House resource information recommendation method and device, computer equipment, readable storage medium and program product

Abstract

The invention relates to the field of big data, and discloses a housing resource information recommendation method and device, computer equipment, a readable storage medium and a program product. The method comprises the following steps: acquiring a plurality of housing resource information features of a target housing resource and a plurality of object information features of a target object; determining a first feature category corresponding to each housing resource information feature and a second feature category corresponding to each object information feature; detecting feature category correlation information between each first feature category and each second feature category; according to the feature category correlation information, matching an object information feature for each housing resource information feature, and according to all the matched housing resource information features and object information features, generating a recommendation adaptation degree between the target housing resource and the target object; generating a housing resource recommendation list according to the recommendation adaptation degrees of the plurality of target housing resources; and according to the housing resource recommendation list, housing resource information recommendation is carried out on the target object. By adopting the method, the accuracy of house resource recommendation can be improved.

Description

Technical Field

[0001] This application relates to the field of big data technology, and in particular to a method, apparatus, computer device, computer-readable storage medium, and computer program product for recommending housing information. Background Technology

[0002] With the development of the real estate industry and the economy, people's demand for housing has become increasingly apparent. In order to improve the efficiency of users' housing selection, housing information recommendation technology has emerged.

[0003] Traditional methods of recommending housing information involve showing users one or more general indicators (such as property value, location, and age of the property), and then recommending housing information to users based on the range or conditions of the indicators they select.

[0004] However, when using the above-mentioned housing information recommendation method, users' actual needs may be complex (for example, they may have requirements for multiple indicators), making it impossible to obtain housing information that combines various user needs, which leads to lower accuracy in housing information recommendation. Summary of the Invention

[0005] Therefore, it is necessary to provide a method, apparatus, computer equipment, computer-readable storage medium, and computer program product that can improve the accuracy of housing information recommendation in response to the above-mentioned technical problems.

[0006] Firstly, this application provides a method for recommending housing information, including:

[0007] Obtain multiple property information features of the target property and multiple object information features of the target object;

[0008] Determine the first feature category corresponding to each of the housing information features and the second feature category corresponding to each of the object information features;

[0009] Detect feature category correlation information between each of the first feature category and each of the second feature categories;

[0010] Based on the feature category relevance information, match object information features for each property information feature, and generate a recommendation fit between the target property and the target object based on all matched property information features and object information features.

[0011] A property recommendation list is generated based on the recommendation suitability of multiple target properties.

[0012] Based on the property recommendation list, property information is recommended to the target audience.

[0013] In one embodiment, matching object information features for each of the housing information features based on the feature category relevance information includes:

[0014] Based on the feature category correlation information, select one-to-one matching first feature categories and second feature categories from all first feature categories and all second feature categories;

[0015] For the first feature category and the second feature category that are matched one-to-one, the housing information feature is randomly selected from the first feature category, and the object information feature is randomly selected from the second feature category;

[0016] The randomly selected housing information features and the randomly selected object information features are determined as mutually matching housing information features and object information features.

[0017] In one embodiment, matching object information features for each of the housing information features based on the feature category relevance information includes:

[0018] Based on the feature category correlation information, select one-to-one matching first feature categories and second feature categories from all first feature categories and all second feature categories;

[0019] For the first feature category and the second feature category that are matched one-to-one, the housing information feature is randomly selected from the first feature category, and the object information feature is randomly selected from the second feature category;

[0020] The randomly selected housing information features and the randomly selected object information features are determined as mutually matching housing information features and object information features.

[0021] In one embodiment, generating a recommendation fit between the target property and the target object based on all matching property information features and object information features includes:

[0022] For each set of matched housing information features and object information features, obtain the first feature score corresponding to the housing information features and the second feature score corresponding to the object information features, and calculate the absolute value of the difference between the first feature score and the second feature score;

[0023] Based on the absolute value of the difference between the property information features and the object information features of each matching pair, a recommendation fit degree is generated between the target property and the target object.

[0024] In one embodiment, detecting feature category correlation information between each of the first feature category and each of the second feature categories includes:

[0025] Obtain multiple first target features belonging to the first feature category and multiple second target features belonging to the second feature category from a preset database;

[0026] Generate multiple first target feature vectors corresponding to the first target features, and multiple second target feature vectors corresponding to the second target features;

[0027] Based on the vector distance between the first target feature vector and the second target feature vector, feature category correlation information between the first feature category and the second feature category is detected.

[0028] In one embodiment, the property information features include at least one of the following: property location information, property value assessment information, property area information, and surrounding environment information of the target property; the object information features include at least one of the following: the target object's work status information, age information, user consumption information, and associated object information.

[0029] Secondly, this application also provides a housing information recommendation device, comprising:

[0030] The acquisition module is used to acquire multiple property information features of the target property and multiple object information features of the target object;

[0031] The determining module is used to determine the first feature category corresponding to each of the housing information features and the second feature category corresponding to each of the object information features;

[0032] The first detection module is used to detect feature category correlation information between each first feature category and each second feature category;

[0033] The second detection module is used to match object information features for each property information feature according to the feature category relevance information, and generate a recommendation fit between the target property and the target object based on all the matched property information features and object information features.

[0034] The generation module is used to generate a property recommendation list based on the recommendation fit of multiple target properties;

[0035] The recommendation module is used to recommend housing information to the target object based on the housing recommendation list.

[0036] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0037] Obtain multiple property information features of the target property and multiple object information features of the target object;

[0038] Determine the first feature category corresponding to each of the housing information features and the second feature category corresponding to each of the object information features;

[0039] Detect feature category correlation information between each of the first feature category and each of the second feature categories;

[0040] Based on the feature category relevance information, match object information features for each property information feature, and generate a recommendation fit between the target property and the target object based on all matched property information features and object information features.

[0041] A property recommendation list is generated based on the recommendation suitability of multiple target properties.

[0042] Based on the property recommendation list, property information is recommended to the target audience.

[0043] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0044] Obtain multiple property information features of the target property and multiple object information features of the target object;

[0045] Determine the first feature category corresponding to each of the housing information features and the second feature category corresponding to each of the object information features;

[0046] Detect feature category correlation information between each of the first feature category and each of the second feature categories;

[0047] Based on the feature category relevance information, match object information features for each property information feature, and generate a recommendation fit between the target property and the target object based on all matched property information features and object information features.

[0048] A property recommendation list is generated based on the recommendation suitability of multiple target properties.

[0049] Based on the property recommendation list, property information is recommended to the target audience.

[0050] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0051] Obtain multiple property information features of the target property and multiple object information features of the target object;

[0052] Determine the first feature category corresponding to each of the housing information features and the second feature category corresponding to each of the object information features;

[0053] Detect feature category correlation information between each of the first feature category and each of the second feature categories;

[0054] Based on the feature category relevance information, match object information features for each property information feature, and generate a recommendation fit between the target property and the target object based on all matched property information features and object information features.

[0055] A property recommendation list is generated based on the recommendation suitability of multiple target properties.

[0056] Based on the property recommendation list, property information is recommended to the target audience.

[0057] The aforementioned housing information recommendation method, apparatus, computer equipment, computer-readable storage medium, and computer program product acquire multiple housing information features of a target housing unit and multiple object information features of a target object; determine a first feature category corresponding to each housing information feature and a second feature category corresponding to each object information feature; detect feature category correlation information between each first feature category and each second feature category; match object information features for each housing information feature based on the feature category correlation information, and generate a recommendation fit degree between the target housing unit and the target object based on all matched housing information features and object information features; generate a housing recommendation list based on the recommendation fit degrees of multiple target housing units; and recommend housing information to the target object based on the housing recommendation list.

[0058] Thus, by acquiring multiple object information features of the target object, the needs of the target object are obtained. By determining the first feature category corresponding to the property information features and the second feature category corresponding to the object information features, feature classification is achieved. By matching object information features with feature category relevance information, property information features and object information features with matching relationships are obtained. Based on all matched property information features and object information features, a recommendation fit degree between the target property and the target object is generated. This generated recommendation fit degree does not depend on existing property information features and object information features, but is derived according to the matching relationship. Thus, the recommendation fit degree between the target property and the target object quantifies whether the needs of the target object match the target property. The property recommendation list generated according to the recommendation fit degree of the target property is then used to recommend property information to the target object. This can achieve the goal of recommending property information that is as close as possible to the needs of the target object, improving the accuracy of property information recommendation. Attached Figure Description

[0059] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0060] Figure 1 This is a diagram illustrating the application environment of a housing information recommendation method in one embodiment.

[0061] Figure 2 This is a flowchart illustrating a housing information recommendation method in one embodiment;

[0062] Figure 3 This is a flowchart illustrating the steps of detecting feature category correlation information between each first feature category and each second feature category in one embodiment;

[0063] Figure 4 This is a structural block diagram of a housing information recommendation device in one embodiment;

[0064] Figure 5 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0065] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application. It should be noted that existing industry solutions such as software, components, and models may be mentioned in the embodiments of this application. These should be considered exemplary and are intended only to illustrate the feasibility of implementing the technical solutions of this application, but do not imply that the applicant has already used or necessarily used such solutions.

[0066] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of related data must comply with relevant regulations. The acquisition, storage, use and processing of data in the technical solution of this application all comply with the relevant provisions of national laws and regulations.

[0067] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.

[0068] The housing information recommendation method provided in this application embodiment can be applied to, for example, Figure 1In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104 or placed on a cloud or other network server. Server 104 acquires multiple property information features of the target property and multiple object information features of the target object; determines the first feature category corresponding to each property information feature and the second feature category corresponding to each object information feature; detects the feature category correlation information between each first feature category and each second feature category; matches object information features for each property information feature based on the feature category correlation information, and generates a recommendation fit between the target property and the target object based on all matched property information features and object information features; generates a property recommendation list based on the recommendation fit of multiple target properties; and recommends property information to the target object based on the property recommendation list. Specifically, terminal 102 can be the device to which the target object belongs, or a device targeting the target object; therefore, server 104 recommends property information to terminal 102 based on the property recommendation list. The terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, smart in-vehicle systems, and projection devices. Portable wearable devices can include smartwatches, smart bracelets, and head-mounted displays. Head-mounted displays can be virtual reality (VR) devices, augmented reality (AR) devices, and smart glasses. The server 104 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0069] In one exemplary embodiment, such as Figure 2 As shown, a method for recommending housing information is provided, which can be applied to... Figure 1 Taking 104 as an example, the explanation includes steps 202 to 212. Wherein:

[0070] Step 202: Obtain multiple property information features of the target property and multiple object information features of the target object.

[0071] In step 202, the target property is a property in a preset property state, which may include, but is not limited to, waiting to be sold, waiting to be resold, and waiting to be rented. The target object is an object in a preset object state, which may include, but is not limited to, a user, and the target object state may include, but is not limited to, at least one of waiting to buy a house and waiting to rent a house.

[0072] In step 202, the property information features include at least one of the following: property location information, property value assessment information, property area information, and surrounding environment information. The target information features include at least one of the following: target target's employment status information, age information, user consumption information, and associated target information. Property location information can represent the distance of the target property to the nearest landmark building (distances mentioned throughout the text can include, but are not limited to, straight-line distance and walking distance), the administrative district to which the target property belongs, the floor where the target property is located, and the property address. Property area information represents at least one of the following: gross floor area, shared area, internal area, and property area. The surrounding environment information of the property represents at least one of the following: landmark building information, service building information, and ecological environment information. The landmark building information represents the distance between the target property and each landmark building. The service building information represents the distance between the target property and each service building. Service buildings may include, but are not limited to, schools, shopping malls, parks, etc. The ecological environment information can represent the distance between the target property and an ecological park. The ecological environment information can also represent at least one of the following: the greening rate and air quality level of the environment where the target property is located.

[0073] For example, obtaining multiple property information features of a target property includes: retrieving multiple property information features of the target property from a property database, wherein the property database is a database with multiple property information features pre-set.

[0074] As one embodiment, obtaining multiple object information features of the target object includes: obtaining multiple object information features sent by the terminal of the target object.

[0075] As another embodiment, obtaining multiple object information features of the target object includes: obtaining multiple object information features that the target object has typed or selected.

[0076] Step 204: Determine the first feature category corresponding to each housing information feature and the second feature category corresponding to each object information feature.

[0077] For example, step 204 includes: obtaining multiple first preset categories and multiple second preset types; for each housing information feature, selecting a first feature category corresponding to the housing information feature from each first preset category according to the similarity between the housing information feature and each first preset category; for each object information feature, selecting a second feature category corresponding to the object information feature from each second preset category according to the similarity between the object information feature and each second preset category.

[0078] Furthermore, as an embodiment, obtaining multiple first preset categories and multiple second preset types includes: obtaining multiple first preset categories and multiple second preset types that are set as needed.

[0079] In another embodiment, obtaining multiple first preset categories and multiple second preset types includes: obtaining housing information of a first preset number of preset housing units, and obtaining object information of a second preset number of preset objects. The housing status of the preset housing units may include, but is not limited to, pending sale, pending resale, pending rental, rental, and sold status. The first and second preset numbers can be set as needed or are empirical values, and are not limited here. The housing information of the multiple preset housing units is clustered to obtain multiple first clusters, and the object information of the multiple preset objects is clustered to obtain multiple second clusters. Each first cluster is determined as a first preset category, and each second cluster is determined as a second preset category.

[0080] Specifically, clustering methods can include similarity aggregation, such as K-means clustering, Euclidean distance clustering, etc., without any restrictions.

[0081] Step 206: Detect the feature category correlation information between each first feature category and each second feature category.

[0082] In step 206, the feature category correlation information is used to characterize the degree of correlation between the first feature category and the second feature category.

[0083] For example, step 206 includes: detecting feature category correlation information between each first feature category and each second feature category using a preset correlation coefficient detection algorithm.

[0084] Among them, the preset correlation coefficient detection algorithms include, but are not limited to, Pearson correlation coefficient detection algorithm, rank correlation coefficient detection algorithm, intragroup correlation coefficient detection algorithm, multiple correlation coefficient detection algorithm, and partial correlation coefficient detection algorithm.

[0085] Step 208: Based on the feature category relevance information, match object information features for each property information feature, and generate a recommendation fit between the target property and the target object based on all matched property information features and object information features.

[0086] For example, matching object information features for each property information feature based on feature category relevance information includes: filtering first feature categories and second feature categories that correspond one-to-one with each other from all first feature categories and all second feature categories based on feature category relevance information; selecting property information features from the first feature categories for the one-to-one matching first feature categories and second feature categories, and selecting object information features from the second feature categories; and determining the selected property information features and object information features as mutually matching property information features and object information features.

[0087] Furthermore, based on the feature category relevance information, a one-to-one matching first feature category and second feature category are selected from all first feature categories and all second feature categories, including: selecting first feature categories and second feature categories whose corresponding feature category relevance information satisfies the relevance condition from all first feature categories and all second feature categories.

[0088] Among them, the relevance condition can be that the degree of relevance represented by the feature category relevance information is greater than a preset degree threshold. The preset degree threshold can be set as needed or it can be an empirical value. The relevance condition can also be that the ranking of the feature category relevance information among all feature category relevance information meets a preset ranking condition. The preset ranking condition can be that the ranking is not greater than a certain value, for example, the ranking is not greater than 4.

[0089] For example, the first feature category includes feature categories A and B, and the second feature category includes feature categories E, F, and G. The correlation degree represented by the feature category correlation information between feature category A and feature category E is 70%, the correlation degree represented by the feature category correlation information between feature category A and feature category F is 90%, the correlation degree represented by the feature category correlation information between feature category A and feature category G is 75%, the correlation degree represented by the feature category correlation information between feature category B and feature category E is 50%, the correlation degree represented by the feature category correlation information between feature category B and feature category F is 95%, and the correlation degree represented by the feature category correlation information between feature category B and feature category G is 85%. When the correlation condition is that the correlation degree represented by the feature category correlation information is greater than a preset degree threshold, and the preset degree threshold is 80%, feature category A and feature category F are determined to be the corresponding matching first feature category and second feature category; feature category B and feature category F are determined to be the corresponding matching first feature category and second feature category; and feature category B and feature category F are determined to be the corresponding matching first feature category and second feature category.

[0090] Alternatively, if the relevance condition is that the ranking of the feature category relevance information among all feature category relevance information meets a preset ranking condition, specifically that the ranking is no greater than 2, then feature category A and feature category F are determined as the corresponding matching first and second feature categories, feature category A and feature category G are determined as the corresponding matching first and second feature categories; feature category B and feature category F are determined as the corresponding matching first and second feature categories, and feature category B and feature category F are determined as the corresponding matching first and second feature categories.

[0091] As one embodiment, selecting housing information features from a first feature category and selecting object information features from a second feature category includes: randomly selecting housing information features from the first feature category and randomly selecting object information features from the second feature category.

[0092] The random selection can be either a random draw with replacement or a random draw without replacement; there is no restriction on this.

[0093] This ensures that the selected housing information features and object information features have a certain degree of randomness, and that each feature has an equal probability of being selected. Furthermore, the non-replacement random sampling ensures that features specific to the target object are not repeatedly extracted, thus increasing the likelihood that each feature will be selected.

[0094] As one embodiment, selecting housing information features from a first feature category and selecting object information features from a second feature category includes: randomly selecting housing information features from the first feature category and randomly selecting object information features from the second feature category.

[0095] As one embodiment, selecting housing information features from a first feature category and selecting object information features from a second feature category includes: randomly selecting housing information features from the first feature category; generating a second selection probability for each object information feature in the second feature category based on the feature category correlation information between the selected housing information features and each object information feature in the second feature category, wherein the second selection probability is positively correlated with the degree of correlation represented by the feature category correlation information between the object information features and the extracted housing information features; and selecting object information features from the second feature category based on the second selection probability of each object information feature in the second feature category.

[0096] As another embodiment, selecting housing information features from a first feature category and selecting object information features from a second feature category includes: randomly selecting object information features from the second feature category; generating a first selection probability for each housing information feature in the first feature category based on the feature category correlation information between the selected object information features and each housing information feature in the first feature category; wherein the first selection probability is positively correlated with the degree of correlation represented by the feature category correlation information between the housing information features and the extracted object information features; and selecting housing information features from the first feature category based on the first selection probability of each housing information feature in the first feature category.

[0097] Therefore, we can consider randomly selecting one of the feature categories, while selecting the remaining categories based on the selected information features to generate selection probabilities. This ensures that the selected housing information features and object information features are strongly correlated, thus improving the accuracy of information feature selection.

[0098] For example, generating a recommendation fit between a target property and a target object based on all matched property information features and object information features includes: for each set of matched property information features and object information features, obtaining a first feature score corresponding to the property information features and a second feature score corresponding to the object information features, and generating a recommendation fit between the target property and the target object based on the first feature score and the second feature score.

[0099] Furthermore, as an embodiment, obtaining the first feature score corresponding to the housing information feature and the second feature score corresponding to the object information feature includes: obtaining the first feature score corresponding to the housing information feature and the second feature score corresponding to the object information feature through a score calculation formula configured on demand.

[0100] As another embodiment, obtaining a first feature score corresponding to the housing information features and a second feature score corresponding to the object information features includes: normalizing the housing information features to obtain the first feature score; and normalizing the object information features to obtain the second feature score.

[0101] As one embodiment, generating a recommendation fit between a target property and a target object based on a first feature score and a second feature score includes: generating a recommendation fit between a target property and a target object based on the absolute value of the difference between the property information features and the object information features of each set of matched properties.

[0102] Furthermore, based on the absolute value of the difference between the common features of the property information and the object information of each set of matched properties, a recommendation fit between the target property and the target object is generated. This includes: fusing the absolute values ​​of the difference between the common features of the property information and the object information of each set of matched properties to obtain a fusion value; determining the sum of the fusion value and 1 as the fusion sum value; and determining the ratio between 1 and the fusion sum value as the recommendation fit between the target property and the target object.

[0103] Optionally, the ratio between 1 and the sum of the values ​​can be determined as the recommendation fit between the target property and the target object, which can be expressed by the formula:

[0104]

[0105] in, For target properties and target object Recommendation fit between them For the first Group matching target properties The first feature score corresponding to the characteristics of the housing information. For the first Group matching target object The second feature score corresponding to the object information features. The total number of sets of matching housing information features and object information features.

[0106] Thus, a method is provided that incorporates both the first feature score and the second feature score into the recommendation fit decision, ensuring that the recommendation fit reflects the matching degree between the target property and the target object.

[0107] Step 210: Generate a property recommendation list based on the recommendation suitability of multiple target properties.

[0108] For example, step 210 includes: sorting multiple target properties according to their recommendation suitability to obtain a sorting result; and generating a property recommendation list based on the sorting result.

[0109] Furthermore, based on the sorting results, a property recommendation list is generated, including: selecting recommended properties from multiple target properties based on the sorting results and a preset number of properties; and adding the property identifiers of the recommended properties to the property recommendation list, wherein the property identifiers may include, but are not limited to, property names and property numbers.

[0110] The preset number of listings can be set as needed, or it can be an empirical value. It can also correspond to the size (length or width) of the terminal screen used to display the listing recommendations. Specifically, the preset number of listings is positively correlated with the size of the terminal screen used to display the listing recommendations.

[0111] Therefore, considering that the screen size of the terminal used to display the property recommendation list will affect the viewing experience of the target audience to some extent, the preset number of properties is set to be positively correlated with the screen size of the terminal used to display the property recommendation list. This allows the terminal to recommend as many property information as possible to the target audience at once, thereby improving the accuracy of property information recommendations.

[0112] For example, if the preset number of listings is 4, and the sorting result is multiple target listings sorted from highest to lowest recommendation suitability, then the first 4 target listings after sorting will be determined as recommended listings.

[0113] Step 212: Based on the property recommendation list, recommend property information to the target audience.

[0114] For example, step 212 includes: recommending housing information to the target object based on the housing information features corresponding to the housing identifiers included in the housing recommendation list.

[0115] Furthermore, as an embodiment, recommending housing information to a target object based on the housing information features corresponding to the housing identifiers included in the housing recommendation list includes: pushing the housing information features corresponding to the housing identifiers included in the housing recommendation list to the target object's terminal to realize the recommendation of housing information to the target object.

[0116] As another embodiment, based on the property information characteristics of the properties in the property recommendation list, property information is recommended to the target object, including: displaying the property information characteristics corresponding to the property identifiers included in the property recommendation list, so as to realize the property information recommendation to the target object.

[0117] In the aforementioned housing information recommendation method, multiple object information features of the target object are obtained to acquire the target object's needs. The first feature category corresponding to the housing information features and the second feature category corresponding to the object information features are determined to classify the features. Based on the relevance information of the feature categories, object information features are matched for each housing information feature, resulting in matching housing and object information features. Based on all matched housing and object information features, a recommendation fit degree between the target housing and the target object is generated. This generated recommendation fit degree does not depend on existing housing and object information features but is derived from the matching relationship. Therefore, the recommendation fit degree quantifies whether the target object's needs match the target housing. A housing recommendation list generated based on the target housing recommendation fit degree is then used to recommend housing information to the target object. This method aims to recommend housing information that best matches the target object's needs, improving the accuracy of housing information recommendations.

[0118] Based on the characteristics of all matched property information and object information, a recommendation fit is generated between the target property and the target object.

[0119] In one exemplary embodiment, such as Figure 3 As shown, step 206 includes steps 302 to 306. Wherein:

[0120] Step 302: Obtain multiple first target features belonging to the first feature category and multiple second target features belonging to the second feature category from the preset database.

[0121] In step 302, the preset database is used to store multiple property information features of multiple preset properties and multiple object information features of multiple preset objects.

[0122] In step 302, the number of the first target features can be set as needed, or it can be an empirical value, or it can be a value that changes periodically. The selection of the first target features can be set as needed, or it can be selected based on experience, or it can be randomly selected periodically. The number of the second target features can be set as needed, or it can be an empirical value, or it can be a value that changes periodically. The selection of the second target features can be set as needed, or it can be selected based on experience, or it can be randomly selected periodically. There are no restrictions here.

[0123] Step 304: Generate first target feature vectors corresponding to multiple first target features, and second target feature vectors corresponding to multiple second target features.

[0124] For example, step 304 includes: performing feature mapping on the first target feature to obtain a first target feature vector; and performing feature mapping on the second target feature to obtain a second target feature vector.

[0125] Step 306: Detect feature category correlation information between the first feature category and the second feature category based on the vector distance between the first target feature vector and the second target feature vector.

[0126] For example, step 306 includes: calculating the vector distance between the first target feature vector and the second target feature vector, and detecting feature category correlation information between the first feature category and the second feature category based on the vector distance, wherein the vector distance is inversely correlated with the degree of correlation represented by the feature category correlation information between the first feature category and the second feature category.

[0127] In this embodiment, multiple first target features belonging to a first feature category and multiple second target features belonging to a second feature category are obtained from a preset database; first target feature vectors corresponding to the multiple first target features and second target feature vectors corresponding to the multiple second target features are generated; based on the vector distance between the first target feature vectors and the second target feature vectors, feature category correlation information between the first feature category and the second feature category is detected. By using global features from the preset database, feature category correlation information between the first feature category and the second feature category can be generated from a global perspective, rather than generating feature category correlation information based on the features of a single user or property, thus improving the accuracy of generating feature category correlation information between the first feature category and the second feature category.

[0128] As a detailed embodiment, multiple housing information features of the target housing and multiple object information features of the target object are obtained; a first feature category corresponding to each housing information feature and a second feature category corresponding to each object information feature are determined; multiple first target features belonging to the first feature category and multiple second target features belonging to the second feature category are obtained from a preset database; a first target feature vector corresponding to the multiple first target features and a second target feature vector corresponding to the multiple second target features are generated; based on the vector distance between the first target feature vector and the second target feature vector, feature category correlation information between the first feature category and the second feature category is detected; based on the feature category correlation information, a one-to-one matching first feature category and second feature category are selected from all first feature categories and all second feature categories.

[0129] Furthermore, for the one-to-one matching of the first feature category and the second feature category, housing information features are randomly selected from the first feature category, and object information features are randomly selected from the second feature category; the randomly selected housing information features and the randomly selected object information features are determined as mutually matching housing information features and object information features; for each pair of matched housing information features and object information features, the first feature score corresponding to the housing information feature and the second feature score corresponding to the object information feature are obtained, and the absolute value of the difference between the first feature score and the second feature score is calculated; based on the absolute value of the difference corresponding to each pair of matched housing information features and object information features, a recommendation fit degree between the target housing and the target object is generated; based on the recommendation fit degrees of multiple target housings, a housing recommendation list is generated; based on the housing recommendation list, housing information is recommended to the target object.

[0130] In this way, by acquiring multiple object information features of the target object, the needs of the target object are obtained. By determining the first feature category corresponding to the property information features and the second feature category corresponding to the object information features, the features are categorized. Then, by measuring the recommendation fit between the target property and the target object, the matching degree between the target object's needs and the target property is quantified. Based on the property recommendation fit generated according to the target property recommendation fit, property information is recommended to the target object. This can achieve the goal of recommending property information that is as close as possible to the target object's needs, thus improving the accuracy of property information recommendation.

[0131] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0132] Based on the same inventive concept, this application also provides a housing information recommendation device for implementing the housing information recommendation method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more housing information recommendation device embodiments provided below can be found in the limitations of the housing information recommendation method described above, and will not be repeated here.

[0133] In one exemplary embodiment, such as Figure 4 As shown, a housing information recommendation device is provided, including: an acquisition module, a determination module, a first detection module, a second detection module, a generation module, and a recommendation module, wherein:

[0134] The acquisition module is used to acquire multiple property information features of the target property and multiple object information features of the target object.

[0135] The determination module is used to determine the first feature category corresponding to each housing information feature and the second feature category corresponding to each object information feature.

[0136] The first detection module is used to detect the feature category correlation information between each first feature category and each second feature category.

[0137] The second detection module is used to match object information features with each property information feature based on feature category relevance information, and generate a recommendation fit between the target property and the target object based on all matched property information features and object information features.

[0138] The generation module is used to generate a list of recommended properties based on the recommendation fit of multiple target properties.

[0139] The recommendation module is used to recommend housing information to target users based on the housing recommendation list.

[0140] In one embodiment, the second detection module is further configured to: filter first feature categories and second feature categories that correspond one-to-one with each other from all first feature categories and all second feature categories based on feature category correlation information; for the one-to-one matching first feature categories and second feature categories, randomly select housing information features from the first feature categories and randomly select object information features from the second feature categories; and determine the randomly selected housing information features and the randomly selected object information features as mutually matching housing information features and object information features.

[0141] In one embodiment, the second detection module is further configured to: filter first feature categories and second feature categories that correspond one-to-one with each other from all first feature categories and all second feature categories based on feature category correlation information; randomly select housing information features from the first feature categories for the one-to-one matching first feature categories and second feature categories; select object information features from the second feature categories based on the randomly selected housing information features; and determine the randomly selected housing information features and the selected object information features as mutually matching housing information features and object information features.

[0142] In one embodiment, the second detection module is further configured to obtain a first feature score corresponding to the housing information feature and a second feature score corresponding to the object information feature for each set of matched housing information features and object information features, and calculate the absolute value of the difference between the first feature score and the second feature score; and generate a recommendation fit degree between the target housing and the target object based on the absolute value of the difference corresponding to each set of matched housing information features and object information features.

[0143] In one embodiment, the first detection module is further configured to obtain multiple first target features belonging to a first feature category and multiple second target features belonging to a second feature category from a preset database; generate first target feature vectors corresponding to the multiple first target features and second target feature vectors corresponding to the multiple second target features; and detect feature category correlation information between the first feature category and the second feature category based on the vector distance between the first target feature vector and the second target feature vector.

[0144] In one embodiment, the property information features include at least one of the following: property location information, property value assessment information, property area information, and property surrounding environment information; the object information features include at least one of the following: target object's work status information, age information, user consumption information, and associated object information.

[0145] Each module in the aforementioned housing information recommendation device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0146] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 5As shown, the computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a method for recommending housing information. The display unit is used to form a visually visible image and can be a display screen, projection device, or virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0147] Those skilled in the art will understand that Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0148] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0149] Obtain multiple property information features of the target property and multiple object information features of the target object;

[0150] Determine the first feature category corresponding to each housing information feature and the second feature category corresponding to each object information feature;

[0151] Detect the feature category correlation information between each first feature category and each second feature category;

[0152] Based on the relevance information of feature categories, match object information features for each property information feature, and generate a recommendation fit between the target property and the target object based on all matched property information features and object information features.

[0153] A property recommendation list is generated based on the recommendation suitability of multiple target properties.

[0154] Based on the property recommendation list, recommend property information to the target audience.

[0155] In one embodiment, when the processor executes the computer program, it further performs the following steps: based on feature category correlation information, filtering out one-to-one matching first feature categories and second feature categories from all first feature categories and all second feature categories; for the one-to-one matching first feature categories and second feature categories, randomly selecting housing information features from the first feature categories; based on the randomly selected housing information features, selecting object information features from the second feature categories; and determining the randomly selected housing information features and the selected object information features as mutually matching housing information features and object information features.

[0156] In one embodiment, when the processor executes the computer program, it further performs the following steps: based on feature category correlation information, filtering out one-to-one matching first feature categories and second feature categories from all first feature categories and all second feature categories; for the one-to-one matching first feature categories and second feature categories, randomly selecting housing information features from the first feature categories and randomly selecting object information features from the second feature categories; and determining the randomly selected housing information features and randomly selected object information features as mutually matching housing information features and object information features.

[0157] In one embodiment, when the processor executes the computer program, it further performs the following steps: for each set of matched housing information features and object information features, it obtains a first feature score corresponding to the housing information features and a second feature score corresponding to the object information features, and calculates the absolute value of the difference between the first feature score and the second feature score; based on the absolute value of the difference corresponding to each set of matched housing information features and object information features, it generates a recommendation fit between the target housing and the target object.

[0158] In one embodiment, when the processor executes the computer program, it further performs the following steps: obtaining multiple first target features belonging to a first feature category and multiple second target features belonging to a second feature category from a preset database; generating first target feature vectors corresponding to the multiple first target features and second target feature vectors corresponding to the multiple second target features; and detecting feature category correlation information between the first feature category and the second feature category based on the vector distance between the first target feature vector and the second target feature vector.

[0159] In one embodiment, when the processor executes the computer program, it further implements the following steps: the housing information features include at least one of the following: housing location information, housing value assessment information, housing area information, and housing surrounding environment information; the object information features include at least one of the following: target object's work status information, age information, user consumption information, and associated object information.

[0160] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0161] Obtain multiple property information features of the target property and multiple object information features of the target object;

[0162] Determine the first feature category corresponding to each housing information feature and the second feature category corresponding to each object information feature;

[0163] Detect the feature category correlation information between each first feature category and each second feature category;

[0164] Based on the relevance information of feature categories, match object information features for each property information feature, and generate a recommendation fit between the target property and the target object based on all matched property information features and object information features.

[0165] A property recommendation list is generated based on the recommendation suitability of multiple target properties.

[0166] Based on the property recommendation list, recommend property information to the target audience.

[0167] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: filtering first feature categories and second feature categories that correspond one-to-one with each other from all first feature categories and all second feature categories based on feature category correlation information; randomly selecting housing information features from the first feature categories for the one-to-one matching first feature categories and second feature categories; selecting object information features from the second feature categories based on the randomly selected housing information features; and determining the randomly selected housing information features and the selected object information features as mutually matching housing information features and object information features.

[0168] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: based on feature category correlation information, filtering out one-to-one matching first feature categories and second feature categories from all first feature categories and all second feature categories; for the one-to-one matching first feature categories and second feature categories, randomly selecting housing information features from the first feature categories and randomly selecting object information features from the second feature categories; and determining the randomly selected housing information features and randomly selected object information features as mutually matching housing information features and object information features.

[0169] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: for each set of matched housing information features and object information features, obtain a first feature score corresponding to the housing information features and a second feature score corresponding to the object information features, and calculate the absolute value of the difference between the first feature score and the second feature score; and generate a recommendation fit degree between the target housing and the target object based on the absolute value of the difference that corresponds to each set of matched housing information features and object information features.

[0170] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: obtaining multiple first target features belonging to a first feature category and multiple second target features belonging to a second feature category from a preset database; generating first target feature vectors corresponding to the multiple first target features and second target feature vectors corresponding to the multiple second target features; and detecting feature category correlation information between the first feature category and the second feature category based on the vector distance between the first target feature vector and the second target feature vector.

[0171] In one embodiment, when the computer program is executed by the processor, it further implements the following steps: the property information features include at least one of the following: property location information, property value assessment information, property area information, and property surrounding environment information; the object information features include at least one of the following: target object's work status information, age information, user consumption information, and associated object information.

[0172] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0173] Obtain multiple property information features of the target property and multiple object information features of the target object;

[0174] Determine the first feature category corresponding to each housing information feature and the second feature category corresponding to each object information feature;

[0175] Detect the feature category correlation information between each first feature category and each second feature category;

[0176] Based on the relevance information of feature categories, match object information features for each property information feature, and generate a recommendation fit between the target property and the target object based on all matched property information features and object information features.

[0177] A property recommendation list is generated based on the recommendation suitability of multiple target properties.

[0178] Based on the property recommendation list, recommend property information to the target audience.

[0179] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: filtering first feature categories and second feature categories that correspond one-to-one with each other from all first feature categories and all second feature categories based on feature category correlation information; randomly selecting housing information features from the first feature categories for the one-to-one matching first feature categories and second feature categories; selecting object information features from the second feature categories based on the randomly selected housing information features; and determining the randomly selected housing information features and the selected object information features as mutually matching housing information features and object information features.

[0180] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: based on feature category correlation information, filtering out one-to-one matching first feature categories and second feature categories from all first feature categories and all second feature categories; for the one-to-one matching first feature categories and second feature categories, randomly selecting housing information features from the first feature categories and randomly selecting object information features from the second feature categories; and determining the randomly selected housing information features and randomly selected object information features as mutually matching housing information features and object information features.

[0181] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: for each set of matched housing information features and object information features, obtain a first feature score corresponding to the housing information features and a second feature score corresponding to the object information features, and calculate the absolute value of the difference between the first feature score and the second feature score; and generate a recommendation fit degree between the target housing and the target object based on the absolute value of the difference that corresponds to each set of matched housing information features and object information features.

[0182] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: obtaining multiple first target features belonging to a first feature category and multiple second target features belonging to a second feature category from a preset database; generating first target feature vectors corresponding to the multiple first target features and second target feature vectors corresponding to the multiple second target features; and detecting feature category correlation information between the first feature category and the second feature category based on the vector distance between the first target feature vector and the second target feature vector.

[0183] In one embodiment, when the computer program is executed by the processor, it further implements the following steps: the property information features include at least one of the following: property location information, property value assessment information, property area information, and property surrounding environment information; the object information features include at least one of the following: target object's work status information, age information, user consumption information, and associated object information.

[0184] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0185] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0186] The above embodiments are merely illustrative of several implementation methods of this application, and their descriptions are relatively specific and detailed. However, they should not be construed as limiting the scope of this application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for recommending housing information, characterized in that, The method includes: Obtain multiple property information features of the target property and multiple object information features of the target object; Determine the first feature category corresponding to each of the housing information features and the second feature category corresponding to each of the object information features; Detect feature category correlation information between each of the first feature category and each of the second feature categories; Based on the feature category relevance information, match object information features for each property information feature, and generate a recommendation fit between the target property and the target object based on all matched property information features and object information features. A property recommendation list is generated based on the recommendation suitability of multiple target properties. Based on the property recommendation list, property information is recommended to the target audience.

2. The method according to claim 1, characterized in that, The step of matching object information features for each of the property information features based on the feature category relevance information includes: Based on the feature category correlation information, select one-to-one matching first feature categories and second feature categories from all first feature categories and all second feature categories; For the first feature category and the second feature category that are matched one-to-one, the housing information feature is randomly selected from the first feature category, and the object information feature is randomly selected from the second feature category; The randomly selected housing information features and the randomly selected object information features are determined as mutually matching housing information features and object information features.

3. The method according to claim 1, characterized in that, The step of matching object information features for each of the property information features based on the feature category relevance information includes: Based on the feature category correlation information, select one-to-one matching first feature categories and second feature categories from all first feature categories and all second feature categories; For the first feature category and the second feature category that are matched one-to-one, the housing information features are randomly selected from the first feature category; Based on the randomly selected housing information features, the object information features are selected from the second feature category; The randomly selected housing information features and the selected object information features are determined as mutually matching housing information features and object information features.

4. The method according to claim 1, characterized in that, The step of generating a recommendation fit between the target property and the target object based on all matching property information features and object information features includes: For each set of matched housing information features and object information features, obtain the first feature score corresponding to the housing information features and the second feature score corresponding to the object information features, and calculate the absolute value of the difference between the first feature score and the second feature score; Based on the absolute value of the difference between the property information features and the object information features of each matching pair, a recommendation fit degree is generated between the target property and the target object.

5. The method according to claim 1, characterized in that, The detection of feature category correlation information between each of the first feature category and each of the second feature categories includes: Obtain multiple first target features belonging to the first feature category and multiple second target features belonging to the second feature category from a preset database; Generate multiple first target feature vectors corresponding to the first target features, and multiple second target feature vectors corresponding to the second target features; Based on the vector distance between the first target feature vector and the second target feature vector, feature category correlation information between the first feature category and the second feature category is detected.

6. The method according to claim 1, characterized in that, The property information features include at least one of the following: property location information, property value assessment information, property area information, and surrounding environment information of the target property; the target object information features include at least one of the following: target object's work status information, age information, user consumption information, and associated object information.

7. A housing information recommendation device, characterized in that, The device includes: The acquisition module is used to acquire multiple property information features of the target property and multiple object information features of the target object; The determining module is used to determine the first feature category corresponding to each of the housing information features and the second feature category corresponding to each of the object information features; The first detection module is used to detect feature category correlation information between each first feature category and each second feature category; The second detection module is used to match object information features for each property information feature according to the feature category relevance information, and generate a recommendation fit between the target property and the target object based on all the matched property information features and object information features. The generation module is used to generate a property recommendation list based on the recommendation fit of multiple target properties; The recommendation module is used to recommend housing information to the target object based on the housing recommendation list.

8. The apparatus according to claim 7, characterized in that, The second detection module is also used for: Based on the feature category relevance information, match object information features for each of the housing information features; Based on all matching property information features and object information features, a recommended fit degree is generated between the target property and the target object.

9. The apparatus according to claim 8, characterized in that, The second detection module is also used for: Based on the feature category correlation information, select one-to-one matching first feature categories and second feature categories from all first feature categories and all second feature categories; For the first feature category and the second feature category that are matched one-to-one, the housing information feature is randomly selected from the first feature category, and the object information feature is randomly selected from the second feature category; The randomly selected housing information features and the randomly selected object information features are determined as mutually matching housing information features and object information features.

10. The apparatus according to claim 8, characterized in that, The second detection module is also used for: For each set of matched housing information features and object information features, obtain the first feature score corresponding to the housing information features and the second feature score corresponding to the object information features, and calculate the absolute value of the difference between the first feature score and the second feature score; Based on the absolute value of the difference between the property information features and the object information features of each matching pair, a recommendation fit degree is generated between the target property and the target object.

11. The apparatus according to claim 7, characterized in that, The first detection module is also used for: Obtain multiple first target features belonging to the first feature category and multiple second target features belonging to the second feature category from a preset database; Generate multiple first target feature vectors corresponding to the first target features, and multiple second target feature vectors corresponding to the second target features; Based on the vector distance between the first target feature vector and the second target feature vector, feature category correlation information between the first feature category and the second feature category is detected.

12. The apparatus according to claim 7, characterized in that, The property information features include at least one of the following: property location information, property value assessment information, property area information, and surrounding environment information of the target property; the target object information features include at least one of the following: target object's work status information, age information, user consumption information, and associated object information.

13. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

14. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

15. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images