Information search method and device, computing equipment, storage medium and program product

Abstract

The embodiment of the invention provides an information searching method and device, computing equipment, a storage medium and a program product. The method comprises the steps of sending intelligent service prompt information of a target renting type to a user side for display by the user side, sending at least one piece of demand inquiry information to the user side based on session connection with the user side in response to an intelligent service request sent by the user side, and obtaining at least one piece of reply information fed back by the user side, determining a plurality of renting requirements based on the at least one reply message by utilizing an artificial intelligence model, selecting at least one renting requirement with the search weight greater than or equal to a target weight threshold value to search whether at least one first renting object meeting the requirement exists or not, if not, increasing the target weight threshold value and then continuing to execute the search operation, and if yes, executing the search operation; and feeding back the related information of the at least one first renting object to the user side for the user side to display. According to the technical scheme provided by the embodiment of the invention, the search accuracy and efficiency of the rented object can be improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of computer technology, and in particular to an information search method, apparatus, computing device, storage medium, and program product. Background Art

[0002] With the development of Internet technology, the demand for using the Internet to find various types of rental objects (such as houses, venues, etc.) is constantly increasing.

[0003] Currently, the most common approach is for tenants to post their rental information on internet platforms, waiting for landlords to discover and contact them. Alternatively, tenants can search independently for tenants that meet their needs on e-commerce platforms offering rental properties. Both of these approaches suffer from inaccurate search results and low efficiency, and are in urgent need of improvement. Summary of the Invention

[0004] The embodiments of the present application provide an information search method, apparatus, computing device, storage medium, and program product to solve the problem in the prior art of inaccurate and inefficient search results when searching for rental objects through an e-commerce platform.

[0005] The present application provides an information search method, which is applied to a server and includes:

[0006] Sending intelligent service prompt information for the target rental type to the user terminal so that the user terminal displays the intelligent service prompt information;

[0007] In response to an intelligent service request sent by the user terminal, establishing a session connection with the user terminal; the intelligent service request is generated in response to a triggering operation of the intelligent service prompt information;

[0008] Based on the session connection, sending at least one demand inquiry message for the target lease type to the user terminal, and obtaining at least one reply message fed back by the user terminal for the at least one demand inquiry message;

[0009] Determining, using an artificial intelligence model, a plurality of lease requirements for the target lease type based on the at least one reply message;

[0010] Determining a search weight corresponding to each of the plurality of rental demands;

[0011] Determine a target weight threshold and perform the following search operation; the search operation includes: based on at least one rental demand whose search weight is greater than or equal to the target weight threshold, find whether there is at least one first rental object that meets the at least one rental demand;

[0012] If not, increase the target weight threshold and re-execute the search operation;

[0013] If so, then based on the session connection, the relevant information of the at least one first leased object is fed back to the user terminal so that the user terminal displays the relevant information of the at least one first leased object.

[0014] The present application also provides an information search method, which is applied to a user terminal and includes:

[0015] receiving intelligent service prompt information for the target rental type sent by the server, and displaying the intelligent service prompt information;

[0016] In response to a triggering operation for the intelligent service prompt information, sending an intelligent service request to the server so that the server establishes a session connection with the user terminal;

[0017] Based on the session connection, receiving at least one demand inquiry information for the target lease type sent by the server, and displaying the at least one demand inquiry information;

[0018] Obtaining at least one reply message for the at least one demand inquiry message;

[0019] Based on the session connection, the at least one reply message is sent to the server, so that the server uses an artificial intelligence model to determine multiple rental requirements for the target rental type based on the at least one reply message; determine a search weight corresponding to each of the multiple rental requirements; determine a target weight threshold and perform the following search operation; the search operation includes: based on at least one rental requirement whose search weight is greater than or equal to the target weight threshold, searching whether there is at least one first rental object that meets the at least one rental requirement; if not, increasing the target weight threshold and re-performing the search operation; if so, feeding back relevant information of the at least one first rental object to the user terminal based on the session connection;

[0020] Based on the session connection, relevant information of the at least one first leased object is acquired and displayed.

[0021] The embodiment of the present application further provides an information search device, which is configured on a server side and includes:

[0022] A first sending module is configured to send intelligent service prompt information for a target rental type to a user terminal so that the user terminal displays the intelligent service prompt information;

[0023] a session establishing module, configured to establish a session connection with the user terminal in response to an intelligent service request sent by the user terminal; the intelligent service request is generated in response to a triggering operation of the intelligent service prompt information;

[0024] The first sending module is further configured to send at least one demand inquiry information for the target lease type to the user terminal based on the session connection;

[0025] A first receiving module is configured to obtain at least one reply message fed back by the user terminal in response to the at least one demand inquiry message;

[0026] a demand determination module, configured to determine, by using an artificial intelligence model and based on the at least one reply message, a plurality of rental demands for the target rental type;

[0027] A weight determination module, configured to determine a search weight corresponding to each of the plurality of rental demands;

[0028] The object search module is configured to determine a target weight threshold and perform the following search operation; the search operation includes: based on at least one rental demand having a search weight greater than or equal to the target weight threshold, searching for at least one first rental object that meets the at least one rental demand; if not, increasing the target weight threshold and re-performing the search operation;

[0029] The first sending module is further configured to, if present, feed back relevant information of the at least one first leased object to the user terminal based on the session connection, so that the user terminal displays relevant information of the at least one first leased object.

[0030] The present application also provides an information search device, which is configured at a user terminal and includes:

[0031] The second receiving module is used to receive the intelligent service prompt information for the target rental type sent by the server;

[0032] A display module, configured to display the intelligent service prompt information;

[0033] A second sending module is configured to send an intelligent service request to the server in response to a triggering operation on the intelligent service prompt information, so that the server establishes a session connection with the user terminal;

[0034] The second receiving module is further configured to receive, based on the session connection, at least one demand inquiry information for the target rental type sent by the server;

[0035] The display module is further configured to display the at least one demand inquiry information;

[0036] An information acquisition module, configured to acquire at least one reply message for the at least one demand inquiry message;

[0037] The second sending module is further configured to send the at least one reply message to the server based on the session connection, so that the server can use the artificial intelligence model to determine multiple rental requirements for the target rental type based on the at least one reply message; determine a search weight corresponding to each of the multiple rental requirements; determine a target weight threshold and perform the following search operation; the search operation includes: based on at least one rental requirement having a search weight greater than or equal to the target weight threshold, searching for at least one first rental object that meets the at least one rental requirement; if not, increasing the target weight threshold and re-performing the search operation; if so, feeding back relevant information of the at least one first rental object to the user based on the session connection;

[0038] The second receiving module is further configured to obtain relevant information of the at least one first leased object based on the session connection;

[0039] The display module is further configured to display relevant information of the at least one first rental object.

[0040] An embodiment of the present application also provides a computing device, including a processing component and a storage component; the storage component stores a computer program; the computer program is used to be called and executed by the processing component to implement the above-mentioned information search method.

[0041] An embodiment of the present application further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processing component, the above-mentioned information search method is implemented.

[0042] An embodiment of the present application further provides a computer program product, including a computer program or instructions, which implement the above-mentioned information search method when executed by a processing component.

[0043] The embodiment of the present application sends an intelligent service prompt message for a target rental type to a user terminal for display by the user terminal. In response to an intelligent service request sent by the user terminal in response to a trigger operation of the intelligent service prompt message, a session connection is established with the user terminal. Based on the session connection, at least one demand inquiry message is sent to the user terminal, and at least one reply message is fed back by the user terminal. Based on the at least one reply message, an artificial intelligence model is used to determine multiple rental requirements. At least one rental requirement with a search weight greater than or equal to a target weight threshold is selected to determine whether there is at least one first rental object that meets the requirement. If not, the target weight threshold is increased and the search operation is continued. If so, relevant information about the at least one first rental object is fed back to the user terminal for display by the user terminal. The embodiment of the present application uses an artificial intelligence model to communicate with the corresponding user of the user terminal to identify the user's rental requirements. This can accurately and comprehensively determine the rental requirements and then accurately search for the first rental object that meets the requirements for the user, thereby improving the accuracy of the search results. Moreover, the entire search process only requires the user to answer the demand inquiry message, eliminating the need to spend a lot of time waiting or searching for rental objects, thereby improving search efficiency. In addition, when searching for the first rental object, this embodiment adopts a sampling weight gradient search strategy, that is, by continuously increasing the target weight value, the number of rental demands used in the search is reduced, thereby ensuring that the first rental object is retrieved based on as many rental demands as possible, further improving the accuracy of the first rental object.

[0044] These and other aspects of the present application will become more readily apparent from the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0046] Figure 1 A system architecture diagram for information search provided by an exemplary embodiment of the present application is shown.

[0047] Figure 2 A flowchart of an embodiment of the information search method provided by the present application is shown.

[0048] Figure 3 A schematic diagram of the first interface displayed by the user terminal provided by this application is shown.

[0049] Figure 4 A schematic diagram of the second interface displayed by the user terminal provided by this application is shown.

[0050] Figure 5 A flowchart of another embodiment of the information search method provided by the present application is shown.

[0051] Figure 6 A schematic diagram of scene interaction in a practical application provided by an exemplary embodiment of the present application is shown.

[0052] Figure 7 A structural diagram of an embodiment of an information search device provided by the present application is shown.

[0053] Figure 8 A structural diagram of another embodiment of the information search device provided by the present application is shown.

[0054] Figure 9 A schematic diagram of the structure of a computing device for information search provided by the present application is shown. DETAILED DESCRIPTION

[0055] To make the purpose, technical solutions, and advantages of this application more clear, the technical solutions of this application will be clearly and completely described below in conjunction with the specific embodiments of this application and the corresponding drawings. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0056] It should be noted that the technical solutions of the embodiments of the present application are applicable to a virtual network environment. The users described are generally referred to as "virtual users." Real users can register a user account on the server through a registration method to obtain a user identity in the network environment. The same user account can log in to the server through different types of client terminals, allowing the server to identify the same user. For example, the user of the embodiments of the present application can be a user who has a corresponding rental type of the rental target, that is, a tenant.

[0057] Interactions between the server and the user can be implemented based on user accounts. Data sent or received by the server to the user is also based on user accounts. The user corresponding to the user account actually receives or sends data to the server. Furthermore, users can communicate with each other through user accounts. The term "user" can refer to an individual or an organization, such as a business, and this application does not impose specific restrictions on this.

[0058] It should be noted that, in the case of user information involved in the embodiments of the present application, 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, stored data, displayed data, etc.) involved in the embodiments of the present application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data need to comply with the relevant laws, regulations and standards of the relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse. In addition, the various models involved in this application (including but not limited to language models or large models) are in compliance with relevant laws and standards.

[0059] In addition, it should be noted that when the embodiments of the present application involve user interaction operations or triggering operations, the user interaction operations or triggering operations involved in the embodiments of the present application include but are not limited to: touch operations, gesture operations, voice operations, head movement operations, eye movement operations and other interactive operations in various ways; among which, touch operations include but are not limited to: click operations, double-click operations, long press operations, sliding operations, pinch operations or mouse hover operations, etc. Sliding operations include but are not limited to: straight sliding, curved sliding, etc.

[0060] With the development of Internet technology, the use of the Internet to find various types of rental objects (such as houses, venues, etc.) has gradually become popular. Compared with offline intermediaries recommending suitable rental objects to tenants based on their needs, finding rental objects through the Internet can not only reduce the cost of finding rental objects, but also expand the scope of finding rental objects.

[0061] Currently, a common method is for tenants to post rental information on internet platforms and wait for landlords to discover and contact them. However, this method puts tenants in a passive waiting state, resulting in limited options, long waiting times, and low efficiency. Another method is for e-commerce platforms to allow landlords to upload their rental properties. As a result, e-commerce platforms have a large supply of rental properties, and tenants can enter filtering criteria on the e-commerce platform to search for rental properties that meet their needs. However, if the filtering criteria entered by the tenant is inaccurate or incomplete, it will seriously affect the accuracy of the search results. The search process also requires the tenant to spend a lot of time screening rental properties, resulting in low search efficiency.

[0062] To address the problem of inaccurate and inefficient search results when searching for rental objects through e-commerce platforms in the prior art, an embodiment of the present application provides a solution. The basic idea is to send an intelligent service prompt message for the target rental type to a user terminal for display by the user terminal. In response to an intelligent service request sent by the user terminal in response to a trigger operation of the intelligent service prompt message, a session connection is established with the user terminal. Based on the session connection, at least one demand inquiry message is sent to the user terminal, and at least one reply message is fed back by the user terminal. An artificial intelligence model is used to determine multiple rental requirements based on the at least one reply message. At least one rental requirement with a search weight greater than or equal to a target weight threshold is selected to determine whether there is at least one first rental object that meets the requirement. If no first rental object exists, the target weight threshold is increased and the search operation is continued. If so, relevant information about the at least one first rental object is fed back to the user terminal for display by the user terminal. The embodiment of the present application uses an artificial intelligence model to communicate with the corresponding user of the user terminal to identify the user's rental requirements. This can accurately and comprehensively determine the rental requirements, and then accurately search for the first rental object that meets the requirements for the user, thereby improving the accuracy of the search results. The entire search process only requires the user to answer the request query information, eliminating the need to wait or search for rental objects, thereby improving search efficiency. Furthermore, this embodiment employs a weighted gradient search strategy when searching for the first rental object. This strategy reduces the number of rental requirements used in the search by continuously increasing the target weight value, thereby ensuring that the first rental object is retrieved based on as many rental requirements as possible, further improving the accuracy of the first rental object.

[0063] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without making creative efforts are within the scope of protection of this application.

[0064] Figure 1 A diagram illustrating a system architecture for information search using the technical solution of an embodiment of the present application is provided. For example, the system may be an e-commerce service system. The system architecture may include a user terminal 101 and a server terminal 102. (Alternatively, it may include a server terminal and multiple user terminals; or it may include a server terminal, a first user terminal, and a second user terminal, etc.)

[0065] The client 101 and the server 102 can be connected via a network. The network provides a medium for the communication link between the client 101 and the server 102. The network can include various connection types, such as wired, wireless, or fiber optic cables. The client 101 can interact with the server 102 via the network to receive or send messages.

[0066] The user terminal 101 may be a browser, an APP (Application), or a web application such as an H5 (HyperText Markup Language 5, version 5 of Hypertext Markup Language) application, or a light application (also known as a mini-program, a lightweight application) or a cloud application. The user terminal 101 may be deployed in an electronic device and may rely on the device to run or on certain apps in the device to run. For example, the electronic device may have a display screen and support information browsing, such as a personal mobile terminal such as a mobile phone, a tablet computer, a personal computer, a desktop computer, a smart speaker, a smart watch, etc. For ease of understanding, Figure 1 The user end is mainly represented by the image of a device. Various other types of applications can usually be configured in electronic devices, such as human-computer dialogue applications, model training applications, text processing applications, web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc. Electronic devices can refer to devices used by users, which have the functions of computing, Internet access, communication, etc. required by users, such as mobile phones, tablet computers, personal computers, wearable devices, etc. Electronic devices can usually include at least one processing component and at least one storage component. Electronic devices may also include basic configurations such as network card chips, IO (input / output) buses, audio and video components, which are not limited in this application. Optionally, according to the implementation form of the electronic device, some peripheral devices may also be included, such as keyboards, mice, input pens, printers, etc., which are not limited in this application.

[0067] The server 102 may include servers that provide various services, such as a server for background training that provides support for the model used on the user terminal 101, or a server that processes interactive information sent by the user terminal.

[0068] It should be noted that the server 102 can be implemented as a distributed server cluster consisting of multiple servers, or as a single server. The server can also be a server of a distributed system, or a server combined with a blockchain. The server can also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms, or an intelligent cloud computing server or intelligent cloud host with artificial intelligence technology.

[0069] It should be noted that the information search method provided in the embodiment of the present application is generally performed by the user terminal 101 and the server terminal 102 together. It should be understood that Figure 1 The number of the client terminals 101 and the server terminals 102 is merely illustrative and any number of the client terminals and the server terminals may be provided as required.

[0070] The following describes in detail the implementation details of the technical solutions of the embodiments of the present application.

[0071] Figure 2 This is a flow chart of an embodiment of an information search method provided by this application. The technical solution of this embodiment can be executed by the server. Figure 2 As shown, the method may include the following steps:

[0072] S201: Sending intelligent service prompt information for a target rental type to a user terminal so that the user terminal displays the intelligent service prompt information.

[0073] The target rental type may be a type of rental object that can be provided by the e-commerce platform, for example, it may be an item such as a house, a venue, or a vehicle.

[0074] The intelligent service prompt information can be prompt information that prompts the corresponding user of the user end (i.e., the user who logs into the e-commerce platform to rent) that the platform can provide intelligent search services for them. It can include but is not limited to prompt information such as touch components, text, and icons that provide intelligent search services. For example, if the target rental type in this embodiment is a house, the intelligent service prompt information at this time can be a rental entry button that provides an intelligent search for housing. In this embodiment, the intelligent service prompt information corresponding to different target rental types can be the same or different. For example, the touch components can be the same, but the text and icons can be different.

[0075] Optionally, the server may send the intelligent service prompt information to the user end when it detects that the corresponding user of the user end has a rental object search demand (such as performing a rental object search operation, etc.) or requests to enter a certain interface (such as an object list interface and an object search interface, etc.). At this time, the user end will add the received release prompt information to the display interface corresponding to the rental object search demand or the interface to be entered. It can also be that when it is detected that the user end requests to enter the official account of the e-commerce platform, the intelligent service prompt information is sent to the user end. At this time, the user end can add the intelligent service prompt information to the operation bar of the corresponding interface of the official account (such as the official account homepage). This embodiment can support users to trigger intelligent service requests through intelligent service prompt information displayed on multiple interfaces (i.e., e-commerce platform interface or official account interface), thereby improving the flexibility and convenience of the intelligent service request triggering method.

[0076] Optionally, the user end may add the intelligent service prompt information by adding a touch component to a preset position of the interface (such as the operation bar below the interface), and then adding corresponding icons and texts to the touch component. At this time, when displaying the intelligent service prompt information, a touch component with an icon for providing an intelligent search service may be displayed at a preset position in the user interface, and relevant text descriptions (such as a rental entrance) may be displayed below the icon for easy user identification.

[0077] S202: In response to the intelligent service request sent by the user terminal, establish a session connection with the user terminal.

[0078] The intelligent service request is generated in response to a triggering operation of the intelligent service prompt information, and is used to request the server to provide the user with an object search service for a target rental type as an intelligent customer service.

[0079] Optionally, when the user terminal displays the intelligent service prompt information, if it detects a triggering operation for the intelligent service prompt information (for example, detecting that the user has clicked on the intelligent service prompt information), it generates an intelligent service request and sends the intelligent service request to the server terminal. After receiving the intelligent service request, the server terminal will establish a session connection between the server terminal and the user terminal based on the user identifier corresponding to the user terminal (such as the user account). The session connection provides a channel for the server terminal to interact with the user terminal as an intelligent customer service. For example, based on the session connection, a session interface is created, and multiple rounds of dialogue are conducted with the user terminal in the session interface, and search results of rental objects are provided to the user terminal.

[0080] S203: Send at least one piece of demand inquiry information for the target lease type to the user terminal based on the session connection, and obtain at least one piece of reply information fed back by the user terminal for the at least one piece of demand inquiry information.

[0081] The demand inquiry information may be information inquiring about the user's rental needs. This demand inquiry information can be a pre-set fixed inquiry script for the target rental type, or it can be generated using an artificial intelligence model. For example, the artificial intelligence model can be used to refine the fixed inquiry script corresponding to the target rental type, outputting demand inquiry information that is more consistent with the expression of human customer service. Alternatively, the artificial intelligence model can be used to generate demand inquiry information based on the fixed inquiry script, further combining the target rental type and historical conversation records with the user, to increase the flexibility and pertinence of the demand inquiry information.

[0082] Optionally, one implementation of this embodiment can generate a demand inquiry message (e.g., "Please send a rental request") for the target rental type, and send the demand inquiry message to the user terminal based on the session connection established in S202. The user terminal will then create a corresponding session interface for the session connection and display the demand inquiry message in the session interface. After viewing the demand inquiry message, the user can enter at least one reply message for the demand inquiry message in the session interface. The user terminal will then feed back the at least one reply message entered by the user to the user terminal. After receiving the reply message, the server will determine whether the reply message lacks necessary demand information. If so, it will generate a demand inquiry message for the missing necessary demand information and send it to the user terminal until the received reply message does not lack the necessary demand information. The necessary demand information can be the required demand information required for searching for the rental object. For example, if the rental object is a house, the necessary demand information at this time may include: rental location, rental price, and rental type (entire rental or shared rental).

[0083] Another possible implementation of this embodiment may be to determine the corresponding demand inquiry information for each of the at least one screening conditions required for searching for the rental object, and then send each demand inquiry information to the user end in turn through at least one round of dialogue, and after receiving the reply information fed back by the user end for the demand inquiry information, send the next demand inquiry information, thereby obtaining at least one reply information for at least one demand inquiry information feedback.

[0084] Optionally, in order to facilitate the user to respond to the rental demand more accurately, the server of this embodiment may send at least one demand description example corresponding to the inquiry message when sending at least one inquiry message to the user. For example, Figure 3 In the schematic diagram of the first interface (ie, the session interface corresponding to the session connection), 301 represents demand inquiry information, 302 represents reply information, and 303 represents a demand description example.

[0085] S204: Determine multiple lease requirements for the target lease type based on at least one reply message using an artificial intelligence model.

[0086] The rental requirements in this embodiment typically include multiple requirements, including at least the essential requirements for searching for rental objects. To improve the accuracy of the rental object search, the rental requirements in this embodiment may also include additional requirements. For example, in the case of renting a house, the rental requirements in this embodiment include not only the essential requirements such as the location, price, and type of rental, but also additional requirements such as the unit type, orientation, floor, interior decoration, facilities, and lease term.

[0087] The artificial intelligence model involved in this article can be an artificial intelligence-based language model (Language Mode, LM) or a multimodal model (Multimodal Model, MM), etc. The embodiment of this application does not limit the number of model parameters supported by the model, with the goal of meeting actual needs.

[0088] Optionally, this embodiment may utilize an artificial intelligence model to perform demand analysis on at least one reply message fed back by the user terminal according to demand reasoning logic, and determine multiple rental demands of the corresponding user of the user terminal for the target rental type.

[0089] S205: Determine the search weights corresponding to the multiple rental requirements.

[0090] Optionally, this embodiment can assign different importance levels to multiple rental requirements based on the importance of each rental requirement in the rental object search process, and assign search weights to the multiple rental requirements in descending order of importance (i.e., the higher the importance level, the higher the corresponding search weight). Specifically, this embodiment can pre-set corresponding search weights for various types of rental requirements based on their importance. In this case, for multiple rental requirements, the weights of the rental requirement types to which they belong are sequentially searched and used as the corresponding search weights for each.

[0091] For example, if the object to be rented is a house, among the various rental demand types, the search weight corresponding to the rental location and rental type is 100%; the search weight corresponding to the rental price and apartment type is 90%; the search weight corresponding to the orientation and area is 80%; the search weight corresponding to the floor and decoration is 75%; the search weight corresponding to the facility configuration is 70%; the search weight corresponding to the lease period is 60%, etc.

[0092] S206, determining a target weight threshold and performing the following search operation; the search operation includes: based on at least one rental requirement whose search weight is greater than or equal to the target weight threshold, searching whether there is at least one first rental object that meets the at least one rental requirement.

[0093] Optionally, this example may be to use the smallest search weight among the search weights corresponding to multiple rental requirements as the initial target weight threshold, and then use at least one rental requirement with a search weight greater than or equal to the target weight threshold as a screening condition to search the rental object database for a rental object (i.e., the first rental object) that meets these rental requirements. If so, execute S208; if not, execute S207.

[0094] S207: If the target does not exist, increase the target weight threshold and re-execute the search operation.

[0095] Optionally, if there is no at least one first rental object that meets at least one rental requirement, it is necessary to increase the current target weight threshold. For example, the preset value can be increased (such as increased by 10%), or the search weight corresponding to multiple rental requirements, which is closest to the current target weight threshold and greater than the target weight threshold, can be used as the increased target weight threshold, and based on the increased target weight threshold, return to continue executing the search operation of S206.

[0096] Optionally, to ensure the accuracy of the rental object search, this embodiment may set an upper limit for the target weight threshold, i.e., a preset value. This preset value may be determined based on the minimum search weight corresponding to the necessary rental requirements, or based on a large number of statistical or inference operations. If at least one first rental object that meets at least one rental requirement does not exist and the target weight threshold reaches the preset value, the search operation is terminated and a search failure prompt is fed back to the user terminal.

[0097] Specifically, if S206 does not search for the first rental object that meets the requirements, and the target weight threshold is greater than a preset value (such as 90%), if the target weight threshold is increased at this time, it will result in the lack of necessary rental requirements for the rental requirements used. Therefore, even if the first rental object is searched, the accuracy of the first rental object is not high. Therefore, when the target weight threshold is greater than the preset value, this embodiment will no longer increase the target weight threshold, but stop the search operation and feedback a search failure prompt message to the user, for example, no house that meets your requirements was found.

[0098] S208: If so, then based on the session connection, feed back relevant information of the at least one first leased object to the user terminal, so that the user terminal displays the relevant information of the at least one first leased object.

[0099] In this embodiment, the relevant information of the rental object may include description information, pictures, release time, and communication prompt information of the rental object.

[0100] Optionally, one implementation method of this embodiment may be to obtain relevant information of at least one first leased object found, and based on the session connection, send the relevant information of at least one first leased object found to the user terminal, so that the user terminal displays the relevant information of at least one first leased object on the session interface corresponding to the session connection.

[0101] If a large number of first rental objects are found, in order to facilitate the user to view the search results in a targeted manner, this embodiment may be to select at least one first recommended object from multiple first rental objects, and based on the session connection, feedback the relevant information of the at least one first recommended object to the user end; if it is detected that the secondary recommendation condition is met, then at least one second recommended object is selected from other first rental objects other than the first recommended object, and based on the session connection, feedback the relevant information of the at least one second recommended object to the user end. Specifically, when selecting recommended objects (i.e., first recommended objects or second recommended objects) from multiple first rental objects, a preset number of first rental objects with a high degree of matching with multiple rental requirements may be selected as recommended objects; or a preset number of first rental objects may be randomly selected as recommended objects. Detecting that the secondary recommendation condition is met may be detecting that the user has not clicked to view the relevant information of the first recommended object for a long time, or that a preset interval time has been reached, or that the user has not turned off the function of the intelligent search service, etc.

[0102] For example, Figure 4 In the second interface shown on the user terminal, the relevant information of the three first rental objects is displayed. In this embodiment, when the relevant information of the first rental object is displayed through the user terminal, the push will stop, that is, the function of the intelligent search service is turned off. If the user is not satisfied with the first rental object displayed this time, the function of the intelligent search service can be manually turned on. For example, click Figure 4 In addition, the upper part of the interface displays the corresponding rental demand of the user end for the user to view.

[0103] In some embodiments, to prevent the user from being disturbed by the direct push of a large amount of information related to the rental object, during this step, an object viewing prompt message may be sent to the user terminal based on the session connection; in response to the viewing confirmation message fed back by the user terminal, information related to at least one first rental object may be fed back to the user terminal based on the session connection; the viewing confirmation message is generated in response to the triggering operation of the object viewing prompt message. The object viewing prompt message is used to prompt the user to view the information related to the at least one first rental object. For example, it may be "There is a new matching landlord. You can chat with the landlord directly to view details."

[0104] This embodiment can first obtain the object viewing prompt information, and then send the object viewing prompt information to the user end based on the session connection, so that the user end displays the conversation viewing prompt information on the conversation page corresponding to the session connection. If the user end detects that the user triggers the operation for viewing the conversation prompt information, it means that the user wants to view the relevant information of the searched first rental object. At this time, the viewing confirmation information is generated and sent to the server end. After receiving the viewing confirmation information, the server end will feedback the relevant information of at least one first rental object to the user end based on the session connection. The specific sending method has been introduced in the above embodiment and will not be repeated here. Optionally, the method for obtaining the object viewing prompt information in this embodiment can be to obtain the conversation viewing prompt information with fixed words; or it can be to generate the object viewing prompt information based on the number of the first rental objects found, the relevant information of the first rental objects, etc.

[0105] For example, Figure 3 The 304 in the above is the object viewing prompt information sent to the user end for display. If the user end detects that the user triggers the "view details" operation, it will generate a view confirmation message and send it to the server end. At this time, the server end will further push the relevant information of the first leased object to the user end, that is, Figure 4 The interface shown.

[0106] Optionally, in this embodiment, when the server performs an object search operation, it can send a search progress prompt to the user terminal so that the corresponding user of the user terminal can understand the progress of the current intelligent service. Figure 3 "We are matching landlords according to your requirements. We will notify you when the match is successful. See details." You can also add some promotional information to the search progress prompt, for example, Figure 3 "We are accelerating the matching of landlords. Follow the official account to promptly notify you of new information ~ Official account details."

[0107] Optionally, in order to facilitate communication between the user and the provider of the first rental object, the relevant information of the first rental object in this embodiment includes communication prompt information; the communication prompt information may include: touch components, text, and icons that provide the user end with information for communicating with the provider of the rental object. After the three are rendered and displayed on the conversation interface, they may be displayed in the form of touch components, such as Figure 4 The touch components shown in "Online Chat".

[0108] Accordingly, this implementation method further includes: establishing a communication connection in response to a communication request sent by the user end; the communication connection is used for a conversation between the corresponding user of the user end and the provider of the first rental object; the communication request is generated in response to a triggering operation of the communication prompt information. Specifically, after the user end detects the user triggering the communication prompt information, it generates a communication request based on the current login account and the identifier of the first rental object corresponding to the triggering operation (such as a number) or the identifier of the provider of the rental object (such as a phone number) and sends it to the server end. The server end responds to the communication request and establishes a communication connection between the corresponding user of the user end and the provider of the first rental object, so that the two parties can communicate based on the communication connection. The communication connection can be a telephone connection or an interface session connection, etc.

[0109] Optionally, in this embodiment, in order to be able to continuously search for and push suitable rental objects to users, this embodiment can also be such that, when the secondary recommendation conditions are met, if a new rental object event is detected, the target weight threshold is determined again and the following search operation is performed to obtain at least one new first rental object; based on the session connection, relevant information of the new at least one first rental object is fed back to the user terminal.

[0110] In this embodiment, satisfying the secondary recommendation condition may be a criterion for determining whether a new rental object that meets the user's rental needs should be recommended to the user again. For example, the conditions may include but are not limited to: after multiple searches in S206, the first rental object is not found; it is detected that the user has not viewed the relevant information of the first rental object (for example, has not clicked on the object viewing prompt information about the first rental object); the user has not disabled the smart search service function; the user has not reached a transaction with the provider of the first rental object; the time interval since the last search operation is greater than a preset time interval, etc.

[0111] The newly added rental object event may refer to an event in which a new rental object is added to the e-commerce platform. For example, if the rental object is a house, it may be that the landlord has uploaded a new rental listing.

[0112] Specifically, if it is detected that any of the above-mentioned secondary recommendation conditions are met at the current moment, it means that new search results need to be recommended to the user for the search operation again. However, if there are no new rental objects in the e-commerce platform, the search results will remain the same as last time. Therefore, this embodiment detects whether there is a new rental object event in the e-commerce platform. If so, it returns to execute the operation S206 again. It should be noted that since the existing rental objects have been searched, in order to improve search efficiency, this embodiment can also execute the operation S206 only for the newly added rental objects. This embodiment can continuously search for rental objects that meet the requirements for the user when the secondary recommendation conditions are met and new rental objects are added, avoiding missing high-quality rental objects.

[0113] Optionally, in this embodiment, after searching for at least one first rental object that meets the user's rental needs, relevant information (such as phone number) of the user corresponding to the user end can be further sent to the provider of at least one first rental object, so that if the user corresponding to the user end is not interested in the first rental object, the provider can actively contact the user to avoid user loss.

[0114] This embodiment sends an intelligent service prompt message for a target rental type to a user terminal for display by the user terminal. In response to an intelligent service request sent by the user terminal in response to a triggering operation of the intelligent service prompt message, a session connection is established with the user terminal. Based on the session connection, at least one demand inquiry message is sent to the user terminal, and at least one reply message is received from the user terminal. Based on the at least one reply message, an artificial intelligence model is used to determine multiple rental requirements. At least one rental requirement with a search weight greater than or equal to a target weight threshold is selected to determine whether there is at least one first rental object that meets the requirement. If not, the target weight threshold is increased and the search operation is continued. If so, relevant information about the at least one first rental object is fed back to the user terminal for display by the user terminal. This embodiment of the present application uses an artificial intelligence model to communicate with the corresponding user on the user terminal to identify the user's rental requirements. This can accurately and comprehensively determine the rental requirements and then accurately search for the first rental object that meets the requirements for the user, thereby improving the accuracy of the search results. Moreover, the entire search process only requires the user to answer the demand inquiry message, eliminating the need to spend a lot of time waiting or searching for rental objects, thereby improving search efficiency. In addition, when searching for the first rental object, this embodiment adopts a sampling weight gradient search strategy, that is, by continuously increasing the target weight value, the number of rental demands used in the search is reduced, thereby ensuring that the first rental object is retrieved based on as many rental demands as possible, further improving the accuracy of the first rental object.

[0115] In some embodiments, to improve the accuracy of searching for the first rental object, this embodiment may use a combination of precise search and fuzzy search to perform the operation of searching for the first rental object in S206, which may specifically include the following two sub-steps:

[0116] Sub-step 1: Based on a matching relationship between at least one rental requirement having a search weight greater than or equal to a target weight threshold and a plurality of preset requirements, determining a search method corresponding to each of the at least one rental requirements.

[0117] Among them, the preset requirements can be pre-set for multiple rental demand categories corresponding to the target rental type, the purpose of which is to label the available rental objects (i.e., candidate objects) provided by the e-commerce platform, so as to facilitate the subsequent quick and accurate search for the first rental object that meets the user's needs. For example, if the target rental type is a house, then for the rental demand category of location, the pre-set preset requirements may include: XX city, XX district, XX business district, XX community, etc. For the rental demand category of apartment type, the pre-set preset requirements may include: one room, two rooms, three rooms, etc. It should be noted that in order to ensure the accuracy of the search results, the finer the rental demand categories of this embodiment are divided, the better, and the more detailed the corresponding preset requirements are set, the better.

[0118] In this embodiment, the search method corresponding to each rental demand is either precise search or fuzzy search, so the search method corresponding to at least one rental demand finally determined may be precise search, fuzzy search, or both precise search and fuzzy search.

[0119] Specifically, in this embodiment, for any rental demand with a search weight greater than or equal to a target weight threshold, if there is a match between the rental demand and a preset demand, the search method corresponding to the rental demand is determined to be a precise search; if there is no match between the rental demand and the multiple preset demands, the search method corresponding to the rental demand is determined to be a fuzzy search. In this embodiment, the so-called "match" means that the rental demand has a high degree of similarity with any of the multiple preset demands. Alternatively, the rental demand may be completely identical to any of the multiple preset demands.

[0120] It should be noted that, to ensure the accuracy of the search results, the preset requirements in this embodiment are typically set in relatively detailed terms. Therefore, under normal circumstances, an identified rental requirement will typically only match one preset requirement. However, because multiple rental requirements are identified using an artificial intelligence model, even with high recognition accuracy, it is inevitable that recognition errors, known as AI (Artificial Intelligence) illusions, may occur. For example, if only a portion of a rental requirement is identified, when determining the degree of match between the rental requirement and the preset requirements, the rental requirement may be simultaneously matched with multiple preset requirements due to the inaccurate rental requirement. For example, suppose the artificial intelligence model identifies the rental requirement as XX Road, and the preset requirements include four subway stations: "XX Road East," "XX Road West," "XX Road South," and "XX Road North." In this case, the rental requirement will simultaneously match four preset requirements.

[0121] In order to solve the problem of the above-mentioned AI illusion affecting the search accuracy of the first rental object, this embodiment can be that if there is a matching relationship between the rental demand and at least two preset demands, then the artificial intelligence model is used to determine the confirmation query information based on the at least two preset demands with a matching relationship; the confirmation query information is sent to the user end, and the demand confirmation information fed back by the user end in response to the confirmation query information is obtained; the rental demand is adjusted based on the demand confirmation information, and the search method corresponding to the adjusted rental demand is determined to be a precise search. Among them, the confirmation query information can be an inquiry information that allows the user to confirm the specific rental demand. For example, it can be "Please confirm which of the following four subway stations is the rental location you want to choose: 'XX Road East', 'XX Road West', 'XX Road South' and 'XX Road North' four subway stations." The demand confirmation information can be the preset demand corresponding to the user selection operation.

[0122] Specifically, when a matching relationship exists between the rental demand and at least two preset demands, the server can generate confirmation query information based on the at least two matching preset demands. For example, an artificial intelligence model can be used to generate confirmation query information based on the at least two matching preset demands, so that the generated confirmation query information is closer to the conversation style of human customer service and improves user acceptance. The confirmation query information is then sent to the user terminal, which can then display the confirmation query information on the session interface corresponding to the session connection. For example, the touch component of the matching preset demand can be displayed in the form of a card so that the user can click the corresponding touch component. The user terminal will respond to the user's triggering operation on the touch component of the preset demand and generate demand confirmation information. The preset demand corresponding to the demand confirmation information will then replace the rental demand to adjust the rental demand. The search method corresponding to the adjusted rental demand will then be set to precise search.

[0123] Sub-step 2: searching for at least one first rental object that meets the at least one rental requirement according to the search method corresponding to the at least one rental requirement.

[0124] Case 1: If the search method corresponding to at least one rental requirement is a precise search, then the multiple rental requirements are used as indexes, and combined with the preset requirements corresponding to the candidate objects provided by the e-commerce platform, a search is performed to determine whether there is at least one candidate object among the candidate objects that meets the multiple rental requirements (i.e., the preset requirements of the at least one candidate object can meet the multiple rental requirements). If so, the at least one candidate object is selected as the at least one first rental object. If not, it indicates that no first rental object that meets the requirements has been found.

[0125] Optionally, for precise search, in order to improve search efficiency, this embodiment may pre-set corresponding identifiers for each preset requirement, for example, identifier 11 for whole rental, identifier 12 for shared rental, identifier 1 for city A, identifier 2 for city B, etc. Before performing a precise search, each rental object for which the precise search method is used is first converted into an identifier corresponding to the preset requirement, and then, using the identifier as an index, a candidate object containing the identifier corresponding to each rental requirement (each rental requirement corresponding to the precise search) is searched and selected as the first rental object.

[0126] Case 2: If the search method corresponding to at least one rental requirement is fuzzy search, then the introduction information of the candidate objects provided by the e-commerce platform, such as object description information, provider remarks information, etc., can be combined to match at least one rental requirement, and search whether there is at least one candidate object with introduction information (i.e., the content of the introduction information record) in the candidate objects and meets at least one rental requirement. If so, the at least one candidate object is used as the at least one first rental object; if not, it means that no first rental object that meets the requirements has been found.

[0127] Case 3: If the search methods corresponding to multiple rental requirements include both precise search and fuzzy search, then

[0128] Based on the preset search intent corresponding to the candidate rental objects, a search is performed to determine whether there is at least one pre-screened rental object that meets the rental requirements corresponding to the fuzzy search method; if so, based on the matching relationship between the relevant information of the pre-screened rental object and the rental requirements corresponding to the fuzzy search method, a search is performed to determine whether there is at least one first rental object that meets the rental requirements corresponding to the fuzzy search method.

[0129] Specifically, in this case, for at least one rental demand whose search method is precise search (i.e., precise search demand), according to the method described in the first case above, a search is conducted from the candidate objects provided by the e-commerce platform to determine whether there is at least one candidate object that meets each precise search demand as at least one initially screened rental object; if there is at least one initially screened rental object that meets the demand, then, for at least one rental demand whose search method is fuzzy search (i.e., fuzzy search demand), according to the method described in the second case above, a search is conducted from the at least one initially screened rental object obtained from the precise search to determine whether there is at least one initially screened rental object that meets each fuzzy search demand as at least one first rental object. If, after the precise search, it is found that there is no at least one candidate object that meets the demand, or after the fuzzy search, it is found that there is no at least one initially screened rental object that meets the demand, it is directly determined that there is no first rental object that meets the requirements. In this case, the accuracy of the search results is improved by combining precise search and fuzzy search.

[0130] In some embodiments, in order to ensure the accuracy of the display timing of the intelligent service prompt information, this embodiment may further include the following sub-steps when sending the intelligent service prompt information for the target rental type to the user terminal:

[0131] Sub-step 3: Receive an information search request for the target rental type from the user. The information search request can be a user input operation for at least one search condition under any target rental type, or a request generated by a search component triggering an operation, including at least one search condition. The information search request is used to request the server to search for a rental object (i.e., a second rental object) that meets the at least one search condition. The search condition can be a search requirement manually entered by the user in the search input box, or a target item selected from the options listed in the search prompt bar.

[0132] Specifically, when a user has an object rental demand for a target rental type, he or she will enter the search interface corresponding to the target rental type through the user terminal, and then enter at least one search condition in the search interface, and trigger the search component. After the user terminal detects the operation, it will generate an information search request for the target rental type based on the at least one search condition entered by the user and the target rental type, and send it to the server.

[0133] Sub-step 4: Searching for a second rental object that meets at least one search condition.

[0134] Specifically, after receiving the information search request, the server will search the candidate objects provided by the e-commerce platform according to at least one search criterion to see if there is a second rental object that meets the at least one search criterion. It should be noted that in this step, when searching for the second rental object, priority is given to searching for second rental objects that meet all search criteria. If no second rental object is found, the search criteria can be gradually reduced to further find the second rental object. In other words, to ensure that rental objects are displayed in the search list interface, even if no rental object that meets at least one search criterion is found, a rental object that closely matches the second rental object can be selected as the second rental object.

[0135] Sub-step 5: Sending the relevant information of the second leased object and the intelligent service prompt information of the lease type to the user terminal, so that the user terminal displays the relevant information of the second leased object and the intelligent service prompt information on the search list interface.

[0136] Specifically, the server may render the relevant information about the second leased object and the intelligent service prompt information of the lease type onto the search list interface, and then send the rendered search list interface to the user terminal, which may then directly display the received search list interface. Alternatively, the server may directly send the relevant information about the second leased object and the intelligent service prompt information of the lease type to the user terminal, which may then render the relevant information about the second leased object and the intelligent service prompt information of the lease type onto the search list interface and then display the search list interface.

[0137] Since the user terminal displays the search list interface, it indicates that the corresponding user of the user terminal has a rental demand for the target rental type, and in general the search conditions entered by the user are not very accurate, so this embodiment displays the intelligent service prompt information in the search list interface, which helps to attract users to trigger the intelligent service prompt information and improve the conversion rate of the intelligent search service.

[0138] Based on this embodiment, in order to improve the intelligence of the inquiry process and ensure the accuracy of the rental demand positioning, this example can use the artificial intelligence model to conduct multiple rounds of dialogue interaction with the user end to obtain at least one reply message. The specific steps can include the following:

[0139] Sub-step 6: Utilizing the artificial intelligence model, generate current demand query information for the target rental type based on at least one search condition in the information search request. Since this embodiment involves multiple rounds of conversational interaction to obtain at least one reply message, the demand query information sent to the user end for each round of conversational interaction is referred to as the current demand query information corresponding to that round of conversational interaction. For the first round of conversational interaction, since at least one search condition included in the information search request also represents at least one rental requirement of the user, to prevent repeated inquiries about user requirements and improve the intelligence of the inquiry process, when generating the current demand query information for the first round of conversational interaction, the rental requirement corresponding to the at least one search condition may be first determined. Then, corresponding demand query information for all rental requirements other than that rental requirement is generated as the current demand query information.

[0140] Sub-step 7: Based on the session connection, the current demand inquiry information is sent to the user terminal, and the current response information fed back by the user terminal in response to the current demand inquiry information is obtained. It should be noted that the specific implementation method has been introduced in the above embodiment and will not be repeated here.

[0141] Sub-step 8: Based on the current response, determine whether necessary requirement information is missing. For each target rental type, the required requirement information (i.e., information about the rental requirement category) is pre-set for the search operation. For example, if the target rental type is a house, the corresponding necessary requirement information may include the rental location, rental price, and rental type (whole rental or shared rental). The specific determination process has been described in the above embodiment and will not be repeated here.

[0142] Sub-step 9: If the information is missing, the AI ​​model is used to generate a new current demand query based on the missing necessary demand information. The process then returns to Sub-step 7 to continue executing the session connection, sending the current demand query to the user end until Sub-step 8 is executed to determine that the necessary demand information is not missing. Specifically, if the necessary demand information is missing, it indicates that the next round of dialogue interaction is necessary. The specific operation has been described in the above embodiment and will not be repeated here.

[0143] In some embodiments, in order to improve the intelligence of the service and assist the user in searching for the first rental object that meets the needs as much as possible, this embodiment may also include: if it is detected that the demand modification conditions are met, based on the session connection, sending demand modification prompt information to the user terminal, and obtaining the demand modification information fed back by the user terminal in response to the demand modification prompt information; using the artificial intelligence model, based on the at least one reply information and the demand modification information, re-determining multiple rental needs for the target rental type, and continuing to determine the search weights corresponding to each of the multiple rental needs.

[0144] The demand modification condition may be a judgment condition for determining whether it is necessary to prompt the user to modify the rental demand, for example, including but not limited to the following: Condition 1: The user is not satisfied with the first rental object recommended. For example, after the user is sent the relevant information of the first pair of rental objects found, the user activates the function of providing the intelligent search service (for example, in Figure 4 (The "Start Request" button is clicked in the interface shown) Condition 2: The first rental object is not found. The request modification prompt information sent to the user terminal in this embodiment is used to prompt the user to modify the rental request. The prompt information can be a pre-set fixed wording or a fixed wording modified using an artificial intelligence model to better align with the expression habits of human customer service staff.

[0145] Optionally, in this embodiment, the user end utilizes an artificial intelligence model to re-determine multiple rental requirements for the target rental type based on at least one reply message and the requirement modification information. This is similar to the method described in the above embodiment for utilizing an artificial intelligence model to determine multiple rental requirements for the target rental type based on at least one reply message, and is not further described here. After determining the new multiple rental requirements, the user end continues to perform operations similar to those described in the above embodiment for gradient search of rental objects (i.e., S205 and subsequent operations in the above embodiment).

[0146] It should be noted that, in addition to actively sending a demand modification prompt message to the user terminal to prompt the user to modify the rental demand, this embodiment can also support the user to actively modify the demand at the user terminal. For example, the user can Figure 3 Enter the demand modification information in the input bar below the shown interface. At this time, the user end will send the demand modification information entered by the user to the server end. After receiving the demand modification information, the server end will also use the artificial intelligence model to re-determine multiple rental demands for the target rental type based on at least one reply message and the demand modification information, and return to continue to determine the search weights corresponding to the multiple rental demands.

[0147] Based on the above embodiment, in order to better assist users in modifying their needs, this embodiment may include: utilizing an artificial intelligence model to determine a reason for the need modification based on multiple rental needs of the target rental type, and determining a need modification prompt based on the reason; and transmitting the need modification prompt to the user based on the session connection. Specifically, the artificial intelligence model may be utilized, according to preset inference rules, to analyze the reason why no rental object meeting the need was found (i.e., the need modification reason), such as a price that is too low or a lack of housing near the desired location, based on the analyzed need modification reason. Based on this reason, a need modification prompt is generated and sent to the user for display.

[0148] Figure 5 This is a flow chart of an embodiment of an information search method provided by this application. The technical solution of this embodiment can be executed by the user terminal. Figure 5 As shown, the method may include the following steps:

[0149] S501: Receive intelligent service prompt information for a target rental type sent by a server, and display the intelligent service prompt information.

[0150] S502 : In response to a triggering operation on the intelligent service prompt information, sending an intelligent service request to the server, so that the server establishes a session connection with the user.

[0151] S503: Based on the session connection, receive at least one piece of demand inquiry information for the target lease type sent by the server, and display the at least one piece of demand inquiry information.

[0152] S504: Obtain at least one reply message for at least one demand inquiry message.

[0153] S505: Based on the session connection, at least one reply message is sent to the server, so that the server can use the artificial intelligence model to determine multiple rental requirements for the target rental type based on the at least one reply message, and determine search weights corresponding to each of the multiple rental requirements; determine a target weight threshold, and perform the following search operation; the search operation includes: based on at least one rental requirement having a search weight greater than or equal to the target weight threshold, searching for at least one first rental object that meets the at least one rental requirement; if not, increasing the target weight threshold and re-performing the search operation; if so, feeding back relevant information of the at least one first rental object to the user terminal based on the session connection.

[0154] S506: Based on the session connection, obtain and display relevant information of at least one first leased object.

[0155] In some embodiments, it also includes: receiving confirmation inquiry information sent by the server based on the session connection; the confirmation inquiry information is generated based on at least two preset requirements with a matching relationship using the artificial intelligence model when there is a matching relationship between the rental requirement and at least two preset requirements; in response to the demand confirmation information generated by the trigger operation for the confirmation inquiry information, the demand confirmation information is sent to the server based on the session connection, so that the server adjusts the rental requirement based on the demand confirmation information, and determines that the search method corresponding to the adjusted rental requirement is a precise search.

[0156] In some embodiments, the method further includes: obtaining at least one search condition, generating an information search request for a target rental type based on the at least one search condition, and sending the information search request to a server based on the session connection, so that the server searches for a second rental object that meets the at least one search condition;

[0157] Accordingly, executing S501 specifically includes: obtaining relevant information of the second leased object and intelligent service prompt information of the lease type based on the session connection, and displaying relevant information of the second leased object and the intelligent service prompt information on the search list interface.

[0158] In some embodiments, it also includes: obtaining current demand inquiry information based on the session connection; wherein, the current demand inquiry information is generated based on at least one search condition in the information search request using an artificial intelligence model; obtaining current reply information for the current demand inquiry information feedback, and sending the current reply information to the server based on the session connection, so that the server can determine whether necessary demand information is missing based on the current reply information; if missing, generating new current demand inquiry information based on the missing necessary demand information using the artificial intelligence model, and continuing to send the current demand inquiry information to the user end based on the session connection until necessary demand information is no longer missing.

[0159] In some embodiments, the operation of S506 above specifically includes: obtaining object viewing prompt information sent by the server based on the session connection; the object viewing prompt information is used to prompt viewing of relevant information of the at least one first leased object; generating viewing confirmation information in response to a trigger operation for the object viewing prompt information, sending the viewing confirmation information to the server based on the session connection, and obtaining relevant information of the at least one first leased object fed back by the server in response to the viewing confirmation information based on the session connection, and displaying relevant information of the at least one first leased object.

[0160] In some embodiments, the relevant information of the first rental object includes communication prompt information; the method further includes: generating a communication request in response to a trigger operation for the communication prompt information, and sending the communication request to the server, so that the server establishes a communication connection in response to the communication request; the communication connection is used for a corresponding user of the user end to communicate with the provider of the first rental object.

[0161] In some embodiments, the above method further includes: based on the session connection, obtaining relevant information of at least one new first rental object fed back by the service, and displaying relevant information of the at least one new first rental object; wherein, the relevant information of the at least one first rental object is determined by re-executing the target weight threshold and performing a search operation when the secondary recommendation condition is met and a new rental object event is detected.

[0162] In some embodiments, the above method also includes: receiving demand modification prompt information sent by the server; obtaining the modification requirements for the demand modification prompt information feedback, and sending the modification requirements to the server, so that the server uses the artificial intelligence model to re-determine multiple rental requirements for the target rental type based on the at least one reply information and the demand modification information, and continue to determine the search weights corresponding to each of the multiple rental requirements.

[0163] It should be noted that the information search method of this embodiment is applied to the user side, and the specific implementation method and beneficial effects of each step have been introduced on the above-mentioned server side, which will not be repeated here.

[0164] In a practical application, Figure 6 This diagram shows a scenario interaction diagram of an actual application provided by an exemplary embodiment of the present application. In this scenario, a tenant interacts with a service end and a landlord end through their user end to provide the tenant with a smart housing search service. The user end in this embodiment refers to the user end used by the tenant. Figure 6 The server side shown further includes an AI big model module, a search engine module, and a landlord service module. The AI ​​big model module primarily performs AI model processing operations. The search engine module primarily performs object search operations. The landlord service module serves as a bridge connecting the AI ​​big model module and the search engine module.

[0165] like Figure 6As shown, the specific implementation method is as follows: if the user terminal triggers an information search request to the server terminal based on the search conditions input by the user, the server terminal will not only feedback the house list (i.e., the second rental object) found based on the search conditions to the user terminal, but also feedback the rental entrance information (i.e., intelligent service prompt information). At this time, the user terminal will display the house list and rental entrance information on the search list interface. At this time, while previewing the house list through the user terminal (S601), the user will view the rental entrance displayed in the interface (S602). When the user clicks on the rental entrance, the user terminal will collect the search conditions input by the user (S603), and then initiate an intelligent service request containing the search conditions to the server terminal. At this time, the server terminal will respond to the intelligent service request, use the artificial intelligence model module to start the conversation mode, interact with the corresponding user of the user terminal through multiple rounds of dialogue, and use AI to analyze the tenant's rental needs (i.e., rental needs), thereby obtaining the tenant's necessary rental needs (such as rental location, price, whole rental / shared rental) and differentiated rental needs (such as floor, orientation, check-in time, etc.) (S604). The AI ​​big model module will use the parsed rental demand as the tenant's housing search conditions and send it to the landlord service module (S605). The landlord service module will asynchronously trigger the search engine module to retrieve housing resources based on the tenant's housing search conditions using the method described in the above embodiment (S606), and send the retrieved housing resources to the user end (S607), and the user will present the housing resources to the tenant (S607). Figure 4 As shown, the housing information presented in this embodiment includes communication prompt information. If the user actively triggers the communication prompt information (S608), the user end will send a communication request to the server end (such as the landlord service module) based on the user's triggering operation. The server end will establish a communication connection in response to the communication request, so that the tenant can communicate with the landlord corresponding to the landlord end through the user end (S609). In addition, after the search engine module of this embodiment searches for a matching housing source, it will also notify the landlord corresponding to the housing source. At this time, the landlord can also actively communicate with the tenant in a similar manner (S610).

[0166] The detailed implementation and beneficial effects of each step in the method of this embodiment have been described in detail in the aforementioned embodiments and will not be elaborated here.

[0167] It should be noted that some of the processes described in the above embodiments and the accompanying drawings include multiple operations that appear in a specific order, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or may be executed in parallel. The sequence numbers of the operations, such as S601, S602, etc., are only used to distinguish between different operations, and the sequence numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article 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.

[0168] Figure 7 A structural diagram of an information search device provided for an exemplary embodiment of the present application, the device is configured at a server end, and includes: a first sending module 701, used to send intelligent service prompt information for a target rental type to a user end, so that the user end displays the intelligent service prompt information; a session establishing module 702, used to establish a session connection with the user end in response to an intelligent service request sent by the user end; the intelligent service request is generated for a triggering operation of the intelligent service prompt information; the first sending module 701 is also used to send at least one demand inquiry information for the target rental type to the user end based on the session connection; a first obtaining module 703 is used to obtain at least one reply information fed back by the user end for the at least one demand inquiry information; a demand determination module 704 is used to utilize an artificial intelligence model, based on The at least one reply message determines multiple rental requirements for the target rental type; a weight determination module 705 is used to determine the search weight corresponding to each of the multiple rental requirements; and to determine a target weight threshold; a search module 706 is used to perform the following search operation; the search operation includes: based on at least one rental requirement whose search weight is greater than or equal to the target weight threshold, searching whether there is at least one first rental object that meets the at least one rental requirement; the weight determination module 705 is further used to increase the target weight threshold and re-execute the search operation using the search module if no such object exists; the first sending module 701 is further used to, if no such object exists, feedback relevant information of the at least one first rental object to the user terminal based on the session connection, so that the user terminal displays the relevant information of the at least one first rental object.

[0169] In an optional embodiment, the search module 706 is specifically used to: determine the search method corresponding to each of the at least one rental requirements based on the matching relationship between at least one rental requirement whose search weight is greater than or equal to the target weight threshold and multiple preset requirements; the search method includes precise search and / or fuzzy search; and according to the search method corresponding to each of the at least one rental requirements, find out whether there is at least one first rental object that meets the at least one rental requirement.

[0170] In an optional embodiment, the search module 706 is further specifically used to: for any rental demand whose search weight is greater than or equal to the target weight threshold, if there is a matching relationship between the rental demand and the preset demand, determine that the search method corresponding to the rental demand is a precise search; if there is no matching relationship between the rental demand and the multiple preset demands, determine that the search method corresponding to the rental demand is a fuzzy search.

[0171] In an optional embodiment, the search module 706 is further specifically used to: if there is a matching relationship between the rental demand and at least two preset demands, then using the artificial intelligence model to determine confirmation query information based on at least two preset demands with a matching relationship; sending the confirmation query information to the user terminal, and obtaining demand confirmation information fed back by the user terminal in response to the confirmation query information; adjusting the rental demand based on the demand confirmation information, and determining that the search method corresponding to the adjusted rental demand is a precise search.

[0172] In an optional embodiment, the search module 706 is further specifically used to: based on the preset search intention corresponding to the candidate rental object, find out whether there is at least one preliminary screened rental object that meets the rental requirements corresponding to the fuzzy search method; if so, based on the matching relationship between the relevant information of the preliminary screened rental object and the rental requirements corresponding to the fuzzy search method, find out whether there is at least one first rental object that meets the rental requirements corresponding to the fuzzy search method.

[0173] In an optional embodiment, the search module 706 is further used to: stop the search operation if there is no at least one first rental object that meets the at least one rental requirement and the target weight threshold reaches a preset value; the first sending module 701 is further used to feedback a search failure prompt message to the user terminal.

[0174] In an optional embodiment, the first acquisition module 703 is further configured to receive an information search request sent by a user terminal for a target rental type; the information search request includes at least one search condition; the search module 706 is further configured to search for a second rental object that meets the at least one search condition; and the first sending module 701 is further specifically configured to send relevant information about the second rental object and intelligent service prompt information about the rental type to the user terminal, so that the user terminal displays relevant information about the second rental object and the intelligent service prompt information on a search list interface.

[0175] In an optional embodiment, the demand determination module 704 is specifically used to utilize an artificial intelligence model to generate current demand inquiry information for the target rental type based on at least one search condition in the information search request; based on the session connection, send the current demand inquiry information to the user terminal, and obtain the current reply information fed back by the user terminal for the current demand inquiry information; determine whether necessary demand information is missing based on the current reply information; if missing, utilize the artificial intelligence model to generate new current demand inquiry information based on the missing necessary demand information, and continue to execute based on the session connection to send the current demand inquiry information to the user terminal until the necessary demand information is no longer missing.

[0176] In an optional embodiment, the first sending module 701 is specifically configured to send object viewing prompt information to the user terminal based on the session connection; the object viewing prompt information is used to prompt the user to view relevant information of the at least one first leased object; in response to viewing confirmation information fed back by the user terminal, the relevant information of the at least one first leased object is fed back to the user terminal based on the session connection; the viewing confirmation information is generated in response to the triggering operation of the object viewing prompt information.

[0177] In an optional embodiment, the relevant information of the first rental object includes communication prompt information; the session establishment module 702 is further used to establish a communication connection in response to a communication request sent by the user terminal; the communication connection is used to enable a corresponding user of the user terminal to communicate with the provider of the first rental object; and the communication request is generated in response to a triggering operation of the communication prompt information.

[0178] In an optional embodiment, the search module 706 is further configured to, when the secondary recommendation condition is met, re-execute the determination of the target weight threshold and perform the following search operation to obtain at least one new first rental object if a new rental object addition event is detected; the first sending module 701 is further configured to feed back relevant information of the at least one new first rental object to the user terminal based on the session connection.

[0179] In an optional embodiment, the first sending module 701 is further used to send demand modification prompt information to the user terminal based on the session connection if it is detected that the demand modification condition is met, and the first obtaining module 703 is further used to obtain demand modification information fed back by the user terminal in response to the demand modification prompt information; the search module 706 is further used to utilize the artificial intelligence model to re-determine multiple rental requirements for the target rental type based on the at least one reply information and the demand modification information, and continue to determine the search weights corresponding to each of the multiple rental requirements.

[0180] In an optional embodiment, it further includes a demand modification module for using the artificial intelligence model to determine the reason for demand modification based on multiple rental requirements of the target rental type, and determine demand modification prompt information based on the reason for demand modification; the first sending module 701 is also specifically used to send demand modification prompt information to the user terminal based on the session connection.

[0181] Figure 7 The information search device can perform Figure 2 The implementation principle and technical effects of the information search method described in the illustrated embodiment will not be described in detail. The specific manner in which each module and unit performs operations in the 7 devices in the above embodiment has been described in detail in the embodiment of the method and will not be elaborated on here.

[0182] Figure 8A structural diagram of an information search device provided for an exemplary embodiment of the present application, the device is configured at a user end, and includes: a second receiving module 801, for receiving intelligent service prompt information for a target rental type sent by a server end; a display module 802, for displaying the intelligent service prompt information; a second sending module 803, for sending an intelligent service request to the server end in response to a trigger operation for the intelligent service prompt information, so that the server end establishes a session connection with the user end; the second receiving module 801 is also used to receive at least one demand inquiry information for the target rental type sent by the server end based on the session connection; the display module 802 is also used to display the at least one demand inquiry information; an information acquisition module 804 is used to obtain at least one reply information for the at least one demand inquiry information; the second sending module 803 is also used to send the requested information to the server end based on the session connection. The at least one reply message is sent to the server, so that the server uses an artificial intelligence model to determine multiple rental requirements for the target rental type based on the at least one reply message; determine a search weight corresponding to each of the multiple rental requirements; determine a target weight threshold and perform the following search operation; the search operation includes: based on at least one rental requirement whose search weight is greater than or equal to the target weight threshold, searching whether there is at least one first rental object that meets the at least one rental requirement; if not, increasing the target weight threshold and re-performing the search operation; if so, feeding back relevant information of the at least one first rental object to the user terminal based on the session connection; the second receiving module 801 is further used to obtain relevant information of the at least one first rental object based on the session connection; the display module 802 is further used to display relevant information of the at least one first rental object.

[0183] In some embodiments, the second receiving module 801 is also used to receive confirmation inquiry information sent by the server based on the session connection; the confirmation inquiry information is generated based on at least two preset requirements with a matching relationship using the artificial intelligence model when there is a matching relationship between the rental requirement and at least two preset requirements; the information acquisition module 804 is also used to generate demand confirmation information in response to a trigger operation for the confirmation inquiry information; the second sending module 803 is also used to send the demand confirmation information to the server based on the session connection, so that the server adjusts the rental requirement based on the demand confirmation information, and determines that the search method corresponding to the adjusted rental requirement is a precise search.

[0184] In some embodiments, the request generation module is used to obtain at least one search condition and generate an information search request for the target rental type based on the at least one search condition; the second sending module 803 is also used to send the information search request to the server based on the session connection, so that the server searches for the second rental object that meets the at least one search condition; accordingly, the second receiving module 801 is also specifically used to obtain relevant information of the second rental object and intelligent service prompt information of the rental type based on the session connection; the display module 802 is also specifically used to display relevant information of the second rental object and the intelligent service prompt information on the search list interface.

[0185] In some embodiments, the second receiving module 801 is further specifically used to obtain current demand inquiry information based on a session connection; wherein, the current demand inquiry information is generated based on at least one search condition in the information search request using an artificial intelligence model; the information acquisition module 804 is further used to obtain current reply information for feedback on the current demand inquiry information; the second sending module 803 is further specifically used to send the current reply information to the server based on the session connection, so that the server can determine whether necessary demand information is missing based on the current reply information; if missing, new current demand inquiry information is generated based on the missing necessary demand information using the artificial intelligence model, and the current demand inquiry information is continued to be sent to the user end based on the session connection until the necessary demand information is no longer missing.

[0186] In some embodiments, the second receiving module 801 is further specifically configured to obtain, based on the session connection, object viewing prompt information sent by the server; the object viewing prompt information is used to prompt viewing of relevant information of the at least one first leased object; the information obtaining module 804 is further configured to generate viewing confirmation information in response to a triggering operation for the object viewing prompt information, and the second sending module 803 is further specifically configured to send the viewing confirmation information to the server based on the session connection; the second receiving module 801 is further specifically configured to obtain, based on the session connection, relevant information of the at least one first leased object fed back by the server in response to the viewing confirmation information, and the display module 802 is further specifically configured to display relevant information of the at least one first leased object.

[0187] In some embodiments, the relevant information of the first rental object includes communication prompt information; the request generation module is further used to generate a communication request in response to a trigger operation for the communication prompt information; the second sending module 803 is further specifically used to send the communication request to the server, so that the server establishes a communication connection in response to the communication request; the communication connection is used for the corresponding user of the user end to communicate with the provider of the first rental object.

[0188] In some embodiments, the second receiving module 801 is further specifically configured to obtain, based on the session connection, relevant information of at least one new first rental object fed back by the service; the display module 802 is further specifically configured to display relevant information of the at least one new first rental object; wherein, the relevant information of the at least one first rental object is determined by re-determining the target weight threshold and performing a search operation when a secondary recommendation condition is met and a new rental object event is detected.

[0189] In some embodiments, the second receiving module 801 is further specifically used to receive demand modification prompt information sent by the server; the information acquisition module 804 is further used to obtain modification requirements for the demand modification prompt information feedback, and the second sending module 803 is further specifically used to send the modification requirements to the server, so that the server uses the artificial intelligence model to re-determine multiple rental requirements for the target rental type based on the at least one reply information and the demand modification information, and continue to determine the search weights corresponding to each of the multiple rental requirements.

[0190] Figure 8 The information search device can perform Figure 5 The implementation principle and technical effects of the information search method described in the illustrated embodiment will not be described in detail. The specific manner in which each module and unit performs operations in the 8 devices in the above embodiment has been described in detail in the embodiment of the method, and will not be elaborated here.

[0191] Figure 9 This is a schematic diagram of a computing device according to an embodiment of the present application. Figure 9 As shown, in practice, the computing device may include: a storage component 901 and a processing component 902 .

[0192] The storage component 901 is used to store computer programs and can be configured to store various other data to support operations on the computing device. Examples of such data include instructions for any application or method operating on the computing device, data structures, contact data, phone book data, messages, images, videos, etc.

[0193] The processing component 902 is coupled to the storage component 901 and is used to execute the computer program in the storage component 901 to implement the following Figure 2 or Figure 5 Information search method shown.

[0194] Further, if Figure 9 As shown, the computing device may further include: a communication component 903, a display component 904, a power component 905, an audio component 906 and other components. Figure 9 Only some components are shown schematically, which does not mean that the equipment only includes Figure 9 In addition, Figure 9 The components in the dotted box are optional components, not mandatory components, and depend on the specific product form of the computing device. The computing device of this embodiment can be implemented as a terminal device such as a desktop computer, a laptop computer, a smart phone or an IOT (Internet of Things) device, or a server device such as a conventional server, a cloud server or a server array. If the computing device of this embodiment is implemented as a terminal device such as a desktop computer, a laptop computer, a smart phone, etc., it can include Figure 9 If the computing device of this embodiment is implemented as a server device such as a conventional server, a cloud server or a server array, it may not include the components in the dotted box; Figure 9 Components within the dotted box.

[0195] The processing component includes one or more processors to execute computer instructions to perform all or part of the steps in the above method. Of course, the processing component can also be implemented as one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above method.

[0196] The above-mentioned storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random-access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0197] The communication component is configured to facilitate wired or wireless communication between the device in which the communication component resides and other devices. The device in which the communication component resides may access a wireless network based on a communication standard, such as a mobile communication network, or a combination thereof. In an exemplary embodiment, the communication component receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel.

[0198] The display assembly may include a screen, which may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touches, slides, and gestures on the touch panel. The touch sensor may not only sense the boundaries of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation.

[0199] The power supply assembly provides power to various components of the device in which the power supply assembly is located. The power supply assembly may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the device in which the power supply assembly is located.

[0200] The above-mentioned audio component can be configured to output and / or input audio signals. For example, the audio component includes a microphone (MIC), and when the device where the audio component is located is in an operating mode, such as call mode, recording mode, and voice recognition mode, the microphone is configured to receive external audio signals. The received audio signal can be further stored in a memory or sent via a communication component. In some embodiments, the audio component also includes a speaker for outputting audio signals.

[0201] Accordingly, an embodiment of the present 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 above method embodiment. The computer-readable storage medium includes volatile or non-volatile or a combination thereof, and may be removable or non-removable. Examples of computer-readable storage media include, but are not limited to, phase-change random access memory (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), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), flash memory or other memory technology, CD-ROM, digital versatile disc (DVD) or other optical storage, magnetic cassette, tape disk storage or other magnetic storage device or any other non-transmission medium.

[0202] Accordingly, an embodiment of the present application further provides a computer program product, which includes a computer program or instructions, and when the computer program or instructions are executed by a processor, the processor is enabled to implement the steps in the above-mentioned method embodiment. It should be understood that each process or a combination of multiple processes in the above-mentioned method flow can be implemented by a computer program or instruction. In addition, these computer programs or instructions can be applied to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device, so that the processor of the general-purpose computer, the special-purpose computer, the embedded processor or other programmable data processing device can be implemented as a device for implementing the corresponding functions in the above-mentioned method embodiment.

[0203] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0204] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0205] Finally, it should be noted that the above are merely examples of the present application and are not intended to limit the present application. Various modifications and variations are possible for those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application are intended to be included within the scope of the claims of the present application.

Claims

1. An information search method, characterized in that: Applied to the server, including: Sending intelligent service prompt information for the target rental type to the user terminal so that the user terminal displays the intelligent service prompt information; In response to an intelligent service request sent by the user terminal, establishing a session connection with the user terminal; the intelligent service request is generated in response to a triggering operation of the intelligent service prompt information; Based on the session connection, sending at least one demand inquiry message for the target lease type to the user terminal, and obtaining at least one reply message fed back by the user terminal for the at least one demand inquiry message; Determining, using an artificial intelligence model, a plurality of lease requirements for the target lease type based on the at least one reply message; Determining a search weight corresponding to each of the plurality of rental demands; Determine a target weight threshold and perform the following search operation; the search operation includes: based on at least one rental demand whose search weight is greater than or equal to the target weight threshold, find whether there is at least one first rental object that meets the at least one rental demand; If not, increase the target weight threshold and re-execute the search operation; If so, then based on the session connection, the relevant information of the at least one first leased object is fed back to the user terminal so that the user terminal displays the relevant information of the at least one first leased object.

2. The method according to claim 1, characterized in that The searching, based on at least one rental demand having a search weight greater than or equal to the target weight threshold, for whether there is at least one first rental object that meets the at least one rental demand comprises: Determining a search method corresponding to each of the at least one rental demand based on a matching relationship between the at least one rental demand having a search weight greater than or equal to the target weight threshold and a plurality of preset demands; the search method including precise search and / or fuzzy search; According to the search method corresponding to each of the at least one rental requirements, it is searched whether there is at least one first rental object that meets the at least one rental requirement.

3. The method according to claim 2, characterized in that The determining of the search method corresponding to each of the at least one rental demand based on the matching relationship between the at least one rental demand having a search weight greater than or equal to the target weight threshold and the plurality of preset demands includes: For any rental demand with a search weight greater than or equal to the target weight threshold, if there is a matching relationship between the rental demand and the preset demand, determining that the search mode corresponding to the rental demand is a precise search; If there is no matching relationship between the rental requirement and the multiple preset requirements, it is determined that the search method corresponding to the rental requirement is fuzzy search.

4. The method according to claim 3, characterized in that If there is a matching relationship between the rental demand and the preset demand, determining that the search method corresponding to the rental demand is a precise search includes: If there is a matching relationship between the rental demand and at least two preset demands, using the artificial intelligence model to determine confirmation of the inquiry information based on the at least two preset demands with a matching relationship; Sending the confirmation inquiry information to the user terminal, and obtaining the demand confirmation information fed back by the user terminal in response to the confirmation inquiry information; The rental demand is adjusted based on the demand confirmation information, and the search mode corresponding to the adjusted rental demand is determined to be a precise search.

5. The method according to claim 2, characterized in that Searching, according to the search method corresponding to each of the at least one rental requirements, whether there is at least one first rental object that meets the at least one rental requirement includes: Based on the preset search intent corresponding to the candidate rental objects, searching whether there is at least one pre-screened rental object that meets the rental requirements corresponding to the fuzzy search method; If so, based on the matching relationship between the relevant information of the initially screened rental objects and the rental requirements corresponding to the fuzzy search method, it is checked whether there is at least one first rental object that meets the rental requirements corresponding to the fuzzy search method.

6. The method according to claim 1, wherein Also includes: If there is no at least one first rental object that meets the at least one rental requirement, and the target weight threshold reaches a preset value, stopping the search operation; Feedback search failure prompt information to the user end.

7. The method according to claim 1, characterized in that The sending of intelligent service prompt information for the target rental type to the user terminal includes: Receiving an information search request sent by a user terminal for a target rental type; the information search request includes at least one search condition; searching for a second rental object that meets the at least one search condition; The relevant information of the second lease object and the intelligent service prompt information of the lease type are sent to the user terminal, so that the user terminal displays the relevant information of the second lease object and the intelligent service prompt information on the search list interface.

8. The method according to claim 7, characterized in that The sending, based on the session connection, at least one demand inquiry message for the target lease type to the user terminal, and obtaining at least one reply message fed back by the user terminal for the at least one demand inquiry message includes: generating, using an artificial intelligence model, current demand inquiry information for the target rental type based on at least one search condition in the information search request; Based on the session connection, the current demand inquiry information is sent to the user terminal, and current reply information fed back by the user terminal in response to the current demand inquiry information is obtained; Determine whether necessary requirement information is missing based on the current response information; If it is missing, the artificial intelligence model is used to generate new current demand query information based on the missing necessary demand information, and the current demand query information is continued to be sent to the user end based on the session connection until the necessary demand information is not missing.

9. The method according to claim 1, characterized in that Feedback of the relevant information of the at least one first leased object to the user terminal based on the session connection includes: Based on the session connection, sending object viewing prompt information to the user terminal; the object viewing prompt information is used to prompt viewing relevant information of the at least one first leased object; In response to the viewing confirmation information fed back by the user terminal, information related to the at least one first leased object is fed back to the user terminal based on the session connection; the viewing confirmation information is generated in response to a triggering operation of the object viewing prompt information.

10. The method according to claim 1 or 9, characterized in that The relevant information of the first leased object includes communication prompt information; the method further includes: In response to the communication request sent by the user terminal, a communication connection is established; the communication connection is used for a conversation between a corresponding user of the user terminal and a provider of the first rental object; the communication request is generated in response to a triggering operation of the communication prompt information.

11. The method according to claim 1, characterized in that Also includes: When the secondary recommendation condition is met, if a new rental object event is detected, the target weight threshold is determined again and the following search operation is performed to obtain at least one new first rental object; Based on the session connection, relevant information of the new at least one first leased object is fed back to the user terminal.

12. The method according to claim 1, characterized in that Also includes: If it is detected that the requirement modification condition is met, sending requirement modification prompt information to the user terminal based on the session connection, and obtaining requirement modification information fed back by the user terminal in response to the requirement modification prompt information; The artificial intelligence model is used to redetermine multiple rental requirements for the target rental type based on the at least one reply message and the requirement modification information, and the search weight corresponding to each of the multiple rental requirements is further determined.

13. The method according to claim 12, characterized in that The sending the requirement modification prompt information to the user terminal based on the session connection includes: Determining a demand modification reason based on multiple rental demands of the target rental type using the artificial intelligence model, and determining demand modification prompt information based on the demand modification reason; Based on the session connection, a requirement modification prompt message is sent to the user terminal.

14. An information search method, characterized in that: Applied to the user side, including: receiving intelligent service prompt information for the target rental type sent by the server, and displaying the intelligent service prompt information; In response to a triggering operation for the intelligent service prompt information, sending an intelligent service request to the server so that the server establishes a session connection with the user terminal; Based on the session connection, receiving at least one demand inquiry information for the target lease type sent by the server, and displaying the at least one demand inquiry information; Obtaining at least one reply message for the at least one demand inquiry message; Based on the session connection, the at least one reply message is sent to the server, so that the server uses an artificial intelligence model to determine multiple rental requirements for the target rental type based on the at least one reply message; determine a search weight corresponding to each of the multiple rental requirements; determine a target weight threshold and perform the following search operation; the search operation includes: based on at least one rental requirement whose search weight is greater than or equal to the target weight threshold, searching whether there is at least one first rental object that meets the at least one rental requirement; if not, increasing the target weight threshold and re-performing the search operation; if so, feeding back relevant information of the at least one first rental object to the user terminal based on the session connection; Based on the session connection, relevant information of the at least one first leased object is acquired and displayed.

15. An information search device, characterized in that: Configuration on the server side includes: A first sending module is configured to send intelligent service prompt information for a target rental type to a user terminal so that the user terminal displays the intelligent service prompt information; a session establishing module, configured to establish a session connection with the user terminal in response to an intelligent service request sent by the user terminal; the intelligent service request is generated in response to a triggering operation of the intelligent service prompt information; The first sending module is further configured to send at least one demand inquiry information for the target lease type to the user terminal based on the session connection; A first receiving module is configured to obtain at least one reply message fed back by the user terminal in response to the at least one demand inquiry message; a demand determination module, configured to determine, by using an artificial intelligence model and based on the at least one reply message, a plurality of rental demands for the target rental type; A weight determination module, configured to determine a search weight corresponding to each of the plurality of rental demands; The object search module is configured to determine a target weight threshold and perform the following search operation; the search operation includes: based on at least one rental demand having a search weight greater than or equal to the target weight threshold, searching for at least one first rental object that meets the at least one rental demand; if not, increasing the target weight threshold and re-performing the search operation; The first sending module is further configured to, if present, feed back relevant information of the at least one first leased object to the user terminal based on the session connection, so that the user terminal displays relevant information of the at least one first leased object.

16. An information search device, characterized in that: Configuration on the user side includes: The second receiving module is used to receive the intelligent service prompt information for the target rental type sent by the server; A display module, configured to display the intelligent service prompt information; A second sending module is configured to send an intelligent service request to the server in response to a triggering operation on the intelligent service prompt information, so that the server establishes a session connection with the user terminal; The second receiving module is further configured to receive, based on the session connection, at least one demand inquiry information for the target rental type sent by the server; The display module is further configured to display the at least one demand inquiry information; An information acquisition module, configured to acquire at least one reply message for the at least one demand inquiry message; The second sending module is further configured to send the at least one reply message to the server based on the session connection, so that the server can use the artificial intelligence model to determine multiple rental requirements for the target rental type based on the at least one reply message; determine a search weight corresponding to each of the multiple rental requirements; determine a target weight threshold and perform the following search operation; the search operation includes: based on at least one rental requirement having a search weight greater than or equal to the target weight threshold, searching for at least one first rental object that meets the at least one rental requirement; if not, increasing the target weight threshold and re-performing the search operation; if so, feeding back relevant information of the at least one first rental object to the user based on the session connection; The second receiving module is further configured to obtain relevant information of the at least one first leased object based on the session connection; The display module is further configured to display relevant information of the at least one first rental object.

17. A computing device, characterized in that including processing components and storage components; The storage component stores a computer program; the computer program is used to be called and executed by the processing component to implement the information search method according to any one of claims 1 to 14.

18. A computer-readable storage medium, characterized in that A computer program is stored thereon, and when the computer program is executed by the processing component, the information search method according to any one of claims 1 to 14 is implemented.

19. A computer program product, characterized in that The method comprises a computer program or an instruction, which implements the information search method according to any one of claims 1 to 14 when the computer program or the instruction is executed by the processing component.

Images