House resource intelligent recommendation system
By establishing a housing database and a personal labeling of the user, combined with artificial intelligence technology to screen and recommend housing information, solve the explanatory and fit of housing recommendation in existing technology, and achieve efficient user viscosity maintenance and maintenance and the maintenance and maintenance of user viscosity and Raising the volume of housing.
Patent Information
- Application Number
- CN202310890951.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-07-20
- Publication Date
- 2025-01-24
AI Technical Summary
The existing housing recommendation system has poor interpretability of recommendation results, poor fit with user needs, and the inability to efficiently maintain user viscosity, resulting in low housing transaction volume.
Design a housing intelligent recommendation system. By establishing a housing database and performing cyclical updates. After the user sets a personal label, the system is selected step by step and recommendation to the housing information based on artificial intelligence technology. Source information maintains user viscosity.
It achieves the accuracy and interpretability of housing recommendation, improves user experience and housing transaction volume, while ensuring data accuracy and user stickiness.
Smart Images
Figure CN119359379A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of house information processing, and in particular to an intelligent house recommendation system. Background Art
[0002] With the rapid development of computers, mankind has entered the information age; from the previous society of commodity shortages, lack of information and lack of advertising, to the current society of commodity surplus, excessive information and excessive advertising; mankind has gone from facing the dilemma of not being able to make diversified choices to now facing the dilemma of too many choices and even the embarrassing situation of having no choice because of too many choices.
[0003] In the real economy, humans can not only actively search and purchase goods through search engines, but also passively accept various recommended goods calculated by recommendation algorithms and tailored for individuals. Recommendation algorithms have been rapidly developed and applied, and are widely used in various scenarios, such as product recommendations on e-commerce platforms, information recommendations on consulting platforms, advertising recommendations on search platforms, and house recommendations in the real estate industry. Current recommendation technologies can be divided into six types: association rule-based recommendations, content-based recommendations, collaborative filtering-based recommendations, utility-based recommendations, knowledge-based recommendations, and combination recommendations.
[0004] For house recommendation, the above recommendation methods can recommend houses that users are interested in to a certain extent, but they all have the problem of poor interpretability of the recommendation results or poor fit with user needs, as well as some recommendation results that users are very disgusted with or are inexplicably recommended certain houses. In addition, common recommendation systems can usually only recommend houses, but cannot maintain users with high stickiness, resulting in low house transaction volume. For this reason, we propose a house intelligent recommendation system to solve the above problems. Summary of the invention
[0005] In view of the deficiencies in the prior art, the present invention provides an intelligent housing recommendation system, which solves the problems raised in the above background technology.
[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: A house source intelligent recommendation system, comprising: establishing a house source database: collecting house source information within the coverage area of the system and updating it periodically;
[0007] User personal tag establishment: Users can set their own personal tags based on their preference information;
[0008] Obtain recommended housing information based on the housing database and user tags: Screen the housing information in the database step by step based on user tags, and finally push the recommended housing information that matches the user tags to the user;
[0009] Maintain user stickiness: Periodically send listing information to users based on recommended listings;
[0010] The property information includes the number of times the property has been transferred, the property's location, unit price, supporting facilities, years of use and floor area ratio, appreciation rate, payment method, environment, surrounding user reviews, as well as the occupancy rate of a single building, number of floors, area, apartment type, and basic information about surrounding neighbors.
[0011] Preferably, the housing source information collection method includes but is not limited to relevant website information, relevant APP information, and real estate developer release information, and the housing source database is periodically updated every 5-10 hours.
[0012] Preferably, the user personal tags include: requirements for the number of property transfers; requirements for property location, unit price, supporting facilities, and service life; requirements for floor area ratio, appreciation rate, payment method, environment, and surrounding user evaluation; requirements for single-building occupancy rate, number of floors, area, apartment type, and surrounding neighbors.
[0013] Preferably, the specific process of obtaining recommended housing information based on the housing database and user tags is: according to the number of housing transfers required in the user's personal tags, it is determined whether the user needs a new house or a second-hand house.
[0014] Preferably, the specific process of obtaining recommended housing information based on the housing database and user tags also includes: screening the approximate area of the housing according to the location, unit price, supporting facilities, and service life requirements of the housing; screening the specific communities in the area according to the floor area ratio, appreciation rate, payment method, environment, and surrounding user evaluation requirements; screening the specific housing numbers in the community according to the occupancy rate of a single building, number of floors, area, apartment type, and surrounding neighbors.
[0015] Preferably, the method for pushing the recommended housing information to the user is: scoring various housing information in the area according to the housing requirements in the user's personal tags, and arranging the housing information in descending order according to the total score to generate a recommended housing list.
[0016] Preferably, the user stickiness maintenance specifically includes: periodically sending housing information to users according to recommended housing sources, and adjusting the housing information according to user feedback.
[0017] Preferably, the periodic sending time is determined according to user attention.
[0018] The present invention provides a house intelligent recommendation system, which has the following beneficial effects:
[0019] 1. The intelligent housing recommendation system establishes a housing database and performs periodic data updates. After setting personal tags, users can directly search the housing database according to their needs. Artificial intelligence technology directly recommends suitable housing based on user personal tags, which is more intelligent and efficient. Periodic data updates ensure data accuracy and provide users with more choices.
[0020] 2. The intelligent housing recommendation system has rich user personal label settings. In addition to the common basic information of housing such as location, unit price, supporting facilities, it also adds volume ratio, appreciation rate, surrounding user evaluation, occupancy rate, payment method, surrounding neighbor requirements, etc. On the basis of common housing information, combined with surrounding neighbor requirements, surrounding user evaluation settings and other details, multi-level screening of housing is carried out, so as to accurately screen out user needs and make housing recommendations more accurate.
[0021] 3. After the user's recommended property is confirmed, the intelligent property recommendation system can periodically send recommended property information to the user based on the user's attention to the system. At the same time, the recommended property can be modified in real time based on user feedback, thereby improving the stickiness between the user and the system and increasing the transaction volume of the property. BRIEF DESCRIPTION OF THE DRAWINGS
[0022] Figure 1 Schematic diagram of the flow of the intelligent house recommendation system of the present invention. DETAILED DESCRIPTION
[0023] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.
[0024] See also Figure 1 ,The present invention provides a technical solution: a house source intelligent recommendation system, characterized by comprising: ,establishing a house source database: collecting house source information within the coverage of the system, and updating it periodically;
[0025] User personal tag establishment: Users can set their own personal tags based on their preference information;
[0026] Obtain recommended housing information based on the housing database and user tags: Screen the housing information in the database step by step based on user tags, and finally push the recommended housing information that matches the user tags to the user;
[0027] Maintain user stickiness: Periodically send listing information to users based on recommended listings.
[0028] The intelligent housing recommendation system is based on AIGC artificial intelligence technology, which can automatically update the housing database periodically. After the user's personal tags are set, it will automatically recommend corresponding housing to the user and automatically maintain user stickiness based on the user's attention.
[0029] Property information includes the number of times the property has changed hands, its location, unit price, supporting facilities, years of use and floor area ratio, appreciation rate, payment method, environment, surrounding user reviews, as well as single-building occupancy rate, number of floors, area, unit type, and basic information about surrounding neighbors. In addition to basic information such as location, unit price, supporting facilities, area, and unit type, property information also includes payment method, occupancy rate, surrounding user reviews, basic information about surrounding neighbors, etc., which can improve your understanding of the property.
[0030] The way of collecting property information includes but is not limited to relevant website information, relevant APP information, and information released by real estate developers. A property database is established and the data is updated periodically. After setting personal tags, users can directly search the property database according to their needs. Artificial intelligence technology directly recommends suitable properties based on user personal tags, which is more intelligent and efficient. The property database is updated periodically every 5-10 hours. Periodic data updates ensure the accuracy of the data and provide users with more choices.
[0031] User personal tags include: requirements for the number of property transfers; requirements for property location, unit price, supporting facilities, and years of use; requirements for floor area ratio, appreciation rate, payment method, environment, and surrounding user evaluations; requirements for single-building occupancy rate, number of floors, area, apartment type, and surrounding neighbors. User personal tags are richly set. In addition to the common basic information such as location, unit price, and supporting facilities, floor area ratio, appreciation rate, surrounding user evaluations, occupancy rate, payment method, surrounding neighbor requirements, etc. are also added. On the basis of common property information, combined with details such as surrounding neighbor requirements and surrounding user evaluation settings, properties are screened at multiple levels to accurately screen out user needs.
[0032] Especially for the evaluation of surrounding users, it can more intuitively reflect the quality of the property. At the same time, setting requirements for surrounding neighbors can avoid subsequent neighborhood disputes.
[0033] The specific process of obtaining recommended housing information based on the housing database and user tags is as follows: according to the number of housing transfers in the user's personal tags, it is determined whether the user needs a new or second-hand house, and the user's personal tags are compared with the housing information layer by layer from the outside to the inside, so as to screen out the housing that best suits the user and better meet the user's needs.
[0034] The specific process of obtaining recommended housing information based on the housing database and user tags also includes: screening the approximate area of the housing according to the location, unit price, supporting facilities, and service life requirements; screening the specific communities in the area according to the floor area ratio, appreciation rate, payment method, environment, and surrounding user evaluation requirements; screening the specific housing numbers in the community according to the occupancy rate of a single building, number of floors, area, apartment type, and surrounding neighbors; and screening the housing according to the number of housing transfers, area, community, number of buildings, units, and room numbers based on the comparison of the user's personal tags with the housing information. This will accurately screen out user needs, improve user experience, and thereby increase housing transaction volume.
[0035] The method for pushing recommended housing information to users is as follows: score various housing information in the area according to the housing requirements in the user's personal tags, and arrange the housing information in descending order according to the total score to generate a recommended housing list. Score the housing according to the user's personal tag requirements, and arrange the housing in descending order according to the total score. This can display the housing to users more intuitively and improve the efficiency and effectiveness of recommendations.
[0036] Maintaining user stickiness is specifically as follows: based on recommended properties, periodically sending property information to users; after the user's recommended property is confirmed, periodically sending recommended property information to users based on the user's attention to the system, maintaining the stickiness between the user and the system, increasing the probability of property transaction, and adjusting the property information based on user feedback; based on user feedback, making real-time changes to recommended properties to ensure that the recommended properties always meet user needs, further increasing the stickiness between the user and the system; the periodic sending time is determined based on the user's attention, and the attention standard is determined based on the user's views of the system and the viewing time.
[0037] In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific position, be constructed and operated in a specific position, and therefore cannot be understood as limiting the present invention; the terms "first", "second", and "third" are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance. In addition, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be a connection between the two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not expressly listed, or also includes elements inherent to such process, method, article, or apparatus.
[0038] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.
Claims
1. A house intelligent recommendation system, characterized in that: include: Establishment of housing database: collect housing information within the coverage of the system and update it periodically; User personal tag establishment: Users can set their own personal tags based on their preference information; Obtain recommended housing information based on the housing database and user tags: Screen the housing information in the database step by step based on user tags, and finally push the recommended housing information that matches the user tags to the user; Maintain user stickiness: Periodically send listing information to users based on recommended listings; The property information includes the number of property transfers, property location, unit price, supporting facilities, years of use and floor area ratio, appreciation rate, payment method, environment, surrounding user reviews, and basic information such as single building occupancy rate, number of floors, area, apartment type, and surrounding neighbors.
2. The intelligent house recommendation system according to claim 1, characterized in that: The housing information collection method includes but is not limited to relevant website information, relevant APP information, and real estate developer release information. The housing database is updated periodically every 5-10 hours.
3. The intelligent house recommendation system according to claim 2, characterized in that: The user's personal tags include: requirements for the number of property transfers; requirements for property location, unit price, supporting facilities, and years of use; requirements for floor area ratio, appreciation rate, payment method, environment, and surrounding user evaluations; requirements for single-building occupancy rate, number of floors, area, apartment type, and surrounding neighbors.
4. The intelligent house recommendation system according to claim 3, characterized in that: The specific process of obtaining recommended housing information based on the housing database and user tags is as follows: according to the number of housing transfers required in the user's personal tags, it is determined whether the user needs a new house or a second-hand house.
5. The intelligent house recommendation system according to claim 4, characterized in that: The specific process of obtaining recommended housing information based on the housing database and user tags also includes: screening the approximate area of the housing according to the location, unit price, supporting facilities, and service life requirements of the housing; screening the specific communities in the area according to the floor area ratio, appreciation rate, payment method, environment, and surrounding user evaluation requirements; screening the specific housing numbers in the community according to the occupancy rate of a single building, number of floors, area, apartment type, and surrounding neighbors.
6. The intelligent house recommendation system according to claim 5, characterized in that: The method for pushing the recommended housing information to the user is: scoring various housing information in the area according to the requirements for housing in the user's personal tags, and arranging the housing information in descending order according to the total score to generate a recommended housing list.
7. The intelligent house recommendation system according to claim 6, characterized in that: The user stickiness maintenance specifically includes: periodically sending housing information to users based on recommended housing sources, and adjusting the housing information based on user feedback.
8. The intelligent house recommendation system according to claim 7, characterized in that: The periodic sending time is determined according to the user's attention.