Housing recommendation method, device, equipment and medium

Abstract

The present application relates to a housing recommendation method, device, equipment and medium, which are applied to the field of computer software application technology, and the method includes: obtaining first demand information and housing information; establishing a multidimensional coordinate system based on preset features; converting the housing information into housing coordinates in the multidimensional coordinate system based on preset rules; converting the first demand information into demand coordinates in the multidimensional coordinate system based on preset rules; determining the first housing information based on the demand coordinates and the housing coordinates; determining the second demand information based on the preset features and the first demand information, the second demand information being the first demand information that does not exist in the preset features; determining the recommended housing information based on the first housing information and the second demand information. The present application has the effect of improving the efficiency and accuracy of housing matching.

Description

Technical Field

[0001] The present application relates to the technical field of computer software applications, and in particular to a housing recommendation method, device, equipment and medium. Background Art

[0002] Currently, in the field of housing rental services, manual customer service is mainly relied on to check users' accommodation needs and match housing sources according to their accommodation needs. However, this method is highly dependent on manual labor, which will lead to longer processing time and low efficiency. In addition, manual operations are prone to errors and have low accuracy. Summary of the invention

[0003] In order to improve the efficiency and accuracy of house matching, the present application provides a house recommendation method, device, equipment and medium.

[0004] In the first aspect, the present application provides a housing recommendation method, which adopts the following technical solution:

[0005] A housing recommendation method, comprising:

[0006] Obtain the first demand information and housing information;

[0007] Establish a multi-dimensional coordinate system based on preset features;

[0008] Converting the house source information into house source coordinates in the multi-dimensional coordinate system based on preset rules;

[0009] Converting the first demand information into demand coordinates in the multidimensional coordinate system based on a preset rule;

[0010] Determine first housing source information based on the demand coordinates and the housing source coordinates;

[0011] Determine second requirement information based on the preset feature and the first requirement information, where the second requirement information is the first requirement information that does not exist in the preset feature;

[0012] Determine recommended housing information based on the first housing information and the second demand information.

[0013] By adopting the above technical solution, the user's first demand information and housing information are converted into coordinate points on a multi-dimensional coordinate system, so that the first housing information can be found more clearly and conveniently, and the matching efficiency is improved. The demand characteristics that cannot be matched by the preset characteristics corresponding to the multi-dimensional coordinate system are determined as the second demand information, and the first housing information is further screened according to the second demand information to obtain recommended housing information. By performing housing matching twice, the dimension of housing matching is increased, thereby improving the accuracy of housing matching.

[0014] Optionally, converting the house source information into house source coordinates in the multi-dimensional coordinate system based on a preset rule includes:

[0015] Standardizing the information corresponding to the preset features in the house information to obtain standardized features;

[0016] Determining an origin feature based on the multidimensional coordinate system;

[0017] Calculate the distance between the standardized feature and the origin feature and the direction of the coordinate axis based on a preset rule;

[0018] The property coordinates are determined based on the multiple distances and the corresponding coordinate axis directions.

[0019] By adopting the above technical solution, before determining the house source coordinates, the information corresponding to the preset features in the house source information is standardized, so that the calculation of the house source coordinates is more standardized and the accuracy of the house source coordinates is improved.

[0020] Optionally, the determining the first housing source information based on the demand coordinates and the housing source coordinates includes:

[0021] If the required coordinates are a range consisting of multiple coordinate points, the house source coordinates within the range are determined as first house source coordinates; and the house source information corresponding to the first house source coordinates is determined as first house source information;

[0022] If the required coordinate is a coordinate point, the distance between the required coordinate and the house source coordinate is calculated to obtain a plurality of first distances;

[0023] Sort the house information in ascending order according to the first distance to obtain a sorting result;

[0024] The first preset number of house source information in the sorting result is determined as the first house source information.

[0025] By adopting the above technical solution, different methods for determining the first housing source information are set according to different demand coordinates, so that users can provide their demands in multiple ways, thereby improving the flexibility and accuracy of housing source matching.

[0026] Optionally, the determining the first housing source information based on the demand coordinates and the housing source coordinates includes:

[0027] If the first housing source information does not exist, determining the demand information corresponding to the preset feature in the first demand information as standard demand information;

[0028] Acquire a recommended transaction order, wherein the recommended transaction order includes standard demand information and transaction demand information, wherein the transaction demand information is information of a characteristic type corresponding to the standard demand information in the transaction housing source information;

[0029] Determining the recommended transaction order that has different standard demand information and transaction demand information as a replacement transaction order;

[0030] Determine the standard requirement information and the transaction requirement information of the same feature type in each of the replacement transaction orders as a feature combination;

[0031] Counting the number of each feature combination in the alternative transaction orders;

[0032] determining a substitution relationship based on the quantities;

[0033] Determine alternative requirement information based on the standard requirement information and the alternative relationship;

[0034] Converting the replacement demand information into replacement demand coordinates in the multi-dimensional coordinate system based on the preset rule;

[0035] The first housing source information is determined based on the alternative demand coordinates and the housing source coordinates.

[0036] By adopting the above technical solution, when the first housing source information cannot be matched according to the user's first demand information, a reasonable substitution relationship is obtained by analyzing the historical recommended transaction orders, and the housing source is re-matched for the user according to the substitution relationship, thereby improving the reliability of housing source matching.

[0037] Optionally, determining the recommended housing information based on the first housing information and the second demand information includes:

[0038] Get user information;

[0039] Determine user preference information based on the user information and the second demand information, the user preference information including housing preference information and public facility preference;

[0040] Determining a preference type and a preference weight based on the user preference information;

[0041] Determine a matching preference category based on the first housing source information and the preference category;

[0042] Calculating a first score based on the matching preference type and the corresponding preference weight;

[0043] Obtaining first historical transaction information and recommendation records of the first property information;

[0044] Determine the number of historical transactions based on the first historical transaction information;

[0045] determining the number of recommendations based on the recommendation record;

[0046] Calculating a historical transaction ratio based on the number of recommendations and the number of historical transactions;

[0047] Determining a second score based on the historical transaction ratio;

[0048] Determine a house source score based on the first score, the second score, and a preset weight;

[0049] Sorting the first house source information according to the house source scores to obtain a sorting result;

[0050] Recommended housing information is determined based on the sorting result and a second preset number.

[0051] By adopting the above technical solution, user preference information is obtained by analyzing user information and the second demand information, the first housing source information is scored once according to the user preference information to obtain a first score, the first housing source information is scored again according to the first historical transaction information of the housing source to obtain a second score, and the housing source score is calculated according to the first score, the second score and the preset weight, the first housing source information is sorted and screened according to the housing source score, so as to obtain recommended housing source information, and the housing source score is determined by comprehensively considering the two factors of user preference and historical transaction information, which takes into account both the personalized needs of users and the specific circumstances of the housing source, thereby improving the accuracy of housing source matching.

[0052] Optionally, the determining the user preference information based on the user information and the second demand information includes:

[0053] Determine historical search information, historical transaction information, and favorite information based on the user information;

[0054] Analyze the historical search information, the historical transaction information, and the favorite information to obtain first preference information;

[0055] Determine the user's subject category based on the user information;

[0056] Acquire second historical transaction information based on the user subject category, where the second historical transaction information includes historical transaction information corresponding to the user subject category;

[0057] Analyze the second historical transaction information to obtain second preference information;

[0058] The user preference information is determined based on the first preference information, the second preference information, and the second requirement information.

[0059] By adopting the above technical solution, by analyzing the user's historical search information, historical transaction information and collection information, we can understand the user's preference for different properties. By determining the user's subject category and obtaining the historical transaction information corresponding to the subject category, we can further understand the housing demand related to the subject category. By comprehensively considering the above factors, we can more accurately determine the user's preference information, match properties according to the user's preference information, improve the accuracy of property matching, and thus improve user satisfaction.

[0060] Optionally, after determining the recommended housing information based on the first housing information and the second demand information, the method further includes:

[0061] Obtaining user feedback information, wherein the user feedback information includes satisfaction and user chat records;

[0062] If the user is not satisfied with the recommended housing information, the chat record is analyzed to determine the user's emotional state and third demand information;

[0063] Obtain the correspondence between emotional state and housing demand;

[0064] Determining fourth demand information based on the corresponding relationship and the emotional state;

[0065] Determine user demand information based on the first demand information, the third demand information and the fourth demand information;

[0066] The housing information is re-screened based on the user demand information to obtain new recommended housing information.

[0067] By adopting the above technical solution, when the user is not satisfied with the housing information recommended for the first time, the user's third demand information is determined through the chat records, and the user's emotional state at this time is analyzed through the chat records, and the fourth demand information is determined according to the emotional state, and the user's demand information is determined through the first demand information, the third demand information and the fourth demand information, and the housing information is screened according to the user's demand information to obtain new recommended housing information, and housing matching is performed by comprehensively considering the original demand information, the new demand information and the demand information under the current emotion, thereby improving the accuracy of housing matching.

[0068] In a second aspect, the present application provides a housing recommendation device, which adopts the following technical solution:

[0069] A housing source recommendation device, comprising:

[0070] An information acquisition module, used to acquire first demand information and house source information;

[0071] A coordinate establishment module, used to establish a multi-dimensional coordinate system based on preset features;

[0072] A housing source conversion module, used for converting the housing source information into housing source coordinates in the multi-dimensional coordinate system based on preset rules;

[0073] A demand conversion module, used for converting the first demand information into demand coordinates in the multi-dimensional coordinate system based on preset rules;

[0074] A first determining module, configured to determine first housing source information based on the required coordinates and the housing source coordinates;

[0075] A demand screening module, used to determine second demand information based on the preset feature and the first demand information, where the second demand information is the first demand information that does not exist in the preset feature;

[0076] The second determining module is used to determine recommended housing information based on the first housing information and the second demand information.

[0077] By adopting the above technical solution, the user's first demand information and housing information are converted into coordinate points on a multi-dimensional coordinate system, so that the first housing information can be found more clearly and conveniently, and the matching efficiency is improved. The demand characteristics that cannot be matched by the preset characteristics corresponding to the multi-dimensional coordinate system are determined as the second demand information, and the first housing information is further screened according to the second demand information to obtain recommended housing information. By performing housing matching twice, the dimension of housing matching is increased, thereby improving the accuracy of housing matching.

[0078] In a third aspect, the present application provides an electronic device, which adopts the following technical solution:

[0079] An electronic device comprises a processor, wherein the processor is coupled to a memory;

[0080] The memory stores a computer program that can be loaded by the processor and executes the housing recommendation method described in any one of the first aspects.

[0081] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution:

[0082] A computer-readable storage medium stores a computer program that can be loaded by a processor and execute the housing recommendation method described in any one of the first aspects. BRIEF DESCRIPTION OF THE DRAWINGS

[0083] Figure 1 It is a flowchart of a housing recommendation method provided in an embodiment of the present application.

[0084] Figure 2It is a structural block diagram of a housing recommendation device provided in an embodiment of the present application.

[0085] Figure 3 It is a structural block diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0086] The present application is further described in detail below in conjunction with the accompanying drawings.

[0087] The embodiment of the present application provides a housing recommendation method, which can be executed by an electronic device, which can be a server or a terminal device, wherein the server can be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smart phone, a tablet computer, a desktop computer, etc., but is not limited thereto.

[0088] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0089] In addition, the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article, unless otherwise specified, generally means that the associated objects before and after are in an "or" relationship.

[0090] like Figure 1 As shown, a housing recommendation method is provided, and the main process of the method is described as follows (steps S101 to S107):

[0091] Step S101, obtaining first demand information and housing source information.

[0092] When users need to find a house, they usually need to communicate with customer service. The user's demand information, that is, the first demand information, can be obtained from the chat record, and the house information can be obtained from the database.

[0093] It is worth noting that when communicating with users, an AI-driven question-and-answer engine can be used to conduct user questions and answers through natural language processing technology. Specifically, this step can be completed using OpenAI's large language model.

[0094] Step S102: establishing a multi-dimensional coordinate system based on preset features.

[0095] Preset features such as location, house area and price are pre-set features and are not specifically limited here. Each preset feature corresponds to a coordinate axis (dimension). The dimension of the coordinate system is determined according to the number of preset features. The origin of the coordinate system is a pre-set preset feature reference value and is not specifically limited here.

[0096] Step S103: convert the house source information into house source coordinates in a multi-dimensional coordinate system based on preset rules.

[0097] Specifically, the housing information is converted into housing coordinates in a multidimensional coordinate system based on preset rules, including: standardizing information in the housing information corresponding to preset features to obtain standardized features; determining the origin feature based on the multidimensional coordinate system; calculating the distance between the standardized feature and the origin feature and the direction of the coordinate axis based on preset rules; and determining the housing coordinates based on multiple distances and corresponding coordinate axis directions.

[0098] In this embodiment, the feature information corresponding to the preset feature in the housing information is converted into the same unit of measurement as the coordinate system to obtain the standardized feature, and the feature reference value corresponding to the origin feature is found from the multi-dimensional coordinate system (the feature reference value may be zero or non-zero, for example, the origin feature reference value corresponding to the price coordinate axis may be 1,000 yuan), and the difference between the feature value of the standardized feature and the feature reference value corresponding to the origin feature is calculated. The correspondence between the difference and the distance and the correspondence between the positive and negative of the difference and the direction of the coordinate axis are found from the preset rules. According to the correspondence, the distance between the standardized feature and the origin on the coordinate axis and the direction of the coordinate axis can be determined, so that the housing coordinates can be obtained according to the distances and coordinate axis directions of multiple dimensions. Since there are multiple housing information, multiple housing coordinates will be obtained, and each housing information corresponds to one housing coordinate.

[0099] Step S104: convert the first demand information into demand coordinates in a multi-dimensional coordinate system based on preset rules.

[0100] The method of converting the first demand information into demand coordinates in a multidimensional coordinate system is the same as the method of determining the property coordinates mentioned above, and will not be repeated here. It is worth noting that the demand coordinates obtained from the first demand information can be a coordinate point or a range. For example, if the first demand information includes a price of 1,000 to 2,000 yuan, the demand coordinates are a range. If the first demand information includes a price of around 1,000 yuan, then when determining the demand coordinates, it is converted according to the price of 1,000 yuan, and the demand coordinates obtained are a coordinate point.

[0101] Step S105: Determine the first housing source information based on the demand coordinates and the housing source coordinates.

[0102] Specifically, the first housing source information is determined based on the demand coordinates and the housing source coordinates, including: if the demand coordinates are a range composed of multiple coordinate points, the housing source coordinates within the range are determined as the first housing source coordinates; the housing source information corresponding to the first housing source coordinates is determined as the first housing source information; if the demand coordinates are one coordinate point, the distance between the demand coordinates and the housing source coordinates is calculated to obtain multiple first distances; the housing source information is sorted from small to large according to the first distance to obtain a sorting result; and the housing source information of the first preset number in the sorting result is determined as the first housing source information.

[0103] In this embodiment, different methods are used to determine the first housing source information according to different demand coordinates. When the demand coordinates are a range composed of multiple coordinate points, all housing source coordinates within the range are determined as the first housing source coordinates, and the housing source information corresponding to the first housing source coordinates is determined as the first housing source information; when the demand coordinates are one coordinate point, the first distance between the demand coordinates and all housing source coordinates is calculated, and all housing source information is sorted from small to large according to the first distance to obtain a sorting result, and the housing source information before a first preset number in the sorting result is determined as the first housing source information, wherein the first preset number is pre-set and is not specifically limited here.

[0104] Further, the first housing source information is determined based on the demand coordinates and the housing source coordinates, including: if the first housing source information does not exist, determining the demand information corresponding to the preset characteristics in the first demand information as standard demand information; obtaining a recommended transaction order, the recommended transaction order includes standard demand information and transaction demand information, the transaction demand information is information of the characteristic type corresponding to the standard demand information in the transaction housing information; determining the recommended transaction order in which the standard demand information and the transaction demand information are different as an alternative transaction order; determining the standard demand information and the transaction demand information of the same characteristic type in each alternative transaction order as a characteristic combination; counting the number of each characteristic combination in the alternative transaction order; determining the substitution relationship based on the number; determining the alternative demand information based on the standard demand information and the substitution relationship; converting the alternative demand information into alternative demand coordinates in a multidimensional coordinate system based on preset rules; and determining the first housing source information based on the alternative demand coordinates and the housing source coordinates.

[0105] In this embodiment, when the demand coordinates are a range composed of multiple coordinate points and there are no house coordinates within the range, that is, when the first house information does not exist, the demand information corresponding to the preset features in the first demand information is determined as the standard demand information. For example, the preset features include the house type, and the first demand information includes that the house type is two bedrooms and one living room, then the standard demand information includes that the house type is two bedrooms and one living room.

[0106] Historical recommended transaction orders are obtained from the database. The recommended transaction orders include standard demand information (determined based on the user's first demand information at the time and preset features) and corresponding transaction demand information. For example, the standard demand information includes that the house type is two bedrooms and one living room. The house type corresponding to the actual transaction information is three bedrooms and one living room. The corresponding transaction demand information includes that the house type is three bedrooms and one living room. The recommended transaction order with different standard demand information and corresponding transaction demand information is determined as an alternative transaction order, that is, an order that is completed by replacing part of the demand.

[0107] The standard demand information and transaction demand information of the same feature type (such as house type) in each alternative transaction order are determined as a feature combination. For example, a feature combination is that the standard demand information includes that the house type is two bedrooms and one living room, and the transaction demand information includes that the house type is three bedrooms and one living room. Since there may be multiple feature types, each alternative transaction order will include multiple feature combinations. At the same time, the feature types corresponding to the multiple feature combinations are different. In addition, since there are multiple alternative transaction orders, one feature type will also correspond to multiple feature combinations.

[0108] The number of each feature combination in all replacement transaction orders is counted, and the feature combination whose number exceeds the preset feature number is determined as the replacement feature combination. The standard demand information in the replacement feature combination and the two feature types actually corresponding to the transaction demand information have a replacement relationship. For example, a feature combination is that the standard demand information includes the house type of two bedrooms and one living room, and the transaction demand information includes the house type of three bedrooms and one living room. The number of such feature combinations exceeds the preset feature number, and the two feature types of "two bedrooms and one living room" and "three bedrooms and one living room" have a replacement relationship. That is, by analyzing the recommended transaction orders, a high-frequency replacement combination is found, and then the probability of transaction can be increased by replacing it according to the replacement combination.

[0109] According to the standard demand information, find the alternative demand information from the alternative relationship. For example, there is a substitution relationship between the two feature types "two bedrooms and one living room" and "three bedrooms and one living room". The standard demand information is "two bedrooms and one living room", and the alternative demand information is "three bedrooms and one living room".

[0110] The method for converting the alternative demand information into alternative demand coordinates in a multidimensional coordinate system is the same as above and will not be repeated here; based on the alternative demand coordinates and the house source coordinates, the first house source information is re-determined according to the method for determining the first house source information as described above.

[0111] Step S106: Determine the second demand information based on the preset characteristics and the first demand information.

[0112] The second demand information is the first demand information that does not exist in the preset feature, that is, the information corresponding to the preset feature in the first demand information is deleted, and the remaining information is the second demand information.

[0113] Step S107: Determine recommended housing information based on the first housing information and the second demand information.

[0114] Specifically, determining recommended housing information based on the first housing information and the second demand information includes: obtaining user information; determining user preference information based on the user information and the second demand information, the user preference information including housing preference information and public facility preference; determining preference types and preference weights based on the user preference information; determining matching preference types based on the first housing information and the preference types; calculating a first score based on the matching preference types and corresponding preference weights; obtaining first historical transaction information and recommendation records of the first housing information; determining the number of historical transactions based on the first historical transaction information; determining the number of recommendations based on the recommendation records; calculating the historical transaction ratio based on the number of recommendations and the historical number of transactions; determining a second score based on the historical transaction ratio; determining a housing score based on the first score, the second score and a preset weight; sorting the first housing information according to the housing score to obtain a sorting result; and determining recommended housing information based on the sorting result and a second preset number.

[0115] In this embodiment, user information is obtained from a user database, and the user information and the second demand information are analyzed by a data analysis tool to obtain user preference information, wherein the data analysis tool can be EXCEL, Python, or MATLAB, which is not specifically limited here.

[0116] Search the preference categories and the preference weights corresponding to each preference category from the user preference information, such as decoration style. Search for the preference categories that can be matched in each first housing source information, and determine the preference category as the matching preference category. The value corresponding to the matching preference category is determined to be 1, and the values ​​corresponding to the remaining preference categories are 0. For example: the first housing source information A includes three matching preference categories, and the preference weights corresponding to the three matching preference categories are 0.2, 0.3, and 0.1 respectively. Then the first score corresponding to the first housing source information A is 0.2+0.3+0.1=0.6.

[0117] Obtain historical transaction information corresponding to the first property information from the database, that is, the first historical transaction information, count the historical transaction times of each first property information, and obtain recommendation records from the database, that is, records recommended to users, count the number of recommendations, and calculate the historical transaction ratio through the formula "historical transaction ratio = historical transaction times / recommendation times". The database stores the corresponding relationship between the historical transaction ratio and the second score, and obtains the corresponding second score from the database according to the historical transaction ratio.

[0118] The preset weights include a first preset weight and a second preset weight. The first preset weight is greater than the second preset weight. The property score is calculated as the first score * first preset weight + second score * second preset weight. The first property information is sorted from large to small according to the property score to obtain a sorting result, and the first property information of the first second preset number in the sorting result is determined as the recommended property information.

[0119] Furthermore, user preference information is determined based on the user information and the second demand information, including: determining historical search information, historical transaction information and collection information based on the user information; analyzing the historical search information, historical transaction information and collection information to obtain first preference information; determining the user subject category based on the user information; obtaining second historical transaction information based on the user subject category, the second historical transaction information including historical transaction information corresponding to the user subject category; analyzing the second historical transaction information to obtain second preference information; determining the user preference information based on the first preference information, the second preference information and the second demand information.

[0120] In this embodiment, historical search information, historical transaction information and favorite information are searched from the user information, and the historical search information, historical transaction information and favorite information are analyzed by data analysis technology to obtain the user's first preference information, wherein the data analysis technology may be cluster analysis or association rule mining, which is not specifically limited here. The first preference information may include floor, decoration style, etc., and the user subject category (for example, sports) is obtained from the user information. The historical transaction information corresponding to the user subject category is obtained from the database, that is, the second historical transaction information. The housing information in the second historical transaction information is analyzed by data analysis technology to obtain the second preference information. The housing information includes public facility information within a preset distance, such as parks, hospitals, and gyms, so the second preference information includes public facility preference. The first preference information, the second preference information and the second demand information are jointly determined as the user preference information.

[0121] When the recommended housing information is pushed to the user, the multi-dimensional coordinate system, the housing coordinates corresponding to the recommended housing information and the demand coordinates can also be pushed synchronously, so that the user can view the relationship between the housing and the demand more intuitively.

[0122] Specifically, after determining the recommended housing information based on the first housing information and the second demand information, the method also includes: obtaining user feedback information, the user feedback information including satisfaction and user chat records; if the user is not satisfied with the recommended housing information, analyzing the chat records to determine the user's emotional state and third demand information; obtaining the correspondence between the emotional state and the housing demand; determining the fourth demand information based on the correspondence and the emotional state; determining the user demand information based on the first demand information, the third demand information and the fourth demand information; and re-screening the housing information based on the user demand information to obtain new recommended housing information.

[0123] The user's emotional state is also very important for choosing a house. For example, recommending a more spacious and brighter house when the user is anxious can soothe the user's emotions and improve user satisfaction.

[0124] In this embodiment, after the recommended housing information is pushed to the user, user feedback information is obtained from the user. If the user is dissatisfied with the recommended housing information, the user chat record is input into the Few shot model or the machine learning model to obtain the user's emotional state. The user's emotional state includes excitement, anxiety, and satisfaction. Both the Few shot model and the machine learning model are models trained with sample data. The correspondence between the user's emotional state and the housing demand is obtained from the database. The fourth demand information is searched from the correspondence according to the emotional state, and the third demand information is filtered from the chat record. The first demand information, the third demand information and the fourth demand information are jointly determined as the user demand information. The housing information is re-filtered according to the user demand information to obtain new recommended housing information. The filtering steps are the same as above and will not be repeated here.

[0125] Specifically, before obtaining user feedback information, the method also includes: obtaining physical data of the house; constructing a three-dimensional model of the house based on the physical data of the house; and simulating the decoration of the house through the three-dimensional model in response to user instructions.

[0126] The physical data of the house is obtained from the database or the owner, and the physical data of the house is input into the 3D model tool to construct a 3D model of the house. The 3D model tool can be SketchUp, Revit, or 3ds Max. Users can choose their favorite furniture types, placements, and wallpapers through the 3D model, so as to simulate the house decoration more intuitively, and provide user feedback information based on the display effects corresponding to the house decoration.

[0127] Figure 2 A structural block diagram of a housing recommendation device 200 provided in an embodiment of the present application.

[0128] like Figure 2 As shown, the housing source recommendation device 200 mainly includes:

[0129] The information acquisition module 201 is used to acquire the first demand information and the house source information;

[0130] A coordinate establishing module 202, used to establish a multi-dimensional coordinate system based on preset features;

[0131] A house source conversion module 203, used to convert house source information into house source coordinates in a multi-dimensional coordinate system based on preset rules;

[0132] A demand conversion module 204, configured to convert the first demand information into demand coordinates in a multi-dimensional coordinate system based on a preset rule;

[0133] A first determination module 205, configured to determine first house source information based on the demand coordinates and the house source coordinates;

[0134] A demand screening module 206, configured to determine second demand information based on the preset features and the first demand information, wherein the second demand information is the first demand information that does not exist in the preset features;

[0135] The second determining module 207 is used to determine recommended housing information based on the first housing information and the second demand information.

[0136] As an optional implementation of this embodiment, the house conversion module 203 is also specifically used to convert the house information into house coordinates in a multi-dimensional coordinate system based on preset rules, including: standardizing the information corresponding to the preset features in the house information to obtain standardized features; determining the origin feature based on the multi-dimensional coordinate system; calculating the distance between the standardized feature and the origin feature and the direction of the coordinate axis based on preset rules; and determining the house coordinates based on multiple distances and corresponding coordinate axis directions.

[0137] As an optional implementation of this embodiment, the first determination module 205 is also specifically used to determine the first housing source information based on the demand coordinates and the housing source coordinates, including: if the demand coordinates are a range composed of multiple coordinate points, the housing source coordinates within the range are determined as the first housing source coordinates; the housing source information corresponding to the first housing source coordinates is determined as the first housing source information; if the demand coordinates are a coordinate point, the distance between the demand coordinates and the housing source coordinates is calculated to obtain multiple first distances; the housing source information is sorted from small to large according to the first distance to obtain a sorting result; and the housing source information of the first preset number in the sorting result is determined as the first housing source information.

[0138] As an optional implementation manner of this embodiment, the first determination module 205 is also specifically used to determine the first housing source information based on the demand coordinates and the housing source coordinates, including: if the first housing source information does not exist, determining the demand information corresponding to the preset characteristics in the first demand information as the standard demand information; obtaining a recommended transaction order, the recommended transaction order includes the standard demand information and the transaction demand information, the transaction demand information is the information of the feature type corresponding to the standard demand information in the transaction housing information; determining the recommended transaction order in which the standard demand information and the transaction demand information are different as an alternative transaction order; determining the standard demand information and the transaction demand information of the same feature type in each alternative transaction order as a feature combination; counting the number of each feature combination in the alternative transaction order; determining the substitution relationship based on the number; determining the alternative demand information based on the standard demand information and the substitution relationship; converting the alternative demand information into alternative demand coordinates in a multidimensional coordinate system based on preset rules; and determining the first housing source information based on the alternative demand coordinates and the housing source coordinates.

[0139] As an optional implementation of this embodiment, the second determination module 207 is also specifically used to determine recommended housing information based on the first housing information and the second demand information, including: obtaining user information; determining user preference information based on the user information and the second demand information, the user preference information including housing preference information and public facility preference; determining preference types and preference weights based on the user preference information; determining matching preference types based on the first housing information and the preference types; calculating a first score based on the matching preference types and corresponding preference weights; obtaining first historical transaction information and recommendation records of the first housing information; determining the number of historical transactions based on the first historical transaction information; determining the number of recommendations based on the recommendation records; calculating the historical transaction ratio based on the number of recommendations and the historical number of transactions; determining a second score based on the historical transaction ratio; determining a housing score based on the first score, the second score and a preset weight; sorting the first housing information according to the housing score to obtain a sorting result; and determining the recommended housing information based on the sorting result and a second preset number.

[0140] As an optional implementation of this embodiment, the second determination module 207 is also specifically used to determine user preference information based on user information and second demand information, including: determining historical search information, historical transaction information and collection information based on user information; analyzing the historical search information, historical transaction information and collection information to obtain first preference information; determining the user subject category based on the user information; obtaining second historical transaction information based on the user subject category, the second historical transaction information including historical transaction information corresponding to the user subject category; analyzing the second historical transaction information to obtain second preference information; determining the user preference information based on the first preference information, the second preference information and the second demand information.

[0141] As an optional implementation of this embodiment, the second determination module 207 is also specifically used to, after determining the recommended housing information based on the first housing information and the second demand information, also include: obtaining user feedback information, the user feedback information including satisfaction and user chat records; if the user is not satisfied with the recommended housing information, analyzing the chat records to determine the user's emotional state and third demand information; obtaining the correspondence between the emotional state and the housing demand; determining the fourth demand information based on the correspondence and the emotional state; determining the user demand information based on the first demand information, the third demand information and the fourth demand information; and re-screening the housing information based on the user demand information to obtain new recommended housing information.

[0142] In one example, the module in any of the above devices can be one or more integrated circuits configured to implement the above methods, such as: one or more application specific integrated circuits (ASICs), or, one or more digital signal processors (DSPs), or, one or more field programmable gate arrays (FPGAs), or a combination of at least two of these integrated circuit forms.

[0143] For another example, when the modules in the device can be implemented in the form of a processing element scheduling program, the processing element can be a general-purpose processor, such as a central processing unit (CPU) or other processor that can call a program. For another example, these modules can be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0144] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and modules can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0145] Figure 3 A structural block diagram of an electronic device 300 provided in an embodiment of the present application.

[0146] like Figure 3 As shown, the electronic device 300 includes a processor 301 and a memory 302 , and may further include an information input / information output (I / O) interface 303 , one or more of a communication component 304 , and a communication bus 305 .

[0147] The processor 301 is used to control the overall operation of the electronic device 300 to complete all or part of the steps of the above-mentioned housing recommendation method; the memory 302 is used to store various types of data to support the operation of the electronic device 300, and these data may include, for example, instructions for any application or method operated on the electronic device 300, and data related to the application. The memory 302 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0148] The I / O interface 303 provides an interface between the processor 301 and other interface modules, and the above-mentioned other interface modules can be keyboards, mice, buttons, etc. These buttons can be virtual buttons or physical buttons. The communication component 304 is used for wired or wireless communication between the electronic device 300 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G or 4G, or a combination of one or more of them, so the corresponding communication component 304 can include: Wi-Fi components, Bluetooth components, NFC components.

[0149] The electronic device 300 can be implemented by one or more application specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field programmable gate arrays (FPGA), controllers, microcontrollers, microprocessors or other electronic components to execute the housing recommendation method given in the above embodiment.

[0150] The communication bus 305 may include a path to transmit information between the above components. The communication bus 305 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The communication bus 305 may be divided into an address bus, a data bus, a control bus, etc.

[0151] The electronic device 300 may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc., and may also be servers, etc.

[0152] The present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned housing recommendation method are implemented.

[0153] The computer-readable storage medium may include: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0154] 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.

[0155] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of application involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the aforementioned application concept. For example, the above features are replaced with (but not limited to) technical features with similar functions applied in the present application.

Claims

1. A housing recommendation method, characterized in that: include: Acquire first demand information and house source information, wherein the first demand information is acquired from the chat record; Establish a multi-dimensional coordinate system based on preset features; Converting the house source information into house source coordinates in the multi-dimensional coordinate system based on preset rules; Converting the first demand information into demand coordinates in the multidimensional coordinate system based on a preset rule; Determine first housing source information based on the demand coordinates and the housing source coordinates; Determine second requirement information based on the preset feature and the first requirement information, where the second requirement information is the first requirement information that does not exist in the preset feature; Determine recommended housing information based on the first housing information and the second demand information; The determining the first housing source information based on the demand coordinates and the housing source coordinates includes: If the first housing source information does not exist, determining the demand information corresponding to the preset feature in the first demand information as standard demand information; Acquire a recommended transaction order, wherein the recommended transaction order includes standard demand information and transaction demand information, wherein the transaction demand information is information of a characteristic type corresponding to the standard demand information in the transaction housing source information; Determining the recommended transaction order that has different standard demand information and transaction demand information as a replacement transaction order; Determine the standard requirement information and the transaction requirement information of the same feature type in each of the replacement transaction orders as a feature combination; Counting the number of each feature combination in the alternative transaction orders; determining a substitution relationship based on the quantities; Determine alternative requirement information based on the standard requirement information and the alternative relationship; Converting the replacement demand information into replacement demand coordinates in the multi-dimensional coordinate system based on the preset rule; Determine first housing source information based on the alternative demand coordinates and the housing source coordinates; The determining the recommended housing information based on the first housing information and the second demand information includes: Get user information; Determine user preference information based on the user information and the second demand information, the user preference information including housing preference information and public facility preference; Determining a preference type and a preference weight based on the user preference information; Determine a matching preference category based on the first housing source information and the preference category; Calculating a first score based on the matching preference type and the corresponding preference weight; Obtaining first historical transaction information and recommendation records of the first property information; Determine the number of historical transactions based on the first historical transaction information; determining the number of recommendations based on the recommendation record; Calculate the historical transaction ratio based on the number of recommendations and the number of historical transactions, where the historical transaction ratio=the number of historical transactions / the number of recommendations; Determining a second score based on the historical transaction ratio; Determine a house source score based on the first score, the second score, and a preset weight; Sorting the first house source information according to the house source scores to obtain a sorting result; Recommended housing information is determined based on the sorting result and a second preset number.

2. The method according to claim 1, characterized in that The converting the house source information into house source coordinates in the multi-dimensional coordinate system based on a preset rule includes: Standardizing the information corresponding to the preset features in the house information to obtain standardized features; Determining an origin feature based on the multidimensional coordinate system; Calculate the distance between the standardized feature and the origin feature and the direction of the coordinate axis based on a preset rule; The property coordinates are determined based on the multiple distances and the corresponding coordinate axis directions.

3. The method according to claim 1, characterized in that The determining the first housing source information based on the demand coordinates and the housing source coordinates includes: If the required coordinates are a range consisting of multiple coordinate points, the house source coordinates within the range are determined as first house source coordinates; and the house source information corresponding to the first house source coordinates is determined as first house source information; If the required coordinate is a coordinate point, the distance between the required coordinate and the house source coordinate is calculated to obtain a plurality of first distances; Sort the house information in ascending order according to the first distance to obtain a sorting result; The first preset number of house source information in the sorting result is determined as the first house source information.

4. The method according to claim 1, characterized in that: The determining the user preference information based on the user information and the second demand information includes: Determine historical search information, historical transaction information, and favorite information based on the user information; Analyze the historical search information, the historical transaction information, and the favorite information to obtain first preference information; Determine the user's subject category based on the user information; Acquire second historical transaction information based on the user subject category, where the second historical transaction information includes historical transaction information corresponding to the user subject category; Analyze the second historical transaction information to obtain second preference information; The user preference information is determined based on the first preference information, the second preference information, and the second requirement information.

5. The method according to claim 1, characterized in that After determining the recommended housing information based on the first housing information and the second demand information, the method further includes: Obtaining user feedback information, wherein the user feedback information includes satisfaction and user chat records; If the user is not satisfied with the recommended housing information, the chat record is analyzed to determine the user's emotional state and third demand information; Obtain the correspondence between emotional state and housing demand; Determining fourth demand information based on the corresponding relationship and the emotional state; Determine user demand information based on the first demand information, the third demand information and the fourth demand information; The housing information is re-screened based on the user demand information to obtain new recommended housing information.

6. A housing recommendation device, characterized in that: include: An information acquisition module, used to acquire first demand information and house source information, wherein the first demand information is acquired from the chat record; A coordinate establishment module, used to establish a multi-dimensional coordinate system based on preset features; A housing source conversion module, used for converting the housing source information into housing source coordinates in the multi-dimensional coordinate system based on preset rules; A demand conversion module, used for converting the first demand information into demand coordinates in the multi-dimensional coordinate system based on preset rules; A first determining module, configured to determine first housing source information based on the required coordinates and the housing source coordinates; A demand screening module, used to determine second demand information based on the preset feature and the first demand information, where the second demand information is the first demand information that does not exist in the preset feature; A second determining module, configured to determine recommended housing information based on the first housing information and the second demand information; The first determination module is specifically used to determine the first housing source information based on the demand coordinates and the housing source coordinates, including: If the first housing source information does not exist, determining the demand information corresponding to the preset feature in the first demand information as standard demand information; Acquire a recommended transaction order, wherein the recommended transaction order includes standard demand information and transaction demand information, wherein the transaction demand information is information of a characteristic type corresponding to the standard demand information in the transaction housing source information; Determining the recommended transaction order that has different standard demand information and transaction demand information as a replacement transaction order; Determine the standard requirement information and the transaction requirement information of the same feature type in each of the replacement transaction orders as a feature combination; Counting the number of each feature combination in the alternative transaction orders; determining a substitution relationship based on the quantities; Determine alternative requirement information based on the standard requirement information and the alternative relationship; Converting the replacement demand information into replacement demand coordinates in the multi-dimensional coordinate system based on the preset rule; Determine first housing source information based on the alternative demand coordinates and the housing source coordinates; The second determination module is specifically used to determine the recommended housing information based on the first housing information and the second demand information, including: Get user information; Determine user preference information based on the user information and the second demand information, the user preference information including housing preference information and public facility preference; Determining a preference type and a preference weight based on the user preference information; Determine a matching preference category based on the first housing source information and the preference category; Calculating a first score based on the matching preference type and the corresponding preference weight; Obtaining first historical transaction information and recommendation records of the first property information; Determine the number of historical transactions based on the first historical transaction information; determining the number of recommendations based on the recommendation record; Calculate the historical transaction ratio based on the number of recommendations and the number of historical transactions, where the historical transaction ratio=the number of historical transactions / the number of recommendations; Determining a second score based on the historical transaction ratio; Determine a house source score based on the first score, the second score, and a preset weight; Sorting the first house source information according to the house source scores to obtain a sorting result; Recommended housing information is determined based on the sorting result and a second preset number.

7. An electronic device, characterized in that: comprising a processor coupled to a memory; The processor is configured to execute a computer program stored in the memory, so that the electronic device executes the method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that: The method comprises a computer program or an instruction, which, when executed on a computer, causes the computer to execute the method according to any one of claims 1 to 5.

Images