A blockchain-based house rental system and rental method

Abstract

The application relates to the technical field of intelligent house leasing, in particular to a house leasing system and method based on a block chain. The method takes a tenant who needs to rent a house as a target tenant, filters initial house sources based on the demand of the target tenant, obtains reference house sources of each initial house source, obtains the universal attention degree of each kind of house information of the reference house sources according to the house information of each time of house leasing of the target tenant in the historical house leasing and the historical house leasing times of the target tenant, obtains the recommendation degree of each initial house source according to the universal attention degree, the difference of each kind of house information between each reference house source and other reference house sources and the difference of the universal attention degree, and further recommends the house sources to the target tenant. The application can accurately obtain the recommendation degree of each initial house source, effectively avoids the interference of the personal intention of the tenant, improves the accuracy and rationality of the house source recommendation for the target tenant, and effectively improves the house leasing efficiency of the target tenant.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent house leasing, and particularly relates to a house leasing system and method based on a blockchain. BACKGROUND

[0002] With the increase of urban population mobility, the house leasing market has gradually become an important part of modern urban life. In recent years, as a decentralized and tamper-proof distributed ledger technology, the blockchain technology can effectively solve the trust problem in the traditional leasing mode and improve the transparency and security of the leasing process.

[0003] The existing house leasing system usually displays all the house information to the tenants, and the tenants need to spend a lot of time in the process of finding suitable house, and the house may not meet the needs of the tenants, which leads to poor efficiency of house leasing and causes adverse effects on both tenants and landlords. SUMMARY

[0004] In order to solve the technical problem that the existing house leasing system does not accurately recommend house information to tenants, resulting in poor efficiency of house leasing, the purpose of the present application is to provide a house leasing system and method based on a blockchain, and the technical solution adopted is as follows:

[0005] In the first aspect, one embodiment of the present application provides a house leasing method based on a blockchain, which comprises the following steps:

[0006] Taking any tenant who needs to rent a house as a target tenant, screening initial houses based on the house renting needs of the target tenant, and taking all the house information of the house in the house leasing system in the preset local area of each initial house as reference house information; obtaining the universal attention degree of each house information of each reference house according to the house information of each reference house in each rental of each reference house and the historical rental times of each rental tenant;

[0007] According to the universal attention degree of each house information of each reference house in the preset local area of each initial house, the difference between each house information of each reference house and other reference houses, and the difference in universal attention degree, the recommendation degree of each initial house is obtained;

[0008] Based on the recommendation degree, the target tenant is recommended for house.

[0009] Further, the method for obtaining the universal attention degree is as follows:

[0010] For any reference house, each rental tenant of the reference house is taken as a reference tenant;

[0011] For any reference tenant and any kind of housing information, obtain the variance of the data corresponding to the kind of housing information of all the rented housing sources of the reference tenant in the historical housing renting as the degree of disinterest of the reference tenant in the kind of housing information;

[0012] According to the historical leasing times of the reference tenant and the degree of disinterest, obtain the degree of interest of the reference tenant in the kind of housing information; wherein the historical leasing times and the degree of interest are in a positive correlation, and the degree of disinterest and the degree of interest are in a negative correlation;

[0013] Obtain the mean of the degrees of interest of all the reference tenants in the kind of housing information as the general degree of interest of the kind of housing information of the reference housing source.

[0014] Further, the obtaining method of the recommendation degree is:

[0015] For any initial housing source, the reference housing sources in the preset local area of the initial housing source are all taken as analysis housing sources;

[0016] For any two analysis housing sources and any kind of housing information, according to the difference of the data corresponding to the kind of housing information of the two analysis housing sources and the difference of the general degrees of interest of the kind of housing information of the two analysis housing sources, obtain the personal interest deviation degree of the kind of housing information of the two analysis housing sources;

[0017] Divide all the kinds of housing information of each analysis housing source based on the general degree of interest of each kind of housing information of each analysis housing source, and obtain the housing information category of each analysis housing source;

[0018] Arrange each kind of housing information of each analysis housing source according to the order from large to small of the general degree of interest thereof, and obtain the housing information sequence of each analysis housing source;

[0019] According to the similarity of the housing information categories in which the kind of housing information of the two analysis housing sources is located and the difference of the positions of the kind of housing information in the housing information sequences of the two analysis housing sources, obtain the personal interest correction weight of the kind of housing information of the two analysis housing sources;

[0020] Take the product of the personal interest deviation degree and the personal interest correction weight as the corrected personal interest deviation degree of the kind of housing information of the two analysis housing sources;

[0021] According to the general degree of interest of each kind of housing information of each analysis housing source and the corrected personal interest deviation degree of each kind of housing information of each analysis housing source and other analysis housing sources, obtain the recommendation degree of the initial housing source.

[0022] Further, the calculation formula of the personal interest deviation degree is: In the formula, a personal attention deviation degree of the jth kind of house information of the ath analyzed house source in the preset local area of the ith initial house source; a universal attention degree of the jth kind of house information of the ath analyzed house source in the preset local area of the ith initial house source; a universal attention degree of the jth kind of house information of the bth analyzed house source in the preset local area of the jth initial house source; data corresponding to the jth kind of house information of the ath analyzed house source in the preset local area of the ith initial house source; data corresponding to the jth kind of house information of the bth analyzed house source in the preset local area of the ith initial house source; is a first preset constant, greater than 0; | | is an absolute value function; norm is a normalization function.

[0023] Further, the method for obtaining the personal attention correction weight comprises:

[0024] for the ath analyzed house source and the bth analyzed house source in the preset local area of the ith initial house source, and the jth kind of house information; wherein the ath analyzed house source and the bth analyzed house source are any two analyzed house sources in the preset local area of the ith initial house source, the ith initial house source is any initial house source, and the jth kind of house information is any kind of house information of a house source;

[0025] taking the house information category in which the jth kind of house information of the ath analyzed house source is located as a first house information category;

[0026] taking the house information category in which the jth kind of house information of the bth analyzed house source is located as a second house information category;

[0027] obtaining the number of same house information between the first house information category and the second house information category as a first number;

[0028] taking the ratio of the first number to the total number of elements in the first house information category as a first reference value;

[0029] taking the ratio of the first number to the total number of elements in the second house information category as a second reference value;

[0030] taking the negative correlation result of the product of the first reference value and the second reference value as a first eigenvalue of the jth kind of house information of the ath analyzed house source and the bth analyzed house source;

[0031] taking the position sequence number of the jth kind of house information in the house information sequence of the ath analyzed house source from front to back as a first sequence number;

[0032] a first sequence number of the jth house information of the bth analyzed house source in a sequence of house information of the bth analyzed house source from front to back;

[0033] a result of normalizing a difference between the first sequence number and the second sequence number as a second characteristic value of the jth house information of the ath analyzed house source and the bth analyzed house source;

[0034] a result of normalizing a sum of the first characteristic value and the second characteristic value as a personal attention correction weight of the jth house information of the ath analyzed house source and the bth analyzed house source.

[0035] Further, the method for obtaining the recommendation degree is:

[0036] For any analyzed house source and any house information, according to the correction personal attention deviation degree of the house information of the analyzed house source and each other analyzed house source, and the universal attention degree of the house information of the analyzed house source, a local speculation reference degree of the house information of the analyzed house source is obtained.

[0037] A sum of the local speculation reference degrees of all house information of the analyzed house source is taken as a global speculation reference degree of the analyzed house source.

[0038] A sum of the global speculation reference degrees of all analyzed house sources is taken as the recommendation degree of the initial house source.

[0039] Further, the method for obtaining the local speculation reference degree is:

[0040] A mean of the correction personal attention deviation degrees of the house information of the analyzed house source and each other analyzed house source is taken as a personal attention degree of the house information of the analyzed house source.

[0041] According to the universal attention degree and the personal attention degree of the house information of the analyzed house source, a local speculation reference degree of the house information of the analyzed house source is obtained; wherein the universal attention degree and the local speculation reference degree are positively correlated, and the personal attention degree and the local speculation reference degree are negatively correlated.

[0042] Further, the method for recommending house sources to the target tenant based on the recommendation degree is:

[0043] All initial house sources are arranged in a sequence from large to small according to their recommendation degrees, and an initial house source sequence is obtained.

[0044] The initial house source sequence is divided into groups in a preset number from front to back, and a house source recommendation group is obtained.

[0045] The house source recommendation group is recommended to the target tenant in turn according to the division order.

[0046] Further, the method for obtaining the house information corresponding data is:

[0047] For any house information, when the house information can be represented by data, the data that the house information can represent is the house information corresponding data;

[0048] When the house information can only be represented by words, the data of various situations corresponding to the house information is marked by people, and the marked data is taken as the house information corresponding data.

[0049] In a second aspect, another embodiment of the present application provides a house rental system based on a block chain, which comprises a memory, a processor and a computer program stored in the memory and running on the processor, and when the processor executes the computer program, the steps of any one of the above methods are realized.

[0050] The present application has the following beneficial effects:

[0051] The present application first filters out initial house sources based on the house rental demand of the target tenant, analyzes the initial house sources to improve the efficiency of reasonable house source recommendation for the target tenant, takes each house source in the preset local area of each initial house source in the house rental system as a reference house source to improve the accuracy of analysis of each initial house source, further obtains the universal attention degree of each house information of each reference house source according to each house information of each house source rented by each rental tenant in the historical house rental and the historical rental times of each rental tenant, preliminarily reflects the attention situation of each house information of each reference house source and indirectly reflects the importance of each house information of each reference house source, avoids the inaccurate house source recommendation for the target tenant due to the personal intention of the tenant, and further obtains the recommendation degree of each initial house source according to the universal attention degree of each house information of each reference house source in the preset local area of each initial house source, the difference of each house information between each reference house source and other reference house sources and the difference of the universal attention degree, accurately reflects the rationality of each initial house source, and further accurately and reasonably recommends the house source for the target tenant based on the recommendation degree, and effectively improves the rental efficiency of the target tenant. BRIEF DESCRIPTION OF DRAWINGS

[0052] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, and the advantages thereof, the drawings needed to be used in the embodiments or prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained without creative labor based on these drawings.

[0053] Figure 1 A schematic flow chart of a blockchain-based house renting method provided by an embodiment of the present application;

[0054] Figure 2 A flow chart of a recommendation degree acquisition method provided by an embodiment of the present application;

[0055] Figure 3 A structure diagram of a blockchain-based house renting system provided by an embodiment of the present application;

[0056] Figure 4 A schematic diagram of a computer device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0057] In order to further illustrate the technical means and effects taken by the present application to achieve the predetermined purposes, the specific embodiments, structures, features and effects of the blockchain-based house renting system and method according to the present application are described in detail as follows in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0058] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs.

[0059] The specific scheme of the blockchain-based house renting system and method provided by the present application is specifically described below in combination with the accompanying drawings.

[0060] Embodiment 1:

[0061] The present application proposes a blockchain-based house renting method, please refer to Figure 1 which shows a schematic flow chart of a blockchain-based house renting method provided by an embodiment of the present application, and the method comprises the following steps:

[0062] Step S1: taking any tenant who needs to rent a house as a target tenant, screening out initial house sources based on the house renting demand of the target tenant, taking each initial house source in a preset local area as a reference house source in the house renting system; and according to each kind of house information of each reference house source in each rental tenant's each rented house source in the historical house renting, and the historical rental times of each rental tenant, acquiring the universal attention degree of each kind of house information of each reference house source.

[0063] Specifically, the house leasing system is a medium for tenants to find house resources through terminals. The house leasing system stores the relevant information of each house resource entered and makes the information transparent, so that all tenants using the house leasing system can cross-verify all house resource information data, helping tenants compare different house resources and filter out the most desirable house resources. At the same time, the house leasing system also stores the information of the tenants using it, but not transparently. The house information of the house resource includes address, house type, area, floor, orientation, house type, rent, and real scene photos, etc. The information of the tenant includes name, ID number, contact information, occupation, work unit, income proof (for assessing payment ability), credit record (which can be obtained through a third-party credit agency), and historical leasing record, etc. Among them, the historical leasing record of the tenant can obtain the house information of the house resource that the tenant has historically leased. It should be noted that the house information of the house resource and the information of the tenant are stored based on the blockchain for subsequent retrieval and operation.

[0064] In order to analyze the present embodiment more clearly, the present embodiment takes any tenant who needs to rent a house as a target tenant, and analyzes the target tenant as an example. It should be noted that the target tenant appearing later is the target tenant. The target tenant inputs his / her house renting demand (such as the price, area, location, and orientation of the desired house resource) into the house leasing system, and the house leasing system performs preliminary screening on the house resources to obtain initial house resources. At this time, the initial house resources screened by the house leasing system are relatively many, and due to the influence of the personal intentions of the tenants, the recommended initial house resources are not very accurate, which affects the efficiency of the target tenant in finding suitable house resources.

[0065] In order to improve the efficiency of the target tenant in finding suitable house resources, the present embodiment takes all house resources (including rented house resources) in the preset local area in the house leasing system as reference house resources for each initial house resource. In the present embodiment, the preset local area is set as the community where each initial house resource is located. Because the tenants in the same community consider the house information of the house resources more similarly, the tenants in the same community pay more attention to each kind of house information, which is more specific and has more reference significance, and is conducive to subsequent accurate analysis of the suitability of each initial house resource to the target tenant. The implementer can set the range of the preset local area according to the actual situation, which is not limited here.

[0066] In order to improve the analysis efficiency, the embodiment selects the data corresponding to each housing information. For any housing information, when the housing information can be represented by data, the data represented by the housing information is the data corresponding to the housing information. For example, the data corresponding to the housing area is the size of the area, and the data corresponding to the floor of the house is the number of floors. When the housing information can only be represented by text, the data corresponding to various situations of the housing information is marked by a person, and the marked data is taken as the data corresponding to the housing information. For example, the orientation of the house is east, south, west, and north. The embodiment marks east, south, west, and north as 1, 2, 3, and 4, respectively. The implementer can mark the data according to the actual situation, which is not limited herein. Therefore, the data corresponding to the orientation of the house is 1, 2, 3, and 4, respectively.

[0067] By analyzing the reference housing sources in the preset local area of each initial housing source, the attention of each housing information of each initial housing source in the rental process can be indirectly predicted, so that the target tenant can be more accurately recommended. Therefore, the embodiment first analyzes each reference housing source. By analyzing the fluctuation of each housing information of the housing source rented by the tenant in the historical housing rental each time for each rental of each reference housing source, the general attention of each housing information of each reference housing source is determined. In the actual situation, the more the number of times that the tenant in the historical housing rental each time for each rental of each reference housing source, the more accurate the result reflected by the data of the corresponding tenant, which effectively avoids the contingency. In order to ensure the authenticity of the analysis result, the general attention degree of each housing information of each reference housing source is obtained according to the housing information of the housing source rented by the tenant in the historical housing rental each time for each rental of each reference housing source and the historical rental times of the tenant each time.

[0068] Preferably, in an implementable manner of the embodiment, the general attention degree is obtained by: for any reference housing source, each rental tenant of the reference housing source is taken as a reference tenant; for any reference tenant and any housing information, the variance of the data corresponding to the housing information of all the housing sources rented by the reference tenant in the historical housing rental is obtained as the inattention degree of the reference tenant to the housing information; the greater the inattention degree, the more inconsistent the housing information of the housing source in the historical housing rental of the reference tenant, which indirectly reflects that the reference tenant pays less attention to the housing information; it should be noted that the reference tenant with only one rental information is not analyzed because it has no reference significance. The more the number of the housing sources rented by the reference tenant in the historical housing rental, the more accurate the inattention degree, and then the attention degree of the reference tenant to the housing information is obtained according to the historical rental times of the reference tenant and the inattention degree; wherein the historical rental times and the attention degree are positively correlated, and the inattention degree and the attention degree are negatively correlated; wherein the calculation formula of the attention degree is: In the formula, p u,j is the attention degree of the u-th reference tenant to the j-th housing information; n u is the historical leasing times of the u-th reference tenant; σ u,j is the inattention degree of the u-th reference tenant to the j-th housing information; β is a second preset constant and is greater than 0; in the embodiment, β is set to 1 to avoid a denominator of 0, and the implementer can set the size of β according to the actual situation, which is not limited herein;

[0069] In order to accurately represent the attention situation of the reference housing source to the housing information, and further obtain the average of the attention degrees of all reference tenants to the housing information as the general attention degree of the reference housing source to the housing information. The greater the general attention degree is, the greater the possibility that the reference housing source to the housing information is generally considered by the tenants is, and the more important the reference housing source to the housing information is.

[0070] Up to now, the general attention degree of each reference housing source to each housing information is obtained.

[0071] Step S2: obtaining the recommendation degree of each initial housing source according to the general attention degree of each reference housing source to each housing information in the preset local area of each initial housing source, the difference of each housing information between each reference housing source and other reference housing sources, and the difference of the general attention degrees.

[0072] In the actual situation, there is personal intention in the leasing process of different tenants, and different tenants will have obvious differences in attention to the same housing information due to the influence of personal intention. Therefore, it is impossible to directly obtain the attention situation of each initial housing source to each housing information according to the general attention degree of each reference housing source to each housing information in the preset local area of each initial housing source, and further to accurately provide reasonable housing sources for the target tenant. In order to avoid the situation that the recommended housing sources for the target tenant are chaotic due to personal intention, the reference housing sources in the preset local area of each initial housing source are analyzed respectively in the embodiment, the difference of each housing information between each reference housing source and other reference housing sources in the preset local area of a certain initial housing source is analyzed, the interference situation of each housing information of each initial housing source by personal intention is indirectly reflected, and the real attention situation of each housing information of each initial housing source is accurately analyzed, and the recommendation degree of each initial housing source is accurately obtained. Therefore, the recommendation degree of each initial housing source is obtained according to the general attention degree of each reference housing source to each housing information in the preset local area of each initial housing source, the difference of each housing information between each reference housing source and other reference housing sources, and the difference of the general attention degrees. The greater the recommendation degree is, the earlier the corresponding initial housing source should be recommended to the target user.

[0073] Preferably, in one implementation of the present embodiment, the recommendation degree acquisition method is as follows Figure 2 which shows a flowchart of a recommendation degree acquisition method provided by the present embodiment, the method comprising the following steps:

[0074] Step S201: Acquire the personal attention deviation degree.

[0075] For the purpose of clearer analysis, for any initial house, the present embodiment takes the reference houses in the preset local area of the initial house as analysis houses; for any two analysis houses and any kind of house information, the smaller the difference between the data corresponding to the house information of the two analysis houses, the more similar the house information of the two analysis houses; in the case that the difference between the data corresponding to the house information of the two analysis houses is smaller, the greater the difference between the universal attention degrees of the house information of the two analysis houses, the greater the degree of influence of the house information of the two analysis houses by personal subjective consciousness, and the greater the personal attention deviation degree of the house information of the two analysis houses. Further, the present embodiment acquires the personal attention deviation degree of the house information of the two analysis houses according to the difference between the data corresponding to the house information of the two analysis houses and the difference between the universal attention degrees of the house information of the two analysis houses.

[0076] wherein the calculation formula of the personal attention deviation degree is as follows: in the formula, is the personal attention deviation degree of the jth kind of house information of the a th analysis house and the b th analysis house in the preset local area of the i th initial house; is the universal attention degree of the jth kind of house information of the a th analysis house in the preset local area of the i th initial house; is the universal attention degree of the jth kind of house information of the b th analysis house in the preset local area of the i th initial house; is the data corresponding to the jth kind of house information of the a th analysis house in the preset local area of the i th initial house; is the data corresponding to the jth kind of house information of the b th analysis house in the preset local area of the i th initial house; is the first preset constant, greater than 0; | | is the absolute value function; norm is the normalization function.

[0077] The present embodiment sets to 1 to avoid the denominator being 0, and the implementer can set the size of according to the actual situation, which is not limited herein.

[0078] Thus, the personal attention deviation degree of each kind of house information of any two analysis houses is acquired.

[0079] Step S202: Obtain the personal attention correction weight.

[0080] In consideration of the potential attention points of the tenant in addition to the house information, for example, the lighting time of the living room is not recorded in detail, but the historical tenant excludes various house information in the process of selecting a house source and actually investigating, and selects the house source due to the potential attention point, so it can be inferred that there is a certain error in determining the degree of influence of the personal intention on the corresponding house information of the two analysis house sources according to the personal attention deviation degree obtained in step S201. It is known that the potential attention point often has a certain correlation with the house information, for example, the lighting time of the living room is usually jointly determined by the floor of the house source, the orientation, and the distance between the buildings, and the floor of the house source, the orientation, and the distance between the buildings are all actual obtainable house information. For any potential attention point, the house information associated with it usually presents a phenomenon that the general attention degree is similar. Therefore, the embodiment first divides all kinds of house information of each analysis house source based on the general attention degree of each kind of house information of each analysis house source by using the DBSCAN density clustering algorithm, to obtain the house information category of each analysis house source; wherein the DBSCAN density clustering algorithm is a known technology and will not be described in detail. The same house information category may correspond to a potential attention point.

[0081] In order to accurately analyze the reasonable degree of the personal attention deviation degree of any two analysis house sources for a certain kind of house information, and further analyze the similarity between the house information categories of the house information of the two analysis house sources, and the difference in the importance of the house information of the two analysis house sources, to determine the personal attention correction weight of the house information of the two analysis house sources, which is conducive to accurately correcting the personal attention deviation degree of the house information of the two analysis house sources.

[0082] In order to show the importance of each kind of house information of each analysis house source, the embodiment arranges each kind of house information of each analysis house source in the order from large to small according to its general attention degree, to obtain the house information sequence of each analysis house source; wherein the more important the house information is in the house information sequence. Further, according to the similarity of the house information categories of the house information of the two analysis house sources, and the difference in the positions of the house information in the house information sequences of the two analysis house sources, the personal attention correction weight of the house information of the two analysis house sources is obtained;

[0083] Preferably, in one implementation of the present embodiment, the method for obtaining the personal attention correction weight is as follows: for the jth kind of housing information of the a th analysis house and the b th analysis house in the preset local area of the ith initial house; wherein, the a th analysis house and the b th analysis house are any two analysis houses in the preset local area of the ith initial house, the ith initial house is any initial house, and the jth kind of housing information is any kind of housing information of the house; the housing information category in which the jth kind of housing information is located in the housing information category of the a th analysis house is taken as a first housing information category; the housing information category in which the jth kind of housing information is located in the housing information category of the b th analysis house is taken as a second housing information category; the number of the same housing information between the first housing information category and the second housing information category is taken as a first number; the greater the first number is, the less the personal attention deviation degree of the jth kind of housing information of the a th analysis house and the b th analysis house is meaningful for reference; in order to accurately analyze the rationality of the personal attention deviation degree of the jth kind of housing information of the a th analysis house and the b th analysis house, the ratio of the first number to the total number of elements in the first housing information category is taken as a first reference value; the ratio of the first number to the total number of elements in the second housing information category is taken as a second reference value; wherein, the greater the first reference value and the second reference value are, the less the personal attention deviation degree of the jth kind of housing information of the a th analysis house and the b th analysis house is meaningful for reference; and the product of the first reference value and the second reference value is negatively correlated to obtain a first characteristic value of the jth kind of housing information of the a th analysis house and the b th analysis house; the greater the first characteristic value is, the more reasonable the personal attention deviation degree of the jth kind of housing information of the a th analysis house and the b th analysis house is, and the more meaningful it is for reference. The calculation formula of the first characteristic value is: wherein, is the first characteristic value of the jth kind of housing information of the a th analysis house and the b th analysis house in the preset local area of the ith initial house; is the first number; is the total number of elements in the first housing information category; is the total number of elements in the second housing information category; is the first reference value; is the second reference value; and exp is an exponential function with a natural constant as the base number.

[0084] The first sequence number of the jth house information in the house information sequence of the a th analysis house source from front to back is taken as a first sequence number; the first sequence number of the jth house information in the house information sequence of the b th analysis house source from front to back is taken as a second sequence number; and a result of normalizing an absolute value of a difference between the first sequence number and the second sequence number is taken as a second characteristic value of the jth house information of the a th analysis house source and the b th analysis house source. The greater the second characteristic value is, the more reasonable the personal attention deviation degree of the jth house information of the a th analysis house source and the b th analysis house source is, and the more reference significance the jth house information has. In this embodiment, the norm normalization function is used to normalize the absolute value of the difference between the first sequence number and the second sequence number.

[0085] In order to accurately represent the reasonable situation of the personal attention deviation degree of the jth house information of the a th analysis house source and the b th analysis house source, a result of normalizing a sum of the first characteristic value and the second characteristic value is taken as a personal attention correction weight of the jth house information of the a th analysis house source and the b th analysis house source. The greater the personal attention correction weight is, the more accurate the personal attention deviation degree of the jth house information of the a th analysis house source and the b th analysis house source is. In this embodiment, the norm normalization function is used to normalize the sum of the first characteristic value and the second characteristic value.

[0086] At this point, the personal attention correction weight of each house information of any two analysis house sources is obtained.

[0087] Step S203: Obtain a corrected personal attention deviation degree.

[0088] It is known that the greater the personal attention correction weight is, the more accurate the personal attention deviation degree of the corresponding house information of the two analysis house sources is. Therefore, in this embodiment, a product of the personal attention deviation degree of the house information of any two analysis house sources and the personal attention correction weight is taken as a corrected personal attention deviation degree of the house information of the two analysis house sources.

[0089] At this point, the corrected personal attention deviation degree of each house information of any two analysis house sources is obtained.

[0090] Step S204: Obtain a recommendation degree.

[0091] Specifically, when the attention degree of a certain initial house source is greater than that of other initial house sources in terms of various house information, it indicates that the house information of the initial house source is more concerned by the tenant, and indirectly reflects that the more important the house information of the initial house source is, the more the initial house source should be recommended to the target tenant. Meanwhile, in order to avoid the inaccurate universal attention degree of each house information of the reference house source in the preset local area of each initial house source due to personal intention, the attention of each house information of each initial house source is more accurately analyzed, and the recommendation degree of each initial house source is obtained, and then the recommendation degree of the initial house source is obtained according to the universal attention degree of each house information of each analysis house source and the correction personal attention deviation degree of each house information of each analysis house source and other analysis house sources.

[0092] Preferably, in an implementable manner of the embodiment, the recommendation degree is obtained by: for any analysis house source and any house information, the local speculation reference degree of the house information of the analysis house source is obtained according to the correction personal attention deviation degree of the house information of the analysis house source and other analysis house sources, and the universal attention degree of the house information of the analysis house source. The greater the local speculation reference degree is, the more the house information of the analysis house source is concerned by the tenant, and indirectly indicates that the more important the house information of the analysis house source is. The local speculation reference degree is obtained by: obtaining the mean value of the correction personal attention deviation degree of the house information of the analysis house source and other analysis house sources as the personal attention degree of the house information of the analysis house source; the smaller the personal attention degree is, the more accurate the universal attention degree of the house information of the analysis house source is, and the smaller the degree of influence by personal intention is, and then the local speculation reference degree of the house information of the analysis house source is obtained according to the universal attention degree and the personal attention degree of the house information of the analysis house source; wherein the universal attention degree and the local speculation reference degree are positively correlated, and the personal attention degree and the local speculation reference degree are negatively correlated. Therefore, the calculation formula of the local speculation reference degree is: In the formula, a and j are integers greater than or equal to 1, and a is less than or equal to K, and j is less than or equal to M; K is the number of analysis house sources in the preset local area of the i th initial house source; M is the number of house information of the analysis house source; and is the local speculation reference degree of the j th house information of the a th analysis house source in the preset local area of the i th initial house source; is the universal attention degree of the j th house information of the a th analysis house source in the preset local area of the i th initial house source; and K is the number of analysis house sources in the preset local area of the i th initial house source; is the correction personal attention deviation degree of the j th house information of the a th analysis house source and the k th analysis house source in the preset local area of the i th initial house source; and γ is a third preset constant greater than 0; The personal attention degree of the jth house information of the ath analysis house resource; in this embodiment, gamma is set to 1 to avoid a denominator of 0, and the implementer can set the size of gamma according to the actual situation, which is not limited here;

[0093] Then, the sum of the local estimated reference degrees of all kinds of house information of the analysis house resource is taken as the overall estimated reference degree of the analysis house resource, and finally the sum of the overall estimated reference degrees of all analysis house resources is taken as the recommendation degree of the initial house resource.

[0094] Up to now, the recommendation degree of each initial house resource is obtained.

[0095] Step S3: recommending a house resource to the target tenant based on the recommendation degree.

[0096] The greater the recommendation degree is, the earlier the corresponding initial house resource should be recommended to the target user. In order to more reasonably and efficiently recommend a house resource to the target tenant, the initial house resources are arranged in the order from large to small according to the recommendation degree in this embodiment, and an initial house resource sequence is obtained. Then, the preset number is set to 8, the implementer can set the size of the preset number according to the actual situation, which is not limited here, the initial house resource sequence is divided into a preset number of groups from front to back, and a house resource recommendation group is obtained, that is, an initial house resource recommendation group contains 8 initial house resources. The house resource recommendation groups are recommended to the target tenant in turn according to the division order, which effectively avoids the interference of personal inclination, makes the recommendation of the house resource more reasonable and accurate, and effectively improves the efficiency of the target tenant's leasing.

[0097] In summary, in this embodiment, the tenant who needs to rent a house at present is taken as a target tenant, the initial house resources are screened based on the demand of the target tenant, the reference house resources of each initial house resource are obtained, the universal attention degree of each kind of house information of the reference house resources is obtained according to the house information of each time of leasing of the tenant in the historical house renting, the historical leasing times of the leasing tenant, the universal attention degree, the difference of each kind of house information between each reference house resource and other reference house resources, and the difference of the universal attention degree, the recommendation degree of each initial house resource is obtained, and then the target tenant is recommended a house resource. The present application accurately obtains the recommendation degree of each initial house resource, effectively avoids the interference of the personal intention of the tenant, improves the accuracy and rationality of recommending a house resource to the target tenant, and effectively improves the efficiency of the target tenant's leasing.

[0098] Embodiment 2:

[0099] The present application also proposes a house leasing system based on a block chain, please refer to Figure 3 which shows a structure diagram of a house leasing system based on a block chain provided by one embodiment of the present application, the system comprises a universal attention degree obtaining module 10, a recommendation degree obtaining module 20 and a house resource recommendation module 30.

[0100] The universal attention obtaining module 10 is configured to take any tenant currently in need of renting a house as a target tenant, filter out initial house sources based on the house renting demand of the target tenant, take each house source appearing in the house renting system in a preset local area of each initial house source as a reference house source, and obtain the universal attention of each house information of each reference house source according to each house information of each reference house source in each historical house rented by each tenant in each tenancy and the historical tenancy times of each tenancy tenant.

[0101] The recommendation degree obtaining module 20 is configured to obtain the recommendation degree of each initial house source according to the universal attention of each house information of each reference house source in the preset local area of each initial house source, the difference between each house information of each reference house source and other reference house sources, and the difference in universal attention.

[0102] The house source recommendation module 30 is configured to recommend house sources to the target tenant based on the recommendation degree.

[0103] It should be noted that the system provided in the above embodiments is only exemplified by the division of the above functional modules. In actual applications, the above functions can be completed by different functional modules according to needs, that is, the internal structure of the computer device is divided into different functional modules to complete all or part of the above-described functions. In addition, the housing leasing system based on the blockchain and the housing leasing method based on the blockchain provided in the above embodiments belong to the same concept, and the specific implementation process is detailed in the method embodiments, which will not be described here.

[0104] Embodiment 3:

[0105] The application further provides a housing leasing device based on the blockchain. The device comprises a memory and a processor. The memory stores executable program codes. The processor is configured to call and execute the executable program codes to execute the housing leasing method based on the blockchain provided in the embodiments. The device can be a chip, an assembly or a module. The chip can comprise a connected processor and a memory. The memory is configured to store instructions. When the processor calls and executes the instructions, the chip can execute the housing leasing method based on the blockchain provided in the embodiments.

[0106] In addition, the embodiments of the present application also protect a computer device. Please refer to Figure 4 The computer device comprises a memory 401, a processor 402 and a computer program 403 stored in the memory 401 and running on the processor 402. When the processor 402 executes the computer program 403, the computer device can execute any of the housing leasing methods based on the blockchain introduced above.

[0107] Embodiment 4:

[0108] The embodiment also provides a computer readable storage medium, which stores computer program codes, and when the computer program codes are run on a computer, the computer is caused to execute the above-mentioned related method steps to realize the blockchain-based house renting method provided in the above-mentioned embodiment.

[0109] Embodiment 5:

[0110] The embodiment also provides a computer program product, which, when run on a computer, causes the computer to execute the above-mentioned related steps to realize the blockchain-based house renting method provided in the above-mentioned embodiment.

[0111] The device, the computer readable storage medium, the computer program product or the chip provided in the embodiment are used to execute the corresponding method provided above, and thus the beneficial effects that can be achieved are referable to the beneficial effects in the corresponding method provided above, which will not be described here again.

[0112] It should be noted that the above-mentioned sequence of the embodiments of the application is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are possible or can be advantageous.

[0113] Each of the embodiments in the specification is described in a progressive manner, and the same and similar parts between the embodiments can be referred to each other. Each embodiment mainly describes the difference from other embodiments.

Claims

1. A house rental method based on blockchain, characterized in that: The method comprises the following steps: Any tenant who currently needs to rent a house is taken as a target tenant. Initial housing sources are screened based on the target tenant's rental needs. All housing sources that appear in the housing rental system within a preset local area of ​​each initial housing source are used as reference housing sources. Based on each type of housing information of each reference housing source rented by each tenant in the historical rental history and the historical rental frequency of each tenant, the general attention of each type of housing information of each reference housing source is obtained. Obtain the recommendation level of each initial listing based on the general attention of each type of housing information of each reference listing in the preset local area of ​​each initial listing, the difference of each type of housing information between each reference listing and other reference listings, and the difference in general attention; Recommend properties to target tenants based on the degree of recommendation; The method for obtaining the general attention is: For any reference property, each tenant who rents the reference property shall be regarded as the reference tenant; For any reference tenant and any type of housing information, obtain the variance of the corresponding data of this type of housing information for all rental sources rented by the reference tenant in history as the degree of indifference of the reference tenant to this type of housing information; Obtaining the reference tenant's attention to the housing information based on the reference tenant's historical rental times and the degree of indifference; wherein the historical rental times are positively correlated with the degree of attention, and the degree of indifference is negatively correlated with the degree of attention; The average of the attention levels of all reference tenants to this type of housing information is obtained as the general attention level of this type of housing information for the reference property.

2. A blockchain-based house rental method according to claim 1, characterized in that: The method for obtaining the recommendation degree is: For any initial listing, all reference listings within the preset local area of ​​the initial listing are used as analysis listings; For any two analyzed listings and any type of housing information, based on the difference in corresponding data of the housing information of the two analyzed listings and the difference in the general attention of the housing information of the two analyzed listings, the degree of individual attention bias of the housing information of the two analyzed listings is obtained; Divide all types of housing information of each analyzed listing based on the general popularity of each type of housing information of each analyzed listing to obtain the housing information category of each analyzed listing; Arrange each type of house information of each analyzed house listing in descending order according to its general attention degree, and obtain the house information sequence of each analyzed house listing; Obtaining individual attention correction weights for the housing information of the two analyzed housing listings based on similarities in the housing information categories of the housing information of the two analyzed housing listings and differences in the positions of the housing information of the two analyzed housing listings in the housing information sequences; The product of the personal attention bias degree and the personal attention correction weight is used as the corrected personal attention bias degree of the housing information of the two analyzed housing sources; The recommendation degree of the initial listing is obtained based on the general attention degree of each type of housing information of each analyzed listing and the corrected personal attention deviation degree between each analyzed listing and each type of housing information of other analyzed listings.

3. A blockchain-based house rental method as claimed in claim 2, characterized in that: The calculation formula for the degree of personal attention bias is: Where, is the degree of personal attention deviation between the j-th type of housing information of the a-th analysis listing and the b-th analysis listing in the preset local area of ​​the i-th initial listing; is the general attention level of the j-th type of housing information of the a-th analysis listing in the preset local area of ​​the i-th initial listing; is the general attention level of the j-th housing information of the b-th analysis listing in the preset local area of ​​the i-th initial listing; The data corresponding to the j-th type of housing information of the a-th analyzed housing listing in the preset local area of ​​the i-th initial housing listing; The data corresponding to the j-th type of housing information of the b-th analyzed housing listing in the preset local area of ​​the i-th initial housing listing; is the first preset constant, which is greater than 0; | | is the absolute value function; norm is the normalization function.

4. A blockchain-based house rental method according to claim 2, characterized in that: The method for obtaining the personal attention correction weight is: For the ath analysis listing and the bth analysis listing, and the jth type of housing information within the preset local area of ​​the i-th initial listing; wherein the ath analysis listing and the bth analysis listing are any two analysis listings within the preset local area of ​​the i-th initial listing, the i-th initial listing is any initial listing, and the j-th type of housing information is any type of housing information in the listing; The housing information category of the j-th housing information in the a-th analyzed housing source is taken as the first housing information category; The housing information category of the j-th housing information in the b-th analyzed housing source is used as the second housing information category; Obtain the number of identical housing information between the first housing information category and the second housing information category as a first number; using a ratio of the first quantity to the total number of elements in the first housing information category as a first reference value; using a ratio of the first quantity to the total number of elements in the second housing information category as a second reference value; The result of negative correlation of the product of the first reference value and the second reference value is used as the first eigenvalue of the j-th type of housing information of the a-th analysis listing and the b-th analysis listing; The first serial number is the position of the j-th house information in the house information sequence of the a-th analyzed house. The position number of the j-th house information in the house information sequence of the b-th analyzed house is used as the second serial number; Normalize the difference between the first and second serial numbers and use it as the second eigenvalue of the j-th type of housing information between the a-th analyzed housing source and the b-th analyzed housing source; The result of normalizing the sum of the first eigenvalue and the second eigenvalue is used as the personal attention correction weight of the j-th type of housing information of the a-th analyzed housing source and the b-th analyzed housing source.

5. A blockchain-based house rental method as claimed in claim 2, characterized in that: The method for obtaining the recommendation degree is: For any analyzed property and any type of housing information, obtain the local estimated reference level of the analyzed property's housing information based on the corrected individual attention bias between the analyzed property and the housing information of the same type in each other analyzed property, and the general attention level of the analyzed property's housing information of the same type; The sum of the local estimated reference levels of all types of housing information of the analyzed house is used as the overall estimated reference level of the analyzed house; The sum of the overall estimated reference levels of all analyzed properties is obtained as the recommendation level of the initial property.

6. A blockchain-based house rental method according to claim 5, characterized in that: The method for obtaining the local inference reference degree is: Obtain the average of the corrected personal attention biases of the analyzed property and the property information of each other analyzed property, as the personal attention level of the property information of the analyzed property; According to the general attention and personal attention of the housing information of the analyzed housing source, the local speculation reference degree of the housing information of the analyzed housing source is obtained; wherein, the general attention and the local speculation reference degree are positively correlated, and the personal attention and the local speculation reference degree are negatively correlated.

7. A blockchain-based house rental method according to claim 1, characterized in that: The method for recommending properties to target tenants based on the recommendation degree is as follows: Arrange all initial listings in descending order of recommendation to obtain an initial listing sequence; Divide the initial listing sequence into a preset number of groups from front to back to obtain recommended listing groups; Recommend the property recommendation groups to the target tenants in the order of classification.

8. A blockchain-based house rental method according to claim 1, characterized in that: The method for obtaining the data corresponding to the housing information is as follows: For any type of housing information, when the housing information can be represented by data, the data that can be represented by the housing information is the data corresponding to the housing information; When the house information can only be expressed in words, data marking is performed manually on various situations corresponding to the house information, and the marked data is used as the corresponding data of the house information.

9. A house rental system based on blockchain, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When executing the computer program, the processor implements the steps of a blockchain-based house rental method as described in any one of claims 1 to 8.

Images