House information processing method, electronic equipment and storage medium

Abstract

Embodiments of the present application provide a house information processing method, an electronic device and a storage medium. In the embodiments of the present application, the original feature information of at least one dimension of house features extracted from the original house description information is polished, and the missing feature information of the house features in the original house description information is completed. Based on the polished feature information of at least one dimension of house features and the missing feature information of house features, the standard house description information of the house to be rented can be generated, the quality of the standard house description information of the house to be rented is effectively improved, and the success rate of house rental is improved.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and in particular to a method for processing housing information, an electronic device, and a storage medium. Background Technology

[0002] With the continuous development of the internet, online rentals have become mainstream. Landlords can post rental listings on rental platforms, and tenants can browse these listings to find suitable properties. In practice, the quality of the rental listings directly impacts the success rate of rentals; therefore, it is essential to improve the quality of rental listings. Summary of the Invention

[0003] This application provides a method for processing housing information, an electronic device, and a storage medium to improve the quality of housing information and thereby increase the success rate of housing rentals.

[0004] This application provides a method for processing housing information, including: obtaining original housing description information in text form of a housing property to be rented; extracting features from the original housing description information to obtain original feature information of at least one dimension of housing features in the original housing description information; refining the original feature information of the at least one dimension of housing features to obtain feature information of the at least one dimension of housing features; determining the missing housing features in the original housing description information based on the multiple dimensions of housing features required for standard housing description information and the at least one dimension of housing features in the original housing description information, and obtaining the feature information of the missing housing features; and generating standard housing description information of the housing property to be rented based on the feature information of the at least one dimension of housing features and the feature information of the missing housing features.

[0005] This application also provides an electronic device, including: a memory and a processor; the memory for storing a computer program; and the processor coupled to the memory for executing the computer program to perform steps in the housing information processing method.

[0006] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, enables the processor to implement the steps in the housing information processing method.

[0007] In this embodiment, the original feature information of at least one dimension of the property features extracted from the original property description information is polished, and the feature information of the missing property features in the original property description information is supplemented. Based on the feature information of at least one dimension of the property features and the feature information of the missing property features obtained by the polishing process, the standard property description information of the rental property can be updated, enriched and improved, which effectively improves the quality of the standard property description information of the rental property and helps to improve the success rate of property rental. Attached Figure Description

[0008] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0009] Figure 1 An exemplary application scenario diagram provided for an embodiment of this application;

[0010] Figure 2 A flowchart illustrating a housing information processing method provided in this application embodiment;

[0011] Figure 3 This is another exemplary application scenario diagram provided for embodiments of this application;

[0012] Figure 4 This is a schematic diagram of the structure of a housing information processing device provided in an embodiment of this application;

[0013] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0014] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0015] In the embodiments of this application, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the access relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone, where A and B can be singular or plural. In the textual description of this application, the character " / " generally indicates that the preceding and following associated objects have an "or" relationship. Furthermore, in the embodiments of this application, "first," "second," "third," etc., are only used to distinguish the content of different objects and have no other special meaning.

[0016] With the continuous development of the internet, online rentals have become mainstream. Landlords can post rental listings on rental platforms, and tenants can browse these listings to find suitable properties. In practice, the quality of the rental listings directly impacts the success rate of rentals; therefore, it is essential to improve the quality of rental listings.

[0017] Therefore, this application provides a method for processing housing information, an electronic device, and a storage medium. In this application, the original feature information of at least one dimension of housing features extracted from the original housing description information is refined, and the feature information of missing housing features in the original housing description information is supplemented. Based on the feature information of at least one dimension of housing features and the feature information of missing housing features obtained through the refinement process, updated, richer, and more complete standard housing description information of rental properties can be generated, which effectively improves the quality of the standard housing description information of rental properties and helps to increase the success rate of housing rental.

[0018] Figure 1 This is an exemplary application scenario diagram provided for an embodiment of this application. See also... Figure 1 In online rental scenarios, the server-side of the online platform provides online rental services. When landlords want to post rental information on the platform, they can request the server to enrich and improve the description information of the property. Specifically, landlords can input descriptions of the property's characteristics (referred to as the original property description) through voice or text input in the rental client. An example of the original property description is: "The apartment has 2 bedrooms, 1 living room, and 1 bathroom; the interior is fully furnished and ready to move in. The community has a beautiful environment, ample green space, and affordable property management fees. The surrounding facilities are complete, and the transportation is convenient for daily life." See also... Figure 1As shown in ①, the landlord triggers the rental client to send the original property description information of the property to be rented to the server. The server enriches and improves the original property description information of the property to be rented, and obtains the standard property description information of the property to be rented. See [link / reference]. Figure 1 As shown in ②, the server returns standard property description information to the landlord's rental client. Furthermore, in the process of enriching and improving the original property description information, the server can also introduce an LLM (Large Language Model). For example, the server inputs the original property description information of the property to be rented into the LLM to obtain the standard property description information output by the LLM. A standard property description might be: "A 2-bedroom, 1-living room, 1-bathroom apartment, beautifully decorated, well-ventilated, excellent natural light, fully furnished, ready to move in. Spacious living room, prime location, prime floor, spacious kitchen. Beautiful community environment, extensive green space, affordable property management fees, high-quality residents, excellent property management, low-density community. Complete surrounding facilities, convenient transportation, hospitals, schools, banks, and supermarkets nearby, convenient for daily life."

[0019] LLM refers to a class of large-scale natural language processing models with a large number of parameters to achieve better performance and generalization ability. LLMs typically use the Transformer architecture and learn the features and structure of natural language through pre-training on large-scale text data. This enables them to excel in various NLP (Natural Language Processing) tasks, such as text generation, sentiment analysis, question answering systems, and translation. The Transformer architecture is a model based on a multi-head attention mechanism, consisting of an Encoder and a Decoder.

[0020] In practical applications, landlords can view the standard property description information of properties available for rent on the rental client. They can also modify the standard property description information as needed to further improve the quality of the standard property description information, thereby increasing the success rate of property rentals.

[0021] In practice, after confirming that the standard property description of a rental property meets their needs, landlords publish the listing on a rental app, making the property available to more potential tenants. Tenants can then browse the landlord's listings on their devices using the rental app and, for properties they like, discuss rental details with the landlord. See also... Figure 1As shown in ③, tenants can also post their rental listings through the rental app to attract landlords' attention and receive standard listing descriptions, thus increasing the success rate of rentals.

[0022] It should be noted that, Figure 1 The application scenario shown is merely an exemplary scenario, and the embodiments of this application do not limit the application scenarios. The embodiments of this application do not... Figure 1 The included equipment is not limited, nor is it restricted. Figure 1 The positional relationships between the devices are defined.

[0023] In this application embodiment, the terminal device is, for example, a mobile phone, tablet computer, desktop computer, wearable smart device, smart home device, etc. The server is, for example, a single server, a distributed server cluster consisting of multiple servers, a cloud server, etc. The terminal device can interact with the server through a wired network or a wireless network. For example, the wired network can include coaxial cable, twisted pair, and fiber optic cable, etc., and the wireless network can be a 2G (2nd Generation) network, a 3G (3rd Generation) network, a 4G (4th Generation) network, a 5G (5th Generation) network, a Wireless Fidelity (WIFI) network, etc. This application does not limit the specific type or form of interaction, as long as it can realize the function of interaction between the terminal device and the server.

[0024] The technical solutions provided by the various embodiments of this application are described in detail below with reference to the accompanying drawings.

[0025] Figure 2 This is a flowchart illustrating a method for processing housing information provided in an embodiment of this application. The method can be executed by a housing information processing device, which may consist of software and / or hardware, and is generally configured in a client or server. In some optional embodiments, the housing information processing device may also be configured in an AI assistant module that provides AI (Artificial Intelligence) services.

[0026] See Figure 2 The method may include the following steps:

[0027] 201. Obtain the original property description information in text form for the properties to be rented.

[0028] Specifically, the original property description information can be understood as the complete description of the characteristics of the property to be rented. In practical applications, landlords can input the property description information in text format. Optionally, to facilitate landlords in easily completing the property description information and improve efficiency, voice input is also supported. Based on this, the landlord's voice data can be obtained and processed using speech-to-text (STT) to obtain the original property description information in text format.

[0029] For example, the landlord can trigger the rental client on the terminal device to display the property information creation page, and input the original property description information in text form on the property information creation page. Alternatively, the landlord can trigger the voice control on the property information creation page, and use the terminal device's microphone to collect the voice data representing the original property description information spoken by the landlord. The voice data can be processed into text to obtain the original property description information in text form.

[0030] Further optionally, in order to accurately obtain the original property description information in text form of the property to be rented, one possible implementation method is to obtain the landlord's voice data, and then perform voice noise reduction processing, voice-to-text processing and error correction processing on the voice data in sequence to obtain the original property description information in text form of the property to be rented.

[0031] Specifically, noise data in the landlord's voice data can be removed through voice noise reduction processing. The text information obtained by voice-to-text processing of the noise-reduced voice data is then corrected. The text information after error correction is used as the original property description information in text form for the rental property, thereby obtaining more accurate original property description information in text form for the rental property.

[0032] 202. Extract features from the original property description information to obtain the original feature information of at least one dimension of property features in the original property description information.

[0033] 203. Refine the original feature information of at least one dimension of housing features to obtain feature information of at least one dimension of housing features.

[0034] Specifically, the characteristics of a property across multiple dimensions include the following: transportation conditions, property security, internal facilities, community environment, surrounding facilities, property renovation level, mortgage payment method, unit type, or property management.

[0035] In practical applications, one or more dimensions of original property features can be extracted from the original property description information. These original features can be understood as the features before any refinement or polishing. For example, the original features of at least one dimension of property features include: apartment layout, level of renovation, internal amenities, community environment, property management, and other features. Specifically, the original features of the apartment layout might be: 2 bedrooms, 1 living room, 1 bathroom; the original features of the renovation level might be: standard renovation; the original features of the community environment might be: beautiful environment, large green area; and the original features of property management might be: affordable property management fees, excellent property management, etc.

[0036] For the original feature information of at least one dimension of property features extracted from the original property listing information, the original feature information of at least one dimension of property features is refined to obtain the feature information of at least one dimension of property features. It can be understood that the feature information of property features is obtained by refining the original feature information of property features. The refinement process can enrich and improve the property listing information and enhance its quality.

[0037] 204. Based on the multiple dimensions of property features required by the standard property description information and at least one dimension of property features in the original property description information, determine the missing property features in the original property description information and obtain the feature information of the missing property features.

[0038] Specifically, the number of property features required for standard property description information can be flexibly set as needed; the more features, the richer the standard property description information. For example, the multiple dimensions of property features required for standard property description information may include transportation conditions, property security, internal facilities, community environment, surrounding facilities, property renovation level, mortgage payment method, unit type, or property management.

[0039] In this embodiment, to enrich and improve the property description information and enhance its quality, it is possible to determine whether the original property description information is missing some property features based on the multiple dimensions of property features required by the standard property description information. It is understood that missing property features refer to those that appear in the multiple dimensions of property features required by the standard property description information but are not present in at least one dimension of the original property description information. By comparing the multiple dimensions of property features required by the standard property description information with at least one dimension of property features in the original property description information, the missing property features in the original property description information can be accurately determined.

[0040] In practical applications, after identifying the missing property features in the original property description information, text mining can be performed on the massive amount of standard property description information of rented properties to extract the feature information of the missing property features. For example, the missing property features might be the internal and surrounding amenities. The extracted features of the internal amenities include: fully equipped with appliances such as a refrigerator, washing machine, air conditioner, and robot vacuum cleaner; the extracted features of the surrounding amenities include: nearby hospitals, schools, banks, and supermarkets, facilitating daily life.

[0041] Further, optionally, in order to improve the authenticity and reliability of the property description information of the properties to be rented, similar properties that are similar to the properties to be rented can be identified; and feature information of the missing property features can be extracted from the standard property description information of the similar properties.

[0042] In practical applications, when determining similar properties to the property to be rented, the similarity between the original property description information of the property to be rented and the standard property description information of each other property can be determined. The other property with the highest similarity can be selected as the similar property to the property to be rented. Alternatively, among multiple other properties with a similarity greater than a preset similarity threshold, one other property can be selected as the similar property to the property to be rented.

[0043] Optionally, to accurately identify similar properties to the property to be rented, the similarity between the original property description information of the property to be rented and the standard property description information of each other property can be determined; multiple candidate similar properties with the highest similarity ranking can be selected from the other properties; the comment data, positive review data, and favorite data of the multiple candidate similar properties can be input into a customer satisfaction model to evaluate the customer satisfaction of the multiple candidate similar properties through the customer satisfaction model; and the candidate similar property with the highest customer satisfaction can be selected from the multiple candidate similar properties to determine the similar property to the property to be rented.

[0044] In this embodiment, the data on comments for the property listing includes, but is not limited to: the number of comments, the number of users who left comments, the content of the comments, and the number of valid replies. The data on positive reviews for the property listing includes, but is not limited to: the number of positive reviews, the number of users who gave positive reviews, and the content of the positive reviews. The data on favorites for the property listing includes, but is not limited to: the number of times the property listing has been favorited, the number of users who have favorited the property listing, etc. Customer satisfaction with the property listing is accurately assessed from multiple dimensions of data, including comment data, positive review data, and favorites data.

[0045] Alternatively, a customer satisfaction model can be trained to assess the customer satisfaction of the property listings more accurately. Specifically, a large amount of sample property listings' comment data, positive review data, and favorites data, along with their labeled customer satisfaction levels, are used as training data to train a neural network model, resulting in a customer satisfaction model capable of evaluating property customer satisfaction. During model training, the sample property listings' comment data, positive review data, and favorites data are input into the neural network model to obtain the predicted customer satisfaction level output by the model. The model parameters of the neural network model are adjusted based on the loss value between the predicted and labeled customer satisfaction levels. This process is iteratively repeated until the model parameters of the trained neural network model converge. The converged neural network model is then used as the customer satisfaction model.

[0046] In this embodiment, the number of candidate similar properties ranked high in similarity is set as needed, for example, the top 3 candidate similar properties. After selecting multiple candidate similar properties, a customer satisfaction model is used to evaluate the customer satisfaction of these properties. From these multiple candidate similar properties, the one with the highest customer satisfaction is selected as the similar property to the property to be rented. It is understood that properties with higher customer satisfaction are more likely to attract tenants' interest in their descriptions, effectively increasing the success rate of property rentals.

[0047] 205. Generate standard property description information for properties to be rented based on the feature information of at least one dimension of property features and the feature information of missing property features.

[0048] In some optional embodiments, steps 201 to 205 are performed by the large language model to obtain richer and more complete standard property description information for rental properties by utilizing the capabilities of the large language model.

[0049] The technical solution provided in this application not only refines the original feature information of at least one dimension of property features extracted from the original property description information, but also completes the feature information of missing property features in the original property description information. Based on the feature information of at least one dimension of property features and the feature information of missing property features obtained through the refinement process, it is possible to generate updated, richer and more complete standard property description information for properties to be rented, which effectively improves the quality of the standard property description information for properties to be rented and is conducive to improving the success rate of property rental.

[0050] In practical applications, the standard property description information of a property to be rented can be used as the property information. In some optional embodiments, after generating the standard property description information, it is also possible to: generate title information for the property to be rented based on the standard property description information; and push the property information, including the standard property description information and the title information, to the landlord of the property to be rented.

[0051] Understandably, generating title information for rental listings and enriching their details can effectively attract tenants' attention and increase the success rate of rentals.

[0052] Alternatively, a massive amount of text content and its labeled titles can be used to train the model to obtain a title generation model with title generation capabilities. The title generation model includes, but is not limited to, the Transformer model and the seq2seq (sequence to sequence) model.

[0053] In practical applications, the standard property description information for rental properties can be input into the title generation model to obtain the title information for the rental properties. Optionally, to further improve the quality of the title information, the feature information of each property characteristic in the standard property description information can be input into the title generation model to obtain the title information corresponding to each property characteristic; the title information corresponding to multiple property characteristics can then be combined to obtain the title information for the rental properties. The title information generated in this way can reflect the advantages of the rental properties from multiple dimensions.

[0054] In practical applications, landlords can view and directly publish rental listings through a rental app. Optionally, to meet landlords' personalized needs, they can also modify the rental listing information. Therefore, in some optional embodiments, after pushing the rental listing information to landlords, the app can respond to landlord-initiated modification requests and modify the listing information. For example, it can modify the standard listing description and / or title information to continuously improve the rental listing information.

[0055] In some optional embodiments, to improve the success rate of property rentals, after pushing the rental information of properties to landlords, the system can further: extract profile information of properties to be rented from the rental information through a recommendation system; select target rental information that matches the profile information of the properties to be rented from multiple rental listings posted by multiple tenants through the recommendation system; push the target rental information to the landlords; and, in response to the push operation triggered by the landlords, push the rental information of the properties to the tenants who posted the target rental information.

[0056] In this embodiment, the recommendation technologies used by the recommendation system include, but are not limited to: collaborative filtering recommendation, association rule-based recommendation, utility-based recommendation, and knowledge-based recommendation.

[0057] In this embodiment, the target rental listing information refers to the rental listing information selected by the recommendation system from multiple rental listing listings that matches the profile information of the rental property. The recommendation system first recommends target rental listing information that matches the profile information of the rental property to landlords, and then the landlords push the rental property information to tenants who posted the target rental listing information. This can greatly improve the success rate of property rentals.

[0058] Figure 3 Another exemplary application scenario diagram provided for embodiments of this application. See also Figure 3 Landlords interact with the app (e.g., a rental app) by inputting information via voice or text, including raw descriptions of the properties for rent. This information is then sent to the app server via the SDK (Software Development Kit). The app server calls the corpus API (Application Programming Interface) to send it to the algorithm system. The algorithm system uses a large language model to generate rental information based on the corpus. The app server then forwards the rental information from the algorithm system to the app application via the data refinement API. The algorithm system then calls the recommendation system to determine suitable rental listings to recommend to landlords based on the rental property profiles. The app server then forwards these recommended listings to the app application via the recommendation API. Landlords can modify and publish information about properties available for rent. They can also push information about their properties to tenants who have posted job-seeking listings to attract their attention and increase the success rate of renting out the properties.

[0059] Figure 4 This is a schematic diagram of a housing information processing device provided in an embodiment of this application. See also... Figure 4 The device may include:

[0060] The acquisition module 41 is used to acquire the original property description information in text form of the property to be rented;

[0061] The feature extraction module 42 is used to extract features from the original property description information to obtain the original feature information of at least one dimension of property features in the original property description information.

[0062] The polishing module 43 is used to polish the original feature information of the housing feature in at least one dimension to obtain the feature information of the housing feature in at least one dimension.

[0063] The missing feature processing module 44 is used to determine the missing property features in the original property description information based on the multiple dimensions of property features required by the standard property description information and at least one dimension of property features in the original property description information, and to obtain the feature information of the missing property features.

[0064] The generation module 45 is used to generate standard property description information for properties to be rented out based on the feature information of at least one dimension of property features and the feature information of missing property features.

[0065] Further optionally, when the missing property feature processing module 44 obtains the feature information of the missing property feature, it is specifically used to: identify similar properties that are similar to the property to be rented; and extract the feature information of the missing property feature from the standard property description information of the similar properties.

[0066] Optionally, when the missing information processing module 44 identifies similar properties to the property to be rented, it is specifically used to: determine the similarity between the original property description information of the property to be rented and the standard property description information of each other property; select multiple candidate similar properties with the highest similarity ranking from each other property; input the comment data, positive review data, and favorite data of the multiple candidate similar properties into the customer satisfaction model to evaluate the customer satisfaction of the multiple candidate similar properties through the customer satisfaction model; and select the candidate similar property with the highest customer satisfaction from the multiple candidate similar properties as the similar property to the property to be rented.

[0067] Further optionally, the acquisition module 41 is specifically used to: acquire the landlord's voice data; sequentially perform voice noise reduction processing, voice-to-text processing and error correction processing on the voice data to obtain the original property description information in text form of the property to be rented.

[0068] Optionally, the generation module 45 is further configured to: generate title information of the rental property based on the standard property description information of the rental property; the above device also includes a push module and a modification module, the push module being configured to push the rental property information of the rental property to the landlord of the rental property, the rental property information including the standard property description information and title information; the modification module being configured to modify the rental property information of the rental property in response to the modification operation initiated by the landlord.

[0069] Optionally, when generating title information for a rental property based on the standard property description information, the generation module 45 is specifically used to: input the feature information of each property feature in the standard property description information into the title generation model to obtain the title information corresponding to each property feature; and combine the title information corresponding to multiple property features to obtain the title information for the rental property.

[0070] Optionally, the push module is also used to: extract profile information of rental properties from the rental property information through the recommendation system; select target rental property information that matches the profile information of the rental property from multiple rental property information posted by multiple tenants through the recommendation system; push the target rental property information to the landlord; and push the rental property information to the tenant who posted the target rental property information in response to the push operation triggered by the landlord.

[0071] Further optional property features across multiple dimensions include: transportation access, property security, internal amenities, community environment, surrounding amenities, property renovation status, mortgage payment method, unit type, or property management.

[0072] Alternatively, the above-mentioned device can be applied to an AI assistant module that provides AI services.

[0073] Figure 4 The device shown can perform Figure 2 The implementation principle and technical effects of the method shown in the embodiments will not be elaborated further. Regarding the above embodiments... Figure 4 The specific ways in which each module and unit of the device performs operations have been described in detail in the embodiments of the method, and will not be elaborated here.

[0074] It should be noted that the execution subject of each step of the method provided in the above embodiments can be the same device, or the method can be executed by different devices. For example, the execution subject of steps 201 to 205 can be device A; or the execution subject of steps 201 and 202 can be device A, and the execution subject of steps 203 to 205 can be device B; and so on.

[0075] Furthermore, in some of the processes described in the above embodiments and accompanying drawings, multiple operations appear in a specific order. However, it should be clearly understood that these operations may not be executed in the order they appear herein, or they may be executed in parallel. The operation numbers, such as 201, 202, etc., are merely used to distinguish different operations and do not represent any execution order. Additionally, these processes may include more or fewer operations, and these operations may be executed sequentially or in parallel. It should be noted that the descriptions such as "first" and "second" in this document are used to distinguish different messages, devices, modules, etc., and do not represent a sequential order, nor do they limit "first" and "second" to different types.

[0076] 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. Furthermore, the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation portals are provided for users to choose to authorize or refuse.

[0077] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 5 As shown, the electronic device includes: a memory 51 and a processor 52;

[0078] Memory 51 is used to store computer programs and can be configured to store various other data to support operation on the computing platform. Examples of this data include instructions for any application or method operating on the computing platform, contact data, phone book data, messages, pictures, videos, etc.

[0079] The memory 51 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 storage, flash memory, magnetic disk, or optical disk.

[0080] The processor 52, coupled to the memory 51, is used to execute the computer program in the memory 51 for: performing the steps in the housing information processing method.

[0081] Further optional, such as Figure 5 As shown, the electronic device also includes other components such as a communication component 53, a display 54, a power supply component 55, and an audio component 56. Figure 5 The diagram only shows some components and does not mean that the electronic device includes only these components. Figure 5 The components shown. Additionally... Figure 5 The components within the dashed box are optional, not mandatory, and their specific requirements depend on the product form of the electronic device. The electronic device in this embodiment can be a desktop computer, laptop computer, smartphone, or IoT (Internet of Things) device, or a server-side device such as a conventional server, cloud server, or server array. If the electronic device in this embodiment is a desktop computer, laptop computer, or smartphone, it may include... Figure 5 The components within the dashed box; if the electronic device in this embodiment is implemented as a conventional server, cloud server, or server array, etc., it may be omitted. Figure 5 The component within the dashed box.

[0082] For a detailed description of the implementation process of each action by the processor, please refer to the relevant descriptions in the foregoing method embodiments or device embodiments, which will not be repeated here.

[0083] Accordingly, embodiments of this application also provide a computer-readable storage medium storing a computer program, which, when executed, can implement the steps that can be performed by an electronic device in the above method embodiments.

[0084] Accordingly, this application also provides a computer program product, including a computer program / instructions, which, when executed by a processor, enables the processor to perform the steps that can be executed by an electronic device in the above method embodiments.

[0085] The aforementioned communication components are configured to facilitate wired or wireless communication between the device containing the communication components and other devices. The device containing the communication components can access wireless networks based on communication standards, such as WiFi (Wireless Fidelity), 2G (2nd Generation), 3G (3rd Generation), 4G (4th Generation) / LTE (long Term Evolution), 5G (5th Generation), or combinations thereof. In one exemplary embodiment, the communication components receive broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, the communication components also include a Near Field Communication (NFC) module to facilitate short-range communication. For example, the NFC module may be based on Radio Frequency Identification (RFID), Infrared Data Association (IrDA), Ultra Wide Band (UWB), Bluetooth, and other technologies.

[0086] The aforementioned display includes a screen, which may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a Touch Panel, the screen can be implemented as a touchscreen to receive input signals from the user. The Touch Panel includes one or more touch sensors to sense touches, swipes, and gestures on the Touch Panel. The touch sensors can sense not only the boundaries of touch or swipe actions but also the duration and pressure associated with the touch or swipe operation.

[0087] The aforementioned power supply components provide power to various components within the device in which they reside. These power supply components may include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power to the device in which they reside.

[0088] The aforementioned audio component can be configured to output and / or input audio signals. For example, the audio component includes a microphone (MIC) configured to receive external audio signals when the device containing the audio component is in an operating mode, such as call mode, recording mode, or voice recognition mode. The received audio signals can be further stored in memory or transmitted via a communication component. In some embodiments, the audio component also includes a speaker for outputting audio signals.

[0089] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0090] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0091] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0092] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0093] In a typical configuration, a computing device includes one or more processors (Central Processing Unit, CPU), input / output interfaces, network interfaces, and memory.

[0094] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0095] Computer-readable media, including both permanent and non-permanent, removable and non-removable media, can store information using any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change RAM (PRAM), static random-access memory (SRAM), dynamic random-access memory (DRAM), other types of random-access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device. As defined in this article, computer-readable media do not include transient media, such as modulated data signals and carrier waves.

[0096] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0097] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for processing housing information, characterized in that, include: Obtain the original property description information in text form for the properties available for rent; Feature extraction is performed on the original property description information to obtain the original feature information of at least one dimension of property features in the original property description information; The original feature information of the property features in at least one dimension is refined to obtain the feature information of the property features in at least one dimension. Based on the multiple dimensions of property features required by the standard property description information and at least one dimension of property features in the original property description information, determine the missing property features in the original property description information; Determine the similarity between the original property description information of the rental property and the standard property description information of each other property; select multiple candidate similar properties with the highest similarity ranking from each other property; input the comment data, positive review data and favorite data of the multiple candidate similar properties into the customer satisfaction model, so as to evaluate the customer satisfaction of the multiple candidate similar properties through the customer satisfaction model; From multiple candidate similar properties, the candidate similar property with the highest customer satisfaction is selected as the similar property to the property to be rented. Extract the missing property features from the standard property description information of the similar properties; Based on the feature information of the property features in at least one dimension and the feature information of the missing property features, standard property description information for the property to be rented is generated.

2. The method according to claim 1, characterized in that, Obtain the original property description information in text form for the properties to be rented, including: Obtain the landlord's voice data; The voice data is sequentially processed by voice noise reduction, voice-to-text conversion, and error correction to obtain the original property description information in text form for the rental property.

3. The method according to claim 1, characterized in that, After generating the standard property description information for the rental property, the process also includes: Based on the standard property description information of the property to be rented, generate the title information of the property to be rented; The property information for the properties to be rented out is pushed to the landlords of the properties to be rented out. The property information includes the standard property description information and the title information. In response to the modification operation initiated by the landlord, the property information of the rental property is modified.

4. The method according to claim 3, characterized in that, Based on the standard property description information of the property to be rented, generate the title information of the property to be rented, including: Input the feature information of each property feature in the standard property description information of the property to be rented into the title generation model to obtain the title information corresponding to each property feature; The title information corresponding to multiple property features is combined to obtain the title information of the properties to be rented.

5. The method according to claim 3, characterized in that, After pushing the rental property information to the landlord of the rental property, the process also includes: The system extracts profile information of the properties for rent from the property information of the properties for rent. The recommendation system selects target rental listings that match the profile information of the rental listings from multiple rental listings posted by multiple tenants. The target rental listing information is pushed to the landlord. In response to the push operation triggered by the landlord, the rental information of the property to be rented is pushed to the tenant who posted the target rental information.

6. The method according to any one of claims 1 to 5, characterized in that, The characteristics of properties across multiple dimensions include the following: Transportation conditions, property safety, internal facilities, community environment, surrounding facilities, property renovation level, mortgage payment method, unit type or property management.

7. The method according to any one of claims 1 to 5, characterized in that, AI assistant modules used to provide AI services.

8. An electronic device, characterized in that, include: Memory and processor; The memory is used to store computer programs; The processor is coupled to the memory for executing the computer program to perform the steps of the method according to any one of claims 1-7.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it causes the processor to perform the steps of the method according to any one of claims 1-7.

Images