House using state identification method, device, equipment, medium and product
By extracting multiple business atomic features from the business basic data of the house, analyzing their correlations, extracting target common factors and calculating their contribution, the problem of low identification accuracy in the prior art is solved, and higher identification accuracy and objectivity are achieved.
Patent Information
- Application Number
- CN202411824095.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-11
- Publication Date
- 2025-04-15
AI Technical Summary
It is difficult to accurately identify group rental housing in the prior art, and the evaluation of variable importance depends on human experience and has strong subjectivity, resulting in low identification accuracy.
By obtaining multiple business atomic features corresponding to the business basic data of the house to be identified, the target common factors are extracted based on the correlation between these features, the contribution degree of each factor is calculated, the feature intensity is obtained, and the usage status of the house is identified based on the feature intensity.
It improves the accuracy of house usage status recognition, reduces the influence of subjective factors, and achieves more objective and accurate identification results.
Smart Images
Figure CN119831644A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of big data technology, and in particular to a method, device, equipment, medium and product for identifying the usage status of a group of houses. Background Art
[0002] With the acceleration of urbanization, group rental is becoming more and more common in urban residents' housing. However, group rental may cause a series of problems, including deterioration of living environment, increased safety hazards and social security issues. Therefore, how to accurately and effectively identify group rental has become a key technical requirement for urban governance and property management.
[0003] The housing use status identification method in the related art can monitor the changes in the water and electricity usage of the residence and infer the number of residents by combining the fluctuation pattern. For example, an abnormal increase in water and electricity consumption and a fluctuation range significantly higher than the normal range of an ordinary household may indicate that the residence is rented by a group. However, the housing use status identification method in the related art is difficult to effectively exclude other situations that may cause abnormal fluctuations in water and electricity, and the importance assessment of variables relies on human experience, which is highly subjective and difficult to quantify, resulting in low recognition accuracy. Summary of the invention
[0004] Based on this, it is necessary to provide a method, device, equipment, medium and product for identifying the usage status of a house that can improve the recognition accuracy in response to the above technical problems.
[0005] In a first aspect, the present application provides a method for identifying a housing usage status. The method comprises:
[0006] Obtain multiple business atomic features corresponding to the business basic data of the house to be identified;
[0007] Extracting at least one target common factor of the house to be identified from the multiple business atomic features based on the correlation between the multiple business atomic features of the house to be identified;
[0008] Based on the contribution degrees of the multiple business atomic features to the target common factor respectively, the feature strength of the house to be identified on the target common factor is obtained, and the usage status of the house to be identified is identified based on the feature strength.
[0009] In one embodiment, determining the feature strength of the house to be identified on the common factor feature based on the contribution of the multiple business atomic features to the common factor feature respectively includes:
[0010] For each target common factor, based on the contribution of the multiple business atomic features to the target common factor, determine a score coefficient of the target common factor for each business atomic feature in the multiple business atomic features;
[0011] The score coefficients are used to linearly combine the multiple business atomic features to obtain the feature strength of the house to be identified on the target common factor.
[0012] In one of the embodiments, the process of determining the score coefficient of the target common factor for each of the multiple business atomic features based on the contribution of the multiple business atomic features to the target common factor adopts a weighted least squares method or a regression method.
[0013] In one embodiment, the identifying the usage status of the house to be identified based on the feature strength includes:
[0014] For each target common factor, determining the explanatory power of the target common factor on the business basic data of the house to be identified;
[0015] According to the feature strength of the house to be identified on each of the target common factors and the explanatory power representations corresponding to each of the target common factors, obtaining the target total feature strength of the house to be identified;
[0016] The target total feature strength is compared with a preset threshold, and the usage status of the house to be identified is identified according to the comparison result.
[0017] In one embodiment, the step of obtaining multiple business atomic features corresponding to the business basic data of the house to be identified includes:
[0018] Acquire the basic business data of the house to be identified;
[0019] Acquire the business basic features and business derived features of the house to be identified according to the business basic data; the business derived features are obtained by performing feature transformation or feature combination on the business basic data;
[0020] The multiple business atomic features are obtained by combining the business basic features and the business derived features.
[0021] In one of the embodiments, the basic business data includes gateway-attached device data of the house to be identified and broadband data of the house to be identified; wherein the gateway-attached device data is obtained through a probe deployed in the gateway of the house to be identified.
[0022] In a second aspect, the present application also provides a device for identifying the use status of a house. The device comprises:
[0023] An acquisition module, used to acquire multiple business atomic features corresponding to the business basic data of the house to be identified;
[0024] An extraction module, configured to extract at least one target common factor of the house to be identified from the multiple business atomic features based on the correlation between the multiple business atomic features of the house to be identified;
[0025] An identification module is used to obtain the feature strength of the house to be identified on the target common factor based on the contribution degree of the multiple business atomic features to the target common factor, and identify the usage status of the house to be identified based on the feature strength.
[0026] In a third aspect, the present application further provides a computer device. The computer device includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:
[0027] Obtain multiple business atomic features corresponding to the business basic data of the house to be identified;
[0028] Extracting at least one target common factor of the house to be identified from the multiple business atomic features based on the correlation between the multiple business atomic features of the house to be identified;
[0029] Based on the contribution degrees of the multiple business atomic features to the target common factor respectively, the feature strength of the house to be identified on the target common factor is obtained, and the usage status of the house to be identified is identified based on the feature strength.
[0030] In a fourth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented:
[0031] Obtain multiple business atomic features corresponding to the business basic data of the house to be identified;
[0032] Extracting at least one target common factor of the house to be identified from the multiple business atomic features based on the correlation between the multiple business atomic features of the house to be identified;
[0033] Based on the contribution degrees of the multiple business atomic features to the target common factor respectively, the feature strength of the house to be identified on the target common factor is obtained, and the usage status of the house to be identified is identified based on the feature strength.
[0034] In a fifth aspect, the present application further provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the following steps are implemented:
[0035] Obtain multiple business atomic features corresponding to the business basic data of the house to be identified;
[0036] Extracting at least one target common factor of the house to be identified from the multiple business atomic features based on the correlation between the multiple business atomic features of the house to be identified;
[0037] Based on the contribution degrees of the multiple business atomic features to the target common factor respectively, the feature strength of the house to be identified on the target common factor is obtained, and the usage status of the house to be identified is identified based on the feature strength.
[0038] The above-mentioned housing use status identification method, device, equipment, medium and product obtain multiple business atomic features corresponding to the business basic data of the house to be identified; based on the correlation between the multiple business atomic features of the house to be identified, extract at least one target common factor of the house to be identified from the multiple business atomic features; based on the contribution degree of the multiple business atomic features to the target common factor, obtain the feature strength of the house to be identified on the target common factor, and identify the use status of the house to be identified based on the feature strength. This application uses a factor analysis method to extract the target common factor from the multiple business atomic features corresponding to the business basic data of the house to be identified. The number of target common factors is less than the number of business atomic features. Multidimensional data is abstracted into low-dimensional common factors, and the main influencing factors are extracted from a large number of data features, and the feature importance is assigned. The model can clearly know the importance of each feature, and then obtain the feature strength of the house to be identified on the target common factor through the contribution degree of multiple business atomic features to the target common factor, thereby identifying the use status of the house to be identified, avoiding interference from subjective factors, and improving the recognition accuracy. BRIEF DESCRIPTION OF THE DRAWINGS
[0039] Figure 1 is an application environment diagram of a housing use status identification method in one embodiment;
[0040] Figure 2 A schematic diagram of a flow chart of a method for identifying a housing usage status in one embodiment;
[0041] Figure 3 A schematic diagram of a flow chart of steps for obtaining multiple service atomic features in one embodiment;
[0042] Figure 4A schematic flow chart of a step of determining the feature strength of a house to be identified on a common factor feature in one embodiment;
[0043] Figure 5 A schematic diagram of a flow chart of a step of identifying the usage status of a house to be identified in an embodiment;
[0044] Figure 6 A schematic diagram of constructing atomic data features in one embodiment;
[0045] Figure 7 is a structural block diagram of a housing use status identification device in one embodiment;
[0046] Figure 8 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION
[0047] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0048] FA (Factor Analysis): used to simplify data sets and reveal the relationship between variables, decomposing variables into linear combinations of common factors and special factors, and reflecting the correlation between the original p variables through m common factors (m<p). It helps reduce the dimension of data, reduce redundant information, and gain insight into the relationship between variables by finding potential factors in the data that can explain the relationship between observed variables.
[0049] DPI (Deep Packet Inspection): A technology that analyzes the contents of data packets to identify device and traffic characteristics, and is used to accurately capture the Internet behavior data of user terminals.
[0050] This application belongs to the field of big data and artificial intelligence, and in particular, it relates to intelligent analysis and house usage status detection technology based on home gateway data. Among the house usage status identification methods in related technologies, there are methods for identifying group rental houses based on fluctuations in water and electricity usage, and for identifying group rental houses based on user online shopping orders and mobile phone numbers. These technologies are based on data foundations that infer family population through certain quantitative changes. When assigning weights to each variable, they are based on a human experience judgment method, which cannot well evaluate the importance of the variable.
[0051] The housing usage status recognition method provided in the embodiment of the present application can be applied to Figure 1In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. Among them, the terminal 102 can be but is not limited to various personal computers, laptops, smart phones, tablets, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car-mounted devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The server 104 can be implemented with an independent server or a server cluster consisting of multiple servers.
[0052] In one embodiment, Figure 2 As shown, a housing usage status recognition method is provided, and the method is applied to Figure 1 Taking the server 104 in the example as an example, the following steps are included:
[0053] Step 202: Acquire multiple business atomic features corresponding to the business basic data of the house to be identified.
[0054] Among them, multiple business atomic features are used to indicate business data information related to the house to be identified.
[0055] Exemplarily, the server obtains basic business data of the house to be identified, and extracts features from the basic business data to determine multiple business atomic features.
[0056] Step 204: extract at least one target common factor of the house to be identified from the multiple business atomic features based on the correlation between the multiple business atomic features of the house to be identified.
[0057] Among them, the number of target common factors is less than the number of business atomic features.
[0058] The embodiment of the present application analyzes the basic structure of multiple business atomic feature data based on the internal dependency relationship between multiple business atomic features of the house to be identified, and extracts a few target common factors to represent its basic data structure. This target common factor can reflect the main information of the original multiple business atomic features. Multiple business atomic features are observable explicit variables, while the target common factor is an unobservable potential variable.
[0059] For example, the server analyzes the correlation between multiple business atomic features of the house to be identified, and determines the feature vector corresponding to the feature root greater than the preset feature root threshold as the target common factor. Alternatively, based on the gravel principle, the server arranges the feature roots from large to small, and deletes the initial common factor corresponding to the feature root decreasing speed slowing down.
[0060] Step 206, based on the contribution of multiple business atomic features to the target common factor, obtain the feature strength of the house to be identified on the target common factor, and identify the usage status of the house to be identified based on the feature strength.
[0061] The contribution degree of the business atomic feature to the target common factor is used to indicate the correlation between the business atomic feature and the target common factor.
[0062] In the above-mentioned housing usage status identification method, multiple business atomic features corresponding to the business basic data of the housing to be identified are obtained; based on the correlation between the multiple business atomic features of the housing to be identified, at least one target common factor of the housing to be identified is extracted from the multiple business atomic features; based on the contribution of the multiple business atomic features to the target common factor, the feature strength of the housing to be identified on the target common factor is obtained, and the usage status of the housing to be identified is identified based on the feature strength. The embodiment of the present application uses a factor analysis method to extract the target common factor from the multiple business atomic features corresponding to the business basic data of the housing to be identified. The number of target common factors is less than the number of business atomic features. Multidimensional data is abstracted into low-dimensional common factors, and the main influencing factors are extracted from a large number of data features, and the feature importance is assigned. The model can clearly know the importance of each feature, and then the feature strength of the housing to be identified on the target common factor is obtained through the contribution of multiple business atomic features to the target common factor, thereby identifying the usage status of the housing to be identified to avoid interference from subjective factors and improve the recognition accuracy.
[0063] In one embodiment, Figure 3 As shown, the steps of obtaining multiple business atomic features corresponding to the business basic data of the house to be identified include:
[0064] Step 302, obtaining the basic business data of the house to be identified.
[0065] Among them, the basic business data includes the gateway-attached device data of the house to be identified and the broadband data of the house to be identified; wherein the gateway-attached device data is obtained through a probe deployed in the gateway of the house to be identified.
[0066] For example, the server of the embodiment of the present application obtains the basic business data information such as online time, traffic, device brand, model, category, app usage, high traffic time, etc. of the devices connected to the gateway in real time through the probe deployed on the home gateway of the house to be identified. The server can also obtain the basic business data of the home broadband installation address information and the basic business data of the broadband package information through the broadband service provider.
[0067] Step 304, obtaining the business basic features and business derived features of the house to be identified based on the business basic data.
[0068] Among them, the business-derived features are obtained by performing feature transformation or feature combination on the business basic data.
[0069] Exemplarily, the server directly extracts basic business features from basic business data, such as directly extracting key fields as basic features. The server can also combine or transform multiple variables to obtain business-derived features. These transformations can include mathematical operations (such as addition, multiplication, logarithm, etc.), statistical characteristics (such as mean, variance, etc.), and derivation based on business logic (such as time difference, frequency, etc.), such as annual similarity of mobile phone terminals and number of mobile phones / number of rooms. These feature transformations are the core of volatility and group living, the two major factors that affect group rental housing. Too large or too many can reflect that it is a group rental housing.
[0070] Step 306: Combine the basic service features and the derived service features to obtain multiple service atomic features.
[0071] In this embodiment, based on the data collection of the gateway, the biggest feature of group rental housing is its high mobility and dense population. The number and changes of terminals connected to the gateway can more intuitively reflect the changes in the family population and the population size. At the same time, by performing feature transformation or feature combination on the basic business data to obtain business-derived features, combined with the directly extracted business basic features, multiple business atomic features are obtained. This feature can better reflect the important information in the task of identifying group rental housing, and can be used to improve the prediction accuracy or recognition effect during the analysis process.
[0072] In one embodiment, Figure 4 As shown, based on the contribution of multiple business atomic features to the common factor features, the feature strength of the house to be identified on the common factor features is determined, including:
[0073] Step 402 : for each target common factor, based on the contribution of the multiple business atomic features to the target common factor, determine the score coefficient of the target common factor to each business atomic feature in the multiple business atomic features.
[0074] Among them, the contribution degree of multiple business atomic features to the target common factor can be expressed by the load coefficient in the rotated factor loading matrix.
[0075] Exemplarily, the server extracts common factors through principal component analysis, and then applies methods such as orthogonal rotation or oblique rotation to optimize the factor loading matrix to obtain the rotated factor loading matrix, in which the loading value of each common factor is more concentrated and easier to interpret. The larger the absolute value of the loading coefficient of a variable, i.e., a business atomic feature, on a target common factor, the more relevant the business atomic feature is to the target common factor. For example, an embodiment of the present application extracts four common factors from business data collected based on gateway data, and analyzes the contribution of multiple business atomic features to the common factor features through the rotated factor loading matrix, and obtains the explanatory representation of each common factor, such as liquidity, economy, convenience, and sociability.
[0076] After obtaining the contribution of multiple business atomic features to the target common factor, the server of the embodiment of the present application uses a weighted least square method or a regression method based on the factor loading matrix to calculate a component score coefficient matrix, and the component score coefficient matrix includes the score coefficients of each target common factor to each business atomic feature in the multiple business atomic features. For example, the relationship between the original variable and the factor is fitted by the least square method to ensure that the factor score is optimal when explaining the factor variance, or when estimating the factor score, the covariance of the factor score and the factor loading is constrained to be zero.
[0077] Step 404, using the score coefficients to linearly combine multiple business atomic features to obtain the feature strength of the house to be identified on the target common factor.
[0078] The characteristic strength of the house to be identified on the target common factor can be represented by the factor score of the target common factor.
[0079] Exemplarily, the factor score function is an expression that linearly combines the original variables into factor scores. For each target common factor, according to the score coefficient of the target common factor for each business atomic feature, the factor score of the linear combination of the target common factor represented by multiple business atomic features is obtained.
[0080] In this embodiment, by adopting the factor analysis method, the main influencing factors can be extracted from a large number of data features, and the features are assigned importance. The basic data dimensions are abstracted into low-dimensional common factors, and the linear combination of common factors and variables is obtained through the component score matrix, so as to calculate the factor score and avoid interference from subjective factors.
[0081] In one embodiment, Figure 5 As shown, the use status of the house to be identified is identified based on the feature strength, including:
[0082] Step 502: for each target common factor, determine the explanatory power of the target common factor on the business basic data of the house to be identified.
[0083] Among them, the explanatory power of the target common factor on the business basic data of the identified house can be represented by the variance contribution rate of the target common factor.
[0084] Step 504, obtaining the target total feature strength of the house to be identified according to the feature strength of the house to be identified on each target common factor and the explanatory power representation corresponding to each target common factor.
[0085] Exemplarily, the server obtains a group rental housing evaluation function through the factor scores of each target common factor and the variance contribution rate of each target common factor, and determines the evaluation score of the group rental housing, that is, the target total feature strength of the house to be identified.
[0086] Step 506, comparing the target total feature strength with a preset threshold, and identifying the usage status of the house to be identified based on the comparison result.
[0087] Exemplarily, when the computer device determines that the target total feature strength is greater than a preset threshold, it determines that the house to be identified meets the pattern of a shared rental house. When the computer device determines that the target total feature strength is less than or equal to the preset threshold, it determines that the house to be identified does not meet the pattern of a shared rental house.
[0088] In one embodiment, taking the example of a computer device acquiring raw data through a probe of a home gateway, and the computer device being able to acquire address information and package information for broadband processing, the embodiment of the present application provides a method for identifying a housing usage status, the method comprising the following contents:
[0089] Step A, obtaining basic data of the housing business to be identified.
[0090] The embodiment of the present application collects multi-dimensional data related to the business of the house to be identified in real time through the probe deployed on the home gateway, and can also obtain the broadband installation address through the broadband service provider or customer relationship management system (CRM), so as to collect relevant information of the installation area, such as geographical location, environmental attributes (community or self-built house, etc.), and broadband-related package information.
[0091] For example, computer equipment can obtain relevant basic business data of the terminal devices connected to the gateway in real time through the probes deployed on the home gateway. The relevant business data of the terminal devices include the online time of the terminal devices, the traffic usage of the terminal devices at the corresponding time, the device brand of the terminal devices, the device model of the terminal devices, the device category of the terminal devices, the apps accessed by the terminal devices, and the period of high traffic usage. In addition, computer equipment can also obtain the installation address information of the home broadband.
[0092] Step B: construct atomic data features based on the basic data of the housing business to be identified.
[0093] The atomic data feature refers to the minimized basic data unit extracted from the basic data of the housing business to be identified in the embodiment of the present application, which can be directly obtained through data collection or obtained through feature transformation calculation or derived variables, such as Figure 6 shown.
[0094] For example, taking home terminal devices as the core, terminal-related features are extracted from terminal-related data to construct terminal business atomic features, such as device quantity-related features, price and type-related features, usage period distribution features, and terminal annual similarity features. Specifically, these may include the number of mobile phones in the home, mobile phone prices, whether there are IoT devices, the number of IoT device categories, time period distribution of mobile phone terminals, the average number of mobile phones per room, the number of mobile phones / rooms, and the annual similarity of mobile phone terminals. The similarity calculation can be: (μ_1∩μ_2)÷(μ_1∪μ_2), where μ is the set of mobile phone macs.
[0095] For another example, atomic features of access behavior are extracted from user access behavior data, such as access application features and traffic usage pattern features, which may specifically include applications accessed by mobile phones, peak time distribution of mobile Internet traffic, etc.
[0096] For example, atomic features of household attributes are extracted from bandwidth and CRM data, such as community information features, location features, and package information features. Specifically, these may include community housing prices, house types, floors, whether they are self-built houses, subway distance, bandwidth, packages, etc. determined based on the broadband installation address.
[0097] Step C, factor analysis: Based on the features obtained in step B, a factor model is constructed and the common factor F is evaluated. Factor rotation can be continued. The rotated factor loading matrix can intuitively reflect the contribution of each variable to the principal component. The larger the absolute value of the loading coefficient of a variable on a common factor, the more relevant the variable is to the common factor.
[0098] Specifically, the common factors can be evaluated using the following method:
[0099] Assume that X is known and A and Φ are known, through the factor model , we need to estimate the common factor F. Multiply both sides of the model by ,get Among them, record ; ; , then we get a new random variable X * Model: ; The factor ε * The variance term satisfies ; When X is known and standardized, and A and Φ are known, A *, X * It is also known that as long as we minimize The F estimate can be obtained, that is, the least squares estimate. The least squares estimate of F (actually the weighted least squares estimate) can be expressed as: .
[0100] Step D, calculate factor scores.
[0101] After determining the factors, we further calculate the scores of each factor. We can calculate the coefficient matrix of the factors corresponding to each observation. According to the component score coefficient matrix, we can get the factor score function of the linear combination of the common factor F represented by the variable X, and finally calculate the factor score of each rental.
[0102] For example, in actual use, suppose X has n groups of observations, denoted as ; The kth row is recorded as , is the kth observation of X. Assuming that each column of M is standardized, we can take the sample correlation matrix R from M, and then use the eigenvalues of R to estimate A and Φ. Assuming that A and Φ are obtained, then the kth observation of X The calculation formula for the factor score is:
[0103] ;
[0104] ;
[0105] The factor scores of all n observations can be written as the following matrix:
[0106] ;
[0107] in, It is an n*m matrix, each row is the factor score corresponding to an observation, and each column is all the observed values of a factor.
[0108] Step E, determine group rental housing: After factor analysis, the component score coefficient matrix is shown in Table 1. Each component represents a target common factor. The interpretation of the four target common factors can be mobility, economy, convenience, and group living.
[0109] Table 1
[0110]
[0111] Linear combination can be used to calculate the score of each factor as follows:
[0112] F1 = alph101*terminal price+alph102*number of mobile phones+alph103*annual mobile phone volatility+ ...;
[0113] F2 = alph201*terminal price+alph202*number of mobile phones+alph203*annual mobile phone volatility+ ...;
[0114] F3 = alph301*terminal price+alph302*number of mobile phones+alph303*annual mobile phone volatility+ ...;
[0115] F4 = alph401*terminal price+alph402*number of mobile phones+alph403*annual mobile phone volatility+ ...;
[0116] Through the above factor scoring function, the group rental scoring function is constructed, and the group rental evaluation function is calculated using the variance contribution rate. Assuming that the variance contribution rate of each factor is lamda1, lamda2, lamda3, and lamda4, the group rental evaluation function is as follows:
[0117] z_score=(F1*lamda1+F2*lamda2+F3*lamda3+F4*lamda4) / sum(lamda1,lamda2,lamda3,lamda4);
[0118] Among them, z_score represents the house usage status score, that is, the total feature strength of the target.
[0119] According to the z_score sorting by size, group rental users can be identified based on a certain threshold.
[0120] In this embodiment, based on the data of the home gateway and broadband, the address for applying for broadband can be accurately located. Through the DPI probe in the household optical modem, the terminal device connected to the optical modem can be reported in real time and the type of terminal device can be identified. With the home address and the category of the Internet terminal in the home, the terminal's change characteristics, value, Internet behavior and other characteristic receipts, the biggest feature of group rental housing is its high mobility and dense population. The number and changes of terminals hanging from the gateway can more intuitively reflect the changes in the family population and the population size. Through factor analysis, the factors affecting group rental housing are abstracted, including economy, mobility, group living, and convenience. After normalization of the variance explanation rate after rotation, the weights of the four factors are obtained, and the score of group rental housing can be calculated to avoid interference from subjective factors and improve recognition efficiency.
[0121] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.
[0122] Based on the same inventive concept, the embodiment of the present application also provides a house use status recognition device for implementing the house use status recognition method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more house use status recognition device embodiments provided below can refer to the limitations of the house use status recognition method above, and will not be repeated here.
[0123] In one embodiment, Figure 7 As shown, a housing use status recognition device is provided, comprising: an acquisition module 702, an extraction module 704 and a recognition module 706, wherein:
[0124] An acquisition module 702 is used to acquire multiple business atomic features corresponding to the business basic data of the house to be identified;
[0125] An extraction module 704, configured to extract at least one target common factor of the house to be identified from the multiple business atomic features based on the correlation between the multiple business atomic features of the house to be identified;
[0126] The identification module 706 is used to obtain the feature strength of the house to be identified on the target common factor based on the contribution degree of the multiple business atomic features to the target common factor, and identify the usage status of the house to be identified based on the feature strength.
[0127] Each module in the above-mentioned house usage status recognition device can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each module.
[0128] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 8 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for identifying the use status of a house is implemented.
[0129] Those skilled in the art will understand that Figure 8 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.
[0130] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.
[0131] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.
[0132] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.
[0133] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions.
[0134] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.
[0135] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0136] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.
Claims
1. A method for identifying housing usage status, characterized in that: The method comprises: Obtain multiple business atomic features corresponding to the business basic data of the house to be identified; Extracting at least one target common factor of the house to be identified from the multiple business atomic features based on the correlation between the multiple business atomic features of the house to be identified; Based on the contribution degrees of the multiple business atomic features to the target common factor, the feature strength of the house to be identified on the target common factor is obtained, and the usage status of the house to be identified is identified based on the feature strength.
2. The method according to claim 1, characterized in that: The determining the feature strength of the house to be identified on the common factor feature based on the contribution of the multiple business atomic features to the common factor feature respectively includes: For each target common factor, based on the contribution of the multiple business atomic features to the target common factor, determine a score coefficient of the target common factor for each business atomic feature in the multiple business atomic features; The score coefficients are used to linearly combine the multiple business atomic features to obtain the feature strength of the house to be identified on the target common factor.
3. The method according to claim 2, characterized in that The process of determining the score coefficient of the target common factor for each of the multiple business atomic features based on the contribution of the multiple business atomic features to the target common factor adopts a weighted least squares method or a regression method.
4. The method according to claim 1, characterized in that The identifying the usage status of the house to be identified based on the feature strength includes: For each target common factor, determining the explanatory power of the target common factor on the business basic data of the house to be identified; According to the feature strength of the house to be identified on each of the target common factors and the explanatory power representations corresponding to each of the target common factors, obtaining the target total feature strength of the house to be identified; The target total feature strength is compared with a preset threshold, and the usage status of the house to be identified is identified according to the comparison result.
5. The method according to claim 1, characterized in that: The step of obtaining multiple business atomic features corresponding to the business basic data of the house to be identified includes: Acquire the basic business data of the house to be identified; Acquire the business basic features and business derived features of the house to be identified according to the business basic data; the business derived features are obtained by performing feature transformation or feature combination on the business basic data; The multiple business atomic features are obtained by combining the business basic features and the business derived features.
6. The method according to claim 5, characterized in that The basic business data includes the gateway-attached device data of the house to be identified and the broadband data of the house to be identified; wherein the gateway-attached device data is obtained through a probe deployed in the gateway of the house to be identified.
7. A device for identifying housing usage status, characterized in that: The device comprises: An acquisition module, used to acquire multiple business atomic features corresponding to the business basic data of the house to be identified; An extraction module, configured to extract at least one target common factor of the house to be identified from the multiple business atomic features based on the correlation between the multiple business atomic features of the house to be identified; An identification module is used to obtain the feature strength of the house to be identified on the target common factor based on the contribution degree of the multiple business atomic features to the target common factor, and identify the usage status of the house to be identified based on the feature strength.
8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.
10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.