Public rental housing management and risk assessment system based on big data and artificial intelligence

Abstract

The invention relates to the field of public rental housing management, and discloses a public rental housing management and risk assessment system based on big data and artificial intelligence, which comprises a data collection module, a public rental housing information module, a management module and a risk assessment module, and is characterized in that the data collection module collects tenant information data and rental information data of tenants; housing information data of the public rental housing is input through the public rental housing information module; the management module analyzes the lessee information data and the housing information data and distributes public rental houses to the tenants according to the analysis result; analyzing the leasing information data, the housing information data and the renting information data through a risk evaluation module to obtain a comprehensive risk index, and judging whether the renting of the tenant is abnormal or not; the public rental housing allocated by the tenant can better meet the potential requirements of the resident, and the risk of subleasing after the tenant applies is reduced; whether renting of the tenant is abnormal or not is judged in time through the comprehensive risk index; and effective management of the management terminal on the public rental housing is effectively enhanced.

Description

Technical Field

[0001] The present invention relates to the field of public rental housing management, and in particular to a public rental housing management and risk assessment system based on big data and artificial intelligence. Background Art

[0002] Public rental housing is public welfare rental housing provided by the state to solve the housing problems of lower-middle-income families with housing difficulties in cities, newly employed employees without housing, and migrant workers with stable employment in cities.

[0003] The application process for public rental housing is generally that the applicant needs to submit application materials to the relevant department. The relevant department will review the applicant's materials to determine whether they meet the requirements. If they meet the requirements, the applicant will become a tenant and the housing will be allocated according to the actual situation of the tenant. Generally, it will be allocated according to the area and number of people. Since public rental housing is welfare rental housing, it is provided to tenants and their co-residents who apply for it. Subletting or sharing is not allowed.

[0004] However, due to the different needs of different applicants, for example, the needs of elderly applicants may be close to the hospital and on a lower floor; while the needs of middle-aged applicants may be convenient transportation. If the public rental housing is allocated only based on the area and number of people, the allocated public rental housing may not match the needs of the applicants, and there is a great risk that the tenants will sublet the allocated public rental housing to others, making it difficult for the relevant departments to manage public rental housing. Summary of the invention

[0005] The purpose of this invention is to provide a public rental housing management and risk assessment system based on big data and artificial intelligence to solve the following technical problems:

[0006] How to improve the matching degree between allocated public rental housing and tenants’ needs.

[0007] The purpose of the present invention can be achieved through the following technical solutions:

[0008] A public rental housing management and risk assessment system based on big data and artificial intelligence, the management and risk assessment system comprising:

[0009] A data collection module is used to collect the lessee's leasing information data and the lessee's rental information data;

[0010] Public rental housing information module, used to input housing information data of public rental housing;

[0011] A management module is used to analyze the tenant information data and housing information data, and allocate public rental housing to the tenant according to the analysis results;

[0012] The risk assessment module is used to analyze the lessee information data, housing information data, and rental information data to obtain a comprehensive risk index; and to determine whether the lessee's rental is abnormal based on the comprehensive risk index.

[0013] As a further solution of the present invention: the tenant information data includes the tenant's age, the number of co-residents, the co-residents' ages and the desired landmark location;

[0014] The housing information data includes preset resident ages, preset occupancy numbers and housing locations.

[0015] As a further solution of the present invention: the analysis process of the management module includes:

[0016] S1: Obtain the matching index between the tenant and each public rental housing by analyzing the tenant's age, number of co-residents, age of co-residents, expected landmark location, the preset resident age, number of occupants and housing location of each public rental housing;

[0017] S2: Allocate the public housing unit with the highest matching index between the tenant and each public housing unit to the tenant.

[0018] As a further solution of the present invention: the matching index includes the formula:

[0019]

[0020] Calculate the matching index P between the nth public rental housing and the tenant n ;

[0021] Among them, A c A is the age of the lessee; n is the preset age of residents in the nth public rental housing; M is the number of co-residents of the tenant; A m is the age of the mth co-resident; Q n is the preset number of occupants of the nth public rental housing; S n is the distance between the housing location of the nth public rental housing and the desired landmark location of the tenant; P0 is the basic matching index; γ1 is the first weight coefficient; γ2 is the second weight coefficient; γ3 is the third weight coefficient; γ4 is the fourth weight coefficient; C1 is the first preset constant; C2 is the second preset constant; C3 is the third preset constant; C4 is the fourth preset constant.

[0022] As a further solution of the present invention: the rental information data includes the monthly fingerprint door opening times of the tenant, the monthly fingerprint door opening times of each co-resident, the monthly water consumption and monthly electricity consumption of the public rental housing.

[0023] As a further solution of the present invention: the process of obtaining the comprehensive risk index is:

[0024] S100: After the lessee moves into the allocated public rental housing, the fingerprint information of the smart door lock is cleared and the fingerprint information of the lessee and his / her co-resident is re-entered;

[0025] S200: Obtaining the first risk index by analyzing the monthly fingerprint door opening times of the lessee and the monthly fingerprint door opening times of each co-resident;

[0026] S300: Obtain the second risk index by analyzing the monthly water consumption and monthly electricity consumption of public rental housing;

[0027] S400: Calculate a comprehensive risk index by performing a matching index, a first risk index and a second risk index according to a preset formula.

[0028] As a further solution of the present invention: the first risk index is obtained by the formula:

[0029]

[0030] Calculate the first risk index F1;

[0031] Wherein, f(X) is the judgment function. When X>0, f(X)=X; when X≤0, f(X)=0; K0 is the preset number; K m The monthly fingerprint door opening times of the mth co-resident; K C Monthly fingerprint door opening times for tenants.

[0032] As a further solution of the present invention: the second risk index is obtained by the formula:

[0033]

[0034] Calculate the second risk index F2;

[0035] Among them, Q W is the monthly water consumption of the previous month, σ W is the monthly water consumption adjustment coefficient of the previous month; Q1 is the basic water consumption per person; W1 is the allowable error value of water consumption; Q D is the monthly electricity consumption of the previous month; D is the monthly electricity consumption adjustment coefficient of the previous month; Q2 is the basic single-person electricity consumption; W2 is the allowable error value of electricity consumption.

[0036] As a further solution of the present invention: the preset formula is:

[0037] Calculate the comprehensive risk index F Z ;

[0038] Among them, P Cis the actual matching index between the allocated public rental housing and the tenants; δ1 is the first comprehensive weight coefficient; δ2 is the second comprehensive weight coefficient; δ3 is the third comprehensive weight coefficient.

[0039] Beneficial effects of the present invention:

[0040] The present invention collects the lessee's leasing information data and the lessee's rental information data through a data collection module; inputs the housing information data of public rental housing through a public rental housing information module; analyzes the leasing information data and the housing information data through a management module, and allocates public rental housing to the lessee according to the analysis result; analyzes the leasing information data, the housing information data and the rental information data through a risk assessment module to obtain a comprehensive risk index; and judges whether the lessee's rental is abnormal according to the comprehensive risk index; so that the public rental housing allocated to the lessee can better meet the potential requirements of the residents, and reduce the risk of subletting after the lessee applies; and timely judges whether the lessee's rental is abnormal through the comprehensive risk index; when it is judged to be abnormal, the management terminal is warned in time, and the effective management of the public rental housing by the management terminal is effectively strengthened. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The present invention will be further described below in conjunction with the accompanying drawings.

[0042] Figure 1 A system module framework diagram of an embodiment of the present invention. DETAILED DESCRIPTION

[0043] 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.

[0044] See also Figure 1 As shown, in one embodiment, a public rental housing management and risk assessment system based on big data and artificial intelligence is provided, and the management and risk assessment system includes:

[0045] A data collection module is used to collect the lessee's leasing information data and the lessee's rental information data;

[0046] Public rental housing information module, used to input housing information data of public rental housing;

[0047] A management module is used to analyze the tenant information data and housing information data, and allocate public rental housing to the tenant according to the analysis results;

[0048] The risk assessment module is used to analyze the tenant information data, housing information data, and rental information data to obtain a comprehensive risk index; and to determine whether the tenant's rental is abnormal based on the comprehensive risk index;

[0049] Through the above technical scheme, this embodiment collects the lessee's leasing information data and the lessee's rental information data through the data collection module; enters the housing information data of public rental housing through the public rental housing information module; analyzes the leasing information data and the housing information data through the management module, and allocates public rental housing to the lessee according to the analysis results; analyzes the leasing information data, the housing information data and the rental information data through the risk assessment module to obtain a comprehensive risk index; and judges whether the lessee's rental is abnormal according to the comprehensive risk index; so that the public rental housing allocated to the lessee can better meet the potential requirements of the residents and reduce the risk of subletting after the lessee applies; and judges whether the lessee's rental is abnormal in time through the comprehensive risk index; when it is judged to be abnormal, the management terminal is warned in time, effectively strengthening the effective management of public rental housing by the management terminal.

[0050] As an implementation mode of the present invention, the tenant information data includes the tenant's age, the number of co-residents, the co-residents' ages and the desired landmark location;

[0051] The housing information data includes preset resident age, preset number of occupants and housing location;

[0052] Through the above technical solution, in this embodiment, the staff analyzes the information such as the housing location, surrounding facilities and the floor where the housing is located to obtain the preset age of the residents, so that the public rental housing allocated to the tenant in the later stage can better meet the potential requirements of the residents and reduce the risk of the tenant subletting after the application;

[0053] It should be noted that the method of obtaining the preset number of occupants and housing location of public rental housing is an existing technology. The tenant's age, the number of co-residents, the age of co-residents and the desired landmark location can be obtained through the tenant's application form and will not be elaborated here.

[0054] As an implementation manner of the present invention, the analysis process of the management module includes:

[0055] S1: Obtain the matching index between the tenant and each public rental housing by analyzing the tenant's age, number of co-residents, age of co-residents, expected landmark location, the preset resident age, number of occupants and housing location of each public rental housing;

[0056] S2: Allocate the public rental housing with the highest matching index between the tenant and each public rental housing to the tenant;

[0057] Through the above technical scheme, this embodiment obtains the matching index between the tenant and each public rental housing by analyzing the tenant's age, the number of co-residents, the age of the co-residents, the expected landmark location, the preset resident age of each public rental housing, the preset number of occupants and the housing location; the public rental housing with the highest matching index between the tenant and each public rental housing is allocated to the tenant; the public rental housing allocated to the tenant is made to match the tenant as closely as possible, thereby reducing the risk of subletting.

[0058] As an embodiment of the present invention, the matching index includes the following formula:

[0059]

[0060] Calculate the matching index P between the nth public rental housing and the tenant n ;

[0061] Among them, A c A is the age of the lessee; n is the preset age of residents in the nth public rental housing; M is the number of co-residents of the tenant; A m is the age of the mth co-resident; Q n is the preset number of occupants of the nth public rental housing; S n is the distance between the housing location of the nth public rental housing and the desired landmark location of the lessee; P0 is the basic matching index; γ1 is the first weight coefficient; γ2 is the second weight coefficient; γ3 is the third weight coefficient; γ4 is the fourth weight coefficient; C1 is the first preset constant; C2 is the second preset constant; C3 is the third preset constant; C4 is the fourth preset constant;

[0062] Through the above technical solution, this embodiment |A c -A n | is the absolute value of the difference between the tenant's age and the preset resident's age of the nth public rental housing, the absolute value of the difference between the tenant's age and the preset resident's age of the nth public rental housing|A c -A n The larger the value of |, the greater the age difference between the tenant and the preset age of the resident of the nth public rental housing, and the lower the matching degree. Therefore, the matching index P between the nth public rental housing and the tenant is n The smaller; |A m -A n | is the absolute value of the difference between the age of the mth co-resident and the preset age of the resident of the nth public rental housing, the absolute value of the difference between the age of the mth co-resident and the preset age of the resident of the nth public rental housing|A m -A n The larger the value of |, the greater the age difference between the mth co-resident and the preset age of the nth public rental housing, and the lower the matching degree. Therefore, the matching index P of the nth public rental housing and the tenant is n The smaller; is the cumulative value of the absolute value of the difference between the ages of the M co-residents and the preset age of the residents of the nth public rental housing, the cumulative value of the absolute value of the difference between the ages of the M co-residents and the preset age of the residents of the nth public rental housing The larger the value is, the greater the age difference between the M co-residents and the preset age of the residents of the nth public rental housing is, and the lower the matching degree is. Therefore, the matching index P of the nth public rental housing and the tenant is n The smaller; M+1 is the number of people living in the public rental housing applied for by the tenant; |M+1-Q n | is the absolute value of the difference between the number of residents in the public rental housing applied by the tenant and the preset number of residents; the absolute value of the difference between the number of residents in the public rental housing applied by the tenant and the preset number of residents|M+1-Q n The larger the | is, the greater the difference between the number of residents in the public rental housing applied by the tenant and the preset number of residents, and the lower the matching degree. Therefore, the matching index P of the nth public rental housing and the tenant is n The smaller the distance S between the location of the nth public rental housing and the desired landmark location of the tenant n The larger the value, the lower the matching degree. Therefore, the matching index P between the nth public rental housing and the tenant is n The smaller;

[0063] It should be noted that the basic matching index P0, the first weight coefficient γ1, the second weight coefficient γ2, the third weight coefficient γ3, the fourth weight coefficient γ4, the first preset constant C1, the second preset constant C2, the third preset constant C3 and the fourth preset constant C4 are preset values, which are obtained based on experience and will not be described in detail here.

[0064] As an implementation mode of the present invention, the rental information data includes the monthly fingerprint door opening times of the lessee, the monthly fingerprint door opening times of each co-resident, the monthly water consumption and monthly electricity consumption of the public rental housing;

[0065] As an implementation mode of the present invention, the process of obtaining the comprehensive risk index is as follows:

[0066] S100: After the lessee moves into the allocated public rental housing, the fingerprint information of the smart door lock is cleared and the fingerprint information of the lessee and his / her co-resident is re-entered;

[0067] S200: Obtaining the first risk index by analyzing the monthly fingerprint door opening times of the lessee and the monthly fingerprint door opening times of each co-resident;

[0068] S300: Obtain the second risk index by analyzing the monthly water consumption and monthly electricity consumption of public rental housing;

[0069] S400: Calculating a comprehensive risk index by performing a matching index, a first risk index, and a second risk index according to a preset formula;

[0070] As an implementation mode of the present invention, the first risk index is calculated by the formula:

[0071]

[0072] Calculate the first risk index F1;

[0073] Wherein, f(X) is the judgment function. When X>0, f(X)=X; when X≤0, f(X)=0; K0 is the preset number; K m The monthly fingerprint door opening times of the mth co-resident; K C Monthly fingerprint door opening times for tenants;

[0074] Through the above technical solution, this embodiment K0-K m is the difference between the preset number and the monthly fingerprint door opening number of the mth co-resident; when K0-K m When K0-K m >0, it means that the monthly fingerprint door opening times of the mth co-resident are less than the preset times, and the difference between the preset times and the monthly fingerprint door opening times of the mth co-resident is K0-K m The larger the value, the smaller the probability that the mth co-resident lives in a public rental housing, the lower the integrity of the tenant, and the larger the first risk index F1; K0-K C is the difference between the preset number and the monthly fingerprint door opening number of the lessee; when K0-K C When K0-K C >0, it means that the lessee's monthly fingerprint door opening times are less than the preset times, and the difference between the preset times and the lessee's monthly fingerprint door opening times is K0-K m The larger the value, the lower the probability that the tenant lives in public housing. The lower the tenant's integrity, the larger the first risk index F1.

[0075] It should be noted that the preset number K0 is a preset value, obtained based on experience, and the monthly fingerprint door opening number K of the mth co-resident is m and the monthly fingerprint door opening times K of the lessee C The method for obtaining is prior art and will not be described in detail here.

[0076] As an embodiment of the present invention, the second risk index is calculated by the formula:

[0077]

[0078] Calculate the second risk index F2;

[0079] Among them, Q W is the monthly water consumption of the previous month, σ W is the monthly water consumption adjustment coefficient of the previous month; Q1 is the basic water consumption per person; W1 is the allowable error value of water consumption; Q D is the monthly electricity consumption of the previous month; D is the monthly electricity consumption adjustment coefficient of the previous month; Q2 is the basic single-person electricity consumption; W2 is the allowable error value of electricity consumption;

[0080] Through the above technical solution, this embodiment is the actual monthly water consumption per person in the previous month; W Q1 is the preset water consumption per person last month; It is the difference between the actual monthly water consumption per person last month and the preset monthly water consumption per person last month; It is the difference between the actual monthly water consumption per person last month and the preset monthly water consumption per person last month and the allowable error value of water consumption; When , it means that the difference between the actual monthly water consumption per person last month and the preset monthly water consumption per person last month is within the allowable error range of water consumption, and there is no risk; when , it means that the difference between the actual monthly water consumption per person last month and the preset single-person water consumption last month exceeds the allowable error value of water consumption. The actual number of people may be different from the number of people applied for by the tenant, and there is a risk. The difference between the actual monthly water consumption per person last month and the preset single-person water consumption last month and the allowable error value of water consumption is The larger it is, the larger the second risk index F2 is; is the actual monthly electricity consumption per person in the previous month; D Q2 is the preset single-person electricity consumption for the previous month; It is the difference between the actual monthly electricity consumption per person last month and the preset monthly electricity consumption per person last month; The difference between the actual monthly electricity consumption per person last month and the preset monthly electricity consumption per person last month and the allowable error value of electricity consumption; When , it means that the difference between the actual monthly electricity consumption of a single person last month and the preset single electricity consumption of last month is within the allowable error value of electricity consumption, and there is no risk; when , it means that the difference between the actual monthly electricity consumption per person last month and the preset single-person electricity consumption last month exceeds the allowable error value of electricity consumption. The actual number of people may be different from the number of people applied for by the tenant, and there is a risk. The difference between the actual monthly electricity consumption per person last month and the preset single-person electricity consumption last month and the allowable error value of electricity consumption is The larger it is, the larger the second risk index F2 is;

[0081] It should be noted that the monthly water consumption Q W and the monthly electricity consumption Q of the previous month D The method of obtaining the water consumption adjustment coefficient σ of the previous month is the existing technology. W and the monthly electricity consumption adjustment coefficient σ of the previous month D are preset values; each month corresponds to a water consumption adjustment coefficient and an electricity consumption adjustment coefficient respectively; the basic single-person water consumption Q1, the allowable error value of water consumption W1, the basic single-person electricity consumption Q2 and the allowable error value of electricity consumption W2 are all preset values, which are obtained based on experience and will not be described in detail here.

[0082] As an implementation manner of the present invention, the preset formula is:

[0083]

[0084] Calculate the comprehensive risk index F Z ;

[0085] Among them, P C is the actual matching index between the allocated public rental housing and the tenant; δ1 is the first comprehensive weight coefficient; δ2 is the second comprehensive weight coefficient; δ3 is the third comprehensive weight coefficient;

[0086] Through the above technical solution, the present embodiment P0-P C The difference between the basic matching index and the actual matching index of the allocated public rental housing and the tenant; the difference between the basic matching index and the actual matching index of the allocated public rental housing and the tenant is P0-P C The larger the value, the less the public rental housing meets the tenant's expectations, so the tenant is more likely to sublet. Therefore, the comprehensive risk index F Z The larger the first risk index F1, the larger the comprehensive risk index F Z The larger the second risk index F2, the greater the comprehensive risk index F Z The bigger;

[0087] It should be noted that the first comprehensive weight coefficient δ1, the second comprehensive weight coefficient δ2 and the third comprehensive weight coefficient δ3 are preset values, which are obtained based on experience and will not be described in detail here.

[0088] As an implementation method of the present invention, the judgment process of whether the lessee's rental is abnormal is as follows: the comprehensive risk index F Z Compare with the first preset value R:

[0089] When F Z When ≤R, there is no abnormality in the lessee's rent;

[0090] When R <F Z When ≤R2, the lessee’s rental is abnormal and needs to be reviewed;

[0091] Through the above technical solution, this embodiment calculates the comprehensive risk index F Z Compared with the first preset value R: When F Z When ≤R, it means the risk is small and there is nothing wrong with the tenant’s rent. <F Z When ≤R2, it indicates that the risk is high and the tenant’s rental is abnormal and needs to be reviewed;

[0092] It should be noted that the first preset value R is a preset value, which is obtained based on experience and will not be described in detail here.

[0093] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A public rental housing management and risk assessment system based on big data and artificial intelligence, characterized in that: The management and risk assessment system includes: A data collection module is used to collect the lessee's leasing information data and the lessee's rental information data; Public rental housing information module, used to input housing information data of public rental housing; A management module is used to analyze the tenant information data and housing information data, and allocate public rental housing to the tenant according to the analysis results; The risk assessment module is used to analyze the lessee information data, housing information data, and rental information data to obtain a comprehensive risk index; and to determine whether the lessee's rental is abnormal based on the comprehensive risk index.

2. According to claim 1, a public rental housing management and risk assessment system based on big data and artificial intelligence is characterized in that: The tenant information data includes the tenant's age, the number of co-residents, the age of the co-residents and the desired landmark location; The housing information data includes preset resident ages, preset occupancy numbers and housing locations.

3. According to claim 2, a public rental housing management and risk assessment system based on big data and artificial intelligence is characterized in that: The analysis process of the management module includes: S1: Obtain the matching index between the tenant and each public rental housing by analyzing the tenant's age, number of co-residents, age of co-residents, expected landmark location, the preset resident age, number of occupants and housing location of each public rental housing; S2: Allocate the public housing unit with the highest matching index between the tenant and each public housing unit to the tenant.

4. According to claim 3, a public rental housing management and risk assessment system based on big data and artificial intelligence is characterized in that: The matching index is comprised by the formula: Calculate the matching index P between the nth public rental housing and the tenant n ; Among them, A c A is the age of the lessee; n is the preset age of residents in the nth public rental housing; M is the number of co-residents of the tenant; A m is the age of the mth co-resident; Q n is the preset number of occupants of the nth public rental housing; S n is the distance between the housing location of the nth public rental housing and the desired landmark location of the tenant; P0 is the basic matching index; γ1 is the first weight coefficient; γ2 is the second weight coefficient; γ3 is the third weight coefficient; γ4 is the fourth weight coefficient; C1 is the first preset constant; C2 is the second preset constant; C3 is the third preset constant; C4 is the fourth preset constant.

5. According to claim 4, a public rental housing management and risk assessment system based on big data and artificial intelligence is characterized in that: The rental information data includes the monthly fingerprint door opening times of the tenant, the monthly fingerprint door opening times of each co-resident, the monthly water consumption and monthly electricity consumption of the public rental housing.

6. According to claim 5, a public rental housing management and risk assessment system based on big data and artificial intelligence is characterized in that: The process of obtaining the comprehensive risk index is as follows: S100: After the lessee moves into the allocated public rental housing, the fingerprint information of the smart door lock is cleared and the fingerprint information of the lessee and his / her co-resident is re-entered; S200: Obtain the first risk index by analyzing the monthly fingerprint door opening times of the lessee and the monthly fingerprint door opening times of each co-resident; S300: Obtain the second risk index by analyzing the monthly water consumption and monthly electricity consumption of public rental housing; S400: Calculate a comprehensive risk index by performing a matching index, a first risk index and a second risk index according to a preset formula.

7. The public rental housing management and risk assessment system based on big data and artificial intelligence according to claim 6 is characterized in that: The first risk index is calculated by the formula: Calculate the first risk index F1; Wherein, f(X) is the judgment function. When X>0, f(X)=X; when X≤0, f(X)=0; K0 is the preset number; K m The monthly fingerprint door opening times of the mth co-resident; K C Monthly fingerprint door opening times for tenants.

8. The public rental housing management and risk assessment system based on big data and artificial intelligence according to claim 7 is characterized in that: The second risk index is calculated by the formula: Calculate the second risk index F2; Among them, Q W is the monthly water consumption of the previous month, σ W is the monthly water consumption adjustment coefficient of the previous month; Q1 is the basic water consumption per person; W1 is the allowable error value of water consumption; Q D is the monthly electricity consumption of the previous month; D is the monthly electricity consumption adjustment coefficient of the previous month; Q2 is the basic single-person electricity consumption; W2 is the allowable error value of electricity consumption.

9. The public rental housing management and risk assessment system based on big data and artificial intelligence according to claim 8 is characterized in that: The preset formula is: Calculate the comprehensive risk index F Z ; Among them, P C is the actual matching index between the allocated public rental housing and the tenants; δ1 is the first comprehensive weight coefficient; δ2 is the second comprehensive weight coefficient; δ3 is the third comprehensive weight coefficient.

Images