Location identification method and device, generation and display device, and proposal system for visual data of buildings

Abstract

Embodiments of the present invention provide a location identification method and device, a generation and display device, and a proposal system for visual data of buildings, the location identification method including a step for acquiring location information relating to a first location requiring modification in a target system of a building and first visual data of the building, a step for identifying a processing node associated with the location information on the basis of a first artificial intelligence model, and a step for identifying, at the processing node, location reference information of a second location associated with the location information from within the first visual data on the basis of a second artificial intelligence model, wherein the location reference information is reference information for identifying the second location in the first visual data at the first location requiring modification in the target system. This makes it possible to accurately identify the location, in the existing first visual data of the building, of the location at which modification is required in the target system of the building, and to accurately generate visual data including the location at which modification is required in the target system on the basis of the location.

Description

Positioning method, device, generation and display device, and proposal system for visual data of buildings

[0001] The present invention relates to the field of building management, and in particular to a positioning method, device, generation and display device, and proposal system for visual data of buildings.

[0002] With the progress of building intelligence and the continuous improvement of user requirements, the type and number of systems that can be arranged in a building and the number of devices included in the systems have gradually increased, which complicates building design data and increases the data volume.

[0003] In intelligent building proposals, due to the complicated building design data and large data volume, manual design of proposal materials has low efficiency, high cost and is prone to errors. In addition, since some customers are not familiar with building design, it is difficult for them to clearly express their transformation requirements, and it is impossible to design proposal materials that meet the actual requirements of users. As a result, user satisfaction with the proposal materials decreases, which affects the proposal success rate and user experience.

[0004] To address the above problems, building design proposal automation technologies have been proposed, for example, (i) generating proposal materials based on characters and fixed templates (e.g., PPT templates), (ii) using an artificial intelligence model to automatically understand user requirements and generate proposal content.

[0005] It should be noted that the above description of the technical background is merely provided to clearly and completely describe the technical solution of the present invention and facilitate understanding by those skilled in the art. The fact that these technical solutions are described in the background section of the present invention does not mean that these technical solutions are recognized as well-known to those skilled in the art.

[0006] The inventors have found that while the above-mentioned prior art (i), which generates proposal materials based on text and fixed templates, achieves proposal automation, the generated proposal materials are not associated with building design data, making it impossible to associate user requests with locations in the building design data, which is detrimental to the user's ability to intuitively and quickly understand the proposal content. Furthermore, while the above-mentioned prior art (ii), which uses an artificial intelligence model to automatically understand user requests and generate proposal content, can generate relatively accurate proposal content, when faced with complex building design data, relying solely on the capabilities of the artificial intelligence model itself still fails to accurately associate locations requiring modification in user requests with locations in the building design data. As a result, there is a significant discrepancy between the locations in the generated design data and the locations requiring modification in user requests, ultimately affecting the proposal success rate and user experience.

[0007] The embodiments of the present invention provide a method, apparatus, generation / display device, and proposed system for identifying locations for building visual data, which can accurately identify the locations in the building's existing first visual data of the building where modifications are needed in the building's target system, that is, accurately identify the locations where modifications are needed in the building's first visual data, thereby enabling the accurate generation of visual data including the locations where modifications are needed in the target system based on those locations.

[0008] According to a first embodiment of the present invention, a method for identifying the location of building visual data is provided, which includes the steps of: acquiring location information relating to a first location requiring modification in a building target system and first visual data of the building; identifying a processing node associated with the location information based on a first artificial intelligence model; and at the processing node, identifying location reference information of a second location associated with the location information among the first visual data based on a second artificial intelligence model, wherein the location reference information is reference information for identifying the second location in the first visual data of the first location requiring modification in the target system; the first artificial intelligence model is based at least on the relationship between location information relating to a first location requiring modification in the target system and a processing node in the target system; and the second artificial intelligence model is based at least on the relationship between location information relating to a first location requiring modification in the target system and location reference information of a second location in the first visual data.

[0009] According to a second embodiment of the present invention, a location identification device for building visual data is provided, comprising: an acquisition module that acquires location information relating to a first location requiring modification in a building target system and first visual data of a building; a first identification module that identifies a processing node associated with the location information based on a first artificial intelligence model; and a second identification module that, at the processing node, identifies location reference information of a second location associated with the location information among the first visual data based on a second artificial intelligence model, wherein the location reference information is reference information for identifying the second location in the first visual data of the first location requiring modification in the target system; the first artificial intelligence model is based at least on the relationship between location information relating to a first location requiring modification in the target system and a processing node in the target system; and the second artificial intelligence model is based at least on the relationship between location information relating to a first location requiring modification in the target system and location reference information of a second location in the first visual data.

[0010] A third embodiment of the present invention provides a building visual data generation and display device that includes a memory in which a computer program is stored, a processor that, when the computer program is executed, realizes the location identification method for building visual data described in the first embodiment of the present invention, acquires location reference information for a second location associated with location information among the first visual data, and generates second visual data according to the first visual data and location reference information, and a display that displays the second visual data of the building.

[0011] According to a fourth embodiment of the present invention, a proposed system for buildings is provided, which includes at least one of the location identification device for building visual data described in the second embodiment of the present invention, and the building visual data generation and display device described in the third embodiment of the present invention.

[0012] One beneficial effect of the embodiment of the present invention is that, by using an artificial intelligence model to identify location reference information for a second location associated with location information for a first location requiring modification in the building's target system, the first location requiring modification can be accurately associated with the location in the first visual data, that is, accurate identification of the location requiring modification in the building's first visual data can be achieved. As a result, visual data including the location requiring modification in the target system can be accurately generated based on that location, and visual data matching user requests or proposals to the user can be accurately generated based on the location reference information and the building's first visual data, which is advantageous for users to intuitively and quickly understand the proposal, improving the proposal success rate and user experience. Furthermore, processing nodes associated with location information are identified based on location information for a first location requiring modification in the building's target system, and location reference information for the second location associated with location information is identified only in the identified processing nodes within the first visual data. As a result, when user requests or proposals to the user change, data from other processing nodes in the processing flow can be reused, and only the data of the processing node corresponding to the updated user requests or proposals to the user needs to be modified, improving the efficiency of proposal generation.

[0013] Furthermore, in the method for determining the location of building visual data according to the first embodiment, if the location information relating to a first location requiring modification in the building's target system includes the first location in the building, the step of determining the location reference information of a second location associated with the location information among the first visual data based on a second artificial intelligence model includes the step of determining the location reference information of a first location among the first visual data based on the first location, based on the second artificial intelligence model.

[0014] This allows for the accurate identification of location reference information based on a clearly defined first location in the location information. In other words, because the first location is clearly given, the identified location reference information is more accurate, and furthermore, the visual data generated based on said location reference information better matches the user requirements.

[0015] Furthermore, if the location information relating to a first location requiring modification in the building's target system does not include the first location in the building, the step of identifying location reference information of a second location associated with the location information among the first visual data based on a second artificial intelligence model includes the step of generating location reference information of the first location associated with the first location among the first visual data using the second artificial intelligence model based on the location information relating to the first location requiring modification in the building's target system and building design criteria information.

[0016] This allows for the accurate generation of location reference information based on location information and architectural design standards information, even if the location information does not include a clearly defined location.

[0017] Furthermore, the location information relating to the first location requiring modification in the building's target system includes location information relating to at least one of the following: a user request, a proposal to the user, the updated user request, and the updated proposal to the user.

[0018] This allows for further improvement in the accuracy of identified location information by identifying locations that require modification based on user requests or suggestions to the user.

[0019] Furthermore, the method for locating the building's visual data further includes the step of associating at least one of the user request, the user's suggestion, the updated user request, and the updated user's suggestion with the corresponding location reference information.

[0020] This allows us to associate user requests with corresponding locations in the building's visual data, improving the degree of agreement between user requests and the actually generated proposed visual data.

[0021] Furthermore, the step of associating at least one of the user request, the content of the suggestion to the user, the updated user request, and the updated content of the suggestion to the user with the corresponding location reference information includes the steps of using a third artificial intelligence model to refine at least one of the user request, the content of the suggestion to the user, the updated user request, and the updated content of the suggestion to the user, and obtaining a first user request; breaking down the first request for each system function of the building and obtaining a second request corresponding to each system function of the target system; and hierarchically extracting the second requests according to the location reference information and obtaining a plurality of user sub-requests that correspond to each system function and include the corresponding location reference information.

[0022] This allows for the generation of accurate and actionable visual data by precisely mapping detailed user sub-requests to specific locations within the building model.

[0023] Furthermore, the method for locating the building's visual data further includes the step of associating at least one of the user request, the suggestion to the user, the updated user request, and the updated suggestion to the user with a processing node associated with the corresponding location information.

[0024] This allows user requests to be associated with specific processing nodes in the processing flow, enabling processing of those requests at the associated processing node and improving processing efficiency by reusing other processing nodes in the processing flow.

[0025] Furthermore, the method for determining the location of the building's visual data further includes the step of generating second visual data of the building that matches at least one of the user request, the user's proposal, the updated user request, and the updated user's proposal, in accordance with the first visual data of the building and the location reference information of a second location associated with the location information among the first visual data.

[0026] This ensures that user requirements can be accurately mapped to specific locations in the building's visual data, improves the efficiency of processing when user requirements are updated, avoids conflicts and errors between system functions, and enhances the efficiency and accuracy of visual data that matches user requirements. Furthermore, it makes it easier for users to quickly and intuitively understand proposals, thereby improving the success rate of proposals.

[0027] Furthermore, the step of generating second visual data of the building that matches at least one of the user request, the content of the suggestion to the user, the updated user request, and the updated content of the suggestion to the user includes, at each associated processing node, the step of generating third visual data of a system function corresponding to each processing node based on the first visual data of the building, at least one of the user request, the content of the suggestion to the user, the updated user request, and the updated content of the suggestion to the user associated with each processing node, and location reference information associated with at least one of the user request, the content of the suggestion to the user, the updated user request, and the updated content of the suggestion to the user; and the step of integrating the third visual data of each system function to obtain second visual data of the building.

[0028] This allows each processing node to generate and integrate corresponding visual data to obtain second visual data, thereby improving the efficiency and accuracy of the generated second visual data. Furthermore, by processing the corresponding processing task for each node, it can adapt to changes in processing content, resulting in greater flexibility. In addition, each processing node may use the artificial intelligence model or algorithm best suited to its corresponding processing content, and different processing nodes may use different artificial intelligence models or algorithms. Therefore, it is possible to use the optimal model for different processing tasks, resulting in better processing quality and higher efficiency.

[0029] Furthermore, the method for determining the location of the building's visual data further includes the steps of: displaying the second visual data using a display device; obtaining user feedback information regarding the displayed second visual data, and if the feedback information includes an updated user request, generating and displaying updated second visual data based on the updated user request; or obtaining updated suggestions for the user, and generating and displaying updated second visual data according to the updated suggestions for the user.

[0030] This improves the degree of agreement between the generated proposal visual data and user requirements by updating the second visual data in response to user requests. Furthermore, displaying the second visual data makes it easier for users to quickly and intuitively understand the proposal, thereby improving the proposal success rate and user experience.

[0031] Furthermore, the processing node includes a processing node for the workflow, and the method for localizing the building's visual data further includes the step of using a fourth artificial intelligence model to construct a first workflow based on a first processing node associated with at least one of a user request and a suggestion to the user.

[0032] This enables the localization of building visual data based on user requests in a workflow format, thereby improving data processing efficiency.

[0033] Furthermore, the method for locating the building's visual data further includes the step of using a fourth artificial intelligence model to update the flow architecture of the first workflow based on at least one of the updated user requests and updated suggestions to the user, thereby obtaining a second workflow, the step of updating the flow architecture of the first workflow including the steps of deleting a first processing node in the first workflow or adding a second processing node to the first workflow associated with at least one of the updated user requests and updated suggestions to the user, and linking the first processing nodes that have not been deleted or linking the first processing nodes that have not been deleted with the newly added second processing nodes, according to a set rule.

[0034] This improves workflow construction efficiency and data location efficiency by updating the corresponding processing node in the workflow whenever user requests or suggestions to the user are updated.

[0035] Furthermore, at least one of the user request, the content of the proposal to the user, the updated user request, and the updated content of the proposal to the user is generated based on at least one of the voice interaction data with the user, the request data table entered by the user, and the user's request record information.

[0036] This makes it easy to obtain user requests or suggestions to users in various forms.

[0037] Furthermore, the user request includes at least one of the following: system information, equipment information, area information, and evaluation information regarding the building's environment. The proposal to the user includes at least one of the following: system information, equipment information, area information, and evaluation information regarding the building's environment.

[0038] This enables easy generation of user requirements and proposal content for users based on evaluation information for systems, equipment, etc. in a building.

[0039] Furthermore, the position specifying method for visual data of a building includes: specifying the second position in the first visual data of the building based on the first visual data of the building and position reference information of a second position associated with position information about a first position that requires modification in a target system among the first visual data; and displaying the first visual data, the second position, and the position reference information.

[0040] This enables display of the first visual data, the second position, and the position reference information, making it easy for a user to intuitively understand the position in the first visual data corresponding to the user's requirement, thereby further improving user experience.

[0041] Furthermore, the first visual data of the building includes at least one of: parameter data, image data, video data, and proposal data of a multidimensional visualization model of a building; and parameter data, image data, video data, and proposal data of a multidimensional visualization model of a building generated based on a previous user requirement or previous proposal content for the user. For example, multidimensional visualization models include, but are not limited to, 2D models, 3D models, 4D models, and the like.

[0042] This makes it easy for a user to view the first visual data based on different data formats, thereby further improving user experience.

[0043] Furthermore, the position reference information includes at least one of position information, spatial information, area information, time information, material information, color information, piping and wiring information, and layer information.

[0044] This enables specification of the second position based on a plurality of different pieces of data, thereby improving the accuracy of specifying a position that requires modification in visual data of a building.

[0045] Furthermore, in the building visual data generating and displaying device according to the third aspect, the display further displays first visual data of the building, a second position associated with position information on a first position that needs modification in a target system in the first visual data, and position reference information.

[0046] This makes it easy for a user to acquire the first visual data of the building, and the corresponding second position and position reference information of the first position that needs modification in the target system in the first visual data, and contributes to further improving user experience.

[0047] By referring to the following description and the accompanying drawings, specific embodiments of the present invention are disclosed in detail, and forms in which the principles of the present invention can be applied are shown. It should be understood that the scope of the embodiments of the present invention is not limited thereby. Within the spirit and scope of the appended claims, the embodiments of the present invention include many changes, modifications and equivalents.

[0048] Features described and illustrated for one embodiment may be used in the same or similar manner in one or more other embodiments, combined with features in other embodiments, or substituted for features in other embodiments.

[0049] It should be emphasized that the term "comprising / comprises" when used herein indicates the presence of a feature, element, step or constituent requirement, but does not exclude the presence or addition of one or more other features, elements or constituent requirements.

[0050] The above and other objects, features and advantages of the embodiments of the present invention will become more apparent from the following detailed description with reference to the accompanying drawings.

[0051] This is a schematic diagram of a method for determining the location of building visual data according to an embodiment of the present invention. This is a schematic diagram of the step of associating with location reference information according to an embodiment of the present invention. This is a schematic diagram of the step of generating second visual data according to an embodiment of the present invention. This is a flowchart of a method for determining the location of building visual data according to an embodiment of the present invention. This is a schematic diagram of the flow of a method for determining the location of building visual data according to an embodiment of the present invention. This is a schematic diagram of a location determination device for building visual data according to an embodiment of the present invention. This is a schematic diagram of a building visual data generation and display device according to an embodiment of the present invention. This is a schematic diagram of a proposed system for buildings according to an embodiment of the present invention.

[0052] The above and other features of the present invention will become apparent from the following description with reference to the drawings. The specification and drawings specifically disclose specific embodiments of the present invention and show some embodiments that may employ the principles of the present invention. It should be understood that the present invention is not limited to the embodiments described and includes all modifications, variations and equivalents that fall within the scope of the appended claims.

[0053] The following describes, with reference to the drawings, a method, apparatus, generation / display device, and proposed system for determining the location of building visual data according to embodiments of the present invention.

[0054] <Examples relating to the first aspect> An embodiment relating to the first aspect of the present invention provides a method for determining the location of building visual data. Figure 1 is a schematic diagram of a method for determining the location of building visual data according to an embodiment of the present invention. As shown in Figure 1, the method for determining the location of building visual data 100 includes: a step 101 of acquiring location information relating to a first location requiring modification in the building's target system and first visual data of the building; a step 102 of identifying a processing node associated with the location information based on a first artificial intelligence model; and a step 103 of identifying location reference information of a second location associated with the location information among the first visual data at the processing node, based on a second artificial intelligence model, wherein the location reference information is reference information for identifying the second location in the first visual data of the first location requiring modification in the target system. The first artificial intelligence model is based at least on the relationship between location information relating to a first location requiring modification in the target system and a processing node in the target system. The second artificial intelligence model is based at least on the relationship between location information relating to a first location requiring modification in the target system and location reference information of a second location in the first visual data.

[0055] This enables the accurate identification of the location requiring modification in the first visual data of a building by using an artificial intelligence model to identify the location reference information of a second location associated with the location information of a first location requiring modification in the building's target system. This allows for accurate correspondence between the first location requiring modification and the location in the first visual data, i.e., accurate identification of the location requiring modification in the building's first visual data. This enables the accurate generation of visual data including the location requiring modification in the target system based on that location, and also enables the accurate generation of visual data that matches user requests or proposals to the user based on the location reference information and the building's first visual data. This is advantageous for users to intuitively and quickly understand the proposal, improving the proposal success rate and user experience. Furthermore, it identifies processing nodes associated with location information based on the location information of the first location requiring modification in the building's target system, and identifies the location reference information of the second location associated with location information in the first visual data only within the identified processing nodes. This allows for the reuse of data from other processing nodes in the processing flow when user requests or proposals change, and only the data of the processing node corresponding to the updated user requests or proposals needs to be modified, improving the efficiency of proposal generation.

[0056] In some embodiments, the building may be of various types, such as an office building, shopping mall, factory plant, school, apartment building, or private residence. The embodiments of the present invention are not limited to the type of building.

[0057] In some embodiments, a building may be called a building, or a building may include various types of buildings.

[0058] In some embodiments, the target system of a building is a system that requires modification (including overall or local modification) to at least one of several systems within the building.

[0059] Systems in a building include, for example, audio-video systems, power systems, network systems, air conditioning systems, water supply and drainage systems, lighting systems, curtain systems, and HVAC systems. Each system within a building may include multiple units and / or multiple types of equipment. Embodiments of the present invention are not limited to systems or equipment within systems.

[0060] In some embodiments, “modification” includes, but is not limited to, the addition, subtraction, replacement of hardware such as systems and equipment within a building, the installation, updating, and design of software for systems and equipment located within the building, and the design and decoration of the building’s spaces.

[0061] In some embodiments, the first location requiring modification includes at least one of a physical location and a virtual location located in the building's target system, where the physical location is, for example, a location located in the building's actual target system, and the virtual location is, for example, a location located in the target system's software, but is not limited to this.

[0062] In some embodiments, the location information relating to a first location requiring modification in the building's target system includes location information relating to at least one of a user request, a suggestion to the user, an updated user request, and an updated suggestion to the user. This allows for further improvement in the accuracy of the identified location information by identifying the location requiring modification based on the user request or the suggestion to the user.

[0063] In some embodiments, user requirements refer to a functional requirements document submitted by the requesting party for the modification (also referred to as the user or client) for the modification of the building's target system. This document serves as the basis for decision-making and is also referred to as the client / user requirements specification.

[0064] In some embodiments, user requests may include at least one of the following: system information, equipment information, area information, and evaluation information regarding the building environment. Here, system information includes, for example, information such as functional defects and upgrade requests for existing systems in the building, such as HVAC systems, power systems, and lighting systems. Equipment information includes, for example, information such as equipment operating parameters (e.g., energy efficiency indicators for air conditioning) and equipment layout (e.g., requests for optimization of the location of distribution boxes). Area information includes, for example, information such as a functional zoning adjustment plan for the building (e.g., converting an office area into a smart conference room). Evaluation information regarding the building environment includes, for example, a direct subjective evaluation of the spatial environment by the user, and includes the building's thermal environment (e.g., overheating in summer / overcooling in winter, uneven cooling in localized areas) and air quality (e.g., stuffiness due to insufficient ventilation, CO2). ２ This includes, but is not limited to, evaluations of the lighting environment (e.g., darkness due to insufficient natural light, interference due to glare), and the sound environment (e.g., equipment noise exceeding standards, significant echo in conference rooms). If users are unable to professionally identify defects and upgrade requirements for the building's existing systems, system information may be provided more intuitively through direct subjective evaluations of the spatial environment.

[0065] In some embodiments, the requester / user for modification includes, but is not limited to, at least one of the following: the owner of all or part of the area within the building; the user of all or part of the area within the building; or the owner or user of the system within all or part of the area within the building.

[0066] In some embodiments, the proposed content to the user refers to a modification plan customized by a professional service provider (also called the contractor or proposal provider) in response to user requests, or a modification plan formulated by a patent service provider in accordance with the existing conditions of the user's building, and is also referred to as a contractor modification proposal. The proposed content to the user includes at least one of the following: system information, equipment information, area information, or evaluation information regarding the building's environment. For details, please refer to the explanation above, and redundant explanations will be omitted here.

[0067] In some embodiments, an updated user request refers to at least one user request obtained after the initial user request has been obtained, and an updated user request includes, for example, a new request submitted by the user after the initial request has been submitted, or an improvement request submitted by the user based on visual data or suggestions to the user generated on any previous occasion. This application is not limited thereto.

[0068] In some embodiments, the updated user proposal refers to at least one proposal submitted after the initial proposal was submitted to the user, and the updated user proposal includes, for example, a further updated proposal in addition to any previous user proposal, and the user proposal is updated, for example, based on updated user requests or user feedback.

[0069] In some embodiments, the suggestions to the user may be generated based on the user request and a pre-configured suggestion template. The pre-configured suggestion template is selected from a pre-configured suggestion template library. For example, based on this pre-configured suggestion template library, an intelligent matching system may be used to match the user request with a modification suggestion database built on the user request and historical cases, selecting the suggestion template that best matches the user request. For example, if the user request only includes modification upgrades to the air conditioning system, only the pre-configured template for the air conditioning system may be output as modification advice from a professional service provider.

[0070] In some embodiments, the proposed template may be stored and derived in various formats such as PPT, Word, Excel, etc., and the embodiments of the present invention are not limited thereto.

[0071] In some embodiments, at least one of the user request, the user's proposal, the updated user request, and the updated user's proposal is generated based on at least one of the following: voice interaction data with the user, a request data table entered by the user, and the proposer's request record information. This makes it easy to obtain the user request or the user's proposal in various forms.

[0072] In some embodiments, the proposer refers to the source of the intelligent modification proposal, which may be, for example, a sales representative in the market who is responsible for the user. Here, the voice interaction data with the user may include at least one of the user's voice data and the proposer's voice data. This voice data is obtained with the user's consent. The request data entered by the user is not limited to table data, nor is it limited to electronic file format or paper file format.

[0073] Similarly, the embodiments of the present invention do not limit the data representation and storage format of the proposer's request record information. The proposer's request record information may include voice interaction data with the user and the request data entered by the user itself, or it may include content that is more suitable for understanding and processing by the artificial intelligence model, obtained by combining the "voice interaction data with the user" and the "request data entered by the user" based on the proposer's understanding of the user's background information.

[0074] In some embodiments, the first visual data of a building includes parameter data, image data, video data, and proposal data for a multidimensional visualization model of the building, and at least one of the following: parameter data for a multidimensional visualization model of the building generated based on a previous user request or proposal to the user; image data for the building generated based on a previous user request or proposal to the user; video data for the building generated based on a previous user request or proposal to the user; and proposal data for the building generated based on a previous user request or proposal to the user.

[0075] For example, multidimensional visualization models include, but are not limited to, 2D models, 3D models, and 4D models.

[0076] This makes it easier for users to view the first visual data based on different data formats, further improving the user experience.

[0077] The data types included in the second and third visual data described later are the same as those in the first visual data described above.

[0078] Note that the first visual data is existing visual data, while the second and third visual data are generated visual data.

[0079] In some embodiments, step 102 identifies a processing node associated with location information relating to a first location in the building's target system that requires modification, based on a first artificial intelligence model. This first artificial intelligence model is based at least on the relationship between location information relating to a first location in the building's target system that requires modification and a processing node in the target system.

[0080] In some embodiments, processing nodes correspond one-to-one with target systems, and processing such as modifications to different target systems is performed in the processing node corresponding to that target system.

[0081] In some embodiments, the method for locating building visual data according to embodiments of the present invention further includes the step of associating at least one of a user request, a suggestion to the user, an updated user request, and an updated suggestion to the user with a processing node associated with the corresponding location information.

[0082] In this embodiment, the corresponding "location information" includes location information related to at least one of the following: user request, user proposal, updated user request, and updated user proposal, i.e., location information relating to the first location in the building's target system that requires modification.

[0083] This allows user requests to be associated with specific processing nodes in the processing flow, enabling processing of those requests at the associated processing node and improving processing efficiency by reusing other processing nodes in the processing flow.

[0084] In some embodiments, the processing node includes a processing node in the workflow and a flow node in the design program. Therefore, when there is a request to modify a first location in the target system of a building that requires modification, it is only necessary to change the relevant processing in the processing node corresponding to the target system, without needing to change other processing nodes in the workflow or other flow nodes in the design program, thereby improving the generation efficiency of the workflow and design program.

[0085] In some embodiments, in step 103, a processing node associated with location information relating to a first location requiring modification in the building's target system identifies location reference information for a second location associated with the location information among the first visual data of the building, based on a second artificial intelligence model. Here, the second artificial intelligence model is based at least on the relationship between location information relating to a first location requiring modification in the building's target system and location reference information for a second location in the first visual data.

[0086] In some embodiments, the second position refers to a virtual position in the first visual data of the building, and the relative position of the second position in the first visual data is the same as the relative position of the first position in the building; in other words, the second position is the position to which the first position is mapped in the first visual data.

[0087] In some embodiments, the location reference information for the second location is used to identify the second location in the first visual data of the building.

[0088] For example, the location reference information includes at least one of the following: location information, spatial information, area information, time information, material information, color information, piping and wiring information, and layer information.

[0089] This allows for the identification of a second location based on multiple different data points, thereby improving the accuracy of identifying locations requiring modification in the building's visual data.

[0090] In some embodiments, location information includes, for example, the specific coordinates of various areas, equipment, and piping within a building. For example, location information for a conference room, such as the coordinates (x=10, y=20, z=0) of a representative point (e.g., the center point) of the conference room, is determined based on a predetermined location coordinate system. The coordinate origin of the location coordinate system includes, but is not limited to, the geometric center of the building, the center of a functional area within the building (e.g., a conference room, an office), or the center of an area where users frequently engage in activities (e.g., a corridor, a lobby).

[0091] In some embodiments, different coordinate origins may be selected depending on the actual requirements. For example, using the geometric center of a building as the coordinate origin is suitable for localizing the overall layout, using the center of a building's functional area as the coordinate origin is suitable for localizing local requirements, and using an area with high user activity as the coordinate origin is suitable for localizing the optimization of the user experience.

[0092] In some embodiments, spatial information includes, for example, the size and shape of each area within a building. For example, the size of a conference room is 10m x 5m x 3m.

[0093] In some embodiments, area information includes, for example, the function and attributes of each area within a building. For example, the function of a conference room is for video conferencing, and its attributes are sound insulation and good natural light.

[0094] In some embodiments, the time information includes, for example, time information about the transitional process of a building at different time stages. For example, it includes time information about the process of a building being progressively constructed from the structural frame to piping and wiring, interior framing, and finishing work.

[0095] In some embodiments, material information includes, for example, the material attributes of each area within a building. For instance, the wall material of a conference room is gypsum board, and the floor material is carpet.

[0096] In some embodiments, the color information includes, for example, the color attributes of each area within a building. For instance, the color of the walls in a conference room is white, and the color of the floor is gray.

[0097] In some embodiments, the piping and wiring information includes, for example, the piping and wiring and connection points in each area of ​​a building. For example, the power piping and wiring in a conference room is from (x=2, y=1, z=0.5) to (x=5, y=1, z=2.5).

[0098] In some embodiments, the layer information includes, for example, the relative positional relationships between different areas within a building, and the relative positional relationships between systems and equipment within each area.

[0099] In some embodiments, the location reference information identified in step 103 includes at least one of a set of location reference information corresponding to a plurality of spatial location regions in a predetermined first visual data of the building. The location reference information corresponding to the plurality of spatial location regions in the first visual data is predetermined, for example, by a generative AI model. For example, the generative AI model converts the first visual data of the building into a format that it can read (e.g., a text format such as XML or IFC), and, in conjunction with the generative AI model's knowledge base and architectural design standards, demarcates the spatial location regions in the first visual data of the building and identifies the location reference information corresponding to each detailed spatial location region in the first visual data.

[0100] For example, if there is a first visual data of a simple office building, the first visual data includes floors, areas, rooms, and equipment of the office building, and the partitioned spatial location area is further refined based on the floors, areas, rooms, and equipment. For example, the office area may be further partitioned from the entire block area into eight smaller areas depending on the area and functional requirements, and the generating AI model may more accurately map user requests to specific locations in the building in subsequent steps by more accurately understanding the building structure and the location of equipment. In this embodiment, the predetermined location reference information is text-type data for describing the spatial location area and its specific location, which is further partitioned in the first visual data of the building for each floor, area, room, and equipment.

[0101] In some embodiments, the partitioning of the building's spatial location area may be performed sequentially at different levels of granularity. For example, first, an initial partitioning is performed on the building's spatial location area for each system function of the building, then the space to which the system belongs is further partitioned for each wall surface, and element correspondences are made for each wall surface to which the system belongs, according to, for example, architectural design standards and user personalization requirements.

[0102] The method of partitioning the spatial location area for each building system function and wall surface as described above has the following advantages: (1) Direct association of user requirements with systems: By partitioning for each building system function (e.g., lighting, air conditioning, security, etc.), each user requirement can be directly associated with a specific system function, helping to ensure that proposals effectively support the functional requirements of each system; (2) Individual optimization of system functions: Each building system has its own specific functional goals and technical requirements, and by partitioning for each building system function, it is possible to ensure that each system function corresponding to the user requirement is individually optimized; and (3) Improved accuracy of spatial location area partitioning: After partitioning for each building system function, the spatial location area is further refined for each wall surface, allowing for more accurate processing of design requirements for each space, including the placement of systems such as lighting, air conditioning, and security. This contributes to the generated AI model making finer decisions in the spatial layout, and ultimately has the advantage of accurately mapping user requirements to specific physical locations.

[0103] In some embodiments, the knowledge base of the generating AI model is generated by, for example, a step of acquiring historical proposed project data and architectural design standards, wherein the proposed project data refers to data showing the correspondence between user requirements and building system functions in historical proposed projects, and the proposed project data includes the historical user requirements and the proposals ultimately accepted by the user corresponding to the user requirements; a step of converting the acquired historical proposed project data and architectural design standards into AI-readable vectors; and a step of storing the vectors in a database to form the knowledge base of the generating AI.

[0104] In some embodiments, building design standards include at least one of various national, regional, or industry standards relating to buildings.

[0105] This allows for the identification of location reference information based on various criteria, and further improves the accuracy and referentiality of the generated location reference information.

[0106] Tables 1 to 3 below are examples of some building design standards related to embodiments of the present invention. Here, Table 1 shows the ratio of the air-conditioned area to the building area in a building, Table 2 shows the approximate building area index for the air conditioning machine room, and Table 3 shows the cooling estimation index (W / m) based on the air conditioning cooling load method. ２ (Indicates the air-conditioned area.)

[0107]

[0108]

[0109]

[0110] In some embodiments, depending on the content included in the location information relating to the first location requiring modification in the building's target system, the location reference information of the second location associated with the location information relating to the first location requiring modification in the building's target system may be identified in a different form from the first visual data.

[0111] In some embodiments, when the location information relating to a first location requiring modification in the building's target system includes a first location in the building, step 103, based on a second artificial intelligence model, identifies location reference information of a location associated with the location information among the first visual data, and includes using the second artificial intelligence model to identify location reference information of a location associated with the first location among the first visual data based on the first location.

[0112] This allows for the accurate identification of location reference information based on a clearly defined first location in the location information. In other words, because the first location is clearly given, the identified location reference information is more accurate, and furthermore, the visual data generated based on said location reference information better matches the user requirements.

[0113] In some embodiments, when the location information relating to a first location requiring modification in the building's target system does not include the first location in the building, step 103, which identifies location reference information of a location associated with the location information in the first visual data based on a second artificial intelligence model, includes the step of generating location reference information of the first location associated with the first location in the first visual data using the second artificial intelligence model based on the location information relating to the first location requiring modification in the building's target system and building design criteria information.

[0114] This allows for the accurate generation of location reference information based on location information and architectural design standards information, even if the location information does not include a clearly defined location.

[0115] The following is an example of identifying location reference information based on location information and building design standard information for a first location requiring modification in the building's target system.

[0116] First, the cooling load is calculated from the basic parameters of the conference room (e.g., area, occupancy density, equipment heat generation, lighting power, building orientation, and exterior wall material). For example, for a 50 square meter conference room, calculating the cooling load for people, equipment, lighting, solar radiation, and exterior wall heat transfer results in a total cooling load of 7.5 kW and a cooling index of 150 W / m². ２ This step provides a basis for selecting the model of air conditioning equipment.

[0117] If the specific location of the air conditioning unit is not clearly specified in the location information for the first location requiring modification in the building's target system, location reference information is generated based on the building design standards. For example, according to the building design standards, the air conditioning unit should be installed in a location where air circulation is good and direct blowing towards occupants should be avoided. In conjunction with the layout of the conference room (e.g., 10m long, 5m wide, 3m high), the air conditioning unit is specified to be installed on one wall of the conference room, 2.5m above the ground. Therefore, the specific coordinates for installing the air conditioning unit can be specified as (2,0,2.5), and this information can be used as location reference information. At the same time, by further specifying the direction of the airflow from the air conditioning unit, it is possible to ensure that the airflow covers the entire conference room.

[0118] In some embodiments, the method for locating building visual data according to embodiments of the present invention further includes the step of associating at least one of a user request, a suggestion to the user, an updated user request, and an updated suggestion to the user with corresponding location reference information.

[0119] In some embodiments, the "location reference information" associated with at least one of the user request, the user's suggestion, the updated user request, and the updated user's suggestion is location reference information for a second location in first visual data, associated with the relevant location information (i.e., location information relating to a first location in the building's target system that requires modification) among at least one of the user request, the user's suggestion, the updated user request, and the updated user's suggestion.

[0120] This allows us to associate user requests with corresponding locations in the building's visual data, improving the degree of agreement between user requests and the actually generated proposed visual data.

[0121] Figure 2 is a schematic diagram of the step of associating location reference information according to an embodiment of the present invention. As shown in Figure 2, the step of associating at least one of user requests, user suggestions, updated user requests, and updated user suggestions with corresponding location reference information includes: step 201 of using a third artificial intelligence model to refine at least one of user requests, user suggestions, updated user requests, and updated user suggestions and obtain a first user request; step 202 of decomposing the first request for each system function of the building and obtaining a second request corresponding to each system function of the target system; and step 203 of hierarchically extracting the second requests according to the location reference information and obtaining a plurality of user sub-requests that correspond to each system function and include corresponding location reference information.

[0122] This is advantageous for generating accurate and actionable visual data by precisely mapping detailed user sub-requests to specific locations in the building model.

[0123] In some embodiments, the third artificial intelligence model is, for example, a generative AI model.

[0124] In some embodiments, in step 201, at least one of the user request, the suggestion to the user, the updated user request, and the updated suggestion to the user is input to a third artificial intelligence model, and combined with the knowledge base of the generated AI model to obtain a first request that refines at least one of the user request, the suggestion to the user, the updated user request, and the updated suggestion to the user.

[0125] In some embodiments, in step 202, the corresponding processing node further breaks down the first requirements, which are detailed for each system function of the building, to obtain a second requirement corresponding to each system function of the target system.

[0126] The "elaboration" procedure in step 201 and the "decomposition" procedure in step 202 above refine at least one of the following from a vague or high-dimensional description to a specific and actionable technical requirement: user requirements, proposals to the user, updated user requirements, and updated proposals to the user. This procedure includes, for example, clarifying the specific target of the user requirements or proposals to the user (e.g., equipment type), identifying the spatial location (e.g., room coordinates), quantizing technical parameters (e.g., power, color temperature), analyzing the relevance of the requirements (e.g., compatibility with existing systems), and generating actionable sub-requirements (e.g., wiring, implementation, debugging). The refined first requirements can be accurately mapped to the first visual data of the building, providing clear input to subsequent steps.

[0127] For example, a user requirement might be that the user wants to add a set of video conferencing equipment, including a camera, microphone, and display, to a conference room, and that these devices be properly powered and connected to the network. The second requirement obtained by refining and breaking down the user requirement in steps 201 and 202 includes system requirements and related function requirements, such as managing the implementation and operation of equipment such as cameras, microphones, and displays for the audio-video system, providing power to the video conferencing equipment for the power system, and ensuring network connectivity for the video conferencing equipment for the network system. The requirements for the system's related functions include, for example, that the camera be mounted at the front of the conference room, at a height of 2.5m, and have a field of view that covers the entire conference room; that the microphone be mounted in the center of the conference room, at a height of 2m, and ensure clear sound capture; that the display be mounted at the front of the conference room, at a height of 1.5m, and easy to view; that for power supply, it may be necessary to add new outlets or use extension cords to ensure that all equipment is properly powered; and for network connectivity, it may be necessary to add new network interfaces or use a wireless network to ensure that all equipment can connect to the network.

[0128] In some embodiments, when user requirements are relatively vague, the generated AI model can supplement and expand upon user requirements based on at least one of the historical proposed projects and architectural design standards.

[0129] As an example of supplementing and expanding user requirements based on historical proposed projects, data collection can be used to obtain requirement data and design proposals from historical proposed projects similar to the user's requirements. For example, design proposals for video conferencing systems in other office buildings can be collected. Subsequently, these proposed projects can be analyzed using generation AI to extract common requirements and design patterns. For example, the analysis might reveal that most video conferencing systems in office buildings include equipment such as cameras, microphones, and displays. Based on the analysis results, the customer's potential requirements can then be expanded. For example, the customer might be advised to add cameras, microphones, and displays to their conference rooms, along with specific equipment model selections and installation locations.

[0130] As an example of supplementing and expanding user requirements based on architectural design standards, a generative AI model can be used to infer typical customer requirements based on architectural design standards. For example, it might infer that the lighting requirement for a conference room is 300 lumens / m2 based on lighting standards. Then, based on the inference results, the AI ​​can supplement the customer's typical requirements, for example, by suggesting that the customer install lighting fixtures that meet the lighting standards in the conference room, and providing specific installation locations and brightness requirements.

[0131] In some embodiments, in step 203, a second request corresponding to each system function of the target system identified in step 202 is extracted hierarchically based on location reference information corresponding to each spatial location region in a predetermined first visual data, and a plurality of user sub-requests corresponding to each system function, including location reference information of the corresponding spatial location region in the first visual data of the target system to which the system function belongs, are obtained, thereby achieving an association between user requests and location reference information in the first visual data of the building.

[0132] This ensures the generation of accurate and functional visual data by obtaining user sub-requests that include location reference information in the building's first visual data, thereby enabling accurate mapping of user requests to specific locations in the building's first visual data. Furthermore, by associating user requests with location reference information in the building's first visual data (e.g., coordinates, area, equipment location, etc.), the specific implementation location of the user request in the building can be clarified (e.g., install a light fixture at (x=12, y=22, z=2.5) in office A), thus avoiding discrepancies between user requests and the actual building layout. This not only improves the accuracy of proposals but also supports rapid location identification and adjustment when user requests are updated, improving overall efficiency and customer satisfaction.

[0133] In some embodiments, step 203 reads the position reference information corresponding to each of the spatial position regions in the first visual data, which is predetermined based on the generated AI model, and maps the position reference information to the second request.

[0134] The following describes the steps for reading location reference information based on a generated AI model, using an example. The generating AI model reads location reference information by: (1) data preprocessing: converting the first visual data of the building into IFC format and cleaning the data; (2) feature extraction: extracting the spatial layout of the conference room (e.g., conference room size 10m x 5m x 3m), equipment locations (e.g., camera location coordinates (x=5, y=1, z=2.5)) and piping and wiring (e.g., power piping has location coordinates (x=5, y=1, z=2.5) from location coordinates (x=2, y=1, z=0.5)); (3) semantic understanding: analyzing text information in the first visual data of the building to identify the type and function of the camera; (4) location parameter generation: generating the camera location coordinates (x=5, y=1, z=2.5) and attribute information such as "Type: High-resolution camera, Resolution: 1080p"; and (5) data validation: checking the consistency between the camera location and the power piping to ensure that the camera is properly powered.

[0135] The following describes the steps for mapping a second request to corresponding location reference information based on a generative AI model, using an example. The generative AI model establishes a mapping relationship between the second request and location reference information through the following steps: (1) Semantic matching: Using the semantic understanding capabilities of the generative AI model, it analyzes the similarity and relationship between the user's second request and existing parameters, for example, by semantic matching, it associates the user request "install a camera in the conference room" with the location (x=10, y=20, z=0) and size (10m x 5m x 3m) of the conference room; (2) Rule definition: Matching rules are defined in advance based on architectural design standards and user requests, and specific attributes of the user's second request are matched with existing location reference information, for example, by setting the camera to be installed on the front side of the conference room and at a height of 2.5m; and (3) Location calculation: Based on the matching rules and matching results, it calculates the specific location of the user request in the first visual data of the building. For example, the camera mounting position is calculated as (x=12, y=22, z=2.5).

[0136] In some embodiments, the location of a user request in the first visual data of a building is achieved by dynamically adjusting the granularity.

[0137] For example, in the early stages of a project, the requirements can be localized at a coarser, second-level granularity, such as localizing the entire conference room as a single area. As the project progresses, the granularity can be refined, for example, by dividing the conference room into sub-areas such as the front, back, left, and right sides, to localize the requirements more precisely. Subsequently, the granularity and accuracy of localization can be adjusted based on customer feedback. For example, the camera mounting position and angle can be adjusted based on customer feedback regarding the camera's field of view.

[0138] In some embodiments, a method for determining the location of building visual data according to an embodiment of the present invention further includes the steps of determining a second location in first visual data according to first visual data of a building and location reference information of a second location associated with location information relating to a first location in the first visual data that requires modification in a target system, and displaying the first visual data, the second location, and the location reference information.

[0139] This allows for the display of first visual data, second location and location reference information, making it easier for users to intuitively understand the user's requested location in the first visual data, thereby further improving the user experience.

[0140] In some embodiments, the display device displays one or more visualization modules that can be operated by the user (e.g., by clicking or touching) simultaneously with or after displaying the first visual data, second location, and location reference information. The user may trigger at least one of the following operations by operating the corresponding visualization module: an operation to confirm the second location, and an operation to obtain updated information for the second location. When the user operation triggers the "operation to obtain updated information for the second location," the user or proposer may be prompted to input the updated information for the second location in the form of an audio broadcast, text, image, etc. Furthermore, the user or proposer may input the updated information for the second location in the form of voice input, text input, file import, click operation, etc. By updating the second location and location reference information based on the updated information for the second location, the second location can be corrected and its accuracy improved.

[0141] This allows users to quickly and intuitively determine whether the second position is accurate, and they can easily verify or provide feedback to further improve the user experience.

[0142] In some embodiments, a method for determining the location of building visual data according to embodiments of the present invention further includes the step of generating second visual data of a building that matches at least one of a user request, a suggestion to the user, an updated user request, and an updated suggestion to the user, based on first visual data of the building and location reference information of a second location associated with location information relating to a first location in the building's target system that requires modification within the first visual data.

[0143] For example, in the above example, in which location reference information is identified based on location information and building design standard information regarding a first location requiring modification in the building's target system, after identifying the location reference information for the location where the air conditioning equipment will be installed (e.g., specific coordinates (2,0,2.5)), the data model corresponding to the air conditioning equipment is precisely positioned at a predetermined location in the first visual data of the building (e.g., the location at coordinates (2,0,2.5)) based on the identified location reference information, generating a second visual data of the building, adjusting the direction of the air outlets, and ensuring that the airflow covers the entire conference room. As a result, the generated second visual data not only accurately reflects the location and function of the air conditioning equipment but also conforms to building design standards and user requirements.

[0144] This ensures that user requirements can be accurately mapped to specific locations in the building's visual data, improves the efficiency of processing when user requirements are updated, avoids conflicts and errors between system functions, and enhances the efficiency and accuracy of visual data that matches user requirements. Furthermore, it makes it easier for users to quickly and intuitively understand proposals, thereby improving the success rate of proposals.

[0145] Figure 3 is a schematic diagram of the steps for generating second visual data according to an embodiment of the present invention. As shown in Figure 3, the steps for generating second visual data of a building that matches at least one of user requests, suggestions to the user, updated user requests, and updated suggestions to the user include: step 301, at each processing node associated with location information relating to a first location requiring modification in the building's target system, generating third visual data of a system function corresponding to each processing node based on first visual data of the building, at least one of user requests, suggestions to the user, updated user requests, and updated suggestions to the user associated with each processing node, and location reference information associated with at least one of user requests, suggestions to the user, updated user requests, and updated suggestions to the user; and step 302, integrating the third visual data of each system function to obtain second visual data of the building. The second visual data is complete visual data of the building that matches the user requests.

[0146] This allows each processing node to generate and integrate corresponding visual data to obtain second visual data, thereby improving the efficiency and accuracy of second visual data generation. Furthermore, by processing corresponding processing tasks for each node, it can adapt to changes in processing content, resulting in greater flexibility. In addition, each processing node may use an artificial intelligence model or algorithm best suited to its corresponding processing content, and different processing nodes may use different artificial intelligence models or algorithms. Therefore, it is possible to use the optimal model for different processing tasks, resulting in better processing quality and higher efficiency.

[0147] In some embodiments, in step 301, each processing node associated with location information relating to a first location requiring modification in the building's target system analyzes the objects necessary to satisfy each user sub-request identified in step 203 in combination with a generated AI model, obtains a data model corresponding to the object from a pre-established data model knowledge base, and after obtaining the data model corresponding to the object necessary to satisfy the user sub-request, identifies the specific spatial arrangement in the corresponding region of the data model corresponding to the object based on the generated AI model, in combination with location reference information included in the user sub-request (see step 203), and after identifying the specific spatial arrangement of the data model of the object necessary to satisfy the user sub-request, generates a third visual data of the building, including the user sub-request, based on the first visual data of the building, using the location reference information included in the user sub-request, the data model of the object identified in the above step, and the specific spatial arrangement of the data model of the object identified in the above step.

[0148] In some embodiments, in the procedure for generating third visual data based on a generative AI model, the knowledge base of the generative AI model, which is built based on the project materials of the aforementioned history proposal, is used to perform matching in the knowledge base based on key information in the user request. The generative AI model then generates proposed text based on the matching result, generates suggested words based on the proposed text, and instructs the generative AI model to generate third visual data using these suggested words. This improves the accuracy of the generated third and second visual data.

[0149] In some embodiments, taking into account differences in the nature and content of user subrequests, the objects required to satisfy the user subrequests of the present invention include at least one of an entity object or an abstract object. An entity object is, for example, something that has a physical form, such as an air conditioner. When a user subrequest relates to a system function, process optimization, or an abstract concept (e.g., improving the user experience), the user subrequest does not directly correspond to a concrete entity object but corresponds to an abstract object. When a user subrequest does not correspond to an entity object but corresponds to an abstract object, it is not necessary to add an entity object to satisfy the user subrequest, and the number and spatial layout of existing systems and equipment may be adjusted, and if an entity object corresponding to the user subrequest has already been established, the attributes of the established entity object (including, but not limited to, location, power, color, etc.) may be updated to satisfy the user subrequest.

[0150] In some embodiments, in step 301, the step of generating third visual data of the system function corresponding to each processing node at each processing node associated with location information relating to the first location requiring modification in the building's target system may be processed in parallel. This improves the efficiency of generating the second visual data of the building.

[0151] In some embodiments, in step 302, if the third visual data is obtained based on the user request or proposal made to the user initially submitted, the third visual data for each system function is integrated with the first visual data for the building to obtain the second visual data for the building. If the third visual data is obtained based on the updated user request or proposal made to the user after the update, the third visual data for each system function is integrated with the second visual data for the building generated based on the previous user request or proposal made to the user to obtain the second visual data for the building after the update.

[0152] In some embodiments, a method for locating building visual data according to embodiments of the present invention further includes the steps of: obtaining user feedback information on generated second visual data; and, if the feedback information includes updated user requests, generating updated second visual data based on updated user requests.

[0153] This allows for updating the second set of visual data in response to user feedback, thereby improving the degree of agreement between the actually generated suggested visual data and user requirements, and further enhancing the user experience.

[0154] In some embodiments, user feedback information includes, but is not limited to, adjustments to the position in the second visual data. User feedback information is collected based on, for example, at least one of the following: voice interaction data with the user, a request data table filled out by the user, or user request record information. This application is not limited thereto.

[0155] In some embodiments, the method for locating building visual data according to embodiments of the present invention further includes the steps of obtaining updated suggestions for the user and generating updated second visual data based on the updated suggestions for the user.

[0156] This allows for updating the second visual data based on the updated user suggestions, thereby improving the degree of agreement between the actually generated suggestion visual data and user requests, and further enhancing the user experience.

[0157] In some embodiments, the procedure for generating the updated second visual data involves performing the same processing as in steps 201 to 203 on the updated user request and the updated suggestions to the user to generate the updated user sub-request including location reference information. Furthermore, in the corresponding processing node, the same processing as in steps 301 and 302 is performed on the updated user sub-request including location reference information to re-identify the data model and spatial arrangement corresponding to the target of the updated user sub-request, and further generate the updated third visual data of the building, including the updated user sub-request. The updated third visual data and the previously generated second visual data are then integrated, for example, by replacing a portion of the data in the previously generated second visual data corresponding to the updated third visual data with the updated third visual data to obtain the updated complete visual data of the building that matches the updated user request.

[0158] This allows for the updating of the second visual data simply by generating visual data corresponding to updated user requests or suggestions for the user and integrating it with the previously generated second visual data, when updated user requests or suggestions for the user exist. This improves the efficiency and accuracy of updating the second visual data.

[0159] In some embodiments, the system efficiently responds to changes in user requirements by including further steps of data integration, validation, and adjustment before obtaining the final second visual data of the building.

[0160] In some embodiments, data integration refers to integrating user-requested location reference information with existing parameters in the building's primary visual data to ensure coordination between all relevant systems in the building.

[0161] For example, if the user requirement is to install a camera in a conference room, the specific data integration steps would include, for example, (1) data alignment: aligning the camera's installation location (e.g., location coordinates x=5, y=1, z=2.5) with the building's first visual data coordinate system; (2) spatial layout integration: associating the camera's location with the conference room's spatial layout and checking whether it conflicts with existing equipment (e.g., lighting fixtures); (3) system function integration: adding a new outlet to the camera with location coordinates (x=4, y=1, z=0.5) and a new network interface with location coordinates (x=3, y=1, z=0.5); and (4) attribute integration: adding the camera's power information (e.g., 50W) to the power system's load calculation.

[0162] In some embodiments, the integrated data is in text format such as XML or IFC, and may be directly converted to visual data by a data conversion tool to facilitate intuitive and quick viewing by the user.

[0163] In some embodiments, verification and adjustment refer to verifying the technical feasibility of user requirements, verifying the feasibility of user requirements in digital form such as pipe collision detection and structural load simulation based on first visual data of the building, and / or generating modification advice such as pre-installed equipment interfaces and spatial layouts through scalability design.

[0164] For example, if the user requirement is to install a camera in a conference room, the specific verification and adjustment steps would include, for example, (1) consistency check: verifying whether the camera's position coordinates (x=5, y=1, z=2.5) and functionality (field of view covering the entire conference room) meet user requirements and industry standards; (2) collision detection: checking whether the camera will collide with lighting fixtures or air conditioning vents; (3) functionality verification: verifying whether the power of the newly added outlets meets the camera's requirements and whether the bandwidth of the newly added network interface meets the camera's requirements; (4) simulation and visualization: simulating the camera's field of view in the building's first visual data to ensure it covers the entire conference room; (5) user feedback: demonstrating the camera's position and functionality to the customer and obtaining user feedback information; and (6) adjustment and optimization: adjusting the camera's position if it is determined that it will collide with lighting fixtures, and optimizing the load distribution of the power system if it is determined that the power system load is insufficient.

[0165] By verifying technical feasibility and designing for scalability, we can eliminate unreasonable or technically impossible user requirements, or parts thereof, resulting in more professional and rational visual data. Furthermore, we can present users with more potential modification suggestions, improving the user experience and the success rate of suggestions.

[0166] In some embodiments, the method for locating building visual data according to embodiments of the present invention further includes the step of displaying the generated second visual data using a display device.

[0167] The displayed second visual data includes the second visual data initially generated based on the user request and the content of the proposal to the user, and the second visual data updated based on the updated user request and the content of the proposal to the user.

[0168] This allows for the display of second visual data, making it easier for users to quickly and intuitively understand proposals, and enabling them to easily review or submit feedback, further improving the user experience. This means that even when building design data is complex and voluminous, and users are not familiar with building design and cannot express clearly defined modification requests, the visualization format allows for the presentation of building design proposals that match user requirements in a visually understandable way for the user to review. Furthermore, by linking a large-scale language model with distributed processing nodes, the content of user requests or proposals to the user can be refined, allowing for a more accurate understanding and processing of user requests, and enabling the generation of visual data that matches user requirements more accurately and efficiently. For example, user requirements can be met by generating visual data only once or a few times.

[0169] In some embodiments, the display device displays, simultaneously with or after displaying the generated second visual data, one or more visualization modules that can be operated by the user (e.g., by clicking, touching, etc.), which are displayed, for example, on (overlapping with) the second visual data or outside (not overlapping with) the second visual data. The user may, by operating the visualization module, trigger at least one of the following operations: confirming the second visual data, obtaining an updated user request, or obtaining an updated suggestion for the user. When the user operation triggers the "obtaining an updated user request," the user may be prompted to input the updated user request in the form of an audio broadcast, text, image, etc. Furthermore, the user may input the updated user request in the form of voice input, text input, file import, etc.

[0170] This makes it easier for users to quickly and intuitively understand suggestions, and allows them to easily review or submit feedback to further improve the user experience.

[0171] In some embodiments, if at least one of the updated user request and the updated suggestion to the user is obtained, the method for locating building visual data according to embodiments of the present invention further includes the step of updating the workflow.

[0172] In some embodiments, the step of updating a workflow further includes the step of using a fourth artificial intelligence model to update the flow architecture of the first workflow based on at least one of the updated user requests and the updated suggestions to the user, thereby obtaining a second workflow, the step of updating the flow architecture of the first workflow includes the steps of deleting a first processing node in the first workflow or adding a second processing node to the first workflow associated with at least one of the updated user requests and the updated suggestions to the user, and linking the first processing nodes that have not been deleted or linking the first processing nodes that have not been deleted with the newly added second processing nodes, according to a set rule.

[0173] For example, if the user's initial request is to design a lighting and air conditioning system for an office building, the existing workflow nodes may include, for example, (1) a lighting system node: which handles the selection and installation of lighting equipment, and (2) an air conditioning system node: which handles the selection and installation of air conditioning equipment. If the updated user request includes adding a set of video conferencing systems to a conference room, the existing workflow nodes may perform the following operations: (1) modify the lighting system node: the newly added video conferencing system requires extra lighting support, so the parameters of the lighting system node are adjusted to increase the lighting requirements for the conference room, for example, by increasing the number and brightness requirements for the conference room lights; (2) remove redundant nodes: if the original workflow has redundant nodes unrelated to the video conferencing system (for example, an outdated security system node), these nodes may be removed to simplify the workflow; and (3) add a new video conferencing system node: in response to the customer's new request, one video conferencing system node is added to handle the selection and location distribution of equipment such as cameras, microphones, and displays.

[0174] This improves workflow construction efficiency and data location efficiency by updating the corresponding processing node in the workflow whenever user requests or suggestions to the user are updated.

[0175] The user request decomposition and mapping, the association of user requests with location reference information, data integration, and the visual data generation procedures according to the above embodiment of the present invention are all implemented in corresponding processing nodes. This allows for processing of user requests in the associated processing node while reusing other processing nodes in the processing flow, thereby improving processing efficiency.

[0176] Figure 4 is a flowchart of a method for determining the location of building visual data according to an embodiment of the present invention, and Figure 5 is a schematic diagram of the flow of a method for determining the location of building visual data according to an embodiment of the present invention. As shown in Figures 4 and 5, the method for determining the location of building visual data includes: Step 401: A step of obtaining a user request or a proposal to the user; Step 402: A step of determining whether the user request or the proposal to the user is being submitted for the first time, and if YES, executing Step 403, and if NO, i.e., if the user request is an updated user request or the proposal to the user is an updated proposal to the user, executing Step 409; Step 403: A step of detailing and breaking down the user request or the proposal to the user and obtaining a request corresponding to the target system.

[0177] For example, as shown in Figure 5, the user request or proposal to the user is broken down into multiple requirements corresponding to the air conditioning system, lighting system, and security system. The execution of step 403 can be seen by referring to the embodiments of steps 201 and 202 above, and redundant explanations are omitted here.

[0178] Step 404: At the processing node corresponding to each target system, the request corresponding to each target system is further refined, and multiple user sub-requests corresponding to each system are obtained.

[0179] For example, as shown in Figure 5, the requirements corresponding to the air conditioning system are further refined into multiple "tier 1 requirements and corresponding location reference information" and "tier 2 requirements and corresponding location reference information" corresponding to the air conditioning system; the requirements corresponding to the lighting system are further refined into multiple "tier 1 requirements and corresponding location reference information" corresponding to the lighting system; and the requirements corresponding to the security system are further refined into multiple "tier 1 requirements and corresponding location reference information" corresponding to the security system. The execution of step 404 can be seen by referring to the embodiment relating to step 203 above, and redundant explanations are omitted here.

[0180] Step 405: In each processing node corresponding to each target system, a third visual data corresponding to the target system is generated in response to the user sub-request of the target system obtained in Step 404.

[0181] For example, as shown in Figure 5, a processing node corresponding to the air conditioning system generates visual data of the air conditioning system in the building, including the corresponding user subrequest; a processing node corresponding to the lighting system generates visual data of the lighting system in the building, including the corresponding user subrequest; and a processing node corresponding to the security system generates visual data of the security system in the building, including the corresponding user subrequest. The execution of step 405 can be described by referring to the embodiment relating to step 301 above, and a redundant explanation is omitted here.

[0182] Step 406: Integrate the third visual data corresponding to each target system to obtain second visual data of the building that matches the user requirements. The execution of Step 406 can be seen by referring to the embodiment of Step 302 above, and a redundant explanation is omitted here.

[0183] Step 407: Obtain user feedback information.

[0184] Step 408: Determine whether the feedback information includes updated user requests or whether updated suggestions for the user have been obtained. If YES, perform step 409; if NO, perform step 410.

[0185] Step 409: Extract the updated parts from the updated user requests or the updated proposals to the user, identify the target system corresponding to the updated parts, and return to Step 404.

[0186] In step 404, the user sub-request is regenerated in the processing node of the target system corresponding to the updated portion; then, in step 405, the third visual data corresponding to the target system is regenerated; and in step 406, the regenerated third visual data corresponding to the target system is integrated with the second visual data of the building generated based on the previous user request or the previous proposal to the user to obtain the updated second visual data.

[0187] Step 410: Output second visual data of the building that matches the user requirements.

[0188] As demonstrated in the above embodiment, the present invention utilizes an artificial intelligence model to identify a second location reference information associated with location information relating to a first location requiring modification in the building's target system, thereby accurately associating the first location requiring modification with the location in the first visual data. In other words, it enables accurate identification of the location requiring modification in the building's first visual data. This allows for the accurate generation of visual data including the location requiring modification in the target system based on that location.

[0189] Furthermore, based on the above-mentioned location reference information and the first visual data of the building, it is possible to accurately generate visual data that matches the user's request or the content of the proposal to the user. This is advantageous for the user to intuitively and quickly understand the content of the proposal, thereby improving the proposal success rate and user experience.

[0190] Furthermore, by identifying the processing node associated with the location information based on the location information of the first location requiring modification in the building's target system, and by identifying the location reference information of the second location associated with the location information within the first visual data only in the identified processing node, data from other processing nodes in the processing flow can be reused when the user request or the content of the proposal to the user changes. This means that only the data of the processing node corresponding to the updated user request or the content of the proposal to the user needs to be modified, thereby improving the efficiency of proposal generation.

[0191] <Examples relating to the second aspect> An embodiment relating to the second aspect of the present invention provides a location identification device for building visual data. Figure 6 is a schematic diagram of a location identification device for building visual data according to an embodiment of the present invention. As shown in Figure 6, the location identification device 600 for building visual data includes: an acquisition module 601 that acquires location information relating to a first location requiring modification in the building's target system and first visual data of the building; a first identification module 602 that identifies a processing node associated with the location information based on a first artificial intelligence model; and a second identification module 603 that, at the processing node, identifies location reference information of a second location associated with the location information among the first visual data based on a second artificial intelligence model, wherein the location reference information is reference information for identifying the second location in the first visual data of the first location requiring modification in the target system; the first artificial intelligence model is based at least on the relationship between location information relating to the first location requiring modification in the target system and a processing node in the target system; and the second artificial intelligence model is based at least on the relationship between location information relating to the first location requiring modification in the target system and location reference information of a second location in the first visual data.

[0192] The location identification device for building visual data according to an embodiment of the present invention may implement the location identification method for building visual data described in the embodiment according to the first aspect of the present invention. Since the principle by which the location identification device for building visual data solves the problem is similar to that of the location identification method for building visual data, the implementation of the location identification device for building visual data can refer to the implementation of the location identification method for building visual data, and redundant explanations are omitted here.

[0193] An embodiment according to a second aspect of the present invention further provides a building visual data generation and display device. Figure 7 is a schematic diagram of a building visual data generation and display device according to an embodiment of the present invention. As shown in Figure 7, the building visual data generation and display device 700 includes: a memory 701 in which a computer program is stored; a processor 702 that, when the computer program is executed, implements a location identification method for building visual data described in any embodiment according to the first aspect of the present invention, obtains location reference information for a second location associated with location information among the first visual data, and generates second visual data according to the first visual data and location reference information; and a display 703 that displays the second visual data of the building.

[0194] In some embodiments, the display 703 further displays first visual data of a building and second location reference information of the first visual data associated with location information relating to a first location in the target system that requires modification.

[0195] As a result, the present invention, based on an artificial intelligence model, identifies a second location reference information associated with location information relating to a first location requiring modification in the building's target system within the first visual data of the building. This accurately associates the first location requiring modification with the location in the first visual data, that is, it enables accurate identification of the location requiring modification in the first visual data of the building. Based on this, it is possible to accurately generate visual data including the location requiring modification in the target system.

[0196] Furthermore, based on the above-mentioned location reference information and the first visual data of the building, it is possible to accurately generate visual data that matches the user's request or the content of the proposal to the user. This is advantageous for the user to intuitively and quickly understand the content of the proposal, thereby improving the proposal success rate and user experience.

[0197] Furthermore, by identifying the processing node associated with the location information based on the location information of the first location requiring modification in the building's target system, and by identifying the location reference information of the second location associated with the location information within the first visual data only in the identified processing node, data from other processing nodes in the processing flow can be reused when the user request or the content of the proposal to the user changes. This means that only the data of the processing node corresponding to the updated user request or the content of the proposal to the user needs to be modified, thereby improving the efficiency of proposal generation.

[0198] <Examples relating to the third aspect> An embodiment relating to the third aspect of the present invention provides a suggestion system for buildings. Figure 8 is a schematic diagram of a suggestion system for buildings relating to an embodiment of the present invention. As shown in Figure 8, the suggestion system for buildings 800 includes at least one of the building visual data location device 600 and the building visual data generation / display device 700 described in the embodiment relating to the second aspect of the present invention. In the embodiments of the present invention, the implementation of the functions of the suggestion system for buildings can be described by referring to the relevant steps in the embodiments relating to the first and second aspects of the present invention, and redundant explanations are omitted here.

[0199] The proposed building system 800 may further include components not shown in Figure 8, and related technologies can be referenced.

[0200] As demonstrated in the above embodiment, the present invention utilizes an artificial intelligence model to identify a second location reference information associated with location information relating to a first location requiring modification in the building's target system, thereby accurately associating the first location requiring modification with the location in the first visual data. In other words, it enables accurate identification of the location requiring modification in the building's first visual data. This allows for the accurate generation of visual data including the location requiring modification in the target system based on that location.

[0201] Furthermore, based on the above-mentioned location reference information and the first visual data of the building, it is possible to accurately generate visual data that matches the user's request or the content of the proposal to the user. This is advantageous for the user to intuitively and quickly understand the content of the proposal, thereby improving the proposal success rate and user experience.

[0202] Furthermore, by identifying the processing node associated with the location information based on the location information of the first location requiring modification in the building's target system, and by identifying the location reference information of the second location associated with the location information within the first visual data only in the identified processing node, data from other processing nodes in the processing flow can be reused when the user request or the content of the proposal to the user changes. This means that only the data of the processing node corresponding to the updated user request or the content of the proposal to the user needs to be modified, thereby improving the efficiency of proposal generation.

[0203] Embodiments of the present invention further provide a computer-readable program that, when executed, causes a computer to perform a location identification method for building visual data described in any embodiment of the first aspect of the present invention.

[0204] Embodiments of the present invention further provide a computer-readable storage medium that stores a computer-readable program that causes a computer to execute a location identification method for visual data of any of the buildings described in the embodiment of the first aspect of the present invention.

[0205] Embodiments of the present invention further provide a computer program product that, when executed by a processor, causes a computer to execute any of the methods for determining the location of building visual data described in the embodiment of the first aspect of the present invention.

[0206] The apparatus and methods according to embodiments of the present invention may be implemented by hardware or by a combination of hardware and software. The present invention relates to a computer-readable program that, when executed by a logic component, causes the logic component to implement the above-described apparatus or component, or to implement the above-described method or step.

[0207] The present invention also relates to storage media for storing the aforementioned programs, such as hard disks, magnetic disks, optical disks, DVDs, and flash memory.

[0208] Furthermore, the limitations of each step according to the present invention are not considered to restrict the order in which the steps are performed, provided that they do not affect the implementation of the specific technical proposal. The steps described earlier may be performed first, later, or simultaneously, and as long as the technical proposal can be implemented, they should be considered to fall within the scope of protection of the present invention.

[0209] Although the present invention has been described above with reference to specific embodiments, those skilled in the art will understand that these descriptions are for illustrative purposes only and do not limit the scope of protection of the present invention. Those skilled in the art will also understand that various changes and modifications can be made to the present invention based on the spirit and principles of the invention, and such changes and modifications are also included within the scope of the present invention.

Claims

1. A method for determining the location of building visual data, comprising: acquiring location information relating to a first location requiring modification in a target system of the building and first visual data of the building; identifying a processing node associated with the location information based on a first artificial intelligence model; and, at the processing node, identifying location reference information of a second location associated with the location information among the first visual data based on a second artificial intelligence model, wherein the location reference information is reference information for identifying the second location in the first visual data of the first location requiring modification in the target system; the first artificial intelligence model is based at least on the relationship between location information relating to a first location requiring modification in the target system and a processing node in the target system; and the second artificial intelligence model is based at least on the relationship between location information relating to a first location requiring modification in the target system and location reference information of a second location in the first visual data.

2. The method according to claim 1, wherein, when the location information relating to a first location requiring modification in a building's target system includes the first location in the building, the step of identifying location reference information of a second location associated with the location information from the first visual data based on the location information includes the step of using the second artificial intelligence model to identify location reference information of a first location associated with the first location from the first visual data based on the first location, and when the location information relating to a first location requiring modification in a building's target system does not include the first location in the building, the step of identifying location reference information of a second location associated with the location information from the first visual data based on the location information relating to a first location requiring modification in a building's target system includes the step of using the second artificial intelligence model to generate location reference information of a first location associated with the first location from the first visual data based on the location information relating to a first location requiring modification in a building's target system and building design criteria information.

3. The method according to claim 1, wherein the location information relating to a first location in the building's target system that requires modification includes location information relating to at least one of a user request, a proposal to the user, an updated user request, and an updated proposal to the user.

4. The method according to claim 3, further comprising the step of associating at least one of the user request, the content of the suggestion to the user, the updated user request, and the updated content of the suggestion to the user with the corresponding location reference information.

5. The method according to claim 4, wherein the step of associating at least one of the user request, the content of the suggestion to the user, the updated user request, and the updated content of the suggestion to the user with the corresponding location reference information includes: using a third artificial intelligence model to refine at least one of the user request, the content of the suggestion to the user, the updated user request, and the updated content of the suggestion to the user, and obtaining a first request from the user; breaking down the first request for each system function of the building and obtaining a second request corresponding to each system function of the target system; and hierarchically extracting the second requests according to the location reference information and obtaining a plurality of user sub-requests corresponding to each system function and including the corresponding location reference information.

6. The method according to claim 4, further comprising the step of associating at least one of the user request, the content of the suggestion to the user, the updated user request, and the updated content of the suggestion to the user with a processing node associated with the corresponding location information.

7. The method according to claim 3, further comprising the step of generating second visual data of the building that matches at least one of the user request, the user proposal, the updated user request, and the updated user proposal, in accordance with first visual data of the building and location reference information of a second location associated with the location information among the first visual data.

8. The method according to claim 7, wherein the step of generating second visual data of the building that matches at least one of the user request, the user's suggestion, the updated user request, and the updated user's suggestion is the step of generating third visual data of a system function corresponding to each associated processing node at each associated processing node, based on first visual data of the building, at least one of the user request, the user's suggestion, the updated user request, and the updated user's suggestion associated with each processing node, and location reference information associated with at least one of the user request, the user's suggestion, the updated user request, and the updated user's suggestion; and the step of integrating the third visual data of each system function to obtain second visual data of the building.

9. The method according to claim 7, further comprising the steps of: displaying the second visual data using a display device; obtaining user feedback information for the displayed second visual data, and if the feedback information includes an updated user request, generating and displaying updated second visual data based on the updated user request; or obtaining updated suggestions for the user, and generating and displaying updated second visual data according to the updated suggestions for the user.

10. The method according to claim 3, wherein the processing node includes a processing node for a workflow, and further comprises the step of constructing a first workflow based on a first processing node associated with at least one of a user request and a suggestion to the user, using a fourth artificial intelligence model.

11. The method according to claim 10, further comprising the step of using a fourth artificial intelligence model to update the flow architecture of the first workflow based on at least one of the updated user request and the updated suggestions to the user, wherein the step of updating the flow architecture of the first workflow includes: deleting a first processing node in the first workflow or adding a second processing node to the first workflow associated with at least one of the updated user request and the updated suggestions to the user; and linking the first processing nodes that have not been deleted or linking the first processing nodes that have not been deleted with the newly added second processing nodes, according to a set rule.

12. The method according to claim 3, wherein at least one of the user request, the content of the suggestion to the user, the updated user request, and the updated content of the suggestion to the user is generated based on at least one of the voice interaction data with the user, the request data table entered by the user, and the user's request record information.

13. The method according to claim 3, wherein the user request includes at least one of the following: system information, equipment information, area information, and evaluation information for the building environment, and the proposed content to the user includes at least one of the following: system information, equipment information, area information, and evaluation information for the building environment.

14. A method according to any one of claims 1 to 13, further comprising: identifying the second location in the first visual data based on the first visual data of the building and location reference information of a second location associated with location information relating to a first location in the target system that requires modification; and displaying the first visual data, the second location, and the location reference information.

15. The method according to any one of claims 1 to 13, wherein the first visual data of the building includes at least one of parameter data, image data, video data, and proposal data of a multidimensional visualization model of the building, and parameter data, image data, video data, and proposal data of a multidimensional visualization model of the building generated based on the previous user request or the content of the previous proposal to the user.

16. The method according to any one of claims 1 to 13, wherein the position reference information includes at least one of position information, spatial information, region information, time information, material information, color information, piping and wiring information, and layer information.

17. A location identification device for building visual data, comprising: an acquisition module that acquires location information relating to a first location requiring modification in a building target system and first visual data of the building; a first identification module that identifies a processing node associated with the location information based on a first artificial intelligence model; and a second identification module that, at the processing node, identifies location reference information of a second location associated with the location information among the first visual data based on a second artificial intelligence model, wherein the location reference information is reference information for identifying the second location in the first visual data of the first location requiring modification in the target system; the first artificial intelligence model is based at least on the relationship between location information relating to a first location requiring modification in the target system and a processing node in the target system; and the second artificial intelligence model is based at least on the relationship between location information relating to a first location requiring modification in the target system and location reference information of a second location in the first visual data.

18. A device for generating and displaying visual data of a building, comprising: a memory in which a computer program is stored; a processor that, when the computer program is executed, realizes the method according to any one of claims 1 to 16, obtains position reference information of a second position associated with the position information among the first visual data, and generates second visual data according to the first visual data and the position reference information; and a display for displaying the second visual data of the building.

19. The apparatus according to claim 18, wherein the display further displays first visual data of the building, a second location associated with location information relating to a first location in the target system that requires modification, and location reference information.

20. A proposed system for a building, comprising the apparatus described in any one of claims 17 to 19.

Images