Method and device for determining electricity consumption of equipment, air conditioning system and electronic equipment

Abstract

The embodiment of the invention provides a method and device for determining electricity consumption of equipment, an air conditioning system and electronic equipment, and relates to the technical field of intelligent household appliances. The determination method comprises the following steps: acquiring multiple pieces of state data of equipment; determining a feature set of the equipment in the preset period according to the state data of the equipment in the preset period; determining energy consumption parameters of the equipment in a preset period according to the feature set and a preset classification model; and determining the power consumption of the equipment in the preset period according to the feature set and the energy consumption parameter. According to the method for determining the power consumption of the equipment provided by the embodiment of the invention, the corresponding energy consumption parameter is determined according to the feature set and the preset classification model, the obtained energy consumption parameter can represent the electric quantity deviation of the equipment in the preset period, and then the power consumption of the equipment is determined according to the energy consumption parameter and the feature set. And the obtained electricity consumption takes deviation caused by the equipment state into consideration, and is relatively accurate.

Description

Technical Field

[0001] The present application relates to the technical field of smart home appliances, and in particular to a method and device for determining power consumption of a device, an air conditioning system, and an electronic device. Background Art

[0002] In recent years, with the rapid development of the economy and society, various smart home appliances have been used more and more widely, such as water heaters, smart ovens, smart stoves, etc.

[0003] When using smart home appliances, users usually do not know how much electricity they have consumed, and are troubled by the inability to obtain electricity usage information.

[0004] In the related technology, electricity consumption is usually obtained by installing an electric meter or using a no-current and no-voltage solution. However, the cost of directly installing an electric meter is high; the no-current and no-voltage solution can only roughly estimate the electricity usage based on the rated operating power of the equipment combined with the usage time. The obtained electricity consumption has poor accuracy and is somewhat different from the actual electricity consumption. It is impossible to display accurate electricity consumption to users in real time. Therefore, how to more accurately determine the electricity consumption of the equipment has become a problem that needs to be solved urgently. Summary of the invention

[0005] The embodiments of the present application provide a method, device, air conditioning system and electronic device for determining the power consumption of a device, which are used to more accurately determine the power consumption of a device based on the status data of the device and a pre-set classification model.

[0006] In a first aspect, an embodiment of the present application provides a device for determining the power consumption of a device, the determination device comprising: an acquisition module for acquiring multiple status data of a device; a determination module for determining a feature set of the device within a preset period based on the status data of the device within the preset period; an input module for inputting the feature set into a pre-set classification model to obtain energy consumption parameters corresponding to the feature set; the determination module is also used to determine the power consumption of the device in the preset period based on the feature set and the energy consumption parameters.

[0007] The device for determining the power consumption of a device provided in the embodiment of the present application can determine the feature set of the device based on the status data of the device within a preset period, and then input the feature set into a preset classification model to obtain the energy consumption parameter corresponding to the feature set. Since the energy consumption parameter can characterize the power deviation of the device within the preset period, the power consumption of the device is determined based on the energy consumption parameter and the feature set, and the obtained power consumption takes into account the deviation caused by the device status and is more accurate.

[0008] In combination with the first implementation method of the first aspect, the acquisition module is also used to acquire multiple sample feature sets of the device, each sample feature set corresponds to an actual power quantity; the determination module is also used to determine the corresponding predicted power quantity based on the sample feature set; the determination module is also used to determine the energy consumption parameters corresponding to the sample feature set based on the relationship between the predicted power quantity and the actual power quantity; the determination device also includes: a training module, which is used to perform training based on multiple sample feature sets and corresponding energy consumption parameters to obtain a classification model.

[0009] In combination with the second implementation of the first aspect, the classification model is a random forest model.

[0010] In combination with the third implementation manner of the first aspect, the determination device also includes: a deletion module, used to delete status data including a target field in the multiple status data; the target field is an alarm field and / or an error field.

[0011] In combination with the fourth implementation method of the first aspect, the deletion module is also used to delete the status data of the target status field outside the corresponding preset range; the status data includes the target status field; and one target status field corresponds to one preset range.

[0012] In combination with the fifth implementation method of the first aspect, the determination device also includes: an aggregation module, used to aggregate power consumption according to preset dimensions to obtain target power consumption; the preset dimensions include at least one preset cycle; and an output module, used to output the target power consumption.

[0013] In a second aspect, an embodiment of the present application provides a method for determining the power consumption of a device, the determination method comprising: obtaining multiple status data of the device; determining a feature set of the device within a preset period based on the status data of the device within a preset period; inputting the feature set into a pre-set classification model to obtain energy consumption parameters corresponding to the feature set; determining the power consumption of the device in the preset period based on the feature set and the energy consumption parameters.

[0014] In combination with the first implementation method of the second aspect, before obtaining multiple status data of the device, the determination method also includes: obtaining multiple sample feature sets of the device, each sample feature set corresponds to an actual power quantity; determining the corresponding predicted power quantity based on the sample feature set; determining the energy consumption parameters corresponding to the sample feature set based on the relationship between the predicted power quantity and the actual power quantity; and training based on multiple sample feature sets and corresponding energy consumption parameters to obtain a classification model.

[0015] In combination with the second implementation method of the second aspect, the classification model is a random forest model.

[0016] In combination with the third implementation manner of the second aspect, after acquiring multiple status data of the device, the determination method also includes: deleting status data including a target field in the multiple status data; the target field is an alarm field and / or an error field.

[0017] In combination with the fourth implementation method of the second aspect, after deleting the status data including the target field in multiple status data, the determination method also includes: deleting the status data of the target status field outside the corresponding preset range; the status data includes the target status field; one target status field corresponds to a preset range.

[0018] In combination with the fifth implementation method of the second aspect, after determining the power consumption of the device within a preset period based on the feature set and energy consumption parameters, the determination method also includes: aggregating the power consumption according to preset dimensions to obtain target power consumption; the preset dimensions include at least one preset period; and outputting the target power consumption.

[0019] In a third aspect, an embodiment of the present application provides an air-conditioning system, comprising: an air-conditioning device and a processing device; the air-conditioning device is used to collect its own status data and send the status data to the processing device; the processing device is used to determine a feature set of the air-conditioning device within a preset period based on the status data of the air-conditioning device within the preset period; the processing device is also used to input the feature set into a pre-set classification model to obtain energy consumption parameters corresponding to the feature set; the processing device is also used to determine the power consumption of the device in the preset period based on the feature set and the energy consumption parameters.

[0020] In a fourth aspect, an embodiment of the present application provides an electronic device, comprising: one or more processors; one or more memories; wherein the one or more memories are used to store computer program codes, the computer program codes include computer instructions, and when the one or more processors execute the computer instructions, the electronic device executes the method for determining the power consumption of the device in the first aspect and any possible implementation method.

[0021] In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium, which includes computer instructions. When the computer instructions are controlled on a computer, the computer executes a method for determining the power consumption of any device provided in the first aspect and possible implementation methods.

[0022] In the sixth aspect, an embodiment of the present invention provides a computer program product, which can be directly loaded into a memory and contains software code. After being loaded and executed by a computer, the computer program product can implement a method for determining the power consumption of any device provided in the first aspect and possible implementation methods.

[0023] It should be noted that the above computer instructions may be stored in whole or in part on a computer-readable storage medium, wherein the computer-readable storage medium may be packaged together with the processor of the controller, or may be packaged separately from the processor of the controller, which is not limited in this application.

[0024] The beneficial effects described in the second to sixth aspects of the present application can be referred to the beneficial effect analysis of the first aspect and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The accompanying drawings are used to provide a further understanding of the technical solution of the present invention and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the technical solution of the present invention and do not constitute a limitation on the technical solution of the present invention.

[0026] Figure 1 A schematic diagram of the structure of a system for determining power consumption of equipment provided in an embodiment of the present application;

[0027] Figure 2 A method flow for determining the power consumption of a device provided in an embodiment of the present application Figure 1 ;

[0028] Figure 3 A method flow for determining the power consumption of a device provided in an embodiment of the present application Figure 2 ;

[0029] Figure 4 A schematic diagram of constructing a random forest model provided in an embodiment of the present application;

[0030] Figure 5 A method flow for determining the power consumption of a device provided in an embodiment of the present application Figure 3 ;

[0031] Figure 6 A method flow for determining the power consumption of a device provided in an embodiment of the present application Figure 4 ;

[0032] Figure 7 A method flow for determining the power consumption of a device provided in an embodiment of the present application Figure 5 ;

[0033] Figure 8 A method flow for determining the power consumption of a device provided in an embodiment of the present application Figure 6 ;

[0034] Fig. 9 An overall flow chart of a method for determining power consumption of a device provided in an embodiment of the present application;

[0035] Fig.10 A schematic diagram of the structure of a determination device provided in an embodiment of the present application;

[0036] Fig.11 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0037] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. 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 creative work are within the scope of protection of this application.

[0038] It should be noted that the terms "first" and "second" used in the embodiments of the present invention are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, the meaning of "plurality" is two or more.

[0039] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "connected" and "connection" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances. In addition, when describing a pipeline, the "connected" and "connection" used in this application have the meaning of conduction. The specific meaning needs to be understood in conjunction with the context.

[0040] In the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0041] As described in the background technology, the related technology usually adopts the installation of electric meters or the non-current and voltage scheme to obtain the power consumption. However, the cost of directly installing electric meters is high; the non-current and voltage scheme can only roughly estimate the power consumption based on the rated operating power of smart home appliances combined with the usage time. The power consumption obtained is less accurate and has a certain gap with the actual power consumption, and it is impossible to display the accurate power consumption to users in real time.

[0042] Based on this, the embodiment of the present application provides a method for determining the power consumption of a device, which can determine the feature set of the device based on the status data of the device in a preset period, and then input the feature set into a preset classification model to obtain the energy consumption parameter corresponding to the feature set. Then, based on the energy consumption parameter and the feature set, the power consumption of the device in the preset period is determined.

[0043] It can be seen that the embodiment of the present application provides a method for determining the power consumption of a device, which does not require an external electric meter for the device. The power consumption of the device can be calculated through the status data reported by the device and the pre-set classification model, and the cost is low. At the same time, a feature set is constructed for the status data reported by the device, and the energy consumption parameters corresponding to the preset period can be dynamically selected based on the feature set and the pre-set classification model, so that the calculated power consumption is more accurate.

[0044] It should be understood that the equipment in the embodiments of the present application may be air conditioning equipment, air treatment equipment, etc., and the embodiments of the present application do not impose any limitations on this.

[0045] For ease of description, the following description takes air conditioning equipment as an example.

[0046] The method for determining the power consumption of a device provided in the embodiment of the present application can be applied to Figure 1 The power consumption of the equipment shown is determined by the system. Figure 1 As shown, the device power consumption determination system 10 includes: a processing device 11, an air conditioning device 12 and a terminal device 13.

[0047] The processing device 11 may establish a connection with the air conditioning device 12 and the terminal device 13 via a wired network or a wireless network.

[0048] In the embodiment of the present application, the air conditioning device 12 is used to send its own status data to the processing device 11, so that the processing device 11 can manage the air conditioning device 12 based on the status data.

[0049] In the embodiment of the present application, the processing device 11 is used to determine the power consumption of the air-conditioning device in each preset cycle according to the status data sent by the air-conditioning device 12.

[0050] In the embodiment of the present application, the terminal device 13 is used to send instructions to the processing device 11 or the air-conditioning device 12 based on the user's operation, so that the processing device 11 or the air-conditioning device 12 executes the instruction.

[0051] For example, if a user wants to query the power consumption of the air conditioner in the target time period, the terminal device 13 performs certain operations based on the terminal device 13, and the terminal device 13 sends a query instruction for querying the power consumption in the target time period to the processing device 11. After receiving the instruction, the processing device 11 aggregates the power consumption according to the target time period, obtains the target power consumption, and returns it to the terminal device 13 for display, so that the user can query the target power consumption of the air conditioner 12 in the target time period based on the terminal device 13.

[0052] It should be noted that Figure 1The application scenario in which the device power consumption determination system only includes one air-conditioning device 12 and one terminal device 13 is shown for exemplary purposes only. In actual application, the fault type determination system may include multiple air-conditioning devices 12 and multiple terminal devices 13, and the embodiments of the present application do not impose any restrictions on this.

[0053] In some embodiments, the processing device 11 may be a server, and the embodiments of the present application do not limit the specific implementation of the server. The server may be a single server, or a server cluster composed of multiple servers. In some implementations, the server cluster may also be a distributed cluster.

[0054] In other embodiments, the processing device 11 may also be a computer device, and the embodiments of the present application do not impose any restrictions on the specific form of the computer device. For example, the computer device may specifically be a terminal device. Among them, the terminal device may be referred to as: terminal, user equipment (UE), terminal equipment, access terminal, user unit, user station, mobile station, remote station, remote terminal, mobile device, user terminal, wireless communication device, user agent or user device, etc. The terminal device may specifically be a mobile phone, augmented reality (AR) device, virtual reality (VR) device, tablet computer, laptop computer, ultra-mobile personal computer (UMPC), netbook, personal digital assistant (PDA), etc.

[0055] For example, in the embodiment of the present application, the terminal device 13 may be any form of mobile terminal, such as a mobile phone, a tablet computer, a desktop computer, a laptop computer, a handheld computer, a notebook computer, an ultra-mobile personal computer (UMPC), a netbook, a cellular phone, a personal digital assistant (PDA), an augmented reality (AR) or virtual reality (VR) device, etc.

[0056] It should be pointed out that Figure 1 The structure shown does not constitute a limitation on the device power consumption determination system. In other embodiments, the system may include fewer or more components than shown, or combine certain components, or arrange components differently, and the embodiments of the present application do not impose any limitation on this.

[0057] The method for determining the power consumption of a device provided in the embodiment of the present application is applicable to the processing device 11 in the above-mentioned system for determining the power consumption of a device 10. Figure 2 The method for determining the power consumption of a device provided in the embodiment of the present application comprises the following steps:

[0058] S201. Obtain multiple status data of a device.

[0059] The processing device obtains multiple status data of the device. As a feasible implementation method, during operation, the device will report the status data of the device to the processing device 101 so that the processing device 101 can manage the device.

[0060] Exemplarily, the status data may include: device type, indoor ambient temperature, outdoor ambient temperature, set temperature, set working mode, voltage, current, frequency, working period and season. The status data is used to characterize the current environmental status and working status of the device.

[0061] S202: Determine a feature set of the device within a preset period according to the status data of the device within a preset period.

[0062] It should be understood that the preset period is pre-set, and in the actual application process, the preset period can be set according to the needs, and the embodiment of the present application does not impose any limitation on this. For example, as a feasible implementation method, the preset period can be 15 minutes, and the feature set of the device within 15 minutes is determined based on the status data of the device within 15 minutes.

[0063] The state data of the device within the preset period, that is, the state data sent by the device is divided according to time, so that the state data within each preset period is a group. Since the state data can represent the instantaneous environmental state and working state of the device, it cannot be used to represent an average state of the device within the period, so it is necessary to determine the feature set of the device within the preset period based on the state data of the device within the preset period.

[0064] It should be understood that the feature set is used to represent the average state of the device within the preset period.

[0065] As a feasible implementation, the feature set may include multiple device status features, such as device type, average indoor temperature, average outdoor temperature, average set temperature, set working mode, average voltage, and average current.

[0066] For example, please refer to Table 1, which is a feature set provided in an embodiment of the present application:

[0067] Table 1

[0068] Equipment Type and Category Current time Current month, season Device time zone Average current Average voltage Average indoor temperature Average outdoor temperature Average set temperature Average exhaust temperature Up and down wind status Working Mode Power on / off status

[0069] As a feasible implementation method, the average current, average voltage, average indoor temperature, average outdoor temperature, etc. in the feature set are the average values ​​of the current, voltage, indoor temperature, and outdoor temperature of multiple state data within a preset period. In this way, the feature set can represent the average state of the device within the preset period.

[0070] S203: Input the feature set into a pre-set classification model to obtain energy consumption parameters corresponding to the feature set.

[0071] Since the status data reported by the device is usually the status data input to the device, that is, the device status characteristics in the feature set are the status characteristics input to the device (such as current and voltage), and the device consumes power during operation, the power consumption obtained only based on the device status characteristics in the feature set is not accurate.

[0072] Based on this, the method for determining the power consumption of a device provided in the embodiment of the present application classifies the feature set according to a preset classification model before determining the power consumption of the device to obtain energy consumption parameters corresponding to the feature set. That is, before S201, the classification model to be used needs to be determined.

[0073] In some embodiments, the device can be connected to an electric meter and run for a period of time to obtain sample status data of the device and the corresponding actual power consumption. Then, a classification model is trained based on the sample status data and the corresponding actual power consumption.

[0074] As a possible implementation, see Figure 3 , the determination method provided in the embodiment of the present application further includes the following steps:

[0075] S301. Acquire multiple sample feature sets of a device, each sample feature set corresponding to an actual power quantity.

[0076] After obtaining the sample status data and the corresponding actual power, multiple sample feature sets of the device can be determined according to the sample status data, so that each sample feature set corresponds to an actual power.

[0077] As a feasible implementation method, the sample feature sets of the sample status data can be extracted according to the multiple granularities such as 0.2kwh, 0.5kwh, 1kwh, etc. of the actual power consumption, to obtain multiple sample feature sets and the corresponding actual power consumption.

[0078] S302: Determine the corresponding predicted power according to the sample feature set.

[0079] As a feasible implementation method, the sample feature set includes current, voltage and time, and the predicted power can be determined according to the following formula (1):

[0080]

[0081] Among them, Q1 is the predicted power, the unit is kwh; U is the voltage, the unit is volt (V), represented by the symbol "V"; I is the current, the unit is ampere (A), represented by the symbol "A"; T is the time, the unit is second.

[0082] Based on formula (1), the predicted power consumption corresponding to the sample feature set can be obtained, that is, the theoretical power consumption of the device under the operating state of the sample feature set.

[0083] S303: Determine energy consumption parameters corresponding to the sample feature set based on the relationship between the predicted power and the actual power.

[0084] After the predicted power consumption corresponding to the sample feature set is obtained, the energy consumption parameters corresponding to the sample feature set can be determined based on the relationship between the actual power consumption and the predicted power consumption.

[0085] As a feasible implementation method, the energy consumption parameters can be determined according to the following formula (2):

[0086]

[0087] Among them, ρ is the energy consumption parameter; Q2 is the actual power; Q1 is the predicted power.

[0088] It can be seen that the energy consumption parameter is the error between the actual power consumption and the theoretical power consumption (predicted power consumption) of the equipment under the operating state of the sample feature set.

[0089] S304: Perform training according to multiple sample feature sets and corresponding energy consumption parameters to obtain a classification model.

[0090] After obtaining the energy consumption parameters corresponding to the sample feature sets, multiple sample feature sets and their corresponding energy consumption parameters are used as sample data for model training to obtain a classification model, so that each type of feature set corresponds to an energy consumption parameter.

[0091] As a feasible implementation method, the classification model is a random forest model.

[0092] The Random Forest (RF) model is a classic bagging model, whose weak learner is a decision tree model. The Random Forest model refers to building a forest using a random sampling method, where random refers to random sampling to build a model; the forest refers to it consisting of many independent decision trees.

[0093] The random forest model follows the two basic principles of "data randomness" and "feature randomness" when establishing each decision tree, which can ensure the generalization ability of the model. The random forest model can handle a large amount of input feature data without the need for dimensionality reduction and is not prone to overfitting. It has good adaptability to situations where the dimensions of the device state features in the feature set of the embodiment of the present application are clear and the data is limited.

[0094] See also Figure 4 , when training the random forest model, the main steps include:

[0095] S401. Randomly sample from the training sample set with replacement to obtain n sampling sample sets.

[0096] The training sample set is the feature set and corresponding energy consumption parameters provided in the above embodiment.

[0097] S402: Randomly select K features from each training data set and build n decision trees.

[0098] Among them, K is smaller than the total number of features in the training sample set, that is, the number of features (device status features) in the feature set.

[0099] For example, suppose there are 1000 training sample sets, and 1000 data are randomly extracted with replacement to form a sample set. Then a decision tree (weak learner) is trained based on the sample set. After n random extractions with replacement, n decision trees trained by n sample sets can be obtained at the end of training.

[0100] In some embodiments, after the random forest model is trained, when the random forest model is subsequently used for prediction, a more accurate and reasonable final prediction result can be obtained based on the prediction results of the n decision trees and in accordance with the principle of "the minority obeys the majority".

[0101] As a possible implementation, see Figure 5 , S203 may specifically include the following steps:

[0102] S501. Apply each decision tree to predict the energy consumption parameters corresponding to the feature set, and save all the energy consumption parameters.

[0103] S502: Vote for all energy consumption parameters, calculate the number of votes for each energy consumption parameter, and select the energy consumption parameter with the highest number of votes.

[0104] It can be seen that the random forest model reduces the overfitting risk of a single decision tree by combining multiple decision trees, improves the accuracy of classification, and can obtain more accurate energy consumption parameters and calculate more accurate power consumption.

[0105] S204: Determine the power consumption of the device in a preset period according to the feature set and the energy consumption parameters.

[0106] After the energy consumption parameters corresponding to the feature set are obtained, the power consumption of the device in a preset period can be determined based on the feature set and the energy consumption parameters.

[0107] As a feasible implementation method, the power consumption can be determined according to the following formula (3):

[0108]

[0109] Among them, Q3 is the power consumption, U is the voltage in the feature set, the unit is V; I is the current in the feature set, the unit is A; T is the total time of the preset cycle, the unit is S.

[0110] It can be seen that the embodiment of the present application provides a method for determining the power consumption of a device. There is no need to connect the device to an electricity meter separately. A more accurate power consumption can be calculated based on the status data reported by the device, the current and voltage in the status data, and a preset classification model.

[0111] The beneficial effects of the present application are described below with reference to specific examples.

[0112] For devices of different device types, 10 devices are respectively selected, and the power consumption is calculated using the determination method provided in the embodiment of the present application and the original calculation method. The results obtained are shown in Table 2:

[0113] Table 2

[0114]

[0115] It can be seen that the method for determining the power consumption of the device provided in the embodiment of the present application has a smaller error between the calculated power and the actual power, while the error calculated by the original calculation method is larger. Therefore, the method for determining the power consumption of the device provided in the embodiment of the present application is more accurate.

[0116] In some embodiments, when a device reports status data, it may report multiple status data in 1 minute, and there may be abnormal data in the reported status data, such as the temperature sensor cannot detect the temperature and returns an error (ERROR). In order to prevent abnormal data from affecting the calculation of power consumption, it is necessary to filter the status data reported when the device is abnormal.

[0117] As a possible implementation, see Figure 6 After S201, the determination method provided in the embodiment of the present application further includes:

[0118] S601: Delete status data including a target field from a plurality of status data.

[0119] The target field is an alarm field and / or an error field.

[0120] It should be understood that the status data includes multiple status fields, each of which is used to characterize a status of the device, such as current, voltage, etc. When the device is in an abnormal state, the alarm information or the field content of the related field reported will be ERROR, that is, the status field will contain device alarm and / or ERROR related fields, and at this time, the status field is determined to be an alarm field and / or an error field.

[0121] Deleting status data including an alarm field and / or an error field can avoid the influence of abnormal status data on subsequent steps, resulting in inaccurate calculation of power consumption, thereby improving the accuracy of calculating the power consumption of the device.

[0122] In some embodiments, since the status fields such as current, voltage, and temperature in the status data all need to be detected by sensors, the data detected by the sensors during operation are not all accurate. The values ​​detected at a certain moment may have large deviations, resulting in excessive overall deviations.

[0123] As a possible implementation, see Figure 7 After S601, the determination method provided in the embodiment of the present application further includes:

[0124] S701, deleting the status data of the target status field that is outside the corresponding preset range.

[0125] The status data includes a target status field; one target status field corresponds to one preset range.

[0126] It should be understood that the preset range is pre-set, and one target state field corresponds to one preset range. In the actual application process, it can be set according to the needs, and the embodiment of the present application does not impose any restrictions on this. For example, as a feasible implementation method, the target state field includes current, voltage, and temperature. The preset range corresponding to the current is 2A~6A, the preset range corresponding to the voltage is 200V~240V, and the preset range corresponding to the temperature is 0℃~40℃.

[0127] The state data includes multiple state fields, some of which are irrelevant to the extracted feature set, such as device type, device category, etc. Some state fields are closely related to the feature set, such as current, voltage, temperature, humidity, etc. If these state fields have large deviations, the obtained feature set will also have large deviations, so it is necessary to limit the value range of these state fields.

[0128] The status data of the target status field outside the corresponding preset range is deleted to avoid the situation in which the status field with large deviation leads to large deviation of the feature set when the feature set is extracted later. This can ensure the accuracy of the obtained feature set and further ensure the accuracy of the calculated power consumption.

[0129] In some embodiments, since the units of some status fields in the status data reported by the device may be non-standard units, such as the unit of time may be milliseconds (ms), in order to avoid problems in subsequent calculations caused by inconsistent units, as a feasible implementation method, the determination method provided in the embodiment of the present application also includes: converting the units of the usage status field in the status data.

[0130] It should be understood that the usage status field includes temperature, humidity, current, voltage, etc. Converting the units of the usage status field can avoid problems in subsequent calculations caused by inconsistent units.

[0131] In some embodiments, since the power consumption of a device is calculated according to a preset period, when a user views the power consumption of a device, he needs to check it according to the dimensions he needs, such as checking the power consumption of the device for one day.

[0132] As a possible implementation, see Figure 8 After S204, the determination method provided in the embodiment of the present application further includes:

[0133] S801. Aggregate power consumption according to preset dimensions to obtain target power consumption.

[0134] The preset dimension includes at least one preset period.

[0135] It should be understood that the preset dimensions are used to be set based on the terminal device, such as daytime dimension, night dimension, season dimension, etc. When the user needs to query the power consumption of the device within the preset dimension, he needs to operate on the terminal device so that the terminal device sends a query instruction to the processing device. When the processing device receives the query instruction, it aggregates the power consumption according to the preset dimensions included in the query instruction to obtain the corresponding target power consumption within the preset dimension.

[0136] S802: Output target power consumption.

[0137] The processing device outputs the target power consumption to the terminal device, so that the user can check the target power consumption on the terminal device.

[0138] It can be seen that aggregating the power consumption of devices according to the preset dimensions required by users can provide users with rich power query solutions and satisfy their usage experience.

[0139] In some embodiments, see Fig. 9The overall process of the method for determining the power consumption of a device provided in the embodiment of the present application includes the following steps:

[0140] S901, collecting device status.

[0141] The device sends its status data to the processing device.

[0142] S902: Preprocessing.

[0143] After receiving the status data reported by the device, the processing device preprocesses the status data. The preprocessing mainly includes: filtering abnormal status data (including status data of device alarm and ERROR related fields); limiting the range of status field values ​​required for obtaining feature vectors, and deleting abnormal states outside the range.

[0144] S903: Extract corresponding features to obtain a feature set.

[0145] The device status features are extracted from the status data within a preset period to obtain a feature set.

[0146] As a feasible implementation method, the processing equipment can use 15 minutes as a preset cycle to obtain a feature set for the status data within the cycle. The feature set includes: equipment type, average indoor and outdoor ambient temperature, set temperature average, set working mode, voltage, current, frequency, working hours and season.

[0147] S904. Use the random forest model to obtain energy consumption parameters.

[0148] The feature set is input into the random forest model to obtain the corresponding energy consumption parameters.

[0149] S905: Calculate the power consumption within the cycle.

[0150] Calculate the power consumption of the device within the preset period based on the feature set and energy consumption parameters.

[0151] S906: Aggregate and obtain electricity consumption in different dimensions.

[0152] According to the preset dimensions of user needs, electricity consumption is aggregated to obtain electricity consumption in different dimensions.

[0153] S907. Display power consumption.

[0154] The present application also provides a device for determining the power consumption of a device. Fig.10The determination device 100 includes: an acquisition module 101, used to acquire multiple status data of the device; a determination module 102, used to determine the feature set of the device within a preset period according to the status data of the device within the preset period; an input module 103, used to input the feature set into a preset classification model to obtain energy consumption parameters corresponding to the feature set; the determination module 102 is also used to determine the power consumption of the device in the preset period according to the feature set and the energy consumption parameters.

[0155] As a feasible implementation method, the acquisition module 101 is also used to acquire multiple sample feature sets of the device, each sample feature set corresponds to an actual power consumption; the determination module 102 is also used to determine the corresponding predicted power consumption based on the sample feature set; the determination module 102 is also used to determine the energy consumption parameters corresponding to the sample feature set based on the relationship between the predicted power consumption and the actual power consumption; the determination device 100 provided in the embodiment of the present application also includes: a training module, which is used to perform training based on multiple sample feature sets and corresponding energy consumption parameters to obtain a classification model.

[0156] As a feasible implementation method, the classification model is a random forest model.

[0157] As a feasible implementation method, the determination device 100 provided in the embodiment of the present application also includes: a deletion module, which is used to delete the status data including the target field in the multiple status data; the target field is an alarm field and / or an error field.

[0158] As a feasible implementation method, the deletion module is also used to delete the status data of the target status field outside the corresponding preset range; the status data includes the target status field; and one target status field corresponds to one preset range.

[0159] As a feasible implementation method, the determination device 100 provided in the embodiment of the present application also includes: an aggregation module, which is used to aggregate power consumption according to preset dimensions to obtain target power consumption; the preset dimensions include at least one preset cycle; and an output module, which is used to output the target power consumption.

[0160] The present application also provides an electronic device. Fig.11 The electronic device 110 includes: one or more memories 111; one or more processors 112, wherein the one or more memories 111 are used to store computer program codes, and the computer program codes include computer instructions; when the one or more processors 112 execute the computer instructions, the electronic device 110 executes the method for determining the high-frequency trajectory of the vehicle provided in the above embodiment.

[0161] Optionally, the memory 111 may be a non-temporary computer-readable storage medium, for example, the non-temporary computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a CD-ROM, a tape, a floppy disk, and an optical data storage device, etc. The embodiments of the present application do not impose any restrictions on this.

[0162] The processor 112 may be a central processing unit (CPU), a general-purpose processor, a network processor (NP), a digital signal processor (DSP), a microprocessor, a microcontroller, a programmable logic device (PLD), or any combination thereof, and the embodiments of the present application do not impose any limitation on this.

[0163] The embodiments of the present application also provide a computer program product including one or more instructions, where the one or more instructions are stored in a memory of a computer device and executed by a processor to complete the various processes of the above embodiments.

[0164] An embodiment of the present application also provides a computer-readable storage medium, which includes computer-executable instructions. When the computer-executable instructions are executed on a computer, the computer executes the method for determining the high-frequency trajectory of a vehicle provided in the above embodiment.

[0165] Through the description of the above implementation methods, technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0166] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0167] The units described as separate components may or may not be physically separated, and the components shown as units may be one physical unit or multiple physical units, that is, they may be located in one place or distributed in multiple different places. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0168] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0169] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a device (which may be a single-chip microcomputer, etc.) or a processor (processor) to perform all or part of the steps of each embodiment method of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard drives, ROM, RAM, magnetic disks or optical disks.

[0170] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto, and any changes or substitutions within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A device for determining the power consumption of equipment, characterized in that: The determining device comprises: An acquisition module is used to obtain multiple status data of the device; A determination module, configured to determine a feature set of the device within a preset period according to state data of the device within the preset period; An input module, used to input the feature set into a preset classification model to obtain energy consumption parameters corresponding to the feature set; The determination module is further used to determine the power consumption of the device in the preset period according to the feature set and the energy consumption parameter.

2. The determination device according to claim 1, characterized in that: The acquisition module is further used to acquire multiple sample feature sets of the device, each of which corresponds to an actual power quantity; The determination module is further used to determine the corresponding predicted power according to the sample feature set; The determination module is further used to determine the energy consumption parameter corresponding to the sample feature set according to the relationship between the predicted power and the actual power; The determination device also includes: a training module, which is used to perform training according to the multiple sample feature sets and the corresponding energy consumption parameters to obtain the classification model.

3. A method for determining the power consumption of a device, characterized in that: The determination method comprises: Get multiple status data of the device; Determining a feature set of the device within the preset period according to the state data of the device within the preset period; Inputting the feature set into a pre-set classification model to obtain energy consumption parameters corresponding to the feature set; The power consumption of the device in the preset period is determined according to the feature set and the energy consumption parameter.

4. The determination method according to claim 3, characterized in that: Before acquiring the plurality of status data of the device, the determination method further includes: Acquire multiple sample feature sets of the device, each of the sample feature sets corresponding to an actual power quantity; Determining a corresponding predicted power according to the sample feature set; Determining energy consumption parameters corresponding to the sample feature set according to the relationship between the predicted power and the actual power; The classification model is obtained by training based on the multiple sample feature sets and the corresponding energy consumption parameters.

5. The determination method according to claim 4, characterized in that: The classification model is a random forest model.

6. The determination method according to any one of claims 3 to 5, characterized in that: After acquiring the plurality of status data of the device, the determination method further comprises: Delete the status data including the target field in the multiple status data; the target field is an alarm field and / or an error field.

7. The determination method according to claim 6, characterized in that: After deleting the status data including the target field in the plurality of status data, the determination method further includes: Delete the status data of the target status field outside the corresponding preset range; the status data includes the target status field; one target status field corresponds to one preset range.

8. The determination method according to claim 7, characterized in that: After determining the power consumption of the device within the preset period according to the feature set and the energy consumption parameter, the determination method further includes: Aggregating the power consumption according to a preset dimension to obtain a target power consumption; the preset dimension includes at least one preset period; The target power consumption is output.

9. An air conditioning system, characterized in that: include: air conditioning and treatment equipment; The air conditioning device is used to collect its own status data and send the status data to the processing device; The processing device is used to determine a feature set of the air-conditioning device in the preset period according to the state data of the air-conditioning device in the preset period; The processing device is also used to input the feature set into a preset classification model to obtain energy consumption parameters corresponding to the feature set; The processing device is also used to determine the power consumption of the air-conditioning device in the preset period according to the feature set and the energy consumption parameter.

10. An electronic device, characterized in that: include: one or more processors; one or more memories; Among them, one or more memories are used to store computer program codes, and the computer program codes include computer instructions. When one or more processors execute the computer instructions, the electronic device executes the method for determining the power consumption of the device as described in any one of claims 3 to 8.

Images