A house rental adaptation system and method based on virtual reality technology
Through virtual reality technology and digital twin models, the problem that tenants find it difficult to understand the real situation of the house in house rental is solved, and efficient and personalized house choices are achieved, which improves the rental experience and efficiency.
Patent Information
- Application Number
- CN202410971325.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-19
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2044-07-19
AI Technical Summary
During the existing house rental process, it is difficult for tenants to understand the real situation of the house through static resources, resulting in low selection efficiency, low satisfaction, and inability to meet personalized needs.
Adopt a house rental adaptation system based on virtual reality technology, obtain house data through three-dimensional scanning technology, establish a digital twin model, combine artificial intelligence and big data analysis, and generate virtual scenes, allowing tenants to experience the house in a virtual environment and collect interactive data. Assess the fitness of the house.
It greatly improves the efficiency of house selection, realizes personalized adaptation suggestions, improves the selection experience, can meet the living needs of tenants without a field visit, and provides intelligent and efficient house adaptation services.
Smart Images

Figure CN118521387B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of virtual reality technology, and in particular to a house rental adaptation system and method based on virtual reality technology. Background Art
[0002] House rental is an act that has a long-term impact on the quality of life. There are some problems in the existing house rental process: for example, the traditional house selection process relies on simple descriptions and photos provided by the landlord, and it is difficult for tenants to understand the real situation of the house through static resources, which easily leads to dissatisfaction after renting; the degree of matching between house adaptation and tenant needs is difficult to quantify and evaluate, resulting in low selection efficiency and satisfaction, and often requires multiple on-site visits for comparison, which wastes tenants' time and energy; different tenants attach different importance to house functions, and static descriptions cannot meet personalized needs. An efficient, intelligent, and personalized house rental adaptation solution is urgently needed. Summary of the invention
[0003] Based on the above problems, the present invention proposes a house rental adaptation system and method based on virtual reality technology. Through the scheme of the present invention, tenants can experience the target house through virtual reality without an on-site visit, which greatly improves the selection efficiency, realizes personalized adaptation suggestions, and greatly improves the selection experience.
[0004] In view of this, one aspect of the present invention proposes a house rental adaptation system based on virtual reality technology, including: a cloud server and a VR device; wherein,
[0005] The cloud server is configured as follows:
[0006] Using three-dimensional scanning technology to obtain first three-dimensional data of multiple target houses, second three-dimensional data of a first building where the target houses are located, and third three-dimensional data of all entities within a preset range of the location of the first building;
[0007] Establishing a first digital twin model of the target house according to the first three-dimensional data;
[0008] establishing a second digital twin model of the first building according to the second three-dimensional data;
[0009] Establishing a third digital twin model including three-dimensional information of the first building and all the entities according to the second three-dimensional data and the third three-dimensional data;
[0010] Obtain the rental demand data and historical rental data of the first tenant;
[0011] Determine one or more first target houses from the plurality of target houses according to the rental demand data and the historical rental data;
[0012] Obtaining family member information of the first tenant and establishing a tenant family model;
[0013] In a virtual reality environment, generating a first virtual scene and family member roles of the first target house according to the first digital twin model and the tenant family model corresponding to the first target house;
[0014] Planning a first daily activity content and path for the family member role in the first virtual scene through an artificial intelligence algorithm;
[0015] According to the first daily activity content and path, controlling the family member character in the first virtual scene to experience the virtual layout of the first target house;
[0016] collecting and analyzing first interaction data of the first tenant and the family members in the first virtual scene, evaluating whether the first target house meets the actual living needs of the first tenant's family, and indoor evaluation results;
[0017] Based on the indoor evaluation result, housing adaptation suggestions are provided to the first tenant to assist in decision-making on housing selection.
[0018] Another aspect of the present invention provides a housing rental adaptation method based on virtual reality technology, comprising:
[0019] Using three-dimensional scanning technology to obtain first three-dimensional data of multiple target houses, second three-dimensional data of a first building where the target houses are located, and third three-dimensional data of all entities within a preset range of the location of the first building;
[0020] Establishing a first digital twin model of the target house according to the first three-dimensional data;
[0021] establishing a second digital twin model of the first building according to the second three-dimensional data;
[0022] Establishing a third digital twin model including three-dimensional information of the first building and all the entities according to the second three-dimensional data and the third three-dimensional data;
[0023] Obtain the rental demand data and historical rental data of the first tenant;
[0024] Determine one or more first target houses from the plurality of target houses according to the rental demand data and the historical rental data;
[0025] Obtaining family member information of the first tenant and establishing a tenant family model;
[0026] In a virtual reality environment, generating a first virtual scene and family member roles of the first target house according to the first digital twin model and the tenant family model corresponding to the first target house;
[0027] Planning a first daily activity content and path for the family member role in the first virtual scene through an artificial intelligence algorithm;
[0028] According to the first daily activity content and path, controlling the family member character in the first virtual scene to experience the virtual layout of the first target house;
[0029] Collecting and analyzing first interaction data of the first tenant and the family members in the first virtual scene, evaluating whether the first target house meets the actual living needs of the first tenant's family, and obtaining an indoor evaluation result;
[0030] Based on the indoor evaluation result, housing adaptation suggestions are provided to the first tenant to assist in decision-making on housing selection.
[0031] Optionally, after the step of collecting and analyzing the interaction data of the first tenant and the family members in the first virtual scene to evaluate whether the first target house meets the actual living needs of the first tenant's family, the method further includes:
[0032] generating a second virtual scene corresponding to the first building according to the second digital twin model and the tenant household model;
[0033] Generate a third virtual scene including virtual models of all entities within a preset range of the location of the first building according to the third digital twin model and the tenant household model;
[0034] Simulating a second daily activity content and path of the family member role in the second virtual scene;
[0035] Simulating the third daily activity content and path of the family member role in the third virtual scene;
[0036] According to the second daily activity content and path, controlling the family member character in the second virtual scene to experience the virtual space of the first building;
[0037] According to the third daily activity content and path, controlling the family member character in the third virtual scene to experience the surrounding virtual environment of the first target house;
[0038] Collecting and analyzing second interaction data of the first tenant and the family members in the second virtual scene, evaluating whether the first building meets the actual living needs of the first tenant in the building, and obtaining an evaluation result in the building;
[0039] Collect and analyze the third interaction data of the first tenant and the family members in the third virtual scene, evaluate whether the surrounding facilities of the first target house meet the actual living needs of the first tenant when going out, and obtain the surrounding facilities evaluation result.
[0040] Optionally, the step of obtaining the family member information of the first tenant and establishing the tenant family model includes:
[0041] Obtaining basic information, daily behavior data, medical records, and medical insurance-related data of the first tenant's family members as the family member information;
[0042] De-duplication and format standardization of the family member information;
[0043] Using big data analysis technology and machine learning technology, analyze and mine the behavioral preferences, consumption habits, and health status of family members based on the family members' information, and build an overall family portrait model and individual portrait models of each family member;
[0044] The overall family portrait model and the personal portrait model are used as tenant family models.
[0045] Optionally, the step of generating a first virtual scene of the first target house and family member roles according to the first digital twin model and the tenant family model corresponding to the first target house in the virtual reality environment includes:
[0046] Importing the first digital twin model of the first target house into a virtual environment construction platform to generate a virtual three-dimensional scene of the first target house;
[0047] In the virtual three-dimensional scene, automatically generating family member roles with corresponding numbers and attributes according to the tenant family model;
[0048] Placing furniture and home appliance models that match the layout of the first target house in the virtual three-dimensional scene;
[0049] Based on the activity data of family members, an artificial intelligence algorithm is used to generate the first simulated daily route plan for each family member;
[0050] Using the first simulated daily route planning as a clue, making a first form animation of family members changing over time;
[0051] The virtual three-dimensional scene, the family member roles, the furniture and appliance models, the first simulated daily path planning and the first form animation and voice interaction are integrated to construct a first virtual scene.
[0052] Optionally, the step of planning the first daily activity content and path for the family member role in the first virtual scene by using an artificial intelligence algorithm includes:
[0053] identifying a first member attribute of each family member according to the tenant family model;
[0054] predicting the daily activity pattern of each family member from the big data training sample based on the first member attribute;
[0055] Based on the daily activity patterns, using deep learning algorithms to study the sequence and scene dependency of each daily activity;
[0056] In the first virtual scene, identifying the occurrence areas of various daily activities according to the functional area characteristics;
[0057] Combining the sequence, the scene dependency, and the occurrence area, a path planning algorithm is used to generate an activity path for each family member within a specified time;
[0058] Performing AI simulation in the first virtual scene according to the activity path to generate behavioral action rules for family members;
[0059] The activity path and the action rule are integrated to generate a first daily activity content and path for the family member role in the first virtual scene.
[0060] Optionally, the step of controlling the family member character to experience the virtual layout of the first target house in the first virtual scene according to the first daily activity content and path includes:
[0061] The corresponding family members are equipped with VR devices, and the virtual scene system is imported into the VR devices;
[0062] Constructing the first virtual scene in the virtual scene system;
[0063] Importing the first daily activity content and path corresponding to each family member into the virtual scene system;
[0064] The virtual scene system controls the corresponding behavior and movement path of the family member character in the first virtual scene according to the first daily activity content and path;
[0065] While the family member character is moving in the first virtual scene, a first sub-virtual scene corresponding to the current position of the family member character in the first virtual scene is synchronously displayed in the VR device so that the corresponding family member can experience the virtual layout of the first target house from the perspective of his daily activities.
[0066] Optionally, the step of collecting and analyzing the first interaction data of the first tenant and the family members in the first virtual scene, evaluating whether the first target house meets the actual family living needs of the first tenant, and obtaining an indoor evaluation result includes:
[0067] The family members interact with each other in a scenario-simulated manner through voice and action during the experience of the virtual layout of the first target house, and the virtual scene system records first interaction data of the family members during the interaction process;
[0068] Extracting eye tracking data, facial expression data, voice interaction data, and body behavior data from the first interaction data;
[0069] Use eye tracking data to determine how long and how often family members look at different areas;
[0070] Determine family members' evaluation data on different areas through facial expression data and voice interaction data;
[0071] Use machine learning algorithms to classify viewing time, frequency, and evaluation data and mine habit patterns to obtain virtual experience results;
[0072] Performing a matching evaluation based on the rental demand data and the virtual experience results, and using artificial intelligence to give evaluation scores for multiple indicators;
[0073] Output the total scores of various indicators and give the indoor suitability assessment results.
[0074] Optionally, the step of simulating the third daily activity content and path of the family member role in the third virtual scene includes:
[0075] Determining the peripheral activity types of family members according to the tenant family model;
[0076] According to the surrounding activity types, a plurality of travel routes and regional points are determined using the road network topology;
[0077] According to the first member attribute, simulate the activity opportunity distribution data of the first member on the corresponding surrounding activity type;
[0078] A constraint-based path planning algorithm is applied according to the travel routes and regional points and the activity opportunity distribution data to generate third daily activity content and paths.
[0079] Optionally, the step of controlling the family member character to experience the surrounding virtual environment of the first target house in the third virtual scene according to the third daily activity content and path includes:
[0080] Importing the third daily activity content and path into the virtual scene system of the VR device;
[0081] Constructing the third virtual scene in the virtual scene system;
[0082] Integrate the interactive function of the models of relevant important points of interest and the building model in the surrounding environment of the first target house into the third virtual scene;
[0083] Importing the third daily activity content and path corresponding to each family member into the virtual scene system;
[0084] The virtual scene system controls the corresponding behavior and movement path of the family member role in the third virtual scene according to the third daily activity content and path;
[0085] While the family member character is moving in the third virtual scene, a third sub-virtual scene corresponding to the current position of the family member character in the third virtual scene is synchronously displayed in the VR device so that the corresponding family member can experience the surrounding virtual environment of the first target house from the perspective of his daily activities.
[0086] By adopting the technical solution of the present invention, the house rental adaptation method based on virtual reality technology includes: using three-dimensional scanning technology to obtain first three-dimensional data of multiple target houses, second three-dimensional data of a first building where the target houses are located, and third three-dimensional data of all entities within a preset range of the first building; establishing a first digital twin model of the target house according to the first three-dimensional data; establishing a second digital twin model of the first building according to the second three-dimensional data; establishing a third digital twin model including three-dimensional information of the first building and all the entities according to the second three-dimensional data and the third three-dimensional data; obtaining rental demand data and historical rental data of a first tenant; determining one or more first target houses from the multiple target houses according to the rental demand data and the historical rental data; obtaining the home of the first tenant The method comprises the steps of: collecting and analyzing first interactive data of the first tenant and the family members in the first virtual scene, evaluating whether the first target house meets the actual family life needs of the first tenant, and obtaining indoor evaluation results; and providing housing adaptation suggestions for the first tenant based on the indoor evaluation results to assist in decision-making on housing selection. Through the scheme of the present invention, tenants can experience the target house through virtual reality in advance without an on-site visit, thereby greatly improving the selection efficiency; the real activity trajectory of family members in the house is simulated through intelligent algorithms to more comprehensively restore the future life scene; tenants can manually control the virtual scene for multiple iterations to perform experiential evaluation of each detail of the house; the method collects and analyzes the tenant demand model and virtual scene interaction data to achieve personalized adaptation suggestions; a variety of house layout options are provided for different tenants through intelligent planning; it can evaluate in real time whether the surrounding environment meets various life needs such as travel and medical treatment; the immersive experience brought by virtual reality greatly improves the selection experience; VR technology can be used to achieve smarter and more efficient house adaptation services. BRIEF DESCRIPTION OF THE DRAWINGS
[0087] Figure 1 is a schematic block diagram of a house rental adaptation system based on virtual reality technology provided by an embodiment of the present invention;
[0088] Figure 2 It is a flow chart of a house rental adaptation method based on virtual reality technology provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0089] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.
[0090] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.
[0091] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.
[0092] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.
[0093] Refer to the following Figure 1 to Figure 2 To describe a house rental adaptation system and method based on virtual reality technology provided according to some embodiments of the present invention.
[0094] like Figure 1 As shown, an embodiment of the present invention provides a house rental adaptation system based on virtual reality technology, including: a cloud server and a VR device; wherein,
[0095] The cloud server is configured as follows:
[0096] Using three-dimensional scanning technology to obtain first three-dimensional data of multiple target houses, second three-dimensional data of a first building where the target houses are located, and third three-dimensional data of all entities within a preset range of the location of the first building;
[0097] Establishing a first digital twin model of the target house according to the first three-dimensional data;
[0098] establishing a second digital twin model of the first building according to the second three-dimensional data;
[0099] Establishing a third digital twin model including three-dimensional information of the first building and all the entities according to the second three-dimensional data and the third three-dimensional data;
[0100] Obtain the rental demand data and historical rental data of the first tenant;
[0101] Determine one or more first target houses from the plurality of target houses according to the rental demand data and the historical rental data;
[0102] Obtaining family member information of the first tenant and establishing a tenant family model;
[0103] In a virtual reality environment, generating a first virtual scene and family member roles of the first target house according to the first digital twin model and the tenant family model corresponding to the first target house;
[0104] Planning a first daily activity content and path for the family member role in the first virtual scene through an artificial intelligence algorithm;
[0105] According to the first daily activity content and path, controlling the family member character in the first virtual scene to experience the virtual layout of the first target house;
[0106] collecting and analyzing first interaction data of the first tenant and the family members in the first virtual scene, evaluating whether the first target house meets the actual living needs of the first tenant's family, and indoor evaluation results;
[0107] Based on the indoor evaluation result, housing adaptation suggestions are provided to the first tenant to assist in decision-making on housing selection.
[0108] It should be known that Figure 1 The block diagram of the house rental adaptation system based on virtual reality technology is for illustration only, and the number of modules shown therein does not limit the protection scope of the present invention.
[0109] See also Figure 2 Another embodiment of the present invention provides a house rental adaptation method based on virtual reality technology, comprising:
[0110] Using three-dimensional scanning technology to obtain first three-dimensional data of multiple target houses, second three-dimensional data of a first building where the target houses are located, and third three-dimensional data of all entities within a preset range of the location of the first building;
[0111] In this step, the three-dimensional digital model data of multiple target houses are obtained as the first three-dimensional data; the three-dimensional digital model data of the building (such as a community) where the target house is located is obtained as the second three-dimensional data; the three-dimensional digital model data of all entities within a preset range area near the target house (such as a circular area with the location of the first building as the center and a preset distance as the radius) (such as other buildings, greenery, roads and other ancillary facilities, etc.) are obtained as the third three-dimensional data. Through this step, a complete three-dimensional digital model of the target house and its surrounding environment can be established, which is convenient for restoring the real environment scene of the house and its surroundings in a VR or AR environment, which is conducive to the subsequent visual evaluation of the environmental resources around the house (such as transportation, living facilities, etc.), and provides a real three-dimensional scene basis for the virtual simulation of tenants' travel and life in the area, which is conducive to intelligent planning and optimization of house site selection plans to serve different customer groups; the importance of this step lies in building a complete three-dimensional digital environment of the house and its surroundings.
[0112] Establishing a first digital twin model of the target house according to the first three-dimensional data;
[0113] In this step, the collected first three-dimensional data (such as the three-dimensional scanning point cloud data of the target house) is corrected to remove noise and erroneous data; the point cloud data is divided using a three-dimensional reconstruction algorithm to identify the exterior contour and various structural surfaces of the house; the internal structure of the house and each room are further identified according to the architectural details (such as windows, door openings, etc.); the three-dimensional model of the house is reconstructed and the attribute information of the structural parameters (such as area, apartment type, etc.) is annotated; the model is rendered, the material is assigned, and details (such as furniture, home appliances, etc.) are added to obtain the first digital twin model. This step constructs a high-precision three-dimensional digital model of the target house, restores its real structure, and provides accurate three-dimensional structural data support for the subsequent restoration of the house in a virtual simulation environment. It can be used for intelligent planning of house functional layout, furniture configuration, energy efficiency calculation and other analyses, facilitates the acquisition of various structural attribute information of the house, and assists in real estate digital transactions; the model is continuously updated to achieve a synchronous situation map of the house digital twin.
[0114] establishing a second digital twin model of the first building according to the second three-dimensional data;
[0115] In this step, the second three-dimensional data (such as the three-dimensional scanning point cloud data of the first building) is preprocessed to reduce noise and data volume; the three-dimensional reconstruction algorithm is applied to identify the shape features of the building (such as the shell, floor height, etc.); the building structure surface is extracted from the point cloud data, the building frame is reconstructed, and the building details (such as wall material, window position, elevator, stairs, etc.) are produced; the building attribute information is annotated, such as the floor area, the number of floors, etc.; the rendering model generates the second digital twin model of the first building. This step constructs a high-precision, realistic three-dimensional digital model of the first building, provides complete community environment support for the virtual trial of the house, facilitates the viewing of the building structure and the relative position relationship of the house, facilitates the construction of building visualization analysis (such as sunlight evaluation), provides a digital foundation for intelligent planning and digital management, and helps to build and synchronously update the digital twin of the community.
[0116] Establishing a third digital twin model including three-dimensional information of the first building and all the entities according to the second three-dimensional data and the third three-dimensional data;
[0117] In this step, the second three-dimensional data and the third three-dimensional data of the first building are integrated in the same three-dimensional coordinate system; various entity objects (such as other buildings, roads, stations, subway stations, etc.) in the third three-dimensional data are identified, their shapes and other attributes are extracted, and these entity objects are accurately imported into the three-dimensional model scene according to the real spatial position; fine textures and appearance morphological characteristics are given to all target entities, and environmental details in the scene are improved, such as streets, vegetation, etc.; all records of building and environment-related information are imported into the database, and a third digital twin model including the three-dimensional information of the first building and all entities is established. This step can construct a real three-dimensional surrounding community environment model of the target house, restore the realism of the daily living environment of the house, facilitate the multi-angle visual design and evaluation of the house, provide real three-dimensional scene support for smart applications, realize the digital twin and intelligent management of the house and its surrounding environment, contribute to the digital transformation of real estate service business, and build a real three-dimensional intelligent environment of the house and its surroundings as a whole.
[0118] Obtain the rental demand data and historical rental data of the first tenant;
[0119] In this step, the first tenant's rental demand data (including housing location, structure, layout, area, decoration configuration, lease term, access, medical treatment, schooling, consumption and other needs) and historical rental data (including historical rental housing location, structure, layout, area, decoration status, etc.) are obtained. This step can help understand the tenant's actual rental needs and preference characteristics, provide important reference data for personalized housing recommendations, and predict the user's possible future selection trends; accumulate samples for model training to improve service quality; achieve a closed-loop connection from the tenant demand end to the housing source end, and improve the operating efficiency and conversion rate of the rental platform.
[0120] Determine one or more first target houses from the plurality of target houses according to the rental demand data and the historical rental data;
[0121] In this step, the basic information of multiple target houses (such as location, area, etc.) is entered into the database system; each target house is assigned a matching score in comparison with the rental demand data; a collaborative filtering algorithm is used to combine the tenant's historical selection data to give additional scores; the scores are sorted from high to low, the first few are selected as the first target house, and the machine learning model is used to iteratively evaluate and optimize the house selection results, and one or more houses are returned for the tenant to make further choices. Through this step, the ideal house can be quickly identified according to the individual needs of the tenant, and the results are more accurate considering the tenant's historical preferences, so as to achieve accurate matching between the house and the tenant's needs, and greatly improve the rental efficiency; relying on big data to deeply recommend houses, meet personalization, improve user experience and conversion rate, and realize data-driven intelligent identification of target houses.
[0122] Obtain the family member information of the first tenant and establish a tenant family model (including overall family portrait, individual portraits of each family member, daily activity data, consumption habits, travel data, medical data, etc. of each family member);
[0123] In a virtual reality environment, based on the first digital twin model corresponding to the first target house and the tenant family model, a first virtual scene of the first target house (including generating a virtual experience trajectory, interactive guidance, virtual furniture and appliances, etc. based on historical daily activity data / trajectory) and family member roles are generated;
[0124] Planning a first daily activity content and path for the family member role in the first virtual scene through an artificial intelligence algorithm;
[0125] According to the first daily activity content and path, controlling the family member character in the first virtual scene to experience the virtual layout of the first target house;
[0126] Collecting and analyzing first interaction data of the first tenant and the family members in the first virtual scene, evaluating whether the first target house meets the actual living needs of the first tenant's family, and obtaining an indoor evaluation result;
[0127] Based on the indoor evaluation result, housing adaptation suggestions are provided to the first tenant to assist in decision-making on housing selection.
[0128] In this step, the scores of various indoor evaluation indicators are quantitatively analyzed; the adaptation score of the house is given according to the user demand model and the scoring results; it is judged whether a certain adaptation standard is met and a preliminary recommendation is given; based on the degree of score difference, improvement suggestions or content that needs to be modified are given; specific suggestions on deficiencies are provided with text and visual examples; other alternative housing sources are given for reference and selection according to the degree of adaptation; users can reproduce the modification in the system to achieve verification results. In this step, users can be provided with targeted rental selection references, improve user selection rationality and decision-making ability, help realize the personalization and precision of real estate services, improve the service quality of digital products and user stickiness, and form an intelligent and automated closed loop of the rental process.
[0129] Through the solution of this embodiment, tenants can experience the target house through virtual reality without an on-site visit, which greatly improves the selection efficiency; the real activity trajectory of family members in the house is simulated by intelligent algorithms to more comprehensively restore the future life scene; tenants can manually control the virtual scene for multiple iterations to perform experiential evaluation of each detail of the house; the method collects and analyzes the tenant demand model and virtual scene interaction data to achieve personalized adaptation suggestions; through intelligent planning, a variety of house layout options are provided for different tenants; it can evaluate in real time whether the surrounding environment meets various life needs such as travel and medical treatment; the immersive experience brought by virtual reality greatly improves the selection experience; VR technology can be used to achieve smarter and more efficient house adaptation services.
[0130] In some possible implementations of the present invention, after the step of collecting and analyzing the interaction data of the first tenant and the family members in the first virtual scene to evaluate whether the first target house meets the actual living needs of the first tenant's family, the method further includes:
[0131] generating a second virtual scene corresponding to the first building according to the second digital twin model and the tenant household model;
[0132] In this step, the second digital twin model is imported into the virtual scene construction platform to reconstruct the three-dimensional building model scene; virtual characters of family members with corresponding numbers and attributes are set according to the tenant family model; digital furniture, home appliances and decorative objects are placed in the scene according to the building type; lighting, materials and other environmental effects are added to the virtual scene to simulate the sense of reality; the model is trained based on the attributes and behavioral habits of the members, and the daily activity paths are arranged for each member; animation technology is used to enable the members to move and interact naturally and smoothly in the scene; testing and optimization are carried out, and errors are fixed to ensure the smoothness of the scene and the performance of details. Through this step, a realistic virtual environment of the house can be efficiently reconstructed, the fine features of the building and the details of life can be highlighted, a reliable digital carrier for customers to deeply experience the house can be provided, and the digitalization and intelligence level of the real estate industry can be promoted.
[0133] Generate a third virtual scene including virtual models of all entities within a preset range of the location of the first building according to the third digital twin model and the tenant household model;
[0134] In this step, the building data within the location range is extracted from the third digital twin model, and the three-dimensional models of all physical buildings are rebuilt with modeling software. Environmental data such as streets and roads within the range are collected, and various resource data are integrated to build interactive urban environment scenes. Members and daily activity path planning are set according to the tenant family model, and animation and physical simulation are added to restore the interaction of environmental details, and test optimization is performed to achieve a high-fidelity environmental virtual scene. Through this step, the surrounding real environment can be reproduced to assist in selecting a wider field of vision; provide professional digital decision-making service support; test emerging VR / AR scene modeling and application technologies; help customers comprehensively evaluate the degree of matching of the housing environment; and promote the integrated development of digital and smart real estate services.
[0135] Simulating a second daily activity content and path of the family member role in the second virtual scene;
[0136] In this step, based on the tenant family model, predict the main daily activity types of each member in the house; identify the scene functional areas, such as kitchens, bedrooms and other places where activities may occur; apply the path planning algorithm to arrange the optimal activity path for each member in the scene; arrange the main activity steps of the members in a day in chronological order; set the interaction rules between members, such as dining together or traveling together; add voice or action to each step to define the interaction behavior between members; debug and optimize to ensure high consistency of paths and actions. Through this step, the daily activity patterns of members in the house can be highly restored, helping users to fully understand the family's life simulation in the house, evaluate whether the house meets the family's daily needs, and improve the effectiveness and objectivity of smart house recommendations.
[0137] Simulating the third daily activity content and path of the family member role in the third virtual scene;
[0138] According to the second daily activity content and path, controlling the family member character in the second virtual scene to experience the virtual space of the first building;
[0139] In this step, the second daily activity content and member paths are imported into the VR system, and the roles of each family member are driven into the second virtual scene. The members' behaviors in the scene are automatically controlled according to the planned steps and paths. The members interact with each other through voice and action to reflect the situational interaction, and the behavior details data experienced by users from different members' perspectives are recorded. Users can switch roles at any time to experience different life attitudes, and an online questionnaire is given to collect user improvement suggestions. Through this step, the life details of the members in the room can be fully restored, the functionality of the house can be evaluated from a multi-dimensional perspective, detailed user needs can be collected to improve the scene, and the quality of the selection basis and user participation can be improved.
[0140] According to the third daily activity content and path, controlling the family member character in the third virtual scene to experience the surrounding virtual environment of the first target house;
[0141] Collecting and analyzing second interaction data of the first tenant and the family members in the second virtual scene, evaluating whether the first building meets the actual living needs of the first tenant in the building, and obtaining an evaluation result in the building;
[0142] In this step, we record all kinds of user behavior trajectory data in scene operation, collect eye movement and head position for line of sight analysis, collect key areas for speech expression content evaluation, use machine learning to extract behavioral rules and patterns, judge the degree of matching with the customer demand model, score various indicators, give a preliminary degree of adaptation in the building, output a scoring report, and give feedback for revisions. Through this step, we can comprehensively and quantitatively evaluate the degree of satisfaction of housing resources, collect detailed user needs to improve services, assist customers in scientifically and rationally choosing housing resources, enhance the personalization of smart real estate services, and promote the application of digital carriers in leasing.
[0143] Collect and analyze the third interaction data of the first tenant and the family members in the third virtual scene, evaluate whether the surrounding facilities of the first target house meet the actual living needs of the first tenant when going out, and obtain the surrounding facilities evaluation result.
[0144] In this step, the member's behavior data such as the stay time, sight, selection operation, etc. in each node environment is recorded in the third scene; user evaluations in different scenes are collected through voice, facial expressions, etc.; machine learning algorithms are used to perform pattern recognition on the data and match it with the demand model; satisfaction scores for each related supporting facilities are given according to the degree of matching; the correlation between indicators is analyzed to give a primary surrounding environment adaptation degree assessment; detailed results of the report are output and improvement suggestions are given. Through this step, it is possible to comprehensively evaluate whether the surrounding environment meets life needs, collect personalized user feedback to optimize services, improve the scientific nature of house recommendations and decision-making support capabilities, and promote the application and innovation of VR in real estate services.
[0145] In some possible implementations of the present invention, the step of providing the first tenant with housing adaptation suggestions based on the indoor evaluation results to assist in decision-making on housing selection includes:
[0146] According to the indoor evaluation results, combined with the building evaluation results and the surrounding supporting evaluation results, provide the first tenant with housing adaptation suggestions to assist in decision-making on housing selection, specifically:
[0147] Dynamically adjust different weights of the indoor evaluation result, the building evaluation result and the surrounding supporting evaluation result according to the tenant household model;
[0148] The three evaluation results are standardized and quantified according to indicators;
[0149] Assign weights according to the importance of different assessment areas and establish a scoring model;
[0150] The standardized results are combined according to the weighted scores to calculate the overall fitness score;
[0151] Based on the score results, determine whether the house meets the recommended standard line;
[0152] Add suggestions for improvement, giving the strengths and weaknesses of the house;
[0153] Provide other alternative properties for reference and selection;
[0154] Tenants can reproduce the listing effect in the system and choose the ideal solution.
[0155] The different weights of the indoor evaluation result, the building evaluation result and the surrounding supporting evaluation result are dynamically adjusted according to the tenant household model, specifically:
[0156] Extract features that affect selection preferences from tenant family models, such as family member attributes, daily demand directions, etc.; learn historical tenant selection behavior samples through machine learning models to identify the degree of influence of features and weights; when a new tenant family model is input, input its features into the model for predictive evaluation; the model outputs the relative importance weights of the three evaluation factors in the tenant family; the system automatically adjusts the contribution of the three evaluations to the total score based on the predicted weight results. For example: for families with children, the weight of "surrounding facilities" is increased; for working families, the weight of "transportation" is increased; this can achieve: personalized evaluation standards that are more in line with the actual situation of tenants; improve the quality and reference of selection results; and enhance the professionalism and customization of rental services.
[0157] In this embodiment, a comprehensive and quantitative evaluation can be made on the degree to which housing resources meet customer needs, directional suggestions for the best housing selection can be given, the professionalism and scientificity of user selection decisions can be improved, and this can help promote the personalization and intelligence of real estate services and realize the automation and intelligence of housing matching.
[0158] In some possible implementations of the present invention, the step of obtaining the family member information of the first tenant and establishing a tenant family model includes:
[0159] Obtaining basic information (such as name, age, gender, relationship, etc.) of the first tenant's family members, daily behavior data (including data on multiple scenarios such as travel, consumption, Internet access, and entertainment), medical records, and medical insurance-related data as the family member information;
[0160] De-duplication and format standardization of the family member information;
[0161] Using big data analysis technology and machine learning technology, analyze and mine the behavioral preferences, consumption habits, and health status of family members based on the family members' information, and build an overall family portrait model and individual portrait models of each family member;
[0162] The overall family portrait model and the personal portrait model are used as tenant family models.
[0163] In this embodiment, a comprehensive understanding of family users is achieved, the overall and individual conditions of the family are understood, accurate personalized services are provided to family members, and the quality of life is improved; merchants / service providers are assisted in conducting precise marketing and service matching, and the precise implementation of public services and policies such as medical care and social security is facilitated; the dynamics of family needs are discovered and predicted, and industry optimization and innovation are guided; in general, this technology can achieve all-round and dynamic analysis and modeling of family members, and is the basis for family and individual services.
[0164] In this embodiment, the behavioral habit details of each member of the tenant's household are fully obtained, personalized description and label management of the tenant's household are realized, and the quality of products and services based on household characteristics is effectively improved; a personalized basis is provided for intelligent decision-making; and online and offline data are connected to promote accuracy and personalization.
[0165] In some possible implementations of the present invention, the step of generating a first virtual scene and family member roles of the first target house in a virtual reality environment according to the first digital twin model and the tenant family model corresponding to the first target house includes:
[0166] Importing the first digital twin model of the first target house into a virtual environment construction platform to generate a virtual three-dimensional scene of the first target house;
[0167] In the virtual three-dimensional scene, automatically generating family member roles with corresponding numbers and attributes according to the tenant family model;
[0168] Placing furniture and home appliance models that match the layout of the first target house in the virtual three-dimensional scene;
[0169] Based on the activity data of family members, an artificial intelligence algorithm is used to generate the first simulated daily route plan for each family member;
[0170] Using the first simulated daily route planning as a clue, making a first form animation of family members changing over time;
[0171] The virtual three-dimensional scene, the family member roles, the furniture and appliance models, the first simulated daily path planning and the first form animation and voice interaction are integrated to construct a first virtual scene.
[0172] In this embodiment, the members' daily activities in the house can be highly reproduced, guiding tenants to have a multi-angle real experience, helping to quickly and accurately evaluate whether the house meets their needs, realizing the personalization and intelligence of real estate services, and improving user participation and retention time.
[0173] In some possible implementations of the present invention, the step of planning the first daily activity content and path for the family member role in the first virtual scene by using an artificial intelligence algorithm includes:
[0174] According to the tenant household model, identifying the first member attribute (such as occupation, age, etc.) of each family member;
[0175] According to the first member attribute, predicting the daily activity pattern of each family member from a big data training sample (which can be obtained based on the historical activity data of the family members);
[0176] In this step, family member attribute features that affect daily activities, such as age, gender, etc., are extracted from the big data training samples; family member attributes (first member attributes) are input into the features to construct machine learning model training samples; deep learning algorithms (such as RNN) are applied to learn mining patterns for a large amount of historical daily activity data; a joint distribution model between family member attributes and daily activities is trained. When new family member attributes are input, the model is used to predict the corresponding daily activity pattern distribution, including the probability distribution of the main indicators of the schedule such as activity frequency, time, and location, and personalized activity path arrangements are adopted for different members. In this step, the real activity rules of each member can be restored in a personalized manner, the ability of the simulation scene to reflect the details of life can be improved, and a comprehensive understanding of whether the house meets the needs of the family from a multi-dimensional perspective can be obtained.
[0177] Based on the daily activity patterns, using deep learning algorithms to study the sequence and scene dependency of each daily activity;
[0178] In this step, we can combine daily activity patterns, extract the attribute features of each daily activity from the big data sample, apply sequence model algorithms (such as RNN) to learn and mine the schedule sequence, and identify the probability distribution of subsequent activities at a specific time or scene; use the attention mechanism to highlight the impact of different features on subsequent activities, train the association model of activity sequence and environmental dependence, input new activity patterns, predict their specific time and location, and build a high-fidelity on-site schedule for each member. This step can achieve a highly coherent arrangement of daily activities, restore the authenticity of life details and environmental dependence, fully evaluate whether the house meets the needs of all aspects of the family, and help promote the personalization and intelligence of real estate services.
[0179] In the first virtual scene, identifying the occurrence areas of various daily activities according to the functional area characteristics;
[0180] In this step, the functional areas (such as living room, dining room, kitchen, bathroom, etc.) marked in the plan design in advance are identified and reproduced in the first virtual scene, the spatial structure and decoration characteristics of the functional areas are extracted as classification features, a large number of sample housing areas and daily activity correspondence data are marked, and a machine learning algorithm (such as a decision tree) is applied to train the daily activity positioning model. After the model inputs a new scene, the functional area where each activity occurs is predicted, and regional suggestions are given for reference in the schedule (daily activity schedule). In this step, the preferred activity area is analyzed according to the characteristics of the house to achieve the accuracy and consistency of the schedule; it can be evaluated whether the house structure meets daily needs, and the authenticity and reference value of the simulation scene can be improved.
[0181] Combining the sequence, the scene dependency, and the occurrence area, a path planning algorithm is used to generate an activity path for each family member within a specified time;
[0182] In this step, a relationship network between time nodes and activity points can be established according to the sequence, dependency constraints between activity points and time sequences can be set according to the scene dependency, and location constraints between activity points and possible occurrence areas can be set according to the occurrence area. Greedy or dynamic programming algorithms can be used to calculate the minimum cost path, and optimization algorithms such as simulated annealing can be used to obtain sub-optimal solutions. Individualized daily behavior paths can be repeatedly generated for different members to verify planning consistency and authenticity. This step can achieve system optimization and time efficiency of path arrangement, generate more coherent and natural behavior chains based on life rules, fully reproduce life rules for reference, and enhance the authenticity and reference value of the scene's reflection of life details, so as to achieve efficient and detailed behavior path generation.
[0183] Performing AI simulation in the first virtual scene according to the activity path to generate behavioral action rules for family members;
[0184] In this step, the activity path is imported into the virtual scene system path planning module, and the family members are driven to move in the scene according to the path. The posture and movement changes of the members when completing different activities are collected, the key action framework is analyzed and identified, and the action framework is annotated and described to build an action library. The deep learning algorithm is used to train the action recognition and generation model, and the action rules based on the member attributes and activity types are output. This step can simulate the actions in each activity, effectively enrich the scene details to restore the life scene, provide AI basis and reference for member action control, promote the construction of virtual scenes and the development of animation technology, so as to improve the practicality and reference value of scene interaction.
[0185] The activity path and the action rule are integrated to generate a first daily activity content and path for the family member role in the first virtual scene.
[0186] This embodiment can automatically restore the daily activities of members in the room to a high degree, realize the personalization and consistency of members' interactions, facilitate customers to evaluate from multiple angles whether their life requirements are met, enhance customers' immersion and participation perception, and effectively assist customers to make rational choices.
[0187] In some possible implementations of the present invention, the step of controlling the family member character to experience the virtual layout of the first target house in the first virtual scene according to the first daily activity content and path includes:
[0188] The corresponding family members are equipped with VR devices, and the virtual scene system is imported into the VR devices;
[0189] Constructing the first virtual scene in the virtual scene system;
[0190] Importing the first daily activity content and path corresponding to each family member into the virtual scene system;
[0191] The virtual scene system controls the corresponding behavior and movement path of the family member character (which is a virtual animation character) in the first virtual scene according to the first daily activity content and path;
[0192] While the family member character is moving in the first virtual scene, a first sub-virtual scene corresponding to the current position of the family member character in the first virtual scene is synchronously displayed in the VR device so that the corresponding family member can experience the virtual layout of the first target house from the perspective of his daily activities.
[0193] In this embodiment, the living scenario experience of the members in the house can be restored in a test manner, the individual identity switching experience of the house usage function can be realized, the detailed feedback from users can be collected to improve the house layout design, the customer participation and selection experience can be enhanced, and the customer can be effectively helped to evaluate whether the house meets the actual needs.
[0194] In some possible implementations of the present invention, the step of collecting and analyzing the first interaction data of the first tenant and the family members in the first virtual scene, evaluating whether the first target house meets the actual family living needs of the first tenant, and obtaining the indoor evaluation result includes:
[0195] The family members interact with each other in a scenario-simulated manner through voice and action while experiencing the virtual layout of the first target house, and the virtual scene system records the first interaction data (various user behavior tracking data, such as viewing angle, step length, etc.) of the family members during the interaction process;
[0196] Extracting eye tracking data, facial expression data, voice interaction data, and body behavior data from the first interaction data;
[0197] Use eye tracking data to determine how long and how often family members look at different areas;
[0198] Determine family members' evaluation data on different areas through facial expression data and voice interaction data;
[0199] Use machine learning algorithms to classify viewing time, frequency, and evaluation data and mine habit patterns to obtain virtual experience results;
[0200] Perform a matching evaluation based on the rental demand data and the virtual experience results, and use artificial intelligence to give evaluation scores for multiple indicators (such as spatial layout, area size, functional area type, etc.);
[0201] Output the total scores of various indicators and give the indoor suitability assessment results.
[0202] In this embodiment, it is possible to comprehensively and objectively evaluate the quality of housing supply, collect detailed feedback to improve layout design, provide personalized guidance for users to make rational decisions, effectively improve rental service levels and conversion rates, and promote the digitalization and intelligence of the real estate industry.
[0203] In some possible implementations of the present invention, the step of simulating the third daily activity content and path of the family member role in the third virtual scene includes:
[0204] According to the tenant family model, determine the types of surrounding activities of family members (such as shopping, seeing a doctor, going to school, watching movies, buying groceries, etc.);
[0205] According to the surrounding activity types, a plurality of travel routes and regional points are determined using the road network topology;
[0206] In this step, the road network data around the target house can be obtained from open data, and common surrounding points (such as subway stations, supermarkets, etc.) can be imported into the road network as nodes, and relevant nodes can be determined according to the activity type (such as shopping, commuting, etc.); the path planning algorithm (such as Dijkstra) is used to determine the shortest path to different destinations, considering traffic congestion, and providing multiple candidate routes for reference, and recording route-related information (such as mileage, transportation, etc.) to build a database. Through this step, the surrounding travel environment can be restored and routes can be selected, whether the transportation is convenient to meet life needs can be evaluated, and multi-dimensional travel references can be provided for selection support, which is conducive to the digitalization and intelligent development of real estate. The above completes the work of identifying surrounding travel routes.
[0207] According to the first member attribute, simulate the activity opportunity distribution data of the first member on the corresponding surrounding activity type;
[0208] In this step, personal attribute characteristic factors that affect surrounding activities can be extracted from the collected big data (a large amount of data from other individuals), and the machine learning algorithm can be used to train the model of historical data; the first member attribute of each family member is used as a new sample to input the trained model, and the model predicts the probability distribution of each member participating in different surrounding activities, considering the regional selection constraints, giving the possibility of participating in specific routes, and outputting the surrounding activity access opportunity numerical score table. This step simulates personalized surrounding activity trends based on personal characteristics, comprehensively evaluates whether the surrounding area of the house meets various life needs, and provides personalized and detailed opportunity data for reference, which is conducive to the in-depth exploration and application of digital hosting services and helps to fully understand the satisfaction level of the surrounding environment of the house.
[0209] A constraint-based path planning algorithm is applied according to the travel routes and regional points and the activity opportunity distribution data to generate third daily activity content and paths.
[0210] In this embodiment, the travel scenes of family members in the surrounding environment can be fully simulated to help customers understand the surrounding resource environment, evaluate whether the proximity of housing sources meets daily travel needs, optimize leasing practices and decision-making support capabilities, and test VR scene design and application potential.
[0211] In some possible implementations of the present invention, the step of controlling the family member character to experience the surrounding virtual environment of the first target house in the third virtual scene according to the third daily activity content and path includes:
[0212] Importing the third daily activity content and path into the virtual scene system of the VR device;
[0213] Constructing the third virtual scene in the virtual scene system;
[0214] Integrate the interactive function of the models of relevant important points of interest (i.e., POIs; such as shopping malls, hospitals, schools, etc.) and building models in the surrounding environment of the first target house into the third virtual scene;
[0215] Importing the third daily activity content and path corresponding to each family member into the virtual scene system;
[0216] The virtual scene system controls the corresponding behavior and movement path of the family member role in the third virtual scene according to the third daily activity content and path;
[0217] While the family member character is moving in the third virtual scene, a third sub-virtual scene corresponding to the current position of the family member character in the third virtual scene is synchronously displayed in the VR device so that the corresponding family member can experience the surrounding virtual environment of the first target house from the perspective of his daily activities.
[0218] In this embodiment, it is possible to realistically reproduce the daily activities of family members in the surrounding area, comprehensively assess whether the surrounding environment meets life needs, continuously optimize the design and functions of virtual scenes, enhance customer engagement and selection basis, and evaluate the application potential of digital experience scenes in real estate services.
[0219] In some possible implementations of the present invention, the following methods may be used to implement the POI and building model interaction function in a virtual scene:
[0220] Write scripts for POI and building objects, defining their basic properties and behavior rules;
[0221] In the VR Scene Editor of the Virtual Scene System, set up click / gesture recognition events for POIs and buildings;
[0222] When clicking on a POI, the internal scene is opened or an information window pops up, etc. (for example, clicking on a mall door to enter a mall scene);
[0223] Set the relationship between buildings and POIs (for example, display the location of nearby hospital buildings after selecting a hospital);
[0224] Add task / game interaction functions to POIs (e.g. shopping in a mall, completing the medical consultation process in a hospital, etc.);
[0225] Set the visibility of each POI to reflect the user (for example, buildings far away are blurred and become clearer when approaching);
[0226] Record the interaction data between users and POIs (such as length of stay, for analysis and evaluation support);
[0227] Show users the application effects after selection (such as displaying the time after making an appointment);
[0228] Continue to optimize interaction details to enhance scene realism and user engagement.
[0229] In this embodiment, rich interactive functions between POIs and buildings in the virtual scene can be realized.
[0230] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.
[0231] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0232] In the several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the above-mentioned units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.
[0233] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0234] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0235] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the above-mentioned methods of each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or CD-ROM and other media that can store program codes.
[0236] A person skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, and the memory can include: a flash drive, a read-only memory (English: Read-Only Memory, abbreviated as: ROM), a random access memory (English: Random Access Memory, abbreviated as: RAM), a magnetic disk or an optical disk, etc.
[0237] The embodiments of the present application are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of the present application. At the same time, for general technical personnel in this field, according to the idea of the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.
[0238] Although the present invention is disclosed as above, the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions without departing from the spirit and scope of the present invention, and can make various changes and modifications, including the combination of the above-mentioned different functions and implementation steps, including software and hardware implementation methods, all of which are within the scope of protection of the present invention.
Claims
1. A house rental adaptation system based on virtual reality technology, characterized in that: include: Cloud servers and VR devices; among them, The cloud server is configured as follows: Using three-dimensional scanning technology to obtain first three-dimensional data of multiple target houses, second three-dimensional data of a first building where the target houses are located, and third three-dimensional data of all entities within a preset range of the location of the first building; Establishing a first digital twin model of the target house according to the first three-dimensional data; establishing a second digital twin model of the first building according to the second three-dimensional data; Establishing a third digital twin model including three-dimensional information of the first building and all the entities according to the second three-dimensional data and the third three-dimensional data; Obtain the rental demand data and historical rental data of the first tenant; Determine one or more first target houses from the plurality of target houses according to the rental demand data and the historical rental data; Obtaining family member information of the first tenant and establishing a tenant family model; In a virtual reality environment, generating a first virtual scene and family member roles of the first target house according to the first digital twin model and the tenant family model corresponding to the first target house; Planning a first daily activity content and path for the family member role in the first virtual scene through an artificial intelligence algorithm; According to the first daily activity content and path, controlling the family member character in the first virtual scene to experience the virtual layout of the first target house; collecting and analyzing first interaction data of the first tenant and the family members in the first virtual scene, evaluating whether the first target house meets the actual living needs of the first tenant's family, and indoor evaluation results; Providing housing adaptation suggestions to the first tenant based on the indoor evaluation results to assist in making housing selection decisions; The step of collecting and analyzing the first interaction data of the first tenant and the family members in the first virtual scene, evaluating whether the first target house meets the actual family living needs of the first tenant, and obtaining the indoor evaluation result includes: The family members interact with each other in a scenario-simulated manner through voice and action during the experience of the virtual layout of the first target house, and the virtual scene system records first interaction data of the family members during the interaction process; Extracting eye tracking data, facial expression data, voice interaction data, and body behavior data from the first interaction data; Use eye tracking data to determine how long and how often family members look at different areas; Determine family members' evaluation data on different areas through facial expression data and voice interaction data; Use machine learning algorithms to classify viewing time, frequency, and evaluation data and mine habit patterns to obtain virtual experience results; Performing a matching evaluation based on the rental demand data and the virtual experience results, and using artificial intelligence to give evaluation scores for multiple indicators; Output the total scores of various indicators and give the indoor evaluation results.
2. A housing rental adaptation method based on virtual reality technology, characterized in that: include: Using three-dimensional scanning technology to obtain first three-dimensional data of multiple target houses, second three-dimensional data of a first building where the target houses are located, and third three-dimensional data of all entities within a preset range of the location of the first building; Establishing a first digital twin model of the target house according to the first three-dimensional data; establishing a second digital twin model of the first building according to the second three-dimensional data; Establishing a third digital twin model including three-dimensional information of the first building and all the entities according to the second three-dimensional data and the third three-dimensional data; Obtain the rental demand data and historical rental data of the first tenant; Determine one or more first target houses from the plurality of target houses according to the rental demand data and the historical rental data; Obtaining family member information of the first tenant and establishing a tenant family model; In a virtual reality environment, generating a first virtual scene and family member roles of the first target house according to the first digital twin model and the tenant family model corresponding to the first target house; Planning a first daily activity content and path for the family member role in the first virtual scene through an artificial intelligence algorithm; According to the first daily activity content and path, controlling the family member character in the first virtual scene to experience the virtual layout of the first target house; Collecting and analyzing first interaction data of the first tenant and the family members in the first virtual scene, evaluating whether the first target house meets the actual living needs of the first tenant's family, and obtaining an indoor evaluation result; Providing housing adaptation suggestions to the first tenant based on the indoor evaluation results to assist in making housing selection decisions; The step of collecting and analyzing the first interaction data of the first tenant and the family members in the first virtual scene, evaluating whether the first target house meets the actual family living needs of the first tenant, and obtaining the indoor evaluation result includes: The family members interact with each other in a scenario-simulated manner through voice and action during the experience of the virtual layout of the first target house, and the virtual scene system records first interaction data of the family members during the interaction process; Extracting eye tracking data, facial expression data, voice interaction data, and body behavior data from the first interaction data; Use eye tracking data to determine how long and how often family members look at different areas; Determine family members' evaluation data on different areas through facial expression data and voice interaction data; Use machine learning algorithms to classify viewing time, frequency, and evaluation data and mine habit patterns to obtain virtual experience results; Performing a matching evaluation based on the rental demand data and the virtual experience results, and using artificial intelligence to give evaluation scores for multiple indicators; Output the total scores of various indicators and give the indoor evaluation results.
3. The house rental adaptation method based on virtual reality technology according to claim 2 is characterized in that: After the step of collecting and analyzing the interaction data of the first tenant and the family members in the first virtual scene to evaluate whether the first target house meets the actual living needs of the first tenant's family, the method further includes: generating a second virtual scene corresponding to the first building according to the second digital twin model and the tenant household model; Generate a third virtual scene including virtual models of all entities within a preset range of the location of the first building according to the third digital twin model and the tenant household model; Simulating a second daily activity content and path of the family member role in the second virtual scene; Simulating the third daily activity content and path of the family member role in the third virtual scene; According to the second daily activity content and path, controlling the family member character in the second virtual scene to experience the virtual space of the first building; According to the third daily activity content and path, controlling the family member character in the third virtual scene to experience the surrounding virtual environment of the first target house; Collecting and analyzing second interaction data of the first tenant and the family members in the second virtual scene, evaluating whether the first building meets the actual living needs of the first tenant in the building, and obtaining an evaluation result in the building; Collect and analyze the third interaction data of the first tenant and the family members in the third virtual scene, evaluate whether the surrounding facilities of the first target house meet the actual living needs of the first tenant when going out, and obtain the surrounding facilities evaluation result.
4. The house rental adaptation method based on virtual reality technology according to claim 3 is characterized in that: The step of obtaining the family member information of the first tenant and establishing a tenant family model includes: Obtaining basic information, daily behavior data, medical records, and medical insurance-related data of the first tenant's family members as the family member information; De-duplication and format standardization of the family member information; Using big data analysis technology and machine learning technology, analyze and mine the behavioral preferences, consumption habits, and health status of family members based on the family members' information, and build an overall family portrait model and individual portrait models of each family member; The overall family portrait model and the personal portrait model are used as tenant family models.
5. The house rental adaptation method based on virtual reality technology according to claim 4 is characterized in that: The step of generating a first virtual scene and family member roles of the first target house in the virtual reality environment according to the first digital twin model and the tenant family model corresponding to the first target house includes: Importing the first digital twin model of the first target house into a virtual environment construction platform to generate a virtual three-dimensional scene of the first target house; In the virtual three-dimensional scene, automatically generating family member roles with corresponding numbers and attributes according to the tenant family model; Placing furniture and home appliance models that match the layout of the first target house in the virtual three-dimensional scene; Based on the activity data of family members, an artificial intelligence algorithm is used to generate the first simulated daily route plan for each family member; Using the first simulated daily route planning as a clue, making a first form animation of family members changing over time; The virtual three-dimensional scene, the family member roles, the furniture and appliance models, the first simulated daily path planning and the first form animation and voice interaction are integrated to construct a first virtual scene.
6. The housing rental adaptation method based on virtual reality technology according to claim 5 is characterized in that: The step of planning the first daily activity content and path for the family member role in the first virtual scene by using an artificial intelligence algorithm includes: identifying a first member attribute of each family member according to the tenant family model; predicting the daily activity pattern of each family member from the big data training sample based on the first member attribute; Based on the daily activity patterns, using deep learning algorithms to study the sequence and scene dependency of each daily activity; In the first virtual scene, identifying the occurrence areas of various daily activities according to the functional area characteristics; Combining the sequence, the scene dependency, and the occurrence area, a path planning algorithm is used to generate an activity path for each family member within a specified time; Performing AI simulation in the first virtual scene according to the activity path to generate behavioral action rules for family members; The activity path and the action rule are integrated to generate a first daily activity content and path for the family member role in the first virtual scene.
7. The housing rental adaptation method based on virtual reality technology according to claim 6 is characterized in that: The step of controlling the family member character to experience the virtual layout of the first target house in the first virtual scene according to the first daily activity content and path includes: The corresponding family members are equipped with VR devices, and the virtual scene system is imported into the VR devices; Constructing the first virtual scene in the virtual scene system; Importing the first daily activity content and path corresponding to each family member into the virtual scene system; The virtual scene system controls the corresponding behavior and movement path of the family member character in the first virtual scene according to the first daily activity content and path; While the family member character is moving in the first virtual scene, a first sub-virtual scene corresponding to the current position of the family member character in the first virtual scene is synchronously displayed in the VR device so that the corresponding family member can experience the virtual layout of the first target house from the perspective of his daily activities.
8. The housing rental adaptation method based on virtual reality technology according to claim 7 is characterized in that: The step of simulating the third daily activity content and path of the family member role in the third virtual scene includes: Determining the peripheral activity types of family members according to the tenant family model; According to the surrounding activity types, a plurality of travel routes and regional points are determined using the road network topology structure; According to the first member attribute, simulate the activity opportunity distribution data of the first member on the corresponding surrounding activity type; A constraint-based path planning algorithm is applied according to the travel routes and regional points and the activity opportunity distribution data to generate third daily activity content and paths.
9. The housing rental adaptation method based on virtual reality technology according to claim 8 is characterized in that: The step of controlling the family member character to experience the surrounding virtual environment of the first target house in the third virtual scene according to the third daily activity content and path includes: Importing the third daily activity content and path into the virtual scene system of the VR device; Constructing the third virtual scene in the virtual scene system; Integrate the interactive function of the models of relevant important points of interest and the building model in the surrounding environment of the first target house into the third virtual scene; Importing the third daily activity content and path corresponding to each family member into the virtual scene system; The virtual scene system controls the corresponding behavior and movement path of the family member role in the third virtual scene according to the third daily activity content and path; While the family member character is moving in the third virtual scene, a third sub-virtual scene corresponding to the current position of the family member character in the third virtual scene is synchronously displayed in the VR device so that the corresponding family member can experience the surrounding virtual environment of the first target house from the perspective of his daily activities.
