Electrical equipment state detection method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention relates to an electrical equipment state detection method and device, electronic equipment and a storage medium, current electric quantity information sent by an intelligent power line is received, the intelligent power line is used for connecting electrical equipment to a power supply, and an electric quantity acquisition module is integrated on the intelligent power line; the acquisition module acquires electric quantity information of electrical equipment; the current electric quantity information is input into a clustering model, the state category of the electrical equipment is output, and the state of the electrical equipment comprises at least one of power-on, standby, power-off and abnormity; the electric quantity information is obtained through the intelligent power line of the electrical equipment, compared with traditional electric quantity monitoring equipment or an intelligent electric meter, the loss risk, the cost and the operation complexity are reduced, and meanwhile the state detection efficiency of the electrical equipment is improved through the clustering model.

Description

Technical Field

[0001] The present invention relates to the field of electronics, and in particular, to a method, device, electronic device, and storage medium for detecting the state of an electrical appliance device. Background Art

[0002] Real-time monitoring of the state of electrical appliance devices can achieve more intelligent and efficient device management and operation.

[0003] In related technologies, it is usually necessary to separately install a power consumption monitoring device or use a smart meter and other devices to collect the power consumption information of electrical appliance devices, and then the staff determines the state of the electrical appliance devices according to the collected power consumption information.

[0004] However, in the above methods, it is necessary to separately purchase, install, and configure a power consumption monitoring device or a smart meter, and it is also possible to lose the external device due to device relocation, which increases the cost and operation complexity, and the efficiency of manually detecting the state of electrical appliance devices is low. Summary of the Invention

[0005] Embodiments of the present invention provide a method, device, electronic device, and storage medium for detecting the state of an electrical appliance device to solve the technical problem of how to simply, conveniently, and quickly detect the state of an electrical appliance device.

[0006] In a first aspect, an embodiment of the present invention provides a method for detecting the state of an electrical appliance device, which is applied to an application server. The method includes: receiving the current power consumption information sent by a smart power cord, where the smart power cord is used to connect an electrical appliance device to a power source, and a power consumption acquisition module is integrated on the smart power cord for acquiring the power consumption information of the electrical appliance device; inputting the current power consumption information into a clustering model, and outputting the state category of the electrical appliance device, where the state of the electrical appliance device includes at least one of the following: powered on, standby, powered off, and abnormal.

[0007] In some embodiments, after outputting the state category of the electrical appliance device, it further includes: determining the distance between the current power consumption information and the cluster centroid with the smallest distance in the clustering model; determining the credibility of the output result of the clustering model according to the distance.

[0008] In some embodiments, before inputting the current power consumption information into the clustering model, it further includes: acquiring first historical power consumption information collected through the smart power cord and the corresponding first state category label of the electrical appliance device, where the first historical power consumption information and the first state category label of the electrical appliance device form a data set; performing clustering analysis on the data set to obtain the clustering model.

[0009] In some embodiments, the anomalies in the electrical device status include multiple anomaly types; obtaining the first historical power consumption information collected through the intelligent power cord and the corresponding first electrical device status category label, the first historical power consumption information and the first electrical device status category label constitute a data set, including: obtaining the first historical power consumption information and the corresponding first electrical device status category label for multiple historical time periods within a historical duration; determining a corresponding historical time-power consumption curve schematic diagram according to the first historical power consumption information of each historical time period; performing clustering analysis on the data set to obtain the clustering model, including: performing clustering analysis on the multiple historical time-power consumption curve schematic diagrams to obtain a clustering model; determining a reference time-power consumption curve schematic diagram corresponding to each cluster in the clustering model; receiving the current power consumption information sent by the intelligent power cord, including: receiving the current power consumption information corresponding to the current time period sent by the intelligent power supply, and determining a current time-power consumption curve schematic diagram according to the current power consumption information of the current time period; inputting the current power consumption information into the clustering model and outputting the electrical device status category, including: calculating the similarity between the current time-power consumption curve schematic diagram and each reference time-power consumption curve schematic diagram in the clustering model, and determining that the cluster category corresponding to the reference time-power consumption curve schematic diagram with the maximum similarity is the electrical device status of the electrical device in the current time period.

[0010] In some embodiments, the method further includes: every second preset duration, obtaining the second historical power consumption information collected through the intelligent power cord and the corresponding second electrical device status category label, the second historical power consumption information and the second electrical device status category label constitute a supplementary data set; updating the clustering model based on the supplementary data set.

[0011] In some embodiments, the method further includes: repeating the step of receiving the current power consumption information sent by the intelligent power cord until a first preset duration, until obtaining the electrical device status category within the first preset duration; obtaining the on-time period corresponding to the electrical device status category being on within the first preset duration; or, determining the electrical device usage rate according to the number of times the electrical device status category is on or off within the first preset duration.

[0012] In a second aspect, an embodiment of the present invention provides an electrical device status detection device, which is applied to an application server. The device includes: a receiving module, configured to receive the current power consumption information sent by the intelligent power cord, the intelligent power cord is used to connect an electrical device to a power supply, and a power consumption acquisition module is integrated on the intelligent power cord for acquiring the power consumption information of the electrical device; a detection module, configured to input the current power consumption information into the clustering model and output the electrical device status category, where the electrical device status includes at least one of the following: on, standby, off, and abnormal.

[0013] In some embodiments, the detection module is further configured to: determine the distance between the current power information and the cluster centroid with the smallest distance in the clustering model; and determine the credibility of the output result of the clustering model according to the distance.

[0014] In a third aspect, an embodiment of the present invention provides an electronic device, which includes a processor, a communication interface, a memory, and a communication bus. The processor, the communication interface, and the memory communicate with each other through the communication bus. The memory is used to store a computer program. When the processor executes the program stored in the memory, it implements the steps of the electrical device status detection method according to any one of the first aspect.

[0015] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored. The computer program, when executed by a processor, implements the steps of the electrical device status detection method according to any one of the first aspect.

[0016] The embodiments of the present invention have the following beneficial effects:

[0017] The electrical device status detection method, device, electronic device, and storage medium provided by the embodiments of the present invention receive the current power information sent by the smart power cord. The smart power cord is used to connect the electrical device to the power supply, and the smart power cord is integrated with a power acquisition module for collecting the power information of the electrical device. The current power information is input into the clustering model to output the electrical device status category. The electrical device status includes at least one of the following: powered on, standby, powered off, and abnormal. That is, in this embodiment, the power information is obtained through the smart power cord of the electrical device, which reduces the risk of loss, cost, and operation complexity compared with traditional power monitoring devices or smart meters. At the same time, the efficiency of electrical device status detection is improved by using the clustering model. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings herein are incorporated into the specification and form a part of the specification, showing embodiments consistent with the present invention, and are used together with the specification to explain the principles of the present invention.

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0020] Figure 1 It is a schematic diagram of an application scenario provided by an embodiment of the present invention;

[0021] Figure 2Schematic diagram of the structure of a smart power cord provided by an embodiment of the present invention;

[0022] Figure 3 Flowchart of a method for detecting the state of an electrical device provided by an embodiment of the present invention;

[0023] Figure 4 Schematic diagram of the training process of a clustering model provided by an embodiment of the present invention;

[0024] Figure 5 Another flowchart of a method for detecting the state of an electrical device provided by an embodiment of the present invention;

[0025] Figure 6 Schematic diagram of the structure of a device for detecting the state of an electrical device provided by an embodiment of the present invention;

[0026] Figure 7 Schematic diagram of the hardware structure of an electronic device provided by an embodiment of the present invention. Detailed implementation manners

[0027] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Apparently, the described embodiments are some but not all of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0028] Figure 1 Schematic diagram of an application scenario provided by an embodiment of the present invention. As Figure 1 shown, this application scenario includes an electrical device 10, a smart power cord 20, a LoRa gateway 30, and an application server 40. Figure 2 Schematic diagram of the structure of a smart power cord provided by an embodiment of the present invention. As Figure 2 shown, a power consumption acquisition module and a LORA communication module are disposed inside the housing 201 of the smart power cord 20. One end thereof is connected to an electrical plug 202, and the other end is connected to a power input plug 203.

[0029] The usage process is as follows: Insert the electrical plug 202 of the smart power cord 20 into the electrical device 10, and insert the power input plug 203 into the power supply. At this time, the power consumption acquisition module inside the housing 201 of the smart power cord 20 will acquire the power consumption information of the electrical device and send it to the application server 40 through the LoRa communication module and the LoRa gateway 30, and the application server 40 executes the following embodiments.

[0030] Figure 3A flowchart of a method for detecting the status of an electrical device provided by an embodiment of the present invention is applied to an application server as shown in Figure 1 as shown. As shown in Figure 3 , the method for detecting the status of the electrical device includes:

[0031] Step S301: Receive the current power information sent by the intelligent power cord. The intelligent power cord is used to connect the electrical device to the power supply, and a power acquisition module is integrated on the intelligent power cord for acquiring the power information of the electrical device.

[0032] Specifically, the electrical device is connected to the power supply through the intelligent power cord. The power acquisition module integrated inside the housing of the intelligent power cord encodes the acquired power information (such as current, voltage, power, etc.) and sends it to the application server through the LORA communication module and the LoRa gateway; the application server decodes the encoded power information to obtain the current power information.

[0033] Step S302: Input the current power information into the clustering model and output the status category of the electrical device. The status of the electrical device includes at least one of the following: powered on, standby, powered off, and abnormal.

[0034] Specifically, the status of the electrical device includes multiple types: powered on, powered off, standby, and abnormal. Among them, in the powered-on state, the electrical device has a large and stable current, stable voltage, and a high power value, which is close to or equal to the rated power; in the powered-off state, the current, voltage, and power are all zero; in the standby state, it has a small current, stable voltage, and a small power value; in the abnormal state, the current, voltage, or power may fluctuate or exceed the normal range. In this step, the current power information is input into the clustering model to analyze which cluster centroid in the clustering model the current power information belongs to, and the status category of the electrical device corresponding to the cluster centroid is the current status category of the electrical device.

[0035] In some embodiments, after outputting the status category of the electrical device, it further includes: determining the distance between the current power information and the cluster centroid with the smallest distance in the clustering model; determining the credibility of the output result of the clustering model according to the distance.

[0036] Specifically, the Euclidean distance, Manhattan distance, or other distances between the current power information and the closest cluster centroid can be calculated, and the credibility is determined by the reciprocal of the distance, that is, the closer the distance, the higher the credibility.

[0037] In some embodiments, the method further includes: repeatedly executing the step of receiving the current power information sent by the smart power cord until a first preset duration, until obtaining the electrical device status category within the first preset duration; obtaining the power-on duration period corresponding to the electrical device status category being powered on within the first preset duration; or determining the usage rate of the electrical device according to the number of times the electrical device status category is powered on and powered off within the first preset duration.

[0038] Specifically, the first preset duration can be one day. By repeatedly executing the above steps, the power-on duration period of the electrical device within one day can be obtained; the usage rate of the electrical device can also be determined by counting the number of power-on and power-off times within one day.

[0039] The electrical device status detection method provided in this embodiment receives the current power information sent by the smart power cord. The smart power cord is used to connect the electrical device to the power supply, and a power collection module is integrated on the smart power cord for collecting the power information of the electrical device; inputting the current power information into the clustering model to output the electrical device status category, where the electrical device status includes at least one of the following: powered on, standby, powered off, abnormal; that is, obtaining the power information through the smart power cord of the electrical device, which reduces the risk of loss, cost, and operation complexity compared with traditional power monitoring devices or smart meters. At the same time, the efficiency of electrical device status detection is improved by using the clustering model.

[0040] On the basis of the foregoing embodiments, Figure 4 It is a schematic diagram of the training process of a clustering model provided by an embodiment of the present invention. As Figure 4 shown, before executing step S302, the following steps are further included:

[0041] Step S401: Obtain the first historical power information collected through the smart power cord and the corresponding first electrical device status category label, and the first historical power information and the first electrical device status category label constitute a data set.

[0042] Step S402: Perform clustering analysis on the data set to obtain the clustering model.

[0043] Specifically, the historical power information of the electrical device and the corresponding electrical device status category label can be obtained to form a data set; the clustering model is trained using this data set.

[0044] In some embodiments, the method further includes the following steps:

[0045] Step S403: Every second preset time interval, obtain the second historical power consumption information collected through the intelligent power cord and the corresponding second electrical device status category label, where the second historical power consumption information and the second electrical device status category label form a supplementary data set.

[0046] Step S404: Update the clustering model based on the supplementary data set.

[0047] Specifically, considering that the aging of electrical devices has a greater impact on the load of the electrical appliances, set a certain time interval, extract recent historical data to dynamically update the clustering model to ensure the dynamic effectiveness of the clustering model.

[0048] Based on the foregoing embodiments, by obtaining the first historical power consumption information collected through the intelligent power cord and the corresponding first electrical device status category label, the first historical power consumption information and the first electrical device status category label form a data set; perform clustering analysis on the data set to obtain the clustering model, so as to obtain a trained clustering model for detecting the status of electrical devices; also, every second preset time interval, obtain the second historical power consumption information collected through the intelligent power cord and the corresponding second electrical device status category label, where the second historical power consumption information and the second electrical device status category label form a supplementary data set; update the clustering model based on the supplementary data set; realize the real-time update of the clustering model, and avoid the detection error caused by the aging of electrical devices.

[0049] Based on the foregoing embodiments, Figure 5 is a flowchart of another electrical device status detection method provided by an embodiment of the present invention. As Figure 5 shown, it includes the following steps:

[0050] Step S501: Obtain the first historical power consumption information and the corresponding first electrical device status category label for multiple historical time periods within a historical duration, where the electrical device status includes at least one of the following: powered on, standby, powered off, and multiple abnormal types.

[0051] Specifically, the historical duration can be understood as a period of time in the past, such as the past day, and the historical time period can be understood as multiple shorter time periods divided within the past period of time, such as every minute. That is to say, the historical power consumption information (current, voltage, and power) of each minute within the past day is used as a sample, and its sample label, that is, the corresponding electrical device status, is determined. The electrical device status is divided into powered on, standby, powered off, and various abnormal types (such as short circuit, open circuit, overload, insulation, overvoltage, or undervoltage).

[0052] Step S502: Determine the corresponding historical time-power curve schematic diagram according to the first historical power consumption information of each historical time period.

[0053] Specifically, according to the current in each historical time period, a corresponding historical time-current curve is plotted; according to the voltage in each historical time period, a corresponding historical time-voltage curve is plotted; according to the power in each historical time period, a corresponding historical time-power curve is plotted.

[0054] Step S503: Perform clustering analysis on the multiple schematic diagrams of historical time-electric quantity curves to obtain a clustering model.

[0055] Specifically, perform clustering analysis on multiple samples (each sample includes a historical time-current curve, a historical time-voltage curve, a historical time-power curve, and the corresponding electrical equipment status category label) to obtain a clustering model. There are significant differences in the time-electric quantity curves of different types of electrical equipment status. For example, in the power-on state, the current remains at a relatively high stable value, the voltage remains stable, and the power remains close to the rated power value; in the standby state, the current remains at a relatively low stable value, the voltage remains stable, and the power remains at a relatively low stable value; in the power-off state, the current, voltage, and power all remain at zero; in the case of a short-circuit anomaly, the current suddenly increases, the voltage drops to near zero, and the power increases rapidly; in the case of an open-circuit anomaly, the current in the circuit is interrupted, the voltage remains at the supply voltage, and the power is zero; in the case of an overload fault, the current will exceed the rated current of the device, the voltage usually remains within the normal range, exceeding the rated power, and the power value will increase; in the case of an insulation fault, the current may fluctuate abnormally, the voltage usually remains within the normal range, and the power value may fluctuate or increase; in the case of overvoltage or undervoltage anomalies, the voltage will exceed or be lower than the normal range.

[0056] Step S504: Determine the reference time-electric quantity curve schematic diagram corresponding to each cluster in the clustering model.

[0057] Specifically, the reference time-current curve, reference time-voltage curve, and reference time-power curve that can represent the category of the cluster can be determined according to all the historical time-current curves, historical time-voltage curves, and historical time-power curves in each cluster.

[0058] Step S505: Receive the current electric quantity information corresponding to the current time period sent by the intelligent power supply, and determine the current time-electric quantity curve schematic diagram according to the current electric quantity information of the current time period.

[0059] Specifically, the current current, voltage, and power of the current time period of the intelligent power line can be received, and the corresponding current time-current curve, current time-voltage curve, and current time-power curve can be plotted.

[0060] Step S506: Calculate the similarity between the current time - power curve schematic diagram and each reference time - power curve schematic diagram in the clustering model, and determine that the cluster category corresponding to the reference time - power curve schematic diagram with the maximum similarity is the electrical device state of the electrical device in the current time period.

[0061] Specifically, the similarity between the current time - current curve, the current time - voltage curve, and the current time - power curve and the reference time - current curve, the reference time - voltage curve, and the reference time - power curve corresponding to each cluster can be calculated. This similarity is determined based on the power difference at the corresponding time points and the change trend of the overall curve. The cluster with the maximum similarity is determined as the electrical device state of the electrical device in the current time period.

[0062] Based on the foregoing embodiments, by analyzing the power information of the time period to detect the state of the electrical device, the error caused by relying only on the power information at time points is reduced. In addition, through the time - power curve graph, this embodiment can quickly identify different states of the electrical device, especially various abnormal types of states.

[0063] Figure 6 The following is a schematic structural diagram of an electrical device state detection device provided by an embodiment of the present invention, which is applied to an application server. As Figure 6 shown, the device includes:

[0064] A receiving module 601, configured to receive the current power information sent by the smart power cord. The smart power cord is used to connect the electrical device to the power supply, and a power acquisition module is integrated on the smart power cord to collect the power information of the electrical device.

[0065] A detection module 602, configured to input the current power information into the clustering model and output the electrical device state category. The electrical device state includes at least one of the following: powered on, standby, powered off, abnormal.

[0066] In some embodiments, the detection module 602 is further configured to:

[0067] Determine the distance between the current power information and the cluster centroid with the minimum distance in the clustering model;

[0068] Determine the credibility of the output result of the clustering model according to the distance.

[0069] In some embodiments, the device further includes a clustering module 603. The clustering module 603 is configured to obtain the first historical power information collected through the smart power cord and the corresponding first electrical device state category label. The first historical power information and the first electrical device state category label form a data set; perform clustering analysis on the data set to obtain the clustering model.

[0070] In some embodiments, the clustering module 603 is specifically configured to:

[0071] Obtain first historical power consumption information for a plurality of historical time periods within a historical duration and corresponding first electrical device status category labels;

[0072] Determine a corresponding historical time - power consumption curve schematic diagram according to the first historical power consumption information for each historical time period;

[0073] Perform clustering analysis on the plurality of historical time - power consumption curve schematic diagrams to obtain a clustering model;

[0074] Determine a reference time - power consumption curve schematic diagram corresponding to each cluster in the clustering model;

[0075] The receiving module 601 is specifically configured to:

[0076] Receive the current power consumption information corresponding to the current time period sent by the intelligent power supply, and determine a current time - power consumption curve schematic diagram according to the current power consumption information for the current time period;

[0077] The detection module 602 is specifically configured to:

[0078] Calculate the similarity between the current time - power consumption curve schematic diagram and each reference time - power consumption curve schematic diagram in the clustering model, and determine that the cluster category corresponding to the reference time - power consumption curve schematic diagram with the maximum similarity is the electrical device status of the electrical device in the current time period.

[0079] In some embodiments, the clustering module 603 is further configured to:

[0080] Every second preset duration, obtain second historical power consumption information collected through the intelligent power line and corresponding second electrical device status category labels, and the second historical power consumption information and the second electrical device status category labels form a supplementary data set;

[0081] Update the clustering model based on the supplementary data set.

[0082] In some embodiments, the receiving module 601 is further configured to repeatedly execute the step of receiving the current power consumption information sent by the intelligent power line until a first preset duration, until the detection module 602 obtains the electrical device status category within the first preset duration;

[0083] The detection module is further configured to obtain the boot duration period corresponding to the electrical device status category being powered on within the first preset duration;

[0084] Alternatively, the usage rate of the electrical device is determined according to the number of times the electrical device is in the on state and the off state within the first preset time period.

[0085] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working process and corresponding beneficial effects of the above-described electrical device state detection device can refer to the corresponding process in the foregoing method examples, and will not be elaborated herein.

[0086] Figure 7 The following is a schematic hardware structure diagram of an electronic device provided by an embodiment of the present invention. As Figure 7 shown, the electronic device includes: a processor 701, a communication interface 702, a memory 703, and a communication bus 704. Among them, the processor 701, the communication interface 702, and the memory 703 complete mutual communication through the communication bus 704.

[0087] The memory 703 is used to store computer programs.

[0088] In an embodiment of the present application, when the processor 701 executes the program stored on the memory 703, it implements the steps of the electrical device state detection method provided in any of the foregoing method embodiments.

[0089] The electronic device provided by the embodiment of the present application has the same implementation principle and technical effects as the above embodiment, and will not be elaborated herein.

[0090] The above-mentioned memory 703 can be an electronic memory such as flash memory, EEPROM (electrically erasable programmable read-only memory), EPROM, hard disk, or ROM. The memory 703 has a storage space for program codes for executing any method steps in the above methods. For example, the storage space for program codes can include respective program codes for implementing each step in the above methods. These program codes can be read from or written into one or more computer program products. These computer program products include program code carriers such as hard disks, optical discs (CDs), memory cards, or floppy disks. Such computer program products are usually portable or fixed storage units. The storage unit can have a storage segment or storage space arranged similarly to the memory 703 in the above electronic device. The program codes can be compressed in an appropriate form. Usually, the storage unit includes a program for executing the method steps according to the embodiments of the present application, that is, codes that can be read by a processor such as 701, and when these codes are run by the electronic device, the electronic device is caused to execute each step in the above-described method.

[0091] Embodiments of the present application also provide a computer-readable storage medium. A computer program is stored on the above-mentioned computer-readable storage medium, and when the computer program is executed by a processor, the steps of the electrical device state detection method described above are implemented.

[0092] The computer-readable storage medium may be included in the device / apparatus described in the above embodiments; it may also exist alone without being assembled into the device / apparatus. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method according to the embodiments of the present application is implemented.

[0093] According to the embodiments of the present application, the computer-readable storage medium may be a non-volatile computer-readable storage medium, for example, it may include but is not limited to: portable computer disks, hard disks, random access memories (RAMs), read-only memories (ROMs), erasable programmable read-only memories (EPROMs or flash memories), portable compact disk read-only memories (CD-ROMs), optical storage devices, magnetic storage devices, or any suitable combination of the above. In the present application, the computer-readable storage medium may be any tangible medium that contains or stores a program, and the program can be used by or in combination with an instruction execution system, device, or device.

[0094] It should be noted that in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover a non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "including a..." does not exclude the existence of additional identical elements in the process, method, article or device including the element.

[0095] The above are only specific embodiments of the present application, enabling those skilled in the art to understand or implement the present application. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A method for detecting the state of an electrical device, characterized in that: Applied to an application server, the method comprises: Receiving current power information sent by a smart power line, wherein the smart power line is used to connect the electrical device to a power source, and the smart power line is integrated with a power collection module for collecting power information of the electrical device; The current power information is input into a clustering model, and an electrical device status category is output, where the electrical device status includes at least one of the following: on, standby, off, and abnormal.

2. The method according to claim 1, characterized in that After the output of the electrical equipment status category, it also includes: Determine the distance between the current power information and the centroid of the cluster with the smallest distance in the clustering model; The credibility of the output result of the clustering model is determined according to the distance.

3. The method according to claim 2, characterized in that Before inputting the current power information into the clustering model, the method further includes: Acquire first historical power information collected through the smart power line and a corresponding first electrical device status category label, wherein the first historical power information and the first electrical device status category label constitute a data set; Performing cluster analysis on the data set to obtain the cluster model.

4. The method according to claim 3, characterized in that The abnormality in the state of the electrical device includes multiple abnormality types; the first historical power information collected through the smart power line and the corresponding first electrical device state category label are obtained, and the first historical power information and the first electrical device state category label constitute a data set, including: Acquire first historical power information of multiple historical time periods within a historical duration and corresponding first electrical equipment status category labels; Determine a corresponding historical time-electricity curve diagram according to the first historical electricity information of each historical time period; The performing cluster analysis on the data set to obtain the cluster model includes: Performing cluster analysis on the plurality of historical time-electricity curve schematic diagrams to obtain a cluster model; Determine a reference time-electricity curve schematic diagram corresponding to each cluster in the clustering model; The receiving the current power information sent by the smart power cord includes: Receive current power information corresponding to the current time period sent by the smart power supply, and determine a current time-power curve diagram according to the current power information of the current time period; The step of inputting the current power information into a clustering model and outputting the electrical equipment status category includes: The similarity between the current time-electricity curve diagram and each reference time-electricity curve diagram in the clustering model is calculated, and the cluster category corresponding to the reference time-electricity curve diagram with the greatest similarity is determined as the electrical device state of the electrical device in the current time period.

5. The method according to claim 3 or 4, characterized in that: The method further comprises: At intervals of a second preset time, obtaining second historical power information collected through the smart power line and a corresponding second electrical device status category label, wherein the second historical power information and the second electrical device status category label constitute a supplementary data set; The clustering model is updated based on the supplementary data set.

6. The method according to any one of claims 1 to 4, characterized in that: The method further comprises: Repeat the step of receiving the current power information sent by the smart power cord until the first preset time period, until the status category of the electrical device within the first preset time period is obtained; Obtaining a power-on duration period corresponding to the power-on status category of the electrical device within a first preset duration; Alternatively, the usage rate of the electrical device is determined according to the number of times the state category of the electrical device is turned on or off within the first preset time period.

7. An electrical equipment status detection device, characterized in that: Applied to an application server, the device comprises: A receiving module, used to receive current power information sent by a smart power line, wherein the smart power line is used to connect an electrical device to a power source, and the smart power line is integrated with a power collection module for collecting power information of the electrical device; The detection module is used to input the current power information into the clustering model and output the electrical device status category, where the electrical device status includes at least one of the following: power on, standby, power off, and abnormal.

8. The device according to claim 7, characterized in that The detection module is further used for: Determine the distance between the current power information and the centroid of the cluster with the smallest distance in the clustering model; The credibility of the output result of the clustering model is determined according to the distance.

9. An electronic device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; Memory, used to store computer programs; The processor is used to implement the steps of the electrical equipment status detection method described in any one of claims 1-6 when executing the program stored in the memory.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for detecting the state of an electrical device as described in any one of claims 1 to 6 are implemented.

Images