AR-oriented big data mining method and system

Abstract

According to the AR-oriented big data mining method and system provided by the embodiment of the invention, the to-be-analyzed virtual space is efficiently and accurately processed by deeply analyzing AR power service scene big data. After the AR power service scene construction request is monitored, the virtual space to be analyzed can be quickly determined, and related AR space data can be acquired. Based on the AR spatial data, the interactive migration node can be accurately identified, and then the cross fusion partition is determined, so that the reasonable layout of the virtual space and the fluency of interaction are ensured. Besides, by determining the derivative boundary partition and intelligently segmenting the derivative boundary partition, a plurality of AR generation blocks are generated, so that contact nodes among the blocks are all located outside the cross fusion partition, and interaction conflicts and data redundancy are effectively avoided. Therefore, the construction efficiency of the AR scene is improved, the user experience is optimized, and technical support is provided for application of the AR technology in the field of power service.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of power operation and maintenance platform, and specifically, to a big data mining method and system for AR. Background Art

[0002] With the continuous development and popularization of augmented reality (AR) technology, its application in various fields has gradually become widespread. Especially in the field of power services, AR technology, with its unique interactivity and visualization characteristics, provides strong support for improving service efficiency and optimizing user experience. However, how to effectively build AR power service scenarios and achieve efficient integration of virtual and reality is still a challenge facing current technology.

[0003] Traditional AR scene construction methods are often based on preset rules and parameters, and cannot be dynamically adjusted according to real-time data and user needs, thus limiting the flexibility and adaptability of AR scenes. At the same time, these methods often have problems such as low efficiency and poor interaction effects when dealing with large-scale and complex virtual spaces.

[0004] On the other hand, with the rapid development of big data technology, more and more power service scenario data are collected and stored, which contain rich user behavior information and service demand information. However, traditional AR scene construction methods often fail to make full use of this information, resulting in deviations between the constructed AR scenes and the actual needs of users.

[0005] Therefore, how to combine big data technology to realize the dynamic construction of AR scenes based on power service scenario big data and improve the adaptability and user experience of AR scenes has become an important direction of current technical research. Summary of the invention

[0006] In order to at least overcome the above-mentioned deficiencies in the prior art, the purpose of the embodiments of the present application is to provide an AR-oriented big data mining method and system, which aims to realize the efficient and accurate construction of AR power service scenes through in-depth analysis of power service scene big data. In the above context, by monitoring the AR power service scene construction request, the virtual space to be analyzed is determined based on the scene construction parameters in the request, and the AR space data is deeply mined using big data technology. By determining key information such as interactive migration nodes, cross-fusion partitions, and derived boundary partitions, efficient layout and interactive design of virtual space can be achieved, thereby improving the construction efficiency of AR scenes and user experience.

[0007] In a first aspect, an embodiment of the present application provides a big data mining method for AR, the method comprising: When an AR power service scenario construction request is detected, a virtual space to be analyzed is determined based on a scenario construction parameter of the AR power service scenario construction request, and AR space data of the virtual space to be analyzed is acquired, wherein the AR power service scenario construction request is generated based on power service scenario big data; Determining, based on the AR space data, an interactive migration node on the virtual space to be analyzed; Determine the cross-fusion partitions on the virtual space to be analyzed based on the spatial positioning information of each of the interactive migration nodes on the virtual space to be analyzed; Determine a derived boundary partition of the virtual space to be analyzed; the derived boundary partition is a partition surrounding the virtual space to be analyzed; Based on the interactive migration nodes on the virtual space to be analyzed that are outside the cross-fusion partition, the derived boundary partition is segmented to generate multiple AR generation blocks, and the contact nodes between two associated AR generation blocks are outside the cross-fusion partition.

[0008] In the second aspect, the embodiments of the present application also provide an AR-oriented big data mining system, which includes a processor and a machine-readable storage medium, in which machine-readable storage medium is stored machine-executable instructions, which are loaded and executed by the processor to implement the AR-oriented big data mining method in any possible implementation manner in the first aspect.

[0009] In any of the above aspects, the embodiments of the present application achieve efficient and accurate processing of the virtual space to be analyzed by deeply analyzing the AR power service scene big data. After monitoring the AR power service scene construction request, the virtual space to be analyzed can be quickly determined, and the relevant AR space data can be obtained. Based on the AR space data, the interactive migration nodes can be accurately identified, and then the cross-fusion partitions can be determined, ensuring the reasonable layout of the virtual space and the smoothness of the interaction. In addition, by determining the derived boundary partitions and intelligently dividing the derived boundary partitions, multiple AR generation blocks are generated, so that the contact nodes between the blocks are all located outside the cross-fusion partitions, effectively avoiding interaction conflicts and data redundancy. As a result, not only the construction efficiency of the AR scene is improved, but also the user experience is optimized, which provides technical support for the application of AR technology in the field of power services. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required to be used in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be extracted in combination with these drawings without creative work.

[0011] Figure 1 A schematic diagram of a process of a big data mining method for AR provided by an embodiment of the present invention; Figure 2 A schematic block diagram of the structure of an AR-oriented big data mining system for implementing the above-mentioned AR-oriented big data mining method provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0012] The following description is intended to enable one of ordinary skill in the art to implement and incorporate the present invention, and the description is provided in the context of a specific application scenario and its requirements. It will be apparent to one of ordinary skill in the art that various changes may be made to the disclosed embodiments, and that the general principles defined in the present invention may be applied to other embodiments and application scenarios without departing from the principles and scope of the present invention. Therefore, the present invention is not limited to the described embodiments, but should be given the broadest scope consistent with the claims.

[0013] Figure 1 FIG. 1 is a flow chart of an AR-oriented big data mining method provided by an embodiment of the present invention. The AR-oriented big data mining method is introduced in detail below.

[0014] Step S110, when an AR power service scene construction request is monitored, the virtual space to be analyzed is determined based on the scene construction parameters of the AR power service scene construction request, and the AR space data of the virtual space to be analyzed is obtained, wherein the AR power service scene construction request is generated based on power service scene big data.

[0015] In detail, the AR power service scene construction request is used to construct the application of augmented reality (AR) technology in the power service scene. The AR power service scene construction request may be initiated by a user, system or other service for the purpose of creating a power service scene in an AR environment. For example, the power service platform wants to use AR technology to show the operating status of a substation for employee training or customer service. Then, an AR power service scene construction request can be initiated to reconstruct the substation in the AR environment.

[0016] The scene construction parameters are parameters that need to be considered when building an AR power service scene, which define how to build and present the AR scene, and may include the scale, complexity, required level of detail, etc. of the scene. For example, in building an AR scene of a substation, the scene construction parameters may include the size of the substation, the type and layout of equipment, the complexity of electrical connections, etc.

[0017] The virtual space to be analyzed refers to the AR space to be analyzed and constructed. It is a virtual environment used to simulate the real power service scene. For example, when constructing the AR scene of the substation, the virtual space to be analyzed is the virtual model of the substation, including the virtual representation of all equipment such as transformers, switches, cables, etc.

[0018] The AR spatial data refers to the data required to build an AR scene, including spatial dimensions, device locations, device attributes, etc., which is the basis for building a realistic AR scene. For example, when building an AR scene of a substation, the AR spatial data may include the size of the substation, the location coordinates of each device, the electrical parameters of the device, etc.

[0019] The power service scenario big data refers to a large amount of data such as user electricity consumption behavior related to power services, which can be used to analyze power service needs and thus generate AR power service scenario construction requests, so as to simulate and analyze real power service scenarios in a virtual environment.

[0020] Therefore, in this embodiment, the AR-oriented big data mining system acts as a server and receives an AR power service scene construction request, which is automatically triggered by the power service scene big data analysis. The construction request contains a series of scene construction parameters, such as the size of the virtual space, the power equipment and service elements that need to be included, etc. Based on these scene construction parameters, the server determines a virtual space to be analyzed, which will be used for subsequent AR content construction and interaction design. At the same time, the server obtains the AR space data corresponding to the virtual space to be analyzed from the database. These AR space data include information such as the position, attributes, and relationships between the elements in the virtual space to be analyzed.

[0021] Step S120: determining the interactive migration node in the virtual space to be analyzed based on the AR space data.

[0022] In detail, the interactive migration node refers to a specific node defined in the AR space. Users can interact with the virtual environment through these interactive migration nodes. These interactive migration nodes are usually associated with objects, functions or information points in the scene. When users interact with these interactive migration nodes, they can trigger certain actions, display information or perform scene transitions. For example, in an AR power service scenario, an interactive migration node can be a virtual switch device. When the user sees this node through AR glasses or a mobile phone and interacts with it (such as gestures, clicks, etc.), the system can display the status information of the switch, or allow the user to simulate the operation of the switch.

[0023] That is, in this embodiment, after acquiring the AR space data, the server begins to analyze the AR space data to determine the interactive migration nodes in the virtual space to be analyzed. The interactive migration nodes are key locations where users may interact in the virtual space. For example, the server first identifies the initial interactive migration nodes in the virtual space to be analyzed. These initial interactive migration nodes are usually determined based on factors such as the user's historical interaction data and device location. Next, the server generates a first virtual interaction path corresponding to each initial interactive migration node. These first virtual interaction paths reflect the trajectory of the user's possible movement in the virtual space. By analyzing the intersection of these first virtual interaction paths and virtual space elements, the server further determines the extended interactive migration nodes, thereby improving the layout of the interactive migration nodes.

[0024] Step S130: determining cross-fusion partitions on the virtual space to be analyzed based on the spatial positioning information of each of the interactive migration nodes on the virtual space to be analyzed.

[0025] In detail, the cross-fusion partition refers to a specific area in the AR space divided according to the spatial positioning information of the interactive migration nodes. These areas may overlap or may be adjacent to each other. Within these partitions, different AR elements or scenes can be smoothly transitioned and integrated to provide a more coherent and realistic augmented reality experience. For example, in an electric power service AR scenario, a cross-fusion partition can be the internal area of ​​a substation, which contains multiple interactive migration nodes, such as transformers, switchgear, control rooms, etc. When the user moves within these partitions, the AR system will adjust and display the corresponding virtual elements and information in real time according to the user's position and direction.

[0026] The derived boundary partition is a special area delineated around the outer boundary of the virtual space to be analyzed. The role of the derived boundary partition is to define a boundary. When the user or virtual object approaches or crosses this boundary, specific actions or events can be triggered, such as scene switching, warning prompts, etc. For example, in the power service AR scene, the derived boundary partition may be defined as the outer wall or safety fence of the substation. When the user approaches this boundary through the AR device, the system can display a warning message to remind the user not to cross the boundary. Alternatively, when the user crosses this boundary, the AR scene can automatically switch to the environmental view outside the substation.

[0027] Therefore, in this embodiment, after the interactive migration nodes are determined, the server begins to delineate cross-fusion partitions based on the spatial positioning information of these interactive migration nodes in the virtual space to be analyzed. For example, each interactive migration node has a spherical space as its virtual interaction domain, and these virtual interaction domains represent the range in which users may interact near the node. The server determines the cross-fusion partitions in the virtual space by analyzing the overlap and node distribution of these virtual interaction domains. These cross-fusion partitions are areas with dense user interactions and are also areas that need to be focused on and optimized during the subsequent construction of AR content.

[0028] Step S140, determining the derived boundary partition of the virtual space to be analyzed. The derived boundary partition is a partition surrounding the virtual space to be analyzed.

[0029] In this embodiment, next, the server begins to determine the derived boundary partitions of the virtual space to be analyzed. The derived boundary partitions are peripheral areas surrounding the main area of ​​the virtual space, which are used to define the boundaries and expansion space of the AR content. The server delineates reasonable derived boundary partitions based on the overall layout and size of the virtual space to be analyzed, and these derived boundary partitions will serve as the basis for the division of subsequent AR generation blocks.

[0030] Step S150, based on the interactive migration nodes on the virtual space to be analyzed that are located outside the cross-fusion partition, the derived boundary partition is divided to generate multiple AR generation blocks, and the contact nodes between two associated AR generation blocks are outside the cross-fusion partition.

[0031] In detail, the AR generation block refers to an independent area formed after segmentation based on the derived boundary partition. Each AR generation block is responsible for generating and managing a part of the AR content. These AR generation blocks can be divided according to the location of the interactive migration nodes and the characteristics of the derived boundary partitions to ensure the continuity and efficient rendering of the AR content. For example, in the power service AR scene, an AR generation block may represent a specific area of ​​the substation, such as the transformer area, switch area, or control room area. Each AR generation block will independently generate and render the corresponding AR elements and information based on its internal interactive migration nodes and scene content. When the user moves within the AR generation block, the AR content related to the AR generation block can be updated and displayed in real time.

[0032] The contact nodes refer to specific points or lines located between different AR generation blocks for connecting and transitioning AR content. These contact nodes ensure that when the user moves from one block to another, the AR scene can transition smoothly without breaks or jumps. Contact nodes are usually located outside the cross-fusion partition to avoid conflicts or overlaps in the fusion area between the contents of different blocks. For example, in the power service AR scene, the contact node may be located at the junction of two different AR generation blocks, such as the junction of the transformer area and the switch area. When the user moves near these contact nodes through the AR device, it is ensured that the AR content of the two blocks can transition smoothly to provide users with a coherent augmented reality experience. For example, when the user walks from the transformer area to the switch area, the AR elements of the transformer area can be gradually faded out, and the AR elements of the switch area can be faded in at the same time to achieve smooth switching of scenes.

[0033] That is, in this embodiment, finally, the server starts to segment the derived boundary partitions based on the interactive migration nodes outside the cross-fusion partitions. By identifying these interactive migration nodes and determining the second virtual interaction path between them, the server divides the derived boundary partitions into multiple AR generation blocks. Each AR generation block contains specific interactive migration nodes and corresponding virtual space elements. These AR generation blocks are the basic units for subsequent AR content construction. The server will ensure that the AR content in each AR generation block can be independently generated and updated, while maintaining the content consistency and interactivity between AR generation blocks. In this way, the server can efficiently build an AR power service scenario that meets user needs and is highly interactive.

[0034] Based on the above steps, the embodiment of the present application realizes efficient and accurate processing of the virtual space to be analyzed by deeply analyzing the AR power service scene big data. After monitoring the AR power service scene construction request, the virtual space to be analyzed can be quickly determined, and the relevant AR space data can be obtained. Based on the AR space data, the interactive migration nodes can be accurately identified, and then the cross-fusion partitions can be determined, ensuring the reasonable layout of the virtual space and the smoothness of the interaction. In addition, by determining the derived boundary partitions and intelligently dividing the derived boundary partitions, multiple AR generation blocks are generated, so that the contact nodes between each block are located outside the cross-fusion partitions, effectively avoiding interaction conflicts and data redundancy. As a result, not only the construction efficiency of the AR scene is improved, but also the user experience is optimized, which provides technical support for the application of AR technology in the field of power services.

[0035] In a possible implementation, step S120 may include: Step S121: determining an initial interaction migration node in the virtual space to be analyzed based on the AR space data.

[0036] In this embodiment, after receiving the AR power service scene construction request, the server first obtains the relevant AR space data, which may include a 3D model of a substation, equipment layout, electrical connection and other information. Based on these AR space data, the server preliminarily identifies some key equipment points in the virtual space, such as transformers, circuit breakers, disconnectors, etc., and sets these equipment points as initial interaction migration nodes. These initial interaction migration nodes are key points that users may need to interact with in the AR scene.

[0037] Step S122: generating a first virtual interaction path corresponding to each initial interaction migration node in the virtual space to be analyzed.

[0038] After determining the initial interactive migration node, the server starts to generate the corresponding first virtual interactive path for each initial interactive migration node. For example, for the initial interactive migration node of the transformer, the server will generate a virtual path from the user's current location to the transformer. This virtual path will avoid other equipment and obstacles to ensure that the user can smoothly "walk" to the transformer to operate. Similarly, for other device nodes, such as circuit breakers or disconnectors, the server will also generate corresponding virtual interactive paths.

[0039] Step S123: determining intersection nodes between each of the first virtual interaction paths and the virtual space elements in the virtual space to be analyzed.

[0040] After the first virtual interaction paths are generated, the server begins to analyze the intersections of these first virtual interaction paths with other elements in the virtual space, such as equipment, walls, channels, etc. For example, a path can intersect with a switch device while approaching a transformer, and this intersection is considered an intersection node. The server records the locations and properties of these intersection nodes for subsequent processing.

[0041] Step S124: determining an extended interaction migration node on the virtual space to be analyzed based on intersection nodes between each of the first virtual interaction paths and virtual space elements on the virtual space to be analyzed.

[0042] After determining the intersection nodes, the server will further analyze the interaction potential of these intersection nodes. For example, if an intersection node is located between two important devices, or a location that users may need to visit frequently, the server will upgrade this intersection node to an extended interaction migration node, which means that users may also need to perform interactive operations on this intersection node, such as checking device status and performing operations.

[0043] Step S125 : determining the interactive migration nodes on the virtual space to be analyzed based on the initial interactive migration nodes and the extended interactive migration nodes on the virtual space to be analyzed.

[0044] Finally, the server merges the initial interaction migration node and the extended interaction migration node to form the final interaction migration node set, which will serve as the key points for users to interact in the AR scene and trigger various interaction events and operations. For example, when a user walks near an interaction migration node through an AR device, the device information and operation options related to the node can be automatically popped up, thereby providing users with a richer and more convenient AR interaction experience. In a possible implementation, step S121 may include: Step S1211 , extracting AR space features from the AR space data, where the AR space features include the position, size, shape, color, texture of the space object, and the motion trajectory and speed of the space object.

[0045] In this embodiment, the server begins to extract AR spatial features from these AR spatial data, including but not limited to the position, size, shape, color and texture of spatial objects (such as transformers, switchgear, wires, etc.). In addition, the server also analyzes the motion trajectory and speed of these spatial objects. Although the motion trajectory and speed may not be the main considerations in static power equipment scenes, they may be very important for scenes such as simulating fault conditions or dynamic demonstrations.

[0046] Step S1212: identifying interaction points in the AR space data, where the interaction points are potential locations where a user interacts with a spatial object in the virtual space to be analyzed.

[0047] The server continues to process the AR space data and identifies potential locations where users may interact with objects in the virtual space. For example, in a simulated substation scene, the server can identify the control panel next to the transformer, the operating handle of the switchgear, and the connection points of the wires as potential interaction points. These interaction points are locations where users can touch, operate, or obtain information in the AR scene.

[0048] Step S1213, based on the identified interaction points and the AR space features, an initial interaction migration node is determined, where the initial interaction migration node is a key location where the user may interact in the virtual space to be analyzed. A clustering algorithm is used to group the interaction points, and the center point or representative point of each group is used as an initial interaction migration node.

[0049] After identifying the interaction points and analyzing the AR space features, the server begins to determine the initial interaction migration nodes, which are key locations where users may interact in the virtual space. In order to determine these initial interaction migration nodes more accurately, the server uses a clustering algorithm to group the identified interaction points. For example, if multiple interaction points are closely clustered near the control panel of the transformer, then these interaction points can be grouped into a group, and the center point or representative point of the group will be set as an initial interaction migration node. Similarly, the interaction points of other devices or functional areas will also be grouped and set with corresponding initial interaction migration nodes.

[0050] In this way, the server can accurately determine the key locations where users may interact in the AR power service scenario based on the identification of AR spatial data and interaction points, namely the initial interaction migration nodes. These nodes will provide important reference points for subsequent AR scene construction and user interaction.

[0051] In a possible implementation, step S122 may include: Step S1221, traversing each initial interactive migration node on the virtual space to be analyzed, and determining the virtual space element where the traversed initial interactive migration node in the virtual space to be analyzed is located.

[0052] In this embodiment, the server starts to traverse each initial interaction migration node previously determined in the AR spatial data of the power service scene, which may represent different power equipment or key interaction locations, such as transformers, circuit breakers, control panels, etc. The server processes these initial interaction migration nodes one by one in a preset order or based on a certain algorithm (such as distance, importance, etc.).

[0053] For the initial interactive migration node currently being traversed, the server determines the virtual space element that the initial interactive migration node is located in. For example, if the current initial interactive migration node is a control panel of a transformer, the server will recognize that the control panel is an independent element in the virtual space, which includes determining the position, size, shape and other related attributes of the element.

[0054] Step S1222: generating, through the traversed initial interaction migration node, a first virtual interaction path having a resource scheduling relationship with the virtual space element where the traversed initial interaction migration node is located.

[0055] In this embodiment, the server generates a first virtual interaction path that has a resource scheduling relationship with the virtual space element (such as the control panel of the transformer) where the initial interaction migration node currently traversed is located. The resource scheduling relationship here may refer to the direct relationship between the first virtual interaction path and the allocation, control or monitoring of power resources. For example, the server can generate a virtual path from the user's current location to the transformer control panel. This path will avoid other obstacles and ensure that the user can smoothly reach the control panel to operate. At the same time, this first virtual interaction path may also take into account factors such as the operating status and safety distance of the power equipment to ensure the safety and efficiency of the user when interacting.

[0056] In this way, the server can generate a corresponding first virtual interaction path for each initial interaction migration node. These first virtual interaction paths not only take into account the spatial layout, but also take into account the actual operation requirements and resource scheduling logic related to the power equipment, which provides a basis for users to conduct efficient and safe interactions in AR power service scenarios.

[0057] In a possible implementation, step S124 may include: Step S1241, traversing each of the first virtual interaction paths, and extracting, from the virtual space to be analyzed, reference virtual space elements that have an interaction scheduling relationship with the traversed first virtual interaction path.

[0058] In this embodiment, the server starts to process the first virtual interaction paths generated for each initial interaction migration node one by one. For example, in the power service scenario, these first virtual interaction paths may include different paths from the user starting point to the transformer control panel, from the user starting point to the circuit breaker operating handle, etc. The server will traverse these paths according to a preset order or algorithm.

[0059] For the first virtual interaction path currently being traversed (e.g., the path from the user's starting point to the transformer control panel), the server extracts reference virtual space elements that have an interaction scheduling relationship with the path from the virtual space to be analyzed. The interaction scheduling relationship here refers to the direct interaction logic or resource scheduling relationship between the reference virtual space element and the first virtual interaction path. For example, along this first virtual interaction path, the user may need to pass through certain devices, switches, or sensors, etc., which can all be regarded as reference virtual space elements.

[0060] Step S1242: determining the intersection characteristic parameters between the traversed first virtual interaction path and each of the reference virtual space elements.

[0061] The server continues to analyze the intersections between the currently traversed first virtual interaction path and each reference virtual space element, and determines the characteristic parameters of these intersections, which may include the position, angle, distance, etc. of the intersections. For example, for the intersection of the path and a switch device, the server calculates the precise coordinates of the intersection, the intersection angle, and the distance from the path to the intersection.

[0062] Step S1243: extracting target virtual space elements whose intersection characteristic parameters meet preset characteristic conditions from the reference virtual space elements.

[0063] The server extracts target virtual space elements that meet the conditions from the reference virtual space elements according to preset feature conditions (such as the distance of the intersection point is within a certain range, the intersection angle meets specific requirements, etc.), and these target virtual space elements are key points where the user may need to perform additional interactions when moving along the first virtual interaction path. For example, if the intersection point of a switch device and the path is close to the user's starting point, and the intersection angle is convenient for the user to observe and operate, then the switch device may be regarded as a target virtual space element.

[0064] Step S1244: taking the intersection node between the traversed first virtual interaction path and the target virtual space element as an extended interaction migration node.

[0065] Finally, the server determines the intersection nodes between the traversed first virtual interaction path and the target virtual space element as extended interaction migration nodes, which are locations where users may need to perform additional interactions when moving along the path. For example, in an electric service scenario, a switch device intersection point on a path may be set as an extended interaction migration node, where users can perform switch operations, view device status, and other interactive behaviors. In this way, the server can more accurately predict and plan the user's interactive behavior in the AR scene, thereby improving user experience and operational efficiency.

[0066] In a possible implementation, step S1244 may include: Step S1244 - 1 , when traversing the first virtual interaction path, using a spatial geometry algorithm or a ray tracing algorithm in computer graphics to detect candidate intersection nodes between the first virtual interaction path and a target virtual space element.

[0067] In this embodiment, when the server traverses a first virtual interaction path, it can use a spatial geometry algorithm or a ray tracing algorithm in computer graphics to detect candidate intersection nodes between the first virtual interaction path and the target virtual space element. For example, in an AR model of an electric power service scenario, if the first virtual interaction path points from the user's starting point to a transformer control panel, the server will detect whether the first virtual interaction path intersects with other important devices or structures (such as circuit breakers, sensors, or safety fences), and these intersection points are candidate intersection nodes.

[0068] Step S1244-2, verifying the validity of the candidate intersection node by comparing the path attributes or spatial element attributes before and after the candidate intersection node. When the candidate intersection node is verified to be valid, associating relevant node attributes with the candidate intersection node, the node attributes including path ID, spatial element ID, and intersection type.

[0069] In this embodiment, the server will then verify the validity of the detected candidate intersection node, for example, usually involving comparison of path attributes (such as the direction and width of the path) or spatial element attributes (such as the size, shape, position, etc. of the element) before and after the intersection node. For example, if a candidate intersection node is located exactly at the operating handle of a circuit breaker, and the path has an obvious turn here or is at a reasonable close distance to the handle, then the intersection node may be considered valid.

[0070] Once the candidate intersection node is verified to be valid, the server will associate relevant node attributes with the candidate intersection node, which may include path ID (indicating which first virtual interaction path the intersection node belongs to), space element ID (indicating the target virtual space element that intersects with the intersection node), intersection type (such as right-angle intersection, T-type intersection, etc.), etc. Continuing with the example of the circuit breaker operating handle, the server can assign a unique ID to the intersection node, mark the path it belongs to and the device element that intersects with it, and record the type of intersection.

[0071] Step S1244-3: Determine the candidate intersection node that has been verified and associated with the node attributes as an extended interaction migration node, where the extended interaction migration node represents a new interaction node to which the user may expand from the initial interaction migration node along the first virtual interaction path.

[0072] Finally, the server identifies the candidate intersection nodes that have been verified and associated with node attributes as extended interaction migration nodes, which represent new interaction points that users may extend from the initial interaction migration nodes along the first virtual interaction path. In the power service scenario, this means that users may not only interact with the transformer control panel, but also with circuit breakers, sensors, or other devices while moving along the path. By identifying these extended interaction migration nodes, the server can more comprehensively predict and support users' interactive behaviors in the AR environment.

[0073] In a possible implementation, step S130 may include: Step S131, traversing each interactive migration node on the virtual space to be analyzed, and determining a spherical space with the traversed interactive migration node as the positioning center and an influence range of a preset value.

[0074] In this embodiment, in the power service scenario, the server begins to traverse each interactive migration node in the virtual space to be analyzed, which may represent key power equipment such as transformers, circuit breakers, and distribution boxes. For each interactive migration node, the server uses it as the positioning center and determines a spherical space based on a preset influence range value (such as a spherical space with a radius of 10 meters), which represents the effective influence or interaction area of ​​the power equipment in the virtual space.

[0075] Step S132: using the spherical space as a virtual interaction domain corresponding to the traversed interaction migration nodes.

[0076] In the power service virtual space, the server regards each spherical space centered on the power equipment as an independent virtual interaction domain, which represents the area where users may interact when handling power equipment. For example, in a virtual interaction domain centered on a transformer, users can perform interactive operations such as viewing equipment status and adjusting equipment parameters in this area.

[0077] Step S133: determining the statistics of the interactive migration nodes in each of the virtual interactive domains based on the spatial positioning features of each of the virtual interactive domains and the spatial positioning features of each of the interactive migration nodes.

[0078] In the power service scenario, the server analyzes the spatial positioning characteristics of other interactive migration nodes in each virtual interactive domain and calculates the statistics of the nodes in each virtual interactive domain. Taking the transformer virtual interactive domain as an example, the server will count the number of other power equipment (such as circuit breakers, sensors, etc.) in the domain, the average distance from the transformer, and other statistics. These statistics help evaluate the importance of the transformer and the complexity of its interaction with other equipment.

[0079] Step S134: determining the cross-fusion partitions on the virtual space to be analyzed based on the statistics of the interactive migration nodes in each of the virtual interactive domains.

[0080] Based on the statistics of interactive migration nodes in each virtual interaction domain, the server determines the cross-fusion partitions on the virtual space to be analyzed. In the power service scenario, this means that the server will identify those areas where power equipment is dense or the interactions are complex, and divide them into cross-fusion partitions. For example, if a transformer is surrounded by multiple circuit breakers, sensors, and other key equipment, and these devices interact frequently, then the virtual interaction domain where the transformer is located may be divided into a cross-fusion partition. Such partitions help the server optimize resource allocation and improve the efficiency and security of user interactions in these key areas. For example, the server can provide more real-time monitoring data, fault warnings, and other functions in these partitions.

[0081] In a possible implementation, step S134 includes: determining a threshold number of interactive migration nodes, and for each of the virtual interactive domains, when the statistics of the interactive migration nodes in the traversed virtual interactive domain are not less than the threshold number of interactive migration nodes, using the traversed virtual interactive domain as a cross-fusion partition on the virtual space to be analyzed.

[0082] In this embodiment, the server first sets a threshold number of interactive migration nodes, which is determined based on the characteristics and interactive requirements of the power service virtual space. For example, considering the safety and importance of power equipment, the threshold number may be set to 3, which means that only when a virtual interactive domain contains at least 3 interactive migration nodes, the domain will be regarded as a cross-fusion partition.

[0083] The server starts to traverse each virtual interaction domain determined previously. In each virtual interaction domain, the server calculates the number of interaction migration nodes in the domain, which may represent different power equipment, control systems or safety devices.

[0084] Taking the power control room as an example, the server will count the various interaction points in the control room, such as the console, monitoring screen, alarm system, etc., each of which is regarded as an interaction migration node.

[0085] After counting the number of interactive migration nodes in each virtual interactive domain, the server will compare this number with the previously set threshold interactive migration node number. If the number of nodes in a virtual interactive domain is greater than or equal to the threshold number, then the domain is considered an important interactive area.

[0086] Continuing with the example of the power control room, if the number of interactive migration nodes counted in the control room reaches or exceeds the set threshold (for example, 3), the server will determine that the control room is a key interactive area.

[0087] Finally, when the server determines that the number of interactive migration nodes in a virtual interactive domain is not less than the threshold number, it will mark this virtual interactive domain as a cross-fusion partition on the virtual space to be analyzed. This means that in this area, due to the existence of multiple key interaction points, the server needs to integrate multiple interactive elements in this partition and provide more detailed and efficient management and services.

[0088] In the example of the power control room, since the number of interaction points in the control room has reached the threshold, the server will identify it as a cross-fusion partition and may add more monitoring functions in this area, increase the frequency of data updates, etc., to ensure the safe and stable operation of the power system.

[0089] In a possible implementation manner, the derived boundary partition includes a virtual boundary partition corresponding to each virtual space element in the virtual space to be analyzed.

[0090] Step S150 may include: Step S151, traversing each virtual space element on the virtual space to be analyzed, and extracting the interactive migration nodes located outside the cross-fusion partition from the interactive migration nodes on the traversed virtual space elements.

[0091] Step S152: determining a second virtual interaction path corresponding to each interaction migration node extracted from the traversed virtual space element.

[0092] Step S153 : dividing the virtual boundary partitions corresponding to the traversed virtual space elements according to each of the second virtual interaction paths to generate AR generation blocks.

[0093] In this embodiment, the server starts to traverse each virtual space element on the virtual space to be analyzed, which may represent various components in the power system, such as cables, transformers, switchboards, etc. During the traversal process, the server checks the interactive migration nodes on each virtual space element, especially those nodes located outside the previously determined cross-fusion partitions.

[0094] Taking a cable as an example, the server will identify all the interactive migration nodes on this cable and then filter out those nodes that are not in the cross-fusion partition.

[0095] For each interactive migration node extracted from the cable and located outside the cross-fusion partition, the server determines a second virtual interactive path, which can be the best path for the user to reach other key nodes or areas from the current node when performing AR interaction.

[0096] For example, if an interactive migration node is located at one end of a cable and another important interactive point (such as a switchboard) is located at the other end, the server can calculate a shortest or optimal path from the cable node to the switchboard as a second virtual interactive path.

[0097] The server will segment the virtual boundary partitions corresponding to the cables according to the second virtual interaction path of each interaction migration node. The segmentation process is to ensure that in the AR environment, users can interact smoothly along these paths without being disturbed by other irrelevant areas.

[0098] Continuing with the cable example, if the cable passes through multiple different areas, the server can divide the virtual boundary of the cable into multiple parts according to the characteristics and interaction requirements of these areas. Each part will correspond to one or more second virtual interaction paths, thereby ensuring that users can get the best experience when performing AR interaction along these paths.

[0099] After the segmentation in the above steps, the server will generate multiple AR generation blocks. These blocks are defined based on the segmentation results of the virtual boundary partitions. Each block represents an independent and interactive area in the virtual space.

[0100] In the power service scenario, this means that the server will generate corresponding AR generation blocks for each key power equipment such as cable segments, transformers, distribution boards, etc. When users interact with AR in these blocks, the server can provide more accurate and efficient services, such as real-time data display, fault warning, remote control, etc.

[0101] In a possible implementation, step S153 may include: Step S1531: analyzing virtual interaction features of the second virtual interaction path, where the virtual interaction features include the direction, starting point, end point, and possible intersection of the second virtual interaction path.

[0102] In this embodiment, the server first deeply analyzes the virtual interaction features of each second virtual interaction path, which may include the direction of the second virtual interaction path (such as a straight line, curve or broken line), the specific locations of the starting point and the end point, and the possible intersections on the second virtual interaction path. For example, if a second virtual interaction path is from a transformer (starting point) to a switchboard (end point), the server will record the approximate direction of the second virtual interaction path, the coordinates of the starting point and the end point, and whether there are intersections with other paths or devices on the second virtual interaction path.

[0103] Step S1532: Map the second virtual interaction path to the virtual boundary partition of the virtual space element according to the virtual interaction feature, determine the intersection of the second virtual interaction path and the virtual boundary partition, and record the position information of the intersection.

[0104] Next, the server will map the analyzed second virtual interaction path to the virtual boundary partition of the corresponding virtual space element. In this process, the server will determine the intersection of the second virtual interaction path and the virtual boundary partition, and accurately record the location information of these intersections. Taking the path from the transformer to the distribution board mentioned earlier as an example, the server will find the intersection of this second virtual interaction path with the virtual boundaries of other power equipment such as cables and switches, and record their coordinates.

[0105] Step S1533: Analyze the type attribute of the intersection according to the position information of the intersection, and determine the segmentation point and segmentation method according to the type attribute of the intersection.

[0106] After determining the location information of the intersections, the server will further analyze the type attributes of these intersections. For example, some intersections may be simple intersections of paths and device boundaries, while others may be intersections of multiple paths. Based on these attributes, the server will determine the split points and the corresponding splitting methods. For simple intersections, it may only be necessary to split at the intersection; for complex intersections, more complex splitting strategies may be required, such as introducing additional split lines or split surfaces.

[0107] Step S1534 : segmenting the virtual boundary along the second virtual interaction path based on the segmentation point and the segmentation method, and creating corresponding AR generation blocks according to the segmentation result.

[0108] Finally, based on the determined segmentation points and segmentation methods, the server will actually segment the virtual boundary along the second virtual interaction path. This process will create corresponding AR generation blocks based on the segmentation results. In the power service scenario, this means that the server will generate an independent AR block for each segmented area, which will serve as the basic unit for users to interact in the AR environment. For example, a user may view the real-time data of a transformer in one AR block and control the switch status of a distribution board in another AR block.

[0109] In a possible implementation, the method further includes: Step A110, determining the number of preset blocks based on the scene construction parameters.

[0110] The server will first determine the number of preset blocks based on the scene construction parameters, which may include the complexity of the power system, the number of devices to be displayed, the level of detail of the AR content, and the needs of user interaction. For example, if the power system contains a large number of devices and complex interactive scenes, the number of preset blocks can be increased accordingly to ensure that the content within each block is not too crowded, thereby improving the clarity of the AR content and user experience.

[0111] Step A120: When the statistics of the AR generation blocks generated by segmentation are greater than the preset number of blocks, the multiple AR generation blocks are merged to generate the preset number of synchronous construction blocks. The preset number of synchronous construction blocks are used to synchronously construct AR content.

[0112] When the number of AR generation blocks generated by the server exceeds the preset number of blocks, the server will merge these blocks to reduce the number of blocks. The fusion process may include merging adjacent blocks, deleting overlapping blocks, or re-dividing the boundaries of blocks. Through fusion, the server will eventually generate a number of synchronous construction blocks equal to the preset number of blocks, which will be used to synchronously build AR content to ensure the coherence and consistency of the content.

[0113] Step A130 : determining two associated synchronous building blocks, and determining a block connection node between the two associated synchronous building blocks based on the contact nodes of the two associated synchronous building blocks.

[0114] After generating the synchronous building blocks, the server determines which blocks are related to each other. Two related synchronous building blocks are usually blocks that are spatially adjacent or logically related. For example, in a power system, a transformer block may be associated with a switchboard block. The server identifies these associated blocks and finds the contact nodes between them, that is, the block connection nodes, which are the key points for content connection between blocks and the basis for realizing content sharing partitions.

[0115] Step A140: Determine a content sharing partition between the two associated synchronous construction blocks based on the block connection node. The content sharing partition is used to connect the content of the two associated synchronous construction blocks through the content sharing partition after the AR content is synchronously constructed for each synchronous construction block.

[0116] Based on the block connection node, the server will determine the content sharing partition between the two associated synchronous construction blocks. The partition is a virtual space area used to connect the content of the corresponding associated blocks through the partition after the AR content is synchronously constructed for each synchronous construction block. For example, between the transformer block and the switchboard block, the server can create a content sharing partition to display the real-time data of the current or voltage transmitted from the transformer to the switchboard. In this way, when the user views these two blocks in the AR environment, the content sharing partition can intuitively understand the correlation and working status between the two devices.

[0117] In a possible implementation, step A120 may include: Step A121, traverse each cross-fusion partition on the virtual space to be analyzed, take the AR generation block where the traversed cross-fusion partition is located as a candidate fusion block, and when the capacity of the candidate fusion block does not meet the set capacity requirement, determine the associated AR generation block associated with the virtual space element where the traversed cross-fusion partition is located and associated with the candidate fusion block.

[0118] In this embodiment, the server first traverses each cross-fusion partition on the virtual space to be analyzed. For each cross-fusion partition, the server marks the AR generation block where it is located as a candidate fusion block. If the capacity of a candidate fusion block does not meet the set capacity requirements (for example, the capacity is too small to carry enough AR content), the server will search for other AR generation blocks associated with the candidate fusion block. These associated blocks are called associated AR generation blocks.

[0119] Taking the power control system as an example, if a cross-fusion partition is located in the control room and the AR generation block capacity of the control room is insufficient, the server will look for AR generation blocks in other areas adjacent to the control room (such as corridors, lounges, etc.) as associated AR generation blocks.

[0120] Step A122: if the associated AR generation block is located outside the cross-fused partition and the capacity of the associated AR generation block does not meet the set capacity requirement, the candidate fused block is merged with the associated AR generation block to generate an iterative fused block.

[0121] The server checks each associated AR generation block. If the associated AR generation block is outside the cross-fusion partition and its capacity does not meet the set capacity requirements, the server will merge the candidate fusion block with the associated AR generation block to generate a new block, called an iterative fusion block.

[0122] In an electric power control system, this might mean merging the AR generation blocks of the control room and adjacent corridor areas to form a larger block.

[0123] Step A123, if the capacity of the iterative fusion block does not meet the set capacity requirement, the iterative fusion block is used as a new candidate fusion block, and the process returns to step A121 to determine the associated AR generation block associated with the virtual space element of the traversed cross-fusion partition and associated with the candidate fusion block, and continues to execute until the capacity of the generated fusion block meets the set capacity requirement, or until the associated AR generation block is not located outside the cross-fusion partition.

[0124] If the capacity of the iterative fusion block still does not meet the set capacity requirement, the server will regard this iterative fusion block as a new candidate fusion block and repeat the above steps to continue searching for and merging the associated AR generation blocks until the capacity of the generated fusion block meets the requirement or no associated AR generation blocks outside the cross-fusion partition can be found.

[0125] In step A124, the fused block generated at the end is used as the first synchronous building block, and when the first synchronous building blocks corresponding to the cross-fused partitions are obtained, the statistics of the obtained first synchronous building blocks are determined.

[0126] When the fusion process is finished, the server marks the obtained fusion blocks as the first synchronization construction blocks, which will serve as the basis for subsequent AR content construction.

[0127] In power systems, this might mean fusing AR generation blocks in control rooms, corridors, and other adjacent areas into one large first-synchronization building block.

[0128] Step A125: If the statistic of the first synchronous construction blocks is greater than the preset number of blocks, the spatial dependency information between the first synchronous construction blocks is determined, and the capacity interval of each synchronous construction block to be constructed is determined based on the preset number of blocks and the capacity information of the derived boundary partition; based on the spatial dependency information between the first synchronous construction blocks and the capacity interval of each synchronous construction block to be constructed, the first synchronous construction blocks are subjected to a second fusion to generate the preset number of synchronous construction blocks.

[0129] The server counts the number of first synchronous building blocks generated. If the number of these first synchronous building blocks exceeds the preset number of blocks, the server will further process.

[0130] The server first determines the spatial dependency information between the first synchronous construction blocks, including the relative positions and connection relationships between the blocks, etc. Then, based on the preset number of blocks and the capacity information of the derived boundary partitions, the server determines the capacity interval of each synchronous construction block to be constructed.

[0131] Finally, according to the spatial dependency information and capacity intervals, the server performs a second fusion on the first synchronous building blocks to generate synchronous building blocks that meet a preset number.

[0132] In power systems, this may mean further fusing several adjacent and interdependent first synchronization building blocks to reduce the number of blocks while ensuring that the capacity and content complexity of each block is within a manageable range.

[0133] In a possible implementation manner, before step S110, the method further includes: Step S101, collecting power service scenario big data from multiple data sources in real time or periodically.

[0134] Step S102: Analyze the power service scenario big data to predict the user's power service demand for the AR power service scenario.

[0135] Step S103: Generate a corresponding AR power service scenario construction request based on the prediction result.

[0136] In this embodiment, the server first collects power service scenario big data in real time or regularly from multiple data sources, which may come from smart meters, user feedback systems, power service records, etc. For example, the server may collect user power consumption data from smart meters every minute, collect user evaluations and demands for power services from user feedback systems every hour, and collect information such as service type, time, and service results from power service records every day.

[0137] The server then analyzes the collected big data to predict the user's demand for AR power service scenarios. For example, this step may involve data mining and machine learning techniques. For example, the server can analyze the user's electricity consumption data over the past year to find out the peak and trough periods of electricity consumption, and the association between these periods and user activities (such as weekdays, weekends, and holidays). At the same time, the server will also analyze user feedback data to understand the user's satisfaction with the current power service and the need for improvement.

[0138] Based on the above analysis, the server predicts the user's future demand for AR power service scenarios. For example, if the analysis results show that users often encounter power shortages during the peak power consumption period in summer, and users have a high demand for real-time monitoring and early warning functions of power services, then the server will generate an AR power service scenario construction request, requiring the construction of an AR scenario that can monitor power usage in real time and provide early warnings.

[0139] In a possible implementation, step S102 may include: Step S1021, extracting sample key feature data from the sample power service scenario big data in advance, wherein the sample key feature data includes user power consumption characteristics, power consumption time characteristics, power consumption equipment characteristics, power consumption service characteristics, and user feedback characteristics.

[0140] Step S1022, extracting sample pattern knowledge features from the sample key feature data, wherein the sample pattern knowledge features include the user's electricity consumption behavior pattern, the trend and periodic changes in the time series of the user's electricity demand, the electricity consumption characteristics and habits of different user groups, the association between different electricity consumption equipment or services, and the user's satisfaction and demand for current electricity services.

[0141] Step S1023, using the sample pattern knowledge features as training samples and the power service demand knowledge points as training labels to construct a power service prediction model.

[0142] Step S1024, using the constructed power service prediction model to analyze the power service scenario big data, and predict the user's future power service demand for the AR power service scenario.

[0143] In this embodiment, before building the electricity service prediction model, the server extracts key feature data from the sample electricity service scenario big data. These data include user electricity consumption characteristics (such as average electricity consumption, peak electricity consumption, etc.), electricity consumption time characteristics (such as peak electricity consumption periods, low electricity consumption periods, etc.), electricity consumption equipment characteristics (such as equipment type, equipment power, etc.), electricity consumption service characteristics (such as service type, service frequency, etc.) and user feedback characteristics (such as user satisfaction, user suggestions, etc.).

[0144] The server further extracts pattern knowledge features from the sample key feature data. These features reflect the user's electricity consumption behavior patterns (such as periodic electricity consumption habits), trends and periodic changes in the time series of electricity demand (such as seasonal electricity consumption changes), electricity consumption characteristics and habits of different user groups (such as differences in electricity consumption between commercial users and residential users), the correlation between different electricity-consuming equipment or services (such as the correlation between electricity consumption of air conditioners and lighting equipment), and users' satisfaction and demand for current electricity services (such as users' demand for real-time monitoring functions).

[0145] Using the extracted sample pattern knowledge features as training samples and the power service demand knowledge points (such as real-time monitoring, early warning functions, etc.) as training targets, the server builds a power service prediction model through machine learning algorithms. The power service prediction model can learn and simulate users' electricity consumption behaviors and service needs, thereby accurately predicting future users' needs for AR power service scenarios.

[0146] Finally, the server uses the constructed power service prediction model to analyze the real-time power service scenario big data and predict the user's future needs for AR power service scenarios, which may include real-time monitoring of power usage, early warning of power shortages, and optimization of power consumption plans. Based on these prediction results, the server will generate corresponding AR power service scenario construction requests to meet the user's actual needs.

[0147] In a possible implementation, step S103 may include: Step S1031 , pre-constructing a variety of AR power service scenario templates, each AR power service scenario template corresponds to a different combination of power service requirements.

[0148] Step S1032 : selecting a matching AR power service scenario template from the multiple AR power service scenario templates as a basic AR power service scenario template according to the predicted power service demand.

[0149] Step S1033, in combination with the user's personalized customization information, fine-tune the selected basic AR power service scenario template, and after optimizing the resource configuration in the virtual space corresponding to the basic AR power service scenario template based on the predicted power service demand and the selected basic AR power service scenario template, integrate the determined basic AR power service scenario template into an AR power service scenario construction request, and the AR power service scenario construction request includes specific scenario construction parameters.

[0150] In this embodiment, the server will first pre-build a variety of AR power service scenario templates, which are designed according to different combinations of power service needs. For example, some AR power service scenario templates may focus on real-time monitoring and data analysis, suitable for industrial users who need to pay close attention to power usage; some AR power service scenario templates may focus more on energy efficiency management and energy-saving suggestions, suitable for commercial or home users who are concerned about energy conservation and emission reduction. Each AR power service scenario template contains a set of preset virtual space layouts, interface elements, and functional modules.

[0151] When the server predicts the user's power service needs, it can select a template that matches the predicted needs from a variety of pre-built AR power service scenario templates. For example, if the prediction results show that the user needs a scenario that can monitor power consumption in real time and provide energy-saving suggestions, the server will select a template that includes these functions as the basic AR power service scenario template.

[0152] After selecting the basic AR power service scene template, the server will further fine-tune the basic AR power service scene template based on the user's personalized customization information, which may include the user's preferences, device configuration, usage habits, etc. For example, if the user prefers a dark theme, the server will adjust the color scheme of the template; if the user needs to pay special attention to the power consumption of certain devices, the server can highlight this data in the basic AR power service scene template.

[0153] Finally, the server will optimize the resource configuration in the virtual space based on the predicted power service demand and the selected basic AR power service scene template, which can include adjusting the transmission efficiency of data streams, optimizing the layout of interface elements, and enhancing the computing power of specific functional modules. After completing these optimizations, the server will integrate the determined basic AR power service scene template into an AR power service scene construction request, which contains specific scene construction parameters, such as the size of the virtual space, the type and position of the interface elements, the logical relationship of the functional modules, etc. The request will then be sent to the AR scene construction system to create a personalized AR power service scene for the user that meets his needs.

[0154] Figure 2 The hardware structure of the AR-oriented big data mining system 100 for implementing the AR-oriented big data mining method provided by the embodiment of the present invention is shown as follows: Figure 2 As shown, the big data mining system 100 for AR may include a processor 110 , a machine-readable storage medium 120 , a bus 130 , and a communication unit 140 .

[0155] In an exemplary design idea, the big data mining system 100 for AR can be a single big data mining system for AR, or it can be a server group. The server group can be centralized or distributed (for example, the big data mining system 100 for AR can be a distributed system). In an exemplary design idea, the big data mining system 100 for AR can be local or remote. For example, the big data mining system 100 for AR can access data and / or data stored in the machine-readable storage medium 120 via a network. For another example, the big data mining system 100 for AR can be directly connected to the machine-readable storage medium 120 to access the stored data and / or data. In an exemplary design idea, the big data mining system 100 for AR can be implemented on a cloud platform. As an example only, the cloud platform can include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-layer cloud, etc. or any combination thereof.

[0156] The machine-readable storage medium 120 may store data and / or instructions. In an exemplary design concept, the machine-readable storage medium 120 may store multidimensional monitoring data obtained from an external terminal. In an exemplary design concept, the machine-readable storage medium 120 may store multidimensional monitoring data and / or instructions that the AR-oriented big data mining system 100 uses to execute or use to complete the exemplary method described in the present invention. In an exemplary design concept, the machine-readable storage medium 120 may include a large-capacity memory, a removable memory, a volatile read-write memory, a read-only memory (ROM), etc. or any combination thereof. Exemplary large-capacity memories may include disks, optical disks, solid-state disks, etc. Exemplary removable memories may include flash drives, floppy disks, optical disks, memory cards, compressed disks, tapes, etc. Exemplary volatile read-write memories may include random access memory (RAM). Exemplary RAM may include active random access memory (DRAM), double data rate synchronous active random access memory (DDR SDRAM), passive random access memory (SRAM), thyristor random access memory (T-RAM), and zero capacitance random access memory (Z-RAM), etc. Exemplary read-only memories may include mask read-only memories (MROMs), programmable read-only memories (PROMs), erasable programmable read-only memories (PEROMs), electrically erasable programmable read-only memories (EEPROMs), compact disk read-only memories (CD-ROMs), and digital versatile disk read-only memories, etc. In an exemplary design concept, the machine-readable storage medium 120 may be implemented on a cloud platform. As an example only, a cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-layer cloud, etc., or any combination thereof.

[0157] During the specific implementation process, at least one processor 110 executes computer executable instructions stored in the machine-readable storage medium 120, so that the processor 110 can execute the AR-oriented big data mining method of the above method embodiment. The processor 110, the machine-readable storage medium 120 and the communication unit 140 are connected through the bus 130, and the processor 110 can be used to control the sending and receiving actions of the communication unit 140.

[0158] The specific implementation process of the processor 110 can refer to the various method embodiments executed by the above-mentioned AR-oriented big data mining system 100. The implementation principles and technical effects are similar, and this embodiment will not be repeated here.

[0159] In addition, an embodiment of the present invention further provides a readable storage medium, in which computer executable instructions are preset. When a processor executes the computer executable instructions, the above-mentioned big data mining method for AR is implemented.

[0160] Similarly, it should be noted that in order to simplify the description of the present invention disclosure and thus help understand one or more embodiments of the invention, in the foregoing description of the embodiments of the invention, sometimes multiple features are grouped into one embodiment, drawings, or descriptions thereof. Similarly, it should be noted that in order to simplify the description of the present invention disclosure and thus help understand one or more embodiments of the invention, in the foregoing description of the embodiments of the invention, sometimes multiple features are grouped into one embodiment, drawings, or descriptions thereof.

Claims

1. A big data mining method for AR, characterized in that: The method comprises: When an AR power service scenario construction request is detected, a virtual space to be analyzed is determined based on a scenario construction parameter of the AR power service scenario construction request, and AR space data of the virtual space to be analyzed is acquired, wherein the AR power service scenario construction request is generated based on power service scenario big data; Determining, based on the AR space data, an interactive migration node on the virtual space to be analyzed; Determine the cross-fusion partitions on the virtual space to be analyzed based on the spatial positioning information of each of the interactive migration nodes on the virtual space to be analyzed; Determine a derived boundary partition of the virtual space to be analyzed; the derived boundary partition is a partition surrounding the virtual space to be analyzed; Based on the interactive migration nodes on the virtual space to be analyzed that are outside the cross-fusion partition, the derived boundary partition is segmented to generate multiple AR generation blocks, and the contact nodes between two associated AR generation blocks are outside the cross-fusion partition.

2. The AR-oriented big data mining method according to claim 1, characterized in that: The determining, based on the AR space data, the interactive migration node in the virtual space to be analyzed includes: Based on the AR space data, determining an initial interaction migration node on the virtual space to be analyzed; generating a first virtual interaction path corresponding to each initial interaction migration node on the virtual space to be analyzed; Determine an intersection node between each of the first virtual interaction paths and a virtual space element on the virtual space to be analyzed; Determining an extended interaction migration node on the virtual space to be analyzed based on intersection nodes between each of the first virtual interaction paths and virtual space elements on the virtual space to be analyzed; Determining the interactive migration nodes on the virtual space to be analyzed based on the initial interactive migration nodes and the extended interactive migration nodes on the virtual space to be analyzed; The step of determining an initial interaction migration node in the virtual space to be analyzed based on the AR space data includes: Extracting AR space features from the AR space data, wherein the AR space features include the position, size, shape, color, texture of the space object, and the motion trajectory and speed of the space object; Identifying interaction points in the AR spatial data, where the interaction points are potential locations where a user interacts with a spatial object in the virtual space to be analyzed; According to the identified interaction points and the AR space features, an initial interaction migration node is determined, where the initial interaction migration node is a key position where the user may interact in the virtual space to be analyzed; wherein a clustering algorithm is used to group the interaction points, and a center point or representative point of each group is used as an initial interaction migration node.

3. The AR-oriented big data mining method according to claim 2, characterized in that: The generating of the first virtual interaction path corresponding to each initial interaction migration node in the virtual space to be analyzed includes: Traversing each initial interactive migration node on the virtual space to be analyzed, and determining the virtual space element where the traversed initial interactive migration node in the virtual space to be analyzed is located; A first virtual interaction path is generated through the traversed initial interaction migration node, which has a resource scheduling relationship with the virtual space element where the traversed initial interaction migration node is located.

4. The AR-oriented big data mining method according to claim 2, characterized in that: The step of determining the extended interaction migration node on the virtual space to be analyzed based on the intersection nodes between each of the first virtual interaction paths and the virtual space elements on the virtual space to be analyzed includes: traversing each of the first virtual interaction paths, and extracting, from the virtual space to be analyzed, reference virtual space elements that have an interaction scheduling relationship with the traversed first virtual interaction path; Determine the intersection characteristic parameters between the traversed first virtual interaction path and each of the reference virtual space elements; Extracting target virtual space elements whose intersection characteristic parameters meet preset characteristic conditions from the reference virtual space elements; Taking the intersection node between the traversed first virtual interaction path and the target virtual space element as an extended interaction migration node; The step of using the intersection node between the traversed first virtual interaction path and the target virtual space element as the extended interaction migration node includes: When traversing the first virtual interaction path, detecting candidate intersection nodes of the first virtual interaction path and the target virtual space element using a spatial geometry algorithm or a ray tracing algorithm in computer graphics; Verify the validity of the candidate intersection node by comparing the path attributes or space element attributes before and after the candidate intersection node. When the candidate intersection node is verified to be valid, associate relevant node attributes with the candidate intersection node, wherein the node attributes include path ID, space element ID, and intersection type. The candidate intersection node that has been verified and associated with the node attributes is determined as an extended interaction migration node, where the extended interaction migration node represents a new interaction node to which the user may expand from the initial interaction migration node along the first virtual interaction path.

5. The AR-oriented big data mining method according to claim 1, characterized in that: The determining of the cross-fusion partitions on the virtual space to be analyzed based on the spatial positioning information of each of the interactive migration nodes on the virtual space to be analyzed includes: Traversing each interactive migration node on the virtual space to be analyzed, and determining a spherical space with the traversed interactive migration node as the positioning center and an influence range of a preset value; The spherical space is used as a virtual interaction domain corresponding to the traversed interaction migration nodes; Determining statistics of the interactive migration nodes in each of the virtual interactive domains based on the spatial positioning features of each of the virtual interactive domains and the spatial positioning features of each of the interactive migration nodes; Based on the statistics of the interactive migration nodes in each of the virtual interactive domains, the cross-fusion partitions on the virtual space to be analyzed are determined.

6. The AR-oriented big data mining method according to claim 5, characterized in that: The determining, based on the statistics of the interactive migration nodes in each of the virtual interactive domains, the cross-fusion partitions on the virtual space to be analyzed includes: The threshold interactive migration node number is determined, and for each of the virtual interactive domains, when the statistics of the interactive migration nodes in the traversed virtual interactive domain is not less than the threshold interactive migration node number, the traversed virtual interactive domain is used as a cross-fusion partition on the virtual space to be analyzed.

7. The AR-oriented big data mining method according to claim 1, characterized in that: The derived boundary partitions include virtual boundary partitions corresponding to each virtual space element on the virtual space to be analyzed; The step of segmenting the derived boundary partition based on the interactive migration nodes located outside the cross-fusion partition on the virtual space to be analyzed to generate a plurality of AR generation blocks includes: Traversing each virtual space element on the virtual space to be analyzed, and extracting interactive migration nodes located outside the cross-fusion partition from the interactive migration nodes on the traversed virtual space elements; Determine a second virtual interaction path corresponding to each interaction migration node extracted from the traversed virtual space element; According to each of the second virtual interaction paths, virtual boundary partitions corresponding to the traversed virtual space elements are divided to generate AR generation blocks; The step of dividing the virtual boundary partitions corresponding to the traversed virtual space elements according to each of the second virtual interaction paths to generate AR generation blocks includes: analyzing virtual interaction features of the second virtual interaction path, wherein the virtual interaction features include a direction, a starting point, an end point, and a possible intersection of the second virtual interaction path; Mapping the second virtual interaction path to a virtual boundary partition of a virtual space element according to the virtual interaction feature, determining an intersection point between the second virtual interaction path and the virtual boundary partition, and recording position information of the intersection point; Analyzing the type attributes of the intersection according to the location information of the intersection, and determining the segmentation point and the segmentation method according to the type attributes of the intersection; Based on the segmentation point and the segmentation method, the virtual boundary is segmented along the second virtual interaction path, and corresponding AR generation blocks are created according to the segmentation result.

8. The AR-oriented big data mining method according to claim 1, characterized in that: The method further comprises: Based on the scene construction parameters, determining the number of preset blocks; When the statistics of the AR generation blocks generated by segmentation are greater than the preset number of blocks, the multiple AR generation blocks are merged to generate the preset number of synchronous construction blocks; the preset number of synchronous construction blocks are used to synchronously construct AR content; Determine two associated synchronous building blocks, and determine a block connection node between the two associated synchronous building blocks based on contact nodes of the two associated synchronous building blocks; Based on the block connection node, determining a content sharing partition between the two associated synchronous construction blocks; the content sharing partition is used to connect the contents of the two corresponding associated synchronous construction blocks through the content sharing partition after the AR content is synchronously constructed for each of the synchronous construction blocks; The step of fusing the plurality of AR generation blocks to generate the preset number of synchronization building blocks includes: Traversing each cross-fused partition on the virtual space to be analyzed, taking the AR generation block where the traversed cross-fused partition is located as a candidate fused block, and when the capacity of the candidate fused block does not meet the set capacity requirement, determining an associated AR generation block associated with the virtual space element where the traversed cross-fused partition is located and associated with the candidate fused block; If the associated AR generation block is located outside the cross-fusion partition and the capacity of the associated AR generation block does not meet the set capacity requirement, the candidate fusion block is merged with the associated AR generation block to generate an iterative fusion block; If the capacity of the iterative fusion block does not meet the set capacity requirement, the iterative fusion block is used as a new candidate fusion block, and the associated AR generation block associated with the virtual space element where the traversed cross-fusion partition is located and associated with the candidate fusion block is returned to continue execution until the capacity of the generated fusion block meets the set capacity requirement, or until the associated AR generation block is not located outside the cross-fusion partition; The fused block generated at the end is used as the first synchronous building block, and when the first synchronous building blocks corresponding to the cross-fused partitions are obtained, the statistics of the obtained first synchronous building blocks are determined; If the statistic of the first synchronous building blocks is greater than the preset number of blocks, the spatial dependency information between the first synchronous building blocks is determined, and the capacity interval of each synchronous building block to be constructed is determined based on the preset number of blocks and the capacity information of the derived boundary partition; based on the spatial dependency information between the first synchronous building blocks and the capacity interval of each synchronous building block to be constructed, the first synchronous building blocks are subjected to a second fusion to generate the preset number of synchronous building blocks.

9. The AR-oriented big data mining method according to claim 1, characterized in that: Before the step of determining the virtual space to be analyzed based on the scene construction parameters of the AR power service scene construction request when an AR power service scene construction request is detected, the method further includes: Collect power service scenario big data from multiple data sources in real time or periodically; Analyze the big data of the power service scenario to predict the user's power service demand for the AR power service scenario; Generate corresponding AR power service scenario construction request based on the prediction results; The step of analyzing the power service scenario big data to predict the user's power service demand for the AR power service scenario includes: Extracting sample key feature data from sample power service scenario big data in advance, wherein the sample key feature data includes user power consumption characteristics, power consumption time characteristics, power consumption equipment characteristics, power consumption service characteristics, and user feedback characteristics; Extracting sample pattern knowledge features from the sample key feature data, the sample pattern knowledge features include the user's electricity consumption behavior pattern, the trend and periodic changes in the time series of the user's electricity demand, the electricity consumption characteristics and habits of different user groups, the association relationship between different electricity consumption equipment or services, and the user's satisfaction and demand for current electricity services; Using the sample pattern knowledge features as training samples and the power service demand knowledge points as training labels to construct a power service prediction model; Analyze the power service scenario big data using the constructed power service prediction model to predict the user's future power service demand for the AR power service scenario; The step of generating a corresponding AR power service scenario construction request according to the prediction result includes: Pre-build a variety of AR power service scenario templates, each of which corresponds to a different combination of power service requirements; According to the predicted power service demand, selecting a matching AR power service scenario template from the multiple AR power service scenario templates as a basic AR power service scenario template; In combination with the user's personalized customization information, the selected basic AR power service scenario template is fine-tuned, and after optimizing the resource configuration in the virtual space corresponding to the basic AR power service scenario template based on the predicted power service demand and the selected basic AR power service scenario template, the determined basic AR power service scenario template is integrated into an AR power service scenario construction request, and the AR power service scenario construction request includes specific scenario construction parameters.

10. A big data mining system for AR, characterized in that: The AR-oriented big data mining system includes a processor and a machine-readable storage medium, wherein the machine-readable storage medium stores machine-executable instructions, and the machine-executable instructions are loaded and executed by the processor to implement the AR-oriented big data mining method of any one of claims 1-9.

Images