Background data processing method and apparatus, device, and medium

Abstract

This invention relates to the field of data processing technology, and discloses a backend data processing method, apparatus, device, and medium, comprising: standardizing and uploading the basic equipment information of the target device to a backend server; using a preset semantic network for semantic deconstruction and reorganization to generate a structured semantic knowledge graph, thereby deeply revealing the inherent logical relationships between data. Based on this graph, a business indicator heatmap is drawn in conjunction with real-time backend business data to intuitively present risks and performance bottlenecks; a real-time business recommendation strategy is generated in conjunction with customer data to achieve precise marketing decisions; simultaneously, the business logic is modeled and associated with business data to obtain a visualized business process graph, clarifying the business logic and data flow. Finally, the heatmap, recommendation strategy, and process graph are integrated to generate a unified business navigation interface. This invention improves the data integration capability and semantic parsing capability of complex business data during backend data processing.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a background data processing method, apparatus, device, and medium. Background Technology

[0002] In current digital business operations, enterprises rely on massive backend devices, complex business processes, and diverse customer data to support core services. While traditional backend data processing methods can monitor and analyze these elements to some extent, their inherent limitations make it difficult to meet the demands of intelligent, real-time, and integrated operations.

[0003] In existing technologies, basic equipment information (such as performance indicators and configuration status), dynamic business transaction data, and static customer attribute data are typically stored in heterogeneous systems, enabling only simple keyword-based queries or isolated indicator statistics. Existing methods cannot deeply understand the non-explicit logical relationships within business data. This deep semantic fragmentation results in superficial analysis results, failing to form a unified knowledge model that reveals the underlying mechanisms of the business.

[0004] Even when existing technologies generate risk heatmaps, marketing strategy lists, and business process diagrams using different tools, these results often exist in the form of fragmented reports or independent dashboards. Decision-makers need to manually switch and cross-reference across multiple screens or systems to piece together a vague overall understanding. This fragmented and non-real-time information delivery method severely hinders the immediate and intuitive grasp of the overall business operation, resulting in slow responses to emergencies or the capture of fleeting business opportunities. Summary of the Invention

[0005] This invention provides a background data processing method, apparatus, computer equipment, and medium to solve the problems of isolated data, semantic fragmentation, and fragmented processing results in various background data processing methods currently available on the market.

[0006] Firstly, a backend data processing method is provided, including: Obtain the basic equipment information of the preset target device; The basic information of the equipment is processed to standardize the format, resulting in standardized information; Based on the pre-acquired API interface data, the standardized information is uploaded to a preset backend server, and the standardized information is semantically deconstructed using a preset semantic network in the backend server to obtain the generated deconstruction result. The deconstruction result is then reorganized to obtain a structured semantic knowledge graph. Obtain the background business data corresponding to the preset target device when it performs business, and draw and construct a business indicator heat map of the target device based on the semantic knowledge graph and the background business data. Based on the semantic knowledge graph and pre-acquired customer data, a real-time business recommendation strategy for the preset target device is generated. Business logic modeling is performed based on the semantic knowledge graph, and the backend business data is associated with the modeling results to obtain a visualized business process graph. By integrating the business indicator heatmap, the real-time business recommendation strategy, and the visualized business process graph, a business navigation interface that can be used for business display is obtained.

[0007] Secondly, a background data processing device is provided, comprising: The data acquisition module is used to acquire basic equipment information of the preset target equipment; The data processing module is used to perform format standardization processing on the basic information of the device to obtain standardized information; The graph construction module is used to upload the standardized information to a preset backend server based on the pre-acquired API interface data, and use the preset semantic network in the backend server to perform semantic deconstruction on the standardized information to obtain the generated deconstruction result. The deconstruction result is then recombined to obtain a structured semantic knowledge graph. The graph processing module is used to draw and construct a business indicator heatmap of the target device based on the semantic knowledge graph and the back-end business data, generate a real-time business recommendation strategy for the preset target device based on the semantic knowledge graph and pre-acquired customer data, perform business logic modeling based on the semantic knowledge graph, and associate the back-end business data in the modeling results to obtain a visual business process graph. The integrated output module is used to integrate the business indicator heatmap, the real-time business recommendation strategy, and the visualized business process diagram to obtain a business navigation interface that can be used for business display.

[0008] Thirdly, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the aforementioned background data processing method.

[0009] Fourthly, a computer-readable storage medium is provided, which stores a computer program that, when executed by a processor, implements the steps of the aforementioned background data processing method.

[0010] The aforementioned scheme, implemented by the background data processing method, apparatus, computer equipment, and storage medium, can obtain basic equipment information of a preset target device, standardize the format of this basic equipment information to obtain standardized information, providing a comprehensive and original input data foundation for the entire analysis process, ensuring the objectivity and completeness of subsequent analysis. Based on pre-acquired API interface data, the standardized information is uploaded to a preset background server, achieving secure, reliable, and automated data collection, ensuring the real-time performance and stability of the analysis process. Furthermore, the standardized information is semantically deconstructed using a preset semantic network in the background server, generating deconstruction results. These deconstruction results are then recombined to obtain a structured semantic knowledge graph, deeply revealing the inherent logic between data and providing a core cognitive framework for intelligent analysis. The system acquires the backend business data corresponding to the preset target device when performing business. Based on the semantic knowledge graph and the backend business data, it constructs a business indicator heatmap of the target device. Based on the semantic knowledge graph and pre-acquired customer data, it generates a real-time business recommendation strategy for the preset target device. Based on the semantic knowledge graph, it models the business logic and associates the backend business data in the modeling results to obtain a visualized business process graph. This abstracts and presents the end-to-end business logic and data flow, making complex business processes transparent, traceable, and easy to analyze and optimize. By integrating the business indicator heatmap, the real-time business recommendation strategy, and the visualized business process graph, a business navigation interface that can be used for business display is obtained, improving the data integration capability during backend data processing and the semantic parsing capability for complex business data. Attached Figure Description

[0011] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 This is a schematic diagram of an application environment for a background data processing method according to an embodiment of the present invention; Figure 2 This is a flowchart illustrating a background data processing method according to an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of a background data processing device in one embodiment of the present invention; Figure 4 This is a schematic diagram of the structure of a computer device according to an embodiment of the present invention; Figure 5 This is another structural schematic diagram of a computer device according to one embodiment of the present invention. Detailed Implementation

[0013] 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.

[0014] The background data processing method provided in this embodiment of the invention can be applied to, for example... Figure 1 In this application environment, the client communicates with the server via a network. The server can collect and standardize basic information (including identity and real-time status) of the target device through the client, forming a unified format data packet and uploading it to the backend server. Using a pre-set semantic network on the server, the data is deeply deconstructed and reorganized to construct a structured semantic knowledge graph integrating multi-dimensional relationships such as device, location, and status. Using this graph as a unified processing hub, the solution generates three key results in parallel: first, a business indicator heatmap drawn with business data, enabling spatialized and visual early warning of risks; second, a real-time business recommendation strategy generated by integrating customer data, achieving precise customer outreach and action guidance; and third, a visualized business process graph derived from business data, clearly presenting business processes and relationships. The final result is a business navigation interface that can be used for business display, improving the data integration capabilities during backend data processing and the semantic parsing capabilities for complex business data. The client can be, but is not limited to, various personal computers, laptops, smartphones, tablets, and portable wearable devices. The server can be implemented using a standalone server or a server cluster consisting of multiple servers. The invention will be described in detail below through specific embodiments.

[0015] Please see Figure 2 As shown, Figure 2 A flowchart illustrating a background data processing method provided in an embodiment of the present invention includes the following steps: S1. Obtain the basic equipment information of the preset target device.

[0016] In this embodiment of the invention, the acquisition of the basic device information of the preset target device is achieved by calling the preset standard API interface to collect two types of core data: the first type is device identification data, such as the device serial number (SN), International Mobile Equipment Identity (IMEI / CMEI) and other unique hardware codes; the second type is the device's real-time status and environment data, including network connection status (Wi-Fi / mobile network), coarse or precise location information, storage status and other dynamic context information.

[0017] S2. Standardize the format of the basic information of the equipment to obtain standardized information.

[0018] In this embodiment of the invention, the process of standardizing the format of the basic device information to obtain standardized information includes: The identification data, status data, and environmental data contained in the basic equipment information are extracted in a structured manner to obtain a structured equipment information dictionary; Each field in the structured equipment information dictionary is converted into a predefined data type to obtain a standardized equipment information dictionary; The standardized equipment information dictionary is processed by field completion and association expansion to obtain equipment information objects; The device information object is encapsulated and serialized to obtain standardized information.

[0019] In detail, the structured extraction of identity data, status data, and environmental data contained in the device's basic information to obtain a structured device information dictionary involves using predefined parsing rules (such as regular expressions, delimiter splitting, or keyword matching) to accurately extract key fields from the raw data and filter out noise or invalid entries. These fields are then organized into a preliminary dictionary structure in key-value pair format; for example, mapping "SN" to a device serial number string and "location" to coordinate text.

[0020] In detail, the process of converting each field in the structured device information dictionary into a predefined data type to obtain a standardized device information dictionary is based on pre-configured type rules for standardization conversion. For example, string-formatted numbers (such as signal strength "-65") are converted into integer values; timestamp text (such as "2023-06-06 12:00:00") is uniformly formatted into ISO 8601 standard date and time objects; and network status descriptions (such as "WIFI") are mapped to enumeration codes "NT01".

[0021] In detail, the process of performing field completion and association expansion on the standardized equipment information dictionary to obtain equipment information objects enhances information completeness through logical deduction or external data association. For example, the geographical information database is queried based on the latitude and longitude field in the dictionary to automatically complete the country, city, and other hierarchical codes; the internal asset database is matched based on the equipment model field to add derived attributes such as equipment category and supplier.

[0022] In detail, the process of encapsulating and serializing the device information object to obtain standardized information involves verifying the compliance of the object structure according to a predefined data schema (such as JSON Schema) and anonymizing sensitive fields (such as partially masking the IMEI code). Subsequently, a serialization tool (such as Jackson or Gson) is used to convert the object into a lightweight text format (such as JSON or XML) to ensure that the format conforms to industry or enterprise exchange standards.

[0023] S3. Based on the pre-acquired API interface data, the standardized information is uploaded to a preset backend server, and the standardized information is semantically deconstructed using a preset semantic network in the backend server to obtain the generated deconstruction result. The deconstruction result is then recombined to obtain a structured semantic knowledge graph.

[0024] In this embodiment of the invention, the step of using a preset semantic network in the backend server to perform semantic deconstruction on the standardized information to obtain the generated deconstruction result includes: Entity recognition is performed on the standardized information to obtain an entity set; The entity set is matched with the ontology concept nodes in the semantic network to obtain an entity concept mapping set; Based on the entity concept mapping set, relational reasoning and semantic binding are performed to obtain a semantic relation graph; Construct a semantic attribute subgraph of the semantic relationship graph, and extract the structural pattern of the semantic attribute subgraph; Based on the preset business importance, key semantic paths are extracted from the semantic attribute subgraph, and the structural pattern and the key semantic paths are encapsulated into structured data objects to obtain the deconstruction result.

[0025] In detail, the entity recognition process for the standardized information to obtain an entity set involves extracting entities with independent meaning from key-value pairs according to predefined entity recognition rules (usually based on field name keywords, data types, or numerical ranges). For example, from {"SN": "XYZ123", "city_code": "110100", "network_type": "WIFI"}, "XYZ123" is identified as a device entity, "110100" as a geographic location entity, and "WIFI" as a network status entity.

[0026] In detail, the entity set is matched with ontology concept nodes in the semantic network to obtain an entity concept mapping set. Each entity is associated with the most appropriate ontology concept node by looking up a mapping table, string matching, or a type-based classifier. For example, the entity "XYZ123" is mapped to the concept Device, and "110100" is mapped to a specific instance of the concept Location (such as "Beijing").

[0027] In detail, the step of performing relational reasoning and semantic binding based on the entity concept mapping set to obtain a semantic relationship graph involves automatically deriving and instantiating the relationships between entities based on predefined object attributes (such as isLocatedIn and hasConnectionType) and logical rules in the ontology. For example, the rule "If a device instance is located at a location instance, then there is an isLocatedIn relationship between them" is triggered, thereby creating a directed relationship edge between device XYZ123 and location Beijing.

[0028] In detail, the construction of the semantic attribute subgraph of the semantic relationship graph and the extraction of the structural patterns of the semantic attribute subgraph involve performing a graph traversal of limited depth starting from the core entity of the semantic relationship graph, collecting relevant nodes and edges to form a more concise and focused graph structure. The topological features of this graph structure (such as node degree distribution and frequent subgraph patterns) are then processed to extract its implicit and reusable structural patterns. For example, it might be possible to identify "device -> located in -> city -> belongs to -> region" as a typical hierarchical affiliation pattern.

[0029] In detail, the step of extracting key semantic paths from the semantic attribute subgraph based on preset business importance, and encapsulating the structural pattern and the key semantic paths into a structured data object to obtain the deconstruction result, involves selecting the most valuable key semantic paths from the semantic attribute subgraph based on preset business importance weights (such as risk transmission paths and customer behavior chains). For example, for risk control, the path "device -> using a weak network -> in a sensitive area" might be extracted. In implementation, the selection can be accomplished by evaluating the importance scores of nodes and edges in the path using algorithms. Finally, the abstract structural pattern and the specific key semantic paths are integrated and encapsulated into a structured, lightweight data object.

[0030] In this embodiment of the invention, the reorganization of the deconstruction result to obtain a structured semantic knowledge graph includes: The graph patterns in the deconstruction results are analyzed, and corresponding node types and relation types are created in a preset graph database according to the graph patterns to obtain the knowledge graph ontology skeleton. Based on the key semantic paths in the deconstruction results, entity and relation instances are injected into the knowledge graph ontology skeleton to obtain a primary knowledge graph. Based on the deconstruction results, the primary knowledge graph is subjected to context association and knowledge fusion to obtain an enhanced knowledge graph; The enhanced knowledge graph is subjected to spatiotemporal dimension anchoring processing to obtain a temporal-spatial knowledge graph; The temporal-spatial knowledge graph is indexed, constructed, and its interface is encapsulated to obtain the structured semantic knowledge graph.

[0031] In detail, the process of parsing the graph patterns in the deconstruction results and creating corresponding node types and relationship types in a preset graph database based on these patterns to obtain the knowledge graph ontology skeleton is achieved by parsing the graph patterns abstracted from the deconstruction results (e.g., the typical association pattern "device-location-network"). Then, in a preset graph database (such as Neo4j, JanusGraph, or a memory graph database), the database's schema definition language or API is used to create corresponding node types (Labels) and relationship types (Relationship Types). For example, node types such as Device, Location, and Network are created, as well as relationship types such as LOCATED_IN and HAS_CONNECTION. Necessary attribute constraints are defined for each type (e.g., Device nodes must have a device_id attribute).

[0032] In detail, the step of injecting entity and relation instances into the knowledge graph ontology skeleton based on the key semantic paths in the deconstruction results to obtain a primary knowledge graph involves traversing each key semantic path. For each entity in the path, the system checks whether a corresponding instance node already exists in the graph. If not, a new node is created according to the type defined in the skeleton, and specific attribute values ​​extracted from the original data are set (e.g., setting sn="XYZ123" for the Device node). Subsequently, relation edges are created between the corresponding nodes according to the semantic relationships specified in the path (e.g., creating a LOCATED_IN relation between the XYZ123 node and the Beijing node).

[0033] In detail, the enhanced knowledge graph is obtained by performing context association and knowledge fusion on the primary knowledge graph based on the deconstruction results. This involves using entities in the primary knowledge graph as anchor points to query related external business systems (such as CRM, ERP, and asset databases) to obtain supplementary information. For example, based on the customer ID associated with the device node, customer industry, size, and other information are extracted from the CRM to create a Customer node. Simultaneously, knowledge fusion is performed, such as merging nodes representing the same entity from different data sources and resolving conflicts.

[0034] In detail, the spatiotemporal anchoring processing of the enhanced knowledge graph to obtain a temporal-spatial knowledge graph involves adding timestamp attributes to the core facts (such as relation edges and key attributes) in the enhanced knowledge graph to record their effective time range, enabling historical queries and time-series processing. For nodes with spatial attributes, their text descriptions are converted into standard geographic coordinates or geocoding, and a spatial index is established. Simultaneously, the system may create version snapshots of the graph, supporting backtracking of the graph's state by time point.

[0035] S4. Obtain the background business data corresponding to the preset target device when performing business, and draw and construct the business indicator heat map of the target device based on the semantic knowledge graph and the background business data.

[0036] In this embodiment of the invention, the step of drawing and constructing a heatmap of business metrics for the target device based on the semantic knowledge graph and the backend business data includes: Based on the semantic knowledge graph and the business data, risk dimensions are defined and assessment units are divided to obtain a risk assessment framework that clearly defines risk dimensions, assessment units, and quantitative indicators. Risk values ​​are calculated based on the risk assessment framework, the semantic knowledge graph, and the business data to obtain a unit-risk score matrix. The unit-risk score matrix is ​​spatialized and hierarchically aggregated to obtain a multi-level risk raster dataset; The multi-level risk raster dataset is subjected to risk normalization processing to obtain a normalized risk dataset; Heatmaps of business metrics are obtained by performing heat rendering based on the normalized risk dataset.

[0037] In detail, the risk assessment framework, which defines risk dimensions and divides assessment units based on the semantic knowledge graph and business data, yields a clearly defined risk assessment framework with defined risk dimensions, assessment units, and quantitative indicators. This is achieved by processing the risk association patterns contained in the semantic knowledge graph (such as potential operational pressure in densely populated equipment areas) and the risk manifestations in the business data (such as historical high-incidence periods and types of failures), jointly determining core dimensions such as "equipment stability risk," "network security risk," and "business compliance risk." Using spatial or logical entities in the semantic knowledge graph (such as geographical location nodes and project group nodes) as a benchmark, the scope to be assessed is divided into multiple assessment units. Finally, quantifiable indicators (such as "monthly failure rate" and "vulnerability exposure surface score") are designed for each risk dimension, and their data sources are clearly defined (corresponding to graph attributes or business data fields), thus obtaining the risk assessment framework.

[0038] In detail, the step of calculating risk values ​​based on the risk assessment framework, the semantic knowledge graph, and the business data to obtain a unit-risk score matrix involves extracting subgraphs related to the current unit from the semantic knowledge graph and calculating their graph structure features (such as node degree and relation density) as risk factors. Simultaneously, historical indicator data corresponding to the unit is queried from the business database. Subsequently, the graph features and business indicators are fused according to the formula defined in the framework (such as weighted summation or inference through a machine learning model) to calculate the original scores of the unit on each risk dimension.

[0039] In detail, the process of spatializing and hierarchically aggregating the unit-risk score matrix to obtain a multi-level risk raster dataset involves assigning coordinates to each assessment unit: for geographical units, latitude and longitude are directly obtained from the Location node of the knowledge graph; for logical units, virtual coordinates are defined on the management plane. Next, a spatial interpolation algorithm (such as Kriging interpolation) is used to interpolate the discrete point risk values ​​into a continuous risk surface. Simultaneously, according to the management hierarchy (such as "site → city → region"), the risk values ​​of the bottom-level units are aggregated upwards according to rules (such as taking the maximum value or weighted average).

[0040] In detail, the risk normalization process of the multi-level risk raster dataset to obtain a normalized risk dataset involves normalizing the values ​​of each level and each risk dimension in the multi-level risk raster dataset. Typically, the min-max scaling method is used to linearly transform the original scores to a uniform range (such as [0,1] or [0,100]).

[0041] In detail, the process involves performing heat rendering based on the normalized risk dataset to obtain a business indicator heatmap. Each grid cell's risk value is converted into a corresponding color value (RGBA) according to a preset color mapping table (e.g., a gradient from low-risk green to high-risk red). Subsequently, a visualization library (such as ECharts GL on the web or GeoServer on the server) is used to render the grid with color and coordinate information into an image, which is then overlaid on a base map (such as a geographic map or logical layout diagram) to form the business indicator heatmap.

[0042] S5. Generate a real-time business recommendation strategy for the preset target device based on the semantic knowledge graph and the pre-acquired customer data.

[0043] In this embodiment of the invention, generating a real-time service recommendation strategy for the preset target device based on the semantic knowledge graph and pre-acquired customer data includes: The customer data is fused with the discrete behavioral relationships in the semantic knowledge graph to obtain a customer profile; Based on the customer profile, the customer group type is identified; Retrieve the product characteristics of each candidate product in the preset product list; Calculate the fit score between the customer and each candidate product based on the product characteristics, the customer profile, and the customer group type; Based on the fit score, the customer group type, and the customer profile, the system matches the customer with the corresponding product push type, product push channel, and product push timing from the preset product knowledge base to obtain a preliminary marketing strategy. The initial marketing strategy is formatted and encapsulated to obtain the real-time business recommendation strategy.

[0044] In detail, the process of fusing the user data with discrete behavioral relationships in the semantic knowledge graph to obtain a user profile involves using user entities in the semantic knowledge graph as core nodes and associating them with the customer data through their unique identifiers (such as customer IDs). Then, all relationships and adjacent nodes of the customer in the graph are traversed and extracted, such as dynamic behavioral patterns like the model of the device used, frequently visited locations, and associated social circles. This is achieved by fusing static attributes (such as age and occupation) with these dynamic and interconnected graph contexts.

[0045] In detail, identifying customer group types based on the customer profile involves converting the customer profile into feature vectors, and then applying clustering algorithms (such as K-means, DBSCAN, or community detection algorithms based on graph structures) to automatically group customers based on the feature vectors. The grouping is based not only on traditional attributes (such as spending amount), but also on relationship patterns extracted from the graph (such as "device-intensive" users, "service-dependent" users).

[0046] In detail, the process of obtaining the product characteristics of each candidate product in the preset product list includes obtaining the functional attributes (such as "supports 4K resolution"), applicable scenarios (such as "suitable for mobile office"), target customer groups (such as "for small and medium-sized enterprises"), and business policies (such as "subscription system") of each product.

[0047] In detail, the calculation of the fit score between the customer and each candidate product based on the product characteristics, the customer profile, and the customer group type is achieved by establishing a fit calculation model. This model takes the customer profile, customer group type, and product characteristics of the candidate products as input. Through predefined matching rules (such as a weighted scoring card based on business rules), it calculates the customer's demand matching degree, scenario fit, and potential conversion probability for the product.

[0048] In detail, the process involves matching the customer with the corresponding product push type, product push channel, and product push timing from a preset product knowledge base based on the fit score, the customer group type, and the customer profile, thereby obtaining a preliminary marketing strategy.

[0049] In detail, the step of matching the customer with the corresponding product push type, product push channel, and product push timing in the preset product knowledge base based on the fit score, the customer group type, and the customer profile to obtain a preliminary marketing strategy is based on the matching according to the predefined marketing rules in the product knowledge base.

[0050] S6. Perform business logic modeling based on the semantic knowledge graph, and associate the backend business data in the modeling results to obtain a visualized business process graph.

[0051] In this embodiment of the invention, the step of performing business logic modeling based on the semantic knowledge graph and associating the backend business data with the modeling results to obtain a visualized business process graph includes: Identify the entity types related to business processes in the semantic knowledge graph to obtain the business process ontology; Based on the business data, the core entity nodes related to the business process ontology are located in the semantic knowledge graph to obtain the core entities and relationship set of the business process. Based on the core entities and relationship set of the business process, the process path is searched in the semantic knowledge graph; The process path is time-series labeled to obtain a process path diagram; The process path diagram is converted into a standardized business process format to obtain a visualized business process map.

[0052] In detail, the step of identifying the entity types related to the business process in the semantic knowledge graph to obtain the business process ontology is to process the metadata of the semantic knowledge graph to identify the entity types (such as "order", "approval", "task", "product") and relationship types (such as "trigger", "next stage", "belong to") that represent business activities and logic.

[0053] In detail, the step of locating the core entity nodes related to the business process ontology in the semantic knowledge graph based on the business data, and obtaining the core entity and relationship set of the business process, is guided by the business process ontology, using structured business data (such as order ID, approval number) as query keys to accurately match the corresponding entity nodes in the semantic knowledge graph.

[0054] In detail, the process of finding the process path in the semantic knowledge graph based on the core entities and relationship set of the business process is achieved by starting with the typical starting entity of the business process (such as "order created") and performing a graph traversal algorithm (such as depth-first search) along a specific direction in the graph (such as following "next step" or "trigger" type relationships). The algorithm explores all possible forward paths until it reaches the entity type defined as the end point of the process (such as "completed order" or "closed work order").

[0055] In detail, the process path is time-series labeled to obtain a process path graph by extracting timestamps (such as activity start time, end time, and flow trigger time) associated with each path node (business activity) and edge (transition) from business data. Then, this time information is used as attributes and accurately labeled onto the corresponding path nodes and edges.

[0056] In detail, the process of converting the process path diagram into a standardized business process format to obtain a visualized business process map is based on a set of mapping rules, which convert the entities, relationships, and temporal attributes in the process path diagram into elements of a standard business process modeling language. For example, the "approval" activity is mapped to a "user task" in BPMN, conditional branches are mapped to "exclusive gateways," and time stamps are converted into attributes or annotations of elements.

[0057] S7. Integrate the business indicator heatmap, the real-time business recommendation strategy, and the visualized business process diagram to obtain a business navigation interface that can be used for business display.

[0058] In this embodiment of the invention, the integration of the business indicator heatmap, the real-time business recommendation strategy, and the visualized business process graph to obtain a business navigation interface for business display involves establishing the visualized business process graph as the core spatiotemporal coordinates and navigation main line of the business navigation interface, and constructing a macro-business context using its nodes and flow directions. Based on this, the business indicator heatmap is overlaid and mapped to the corresponding functional modules of the visualized business process graph, visually revealing the real-time status and risk pressure of each link through different colors and densities. Simultaneously, the real-time business recommendation strategy is intelligently associated with and anchored to the highlighted area of ​​the business indicator heatmap based on its strategy subject (such as the targeted device, the affected process link, and the associated customer group), presented in the form of interactive prompts, action lists, or parameter panels, forming a closed loop of "perception-analysis-suggestion". Finally, through preset interactive events (such as click, hover, zoom in, zoom out) and view linkage logic, the system generates a unified operating platform integrating panoramic business monitoring, precise risk positioning, intelligent strategy recommendation, and process simulation, namely the business navigation interface.

[0059] As can be seen, in the above solution, basic information of the target device (including identification and real-time status) is collected and standardized to form a unified format data packet, which is then uploaded to the backend server. The data is then deeply deconstructed and reorganized using a pre-set semantic network on the server, constructing a structured semantic knowledge graph that integrates multi-dimensional relationships such as device, location, and status. Using this graph as a unified processing hub, the solution generates three key results in parallel: first, a business indicator heatmap drawn with business data, enabling spatialized and visual early warning of risks; second, a real-time business recommendation strategy generated by integrating customer data, achieving precise customer outreach and action guidance; and third, a visualized business process graph derived from business data, clearly presenting business processes and relationships, ultimately resulting in a business navigation interface that can be used for business display.

[0060] It should be understood that the sequence number of each step in the above embodiments 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.

[0061] In one embodiment, a background data processing device is provided, which corresponds one-to-one with the background data processing methods described in the above embodiments. For example... Figure 3 As shown, the background data processing device includes a data acquisition module 101, a data upload module 102, a map construction module 103, a map processing module 104, and an integration output module 105. Detailed descriptions of each functional module are as follows: Data acquisition module 101 is used to acquire basic equipment information of a preset target device; Data processing module 102 is used to perform format standardization processing on the basic information of the device to obtain standardized information; The graph construction module 103 is used to upload the standardized information to a preset backend server based on the pre-acquired API interface data, and use the preset semantic network in the backend server to perform semantic deconstruction on the standardized information to obtain the generated deconstruction result. The deconstruction result is then recombined to obtain a structured semantic knowledge graph. The graph processing module 104 is used to draw and construct a business indicator heatmap of the target device based on the semantic knowledge graph and the back-end business data, generate a real-time business recommendation strategy for the preset target device based on the semantic knowledge graph and pre-acquired customer data, perform business logic modeling based on the semantic knowledge graph, and associate the back-end business data in the modeling results to obtain a visual business process graph. The integrated output module 105 is used to integrate the business indicator heatmap, the real-time business recommendation strategy, and the visualized business process diagram to obtain a business navigation interface that can be used for business display.

[0062] In one embodiment, when performing the format standardization processing on the device basic information to obtain standardized information, the data processing module 102 is specifically used for: The identification data, status data, and environmental data contained in the basic equipment information are extracted in a structured manner to obtain a structured equipment information dictionary; Each field in the structured equipment information dictionary is converted into a predefined data type to obtain a standardized equipment information dictionary; The standardized equipment information dictionary is processed by field completion and association expansion to obtain equipment information objects; The device information object is encapsulated and serialized to obtain standardized information.

[0063] In one embodiment, the graph construction module 103, when executing the process of semantically deconstructing the standardized information using a preset semantic network in the backend server to obtain the generated deconstruction result, is specifically used for: Entity recognition is performed on the standardized information to obtain an entity set; The entity set is matched with the ontology concept nodes in the semantic network to obtain an entity concept mapping set; Based on the entity concept mapping set, relational reasoning and semantic binding are performed to obtain a semantic relation graph; Construct a semantic attribute subgraph of the semantic relationship graph, and extract the structural pattern of the semantic attribute subgraph; Based on the preset business importance, key semantic paths are extracted from the semantic attribute subgraph, and the structural pattern and the key semantic paths are encapsulated into structured data objects to obtain the deconstruction result.

[0064] In one embodiment, the graph construction module 103, when performing the reorganization of the deconstruction result to obtain a structured semantic knowledge graph, is specifically used for: The graph patterns in the deconstruction results are analyzed, and corresponding node types and relation types are created in a preset graph database according to the graph patterns to obtain the knowledge graph ontology skeleton. Based on the key semantic paths in the deconstruction results, entity and relation instances are injected into the knowledge graph ontology skeleton to obtain a primary knowledge graph. Based on the deconstruction results, the primary knowledge graph is subjected to context association and knowledge fusion to obtain an enhanced knowledge graph; The enhanced knowledge graph is subjected to spatiotemporal dimension anchoring processing to obtain a temporal-spatial knowledge graph; The temporal-spatial knowledge graph is indexed, constructed, and its interface is encapsulated to obtain the structured semantic knowledge graph.

[0065] In one embodiment, the graph processing module 104, when executing the step of drawing and constructing a heatmap of business indicators for the target device based on the semantic knowledge graph and the background business data, is specifically used for: Based on the semantic knowledge graph and the business data, risk dimensions are defined and assessment units are divided to obtain a risk assessment framework that clearly defines risk dimensions, assessment units, and quantitative indicators. Risk values ​​are calculated based on the risk assessment framework, the semantic knowledge graph, and the business data to obtain a unit-risk score matrix. The unit-risk score matrix is ​​spatialized and hierarchically aggregated to obtain a multi-level risk raster dataset; The multi-level risk raster dataset is subjected to risk normalization processing to obtain a normalized risk dataset; Heatmaps of business metrics are obtained by performing heat rendering based on the normalized risk dataset.

[0066] In one embodiment, the graph processing module 104, when executing the real-time business recommendation strategy for the preset target device based on the semantic knowledge graph and pre-acquired customer data, is specifically used for: The customer data is fused with the discrete behavioral relationships in the semantic knowledge graph to obtain a customer profile; Based on the customer profile, the customer group type is identified; Retrieve the product characteristics of each candidate product in the preset product list; Calculate the fit score between the customer and each candidate product based on the product characteristics, the customer profile, and the customer group type; Based on the fit score, the customer group type, and the customer profile, the system matches the customer with the corresponding product push type, product push channel, and product push timing from the preset product knowledge base to obtain a preliminary marketing strategy. The initial marketing strategy is formatted and encapsulated to obtain the real-time business recommendation strategy.

[0067] In one embodiment, the graph processing module 104, when performing business logic modeling based on the semantic knowledge graph and associating the backend business data with the modeling result to obtain a visualized business process graph, is specifically used for: Identify the entity types related to business processes in the semantic knowledge graph to obtain the business process ontology; Based on the business data, the core entity nodes related to the business process ontology are located in the semantic knowledge graph to obtain the core entities and relationship set of the business process. Based on the core entities and relationship set of the business process, the process path is searched in the semantic knowledge graph; The process path is time-series labeled to obtain a process path diagram; The process path diagram is converted into a standardized business process format to obtain a visualized business process map.

[0068] This invention provides a backend data processing device that collects and standardizes basic information (including identification and real-time status) of target devices, forming data packets in a unified format and uploading them to a backend server. Utilizing a pre-set semantic network on the server, the data is deeply deconstructed and reorganized to construct a structured semantic knowledge graph integrating multi-dimensional relationships such as device, location, and status. Using this graph as a unified processing hub, the solution generates three key results in parallel: first, a business indicator heatmap drawn with business data, enabling spatialized and visual early warning of risks; second, a real-time business recommendation strategy generated by integrating customer data, achieving precise customer outreach and action guidance; and third, a visualized business process graph derived from business data, clearly presenting business processes and relationships, ultimately resulting in a business navigation interface that can be used for business display.

[0069] Specific limitations regarding the background data processing device can be found in the limitations of the background data processing method described above, and will not be repeated here. Each module in the aforementioned background data processing device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in the computer device in hardware form, or stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0070] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 4 As shown, the computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile and / or volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and database. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The network interface is used to communicate with external clients via a network connection. When the computer program is executed by the processor, it implements the functions or steps of a background data processing method on the server side.

[0071] In one embodiment, a computer device is provided, which may be a client, and its internal structure diagram may be as follows: Figure 5 As shown, the computer device includes a processor, memory, network interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The network interface is used to communicate with an external server via a network connection. When the computer program is executed by the processor, it implements client-side functions or steps of a background data processing method.

[0072] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to perform the following steps: Obtain the basic equipment information of the preset target device; The basic information of the equipment is processed to standardize the format, resulting in standardized information; Based on the pre-acquired API interface data, the standardized information is uploaded to a preset backend server, and the standardized information is semantically deconstructed using a preset semantic network in the backend server to obtain the generated deconstruction result. The deconstruction result is then reorganized to obtain a structured semantic knowledge graph. Obtain the background business data corresponding to the preset target device when it performs business, and draw and construct a business indicator heat map of the target device based on the semantic knowledge graph and the background business data. Based on the semantic knowledge graph and pre-acquired customer data, a real-time business recommendation strategy for the preset target device is generated. Business logic modeling is performed based on the semantic knowledge graph, and the backend business data is associated with the modeling results to obtain a visualized business process graph. By integrating the business indicator heatmap, the real-time business recommendation strategy, and the visualized business process graph, a business navigation interface that can be used for business display is obtained.

[0073] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor: Obtain the basic equipment information of the preset target device; The basic information of the equipment is processed to standardize the format, resulting in standardized information; Based on the pre-acquired API interface data, the standardized information is uploaded to a preset backend server, and the standardized information is semantically deconstructed using a preset semantic network in the backend server to obtain the generated deconstruction result. The deconstruction result is then reorganized to obtain a structured semantic knowledge graph. Obtain the background business data corresponding to the preset target device when it performs business, and draw and construct a business indicator heat map of the target device based on the semantic knowledge graph and the background business data. Based on the semantic knowledge graph and pre-acquired customer data, a real-time business recommendation strategy for the preset target device is generated. Business logic modeling is performed based on the semantic knowledge graph, and the backend business data is associated with the modeling results to obtain a visualized business process graph. By integrating the business indicator heatmap, the real-time business recommendation strategy, and the visualized business process graph, a business navigation interface that can be used for business display is obtained.

[0074] It should be noted that the functions or steps that can be implemented by the computer-readable storage medium or computer device described above can be referred to the relevant descriptions on the server side and client side in the foregoing method embodiments. To avoid repetition, they will not be described one by one here.

[0075] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0076] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0077] Finally, it should be noted that if any software tools or components not belonging to this company appear in the embodiments of the application, they are merely illustrative examples and do not represent actual use. The embodiments described above are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A background data processing method, characterized in that, include: Obtain the basic equipment information of the preset target device; The basic information of the equipment is processed to standardize the format, resulting in standardized information; Based on the pre-acquired API interface data, the standardized information is uploaded to a preset backend server, and the standardized information is semantically deconstructed using a preset semantic network in the backend server to obtain the generated deconstruction result. The deconstruction result is then reorganized to obtain a structured semantic knowledge graph. Obtain the background business data corresponding to the preset target device when it performs business, and draw and construct a business indicator heat map of the target device based on the semantic knowledge graph and the background business data. Based on the semantic knowledge graph and pre-acquired customer data, a real-time business recommendation strategy for the preset target device is generated. Business logic modeling is performed based on the semantic knowledge graph, and the backend business data is associated with the modeling results to obtain a visualized business process graph. By integrating the business indicator heatmap, the real-time business recommendation strategy, and the visualized business process graph, a business navigation interface that can be used for business display is obtained.

2. The background data processing method as described in claim 1, characterized in that, The process of standardizing the format of the basic equipment information to obtain standardized information includes: The identification data, status data, and environmental data contained in the basic equipment information are extracted in a structured manner to obtain a structured equipment information dictionary; Each field in the structured equipment information dictionary is converted into a predefined data type to obtain a standardized equipment information dictionary; The standardized equipment information dictionary is processed by field completion and association expansion to obtain equipment information objects; The device information object is encapsulated and serialized to obtain standardized information.

3. The background data processing method as described in claim 1, characterized in that, The process involves using a pre-set semantic network in the backend server to perform semantic deconstruction on the standardized information, resulting in a generated deconstruction result, including: Entity recognition is performed on the standardized information to obtain an entity set; The entity set is matched with the ontology concept nodes in the semantic network to obtain an entity concept mapping set; Based on the entity concept mapping set, relational reasoning and semantic binding are performed to obtain a semantic relation graph; Construct a semantic attribute subgraph of the semantic relationship graph, and extract the structural pattern of the semantic attribute subgraph; Based on the preset business importance, key semantic paths are extracted from the semantic attribute subgraph, and the structural pattern and the key semantic paths are encapsulated into structured data objects to obtain the deconstruction result.

4. The background data processing method as described in claim 1, characterized in that, The reorganization of the deconstruction results to obtain a structured semantic knowledge graph includes: The graph patterns in the deconstruction results are analyzed, and corresponding node types and relation types are created in a preset graph database according to the graph patterns to obtain the knowledge graph ontology skeleton. Based on the key semantic paths in the deconstruction results, entity and relation instances are injected into the knowledge graph ontology skeleton to obtain a primary knowledge graph. Based on the deconstruction results, the primary knowledge graph is subjected to context association and knowledge fusion to obtain an enhanced knowledge graph; The enhanced knowledge graph is subjected to spatiotemporal dimension anchoring processing to obtain a temporal-spatial knowledge graph; The temporal-spatial knowledge graph is indexed, constructed, and its interface is encapsulated to obtain the structured semantic knowledge graph.

5. The background data processing method as described in claim 1, characterized in that, The step of drawing and constructing a business indicator heatmap for the target device based on the semantic knowledge graph and the backend business data includes: Based on the semantic knowledge graph and the business data, risk dimensions are defined and assessment units are divided to obtain a risk assessment framework that clearly defines risk dimensions, assessment units, and quantitative indicators. Risk values ​​are calculated based on the risk assessment framework, the semantic knowledge graph, and the business data to obtain a unit-risk score matrix. The unit-risk score matrix is ​​spatialized and hierarchically aggregated to obtain a multi-level risk raster dataset; The multi-level risk raster dataset is subjected to risk normalization processing to obtain a normalized risk dataset; Heatmaps of business metrics are obtained by performing heat rendering based on the normalized risk dataset.

6. The background data processing method as described in claim 1, characterized in that, The step of generating a real-time business recommendation strategy for the preset target device based on the semantic knowledge graph and pre-acquired customer data includes: The customer data is fused with the discrete behavioral relationships in the semantic knowledge graph to obtain a customer profile; Based on the customer profile, the customer group type is identified; Retrieve the product characteristics of each candidate product in the preset product list; Calculate the fit score between the customer and each candidate product based on the product characteristics, the customer profile, and the customer group type; Based on the fit score, the customer group type, and the customer profile, the system matches the customer with the corresponding product push type, product push channel, and product push timing from the preset product knowledge base to obtain a preliminary marketing strategy. The initial marketing strategy is formatted and encapsulated to obtain the real-time business recommendation strategy.

7. The background data processing method as described in claim 1, characterized in that, The step of modeling business logic based on the semantic knowledge graph and associating the backend business data with the modeling results to obtain a visualized business process graph includes: Identify the entity types related to business processes in the semantic knowledge graph to obtain the business process ontology; Based on the business data, the core entity nodes related to the business process ontology are located in the semantic knowledge graph to obtain the core entities and relationship set of the business process. Based on the core entities and relationship set of the business process, the process path is searched in the semantic knowledge graph; The process path is time-series labeled to obtain a process path diagram; The process path diagram is converted into a standardized business process format to obtain a visualized business process map.

8. A background data processing device, characterized in that, include: The data acquisition module is used to acquire basic equipment information of the preset target equipment; The data processing module is used to perform format standardization processing on the basic information of the device to obtain standardized information; The graph construction module is used to upload the standardized information to a preset backend server based on the pre-acquired API interface data, and use the preset semantic network in the backend server to perform semantic deconstruction on the standardized information to obtain the generated deconstruction result. The deconstruction result is then recombined to obtain a structured semantic knowledge graph. The graph processing module is used to draw and construct a business indicator heatmap of the target device based on the semantic knowledge graph and the back-end business data, generate a real-time business recommendation strategy for the preset target device based on the semantic knowledge graph and pre-acquired customer data, perform business logic modeling based on the semantic knowledge graph, and associate the back-end business data in the modeling results to obtain a visual business process graph. The integrated output module is used to integrate the business indicator heatmap, the real-time business recommendation strategy, and the visualized business process diagram to obtain a business navigation interface that can be used for business display.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the background data processing method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the background data processing method as described in any one of claims 1 to 7.

Images