A method and system for building a website for a stand-alone station in a home industry belt

Abstract

The application provides a home industry zone independent station building service method and system, belonging to the technical field of data processing. First, a building request containing a target area identifier and a business feature identifier is obtained. Then, based on a predefined industry resource map, a continuous geographic space associated with the target area identifier is determined. Then, according to the real-time data corresponding to the continuous geographic space, a plurality of service blocks are generated, each block is associated with a geographic sub-area, and its corresponding feature vector is determined. Then, the matching degree of the business feature identifier and each feature vector is calculated, and the proximity is calculated in combination with the real-time load state of each service block and the target area identifier. Finally, based on the matching degree and the proximity, a main service block is determined from all service blocks, and based on the feature vector of the main service block, a final independent station corresponding to the building request is determined and generated. The application realizes the matching of building service and industry zone resources in business relevance and geographic service accessibility.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a method and system for building independent websites in the home furnishing industry. Background Technology

[0002] In the current e-commerce and digital marketing landscape, building independent websites for businesses within specific industrial clusters is a common service. Existing website building methods typically rely on generic templates or fixed functional modules, often neglecting the specific geographical location and real-time status of the industry resources within the website's domain. For example, traditional methods cannot automatically match a furniture factory's industrial cluster with advantageous raw material supplier networks, local logistics services, or unique craft showcase modules. This results in a website disconnected from the local industry chain ecosystem, failing to fully leverage the collaborative efficiency and localized service advantages of geographical proximity. Furthermore, it struggles to dynamically adapt to real-time changes in regional industry resources, leading to deficiencies in resource integration depth, service responsiveness, and long-term adaptability. Summary of the Invention

[0003] This application provides a method and system for building independent websites in the home furnishing industry cluster to improve the above-mentioned problems.

[0004] To achieve the above objectives, this application adopts the following technical solution: Firstly, this application proposes a method for building independent websites for the home furnishing industry belt, including: Obtain a website building request containing the target region identifier and business characteristic identifier; Based on a predefined industry resource map, a continuous geographic space associated with the target area identifier is determined, wherein the industry resource map is used to represent the mapping relationship between geographic coordinates and industry resource data; Based on multiple real-time data points corresponding to continuous geographic space in the industry resource map, multiple service blocks are generated, where each service block is associated with a sub-region of continuous geographic space. Based on the industry resource data corresponding to each sub-region, determine the feature vector corresponding to each service block; Using the business feature identifier as input, obtain the matching degree between the business feature identifier and each feature vector; Obtain the real-time load status of each service block, and based on the real-time load status and the target area identifier, obtain the proximity between the website building request and each service block; Based on matching degree and proximity, a primary service block is determined from multiple service blocks; Based on the feature vector corresponding to the main service block, the independent site corresponding to the site creation request is determined.

[0005] In conjunction with the first aspect, optionally, based on the feature vector corresponding to the main service block, the independent site corresponding to the site creation request is determined, including: Obtain the industry correlation between the main service block and other service blocks from the industry resource map; Construct an industry association graph, in which the main service block and other service blocks are used as the first node, and the degree of association between the first nodes is used as the weight of the edge. The feature vector is used as the initial feature input of the corresponding first node into the graph neural network model, and the industry association graph is used for information propagation and aggregation. The updated feature vector corresponding to the first node of the main service block is output and used as the site configuration vector.

[0006] In conjunction with the first aspect, optionally, based on the industry resource data corresponding to each sub-region, a feature vector corresponding to each service block is determined, including: The industry resource data is divided into resource indicators with multiple preset dimensions; Get the aggregated values ​​of resource metrics from multiple dimensions within the sub-region corresponding to each service block; Determine multidimensional numerical vectors based on aggregated values; Dimensionality reduction and feature extraction are performed on the multidimensional numerical vector to generate a feature vector corresponding to each service block.

[0007] In conjunction with the first aspect, optionally, using the business feature identifier as input, the matching degree between the business feature identifier and each feature vector is obtained, including: Use business characteristic identifiers as structured query conditions, wherein the structured query conditions include at least one industry classification code and resource demand label; Based on the feature vector of each service block, the corresponding set of industry resource descriptions is determined. The set of industry resource descriptions includes resource type, scale and service capability parameters. Based on a pre-trained semantic matching model, the matching probability between structured query conditions and each set of industry resource descriptions is obtained and used as the matching degree.

[0008] In conjunction with the first aspect, optionally, the real-time load status of each service block is obtained, and based on the real-time load status and the target region identifier, the proximity between the website building request and each service block is obtained, including: Determine reference geographic coordinates based on the target area identifier; Obtain the Euclidean distance between the reference geographic coordinates and the geographic center of each service block; Obtain time-series data of resource utilization and service response time for each service block within a preset time window, and obtain the load coefficient based on the resource utilization and time-series data; The first parameter is obtained by normalizing the Euclidean distance, and the current load coefficient is used as the second parameter. Based on the business type specified in the business feature identifier, adjust the weights of the first and second parameters in the weighted fusion; The first and second parameters are weighted and summed based on the adjusted weights to obtain the overall proximity between the website creation request and each service block.

[0009] In conjunction with the first aspect, optionally, based on the business type specified in the business feature identifier, the weights of the first parameter and the second parameter in the weighted fusion are adjusted, including: When the business type is real-time interactive, increase the weight of the second parameter; When the business type is resource-intensive, increase the weight of the first parameter.

[0010] In conjunction with the first aspect, optionally, a primary service block is determined from multiple service blocks based on matching degree and proximity, including: Obtain the first threshold and determine the service blocks with a matching degree higher than the first threshold as the first candidate set; If the first candidate set is empty, the top N service blocks in descending order of matching degree are selected and included in the first candidate set, where N is a preset positive integer; Based on the proximity of all service blocks in the first candidate set, a candidate directed graph is determined with service blocks as second nodes and resource collaboration costs between second nodes as edges. The resource collaboration costs are determined based on the industry relevance and geographical distance between the second nodes. In the candidate directed graph, the reference geographic coordinates mapped by the target region identifier are used as the virtual starting point to determine the path cost to each second node. The path cost includes the load coefficient corresponding to the second node on the path and the collaboration cost corresponding to the edge. The service block corresponding to the path with the minimum path cost is determined as the main service block.

[0011] Secondly, this application proposes a website building service system for independent websites in the home furnishing industry belt, the system being configured as follows: Obtain a website building request containing the target region identifier and business characteristic identifier; Based on a predefined industry resource map, a continuous geographic space associated with the target area identifier is determined, wherein the industry resource map is used to represent the mapping relationship between geographic coordinates and industry resource data; Based on multiple real-time data points corresponding to continuous geographic space in the industry resource map, multiple service blocks are generated, where each service block is associated with a sub-region of continuous geographic space. Based on the industry resource data corresponding to each sub-region, determine the feature vector corresponding to each service block; Using the business feature identifier as input, obtain the matching degree between the business feature identifier and each feature vector; Obtain the real-time load status of each service block, and based on the real-time load status and the target area identifier, obtain the proximity between the website building request and each service block; Based on matching degree and proximity, a primary service block is determined from multiple service blocks; Based on the feature vector corresponding to the main service block, the independent site corresponding to the site creation request is determined.

[0012] In conjunction with the second aspect, optionally, the system is configured as follows: Based on the feature vector corresponding to the main service block, the independent websites corresponding to the website building request are determined, including: Obtain the industry correlation between the main service block and other service blocks from the industry resource map; Construct an industry association graph, in which the main service block and other service blocks are used as the first node, and the degree of association between the first nodes is used as the weight of the edge. The feature vector is used as the initial feature input of the corresponding first node into the graph neural network model, and the industry association graph is used for information propagation and aggregation. The updated feature vector corresponding to the first node of the main service block is output and used as the site configuration vector.

[0013] In conjunction with the second aspect, optionally, the system is configured as follows: Based on the industry resource data corresponding to each sub-region, the feature vector corresponding to each service block is determined, including: The industry resource data is divided into resource indicators with multiple preset dimensions; Get the aggregated values ​​of resource metrics from multiple dimensions within the sub-region corresponding to each service block; Determine multidimensional numerical vectors based on aggregated values; Dimensionality reduction and feature extraction are performed on the multidimensional numerical vector to generate a feature vector corresponding to each service block.

[0014] In conjunction with the second aspect, optionally, the system is configured as follows: Using the business feature identifier as input, obtain the matching degree between the business feature identifier and each feature vector, including: Use business characteristic identifiers as structured query conditions, wherein the structured query conditions include at least one industry classification code and resource demand label; Based on the feature vector of each service block, the corresponding set of industry resource descriptions is determined. The set of industry resource descriptions includes resource type, scale and service capability parameters. Based on a pre-trained semantic matching model, the matching probability between structured query conditions and each set of industry resource descriptions is obtained and used as the matching degree.

[0015] In conjunction with the second aspect, optionally, the system is configured as follows: Obtain the real-time load status of each service block, and based on the real-time load status and the target region identifier, obtain the proximity between the website building request and each service block, including: Determine reference geographic coordinates based on the target area identifier; Obtain the Euclidean distance between the reference geographic coordinates and the geographic center of each service block; Obtain time-series data of resource utilization and service response time for each service block within a preset time window, and obtain the load coefficient based on the resource utilization and time-series data; The first parameter is obtained by normalizing the Euclidean distance, and the current load coefficient is used as the second parameter. Based on the business type specified in the business feature identifier, adjust the weights of the first and second parameters in the weighted fusion; The first and second parameters are weighted and summed based on the adjusted weights to obtain the overall proximity between the website creation request and each service block.

[0016] In conjunction with the second aspect, optionally, the system is configured as follows: Based on the business type specified in the business feature identifier, adjust the weights of the first and second parameters in the weighted fusion, including: When the business type is real-time interactive, increase the weight of the second parameter; When the business type is resource-intensive, increase the weight of the first parameter.

[0017] In conjunction with the second aspect, optionally, the system is configured as follows: Based on matching degree and proximity, a primary service block is determined from multiple service blocks, including: Obtain the first threshold and determine the service blocks with a matching degree higher than the first threshold as the first candidate set; If the first candidate set is empty, the top N service blocks in descending order of matching degree are selected and included in the first candidate set, where N is a preset positive integer; Based on the proximity of all service blocks in the first candidate set, a candidate directed graph is determined with service blocks as second nodes and resource collaboration costs between second nodes as edges. The resource collaboration costs are determined based on the industry relevance and geographical distance between the second nodes. In the candidate directed graph, the reference geographic coordinates mapped by the target region identifier are used as the virtual starting point to determine the path cost to each second node. The path cost includes the load coefficient corresponding to the second node on the path and the collaboration cost corresponding to the edge. The service block corresponding to the path with the minimum path cost is determined as the main service block.

[0018] A third aspect of this invention provides an electronic device, which includes: At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method proposed in the first aspect of the present invention.

[0019] A fourth aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method as described in the first aspect of the present invention.

[0020] In summary, the above method and apparatus have the following technical effects: This invention discloses a method and system for building independent websites within a home furnishing industry cluster. First, a website building request containing a target area identifier and a business feature identifier is obtained. Then, based on a predefined industry resource map, a continuous geographic space associated with the target area identifier is determined. This map represents the mapping relationship between geographic coordinates and industry resource data. Next, based on real-time data corresponding to this continuous geographic space, multiple service blocks are generated, each block associated with a geographic sub-region, and its corresponding feature vector is determined. Then, the matching degree between the business feature identifier and each feature vector is calculated, and the proximity is calculated by combining the real-time load status of each service block with the target area identifier. Finally, based on the matching degree and proximity, a master service block is determined from all service blocks, and based on the feature vector of this master service block, the final independent website corresponding to the website building request is determined and generated. This invention achieves intelligent matching between website building services and industry cluster resources in terms of business relevance and geographic service accessibility. Attached Figure Description

[0021] Figure 1 This is a flowchart illustrating a method for building an independent website for a home furnishing industry cluster, as proposed in an embodiment of this application. Detailed Implementation

[0022] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0023] This application provides a method for building independent websites for the home furnishing industry cluster. Please refer to [link / reference]. Figure 1 This includes the following steps: S101: Obtain a website building request containing the target area identifier and business characteristic identifier.

[0024] Understandably, a target area identifier is an identifier used to define the geographical service scope or resource preference area. It can be a specific administrative region name, such as "XX City XX District," or it can be an area manually selected by the user on an electronic map. No limitation is made here. A business characteristic identifier is an identifier used to describe the core business attributes and functional requirements of the website's main entity, such as raw material suppliers, manufacturers, finished product brand owners, cross-border e-commerce sellers, or other characteristic information. For example, a bamboo product company's business characteristic identifier might be {Industry segment: Manufacturer, Product category: [Bamboo furniture, bamboo handicrafts], Business model: Wholesale and customization, Key requirement: Display of environmentally friendly material certification}.

[0025] For example, if a bamboo products company located in Beijing submits a request, its target area might be Beijing. When subsequently seeking raw materials, logistics, and industry resources, priority should be given to Beijing and its surrounding areas.

[0026] S102: Based on a predefined industry resource map, determine the continuous geographic space associated with the target area identifier, wherein the industry resource map is used to represent the mapping relationship between geographic coordinates and industry resource data.

[0027] Understandably, a predefined industry resource map is a fusion of a specially constructed industry database and a geographic information system. Essentially, it's a massive digital model where each geographic coordinate is associated with one or more sets of structured industry resource data. For example, a coordinate might be associated with a sponge manufacturing plant (resource type: raw materials, capacity: XX tons / month), while another region might be associated with the transportation capacity data of a furniture logistics park (resource type: logistics, average daily shipments: XX trucks). It might also include information such as supplier density, distribution of specialized processes, and locations of supporting service providers.

[0028] Continuous geographic space refers to a physically coherent, unbroken region not fragmented by administrative boundaries or other non-industrial factors. It is dynamically defined by an industrial resource map based on the inherent connections between resources, rather than a simple circular or rectangular area. It's important to note that its continuity implies that the industrial resources within the space are distributed in a continuous manner and are closely linked in economic activities, thus allowing for resource allocation and block division as a whole.

[0029] Specifically, in this embodiment, the core geographic coordinates corresponding to the identifier are first located. Then, instead of being limited to the administrative boundaries of the identifier itself, the boundary is automatically extended and delineated outward based on the actual distribution density and correlation network of industrial resource data in the map, until a natural boundary is found where the resource distribution changes from dense to sparse, or the industrial correlation decreases significantly. This finally delineated area with a coherent internal industrial ecosystem is the associated continuous geographic space.

[0030] S103: Based on multiple real-time data corresponding to continuous geographic space in the industry resource map, generate multiple service blocks, wherein each service block is associated with a sub-region of continuous geographic space.

[0031] Understandably, each service block is a dynamically clustered block based on real-time industry data. For example, it could be a group of resource points that are geographically close, have complementary or similar resource functions, and whose data indicators, such as response speed and load, indicate that they can collaborate efficiently. These are packaged together to form a virtual service block. Therefore, each service block is a virtual logical entity, but it is bound to a specific, continuous physical sub-region.

[0032] S104: Based on the industry resource data corresponding to each sub-region, determine the feature vector corresponding to each service block.

[0033] As is understandable, a feature vector is essentially the industry resource data contained within a block, integrated into a set of structured numerical features. For example, the feature vector of a service block might be: [0.85, 0.92, 0.45, 0.78, 0.33], where: the first value of 0.85 may represent the strength of the solid wood supply chain, the second value of 0.92 may represent the concentration of traditional furniture craftsmanship, the third value of 0.45 may represent the supporting capabilities of modern smart homes, the fourth value of 0.78 may represent the local logistics efficiency index, and the fifth value of 0.33 may represent the current service load rate. Of course, the specific meaning is not specifically limited in this application.

[0034] Specifically, in this application, step S104 may include the following steps: S1041: Divide industry resource data into resource indicators of multiple preset dimensions.

[0035] Understandably, the complex and diverse raw industrial resource information within a service block, such as "Factory A has a daily production capacity of 200 sets", "Logistics point B has 3 idle trucks", and "Design studio C supports 3D modeling", can be categorized, filtered, and quantified according to a series of analytical dimensions related to the evaluation of website building service capabilities, such as "production supply capacity", "logistics agility", and "design support level". This will generate a series of measurable and specific numerical indicators, such as "the comprehensive capacity index of this block is 0.8", "the average logistics response speed is 2 hours", and "the digital design service coverage rate is 75%".

[0036] S1042: Obtain the aggregated values ​​of resource metrics across multiple dimensions within the sub-region corresponding to each service block.

[0037] Understandably, for each resource dimension defined in the previous step, the system iterates through all industry resource points within the sub-regions covered by the specified service block. Using pre-defined mathematical rules, the original indicator values ​​of the same dimension scattered across each resource point are aggregated into a single numerical result that represents the overall level or scale of the block in that dimension. For example, for the dimension of "logistics response speed," the system calculates the harmonic mean of the promised response times of all logistics service providers in the region as the aggregated value; for the dimension of "raw material supplier capacity," it may add up the rated capacity of all relevant suppliers to obtain the total capacity as the aggregated value. This process elevates fine-grained point data into surface data that characterizes the overall service capability of the block.

[0038] S1043: Determine multidimensional numerical vectors based on aggregated values.

[0039] Specifically, firstly, through techniques such as normalization, the dimensional differences between different indicators are eliminated from multiple aggregated values, making them scalar values. Then, these processed scalar values ​​are arranged sequentially according to a preset dimensional order to form a multidimensional array with a unified structure, i.e., a multidimensional numerical vector.

[0040] S1044: Perform dimensionality reduction and feature extraction on the multidimensional numerical vector to generate the feature vector corresponding to each service block.

[0041] Understandably, a multidimensional numerical vector is input into a specific algorithm model. Through mathematical transformations, noise and secondary components in the data are removed, and the few key dimension combinations that best distinguish the industry characteristics of different blocks and are most relevant to the final website construction service goals are extracted and retained. Finally, a new vector with a lower dimension is output, which is the final feature vector of the service block. Specific algorithm models have been disclosed in relevant technical documents and are not limited in this application.

[0042] S105: Using the business feature identifier as input, obtain the matching degree between the business feature identifier and each feature vector.

[0043] Understandably, the matching score is a numerical score used to measure the likelihood and suitability of each service block to meet the specific website building requirements.

[0044] Specifically, as one implementation method, in this application, step S105 may include the following steps: S1051: Use business characteristic identifiers as structured query conditions, wherein the structured query conditions include at least one industry classification code and resource demand label.

[0045] Specifically, the website building intent expressed by users in natural language or simple options is automatically converted and output into a structured data object containing standardized classification codes and clear requirement parameters through preset parsing rules or models; that is, structured query conditions. For example, these conditions include at least one industry classification code pointing to a specific industry category and sub-segment, such as mapping "producing mahogany furniture" to the "C2192 hardwood furniture manufacturing" code in the national industry standard, and one or more resource requirement tags that specifically describe the required services or capabilities, such as needing 3D rotating product display or needing to connect to a local logistics tracking API.

[0046] S1052: Based on the corresponding feature vector of each service block, determine the corresponding set of industry resource descriptions, which includes resource type, scale and service capability parameters.

[0047] Understandably, by calling pre-defined mapping rules or decoding models, the values ​​of each dimension in the feature vector can be restored and combined into a detailed list of industry resources. This list is a set of industry resource descriptions, which clearly lists the types of resources available in the block, such as raw material suppliers, logistics service providers, testing institutions, the scale or quantity of each type, such as the number of suppliers and the total warehouse area, as well as key service capability parameters, such as average delivery cycle, supported languages, and maximum concurrent order processing volume.

[0048] S1053: Based on a pre-trained semantic matching model, obtain the matching probability between structured query conditions and each set of industry resource descriptions, and use it as the matching degree.

[0049] Specifically, the structured query conditions and the set of industry resource descriptions for each block are simultaneously input into a pre-trained semantic matching model, such as a deep neural network model based on BERT, SBERT, etc. (details omitted here). This model analyzes the deep semantic relationship between the two, such as synonym recognition, contextual relevance, and intent fit, to obtain the probability value of the degree of satisfaction between the requirements in the query conditions and the service capabilities represented by each set of resource descriptions. This probability value is directly used as the quantified matching degree output.

[0050] S106: Obtain the real-time load status of each service block, and based on the real-time load status and the target area identifier, obtain the proximity between the website building request and each service block.

[0051] Understandably, real-time load status refers to the current processing capacity and pressure level of each service block. This can be obtained through source utilization, such as the utilization rate of computing resources and bandwidth, or service response metrics, such as the average response latency of API interfaces and task queue length, etc., without limitation here. Specifically, in this application, step S106 may include the following steps: S1061: Determine reference geographic coordinates based on the target area identifier.

[0052] Understandably, the target area identifier may be an administrative place name, and therefore, in this application, it is mapped to a geographic coordinate point with standard latitude and longitude values ​​or a representative coordinate, such as the geometric center of the area.

[0053] S1062: Obtain the Euclidean distance between the reference geographic coordinates and the geographic center of each service block.

[0054] Understandably, after obtaining the geographic center coordinates of each service block, mathematical operations can be performed on the requested coordinate points and the center points of each block one by one to obtain a series of scalar distance values ​​representing absolute spatial intervals.

[0055] S1063: Obtain time-series data of resource utilization and service response time for each service block within a preset time window, and obtain the load coefficient based on the resource utilization and time-series data.

[0056] For example, key performance indicators (KPIs) for each service block can be continuously collected over a preset period of time, including fluctuations in resource utilization and historical sequences of service response times. By cleaning, aggregating, and analyzing this time-series data, a standardized load coefficient for each block can be calculated using specific statistical algorithms or models. This coefficient, as a single value, reflects the block's immediate pressure level and availability status in terms of service capacity and response efficiency. The specific calculation method is not limited in this application.

[0057] S1064: Normalize the Euclidean distance to obtain the first parameter, and use the current load coefficient as the second parameter.

[0058] S1065: Adjust the weights of the first and second parameters in the weighted fusion based on the business type specified in the business feature identifier.

[0059] Specifically, in this application, when a service is identified as a real-time interactive service, the system increases the weight of the second parameter to prioritize service response speed and availability. When a service is identified as a resource-intensive service, the system increases the weight of the first parameter to prioritize stable resource supply and low transmission latency, thereby enabling the proximity evaluation results to more accurately meet the core requirements of different service scenarios.

[0060] S1066: The first and second parameters are weighted and summed based on the adjusted weights to obtain the comprehensive proximity between the site creation request and each service block.

[0061] Understandably, the comprehensive proximity not only quantifies the physical distance between a website creation request and a service block, but more importantly, it reflects the overall potential and proximity of the block to provide efficient and stable services for that specific type of request under the current system state.

[0062] S107: Determine a primary service block from multiple service blocks based on matching degree and proximity.

[0063] Understandably, from all candidate service blocks, the block that achieves the best balance between business fit and service accessibility is selected as the main service block that ultimately serves the website building request.

[0064] For example, in this application, step S107 may include the following steps: S1071: Obtain the first threshold and determine the service blocks with a matching degree higher than the first threshold as the first candidate set.

[0065] Understandably, the first threshold represents the minimum acceptable standard for matching degree, and the specific parameter value is adjusted according to the actual situation. The purpose is to quickly filter out a subset of services from all service blocks that basically meet the website building requirements in terms of business capabilities by setting a minimum qualified line, thereby improving the efficiency of subsequent complex decision-making processes.

[0066] S1072: If the first candidate set is empty, then select the top N service blocks in descending order of matching degree and include them in the first candidate set, where N is a preset positive integer.

[0067] Understandably, all service blocks are sorted in descending order of their matching scores. Then, starting with the top-ranked block, a preset number (N) of blocks are selected sequentially and included in the first candidate set. For example, if N is preset to 3, the system will select the top three matching blocks as candidates regardless of whether their matching scores meet the standard. This ensures that the decision-making process can continue even when resource and demand matching is generally poor.

[0068] S1073: Based on the proximity of all service blocks in the first candidate set, determine a candidate directed graph with service blocks as second nodes and resource collaboration costs between second nodes as edges, wherein the resource collaboration costs are determined according to the industry correlation and geographical distance between the second nodes.

[0069] Understandably, once the first candidate set is determined, each service block is no longer treated as an isolated option, but rather modeled as a potential network where resource flow and collaboration are possible. Specifically, each service block in this set is treated as a second node, and based on data from the industry resource map, the cost of resource collaboration between any two nodes is calculated. This cost is a composite indicator, primarily determined by two factors: first, the degree of industry relevance between the two blocks (e.g., one block specializes in fabric production, and another in sofa manufacturing; a high degree of relevance results in low collaboration costs); second, their geographical distance—the greater the distance, the higher the costs associated with logistics and delays). These costs are used as weights for directed edges, connecting the corresponding nodes to form a complete candidate directed graph. This graph model clearly depicts the potential paths and their costs within the first candidate set where blocks support and combine with each other to jointly satisfy website building requests.

[0070] For example, suppose the first candidate set contains three blocks: Node P: Cloth Supply Block Node Q: Sofa Manufacturing Block Node R: Logistics and distribution block Cost of edge P->Q: Since the fabric and sofa manufacturing industries are highly related and assuming they are geographically close, the collaboration cost of this edge is very low.

[0071] Cost of Q->R: Manufacturing and logistics are highly correlated, but if the geographical distance is moderate, the cost may be moderate.

[0072] Costs of P->R: Fabric supply goes directly to logistics and distribution, with weak industrial linkages, so costs may be higher.

[0073] S1074: In the candidate directed graph, using the reference geographic coordinates mapped by the target region identifier as the virtual starting point, determine the path cost to each second node. The path cost includes the load coefficient corresponding to the second node on the path and the collaboration cost corresponding to the edge.

[0074] Understandably, the geographical coordinates of the test site are set as a virtual starting point, connected to each of the second nodes in the candidate directed graph, and the total cost of the optimal path from this starting point to each second node in the graph is calculated. The path cost here is a composite metric, which includes not only the edges traversed by the path but also the load coefficient of each second node along the path. This means that when selecting a path, not only the collaboration overhead of going from A to B and then collaborating with C is considered, but also the additional burden brought by having the already busy B participate in the service. This design ensures that the final selected main service block is not only the result of business matching and proximity trade-offs, but also that the entire service path it occupies minimizes the overall load and collaboration overhead under the current system state.

[0075] For example, suppose the virtual starting point is G, and there are two potential paths to node Q in the candidate directed graph: Path 1: G->P (Cloth Block, Low Load Factor)->Q (Sofa Block, Medium Load Factor). This path has low collaboration cost (because P and Q are highly related and close), but it requires passing through two nodes.

[0076] Path 2: G->Q (Sofa Block, Medium Load Factor). This path is direct with zero collaboration cost, but Q needs to handle all tasks independently.

[0077] For the total cost of each path: Cost of path 1 = (Load factor of P) + (Cooperation cost of P->Q) + (Load factor of Q); Cost of path 2 = (Load factor of Q). If the total cost of path 1 is lower than that of path 2, it means that although increasing the cooperation cost by having the low-loaded P assist may be better overall. Calculate such a minimum path cost for each second node.

[0078] S1075: Determine the service block corresponding to the path with the minimum path cost as the main service block.

[0079] Understandably, based on the completion of candidate directed graph construction and path cost calculation, the cost of all candidate paths from the virtual starting point to each second node is compared. Through sorting or direct search algorithms, the path with the smallest total path cost is identified and selected. The service block corresponding to the endpoint of this path, that is, the second node that the path finally reaches, is officially determined by the system as the main service block for serving the website building request.

[0080] Understandably, using this block as the core hub or entry point for the service, and considering its own load and the linkage costs with potential collaborating blocks, can minimize the overall resource scheduling cost and system pressure required to meet the site building needs, thereby achieving an optimal balance between business matching, service accessibility and system efficiency.

[0081] S108: Based on the feature vector corresponding to the main service block, determine the independent site corresponding to the site building request.

[0082] Understandably, the aforementioned optimally selected main service block feature vector, which includes enhanced information, is transformed into a workable independent site that precisely matches the site creation request.

[0083] Specifically, in this application, step S108 may include the following steps: S1081: Obtain the industry correlation between the main service block and other service blocks from the industry resource map.

[0084] Understandably, after identifying the main service block, it was not treated as an isolated service unit. By querying the industry resource map, the inherent business connection strength between the main block and all other service blocks within the industry belt was actively detected and quantified, i.e., the industry correlation. This correlation is not a simple geographical proximity, but a deep business coupling indicator calculated based on factors such as industry chain division of labor, resource complementarity, and historical collaboration data.

[0085] For example, a block centered on "sofa manufacturing" may be highly related to other blocks such as "textile fabric supply," "hardware accessories," and "logistics and distribution." Acquiring this network of connections aims to provide crucial input for subsequent steps, ensuring that when building an independent website, not only the core resources of the main block are reflected, but also the service capabilities of highly related blocks are intelligently integrated.

[0086] S1082: Construct an industry association graph, in which the main service block and other service blocks are used as the first node, and the degree of association between the first nodes is used as the weight of the edge.

[0087] Specifically, a weighted graph data structure is created based on industry correlation data. In this graph, the main service block and all other service blocks in the industry resource map are the vertices of the graph, i.e., the first nodes, and the industry correlation value between any two blocks is quantified as the weight of the edge connecting the two vertices.

[0088] S1083: The feature vector is used as the initial feature input graph neural network model of the corresponding first node, and the industry association graph is used for information dissemination and aggregation.

[0089] Understandably, the feature vectors of the main service block and other service blocks are used as the initial feature representations of the corresponding nodes in the industry association graph, i.e., the first node, and input into a pre-trained graph neural network model (GNN). For the specific parameters of the model, please refer to the relevant technical documents, which do not limit them in this application.

[0090] Specifically, this model can perform information propagation and aggregation based on a graph structure. That is, along the edges of the industry association graph, nodes are allowed to exchange, transmit, and merge their feature information multiple times. Understandably, each node receives feature information from all its associated nodes and performs weighted summarization and nonlinear transformation on this information according to the weights of the associated edges, thereby generating a new feature representation updated for that node that integrates its own feature information and that of its associated blocks.

[0091] Understandably, this process results in the feature vector ultimately obtained by the main service block node not only containing its own original resource information, but also deeply integrating complementary or reinforcing resource features from its highly correlated neighboring blocks.

[0092] S1084: Output the updated feature vector corresponding to the first node of the main service block, and use it as the site configuration vector.

[0093] Understandably, after processing the information propagation and aggregation of all nodes, the model will extract the feature vector corresponding to the specific node of the main service block from the final node embedding layer. This vector has deeply integrated its own and the resource information of related blocks.

[0094] Understandably, this updated feature vector can be designated as the site configuration vector. Its content will be directly mapped to specific functional modules, content elements, and service interface configurations.

[0095] This invention discloses a method for building an independent website for a home furnishing industry cluster. First, a website building request containing a target area identifier and a business feature identifier is obtained. Then, based on a predefined industry resource map, a continuous geographic space associated with the target area identifier is determined. Next, based on real-time data corresponding to this continuous geographic space, multiple service blocks are generated, each block associated with a geographic sub-region, and its corresponding feature vector is determined. Then, the matching degree between the business feature identifier and each feature vector is calculated, and the proximity is calculated by combining the real-time load status of each service block with the target area identifier. Finally, based on the matching degree and proximity, a master service block is determined from all service blocks, and based on the feature vector of this master service block, the final independent website corresponding to the website building request is determined and generated. This invention achieves intelligent matching between the website building service and industry cluster resources in terms of business relevance and geographic service accessibility.

[0096] Based on the same inventive concept, embodiments of this application also propose a home furnishing industry belt independent website building service system, the system being configured as follows: Obtain a website building request containing the target region identifier and business characteristic identifier; Based on a predefined industry resource map, a continuous geographic space associated with the target area identifier is determined, wherein the industry resource map is used to represent the mapping relationship between geographic coordinates and industry resource data; Based on multiple real-time data points corresponding to continuous geographic space in the industry resource map, multiple service blocks are generated, where each service block is associated with a sub-region of continuous geographic space. Based on the industry resource data corresponding to each sub-region, determine the feature vector corresponding to each service block; Using the business feature identifier as input, obtain the matching degree between the business feature identifier and each feature vector; Obtain the real-time load status of each service block, and based on the real-time load status and the target area identifier, obtain the proximity between the website building request and each service block; Based on matching degree and proximity, a primary service block is determined from multiple service blocks; Based on the feature vector corresponding to the main service block, the independent site corresponding to the site creation request is determined.

[0097] Optionally, the system is configured as follows: Based on the feature vector corresponding to the main service block, the independent websites corresponding to the website building request are determined, including: Obtain the industry correlation between the main service block and other service blocks from the industry resource map; Construct an industry association graph, in which the main service block and other service blocks are used as the first node, and the degree of association between the first nodes is used as the weight of the edge. The feature vector is used as the initial feature input of the corresponding first node into the graph neural network model, and the industry association graph is used for information propagation and aggregation. The updated feature vector corresponding to the first node of the main service block is output and used as the site configuration vector.

[0098] Optionally, the system is configured as follows: Based on the industry resource data corresponding to each sub-region, the feature vector corresponding to each service block is determined, including: The industry resource data is divided into resource indicators with multiple preset dimensions; Get the aggregated values ​​of resource metrics from multiple dimensions within the sub-region corresponding to each service block; Determine multidimensional numerical vectors based on aggregated values; Dimensionality reduction and feature extraction are performed on the multidimensional numerical vector to generate a feature vector corresponding to each service block.

[0099] Optionally, the system is configured as follows: Using the business feature identifier as input, obtain the matching degree between the business feature identifier and each feature vector, including: Use business characteristic identifiers as structured query conditions, wherein the structured query conditions include at least one industry classification code and resource demand label; Based on the feature vector of each service block, the corresponding set of industry resource descriptions is determined. The set of industry resource descriptions includes resource type, scale and service capability parameters. Based on a pre-trained semantic matching model, the matching probability between structured query conditions and each set of industry resource descriptions is obtained and used as the matching degree.

[0100] Optionally, the system is configured as follows: Obtain the real-time load status of each service block, and based on the real-time load status and the target region identifier, obtain the proximity between the website building request and each service block, including: Determine reference geographic coordinates based on the target area identifier; Obtain the Euclidean distance between the reference geographic coordinates and the geographic center of each service block; Obtain time-series data of resource utilization and service response time for each service block within a preset time window, and obtain the load coefficient based on the resource utilization and time-series data; The first parameter is obtained by normalizing the Euclidean distance, and the current load coefficient is used as the second parameter. Based on the business type specified in the business feature identifier, adjust the weights of the first and second parameters in the weighted fusion; The first and second parameters are weighted and summed based on the adjusted weights to obtain the overall proximity between the website creation request and each service block.

[0101] Optionally, the system is configured as follows: Based on the business type specified in the business feature identifier, adjust the weights of the first and second parameters in the weighted fusion, including: When the business type is real-time interactive, increase the weight of the second parameter; When the business type is resource-intensive, increase the weight of the first parameter.

[0102] Optionally, the system is configured as follows: Based on matching degree and proximity, a primary service block is determined from multiple service blocks, including: Obtain the first threshold and determine the service blocks with a matching degree higher than the first threshold as the first candidate set; If the first candidate set is empty, the top N service blocks in descending order of matching degree are selected and included in the first candidate set, where N is a preset positive integer; Based on the proximity of all service blocks in the first candidate set, a candidate directed graph is determined with service blocks as second nodes and resource collaboration costs between second nodes as edges. The resource collaboration costs are determined based on the industry relevance and geographical distance between the second nodes. In the candidate directed graph, the reference geographic coordinates mapped by the target region identifier are used as the virtual starting point to determine the path cost to each second node. The path cost includes the load coefficient corresponding to the second node on the path and the collaboration cost corresponding to the edge. The service block corresponding to the path with the minimum path cost is determined as the main service block.

[0103] This invention discloses a website building service system for independent websites in a home furnishing industry cluster. First, it obtains a website building request containing a target area identifier and a business feature identifier. Then, based on a predefined industry resource map, it determines a continuous geographic space associated with the target area identifier. Next, based on real-time data corresponding to this continuous geographic space, it generates multiple service blocks, each block associated with a geographic sub-region, and determines its corresponding feature vector. Then, it calculates the matching degree between the business feature identifier and each feature vector, and calculates the proximity between the real-time load status of each service block and the target area identifier. Finally, based on the matching degree and proximity, it determines a master service block from all service blocks, and based on the feature vector of this master service block, it determines and generates the final independent website corresponding to the website building request. This invention achieves intelligent matching between website building services and industry cluster resources in terms of business relevance and geographic service accessibility.

[0104] Based on the same inventive concept, embodiments of this application also propose an electronic device, which includes: At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the home furnishing industry independent website building service method of the present application embodiments.

[0105] In addition, to achieve the above objectives, embodiments of this application also propose a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the home furnishing industry belt independent website building service method of embodiments of this application.

[0106] The following is a detailed introduction to the various components of the electronic device: In this context, the processor is the control center of the electronic device. It can be a single processor or a collective term for multiple processing elements. For example, a processor can be one or more central processing units (CPUs), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention, such as one or more digital signal processors (DSPs), or one or more field-programmable gate arrays (FPGAs).

[0107] Alternatively, the processor can perform various functions of the electronic device by running or executing software programs stored in memory and by calling data stored in memory.

[0108] The memory is used to store the software program that executes the solution of the present invention, and the execution is controlled by the processor. The specific implementation method can be referred to the above method embodiment, which will not be repeated here.

[0109] Optionally, the memory can be read-only memory (ROM) or other types of static storage devices capable of storing static information and instructions, random access memory (RAM) or other types of dynamic storage devices capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. The memory can be integrated with the processor or exist independently and coupled to the processor through an interface circuit of an electronic device; the embodiments of the present invention do not specifically limit this.

[0110] A transceiver is used to communicate with network devices or with terminal devices.

[0111] Optionally, the transceiver may include a receiver and a transmitter. The receiver is used to implement the receiving function, and the transmitter is used to implement the sending function.

[0112] Optionally, the transceiver can be integrated with the processor or exist independently and coupled to the processor through the router's interface circuit. This embodiment of the invention does not specifically limit this.

[0113] Furthermore, the technical effects of the electronic device can be referred to the technical effects of the data transmission method in the above method embodiments, and will not be repeated here.

[0114] It should be understood that the processor in the embodiments of the present invention can be a central processing unit (CPU), or it can be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0115] It should also be understood that the memory in the embodiments of the present invention can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous DRAM (DDRSDRAM), enhanced synchronous DRAM (ESDRAM), synchronous linked DRAM (SLDRAM), and direct rambus RAM (DRRAM).

[0116] The above embodiments can be implemented, in whole or in part, by software, hardware (such as circuits), firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. A computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the flow or function according to the embodiments of the present invention is generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. Computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. A computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. Available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media. Semiconductor media can be solid-state drives.

[0117] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. A and B can be singular or plural. Additionally, the character " / " in this article generally indicates an "or" relationship between the preceding and following related objects, but it can also represent an "and / or" relationship. Please refer to the context for a more accurate understanding.

[0118] In this invention, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of a single item or a plurality of items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be a single item or multiple items.

[0119] It should be understood that, in various embodiments of the present invention, the sequence number of each process does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0120] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

Claims

1. A method for building an independent website for a home furnishing industry cluster, characterized in that, include: Obtain a website building request containing the target region identifier and business characteristic identifier; Based on a predefined industry resource map, a continuous geographic space associated with the target area identifier is determined, wherein the industry resource map is used to represent the mapping relationship between geographic coordinates and industry resource data; Based on multiple real-time data corresponding to the continuous geographic space in the industrial resource map, multiple service blocks are generated, wherein each service block is associated with a sub-region of the continuous geographic space; Based on the industry resource data corresponding to each of the sub-regions, determine the feature vector corresponding to each of the service blocks; Using the business feature identifier as input, obtain the matching degree between the business feature identifier and each feature vector; Obtain the real-time load status of each service block, and based on the real-time load status and the target area identifier, obtain the proximity between the website building request and each service block; Based on the matching degree and the proximity degree, a primary service block is determined from the plurality of service blocks; Based on the feature vector corresponding to the main service block, the independent site corresponding to the site creation request is determined.

2. The method for building an independent website for a home furnishing industry cluster according to claim 1, characterized in that, Based on the feature vector corresponding to the main service block, the independent site corresponding to the site creation request is determined, including: From the industry resource map, obtain the industry correlation between the main service block and other service blocks; Construct an industry association graph, wherein the main service block and other service blocks are used as first nodes in the industry association graph, and the degree of association between the first nodes is used as the weight of the edge. The feature vector is used as the initial feature input to the graph neural network model of the corresponding first node, and the industry association graph is used for information dissemination and aggregation. The updated feature vector corresponding to the first node of the main service block is output and used as the site configuration vector.

3. The method for building an independent website for a home furnishing industry cluster according to claim 2, characterized in that, Based on the industry resource data corresponding to each of the sub-regions, a feature vector corresponding to each of the service blocks is determined, including: The industry resource data is divided into resource indicators of multiple preset dimensions; Obtain the aggregated values ​​of the resource indicators across multiple dimensions within the sub-region corresponding to each service block; Based on the aggregated values, a multidimensional numerical vector is determined; The multidimensional numerical vector is subjected to dimensionality reduction and feature extraction to generate a feature vector corresponding to each service block.

4. The method for building an independent website for a home furnishing industry cluster according to claim 2, characterized in that, Using the business feature identifier as input, the matching degree between the business feature identifier and each feature vector is obtained, including: The business feature identifier is used as a structured query condition, wherein the structured query condition includes at least one industry classification code and resource demand tag; Based on the feature vector corresponding to each service block, a corresponding set of industry resource descriptions is determined, which includes resource type, scale, and service capability parameters. Based on a pre-trained semantic matching model, the matching probability between the structured query conditions and each set of industry resource descriptions is obtained, and this probability is used as the matching degree.

5. The method for building an independent website for a home furnishing industry cluster according to claim 2, characterized in that, Obtain the real-time load status of each service block, and based on the real-time load status and the target region identifier, obtain the proximity between the website building request and each service block, including: The reference geographic coordinates are determined based on the target area identifier; Obtain the Euclidean distance between the reference geographic coordinates and the geographic center of each service block; Obtain time-series data of resource utilization and service response time for each service block within a preset time window, and obtain the load coefficient based on the resource utilization and the time-series data; The first parameter is obtained by normalizing the Euclidean distance, and the current load coefficient is used as the second parameter. Based on the business type specified in the business feature identifier, adjust the weights of the first parameter and the second parameter in the weighted fusion; The first parameter and the second parameter are weighted and summed based on the adjusted weights to obtain the comprehensive proximity of the website building request to each service block.

6. The method for building an independent website for a home furnishing industry cluster according to claim 5, characterized in that, Based on the business type specified in the business feature identifier, the weights of the first parameter and the second parameter in the weighted fusion are adjusted, including: When the business type is real-time interactive, increase the weight of the second parameter; When the business type is resource-intensive, increase the weight of the first parameter.

7. The method for building an independent website for a home furnishing industry cluster according to claim 2, characterized in that, Based on the matching degree and the proximity degree, a primary service block is determined from the plurality of service blocks, including: Obtain a first threshold, and determine the service blocks whose matching degree is higher than the first threshold as the first candidate set; If the first candidate set is empty, then the top N service blocks in descending order of matching degree are selected and included in the first candidate set, where N is a preset positive integer; Based on the proximity of all the service blocks in the first candidate set, a candidate directed graph is determined with the service blocks as second nodes and the resource collaboration cost between the second nodes as edges, wherein the resource collaboration cost is determined according to the industry correlation and geographical distance between the second nodes. In the candidate directed graph, the reference geographic coordinates mapped by the target region identifier are used as virtual starting points to determine the path cost to each second node. The path cost includes the load coefficient corresponding to the second node on the path and the collaboration cost corresponding to the edge. The service block corresponding to the path with the lowest path cost is determined as the main service block.

8. A website building service system for an independent website in a home furnishing industry cluster, characterized in that, The system is configured as follows: Obtain a website building request containing the target region identifier and business characteristic identifier; Based on a predefined industry resource map, a continuous geographic space associated with the target area identifier is determined, wherein the industry resource map is used to represent the mapping relationship between geographic coordinates and industry resource data; Based on multiple real-time data corresponding to the continuous geographic space in the industrial resource map, multiple service blocks are generated, wherein each service block is associated with a sub-region of the continuous geographic space; Based on the industry resource data corresponding to each of the sub-regions, determine the feature vector corresponding to each of the service blocks; Using the business feature identifier as input, obtain the matching degree between the business feature identifier and each feature vector; Obtain the real-time load status of each service block, and based on the real-time load status and the target area identifier, obtain the proximity between the website building request and each service block; Based on the matching degree and the proximity degree, a primary service block is determined from the plurality of service blocks; Based on the feature vector corresponding to the main service block, the independent site corresponding to the site creation request is determined.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; And, the memory that is communicatively connected to at least one of the processors; The memory stores instructions that can be executed by at least one of the processors, which, when executed by at least one of the processors, enable the at least one of the processors to perform the method as claimed in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, It stores a computer program that, when executed by a processor, implements the method as claimed in any one of claims 1-7.

Images