 days as I e30mx̄ , calculate the 30-day long-period monitoring data reference value and set it as I e30mck , I e30mck =I e30mx̄ *116%. Then the threshold update comparison value I is obtained e30mck and Ie7mck .

[0092] In one embodiment, when the monitoring data dimension is line temperature, the threshold update cycle is 1 day, the short cycle is 7 days, and the long cycle is 30 days, the first safety margin coefficient is set to 115%, the second safety margin coefficient is set to 112%, and the server sets the average value (i.e., the second monitoring data reference average value) of the third line temperature reference value (i.e., the monitoring data reference value) of the previous 7 days from the current threshold update cycle as C 7mx̄ Calculate the reference value of the 7-day short-term monitoring data and set it as C 7mck , C 7mck =C 7mx̄ *112%. Set the average value of the third line temperature reference values ​​of the first 30 days (i.e. the first monitoring data reference average value) as C 30mx̄ Calculate the reference value of the 30-day long-term monitoring data and set it as C 30mck , C 30mck =C 30mx̄ *115%. Then we get the threshold update comparison value C 30mck and C 7mck .

[0093] The above-mentioned first safety margin coefficient and second safety margin coefficient can be adjusted by the user according to actual usage conditions, and this application does not make any specific limitations on this.

[0094] S104: The server determines whether to update the previous alarm threshold according to the threshold update rule and each threshold update comparison value to obtain the current alarm threshold.

[0095] In the embodiment of the present application, according to the threshold update rule and each threshold update comparison value, it is determined whether to update the previous alarm threshold to obtain the current alarm threshold, specifically including:

[0096] The server compares the reference value of the monitoring data with the reference value of the short-period monitoring data to obtain a first comparison result. According to the first comparison result and the preset trend compliance division condition of the corresponding monitoring data dimension, the power consumption trend compliance result is determined. The preset trend compliance division condition is used to characterize the degree of specialness of different power consumption trends in the corresponding monitoring data dimension. The power consumption trend compliance result includes trend compliance and trend deviation.

[0097] When the power consumption trend conformity result is a trend deviation, the monitoring data reference value is compared with the long-period monitoring data reference value to determine a provisional alarm threshold value according to the corresponding second comparison result. The provisional alarm threshold value includes at least one of the following: a short-period monitoring data reference value and a third safety margin. The third safety margin is the product of the monitoring data reference value and the third safety margin coefficient. When the power consumption trend conformity result is a trend conformity, the monitoring data reference value is used as the provisional alarm threshold value.

[0098] When the provisional alarm threshold is not equal to the previous alarm threshold, the previous alarm threshold is updated to use the provisional alarm threshold as the current alarm threshold. When the provisional alarm threshold is equal to the previous alarm threshold, the previous alarm threshold is not updated.

[0099] Specifically, the server first compares the monitoring data reference value with the short-period monitoring data reference value obtained above. The comparison can be understood as obtaining the size relationship between the monitoring data reference value and the short-period monitoring data reference value, and adding the size relationship to the first comparison result. For different monitoring data dimensions, different first comparison results, that is, different size relationships, represent different degrees of specialness of electricity consumption trends. For example, under the current monitoring data dimension, if the monitoring data reference value is greater than the short-period monitoring data reference value, it means that the current situation in the threshold update period corresponding to the monitoring data reference value is highly special. At this time, the electricity consumption trend compliance result is trend deviation (that is, it is significantly different from the short-period electricity consumption trend). The monitoring data reference value is taken as the provisional alarm threshold to avoid false alarms. If the monitoring data reference value is not greater than the short-period monitoring data reference value, it means that the current situation in the threshold update period corresponding to the monitoring data reference value is less special. At this time, the electricity consumption trend compliance result is trend compliance (that is, it is slightly different from the short-period electricity consumption trend). The monitoring data reference value is further compared with the long-period monitoring data reference value to obtain a second comparison result. The server can store a provisional alarm threshold selection rule corresponding to the second comparison result, that is, the provisional alarm threshold is selected according to the different size relationships between the monitoring data reference value and the long-period monitoring data reference value.

[0100] The above-mentioned different second comparison results can represent the consistency of the monitoring data reference value with the long-period power consumption trend, or the deviation of the monitoring data reference value from the long-period power consumption trend. At this time, the server can use the short-period monitoring data reference value as the provisional alarm threshold when the power consumption trend is consistent, and use the third safety margin as the provisional alarm threshold when the power consumption trend deviates.

[0101] Meanwhile, if the provisional alarm threshold is different from the previous alarm threshold of the current threshold update cycle, the server uses the provisional alarm threshold as the current alarm threshold of the next threshold update cycle.

[0102] Through the above technical solution, the alarm threshold can be flexibly determined based on the short-term and long-term monitoring data. Instead of relying rigidly on fixed alarm thresholds, the alarm threshold can be intelligently adjusted based on long-term and short-term monitoring data, thereby achieving more reasonable power alarm identification and better smart fire protection. Long-term and short-term monitoring data can reflect the recent power consumption attributes of the power-consuming equipment. Using two parts of monitoring data can ensure that the alarm threshold setting is more humane.

[0103] Taking the example of the monitoring data dimension of current as an example, the server will DCK with I ZCK Compare, if I DCK Greater than I ZCK , then the trend is in line with I DCK As a temporary alarm threshold; if I DCK No more than I ZCK , then it is a trend deviation, and I DCK with I YCK Compare, if I DCK Less than I YCK , the server will use the third safety margin I DCK *90% is used as the provisional alarm threshold; otherwise, I ZCK As a provisional alarm threshold. The current alarm threshold I is obtained through the provisional alarm threshold CK The third safety margin coefficient is set by the user according to the actual usage scenario, and this application does not make any specific limitation on this.

[0104] Taking the example of high voltage as the monitoring data dimension, the server will 1mck with U 7mck Compare, if U 1mck Greater than U 7mck , then the trend is in line with U 1mck As a temporary alarm threshold; if U 1mck No greater than U 7mck , then it is a trend deviation, and U 1mck with U 30mck Compare, if U 1mck Less than U 30mck , the server will use the third safety margin U 1mck *98% is used as the provisional alarm threshold; otherwise, U 7mck As the provisional alarm threshold. The high voltage alarm threshold U is obtained through the provisional alarm threshold mck .

[0105] Taking the example of low voltage as the monitoring data dimension, the server will 1sck with U 7sck Compare, if U 1sck Less than U 7sck , then the trend is in line with U 1sck As a temporary alarm threshold; if U 1sck Not less than U 7sck , then it is a trend deviation, and U 1sck with U 30sck Compare, if U 1sck Greater than U 30sck , the server will use the third safety margin U 1sck *102% is used as the provisional alarm threshold; otherwise, U7sck As the provisional alarm threshold. The low voltage alarm threshold U is obtained through the provisional alarm threshold sck .

[0106] Taking the example of residual current as the monitoring data dimension, the server will e1mck with I e7mck Compare, if I e1mck Greater than I e7mck , then the trend is in line with I e1mck As a temporary alarm threshold; if I e1mck No more than I e7mck , then it is a trend deviation, and I e1mck with I e30mck Compare, if I e1mck Less than I e30mck , the server will use the third safety margin I e1mck *95% is used as the provisional alarm threshold; otherwise, I e7mck As a provisional alarm threshold. The residual current alarm threshold I is obtained through the provisional alarm threshold eck .

[0107] Take the example of line temperature as the monitoring data dimension. The server will 1mck With C 7mck Compare, if C 1mck Greater than C 7mck , then the trend is in line with C 1mck As a temporary alarm threshold; if C 1mck No more than C 7mck , then it is a trend deviation, and C 1mck With C 30mck Compare, if C 1mck Less than C 30mck , the server will use the third safety margin C 1mck *90% is used as the temporary alarm threshold; otherwise, C 7mck As a provisional alarm threshold. The line temperature alarm threshold C is obtained through the provisional alarm threshold ck .

[0108] S105, the server performs alarm identification on the real-time monitoring data of the next threshold update cycle based on the current alarm threshold to determine whether the real-time monitoring data meets the alarm triggering conditions, and generates corresponding alarm prompt information when the alarm triggering conditions are met, and sends it to the user terminal.

[0109] The alarm prompt information can be text, pictures or sounds. The user terminal can be understood as the user's mobile phone, computer and other devices that perform electricity usage alarm identification. This application does not make specific limitations on this.

[0110] In an embodiment of the present application, the server compares the real-time monitoring data of the next threshold update cycle acquired in real time with the current alarm threshold of the corresponding monitoring data dimension, and determines whether the real-time monitoring data meets the alarm triggering condition based on the result of the size comparison. In actual use, the real-time monitoring data of some monitoring data dimensions is greater than the corresponding current alarm threshold, and meets the alarm triggering condition, such as current; the real-time monitoring data of some monitoring data dimensions is less than the corresponding current alarm threshold, and meets the alarm triggering condition, such as low voltage. The specific judgment rules are set by the user according to the actual use scenario, and this application does not make specific restrictions on this.

[0111] In the embodiment of the present application, although the alarm threshold can be regularly updated according to the threshold update cycle, there may be some unnecessary updates in the actual usage scenario. Therefore, the present application provides the following embodiments, which are as follows:

[0112] The server obtains the alarm threshold update record and generates an alarm threshold update curve. The horizontal coordinate of the alarm threshold update curve is time, and the vertical coordinate is the alarm threshold. A first difference curve is generated according to the difference between the values ​​of each vertical coordinate point of the alarm threshold update curve and the representative value of the monitoring data in the corresponding threshold update period. The representative value of the monitoring data is the maximum value of the monitoring data or the minimum value of the monitoring data. A second difference curve is generated according to the difference between the values ​​of each vertical coordinate point of the alarm threshold update curve and the corresponding previous alarm threshold. The first difference curve and the second difference curve are input into the preset update effectiveness recognition model to determine the corresponding update effective alarm coordinate point, and the horizontal coordinate of each update effective alarm coordinate point is added to the interval sequence to be updated. Based on each adjacent time difference and the threshold update period in the interval sequence to be updated, the threshold update interval operation period is determined. The threshold update interval operation period is used to perform an update of the previous alarm threshold after a number of threshold update periods corresponding to the interval threshold update interval operation period.

[0113] In other words, the server can establish an alarm threshold update curve through historical alarm threshold update records and a rectangular coordinate system, and each coordinate point in the curve represents the alarm threshold at each time. The server calculates the difference between the ordinate value of each coordinate point and the representative value of the monitoring data in the threshold update period at the corresponding time, and uses the difference to generate a first difference curve related to time; the ordinate value is subtracted from the previous alarm threshold of the threshold update period before the threshold update period at the corresponding time, and the corresponding difference is obtained to generate a second difference curve. Whether the representative value of the monitoring data takes the maximum value of the monitoring data or the minimum value of the monitoring data depends on the dimension of the monitoring data. For example, the representative value of the monitoring data of the current is the maximum value of the monitoring data, and the representative value of the monitoring data of the low voltage is the minimum value of the monitoring data.

[0114] The server may store a pre-trained preset update effectiveness recognition model, which is obtained by training with a plurality of first difference curve samples, a second difference curve samples and effectiveness labels marked on each coordinate point. The preset update effectiveness recognition model may be a neural network model.

[0115] The server inputs the first difference curve and the second difference curve into the trained preset update effectiveness recognition model. The input first difference curve and the second difference curve can be curve images or curve fitting formulas, which are not specifically limited in this application. The preset update effectiveness recognition model will output each coordinate point whose effectiveness is greater than a preset threshold, and the server uses it as the updated effective alarm coordinate point. Among them, the threshold update corresponding to the updated effective alarm coordinate point can be understood as an effective update that the current alarm threshold can accurately warn more than the previous alarm threshold. For example, the threshold update period corresponding to the current alarm threshold a is A, and the threshold update period corresponding to the previous alarm threshold b is B. If A does not update the previous alarm threshold b to the current alarm threshold a, a false alarm will occur. At this time, it is an effective update. The characterization value corresponding to the effective update degree can be marked by the user during actual use. This application does not make specific limitations on this.

[0116] After the server obtains each updated valid alarm coordinate point, it can sequentially add the time value corresponding to the horizontal coordinate to the interval sequence to be updated. The server calculates the adjacent time difference between two adjacent time values ​​in the sequence, and determines the threshold update interval operation period according to the threshold update period.

[0117] In the embodiment of the present application, the threshold update interval operation period is determined based on each adjacent time difference in the interval sequence to be updated and the threshold update period, specifically including:

[0118] The server calculates the division result of each adjacent time difference and the threshold update period to obtain multiple threshold effective update interval periods. The threshold effective update interval periods are arranged from large to small into an interval period sequence. The median in the interval period sequence is used as the threshold update interval operation period.

[0119] In other words, the server can obtain the threshold effective update interval period by calculating the threshold update period included in the adjacent time difference, and obtain the threshold update interval operation period by generating an interval period sequence and selecting the median of the sequence. Thus, a threshold update interval operation period that is more adaptable to the actual usage scenario is obtained, and the threshold update interval operation period is used to flexibly call the execution of the above steps S102-S104.

[0120] In the embodiment of the present application, the above determination of whether the real-time monitoring data meets the alarm triggering condition specifically includes:

[0121] The real-time monitoring data of the next threshold update cycle is compared with the current alarm threshold to match the third comparison result with the alarm threshold trigger sub-condition in the alarm trigger condition, and whether the real-time monitoring data meets the alarm trigger condition is determined according to the first matching result. In the case where it is determined that the real-time monitoring data does not meet the alarm trigger condition, the real-time monitoring data is matched with the alarm trigger additional sub-condition in the alarm trigger condition to determine whether the real-time monitoring data meets the alarm trigger condition according to the second matching result.

[0122] In other words, in addition to setting the alarm threshold as an alarm trigger condition for each monitoring data dimension, the present application can also set additional alarm trigger sub-conditions, thereby making alarm identification more comprehensive and not completely dependent on the alarm of a threshold, but enabling more flexible alarming.

[0123] For example, the complete alarm trigger condition of current may include current value I ≥ I ck or I ≥ I SCK *120% or I≥ rated current of switching power supply*80% or I≥ safe current carrying capacity of cable*85%. SCK It is the minimum value of the third current reference value in the previous 30 days. The rated current of the switching power supply and the safe current carrying capacity of the cable are set by the user, and this application does not make any specific restrictions on this.

[0124] The complete alarm trigger condition for high voltage can include voltage value U≥U mck Or U ≥ U msck *104% or U≥U mg .U msck It is the minimum value among the third highest voltage reference values ​​in the previous 30 days.

[0125] The complete low voltage alarm trigger condition can include voltage value U≤U sck Or U≤U mmck *94% or U≤U sg .U mmck It is the minimum value among the third lowest voltage reference values ​​in the previous 30 days.

[0126] The complete alarm trigger condition of residual current can include the residual current value I e ≥I eck or I e ≥I esck *112% or I e ≥I eg I esck It is the minimum value among the third residual current reference values ​​in the previous 30 days.

[0127] The complete alarm trigger condition of line temperature can include line temperature C ≥ C ck or C ≥ C sck *110% or C≥C h*132. C sck The minimum value of the third line temperature reference value in the previous 30 days, C h is the ambient temperature.

[0128] Through the above scheme, this application can combine short-cycle data and long-cycle data to flexibly determine whether the alarm threshold needs to be updated in each threshold update cycle, so as to obtain an alarm threshold that is more in line with the actual usage conditions. There is no need to invest excessive manpower costs, and the technical problem that the current alarm threshold data is fixed and prone to false alarms or missed alarms is solved. By flexibly updating the alarm threshold, the sensitivity of the power alarm is improved, and the user experience of smart power alarm identification in the smart fire protection process is improved.

[0129] Figure 2 A schematic diagram of the structure of a smart power usage alarm identification device provided in an embodiment of the present application is shown in FIG. Figure 2 As shown, the smart power usage alarm identification device 200 includes:

[0130] The first determination module 201 determines the operation monitoring information of the power-consuming device end based on the preset threshold update cycle. The operation monitoring information includes a reference value of monitoring data within a threshold update cycle. The matching module 202 is used to match the operation monitoring information with a pre-stored data sequence list to generate a long-short cycle data set corresponding to the operation monitoring information according to the matching result. The data sequence list at least includes the corresponding relationship between the time series and the monitoring data sequence. The long-short cycle data set includes a long-cycle data subset and a short-cycle data subset. The second determination module 203 is used to determine the threshold update comparison values ​​corresponding to the operation monitoring information based on the long-short cycle data set and the safety margin coefficient set corresponding to the power-consuming device end. The third determination module 204 is used to determine whether to update the previous alarm threshold according to the threshold update rule and each threshold update comparison value to obtain the current alarm threshold. The alarm identification module 205 is used to perform alarm identification on the real-time monitoring data of the next threshold update cycle based on the current alarm threshold to determine whether the real-time monitoring data meets the alarm trigger condition, and generate corresponding alarm prompt information when the alarm trigger condition is met, and send it to the user terminal.

[0131] The matching module is specifically used for:

[0132] From the pre-stored data sequence list, match the monitoring data sequence corresponding to the monitoring data dimension of the operation monitoring information. Among them, the monitoring data dimension of the operation monitoring information includes at least one or more of the following: current, voltage, residual current, line temperature. According to the time series, the preset long cycle duration and the preset short cycle duration, the sequence elements in the monitoring data sequence are screened to obtain the sequence element tuples corresponding to the long cycle data subset and the short cycle data subset, respectively, so as to generate a long and short cycle data set according to each sequence element tuple. The preset long cycle duration is greater than the preset short cycle duration. The preset short cycle duration includes multiple threshold update cycles.

[0133] The second determination module is specifically used for:

[0134] According to the equipment type and monitoring data dimension of the electrical equipment end, determine the first safety margin coefficient and the second safety margin coefficient corresponding to the long-period data subset and the short-period data subset in the safety margin coefficient set. Calculate the product value of the first monitoring data reference average value corresponding to the long-period data subset and the first safety margin coefficient as the long-period monitoring data reference value. Calculate the product value of the second monitoring data reference average value corresponding to the short-period data subset and the second safety margin coefficient as the short-period monitoring data reference value. Use the long-period monitoring data reference value and the short-period monitoring data reference value as the threshold update comparison value.

[0135] The third determination module is specifically used for:

[0136] The reference value of the monitoring data is compared with the reference value of the short-period monitoring data to obtain a first comparison result. According to the first comparison result and the preset trend of the corresponding monitoring data dimension, the power consumption trend meets the division condition, and the result is determined. The preset trend meets the division condition to characterize the special degree of different power consumption trends in the corresponding monitoring data dimension. The power consumption trend meets the result includes trend compliance and trend deviation. In the case where the power consumption trend compliance result is trend deviation, the reference value of the monitoring data is compared with the reference value of the long-period monitoring data to determine the provisional alarm threshold according to the corresponding second comparison result. The provisional alarm threshold includes at least one of the following: a short-period monitoring data reference value and a third safety margin. The third safety margin is the product value of the monitoring data reference value and the third safety margin coefficient. In the case where the power consumption trend meets the result is trend compliance, the reference value of the monitoring data is used as the provisional alarm threshold. In the case where the provisional alarm threshold is not equal to the previous alarm threshold, the previous alarm threshold is updated to use the provisional alarm threshold as the current alarm threshold.

[0137] The smart electricity alarm identification device can also:

[0138] Get the alarm threshold update record and generate the alarm threshold update curve. The horizontal coordinate of the alarm threshold update curve is time, and the vertical coordinate is the alarm threshold. Generate a first difference curve based on the difference between each coordinate point of the alarm threshold update curve and the maximum value of the monitoring data in the corresponding threshold update period. Generate a second difference curve based on the difference between each coordinate point of the alarm threshold update curve and the corresponding previous alarm threshold. Input the first difference curve and the second difference curve into the preset update effectiveness recognition model, determine the corresponding update effective alarm coordinate point, and add the horizontal coordinate of each update effective alarm coordinate point to the interval sequence to be updated. Based on each adjacent time difference and the threshold update period in the interval sequence to be updated, determine the threshold update interval operation period. The threshold update interval operation period is used to perform an update of the previous alarm threshold after a number of threshold update periods corresponding to the interval threshold update interval operation period.

[0139] The smart electricity alarm identification device can also:

[0140] Calculate the division result of each adjacent time difference and the threshold update period to obtain multiple threshold effective update interval periods. Arrange the threshold effective update interval periods from large to small into an interval period sequence. Use the median in the interval period sequence as the threshold update interval operation period.

[0141] The alarm identification module is specifically used for:

[0142] The real-time monitoring data of the next threshold update cycle is compared with the current alarm threshold, so as to match the third comparison result with the alarm threshold trigger sub-condition in the alarm trigger condition, and judge whether the real-time monitoring data meets the alarm trigger condition according to the first matching result. If not, the real-time monitoring data is matched with the alarm trigger additional sub-condition in the alarm trigger condition, so as to judge whether the real-time monitoring data meets the alarm trigger condition according to the second matching result.

[0143] In the embodiment of the present application, the power-consuming equipment end includes at least one or more of the following: a charging station distribution box, a campus distribution box, and a residential power distribution box.

[0144] Figure 3 A schematic diagram of the structure of a smart power alarm identification device provided in an embodiment of the present application is shown in FIG. Figure 3 As shown, the device includes:

[0145] At least one processor; and a memory in communication with the at least one processor. The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to:

[0146] Based on the preset threshold update cycle, the operation monitoring information of the power-consuming device is determined. The operation monitoring information includes a reference value of monitoring data within a threshold update cycle. The operation monitoring information is matched with a pre-stored data sequence list to generate a long-short cycle data set corresponding to the operation monitoring information according to the matching result. The data sequence list includes at least the correspondence between the time series and the monitoring data sequence. The long-short cycle data set includes a long-cycle data subset and a short-cycle data subset. Based on the long-short cycle data set and the safety margin coefficient set corresponding to the power-consuming device, the threshold update comparison values ​​corresponding to the operation monitoring information are determined. According to the threshold update rules and the threshold update comparison values, it is determined whether to update the previous alarm threshold to obtain the current alarm threshold. Based on the current alarm threshold, the real-time monitoring data of the next threshold update cycle is alarm identified to determine whether the real-time monitoring data meets the alarm trigger condition, and if the alarm trigger condition is met, the corresponding alarm prompt information is generated and sent to the user terminal.

[0147] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, apparatus and equipment embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0148] The devices, apparatuses and equipment provided in the embodiments of the present application correspond one-to-one to the methods. Therefore, the devices, apparatuses and equipment also have similar beneficial technical effects as the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices, apparatuses and equipment will not be repeated here.

[0149] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0150] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A smart electricity alarm identification method, characterized in that: The method is applied to a smart power consumption alarm identification system connected to one or more power consumption devices; the method comprises: Based on a preset threshold update cycle, determining the operation monitoring information of the electric device end; the operation monitoring information includes a monitoring data reference value within the threshold update cycle; Matching the operation monitoring information with a pre-stored data sequence list to generate a long- and short-cycle data set corresponding to the operation monitoring information according to the matching result; the data sequence list at least includes a corresponding relationship between a time series and a monitoring data sequence; the long- and short-cycle data set includes a long-cycle data subset and a short-cycle data subset; Determine, based on the long- and short-cycle data sets and the safety margin coefficient set corresponding to the power-consuming device end, each threshold update comparison value corresponding to the operation monitoring information; Determine whether to update the previous alarm threshold according to the threshold update rule and the threshold update comparison value to obtain the current alarm threshold; Based on the current alarm threshold, the real-time monitoring data of the next threshold update period is subjected to alarm identification to determine whether the real-time monitoring data meets the alarm triggering condition, and if the alarm triggering condition is met, corresponding alarm prompt information is generated and sent to the user terminal; The operation monitoring information is matched with a pre-stored data sequence list to generate a long- and short-period data set corresponding to the operation monitoring information according to the matching result, specifically including: Matching the monitoring data sequence corresponding to the monitoring data dimension of the operation monitoring information from the pre-stored data sequence list; wherein the monitoring data dimension of the operation monitoring information includes at least one or more of the following: current, voltage, residual current, and line temperature; According to the time series, the preset long cycle duration and the preset short cycle duration, the sequence elements in the monitoring data sequence are screened to obtain the sequence element tuples corresponding to the long cycle data subset and the short cycle data subset, respectively, so as to generate the long and short cycle data set according to the sequence element tuples; the preset long cycle duration is greater than the preset short cycle duration; the preset short cycle duration includes a plurality of the threshold update cycles; Wherein, based on the long and short cycle data sets and the safety margin coefficient set corresponding to the power-consuming device end, determining each threshold update comparison value corresponding to the operation monitoring information specifically includes: According to the equipment type and the monitoring data dimension of the electric equipment end, determine the first safety margin coefficient and the second safety margin coefficient corresponding to the long-period data subset and the short-period data subset in the safety margin coefficient set; wherein different equipment types and different monitoring data dimensions correspond to different safety margin coefficient sets, and the safety margin coefficient set contains safety margin coefficients corresponding to the long-period data subset and the short-period data subset, respectively, so as to perform safety margin calculations corresponding to the long period and the short period, respectively; Calculate the product of the first monitoring data reference average value corresponding to the long-period data subset and the first safety margin coefficient as the long-period monitoring data reference value; Calculate the product of the second monitoring data reference average value corresponding to the short-period data subset and the second safety margin coefficient as the short-period monitoring data reference value; The long-period monitoring data reference value and the short-period monitoring data reference value are used as the threshold update comparison value.

2. A smart electricity alarm identification method according to claim 1, characterized in that: According to the threshold update rule and each of the threshold update comparison values, determining whether to update the previous alarm threshold to obtain the current alarm threshold specifically includes: Comparing the monitoring data reference value with the short-period monitoring data reference value to obtain a first comparison result; According to whether the first comparison result and the preset trend of the corresponding monitoring data dimension meet the division condition, determining the power consumption trend compliance result; the preset trend compliance division condition is used to characterize the special degree of different power consumption trends of the corresponding monitoring data dimension; the power consumption trend compliance result includes trend compliance and trend deviation; In the case where the power consumption trend conformity result is a trend deviation, the monitoring data reference value is compared with the long-period monitoring data reference value to determine a provisional alarm threshold according to the corresponding second comparison result; the provisional alarm threshold includes at least one of the following: the short-period monitoring data reference value and a third safety margin; the third safety margin is the product value of the monitoring data reference value and a third safety margin coefficient; When the power consumption trend compliance result is trend compliance, using the monitoring data reference value as the provisional alarm threshold; In the case that the provisional alarm threshold is not equal to the early alarm threshold, the early alarm threshold is updated to use the provisional alarm threshold as the current alarm threshold.

3. A smart electricity alarm identification method according to claim 1, characterized in that: The method further comprises: Acquire the alarm threshold update record and generate an alarm threshold update curve; the abscissa of the alarm threshold update curve is time, and the ordinate is the alarm threshold; Generate a first difference curve according to the difference between each ordinate value of the alarm threshold update curve and the corresponding representative value of the monitoring data within the threshold update period; the representative value of the monitoring data is the maximum value of the monitoring data or the minimum value of the monitoring data; Generate a second difference curve according to the difference between each ordinate point value of the alarm threshold update curve and the corresponding previous alarm threshold; Inputting the first difference curve and the second difference curve into a preset update effectiveness recognition model, determining corresponding update effective alarm coordinate points, and adding the horizontal coordinates of each of the update effective alarm coordinate points to the interval sequence to be updated; Based on each adjacent time difference in the interval sequence to be updated and the threshold update period, a threshold update interval operation period is determined; the threshold update interval operation period is used to execute the update of the early warning threshold after a number of threshold update periods corresponding to the threshold update interval operation period.

4. A smart electricity alarm identification method according to claim 3, characterized in that: Determining the threshold update interval operation period based on each adjacent time difference in the interval sequence to be updated and the threshold update period specifically includes: Calculate the division result of each of the adjacent time differences and the threshold update period to obtain a plurality of threshold effective update interval periods; Arrange the effective update intervals of the threshold values ​​from large to small to form an interval sequence; The median of the interval period sequence is used as the threshold update interval operation period.

5. The method for identifying a smart power usage alarm according to claim 1, characterized in that: Determining whether the real-time monitoring data meets the alarm triggering condition specifically includes: Comparing the real-time monitoring data of the next threshold update cycle with the current alarm threshold to match the third comparison result with the alarm threshold trigger sub-condition in the alarm trigger condition, and judging whether the real-time monitoring data meets the alarm trigger condition according to the first matching result; If not, the real-time monitoring data is matched with the alarm triggering additional sub-condition in the alarm triggering condition to determine whether the real-time monitoring data satisfies the alarm triggering condition according to a second matching result.

6. A smart electricity alarm identification method according to claim 1, characterized in that: The power-consuming equipment end includes at least one or more of the following: a charging station distribution box, a park distribution box, and a residential power distribution box.

7. A smart electricity alarm identification device, characterized in that: The device comprises: A first determination module determines operation monitoring information of the electric device end based on a preset threshold update period; the operation monitoring information includes a monitoring data reference value within the threshold update period; A matching module, used for matching the operation monitoring information with a pre-stored data sequence list, so as to generate a long-short cycle data set corresponding to the operation monitoring information according to the matching result; the data sequence list at least includes a corresponding relationship between a time series and a monitoring data sequence; the long-short cycle data set includes a long-cycle data subset and a short-cycle data subset; A second determination module is used to determine each threshold update comparison value corresponding to the operation monitoring information based on the long and short cycle data set and the safety margin coefficient set corresponding to the power-consuming device end; A third determination module is used to determine whether to update the previous alarm threshold according to the threshold update rule and each of the threshold update comparison values ​​to obtain the current alarm threshold; An alarm identification module is used to perform alarm identification on the real-time monitoring data of the next threshold update period based on the current alarm threshold to determine whether the real-time monitoring data meets the alarm triggering condition, and generate corresponding alarm prompt information when the alarm triggering condition is met, and send it to the user terminal; Wherein, the matching module is specifically used for: Matching the monitoring data sequence corresponding to the monitoring data dimension of the operation monitoring information from the pre-stored data sequence list; wherein the monitoring data dimension of the operation monitoring information includes at least one or more of the following: current, voltage, residual current, and line temperature; According to the time series, the preset long cycle duration and the preset short cycle duration, the sequence elements in the monitoring data sequence are screened to obtain the sequence element tuples corresponding to the long cycle data subset and the short cycle data subset, respectively, so as to generate the long and short cycle data set according to the sequence element tuples; the preset long cycle duration is greater than the preset short cycle duration; the preset short cycle duration includes a plurality of the threshold update cycles; Wherein, the second determining module is specifically used for: According to the equipment type and the monitoring data dimension of the electric equipment end, determine the first safety margin coefficient and the second safety margin coefficient corresponding to the long-period data subset and the short-period data subset in the safety margin coefficient set; wherein different equipment types and different monitoring data dimensions correspond to different safety margin coefficient sets, and the safety margin coefficient set contains safety margin coefficients corresponding to the long-period data subset and the short-period data subset, respectively, so as to perform safety margin calculations corresponding to the long period and the short period, respectively; Calculate the product of the first monitoring data reference average value corresponding to the long-period data subset and the first safety margin coefficient as the long-period monitoring data reference value; Calculate the product of the second monitoring data reference average value corresponding to the short-period data subset and the second safety margin coefficient as the short-period monitoring data reference value; The long-period monitoring data reference value and the short-period monitoring data reference value are used as the threshold update comparison value.

8. A smart electricity alarm identification device, characterized in that: The device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute a smart electricity alarm identification method as described in any one of claims 1-6 above.

Images