Intelligent scheduling linkage method, system and equipment for mine multi-source data and storage medium

Abstract

The invention discloses an intelligent scheduling linkage method, system and equipment for mine multi-source data and a storage medium, and relates to the technical field of mine intelligent scheduling, which comprises the steps of: performing unified perception, standard acquisition and quality labeling on mine field multi-source data, constructing a basic data unit, and executing exchange cleaning and credible fusion calculation to obtain a data unit; outputting a fusion observation input; mapping the fusion observation input with a mine space coordinate system and object semantics, constructing a spatialized object state description, and based on the object state description, performing quantitative evaluation and hierarchical judgment on an event according to a pre-configured rule constraint, and generating a scheduling linkage instruction meeting a trigger condition; the scheduling linkage instruction is executed in order, and the execution process and the execution result are subjected to continuous tracking and state backflow recording. Through multi-source data credible fusion, spatialization object state modeling and regularization linkage execution, the reliability and the intelligent level of mine dispatching linkage are improved.

Description

Technical Field

[0001] This invention relates to the field of intelligent mine scheduling technology, specifically to intelligent scheduling and linkage methods, systems, equipment, and storage media for multi-source mine data. Background Technology

[0002] With the increasing demands for coal mine safety and the growing scale and complexity of mine production, mine dispatching and management are gradually evolving from a traditional, experience-driven model to a data-driven, intelligent decision-making model. In recent years, information technology tools such as safety monitoring systems, production automation systems, personnel positioning systems, and video surveillance systems have been widely deployed in mines, forming a multi-source data system covering environmental perception, equipment operation, and personnel activities. Simultaneously, integrated mine management and control platforms based on industrial internet, internet of things, and information integration technologies are gradually developing, achieving a holistic understanding of the mine's operational status through centralized collection and display of data from multiple systems. Building upon this foundation, some dispatching systems are beginning to incorporate rule engines, spatial information systems, and automated control methods to assist in dispatching decisions and emergency response, thus driving mine dispatching and management towards informatization, integration, and intelligence.

[0003] Existing mine scheduling and linkage control technologies still have significant limitations, making it difficult to support the high-reliability intelligent scheduling requirements in complex mine scenarios. First, existing technologies often focus on the simple collection and display of multi-source data, lacking systematic modeling of data quality, acquisition link status, and consistency of heterogeneous multi-source data. This results in differences in time, accuracy, and reliability among data from different sources, making it difficult to form a unified data foundation that can be directly used for scheduling decisions. Second, existing scheduling methods often treat data analysis and spatial information separately, failing to deeply integrate the fused data with the mine's spatial coordinate system and object semantics. This makes it difficult to accurately characterize the scope of event impact, object relationships, and spatial risks, thus limiting the precision of scheduling decisions. Furthermore, existing linkage control technologies mostly use static thresholds or fixed logic for triggering, lacking a quantitative judgment mechanism based on comprehensive evaluation of object states, making it difficult to achieve graded responses and differentiated scheduling for different events. Simultaneously, after the execution of scheduling instructions, existing technologies typically lack systematic feedback and analysis of the execution process and results. Scheduling rules and action configurations are difficult to continuously adjust based on historical execution data, making it difficult to form a data-driven closed-loop optimization of scheduling strategies.

[0004] Therefore, existing technologies are insufficient to achieve reliable fusion of multi-source data in mines, spatial state modeling, rule-based intelligent judgment, and adaptive adjustment of scheduling and linkage strategies, and cannot meet the actual needs of safe, efficient, and intelligent scheduling and linkage in complex mine environments. Summary of the Invention

[0005] In view of the above-mentioned problems, the present invention is proposed.

[0006] Therefore, the technical problem solved by this invention is that existing mine scheduling linkage and monitoring management methods lack reliable fusion and unified expression of multi-source data, fail to combine spatial object status for refined analysis of scheduling decisions, and make it difficult to continuously adjust scheduling rules and linkage strategies based on execution results. The invention also addresses the problem of how to achieve intelligent scheduling linkage and closed-loop optimization based on multi-source mine data.

[0007] To address the aforementioned technical problems, this invention provides the following technical solution: an intelligent scheduling and linkage method for multi-source data in mines, comprising: uniformly sensing, standardizing collection, and quality labeling multi-source data from the mine site to construct basic data units; performing exchange cleaning and reliable fusion calculations to output fused observation inputs; mapping the fused observation inputs to the mine spatial coordinate system and object semantics to construct a spatialized object state description containing object location, regional relationships, and associated indexes; based on the object state description, quantitatively evaluating and classifying events according to pre-configured rule constraints to generate scheduling and linkage instructions that meet the triggering conditions; executing the scheduling and linkage instructions in an orderly manner, continuously tracking the execution process and results, and recording state feedback to form a scheduling execution data link; and adjusting the linkage rule parameters and action configurations based on the scheduling execution data link.

[0008] As a preferred embodiment of the intelligent scheduling and linkage method for multi-source data in mines as described in this invention, the construction of basic data units by uniformly sensing, standardizing collection, and quality labeling of multi-source data in the mine includes: collecting multi-source data in the mine, including continuously collecting safety monitoring data, production operation data, and personnel and equipment status data distributed both above and below ground in the mine, and registering the physical identifier, object identifier, collection time, and communication status of each data source during the collection process; performing protocol parsing and field mapping processing on the collected multi-source data in the mine to form a record with a consistent structure from different sources, performing verification, and generating basic data units.

[0009] As a preferred embodiment of the intelligent scheduling and linkage method for multi-source data in mines as described in this invention, the step of performing exchange cleaning and reliable fusion calculation to output fused observation input includes: performing data exchange and cleaning processing on basic data units according to object identifiers and timestamps, merging duplicate records, identifying missing fields, and isolating and labeling outliers; after completing the exchange cleaning, based on the labeled data quality information and acquisition link status information, performing fusion processing on observation records of the same object from different data sources at the same timestamp to generate fused observation input.

[0010] As a preferred embodiment of the intelligent scheduling and linkage method for multi-source data in mines as described in this invention, the step of mapping the fused observation input with the mine spatial coordinate system and object semantics includes: establishing a unified spatial coordinate system based on mine engineering drawings and roadway structure data, and binding safety monitoring points, equipment installation locations, and personnel positioning information with the spatial coordinate system; associating the fused observation input with the corresponding object identifier and spatial coordinates to form an object status record containing object location, region, and spatial index information.

[0011] As a preferred embodiment of the intelligent scheduling and linkage method for multi-source data in mines as described in this invention, the step of quantitatively evaluating and classifying events based on object state descriptions and according to pre-configured rule constraints to generate scheduling and linkage instructions that meet triggering conditions includes: identifying event types based on changes in fused observation values ​​in object state records, and reading threshold parameters, spatial parameters, and permission parameters corresponding to the event type from the rule constraints; evaluating the risk level and impact range of events based on the numerical information and spatial correlation information contained in the object state records, and determining the event level according to the evaluation results, so that the event determination process has an input field and rule mapping relationship.

[0012] As a preferred embodiment of the intelligent scheduling and linkage method for multi-source data in mines as described in this invention, the step of orderly executing scheduling and linkage instructions and continuously tracking and recording the execution process and results to form a scheduling execution data link includes: when an event determination meets the triggering conditions, reading the corresponding action entry from the linkage action configuration according to the event type and event level, generating a scheduling and linkage instruction containing the execution object, execution order, and time identifier; scheduling and executing the scheduling and linkage instruction according to the execution order, and recording the instruction issuance, execution confirmation, and execution completion status during the execution process to form an execution instance record corresponding to the scheduling and linkage instruction.

[0013] As a preferred embodiment of the intelligent scheduling and linkage method for multi-source data in mines as described in this invention, the step of adjusting the linkage rule parameters and action configuration based on the scheduling execution data link includes associating and summarizing the execution instance records of scheduling linkage instructions, object state change records, and abnormal state records to form a scheduling execution data link. Based on the scheduling execution data link, the corresponding threshold parameters, spatial parameters, and action configurations in the rule constraints are identified and updated, and the update results are written into the rule configuration.

[0014] Another objective of this invention is to provide an intelligent scheduling and linkage system for multi-source data in mines. This system can map fused observation inputs with the mine's spatial coordinate system and object semantics to construct a spatialized object state description that includes object location, regional relationships, and associated indexes. Based on the object state description, events are quantitatively evaluated and graded according to pre-configured rule constraints to generate scheduling and linkage instructions that meet the triggering conditions. This solves the problem that current mine scheduling, linkage, and monitoring management methods contain scheduling rules and linkage strategies that are difficult to continuously adjust based on execution results.

[0015] As a preferred embodiment of the intelligent scheduling and linkage system for multi-source data in mines as described in this invention, the system includes: a multi-source data fusion construction module, a spatial state modeling and judgment module, and a linkage execution closed-loop adjustment module. The multi-source data fusion construction module is used to construct basic data units by uniformly sensing, standardizing, and quality-labeling multi-source data from the mine site, and to perform data exchange, cleaning, and reliable fusion processing to output fused observation inputs. The spatial state modeling and judgment module is used to map the fused observation inputs to the mine spatial coordinate system and object semantics to form a spatialized object state description. Based on the object state description, it performs quantitative evaluation and hierarchical judgment of events according to pre-configured rule constraints to generate scheduling and linkage instructions that meet the triggering conditions. The linkage execution closed-loop adjustment module is used to execute the scheduling and linkage instructions in an orderly manner, continuously track the execution process and results, and record state feedback to form a scheduling execution data link. Based on this, it provides feedback adjustments to the linkage rule parameters and action configurations.

[0016] Another objective of this invention is to provide an intelligent scheduling and linkage device for multi-source data in mines, comprising a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps of an intelligent scheduling and linkage method for multi-source data in mines.

[0017] Another objective of this invention is to provide an intelligent scheduling and linkage storage medium for multi-source data in mines, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of an intelligent scheduling and linkage method for multi-source data in mines.

[0018] The beneficial effects of this invention are: The intelligent scheduling and linkage method for multi-source data in mines provided by this invention achieves consistent expression of data from different sources such as safety monitoring, production operation, personnel and equipment in terms of time base, field scope and credibility attributes by uniformly sensing, standardizing collection and quality labeling of multi-source data in the mine, and performing exchange cleaning and trusted fusion calculation on this basis. This fundamentally solves the problems of fragmented multi-source data, uncontrollable quality and difficulty in direct use for scheduling and judgment in the prior art.

[0019] Secondly, by mapping the fusion observation input with the mine spatial coordinate system and object semantics, a spatialized object state description is constructed. Based on the object state, events are quantitatively evaluated and graded according to pre-configured rule constraints. This upgrades the scheduling linkage from the traditional single-point threshold triggering to a refined judgment process that comprehensively considers spatial relationships, object associations, and risk levels. This effectively avoids the shortcomings of existing technologies where numerical limits alone cannot accurately reflect the actual impact range and handling priority. Attached Figure Description

[0020] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. 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.

[0021] Figure 1 The above is an overall flowchart of an intelligent scheduling and linkage method for multi-source data in mines, provided in Embodiment 1 of the present invention. Detailed Implementation

[0022] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0023] Example 1, referring to Figure 1 As an embodiment of the present invention, an intelligent scheduling and linkage method for multi-source data in mines is provided, comprising: S1: By uniformly sensing, standardizing the collection and quality labeling of multi-source data from the mine site, basic data units are constructed, and exchange cleaning and reliable fusion calculation are performed to output fused observation inputs.

[0024] Furthermore, within the mine production and operation environment, a unified data collection and organization is implemented for various sensing objects distributed both above and below ground, focusing on business objectives such as safety monitoring, production automation, personnel and equipment operating status, and scheduling management. This is achieved by connecting field acquisition terminals, communication gateways, and underground control nodes within the mine's industrial network environment to continuously collect data from safety monitoring devices, production automation devices, personnel positioning devices, equipment operation monitoring devices, and business reporting terminals, forming a raw data stream covering the mine's main production and safety elements. During the collection process, the physical identifiers, communication addresses, and data output frequencies of various sensing objects are registered and constrained, ensuring that each piece of collected data possesses clear source and time attributes from the moment it is generated.

[0025] During data acquisition, the data communication methods are uniformly constrained. Addressing the various industrial communication protocols and data formats present in the mine, raw data is transformed into structured data records through protocol parsing and field mapping. During structuring, the types, units, and encoding methods of data fields are standardized, ensuring basic standardization of data from different sources and in different formats at the acquisition stage. This provides a consistent data representation foundation for subsequent data fusion and computation. This approach ensures the alignment of safety monitoring data, equipment operation data, and production status data across timelines and data structures.

[0026] To address the complex communication links and frequent network fluctuations in mine environments, the operational status of data acquisition tasks and communication link status information are recorded simultaneously during the data acquisition process. For each piece of acquired data, the acquisition time, arrival time, and dwell time in the buffer queue are recorded, making data latency information and acquisition task status information secondary attributes of the data itself. Continuous monitoring of the acquisition task's operational status, network connection status, and buffer status enables subsequent assessments of data real-time performance and reliability based on explicit link status information, without relying on experience or manual annotation.

[0027] It should be noted that after completing the basic data collection and protocol parsing, a unified preliminary data quality check is performed on the collected data. The check process focuses on dimensions such as data uniqueness, consistency, accuracy, and completeness. It calculates the duplication of key fields, consistency of encoding and units, valid numerical ranges, and the completeness of required fields to form a data quality index record for each data point during the collection phase. This quality index is stored as an intrinsic attribute of the data along with the collected data, allowing subsequent data fusion or scheduling linkage judgments to directly reference the quality information generated during the collection phase without recalculation.

[0028] Based on the above, the collected raw structured data, corresponding data quality indicators, and link status information are encapsulated together into a multi-source basic data unit for the mine, and written into the data cache and storage medium in chronological order.

[0029] It should also be noted that in the mine production and operation environment, data collection is uniformly organized for various sensing objects distributed both above and below ground, focusing on business objects such as safety monitoring, production automation, personnel and equipment operating status, and scheduling management. By connecting field acquisition terminals, communication gateways, and underground control nodes within the mine's industrial network environment, data from safety monitoring devices, production automation devices, personnel positioning devices, equipment operation monitoring devices, and business reporting terminals are continuously collected, forming a raw data stream covering the mine's main production and safety elements. During the collection process, the physical identifiers, communication addresses, and data output frequencies of various sensing objects are registered and constrained, ensuring that each piece of collected data possesses clear source and time attributes upon generation.

[0030] During data acquisition, the data communication methods are uniformly constrained. Addressing the various industrial communication protocols and data formats present in the mine, raw data is transformed into structured data records through protocol parsing and field mapping. During structuring, the types, units, and encoding methods of data fields are standardized, ensuring basic standardization of data from different sources and in different formats at the acquisition stage. This provides a consistent data representation foundation for subsequent data fusion and computation. This approach ensures the alignment of safety monitoring data, equipment operation data, and production status data across timelines and data structures.

[0031] To address the complex communication links and frequent network fluctuations in mine environments, the operational status of data acquisition tasks and communication link status information are recorded simultaneously during the data acquisition process. For each piece of acquired data, the acquisition time, arrival time, and dwell time in the buffer queue are recorded, making data latency information and acquisition task status information secondary attributes of the data itself. Continuous monitoring of the acquisition task's operational status, network connection status, and buffer status enables subsequent assessments of data real-time performance and reliability based on explicit link status information, without relying on experience or manual annotation.

[0032] After completing basic data collection and protocol parsing, a unified preliminary data quality check is performed on the collected data. The check process focuses on dimensions such as data uniqueness, consistency, accuracy, and completeness. It calculates the duplication of key fields, consistency of encoding and units, valid numerical ranges, and the completeness of required fields to form a data quality index record for each data point during the collection phase. This quality index is stored as an intrinsic attribute of the data along with the collected data, allowing subsequent data fusion or scheduling linkage judgments to directly reference the quality information generated during the collection phase without recalculation.

[0033] Furthermore, the collected raw structured data, corresponding data quality indicators, and link status information are collectively encapsulated into multi-source basic data units for the mine, and written to the data cache and storage medium in chronological order. After forming the multi-source basic data units for the mine, to address the problem of data being difficult to directly correlate across systems and business domains, incremental data exchange and cleaning processing is performed on the structured data records to meet the unified data expression requirements for scheduling and linkage. The cleaning process, based on field mapping relationships, incremental identifier fields, and update time fields, merges and removes duplicate records of the same object from different sources, marks missing fields according to unified data standards, identifies and isolates records that do not meet value range constraints, and constructs an indexable data detail sequence based on object identifiers and timestamps, enabling the formation of a traceable time-series data set for business objects at any given time.

[0034] After the exchange and cleaning process is completed, to meet the real-time and reliability requirements of mine scheduling and linkage, a reliable fusion calculation is performed on observations from different data sources at the same timestamp to obtain reliable observation inputs for subsequent linkage judgments and linkage command generation. The reliable fusion calculation uses quality indicators and link status information already fixed during the acquisition phase as determined weighting factors, ensuring that the fusion result is entirely generated from collectable, configurable, and verifiable data, without relying on manual experience parameters. Specifically, the set of data sources participating in the fusion is denoted as... At any moment Calculate the trusted fusion value Represented as: , in, Indicates time Reliable fused observations; Represents a timestamp; Indicates the number of data sources participating in the fusion; Indicates the data source index number; Indicates the first Data sources at time Standardized observations; Indicates the first Weight of each data source; Indicates the first Data sources at time The data quality factor, calculated and stored synchronously during the data acquisition phase, is represented as follows: , in, The uniqueness indicator is calculated and normalized based on the repetition rate of the primary key or logical primary key of the same object within a time window. This represents a consistency indicator, which is standardized based on the consistency verification results of the encoding, unit, field type, and data standard. The accuracy index is normalized based on the verification results of the valid numerical range and threshold constraints. The integrity index is calculated and normalized based on the proportion of non-empty fields in the required fields. Indicates the first Data sources at time The link reliability factor, calculated and stored based on the data acquisition task status and data latency, is expressed as: , in, This indicates the status flag of the data acquisition task, taken from the data acquisition task running status monitoring record. The value is 1 when the data acquisition task is running and 0 when the data acquisition task is stopped. Indicates data latency; This represents the time delay decay constant.

[0035] S2: The integrated observation input is mapped with the mine spatial coordinate system and object semantics to construct a spatialized object state description that includes object location, regional relationship and associated index. Based on the object state description, the event is quantitatively evaluated and graded according to the pre-configured rule constraints to generate scheduling linkage instructions that meet the triggering conditions.

[0036] Furthermore, after completing the construction of multi-source basic data units and reliable fusion computing in the mine, a unified spatial mapping process is performed on the fused data records to address the dependencies on spatial location, regional scope, and object distribution relationships during the scheduling and linkage process. Based on mine engineering drawings, roadway structure data, and the spatial coordinate system above and below ground, the spatial mapping uniformly calibrates the locations of safety monitoring points, production equipment, personnel positioning coordinates, and production operation area boundaries, giving each piece of fused data a clear spatial attribute in addition to its temporal attributes.

[0037] During the spatial mapping process, based on the existing two-dimensional engineering drawings and three-dimensional roadway structure data of the mine, the spatial coordinates of underground roadways, mining faces, equipment installation locations, and work areas are unified. By establishing a fixed correspondence between the physical identifiers and equipment numbers registered during the data acquisition phase and the spatial coordinate information, safety monitoring data, equipment operation data, and personnel positioning data can be automatically associated with the corresponding spatial locations when written into the fusion result record. This ensures that the fusion data of the same object at different points in time are all mapped to the same spatial coordinate reference.

[0038] To address the characteristics of simultaneous operations across multiple disciplines and areas in mine production, the fused data is further organized by region based on spatial mapping. This regional organization uses mining areas, working faces, roadway sections, and key monitoring areas as boundaries to aggregate fused data within a spatial range, enabling different objects within the same region to form combinable state sets within the same time window. This approach allows subsequent scheduling and coordination to directly filter data based on regional boundaries when determining the scope of an event's impact or related objects, without requiring recalculation of spatial relationships.

[0039] After completing spatial mapping and regional organization, object status processing is performed on the fused data records. Object status processing uses equipment objects, personnel objects, and environmental objects as basic units, combining the fused observation value, spatial location identifier, and region identifier corresponding to the same object at the same timestamp into an object status record. The object status record uses the object's unique identifier and timestamp as index fields, enabling continuous querying and backtracking of its operational, environmental, or job status by object dimension, thereby supporting the analysis needs of object status evolution during scheduling and coordination.

[0040] It should be noted that, based on the object status organization, the spatial relationships between different types of objects are permanently recorded. These spatial relationships include the relative distance between objects, the containment relationship between objects and area boundaries, and the adjacency relationship between objects within the same alleyway or work area. These spatial relationships are saved by calculating the spatially mapped data and writing it into an association index table. This allows for direct retrieval of personnel, equipment, or area information associated with the event object through the index relationship when triggering scheduling and linkage judgments, without requiring real-time spatial traversal at the time of linkage triggering.

[0041] After completing spatial mapping, regional organization, and object status processing, the resulting spatialized fused data is written to the storage medium, and a query structure is established with spatial coordinates, region identifiers, and object identifiers as the main indexes. This query structure supports combined retrieval of fused data by time range, spatial range, and object range, enabling the rapid acquisition of the set of object states related to the event within a specified time window and spatial range during scheduling and linkage processes.

[0042] It should also be noted that after completing the spatial mapping and object state organization of the multi-source fusion data in the mine, to address the need for unified and coordinated handling of safety risks, equipment anomalies, and changes in production status during mine scheduling, a set of rule constraints oriented towards scheduling coordination was constructed around object state changes. The set of rule constraints is organized with event type, object identifier, threshold parameter, spatial parameter, weight parameter, and permission parameter as core fields, ensuring that each rule can be uniquely located when an object state change occurs and that coordinated judgments are executed in a defined calculation order.

[0043] Within the rule constraint set, each rule entry is categorized and stored according to its event type code. A corresponding threshold table, parameter table, and weight table are configured for each event type. The threshold table records the numerical thresholds for different event types at different levels. The parameter table records the normalized scale parameter and spatial influence radius parameter. The weight table records the weight coefficients of each component in the linkage score. All these configuration tables use the event type code as the primary index field, enabling rules to directly index the corresponding configuration parameters by event type at runtime.

[0044] During scheduling operations, when an object's state record is updated, the object's state record at the current timestamp is traversed and checked using the object identifier and timestamp as index conditions. If the object's state record contains a registered event type code, the state change is identified as an event to be determined, and a rule entry matching the event type code is read from the rule constraint set. In this way, scheduling linkage determination always uses object state changes as the trigger source, without relying on manual triggering or external commands.

[0045] After the rule entry is located, the fused observation value, object spatial coordinates, region identifier, and object association index from the object state record are loaded into the calculation context as input fields for rule calculation. During the loading process, multiple state records of the same object under the same timestamp are merged, ensuring that each event participates in the linkage judgment only once under each timestamp, avoiding duplicate triggering caused by differences in data update frequency.

[0046] After preparing the rule input fields, the intensity of event scheduling linkage is quantitatively evaluated. The quantitative evaluation uses the degree of risk exceeding the limit, the degree of spatial proximity, and the degree of data credibility as basic components, and combines them through fixed weights to form a linkage score for determining scheduling linkage.

[0047] The linkage score and trigger criteria are expressed as follows: , in, This represents the event identifier, derived from the event record primary key formed by combining the event type code and object identifier bound in the rule entry. The event types cover a set of events that require coordinated handling in mine scheduling scenarios, such as safety monitoring anomalies, equipment anomalies, and production status anomalies. Indicates an event At any moment The linked score is obtained by linear weighting of three quantitative components, and the value range is determined by the normalization result of each component and the weight coefficient. This indicates the result of the linkage trigger determination. The value is 0 or 1. 1 indicates that the trigger condition is met and a linkage command is generated, while 0 indicates that the linkage command is not triggered. This represents the weight coefficient, stored in the configuration table of the rule constraint set, and read using the event type code as the index field. Its value is a non-negative real number that satisfies... . This indicates a risk exceeding the limit, representing the degree to which the measured value of an event exceeds the threshold. After normalization, the value is taken as... Interval. Spatial proximity term, representing the degree of spatial proximity between an event point and its associated object, with values ​​ranging from... The closer the interval, the larger the value. This represents a data credibility item, indicating the degree of credibility of event data under the acquisition link and quality rules, with values ​​ranging from... Interval. The data source that triggered the event is at time [time]. The corresponding data quality factor and link reliability factor. Specifically, Data quality indicators are taken from the data collection phase and normalized according to fixed dimensions; It is obtained by taking the data acquisition task status and data latency fields and calculating them using a fixed exponential decay formula. The result of the event level mapping is taken from the level mapping table in the rule constraint set. The level mapping table uses the event type code and the risk out-of-bounds range as index fields and outputs a fixed level identifier. This represents the trigger threshold corresponding to the event level, taken from the threshold table of the rule constraint set, and read using the level identifier as the primary key index. This indicates the permission verification result, with a value of 0 or 1. It is derived from the matching verification result between the permission identifier field bound to the rule entry and the identity identifier field of the current scheduling entity. The permission identifier field is fixed during the rule base configuration phase and stored as an index field of the rule entry.

[0048] The calculation process for each component and its mapping relationship with the rule fields are as follows: First, the degree of risk exceeding the limit is calculated. The degree of risk exceeding the limit reflects the extent to which the object's state deviates from a safe or operational threshold at the numerical level, and is expressed as: , in, This represents the event's measured or diagnostic value, taken from the fused observation or diagnostic field in the object's status record. For security monitoring events, Take the formed reliable fused observations The fusion result corresponding to the measurement point; for equipment malfunction events, The diagnostic level value is taken from the equipment operation monitoring record after field mapping. The event threshold is taken from the threshold table of the rule constraint set. The threshold table uses the event type code as the primary key index and uses a fixed field to store the threshold ranges of different levels. This represents the normalization scaling parameter, taken from the parameter table of the rule constraint set, and read using the event type code as the primary key index. The parameter specifies the amount exceeding the limit. The risk of exceeding the limit is given a full score of 1, thus making events of different dimensions comparable.

[0049] Event Measurement The fused observation fields are directly taken from the object's status record. For safety monitoring events, the fused observation fields originate from the generated trusted fused observation values; for equipment anomaly events, the fused observation fields originate from the diagnostic values ​​mapped from the equipment's operating status record. Event Threshold With normalized scaling parameters All parameters are taken from the parameter table in the rule constraint set and read using the event type code as the index field, thus completely determining the calculation path of the risk out-of-bounds item.

[0050] After calculating the risk boundary crossing, the spatial proximity of the event is calculated. Spatial proximity reflects the spatial relationship between the location of the event and personnel, critical equipment, or key areas. The calculation process is as follows: , in, Spatial proximity term, representing the degree of spatial proximity between an event point and its associated object, with values ​​ranging from... The closer the interval, the larger the value. This represents the spatial distance, taken from the spatial association index table. Specifically, based on the spatial coordinates of the event object in the object status record, the nearest personnel object, key equipment object, and key area boundary object are retrieved from the spatial association index table, and the minimum value of the distance field between the event point and the associated object is taken as the spatial distance. . The parameter representing the influence radius is taken from the parameter table of the rule constraint set and read using the event type code as the primary key index. It is used to specify the spatial proximity term when the distance reaches a certain threshold. It decays to 0 over time.

[0051] Spatial distance measurement It is taken from the formed spatial association index table. Specifically, based on the spatial coordinates of the event object in the object status record, the spatial association index table is used to retrieve personnel objects, equipment objects, and area boundary objects associated with the event object, and the minimum value of the retrieved distance field is taken as the spatial distance of the event. Influence radius parameter The parameter table is taken from the rule constraint set and read with the event type code as the main index field, so that the calculation of the spatial proximity term has a fixed spatial decay boundary under different event types.

[0052] Subsequently, the reliability of the event data is calculated. Data reliability reflects the reliability of event measurements during the acquisition and transmission process, and is expressed as: , in, and The data quality factor and link reliability factor are respectively derived from the data quality index records generated during the trusted fusion computation. The data quality factor originates from the data quality index records generated during the acquisition phase, and the link reliability factor originates from the calculation results of the acquisition task status and data latency fields. By directly reusing the already fixed fields, the linkage determination phase does not need to re-evaluate the data quality and link status, thereby maintaining the consistency between the linkage determination and the data fusion process.

[0053] After calculating the above three components, the weight coefficients configured in the rule constraint set are then applied. We perform a weighted summation of the components to obtain the event's timestamp. Linked ratings The weighting coefficients are written to the weight table during the rule configuration phase and read using the event type code as the index field, thereby ensuring that the scoring calculation rules for the same type of event remain consistent at different times.

[0054] After obtaining the linkage score, the score result is compared with the trigger threshold corresponding to the event level. Event Level The trigger threshold is read from the level mapping table according to the risk out-of-bounds item range mapping rules. The level identifier is then used as an index field to read from the threshold table, so that different level events have different trigger sensitivities when scheduling and linking.

[0055] Simultaneously, the permission conditions for the event are validated. Permission validation matches the permission identifier field bound to the rule entry with the identity identifier field of the current scheduling entity. The matching result is... The linkage trigger determination result is made only if and only if the linkage score meets the threshold constraint and the permission verification passes. The value is 1.

[0056] After the linkage trigger determination is established, the corresponding action configuration entry is read from the linkage action mapping table according to the event type code and event level identifier. The action configuration entry records the linkage action number, action execution order, and action associated object identifier. The above information is combined with the event identifier, event space coordinates, associated object list, and timestamp to form a linkage instruction record, and this linkage instruction record is written to the storage medium as the input basis for subsequent scheduling execution and status feedback.

[0057] While generating the linkage instruction record, the linkage score will be... and each component The calculation results are written into the linkage instruction record, so that the calculation process of any linkage trigger can be reviewed and traced in the future, thereby ensuring that the scheduling linkage judgment process has complete interpretability at the field level.

[0058] S3: Executes scheduling and linkage instructions in an orderly manner, continuously tracks the execution process and results, and records status feedback to form a scheduling execution data link. Based on the scheduling execution data link, it provides feedback and adjusts the linkage rule parameters and action configurations.

[0059] Furthermore, after completing the rule-based scheduling and linkage determination and generating linkage instruction records, the generated linkage instruction records are subject to unified execution scheduling and status management to meet the requirements of controllability of instruction execution, traceability of execution process, and traceability of execution results during mine scheduling. The linkage instruction records are organized using event identifiers, linkage action identifiers, associated object identifiers, and timestamps as core fields, ensuring that each linkage instruction has a clear execution object and execution order when entering the execution phase.

[0060] Before the linkage instructions enter the execution phase, multiple linkage instructions generated by the same event are sorted according to the action execution order field contained in the linkage instruction record. During the sorting process, the action execution order field is used as the primary sorting criterion, and the instruction generation timestamp is used as the secondary sorting criterion. This ensures that the linkage instructions are always scheduled and executed sequentially according to the order fixed in the rule configuration phase during the execution phase, thereby avoiding scheduling conflicts caused by uncertain execution order.

[0061] After the execution order is finalized, the linkage instruction records are loaded into the execution context, and the status of the execution objects associated with the linkage instructions is verified. The status verification is based on the formed object status records, and the consistency of the running status, spatial location status, and association status of the execution objects at the current timestamp is checked. This ensures that the execution of linkage instructions is always based on the latest object status information, and that outdated statuses are not used for scheduling operations.

[0062] When a linked instruction begins execution, an independent execution instance record is generated for each linked instruction. The execution instance record uses the linked instruction identifier as a foreign key and records the execution start time, execution object identifier, execution context identifier, and execution node identifier. This method allows the execution process of the same linked instruction at different times or different execution nodes to be recorded separately, thus providing foundational data for subsequent execution process analysis.

[0063] During the execution of the linked instructions, the execution status is continuously tracked, and key status changes are written into the execution instance record. The execution status includes instruction issuance status, execution confirmation status, and execution completion status. Each status is written into the record using a fixed status code and includes a corresponding timestamp field. By recording the execution status in stages, the execution process of the linked instructions forms a complete state sequence on the timeline, thus supporting precise backtracking of the execution process.

[0064] It should be noted that during execution, if the state of the object changes, the maintained object state record is updated accordingly based on the object identifier and timestamp fields in the execution instance record. The update process maintains the temporal continuity of the object state record, allowing the state changes caused by execution to seamlessly connect with the previous object state on the timeline, thereby ensuring the integrity of the object state evolution process.

[0065] After the linkage instruction is executed, the execution instance record is sealed with its status. During status sealing, the execution completion time, the final execution status code, and the execution result identifier are written into the execution instance record, and the record is associated with the original linkage instruction record with a completion identifier, so that the corresponding execution result can be quickly located through the linkage instruction identifier in the future.

[0066] After the execution instance is sealed, the execution results undergo unified reflow processing. This reflow processing uses the event identifier, object identifier, and timestamp as index conditions to write the execution results into the historical record set associated with the event, and establishes a correspondence between these results and the generated linkage score field, spatial association field, and permission verification field. In this way, the result of each linkage execution can form a complete mapping at the field level with the judgment conditions that triggered that execution.

[0067] While the execution results are being fed back, any abnormal states encountered during execution are identified and recorded. Abnormal states include execution timeouts, inconsistent execution object states, and execution interruptions. The abnormal state identifier is written to the execution instance record as a fixed status code, along with the time of the exception and the exception context identifier, enabling subsequent analysis and handling of abnormal execution situations based on the records.

[0068] After execution and reflow processing are completed, the linkage instruction records, execution instance records, and object status records are uniformly stored and indexed. The index maintenance uses event identifier, object identifier, timestamp, and spatial region identifier as composite index fields, enabling subsequent retrieval of the linkage execution history by event dimension, object dimension, or region dimension, thereby providing a data foundation for subsequent scheduling analysis and strategy adjustment.

[0069] It should also be noted that after the execution of the linkage command is completed and the execution instance record and status feedback record are generated, in order to meet the requirements of mine scheduling management for the sustainable operation and strategy adjustability of the linkage process, the various records generated during the linkage execution process are uniformly organized and analyzed. The records include linkage command records, execution instance records, object status change records, and abnormal status identification records. The various records have established a clear index relationship according to event identifier, object identifier, and timestamp.

[0070] When organizing the above records, the event identifier was used as the primary index field to associate and summarize the linkage judgment records, linkage instruction records, and execution instance records corresponding to the same event under different timestamps. In this way, the entire process of each scheduling linkage, from judgment and instruction generation to execution completion, forms a complete link at the data level, providing a continuous data foundation for subsequent analysis of scheduling behavior.

[0071] After summarizing the event-level records, the execution status and time fields in the execution instance records are parsed and processed to form a time-series description of the linked execution process. This time-series description uses the execution start time, state change time, and execution completion time as nodes, enabling the progress of the linked instructions during execution to be accurately depicted and aligned with the object state change records on the same timeline.

[0072] Based on time-series descriptions, the changes in object states during coordinated execution are aggregated. This aggregation process uses object identifiers as indexes to compare and organize the object's state records before and after coordinated execution, ensuring that the changes in object state before and after scheduling intervention are fully preserved. In this way, the impact of scheduling actions on the object's running state is recorded as objective data facts, without relying on manual descriptions.

[0073] After collecting the object state changes, execution instances marked as abnormal during execution are organized separately. Abnormal states include execution timeouts, inconsistent execution states, and execution interruptions. For each abnormal execution instance, its corresponding event identifier, linkage instruction identifier, abnormal status code, and abnormal occurrence time are recorded, enabling independent retrieval and analysis of abnormal execution situations later.

[0074] Based on the above, feedback updates are performed on the parameter fields related to linkage determination in the rule constraint set. The feedback update uses execution instance records and object state change records as input, and identifies the applicability of threshold parameters, normalized scale parameters, spatial influence radius parameters, and weight parameters. Specifically, when a certain type of event continuously experiences execution anomalies or when the execution results do not match the object state changes in multiple executions, the parameter fields in the corresponding rule entries are marked as pending adjustment.

[0075] After parameter identification is completed, parameter adjustment operations are performed on the rule constraint set. Based on the identification results, the parameter adjustment operation updates the parameters of each marked rule entry and writes the updated parameter values ​​to the rule configuration table. The parameter update process retains the correspondence between the original and new parameter values ​​and records the parameter update time and update basis identifier, ensuring a complete historical record of the parameter adjustment process.

[0076] After adjusting the rule parameters, an activation flag is set for the updated rule entries, and they are used in subsequent scheduling linkage judgment processes. To ensure the continuity of scheduling behavior, the rules with adjusted parameters only participate in new linkage judgments after their activation flag is activated, so that the new rules and old rules remain clearly distinguishable on the timeline.

[0077] While adjusting the rule parameters, a consistency check is performed on the linked action mapping table. The check process uses the action execution results in the execution instance records as a basis, verifying the execution order field and execution object field in the action configuration entries to ensure consistency between the action configuration and the actual execution process. When a discrepancy is found between the configuration and the execution result, the action configuration entry is corrected and the correction timestamp is recorded.

[0078] After adjusting the rule parameters and action configurations, the execution records, status change records, and exception records used for this adjustment are archived. The archiving process is done in time windows, writing historical scheduling behavior data to the archive storage area and establishing an archive index structure indexed by event type, object type, and region identifier, enabling subsequent queries of historical scheduling behavior according to different dimensions.

[0079] Through the above-mentioned record accumulation, feedback identification, parameter adjustment and archiving processes, the mine scheduling linkage can continuously adjust the rule configuration based on historical execution while maintaining the stability of the existing judgment and execution logic, thereby forming a closed management process for scheduling linkage at the data level.

[0080] Example 2, one embodiment of the present invention, provides an intelligent scheduling and linkage system for multi-source data in mines, including a multi-source data fusion construction module, a spatial state modeling and judgment module, and a linkage execution closed-loop adjustment module.

[0081] The multi-source data fusion construction module is used to construct basic data units by uniformly sensing, standardizing the collection and quality labeling of multi-source data from the mine site, and performing data exchange, cleaning and reliable fusion processing to output fused observation input. The spatial state modeling and judgment module is used to map the fused observation input with the mine spatial coordinate system and object semantics to form a spatial object state description. Based on the object state description, it performs quantitative evaluation and hierarchical judgment of events according to pre-configured rule constraints to generate scheduling linkage instructions that meet the triggering conditions. The linkage execution closed-loop adjustment module is used to execute the scheduling linkage instructions in an orderly manner, continuously track the execution process and execution results and record the state feedback to form a scheduling execution data link. On this basis, it provides feedback adjustment to the linkage rule parameters and action configuration.

[0082] This embodiment also provides a computer device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements the intelligent scheduling and linkage method for multi-source data in mines proposed in the above embodiment.

[0083] This embodiment also provides a computer-readable storage medium storing a computer program thereon. When the computer program is executed by a processor, it implements the intelligent scheduling and linkage method for multi-source data in mines as proposed in the above embodiment.

[0084] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0085] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0086] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0087] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0088] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for intelligent scheduling and linkage based on multi-source data in mines, characterized in that, include: By uniformly sensing, standardizing the collection and quality labeling of multi-source data from the mine site, basic data units are constructed, and exchange cleaning and reliable fusion calculation are performed to output fused observation inputs. The observation input is mapped with the mine spatial coordinate system and object semantics to construct a spatial object state description that includes object location, regional relationship and associated index. Based on the object state description, the event is quantitatively evaluated and classified according to the pre-configured rule constraints to generate scheduling linkage instructions that meet the triggering conditions. The scheduling and linkage instructions are executed in an orderly manner, and the execution process and results are continuously tracked and the status feedback is recorded to form a scheduling execution data link. Based on the scheduling execution data link, the linkage rule parameters and action configurations are adjusted.

2. The intelligent scheduling and linkage method for multi-source data in mines as described in claim 1, characterized in that: The aforementioned method involves unified perception, standardized collection, and quality labeling of multi-source data from the mine site to construct basic data units, including: Collect multi-source data from the mine site, including continuous collection of safety monitoring data, production operation data, and personnel and equipment status data distributed both above and below ground in the mine. During the collection process, the physical identifier, object identifier, collection time, and communication status of each data source are recorded. The system performs protocol parsing and field mapping on multi-source data collected from the mine site to form records with consistent structure from different sources, performs verification, and generates basic data units.

3. The intelligent scheduling and linkage method for multi-source data in mines as described in claim 1 or 2, characterized in that: The execution of the exchange cleaning and trusted fusion computation, and the output fusion observation inputs include, Data exchange and cleaning are performed on basic data units according to object identifiers and timestamps, duplicate records are merged, missing fields are identified, and outliers are isolated and labeled. After the exchange and cleaning are completed, based on the labeled data quality information and acquisition link status information, the observation records of the same object from different data sources at the same timestamp are fused to generate fused observation input.

4. The intelligent scheduling and linkage method for multi-source data in mines as described in claim 3, characterized in that: The process of mapping the fused observation input with the mine spatial coordinate system and object semantics includes... A unified spatial coordinate system was established based on mine engineering drawings and roadway structure data, and safety monitoring points, equipment installation locations, and personnel positioning information were bound to the spatial coordinate system. The fusion observation input is associated with the corresponding object identifier and spatial coordinates to form an object status record containing information such as object location, region, and spatial index.

5. The intelligent scheduling and linkage method for multi-source data in mines as described in any one of claims 1, 2, and 4, characterized in that: The process of generating scheduling and linkage instructions that meet the triggering conditions, based on object state description and according to pre-configured rule constraints, includes: The event type is identified based on the changes in the fused observations in the object state record, and the threshold parameters, spatial parameters and permission parameters corresponding to the event type are read from the rule constraints. Based on the numerical and spatial association information contained in the object state record, the risk level and impact scope of the event are assessed, and the event level is determined according to the assessment results, so that the event judgment process has a mapping relationship between input fields and rules.

6. The intelligent scheduling and linkage method for multi-source data in mines as described in claim 5, characterized in that: The orderly execution of scheduling and linkage instructions, and the continuous tracking and status feedback recording of the execution process and results, forming a scheduling execution data link, includes: When the event determination meets the triggering conditions, the corresponding action entry is read from the linkage action configuration according to the event type and event level, and a scheduling linkage instruction containing the execution object, execution order and time identifier is generated; The scheduling and linkage instructions are scheduled and executed in the order of execution, and the issuance of instructions, execution confirmation and execution completion status are recorded during the execution process to form an execution instance record corresponding to the scheduling and linkage instructions.

7. The intelligent scheduling and linkage method for multi-source data in mines as described in any one of claims 1, 2, 4, and 6, characterized in that: The step of adjusting the linkage rule parameters and action configuration based on the scheduling execution data link includes: The execution instance records, object status change records, and abnormal status records of the scheduling linkage instructions are linked and summarized to form a scheduling execution data link; Based on the scheduling execution data link, the threshold parameters, spatial parameters and action configurations corresponding to the rule constraints are identified and updated, and the update results are written into the rule configuration.

8. An intelligent scheduling and linkage system for multi-source data in mines, employing the intelligent scheduling and linkage method for multi-source data in mines as described in any one of claims 1 to 7, characterized in that: It includes a multi-source data fusion construction module, a spatial state modeling and judgment module, and a linkage execution closed-loop adjustment module; The multi-source data fusion construction module is used to construct basic data units by uniformly sensing, standardizing the collection and quality labeling of multi-source data from the mine site, and to perform data exchange cleaning and reliable fusion processing to output fused observation input. The spatial state modeling and judgment module is used to map the fused observation input with the mine spatial coordinate system and object semantics to form a spatial object state description. Based on the object state description, the module performs quantitative evaluation and hierarchical judgment of events according to pre-configured rule constraints, and generates scheduling linkage instructions that meet the triggering conditions. The linkage execution closed-loop adjustment module is used to execute the scheduling linkage instructions in an orderly manner, continuously track the execution process and execution results and record the status feedback, forming a scheduling execution data link, and on this basis, to adjust the linkage rule parameters and action configuration.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the intelligent scheduling and linkage method for multi-source data in mines as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the intelligent scheduling and linkage method for multi-source data in mines as described in any one of claims 1 to 7.

Images