User electricity consumption portrait generation method and device based on single-phase intelligent electric energy meter

Abstract

The invention provides a user electricity consumption portrait generation method and device based on a single-phase intelligent electric energy meter, and the method comprises the steps: obtaining the active power collected by each single-phase intelligent electric energy meter (i.e., each family) and the timestamp of the active power; according to the active power and the timestamp, features used for describing the power consumption condition of the user in different dimensions are obtained, in order to reduce the influence of large-order-of-magnitude features on the accuracy of the user portrait, data standardization processing is carried out on each feature, and then according to the standardized features, which preset power consumption portrait label has the closest probability to the user is judged. By means of the method, the user electricity consumption portrait of the user can be determined relatively accurately, and therefore a recommendation basis is provided for follow-up product recommendation.

Description

Technical Field

[0001] This application relates to the field of computer technology, and more specifically, to a method and apparatus for generating user electricity consumption profiles based on single-phase smart meters. Background Technology

[0002] With the rapid development of technology, user electricity consumption profiling plays an indispensable role in the power industry's precision marketing, data application, user analysis, and data analytics. Currently, the power industry offers a wide variety of products, such as peak-valley electricity pricing packages, electric vehicle charging discount packages, and smart home electricity packages. Different products have different business scenarios, and different business scenarios have different needs for user profiling. Therefore, accurately describing user electricity consumption profiles is a pressing issue that needs to be addressed. Summary of the Invention

[0003] In view of this, embodiments of this application provide a method and apparatus for generating user electricity consumption profiles based on single-phase smart meters, so as to obtain user electricity consumption profiles.

[0004] In a first aspect, embodiments of this application provide a method for generating a user electricity consumption profile based on a single-phase smart meter, the method comprising: For each single-phase smart energy meter, obtain the active power and the timestamp of the active power collected by the single-phase smart energy meter according to a preset cycle; For each single-phase smart energy meter, based on the active power and timestamps collected by the single-phase smart energy meter that have a corresponding relationship, the following characteristics are obtained: the first characteristic corresponding to the average consumption level of the user of the single-phase smart energy meter, the second characteristic corresponding to the peak electricity consumption, the third characteristic corresponding to the concentration of electricity consumption, the fourth characteristic corresponding to the stability of electricity consumption, the fifth characteristic corresponding to the stability of electricity consumption, and the sixth characteristic corresponding to the main activity period. The data is standardized for each feature using the following formula to obtain the standard feature for each feature: F x标 =(F x -U x ) / T x ; Among them, F x Let x be the characteristic corresponding to this single-phase smart energy meter, and U be the characteristic of the meter. x The mean of characteristic x corresponding to all single-phase smart energy meters, T x There is a standard deviation of feature x corresponding to a single-phase smart energy meter, and feature x includes the first to sixth features; The single-phase smart energy meter belongs to the following category based on the formula below. j The probability of a preset electricity consumption profile label; ; in,j Indicates the first j There are three preset electricity consumption profile labels, where x is the input feature. This indicates that, given the first to sixth characteristics, the single-phase smart energy meter belongs to the [specific category]. j The probability of a preset electricity consumption profile label. e It is a natural constant. For the first j Preset scores for each preset electricity consumption profile tag; The preset scores for all preset electricity consumption profile tags, The number of preset electricity consumption profile tags; According to the classification of this single-phase smart energy meter, it belongs to the [number]. j The probability of each preset electricity consumption profile label is used to determine the user's electricity consumption profile for the single-phase smart energy meter. The preset electricity consumption profile label with the highest probability is used as the user's electricity consumption profile for the user.

[0005] Secondly, embodiments of this application provide a user electricity consumption profile generation device based on a single-phase smart energy meter, the device comprising: The acquisition unit is used to acquire the active power and the timestamp of the active power collected by each single-phase smart energy meter according to a preset cycle. The processing unit is used to obtain, for each single-phase smart energy meter, a first feature corresponding to the average consumption level of the user of the single-phase smart energy meter, a second feature corresponding to the peak electricity consumption, a third feature corresponding to the concentration of electricity consumption, a fourth feature corresponding to the stability of electricity consumption, a fifth feature corresponding to the stability of electricity consumption, and a sixth feature corresponding to the main activity period, based on the active power and timestamp collected by the single-phase smart energy meter that have a corresponding relationship. The first calculation unit is used to standardize the data for each feature according to the following formula to obtain the standard feature corresponding to each feature: F x标 =(F x -U x ) / T x ; Among them, F x Let x be the characteristic corresponding to this single-phase smart energy meter, and U be the characteristic of the meter. x The mean of characteristic x corresponding to all single-phase smart energy meters, T x There is a standard deviation of feature x corresponding to a single-phase smart energy meter, and feature x includes the first to sixth features; The second calculation unit is used to calculate whether the single-phase smart energy meter belongs to the first generation according to the following formula. j The probability of a preset electricity consumption profile label; ; in, j Indicates the firstj There are three preset electricity consumption profile labels, where x is the input feature. This indicates that, given the first to sixth characteristics, the single-phase smart energy meter belongs to the [specific category]. j The probability of a preset electricity consumption profile label. e It is a natural constant. For the first j Preset scores for each preset electricity consumption profile tag; The preset scores for all preset electricity consumption profile tags, The number of preset electricity consumption profile tags; The determining unit is used to determine whether the single-phase smart energy meter belongs to the first... j The probability of each preset electricity consumption profile label is used to determine the user's electricity consumption profile for the single-phase smart energy meter. The preset electricity consumption profile label with the highest probability is used as the user's electricity consumption profile for the user.

[0006] The technical solution provided in this application includes, but is not limited to, the following beneficial effects: In this application, after obtaining the active power and the timestamp of active power collected by each single-phase smart energy meter (i.e., each household), features for describing the user's electricity consumption in different dimensions are obtained based on the active power and the timestamp. In order to reduce the impact of a large number of features on the accuracy of the user profile, each feature is standardized. Then, based on the standardized features, it is determined which preset electricity consumption profile label the user is most likely to be associated with, so that the preset electricity consumption profile label that is most similar to the user is used as the user's electricity consumption profile. Through the above method, the user's electricity consumption profile can be determined relatively accurately, thereby providing a basis for subsequent product recommendations.

[0007] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0008] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0009] Figure 1 A flowchart illustrating a method for generating user electricity consumption profiles based on a single-phase smart energy meter, provided in an embodiment of this application; Figure 2 This is a schematic diagram of a user electricity consumption profile generation device based on a single-phase smart energy meter, provided in an embodiment of this application. Detailed Implementation

[0010] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0011] Figure 1 This is a flowchart illustrating a method for generating user electricity consumption profiles based on single-phase smart meters, as provided in an embodiment of this application. Figure 1 As shown, the method for generating this user electricity consumption profile includes: Step 101: For each single-phase smart energy meter, obtain the active power and the timestamp of the active power collected by the single-phase smart energy meter according to the preset cycle.

[0012] Step 102: For each single-phase smart energy meter, based on the active power and timestamps collected by the single-phase smart energy meter that have a corresponding relationship, obtain the first feature corresponding to the average consumption level of the user of the single-phase smart energy meter, the second feature corresponding to the peak electricity consumption, the third feature corresponding to the concentration of electricity consumption, the fourth feature corresponding to the stability of electricity consumption, the fifth feature corresponding to the stability of electricity consumption, and the sixth feature corresponding to the main activity period.

[0013] Step 103: Standardize the data for each feature according to the following formula to obtain the standard feature corresponding to each feature: F x标 =(F x -U x ) / T x Formula 1 Among them, F x Let x be the characteristic corresponding to this single-phase smart energy meter, and U be the characteristic of the meter. x The mean of characteristic x corresponding to all single-phase smart energy meters, T x There is a standard deviation of feature x corresponding to a single-phase smart energy meter, and feature x includes the first to sixth features.

[0014] Step 104: Calculate the category of this single-phase smart energy meter according to the following formula (Formula 2). j The probability of a preset electricity consumption profile label; Formula 2 in, j Indicates the first j There are three preset electricity consumption profile labels, where x is the input feature. This indicates that, given the first to sixth characteristics, the single-phase smart energy meter belongs to the [specific category]. j The probability of a preset electricity consumption profile label. e It is a natural constant. For the first j Preset scores for each preset electricity consumption profile tag; The preset scores for all preset electricity consumption profile tags, The preset number of electricity consumption profile tags.

[0015] Step 105: Based on the fact that this single-phase smart energy meter belongs to the [number] [section / type], j The probability of each preset electricity consumption profile label is used to determine the user's electricity consumption profile for the single-phase smart energy meter. The preset electricity consumption profile label with the highest probability is used as the user's electricity consumption profile for the user.

[0016] Specifically, single-phase smart meters have become widespread in most households. Single-phase smart meters have a high data collection frequency, the collected data is relatively accurate, and they have certain data processing capabilities. The user electricity profile generation method involved in this application can run on a single-phase smart meter or on a cloud server, wherein the cloud server and the single-phase smart meter can communicate remotely.

[0017] A single-phase smart meter can collect relevant data on user electricity consumption according to a preset cycle, such as current current, voltage, active power, and the timestamp corresponding to each data point. After obtaining the active power and timestamp of the single-phase smart meter, the following characteristics can be obtained to represent the average consumption level of the user of the single-phase smart meter: a first characteristic corresponding to the peak electricity consumption, a second characteristic corresponding to the peak electricity consumption, a third characteristic corresponding to the concentration of electricity consumption, a fourth characteristic corresponding to the stability of electricity consumption, a fifth characteristic corresponding to the stability of electricity consumption, and a sixth characteristic corresponding to the main activity period.

[0018] After obtaining the above six features, to avoid a feature having a relatively large value that could lead to misjudgment in determining the user profile and thus insufficient accuracy of the determined user electricity consumption profile, it is necessary to standardize each feature to obtain the standard feature corresponding to each feature. Then, formula two is used to calculate which single-phase smart energy meter belongs to which category? jThe probability of a preset electricity consumption profile label is calculated, and the electricity consumption profile label with the highest probability is taken as the user electricity consumption profile of the single-phase smart meter. This results in the user electricity consumption profile (i.e., household) corresponding to the single-phase smart meter. The above method can determine the user electricity consumption profile corresponding to each household, so that products, services or information can be recommended or pushed based on the user electricity consumption profile. The user electricity consumption profile enables accurate content push.

[0019] In this application, after obtaining the active power and the timestamp of active power collected by each single-phase smart energy meter (i.e., each household), features for describing the user's electricity consumption in different dimensions are obtained based on the active power and the timestamp. In order to reduce the impact of a large number of features on the accuracy of the user profile, each feature is standardized. Then, based on the standardized features, it is determined which preset electricity consumption profile label the user is most likely to be associated with, so that the preset electricity consumption profile label that is most similar to the user is used as the user's electricity consumption profile. Through the above method, the user's electricity consumption profile can be determined relatively accurately, thereby providing a basis for subsequent product recommendations.

[0020] In a feasible implementation, when obtaining the first feature corresponding to the average consumption level of the user of the single-phase smart meter based on the corresponding active power and timestamp collected by the single-phase smart meter, the total electricity consumption of the single-phase smart meter within a preset number of days can be determined first based on the timestamp and active power; then, the average daily electricity consumption of the single-phase smart meter can be calculated based on the total electricity consumption, so as to use the average daily electricity consumption as the first feature corresponding to the single-phase smart meter.

[0021] Specifically, after obtaining a certain amount of active power and timestamps, the active power corresponding to multiple whole days is determined based on the timestamps, thereby calculating the total electricity consumption over multiple days. Then, the average value of the total electricity consumption is calculated to obtain the daily average electricity consumption of the single-phase smart meter. The daily average electricity consumption can characterize the user's average consumption level.

[0022] In a feasible implementation, when obtaining the second feature corresponding to the peak electricity consumption of the user of the single-phase smart energy meter based on the corresponding active power and timestamp collected by the single-phase smart energy meter, the active power of the single-phase smart energy meter within a preset number of days can be compared according to the timestamp, and the maximum active power can be used as the second feature corresponding to the single-phase smart energy meter.

[0023] Specifically, after obtaining a certain amount of active power and timestamps, once it is determined from the timestamps that a sufficient number of days of active power have been obtained, all active power is compared to obtain the maximum active power. The maximum active power can represent the peak power consumption of the single-phase smart energy meter, that is, the maximum power required by the user during the power consumption process.

[0024] In a feasible implementation, when obtaining the third characteristic representing the electricity consumption concentration of the user of the single-phase smart meter based on the corresponding active power and timestamp collected by the single-phase smart meter, the first average power of the single-phase smart meter during peak hours and the second average power during off-peak hours can be calculated based on the timestamp and active power; then, the third characteristic corresponding to the single-phase smart meter can be calculated according to the following formula three: P = (P1 - P2) / P1; Formula 3 Wherein, P1 is the first average power and P2 is the second average power.

[0025] Specifically, after obtaining the active power and timestamps over a certain period of time, the first average power of the single-phase smart energy meter during peak hours (e.g., 18:00-22:00) and the second average power during off-peak hours (e.g., 00:00-06:00) can be obtained. The peak-valley difference rate can be obtained through Formula 3. The peak-valley difference rate can characterize the concentration of electricity consumption by users. The higher the value, the more concentrated the user's electricity consumption is during peak hours, which has a greater impact on the power grid and may be more suitable for peak-valley electricity pricing.

[0026] In a feasible implementation, when obtaining the fourth characteristic corresponding to the power consumption stability of the user of the single-phase smart meter based on the corresponding active power and timestamp collected by the single-phase smart meter, the average active power of the single-phase smart meter within a preset number of days can be determined first based on the timestamp and active power; then, the first ratio of the average active power to the second characteristic can be calculated, so that the first ratio is determined as the fourth characteristic corresponding to the single-phase smart meter.

[0027] Specifically, after obtaining the average active power within a preset number of days, the ratio of the average active power to the peak power consumption can be calculated. This ratio is the daily load factor. The higher the daily load factor, the more stable the user's daily electricity consumption; the lower the load factor, the greater the fluctuation in electricity consumption, and the more likely the user has the habit of turning off the power when leaving the house.

[0028] In a feasible implementation, when obtaining the fifth characteristic corresponding to the power consumption stability of the user of the single-phase smart meter based on the corresponding active power and timestamp collected by the single-phase smart meter, the third average power of the single-phase smart meter on weekdays within a preset number of days and the fourth average power of the single-phase smart meter on weekends within a preset number of days can be determined first based on the timestamp and active power; then the difference between the third average power and the fourth average power can be calculated, and this difference can be used as the fifth characteristic corresponding to the single-phase smart meter.

[0029] Specifically, the difference between the average power consumption on weekdays and the average power consumption on weekends (i.e., the average power consumption on Saturdays and Sundays) can indicate the stability of a user's electricity consumption. The greater the difference, the stronger the user's regular work and rest schedule on weekdays, and the more likely they are an office worker with a fixed job.

[0030] It should be noted that non-normal weekends, such as holidays, can be identified based on timestamps to avoid inaccurate calculations of the fifth characteristic when electricity consumption on holidays is treated as workday electricity consumption.

[0031] In a feasible implementation, when obtaining the sixth feature corresponding to the main activity time period of the user of the single-phase smart energy meter based on the corresponding active power and timestamp collected by the single-phase smart energy meter, the first total daytime electricity consumption of the single-phase smart energy meter within a preset number of days and the second total nighttime electricity consumption of the single-phase smart energy meter within a preset number of days can be determined first based on the timestamp and active power; then, the second ratio of the first total electricity consumption to the second total electricity consumption can be calculated, and the second ratio can be used as the sixth feature corresponding to the single-phase smart energy meter.

[0032] Specifically, the ratio of total electricity consumption during the day to total electricity consumption at night can characterize the stability of a user's electricity consumption. A high ratio may indicate a 9-to-5 office worker, while a low ratio may indicate a night worker or a housewife / househusband.

[0033] In a feasible implementation scheme, the formula in Formula 2 above... =tx+S; Where t is the weight of feature x, the weight of feature x is proportional to the importance of feature x in the features, and S represents the bias term constant.

[0034] It should be noted that the specific values ​​of t and S can be flexibly adjusted according to actual needs, and no specific restrictions are imposed here.

[0035] In a feasible implementation plan For the first k The original score is configured with a preset electricity consumption profile label.

[0036] In one feasible implementation, after obtaining a user's electricity consumption profile, when there are multiple recommended contents, the target recommended content is sent to the target user based on the target user's electricity consumption profile and the recommended content configured for each user's electricity consumption profile.

[0037] In a feasible implementation plan, user profile tags include: peak-hour working families, intermittent low-consumption families, stable home-based families, night-shift families, vacant homes, and families with abnormal electricity usage.

[0038] Figure 2 A schematic diagram of a user electricity consumption profile generation device based on a single-phase smart energy meter provided in this application embodiment is shown below. Figure 2 As shown, the device includes: The acquisition unit 21 is used to acquire the active power and the active power timestamp collected by each single-phase smart energy meter according to a preset cycle for each single-phase smart energy meter. The processing unit 22 is used to obtain, for each single-phase smart energy meter, a first feature corresponding to the average consumption level of the user of the single-phase smart energy meter, a second feature corresponding to the peak electricity consumption, a third feature corresponding to the concentration of electricity consumption, a fourth feature corresponding to the stability of electricity consumption, a fifth feature corresponding to the stability of electricity consumption, and a sixth feature corresponding to the main activity period, based on the active power and timestamp collected by the single-phase smart energy meter that have a corresponding relationship. The first calculation unit 23 is used to standardize the data for each feature according to the following formula to obtain the standard feature corresponding to each feature: F x标 =(F x -U x ) / T x ; Among them, F x Let x be the characteristic corresponding to this single-phase smart energy meter, and U be the characteristic of the meter. x The mean of characteristic x corresponding to all single-phase smart energy meters, T x There is a standard deviation of feature x corresponding to a single-phase smart energy meter, and feature x includes the first to sixth features; The second calculation unit 24 is used to calculate, according to the following formula, whether the single-phase smart energy meter belongs to the [number] [phase]. j The probability of a preset electricity consumption profile label; ; in, j Indicates the first j There are three preset electricity consumption profile labels, where x is the input feature. This indicates that, given the first to sixth characteristics, the single-phase smart energy meter belongs to the [specific category]. j The probability of a preset electricity consumption profile label.e It is a natural constant. For the first j Preset scores for each preset electricity consumption profile tag; The preset scores for all preset electricity consumption profile tags, The number of preset electricity consumption profile tags; Determining unit 25 is used to determine whether the single-phase smart energy meter belongs to the first... j The probability of each preset electricity consumption profile label is used to determine the user's electricity consumption profile for the single-phase smart energy meter. The preset electricity consumption profile label with the highest probability is used as the user's electricity consumption profile for the user.

[0039] In one feasible implementation, when the processing unit obtains a first feature representing the average consumption level of the user of the single-phase smart meter based on the corresponding active power and timestamp collected by the single-phase smart meter, it includes: Based on the timestamp and active power, determine the total electricity consumption of the single-phase smart energy meter within a preset number of days; Based on the total electricity consumption, the average daily electricity consumption of the single-phase smart energy meter is calculated, and the average daily electricity consumption is used as the first feature corresponding to the single-phase smart energy meter.

[0040] In one feasible implementation, when the processing unit obtains a second feature representing the peak electricity consumption of the user of the single-phase smart meter based on the corresponding active power and timestamp collected by the single-phase smart meter, it includes: Based on the timestamp, the active power of the single-phase smart energy meter within a preset number of days is compared, and the maximum active power is used as the second feature corresponding to the single-phase smart energy meter.

[0041] In one feasible implementation, when the processing unit obtains a third feature representing the electricity consumption concentration of the user of the single-phase smart meter based on the corresponding active power and timestamp collected by the single-phase smart meter, it includes: Based on the timestamp and active power, calculate the first average power of the single-phase smart energy meter during peak hours and the second average power during off-peak hours. The third characteristic of this single-phase smart energy meter is calculated using the following formula: P = (P1 - P2) / P1; Wherein, P1 is the first average power and P2 is the second average power.

[0042] In one feasible implementation, when the processing unit obtains a fourth feature representing the power consumption stability of the user of the single-phase smart meter based on the corresponding active power and timestamp collected by the single-phase smart meter, it includes: Based on the timestamp and active power, determine the average active power of the single-phase smart energy meter within a preset number of days; Calculate the first ratio of the average active power to the second feature, and determine the first ratio as the fourth feature corresponding to the single-phase smart energy meter.

[0043] In one feasible implementation, when the processing unit obtains the fifth feature representing the electricity consumption stability of the user of the single-phase smart meter based on the corresponding active power and timestamp collected by the single-phase smart meter, it includes: Based on the timestamp and active power, determine the third average power of the single-phase smart energy meter on weekdays within a preset number of days, and the fourth average power of the single-phase smart energy meter on weekends within a preset number of days. The difference between the third average power and the fourth average power is calculated, and this difference is used as the fifth feature corresponding to the single-phase smart energy meter.

[0044] In one feasible implementation, when the processing unit obtains the sixth feature corresponding to the main activity time period of the user of the single-phase smart meter based on the corresponding active power and timestamp collected by the single-phase smart meter, it includes: Based on the timestamp and active power, determine the first total electricity consumption of the single-phase smart energy meter during the day within a preset number of days, and the second total electricity consumption of the single-phase smart energy meter at night within a preset number of days; Calculate a second ratio between the first total electricity consumption and the second total electricity consumption, and use the second ratio as the sixth feature corresponding to the single-phase smart energy meter.

[0045] In a feasible implementation plan =tx+S; Where t is the weight of feature x, the weight of feature x is proportional to the importance of feature x in the features, and S represents the bias term constant.

[0046] In one feasible implementation, the determining unit is further configured to send target recommended content to the target user based on the target user's electricity consumption profile and the recommended content configured for each user's electricity consumption profile.

[0047] about Figure 2 For explanations of the relevant principles, please refer to [link / reference]. Figure 1 Detailed explanations of the relevant content will not be repeated here.

[0048] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some communication interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.

[0049] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0050] In addition, the functional units in the embodiments provided in this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0051] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0052] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. In addition, the terms "first", "second", "third", etc. are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0053] Finally, it should be noted that the above-described embodiments are merely specific implementations of this application, used to illustrate the technical solutions of this application, and not to limit them. The protection scope of this application is not limited thereto. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some of the technical features, within the scope of the technology disclosed in this application; and these modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application. All should be covered within the protection scope of this application. Therefore, the protection scope of this application should be determined by the protection scope of the claims.

Claims

1. A method for generating user electricity consumption profiles based on single-phase smart meters, characterized in that, The method includes: For each single-phase smart energy meter, obtain the active power and the timestamp of the active power collected by the single-phase smart energy meter according to a preset cycle; For each single-phase smart energy meter, based on the active power and timestamps collected by the single-phase smart energy meter that have a corresponding relationship, the following characteristics are obtained: the first characteristic corresponding to the average consumption level of the user of the single-phase smart energy meter, the second characteristic corresponding to the peak electricity consumption, the third characteristic corresponding to the concentration of electricity consumption, the fourth characteristic corresponding to the stability of electricity consumption, the fifth characteristic corresponding to the stability of electricity consumption, and the sixth characteristic corresponding to the main activity period. The data is standardized for each feature using the following formula to obtain the standard feature for each feature: F x标 =(F x -U x ) / T x ; Among them, F x Let x be the characteristic corresponding to this single-phase smart energy meter, and U be the characteristic of the meter. x The mean of characteristic x corresponding to all single-phase smart energy meters, T x There is a standard deviation of feature x corresponding to a single-phase smart energy meter, and feature x includes the first to sixth features; The single-phase smart energy meter belongs to the following category based on the formula below. j The probability of a preset electricity consumption profile label; ； in, j Indicates the first j There are three preset electricity consumption profile labels, where x is the input feature. This indicates that, given the first to sixth characteristics, the single-phase smart energy meter belongs to the [specific category]. j The probability of a preset electricity consumption profile label. e It is a natural constant. For the first j Preset scores for each preset electricity consumption profile tag; The preset scores for all preset electricity consumption profile tags, The number of preset electricity consumption profile tags; According to the classification of this single-phase smart energy meter, it belongs to the [number]. j The probability of each preset electricity consumption profile label is used to determine the user's electricity consumption profile for the single-phase smart energy meter. The preset electricity consumption profile label with the highest probability is used as the user's electricity consumption profile for the user.

2. The user electricity consumption profile generation method as described in claim 1, characterized in that, Based on the corresponding active power and timestamps collected by the single-phase smart meter, a first feature corresponding to the average consumption level of the user of the single-phase smart meter is obtained, including: Based on the timestamp and active power, determine the total electricity consumption of the single-phase smart energy meter within a preset number of days; Based on the total electricity consumption, the average daily electricity consumption of the single-phase smart energy meter is calculated, and the average daily electricity consumption is used as the first feature corresponding to the single-phase smart energy meter.

3. The user electricity consumption profile generation method as described in claim 1, characterized in that, Based on the corresponding active power and timestamps collected by the single-phase smart meter, a second feature corresponding to the peak electricity consumption of the user of the single-phase smart meter is obtained, including: Based on the timestamp, the active power of the single-phase smart energy meter within a preset number of days is compared, and the maximum active power is used as the second feature corresponding to the single-phase smart energy meter.

4. The user electricity consumption profile generation method as described in claim 1, characterized in that, Based on the corresponding active power and timestamps collected by the single-phase smart meter, a third feature is obtained to represent the electricity consumption concentration of the user of the single-phase smart meter, including: Based on the timestamp and active power, calculate the first average power of the single-phase smart energy meter during peak hours and the second average power during off-peak hours. The third characteristic of this single-phase smart energy meter is calculated using the following formula: P = (P1 - P2) / P1; Wherein, P1 is the first average power and P2 is the second average power.

5. The user electricity consumption profile generation method as described in claim 1, characterized in that, Based on the corresponding active power and timestamps collected by the single-phase smart meter, a fourth feature is obtained to represent the power consumption stability of the user of the single-phase smart meter, including: Based on the timestamp and active power, determine the average active power of the single-phase smart energy meter within a preset number of days; Calculate the first ratio of the average active power to the second feature, and determine the first ratio as the fourth feature corresponding to the single-phase smart energy meter.

6. The user electricity consumption profile generation method as described in claim 1, characterized in that, Based on the corresponding active power and timestamps collected by the single-phase smart meter, a fifth feature is obtained to represent the power consumption stability of the user of the single-phase smart meter, including: Based on the timestamp and active power, determine the third average power of the single-phase smart energy meter on weekdays within a preset number of days, and the fourth average power of the single-phase smart energy meter on weekends within a preset number of days. The difference between the third average power and the fourth average power is calculated, and this difference is used as the fifth feature corresponding to the single-phase smart energy meter.

7. The user electricity consumption profile generation method as described in claim 1, characterized in that, Based on the corresponding active power and timestamps collected by the single-phase smart meter, a sixth feature is obtained to represent the main activity time periods of the user of the single-phase smart meter, including: Based on the timestamp and active power, determine the first total electricity consumption of the single-phase smart energy meter during the day within a preset number of days, and the second total electricity consumption of the single-phase smart energy meter at night within a preset number of days; Calculate a second ratio between the first total electricity consumption and the second total electricity consumption, and use the second ratio as the sixth feature corresponding to the single-phase smart energy meter.

8. The user electricity consumption profile generation method as described in claim 1, characterized in that, The method further includes: =tx+S; Where t is the weight of feature x, the weight of feature x is proportional to the importance of feature x in the features, and S represents the bias term constant.

9. The user electricity consumption profile generation method as described in claim 1, characterized in that, The method further includes: Based on the target user's electricity consumption profile and the recommended content configured for each user's electricity consumption profile, the target recommended content is sent to the target user.

10. A user electricity consumption profile generation device based on a single-phase smart energy meter, characterized in that, The device includes: The acquisition unit is used to acquire the active power and the timestamp of the active power collected by each single-phase smart energy meter according to a preset cycle. The processing unit is used to, for each single-phase smart energy meter, obtain, based on the active power and timestamps collected by the single-phase smart energy meter that have a corresponding relationship, a first feature corresponding to the average consumption level of the user of the single-phase smart energy meter, a second feature corresponding to the peak electricity consumption, a third feature corresponding to the concentration of electricity consumption, a fourth feature corresponding to the stability of electricity consumption, a fifth feature corresponding to the stability of electricity consumption, and a sixth feature corresponding to the main activity period. The first calculation unit is used to standardize the data for each feature according to the following formula to obtain the standard feature corresponding to each feature: F x标 =(F x -U x ) / T x ; Among them, F x Let x be the characteristic corresponding to this single-phase smart energy meter, and U be the characteristic of the meter. x The mean of characteristic x corresponding to all single-phase smart energy meters, T x There is a standard deviation of feature x corresponding to a single-phase smart energy meter, and feature x includes the first to sixth features; The second calculation unit is used to calculate whether the single-phase smart energy meter belongs to the first generation according to the following formula. j The probability of a preset electricity consumption profile label; ； in, j Indicates the first j There are three preset electricity consumption profile labels, where x is the input feature. This indicates that, given the first to sixth characteristics, the single-phase smart energy meter belongs to the [specific category]. j The probability of a preset electricity consumption profile label. e It is a natural constant. For the first j Preset scores for each preset electricity consumption profile tag; The preset scores for all preset electricity consumption profile tags, The number of preset electricity consumption profile tags; The determining unit is used to determine whether the single-phase smart energy meter belongs to the first... j The probability of each preset electricity consumption profile label is used to determine the user's electricity consumption profile for the single-phase smart energy meter. The preset electricity consumption profile label with the highest probability is used as the user's electricity consumption profile for the user.

Images