House inspection interaction information processing method and medium

Abstract

The embodiment of the invention relates to a processing method of house seeing interaction information and a medium, and the method comprises the steps: determining house seeing stage information of a house buying user in response to a house seeing problem sent by the house buying user; determining an intention keyword according to the house seeing stage information and the house seeing problem; determining question answering information and model tags corresponding to the intention keywords; and outputting question answering information, and rendering an animation effect according to the cell model data corresponding to the model label. According to the technical scheme, the comprehensiveness of the house seeing interaction information and the consistency of the house seeing interaction information and the personalized requirements of the user are improved, and the accuracy and intuition of displaying the house seeing interaction information are improved.

Description

Technical Field

[0001] This disclosure relates to the field of communication technology, and in particular to a method and medium for processing interactive information related to house viewing. Background Technology

[0002] In the context of house hunting, providing information recommendations to users has become a mainstream demand, such as offering answers to users' questions.

[0003] In related technologies, multiple preset house-viewing interactive questions are provided on the relevant interactive devices. After a user triggers a relevant house-viewing interactive question, the preset answer is displayed to the user. This method of providing house-viewing interactive information results in insufficient information and fails to meet the personalized needs of users. Summary of the Invention

[0004] In order to solve the above-mentioned technical problems, or at least partially solve the above-mentioned technical problems, this disclosure provides a method and medium for processing viewing interaction information.

[0005] This disclosure provides a method for processing viewing interaction information. The method includes: in response to receiving a viewing question sent by a homebuyer, determining the viewing stage information of the homebuyer; determining intent keywords based on the viewing stage information and the viewing question; determining question answer information and model tags corresponding to the intent keywords; outputting the question answer information, and rendering animation effects based on community model data corresponding to the model tags.

[0006] This disclosure also provides a device for processing viewing interaction information, the device comprising: a first determining module, configured to determine the viewing stage information of the homebuyer in response to receiving a viewing question sent by the homebuyer; a second determining module, configured to determine intent keywords based on the viewing stage information and the viewing question; a third determining module, configured to determine question answer information and model tags corresponding to the intent keywords; and a display processing module, configured to output the question answer information and render animation effects based on the community model data corresponding to the model tags.

[0007] This disclosure also provides an electronic device, the electronic device comprising: a processor; a memory for storing executable instructions of the processor; the processor being configured to read the executable instructions from the memory and execute the instructions to implement the method for processing house viewing interactive information as provided in this disclosure.

[0008] This disclosure also provides a computer-readable storage medium storing a computer program for executing the method for processing viewing interaction information as provided in this disclosure.

[0009] The technical solution provided in this disclosure has the following advantages compared with the prior art: The property viewing interaction information processing scheme provided in this disclosure responds to receiving property viewing questions sent by homebuyers, determines the homebuyer's property viewing stage information, determines intent keywords based on the property viewing stage information and the property viewing questions, determines the question-answer information and model tags corresponding to the intent keywords, and then outputs the question-answer information and renders animation effects based on the community model data corresponding to the model tags. This technical solution improves the comprehensiveness of property viewing interaction information and its consistency with user needs, as well as the accuracy and intuitiveness of the displayed property viewing interaction information. Attached Figure Description

[0010] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and the originals and elements are not necessarily drawn to scale.

[0011] Figure 1 A flowchart illustrating a method for processing interactive information related to house viewing provided in an embodiment of this disclosure; Figure 2 This is a schematic diagram illustrating a scenario for displaying interactive information related to house viewing, provided in an embodiment of this disclosure. Figure 3 This is a schematic diagram of the structure of a device for processing interactive information about house viewing provided in an embodiment of the present disclosure; Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0012] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0013] It should be understood that the steps described in the method embodiments of this disclosure may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of this disclosure is not limited in this respect.

[0014] The term "comprising" and its variations as used herein are open-ended inclusions, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the description below.

[0015] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0016] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0017] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0018] To address the aforementioned issues, this disclosure provides a method for processing viewing interaction information, which will be described below with reference to specific embodiments.

[0019] Figure 1 This is a flowchart illustrating a method for processing viewing interaction information according to an embodiment of this disclosure. The method can be executed by a device for processing viewing interaction information, which can be implemented using software and / or hardware, and is generally integrated into an electronic device. Figure 1 As shown, the method includes: Step 101: In response to receiving the viewing questions sent by the homebuyer, determine the homebuyer's viewing stage information.

[0020] In one embodiment of this disclosure, the homebuyer's questions about viewing properties are obtained, wherein the input method for the questions can be any form such as text or voice.

[0021] It should be noted that the methods for obtaining homebuyers' questions about viewing properties differ in different application scenarios, as shown in the following examples: In some possible embodiments, the system acquires homebuyers' questions about viewing properties, inputted via voice or text through an interactive interface. That is, in this embodiment, the platform provides an interactive interface through which homebuyers can input their questions about viewing properties via voice or text; and / or, In some possible embodiments, a list of questions of interest is recommended to homebuyers based on user profiles and viewing stage information, and the homebuyers select the viewing questions to be consulted from the question list. That is, in this embodiment, a question library is pre-set, which includes reference user profile information and reference viewing stage information. Two preset questions are selected from the question library and recommended to the user in the form of a question list. The reference viewing stage information of the questions in the question list is consistent with the homebuyers' viewing stage information, and the similarity between the reference user profile information of the questions and the homebuyers' user profile is greater than a preset similarity threshold.

[0022] Users are concerned with different issues when viewing a house at different stages of the viewing process. For example, the viewing process can be divided into multiple stages, and the information they care about about the house will be different at each stage. The viewing stages can be divided by time or by the frequency of viewings.

[0023] For example, when first learning about a property, users will focus on surrounding amenities, industrial planning, parking conditions, and other related issues. This viewing phase involves a longer period of time. After gaining some understanding, the focus shifts to key differences from surrounding communities, the availability of reasonably priced properties in the community, and the building where those properties are located. Therefore, in this embodiment, the viewing phase information for homebuyers is determined. The method for dividing the viewing phase information can be set according to the scenario, such as "1 viewing phase" (this phase is the initial viewing), "3 or fewer viewings" (this phase is the viewing phase where some understanding has been gained), and "3 or more viewings" (this phase is the viewing phase where the homebuyer has fully understood the relevant information about the property).

[0024] It should be noted that the methods for determining the viewing stage information of homebuyers differ in different application scenarios. For example, in some possible embodiments, multiple candidate viewing stage options are directly displayed on the terminal device, and the candidate viewing stage selected by the homebuyer is obtained as the viewing stage information.

[0025] In some possible implementations, a user profile is generated based on the user's authorized operation data, and the user profile is analyzed to determine the user's current viewing stage information.

[0026] In this embodiment, a user profile is generated based on the operation data authorized by the homebuyer. This operation data can be the user's actions on the property viewing interaction information display platform. The authorized operation data includes: basic user information (e.g., gender, identity, occupation), home purchase intention information (e.g., budget, location), content interaction information (including user interaction information on the corresponding interaction platform, which may include voice interaction information, text interaction information, etc.), lifestyle preference information (e.g., user lifestyle preference information summarized based on daily commute time and location, such as preferred surrounding amenities, preferred properties, preferred community density, etc.), voice interaction information (including chat interaction information on the corresponding display platform), and audio input information (this audio input information refers to...). Users can input operation data via recording, including recordings of their intention to purchase a property. This includes at least one or more of these information combinations. In this embodiment, the authorized operation data of the home-buying user is analyzed to extract first data related to the time dimension and second data unrelated to the time dimension. That is, some operation data is related to the time dimension; for example, the aforementioned lifestyle preference information may be related to the time dimension. For instance, if a user likes to go to a breakfast shop at 8 am, then the time dimension corresponding to the user's preference information is 8 am. Thus, the first data ensures that subsequent property viewing interaction information can be upgraded from static information recommendation to more user-friendly and practically useful information. In this embodiment, some operation data (second data) is unrelated to the time dimension; for example, the aforementioned user basic information is unrelated to the time dimension.

[0027] In the embodiments of this disclosure, a first user profile related to the time dimension is generated based on first data, and a second user profile unrelated to the time dimension is generated based on second data, and a user profile is generated based on the first user profile and the second user profile.

[0028] In this embodiment, the user profile is analyzed to determine the user's current house viewing stage information. The house viewing stage information includes stages such as first house viewing, house viewing for one unit of time, house viewing for two units of time, etc. Each unit of time can be customized, for example, each unit of time can be customized to three months.

[0029] It should be noted that the methods for analyzing user profiles to determine a user's current stage of the house-hunting process differ in different application scenarios, as shown in the following examples: In some possible embodiments, the user profile includes associated information corresponding to the house viewing stage information. For example, if the content interaction information corresponding to the user profile information includes: "This is my first time viewing a house", then the house viewing stage information can be determined directly based on the associated information contained in the user profile.

[0030] In some possible embodiments, user profile information can be input into a pre-trained deep learning model. This deep learning model is pre-trained to obtain corresponding house viewing stage information based on the input user profile. In this embodiment, the user profile is input into the deep learning model to obtain the house viewing stage information output by the deep learning model. Since the user profile is obtained based on the analysis of operation data, and the operation data is updated in real time, the house viewing stage information in this embodiment corresponds to the user's operation data in real time.

[0031] Step 102: Determine the intent keywords based on the information from the house viewing stage and the questions asked during the house viewing.

[0032] The keywords related to the intent to view a property can include terms such as "supporting facilities," "property management," and "school district," highlighting the aspects of the property purchase that the user is interested in. In this embodiment, the keywords can be derived from the viewing question and the stage of the viewing process using a pre-trained intent recognition model.

[0033] Step 103: Determine the question answer information and model tags corresponding to the intent keywords.

[0034] The Q&A information includes textual answers to questions about viewing properties. The community model data corresponding to the model tags can be the rendering data of model objects related to the intent keyword. This rendering data can be three-dimensional or two-dimensional. For example, when the intent keyword is "property management," the community model data could correspond to building model data, landscaping model data within the building, and model data of public facilities within the building. The model tags can also be at least one of numbers, letters, or text.

[0035] In one embodiment of this disclosure, a preset cell knowledge base can be queried based on intent keywords to obtain cell content data and model tags corresponding to the intent keywords. The cell knowledge base includes a first mapping relationship between intent keywords and cell content data, and a second mapping relationship between intent keywords and model tags.

[0036] The pre-set community knowledge base includes the correspondence between intent keywords, community content data, and model tags. The community content data can include relevant descriptive content of the community that matches the intent keyword. For example, when the intent keyword is "property management", the community content data is relevant data describing "property management". The relevant data can be "property management is handled by ** company, resident feedback - 24-hour security patrol - timely garbage collection - installation of high-altitude littering camera - regular greening maintenance - access control system upgrade", etc.

[0037] In the embodiments of this disclosure, a cell knowledge base can be pre-constructed, wherein the cell knowledge base includes: a first mapping relationship between intent keywords and cell content data, and a second mapping relationship between intent keywords and model tags. Thus, in this embodiment, the cell content data and model tags corresponding to the intent keywords are obtained by querying the pre-constructed cell knowledge base based on the intent keywords.

[0038] In the embodiments of this disclosure, a first mapping relationship between intent keywords and community content data is pre-stored. For example, if the intent keyword is "property management", the corresponding community content data is "property management is handled by ** company, homeowner feedback - 24-hour security patrol - timely garbage collection - installation of high-altitude littering camera - regular greening maintenance - access control system upgrade". In the embodiments of this disclosure, a second mapping relationship between intent keywords and model tags is also pre-stored. For example, if the intent keyword is "property management", the corresponding model tag is "183370". In this embodiment, based on the pre-stored community content data corresponding to the intent keywords, question answer information is determined. The question answer information can be obtained through secondary editing of the community content data, or it can be the community content data itself. The secondary editing can include a pre-set feedback information module corresponding to each intent keyword. The feedback information template includes some polished descriptive information, such as "Dear future homeowner, regarding the ** issue you are concerned about, our feedback is: ...". Then, the corresponding community content data is filled into the preset position of the community content data in the feedback information template, and the filled feedback information template is given to the user as feedback information.

[0039] In some possible embodiments, a preset community content database is queried to obtain community content data corresponding to the intent keyword. The community content data is then processed and arranged using a pre-trained language model to generate answer information corresponding to the house viewing question. The pre-trained language model can process the community content data into more natural and vivid language expressions. In this embodiment, the text corresponding to the answer information is displayed on the terminal device, and the text is played back simultaneously by voice, thereby realizing the output of the answer information. The terminal device can be any terminal device with user interaction capabilities.

[0040] Step 104: Output the answer information and render the animation effect based on the cell model data corresponding to the model label.

[0041] In one embodiment of this disclosure, question-and-answer information is output, and animation effects are rendered based on the community model data corresponding to the model label. That is, in this embodiment, community model data is also rendered simultaneously, further enhancing the intuitiveness of the question-and-answer information. For example, when the community model data includes community road model data, and the output question-and-answer information contains text related to "property management," model data such as the community's green belts and public facilities are rendered simultaneously based on the community model data, improving the intuitiveness of the display.

[0042] In one embodiment of this disclosure, a preset cell model database is queried to obtain cell model data corresponding to model tags. Then, the corresponding linked real-time model tag is determined based on the playback time of the text corresponding to the question-and-answer information. That is, in this embodiment, the text in the question-and-answer information and the corresponding real-time model tag can be identified. Keywords contained in each model tag can be pre-stored. The text in the question-and-answer information is split into multiple text fragments, and semantic matching is performed between the keywords and text fragments. Model tags with a matching degree greater than a preset matching degree threshold are determined as the model tags matching the text fragment. Thus, in this embodiment, after generating the question-and-answer information, the text in the question-and-answer information can be split into multiple text fragments, and the model tag matching each text fragment is pre-labeled based on the above embodiment. The playback time of the text corresponding to the question-and-answer information can be determined based on the output time and output speed of the output question-and-answer information. This playback time includes the playback time corresponding to each text fragment. Therefore, the corresponding linked real-time model tag is determined based on the playback time of the text corresponding to the question-and-answer information, and the corresponding target model is rendered based on the cell model data corresponding to the real-time model tag, displaying an animation effect corresponding to the text playback time.

[0043] For example, refer to Figure 2 When the text "From the South Gate, walk along Path A for 12 minutes to reach the entrance of ** Metro Station" is played in the Q&A information, the real-time model data of the community corresponding to the playback time can be synchronized at the same time. The community model data is the path model data of "Path A". Thus, the animation effect of the path model data is displayed synchronously. The animation effect in the figure is to highlight the corresponding path.

[0044] It should be noted that in actual implementation, model tags can correspond to multiple types of model data. For example, in some possible embodiments, a preset community model database is queried to obtain community model data corresponding to the model tag. This includes: querying the preset community model database to obtain one or more of the following: point model data corresponding to the point model tag, line model data corresponding to the line model tag, and volume model data corresponding to the volume model tag. Specifically, point model data corresponds to model data of a specific location point, such as model data of property management companies, schools, or supermarkets. Line model data corresponds to model data of lines formed by multiple consecutive coordinate points, such as model data of linear objects like roads or paths. Volume model data corresponding to a volume model tag corresponds to model data of a set of location point clouds, such as model data of a community or park composed of a set of location point clouds.

[0045] The display methods for various model data corresponding to model labels can differ. For example, point model data can be displayed with a blinking effect, line model data with a continuously highlighted effect, and volume model data with a dynamic animation. Different display methods allow homebuyers to intuitively understand various types of model data.

[0046] In some possible embodiments, when the real-time model label is a line model label, the corresponding target model is rendered based on the cell model data corresponding to the real-time model label. This includes: directly calling the map API to obtain the coordinate data of the path based on the pre-stored path corresponding to the line model label, and highlighting the target path model corresponding to the coordinate data connection on the map; or, passing the starting coordinates and ending coordinates corresponding to the line model label through the API call process, calculating and returning the coordinate data set of the corresponding target path model through the map API, and highlighting the target path model on the map based on the coordinate data set, thus enabling the real-time calculation and display of the target path model.

[0047] In some possible embodiments, after rendering the animation effects corresponding to the pre-stored cell model data corresponding to the model labels and the Q&A information, user actions such as label clicking and / or model dragging can be identified during the animation display using multi-point sensing technology. The labels clicked by the user can be any displayed model label, and the animation effects can be displayed in a media-free holographic imaging device. Thus, the multi-point sensing technology of the media-free holographic imaging device is used to identify user actions such as label clicking and / or model dragging. Furthermore, corresponding user interest points are obtained based on the user actions. User interest points can include the aforementioned lifestyle preference information, etc. User interest points reflect the points of interest that the user determines through the clicks or user actions. For example, if the user clicks on "breakfast shop," the user interest point is determined to be "nearby amenities information." Similarly, if the user's dragging action is a zoom-in action, and the zoomed-in object is "breakfast shop," the user interest point is determined to be "nearby amenities information," and so on.

[0048] One way to determine user interests based on user actions is to identify the attention model corresponding to the user action. For example, the model corresponding to a clicked tag can be used as the action model object, or the model dragged by the user can be used as the attention model.

[0049] In summary, the method for processing viewing interaction information according to this embodiment responds to receiving viewing questions sent by homebuyers, determines the viewing stage information of the homebuyers, determines intent keywords based on the viewing stage information and viewing questions, determines the question-answer information and model tags corresponding to the intent keywords, and then outputs the question-answer information and renders animation effects based on the community model data corresponding to the model tags. This technical solution improves the comprehensiveness of viewing interaction information and its consistency with user needs, and also enhances the accuracy and intuitiveness of the displayed viewing interaction information.

[0050] To implement the above embodiments, this disclosure also proposes a device for processing viewing interaction information.

[0051] Figure 3 This is a schematic diagram of the structure of a property viewing interaction information processing device according to an embodiment of the present disclosure, as shown below. Figure 3 As shown, the device for processing viewing interaction information includes: a first determining module 310, a second determining module 320, a third determining module 330, and a display processing module 340, wherein, The first determining module 310 is used to determine the homebuyer's home viewing stage information in response to receiving the home viewing questions sent by the homebuyer; The second determination module 320 is used to determine intent keywords based on information from the house viewing stage and questions asked during the house viewing. The third determination module 330 is used to determine the question answer information and model labels corresponding to the intent keywords; The display processing module 340 is used to output question answer information and render animation effects based on the cell model data corresponding to the model label.

[0052] The device for processing viewing interaction information provided in this disclosure can execute the method for processing viewing interaction information provided in any embodiment of this disclosure, and has the corresponding functional modules and beneficial effects for executing the method.

[0053] In some implementations, the first determining module 310 is configured to: User profiles are generated based on the authorized operation data of homebuyers, and user profiles are analyzed to determine the current stage of homebuying for each user. The second determining module 320 is specifically used for: Based on a pre-trained intent recognition model, intent analysis is performed on house viewing questions and house viewing stage information to generate intent keywords corresponding to house viewing questions and house viewing stage information.

[0054] In some implementations, the first determining module 310 is configured to: Analyze the authorized operation data of homebuyers to extract primary data related to the time dimension and secondary data unrelated to the time dimension. The operation data authorized by homebuyers includes at least one or a combination of multiple types of information, such as basic user information, homebuying intention information, content interaction information, lifestyle preference information, voice interaction information, and recorded input information. A first user profile related to the time dimension is generated based on the first data, and a second user profile unrelated to the time dimension is generated based on the second data. User profiles are generated based on the first user profile and the second user profile.

[0055] In some implementations, the third determining module 330 is used for: The system queries a pre-defined community knowledge base based on intent keywords to obtain community content data and model tags corresponding to the intent keywords. The community knowledge base includes a first mapping relationship between intent keywords and community content data, and a second mapping relationship between intent keywords and model tags. The system then determines the answer information based on the community content data.

[0056] In some implementations, the third determining module 330 is used for: By using a pre-trained language model to organize and process the community content data, question-and-answer information corresponding to house viewing questions is generated; The display processing module 340 is used to display the text corresponding to the question and answer information on the terminal device, and simultaneously play the question and answer information by voice.

[0057] In some embodiments, the display processing module 340 is used for: Query the preset cell model database to obtain cell model data corresponding to the model labels; The corresponding real-time model label is determined based on the playback time of the text corresponding to the question and answer information. The target model is then rendered based on the cell model data corresponding to the real-time model label, and the animation effect corresponding to the playback time of the text is displayed.

[0058] In some embodiments, the display processing module 340 is used for: Query the preset community model database to obtain one or more of the following data: point model data corresponding to point model labels, line model data corresponding to line model labels, and volume model data corresponding to volume model labels.

[0059] In some implementations, the real-time model label is a line model label, and the display processing module 340 is used for: Based on the pre-stored path corresponding to the line model label, the map API is directly called to obtain the coordinate data of the path, and the target path model corresponding to the coordinate data is highlighted on the map. or, The API call process takes the starting and ending coordinates corresponding to the line model label as input, calculates and returns the coordinate data set of the target path model through the map API, and highlights the target path model on the map based on the coordinate data set.

[0060] In some embodiments, the device further includes a user profile update module, used for: During the animation presentation, multi-point sensing technology is used to identify user actions such as tag clicks and / or model dragging. Identify user interests based on user actions; Update the user profile of homebuyers based on their interests.

[0061] To implement the above embodiments, this disclosure also proposes a computer program product, including a computer program / instruction, which, when executed by a processor, implements the method for processing house viewing interaction information in the above embodiments.

[0062] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure.

[0063] The following is a detailed reference. Figure 4The diagram illustrates a structural schematic suitable for implementing the electronic device 400 in the embodiments of this disclosure. The electronic device 400 in the embodiments of this disclosure may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 4 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0064] like Figure 4 As shown, electronic device 400 may include a processor (e.g., central processing unit, graphics processor, etc.) 401, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 402 or a program loaded from memory 408 into random access memory (RAM) 403. RAM 403 also stores various programs and data required for the operation of electronic device 400. Processor 401, ROM 402, and RAM 403 are interconnected via bus 404. Input / output (I / O) interface 405 is also connected to bus 404.

[0065] Typically, the following devices can be connected to I / O interface 405: input devices 406 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 407 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; memory devices 408 including, for example, magnetic tapes, hard disks, etc.; and communication devices 409. Communication device 409 allows electronic device 400 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 4 An electronic device 400 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively.

[0066] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication device 409, or installed from memory 408, or installed from ROM 402. When the computer program is executed by processor 401, it performs the functions defined in the method for processing viewing interaction information according to embodiments of this disclosure.

[0067] It should be noted that the computer-readable medium described in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0068] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0069] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0070] The aforementioned computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to perform the aforementioned method for processing house viewing interaction information.

[0071] Electronic devices can be programmed with computer program code in one or more programming languages ​​or combinations thereof to perform the operations of this disclosure. These programming languages ​​include, but are not limited to, object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as "C" or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0072] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0073] The units described in the embodiments of this disclosure can be implemented in software or hardware. The names of the units are not, in some cases, intended to limit the specific unit.

[0074] The functions described above in this document can be performed at least in part by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), and so on.

[0075] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0076] The above description is merely a preferred embodiment of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features disclosed in this disclosure that have similar functions.

[0077] Furthermore, while the operations are described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or in a sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of this disclosure. Certain features described in the context of individual embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

[0078] Although the subject matter has been described using language specific to structural features and / or methodological logic, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are merely illustrative examples of implementing the claims.

Claims

1. A method for processing interactive information related to house viewing, characterized in that, include: In response to receiving a homebuyer's inquiry about property viewing, determine the homebuyer's property viewing stage information; Determine intent keywords based on the information about the house viewing stage and the questions asked during the house viewing. Determine the question-answer information and model tags corresponding to the intent keywords; Output the answer to the question and render the animation effect based on the cell model data corresponding to the model label.

2. The method as described in claim 1, characterized in that, The process of determining the homebuyer's property viewing stage information includes: A user profile is generated based on the authorized operation data of the homebuyer, and the user profile is analyzed to determine the current house-hunting stage information of the homebuyer. The step of determining intent keywords based on the viewing stage information and the viewing questions includes: Based on a pre-trained intent recognition model, intent analysis is performed on the house viewing question and the house viewing stage information to generate intent keywords corresponding to the house viewing question and the house viewing stage information.

3. The method as described in claim 2, characterized in that, User profiles are generated based on the user's authorized action data, including: The operation data authorized by the homebuyer was analyzed to extract first data related to the time dimension and second data unrelated to the time dimension. The operation data authorized by the homebuyer includes at least one or a combination of multiple types of information, such as basic user information, homebuying intention information, content interaction information, lifestyle preference information, voice interaction information, and audio input information. A first user profile related to the time dimension is generated based on the first data, and a second user profile unrelated to the time dimension is generated based on the second data; A user profile is generated based on the first user profile and the second user profile.

4. The method as described in claim 1, characterized in that, The process of determining the question-answer information and model tags corresponding to the intent keyword includes: Based on the intent keyword, a preset cell knowledge base is queried to obtain cell content data and model tags corresponding to the intent keyword. The cell knowledge base includes a first mapping relationship between intent keywords and cell content data, and a second mapping relationship between intent keywords and model tags. The answer information for the question is determined based on the content data of the community.

5. The method as described in claim 4, characterized in that, The step of determining the answer information based on the cell content data includes: The community content data is processed and arranged using a pre-trained language model to generate question-and-answer information corresponding to the house viewing questions. The output of the question answer information includes: The terminal device displays text corresponding to the question and answer information, and simultaneously plays the question and answer information aloud.

6. The method according to any one of claims 1-5, characterized in that, The step of rendering animation effects based on cell model data corresponding to the model label includes: Query the preset cell model database to obtain cell model data corresponding to the model label; The corresponding real-time model tag is determined based on the playback time of the text corresponding to the question and answer information, and the corresponding target model is rendered based on the cell model data corresponding to the real-time model tag, displaying the animation effect corresponding to the playback time of the text.

7. The method as described in claim 6, characterized in that, The step of querying a preset cell model database to obtain cell model data corresponding to the model label includes: Query the preset community model database to obtain one or more of the following data: point model data corresponding to point model labels, line model data corresponding to line model labels, and volume model data corresponding to volume model labels.

8. The method as described in claim 7, characterized in that, The real-time model labels are line model labels. The step of rendering the target model based on the cell model data corresponding to the real-time model label includes: The map API is directly called to obtain the coordinate data of the path based on the pre-stored path corresponding to the line model label, and the target path model corresponding to the connection with the coordinate data is highlighted on the map. or, The starting point and ending point coordinates corresponding to the line model label are passed in through the API call process. The coordinate data set of the corresponding target path model is calculated and returned through the map API. The target path model is highlighted on the map based on the coordinate data set.

9. The method according to any one of claims 1-5, characterized in that, After rendering the animation effect based on the cell model data corresponding to the model label, the method further includes: During the animation presentation, multi-point sensing technology is used to identify user actions such as tag clicks and / or model dragging. Obtain the corresponding user interest points based on the user actions; The user profile of the homebuyer is updated based on the user's interests.

10. A computer program product, characterized in that, The system includes a computer program that, when executed by a processor, implements the method for processing viewing interaction information as described in any one of claims 1-9.

Images