Group rental housing identification method, equipment and device based on power data
Through power data analysis and machine learning models, accurate identification of group rental housing has been solved, the problem of inaccurate identification in the existing technology has been improved, and the identification accuracy and real-time nature of management departments have been improved, and the community management problems brought about by group rental housing has been effectively dealt with.
Patent Information
- Application Number
- CN202411182133.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-27
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2044-08-27
AI Technical Summary
The existing technology cannot accurately identify group rental housing, resulting in problems such as community noise, improper garbage management, tight parking spaces, and low rental transparency, deposit disputes and poor living environment quality.
By obtaining the power data of the house in the preset period, building a power evaluation model based on machine learning, generating a power evaluation coefficient, combining Gaussian naive Bayes classification algorithm, identifying the group rental housing category, and performing secondary identification of unidentified houses.
Accurate identification of group rental housing has been achieved, helping management departments to discover potential problems in a timely manner, take appropriate management and supervision measures, curb community management problems and resource consumption, and improve the accuracy and real-time identification.
Smart Images

Figure CN118690278B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of shared rental housing identification, and more specifically, to a shared rental housing identification method, equipment and device based on power data. Background Art
[0002] Shared housing refers to a rental situation where multiple tenants live together, but each tenant usually only rents one bedroom and shares common areas. In some large cities, especially in areas with high housing prices, young people or low-income groups often find it difficult to afford the cost of renting an independent house, and shared housing provides a relatively cheap housing option; tenants may have greatly fluctuating short-term or medium-term housing needs, and shared housing provides a more flexible way of renting that does not require long-term leases; shared housing may increase community noise, parking space shortages, increased domestic waste and other problems, affecting the quality of life of surrounding residents. The management of shared housing is relatively complex, including challenges in managing and resolving conflicts between tenants, regularly maintaining common areas, and ensuring safety; the living environment of shared housing is usually crowded, and the tenants' living experience may be affected, such as privacy and security issues.
[0003] Deficiencies in existing technologies: Group housing fills the gap in the housing market in some places, but also brings a series of challenges. It usually involves multiple tenants living together, which will have a certain impact on the surrounding community and public order; the existence of group housing may bring some social problems, such as noise pollution, improper garbage management, and tight parking spaces; there are a large number of tenants in group housing, and there may be problems such as low rent transparency, deposit disputes, and poor living environment quality; but the existing group housing identification method is not accurate enough, so a group housing identification method based on power data is needed.
[0004] In view of the above problems, the present invention proposes a solution. Summary of the invention
[0005] In order to overcome the above-mentioned defects of the prior art, the embodiments of the present invention provide a method, device and apparatus for identifying shared rental houses based on power data, so as to solve the hidden danger of inaccurate identification of shared rental houses.
[0006] To achieve the above object, the present invention provides the following technical solutions:
[0007] A method for identifying shared rental houses based on power data includes: obtaining power data of a house to be identified within a preset period, the power data including the house's power consumption and load fluctuation coefficient; constructing a power evaluation model based on machine learning according to the power data to generate a power evaluation coefficient; comparing and analyzing the power evaluation coefficient with a preset power stability threshold to obtain an alarm list of shared rental houses, and recording the number of houses in the alarm list; obtaining the posterior probabilities of shared rental house categories and non-shared rental house categories in the alarm list based on a Gaussian naive Bayes classification algorithm, preliminarily identifying shared rental houses according to the posterior probabilities, and performing secondary identification on unidentified houses.
[0008] In a preferred embodiment, the specific method for obtaining the house electricity consumption is as follows: obtain the rated power consumption of the equipment in the house, calculate the power consumption of each device based on the usage time of each device within a preset period, and sum the power consumption of each device to obtain the house electricity consumption.
[0009] In a preferred embodiment, the specific method for obtaining the load fluctuation coefficient is as follows: obtain load data within a preset period, calculate the average load and load standard deviation within the preset period through the load data, and use the ratio of the load standard deviation to the average load as the load fluctuation coefficient.
[0010] In a preferred embodiment, the steps for obtaining the alarm list of the shared rental house are as follows:
[0011] The power assessment coefficient is compared with the preset power stability threshold; if the power assessment coefficient is less than or equal to the preset power stability threshold, the house to be identified will not be included in the alarm list of shared rental houses; if the power assessment coefficient is greater than the preset power stability threshold, the house to be identified will be included in the alarm list of shared rental houses.
[0012] In a preferred embodiment, a specific method for obtaining the posterior probabilities of the group rental housing category and the non-group rental housing category in the alarm list is as follows: obtaining the historical electricity data of the houses in the alarm list and the prior probability of the historical group rental housing category based on the Gaussian Naive Bayes classification algorithm; calculating the conditional probability of the historical electricity data under the historical group rental housing category based on the prior probability; calculating the posterior probability of the group rental housing category and the non-group rental housing category in the alarm list based on the prior probability and the conditional probability.
[0013] In a preferred embodiment, the specific steps for preliminarily identifying group-rented houses are as follows: subtracting the posterior probability of the group-rented house category from the posterior probability of the non-group-rented house category, and when the subtraction result is greater than a preset recognition probability threshold, identifying the house category as a group-rented house category; when the subtraction result is less than the negative value of the preset recognition probability threshold, identifying the house category as a non-group-rented house category; when the absolute value of the subtraction result is less than the preset recognition probability threshold, classifying the house to be identified as an unidentified house.
[0014] In a preferred embodiment, the specific steps of performing secondary identification on unidentified group-rented houses are as follows: obtaining several power evaluation coefficients of unidentified houses within a preset time, and calculating the standard deviation of the power evaluation coefficients of the unidentified houses; when the standard deviation of the power evaluation coefficients is greater than or equal to a preset standard deviation threshold, identifying the unidentified group-rented house as a group-rented house; when the standard deviation of the power evaluation coefficients is less than a preset standard deviation threshold, identifying the unidentified group-rented house as a non-group-rented house.
[0015] An electronic device, characterized in that the electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the group rental housing identification method based on power data provided in an embodiment of the present invention.
[0016] A computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, the method for identifying a shared rental house based on power data provided in an embodiment of the present invention is implemented.
[0017] The technical effects and advantages of the group rental housing identification method, equipment and device based on power data of the present invention are as follows:
[0018] 1. The present invention can accurately identify group rental houses by utilizing power usage patterns and data features through power data analysis. Group rental houses usually exhibit power consumption patterns different from ordinary residences, such as abnormal power consumption and power consumption time. Group rental houses often exceed normal residential power consumption standards, which may be caused by factors such as dense population and multiple equipment use. The power data system can monitor these anomalies in real time, such as frequent high-load power consumption or unconventional power consumption at night. The tenant mobility of continuous group rental houses is high, and the power usage pattern may change frequently, while the traditional single-resident model is usually more stable. By comparing and analyzing historical power data and real-time data, the system can identify this variability and then judge the possible group rental housing situation. This accurate identification capability enables management departments to quickly discover potential group rental housing problems and take appropriate management and supervision measures, thereby effectively curbing community management problems and resource consumption caused by group rental housing.
[0019] 2. Through in-depth analysis of electricity data, the present invention can identify the differences between normal residences and potential shared housing. For example, shared housing often shows higher average electricity consumption, irregular electricity consumption time or frequent load fluctuations. This analysis can help decision makers determine potential shared housing problems. The electricity data system can provide real-time updated data and monitor changes in electricity usage patterns at any time. This real-time and continuous monitoring capability allows decision makers to adjust strategies and measures in a timely manner to respond to new changes and challenges in shared housing problems. Based on historical data and real-time data, the electricity data system can identify changes and trends in electricity usage patterns. The analysis of such patterns and trends provides decision makers with the ability to predict and prevent shared housing problems. BRIEF DESCRIPTION OF THE DRAWINGS
[0020] Figure 1 It is a structural schematic diagram of the group rental housing identification method based on power data of the present invention.
[0021] Figure 2 The figure is a schematic diagram of the electronic device structure of the group rental housing identification method based on power data of the present invention. DETAILED DESCRIPTION
[0022] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0023] Embodiment 1, Figure 1 The present invention provides a group rental housing identification method based on power data.
[0024] S10, obtaining power data of the house to be identified within a preset period, wherein the power data includes power consumption of the house and load fluctuation coefficient;
[0025] The method for obtaining the electricity consumption of the house is as follows:
[0026] First, the rated power consumption of the equipment in the house is obtained through the equipment specification table, and the power consumption of each equipment is calculated based on the usage time of each equipment in the preset period, and the power consumption of each equipment is summed up to get the power consumption of the house;
[0027] The specific calculation formula for house electricity consumption is as follows:
[0028]
[0029] In the formula, is the power consumption of each device, is the rated power consumption of each device, is the preset period, where = , n is the total number of data in the set;
[0030]
[0031] In the formula, is the power consumption of each device, = , n is the total number of data in the set, is the electricity consumption of the house;
[0032] The specific method for obtaining the load fluctuation coefficient is as follows:
[0033] Obtaining load data within a preset period, calculating the average load and load standard deviation within the preset period through the load data, and taking the ratio of the load standard deviation to the average load as the load fluctuation coefficient;
[0034] The specific calculation formula for average load is as follows:
[0035]
[0036] In the formula, is the average load, is the load data within the preset period, where ;
[0037]
[0038] In the formula, is the load standard deviation, is the average load, It is the load data within the preset period;
[0039]
[0040] In the formula, is the load fluctuation coefficient, is the average load, It is the load data within a preset period; obtaining power data has the following functions for identifying shared rental houses:
[0041] Power usage pattern analysis:
[0042] Group rental housing usually has a different electricity usage pattern than ordinary residential buildings due to the large number of residents. By analyzing the electricity usage pattern, it is possible to identify whether there is abnormally high energy consumption, which may indicate a densely populated living situation, that is, the existence of group rental housing;
[0043] Abnormal power consumption behavior detection:
[0044] Through power data analysis, abnormal power usage behaviors can be detected, such as very frequent use of electrical appliances, continuous high-load power usage for a long time, etc. These abnormal behaviors may be unique to shared housing, because in this case, power usage may be more frequent and concentrated than in ordinary residences;
[0045] The relationship between electricity consumption and residential population:
[0046] The number of people living in a residential area can be inferred from electricity data. Due to the dense population, the electricity consumption of shared rental houses is usually higher than that of normal single houses. Therefore, the population living in a residential area can be roughly estimated by electricity consumption, thereby indirectly judging whether there is a shared rental house situation.
[0047] Support other data analysis:
[0048] Electricity data can be combined with other data sources for analysis, such as rental records, property data, etc., to provide a more accurate basis for judging shared rental housing. Combining data from different sources can build a more comprehensive shared rental housing identification model;
[0049] S20, constructing a power evaluation model based on machine learning according to the power data to generate a power evaluation coefficient;
[0050] The specific calculation formula of the power assessment coefficient is as follows:
[0051]
[0052] In the formula, is the power assessment coefficient, is the electricity consumption of the house, Load fluctuation factor;
[0053] Building a power assessment model based on machine learning models based on power data and generating power assessment coefficients can play an important role in identifying group rental housing. The following are some of the functions and possible applications of power assessment models:
[0054] The power assessment coefficient can help decision-makers, management agencies or rental platforms identify possible group rental housing and take necessary management or monitoring measures;
[0055] Based on the results of the power assessment model, more accurate urban planning policies or rental supervision policies can be formulated. For example, based on the probability of group renting assessed by the model, it is decided to increase the frequency of inspections in certain areas or adjust the power price policy.
[0056] At the same time, the model can also serve as an auxiliary tool to help landlords, property management companies or tenants better understand and optimize electricity usage behavior to improve energy efficiency and reduce resource waste;
[0057] S30, comparing and analyzing the power evaluation coefficient with the preset power stability threshold, obtaining an alarm list of shared rental houses, and recording the number of houses in the alarm list;
[0058] The specific steps for obtaining the warning list of group rental housing are as follows:
[0059] Compare each house's power assessment factor with the preset power stability threshold:
[0060] If the power evaluation coefficient is less than or equal to the preset power stability threshold, this means that the power usage pattern of the house meets the expected stability level and is unlikely to be a shared rental house. In this case, the house will not be included in the shared rental house warning list;
[0061] If the power evaluation coefficient is greater than the preset power stability threshold, this indicates that the power usage pattern of the house is significantly different from the typical pattern of shared housing, and it may be a shared housing. In this case, the house should be included in the alarm list of shared housing, and the number of houses in the alarm list should be recorded;
[0062] Once it is determined which houses should be included in the alarm list, the system should record this information and perform necessary follow-up processing:
[0063] Record the number of houses in the warning list: Make sure to record the number of houses identified as possible group-rented houses in each time period, which can help power management agencies or relevant departments understand and monitor the trend of group-rented houses;
[0064] Depending on the number of houses on the alert list, different actions can be taken and further investigations can be conducted to ensure the rational use of housing resources and the safety and stability of the community;
[0065] Obtaining the warning list of shared housing plays an important role in identifying and managing shared housing problems, mainly in the following aspects:
[0066] Identify potential shared housing units:
[0067] The alarm list records the specific units or house addresses identified as group rental houses. These units usually show unstable power usage patterns or exceed the preset stability coefficient. By establishing an alarm list, the power management department can clearly understand which houses may have group rental problems, so as to carry out targeted monitoring and management;
[0068] Carry out regular inspections and patrols:
[0069] With the alert list, the power management agency can arrange regular inspections and patrols, especially for the houses on the list, which helps to verify whether there is a group rental situation, such as whether there are too many tenants using electricity, whether there are any violations such as unauthorized power modifications, etc. Regular inspections can detect problems in time and take necessary corrective measures;
[0070] Improving regulatory efficiency and resource utilization:
[0071] The warning list enables power management departments to allocate resources more efficiently. They can focus on units suspected of being group rental houses instead of conducting extensive monitoring. This precise resource allocation can improve supervision efficiency while ensuring the effective use of resources.
[0072] Supporting regulatory enforcement:
[0073] In some areas, there are laws or policies that prohibit or restrict group renting, because this may affect community safety, environmental sanitation and the use of public resources. By establishing a warning list, relevant departments can carry out corresponding work based on actual data and impose penalties or other necessary legal measures on violations to ensure social order and public interests;
[0074] Data analysis and trend monitoring:
[0075] The data accumulated in the warning list can help power management departments analyze the trends and patterns of the group rental phenomenon. This data analysis will help to better understand the nature of the group rental problem and provide a basis for formulating more effective policies and measures in the future.
[0076] S40, obtaining the posterior probabilities of the group-rented housing category and the non-group-rented housing category in the warning list based on the Gaussian Naive Bayes classification algorithm, preliminarily identifying the group-rented housing according to the posterior probabilities, and performing secondary identification on the unidentified housing;
[0077] The prior probability directly affects the calculation result of the posterior probability. In Bayesian inference, the posterior probability is obtained by performing Bayesian update on the prior probability and the conditional probability. The acquisition of the prior probability will affect the calculation result of the posterior probability. Therefore, it is necessary to obtain the prior probability of historical power data and historical group rental housing categories.
[0078] Based on the Gaussian Naive Bayes classification algorithm, the prior probability of the house electricity consumption and the load fluctuation coefficient in the alarm list is obtained. The probability density function of the prior probability of the house electricity consumption is as follows:
[0079]
[0080] In the formula, is the prior probability of house electricity consumption, is the average electricity consumption of the house, is the standard deviation of electricity consumption of the houses;
[0081] The probability density function of the prior probability of the load fluctuation coefficient is as follows:
[0082]
[0083] In the formula, is the prior probability of the load fluctuation coefficient, is the mean value of the load fluctuation coefficient, is the standard deviation of the load fluctuation factor;
[0084] The probability density function of the prior probability of obtaining a shared rental house in the warning list is as follows:
[0085]
[0086] In the formula, is the prior probability of group renting a house, is the average value of shared housing. is the standard deviation of shared housing;
[0087] The conditional probability of house electricity consumption and load fluctuation coefficient under the group rental housing type is calculated. The specific calculation formula of the conditional probability of house electricity consumption under the group rental housing type is as follows:
[0088]
[0089] In the formula, is the conditional probability of house electricity consumption under the shared housing type, is the prior probability of group renting a house,
[0090] The specific calculation formula of the conditional probability of the load fluctuation coefficient under the group rental housing type is as follows:
[0091]
[0092] In the formula, is the conditional probability of load fluctuation coefficient under the group rental housing type, is the prior probability of group renting a house,
[0093] The posterior probability of the group rental housing category and the non-group rental housing category in the warning list is calculated. The specific formula for the posterior probability of the group rental housing category is as follows:
[0094]
[0095] In the formula, is the posterior probability of the group rental category; is the prior probability of group renting a house, is the prior probability of house electricity consumption, is the prior probability of the load fluctuation coefficient, is the conditional probability of house electricity consumption and load fluctuation coefficient under the group rental housing type;
[0096] The specific calculation formula is as follows:
[0097]
[0098] In the formula, is the conditional probability of house electricity consumption under the shared housing type, is the conditional probability of load fluctuation coefficient under the group rental housing type;
[0099] The specific formula for the posterior probability of the non-group rental category is as follows:
[0100]
[0101] Where Z is the total number of houses in the warning list;
[0102] Subtract the posterior probability of the shared rental housing category from the posterior probability of the non-shared rental housing category, and when the subtraction result is greater than a preset recognition probability threshold, the housing category is identified as a shared rental housing category;
[0103] The specific calculation formula is as follows:
[0104]
[0105] In the formula, is the posterior probability of the group rental category, is the posterior probability of the non-group rental category, is the preset recognition probability threshold;
[0106] When the subtraction result is less than the negative value of the preset recognition probability threshold, the housing category is identified as a non-group rental housing category;
[0107] When the absolute value of the subtraction result is less than the preset recognition probability threshold, the house to be recognized is classified as an unrecognized house;
[0108] The specific steps of performing secondary identification on the unidentified shared rental house are as follows:
[0109] Obtaining a number of power assessment coefficients of unidentified houses within a preset time, and calculating the standard deviation of the power assessment coefficients of the unidentified houses;
[0110] When the standard deviation of the power evaluation coefficient is greater than or equal to a preset standard deviation threshold, the unidentified shared rental house is identified as a shared rental house;
[0111] When the standard deviation of the power evaluation coefficient is less than a preset standard deviation threshold, the unidentified shared rental house is identified as a non-shared rental house.
[0112] The main purpose of group housing identification is to effectively manage and monitor the group housing phenomenon in the city. This phenomenon usually refers to a house being rented by multiple tenants or families, beyond the normal single-family living situation. The following are the specific purposes of group housing identification:
[0113] Urban management and regulation of the rental market: The identification of group rental housing can help urban management departments to timely understand and control the distribution and situation of group rental housing, which helps to maintain the order and safety of the living environment. By identifying group rental housing, the rental market can be regulated to prevent illegal rental activities and excessive use of housing resources;
[0114] Resource regulation and market balance: Group rental often leads to irrational use of housing resources, especially in densely populated cities. Identifying group rental can help relevant departments to rationally allocate housing resources, ensure the effective use of resources and the balanced development of the housing market;
[0115] Improve the quality of life of residents: Group rental housing often has hidden dangers of living safety and environmental sanitation problems, such as exceeding the standard of living and excessive power load. Timely identification and management of group rental housing can reduce these potential safety hazards and improve the quality of life and living environment of residents;
[0116] Legal supervision and social stability: A legal rental market helps maintain social order and citizens’ rights. By identifying shared rental housing, we can effectively supervise rental behavior, reduce illegal rentals and potential social problems, and promote social stability and development.
[0117] Intelligent management and technology application: Using modern technologies such as the Internet of Things and big data analysis to develop a group rental identification system can achieve intelligent management and monitoring, improve urban management efficiency and response speed, and provide scientific and technological support for urban governance;
[0118] To sum up, the purpose of identifying group rental houses is not only to manage and monitor the housing rental phenomenon in the city, but also to optimize the allocation of urban resources, improve the quality of life of residents, maintain social order and legal supervision. It is an important part of modern urban management.
[0119] like Figure 2 FIG. 1 is a schematic diagram of the structure of an electronic device for implementing the group rental housing identification method based on power data according to the present invention.
[0120] The electronic device may include a processor, a memory, a communication bus, and a communication interface, and may also include a computer program stored in the memory and executable on the processor, such as a group rental housing identification method based on power data.
[0121] Among them, the processor is the control core of the electronic device, which uses various interfaces and lines to connect the various components of the entire electronic device, and executes various functions of the electronic device and processes data by running or executing programs or modules stored in the memory, and calling data stored in the memory.
[0122] The memory includes at least one type of readable storage medium, and in some embodiments, the memory may be an internal storage unit of the electronic device, such as a mobile hard disk of the electronic device. The memory may be used to store not only application software installed in the electronic device but also various data.
[0123] The communication bus is configured to realize connection and communication between the memory and at least one processor.
[0124] The communication interface is used for communication between the above electronic device and other devices, including a network interface and a user interface.
[0125] The figure only shows an electronic device with components. Those skilled in the art will understand that the structure shown in the figure does not constitute a limitation on the electronic device, and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.
[0126] It should be understood that the embodiment is for illustration only and the scope of the patent application is not limited to this structure.
[0127] The program stored in the memory in the electronic device is a combination of multiple instructions, and when running in the processor, the steps in the above-mentioned group rental housing identification method based on power data can be implemented.
[0128] Specifically, the specific implementation system of the processor for the above instructions can refer to the description of the relevant steps in the corresponding embodiment of the accompanying drawings, which will not be repeated here.
[0129] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.
[0130] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product.
[0131] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.
[0132] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.
[0133] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which 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.
[0134] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.
Claims
1. A method for identifying shared rental housing based on power data, characterized in that: The following steps are involved: Acquire power data of the house to be identified within a preset period, wherein the power data includes power consumption of the house and a load fluctuation coefficient; Building a power evaluation model based on machine learning according to the power data to generate a power evaluation coefficient; The specific calculation formula of the power evaluation coefficient is as follows: In the formula, is the power assessment coefficient, is the electricity consumption of the house, is the load fluctuation factor; Compare and analyze the power assessment coefficient with the preset power stability threshold, obtain the warning list of shared rental houses, and record the number of houses in the warning list; Based on the Gaussian Naive Bayes classification algorithm, the historical power data of the houses in the alarm list and the prior probability of the historical group rental housing category are obtained, and the conditional probability of the historical power data under the historical group rental housing category is calculated according to the prior probability, and the posterior probability of the group rental housing category and the non-group rental housing category in the alarm list is calculated according to the prior probability and the conditional probability; Subtract the posterior probability of the group-rented house category from the posterior probability of the non-group-rented house category. When the subtraction result is greater than a preset recognition probability threshold, the house category is identified as a group-rented house category; when the subtraction result is less than the negative value of the preset recognition probability threshold, the house category is identified as a non-group-rented house category; when the absolute value of the subtraction result is less than the preset recognition probability threshold, the house to be identified is classified as an unidentified house; Obtaining a number of power assessment coefficients of unidentified houses within a preset time, and calculating the standard deviation of the power assessment coefficients of the unidentified houses; When the standard deviation of the power evaluation coefficient is greater than or equal to the preset standard deviation threshold, the house is identified as a shared rental house; when the standard deviation of the power evaluation coefficient is less than the preset standard deviation threshold, the house is identified as a non-shared rental house.
2. The method for identifying shared housing based on power data according to claim 1, characterized in that: The specific method for obtaining the electricity consumption of the house is as follows: The rated power consumption of the equipment in the house is obtained, and the power consumption of each device is calculated based on the usage time of each device in a preset period. The power consumption of each device is summed up to get the power consumption of the house.
3. The method for identifying shared housing based on power data according to claim 1, characterized in that: The specific method for obtaining the load fluctuation coefficient is as follows: The load data within a preset period is obtained, the average load and the load standard deviation within the preset period are calculated using the load data, and the ratio of the load standard deviation to the average load is used as the load fluctuation coefficient.
4. The method for identifying shared housing based on power data according to claim 1, characterized in that: The steps for obtaining the alarm list of the shared rental house are as follows: comparing the power assessment coefficient with a preset power stability threshold; If the power evaluation coefficient is less than or equal to the preset power stability threshold, the house to be identified will not be included in the group rental house alarm list; If the power assessment coefficient is greater than the preset power stability threshold, the house to be identified will be included in the alarm list of shared rental houses.
5. An electronic device, characterized in that: The electronic device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, The computer program is executed by the at least one processor, So that the at least one processor can execute the group rental housing identification method based on power data as described in any one of claims 1 to 4.
6. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for identifying shared housing based on power data as described in any one of claims 1 to 4 is implemented.
