CN116502904A - Rail transit task handling method and device based on multi-data source processing - Google Patents
Rail transit task handling method and device based on multi-data source processing Download PDFInfo
- Publication number
- CN116502904A CN116502904A CN202310289185.1A CN202310289185A CN116502904A CN 116502904 A CN116502904 A CN 116502904A CN 202310289185 A CN202310289185 A CN 202310289185A CN 116502904 A CN116502904 A CN 116502904A
- Authority
- CN
- China
- Prior art keywords
- data
- task
- semantics
- association
- semantic
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000012545 processing Methods 0.000 title claims abstract description 35
- 238000011282 treatment Methods 0.000 claims abstract description 57
- 238000004088 simulation Methods 0.000 claims abstract description 44
- 238000012216 screening Methods 0.000 claims abstract description 23
- 238000005516 engineering process Methods 0.000 claims abstract description 22
- 238000011369 optimal treatment Methods 0.000 claims abstract description 19
- 230000002776 aggregation Effects 0.000 claims description 16
- 238000004220 aggregation Methods 0.000 claims description 16
- 238000005259 measurement Methods 0.000 claims description 11
- 230000008901 benefit Effects 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 7
- 238000011156 evaluation Methods 0.000 claims description 5
- 238000010801 machine learning Methods 0.000 claims description 5
- 230000008447 perception Effects 0.000 claims description 4
- 230000001364 causal effect Effects 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 4
- 230000007246 mechanism Effects 0.000 description 4
- 230000004044 response Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000001514 detection method Methods 0.000 description 2
- 230000009977 dual effect Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 206010000117 Abnormal behaviour Diseases 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/901—Indexing; Data structures therefor; Storage structures
- G06F16/9027—Trees
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/251—Fusion techniques of input or preprocessed data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/26—Discovering frequent patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Human Resources & Organizations (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- Educational Administration (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Evolutionary Biology (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Game Theory and Decision Science (AREA)
- Computational Linguistics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Operations Research (AREA)
- Primary Health Care (AREA)
- Quality & Reliability (AREA)
- Medical Informatics (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a method and a device for processing a rail transit task based on multi-data source processing, wherein the method comprises the following steps: extracting key semantics in the task, and performing association expansion on the key semantics according to different semantic relations to obtain association semantics; acquiring multi-source data sets associated with the associated semantics, calculating association metric values among the multi-source data sets, and screening multi-source data of the multi-semantics according to the association metric values; based on the multi-source data, constructing a semantic data association structure tree according to the association metric value; dividing task grades according to the associated semantics, and determining a treatment decision scheme of the corresponding grade according to the task grades; and simulating according to the semantic data association structure tree and the treatment decision scheme by a digital twin simulation technology to simulate tasks, and determining an optimal treatment decision scheme according to simulation results. The method solves the problem that a proper treatment decision scheme is difficult to select according to a task scene in the track traffic task.
Description
Technical Field
The present invention relates to the field of data processing technologies, and in particular, to a multi-source data aggregation method and apparatus for multi-tasks.
Background
In recent years, with digital twinning, full life cycle management and other concepts, processing of multi-source data and hidden multi-party association thereof have become important points of public attention. In order to exert potential use energy efficiency of the multi-source data and improve processing capacity for each task, various fields have been studied in depth from the directions of internal association, evolution mechanism and the like of the multi-source data. With the rapid development of novel technologies, particularly the appearance of novel technologies such as artificial intelligence, big data, cloud computing, geographic information and the like, ideas are provided for solving the perception analysis of specific tasks.
The multi-source data set facing the task is mainly used for analyzing and processing data in a limited time space range according to task content, and can give a treatment decision aiming at the current task according to historical processing experience and the current data condition, and a final treatment decision core task is given according to task aggregation data. The task-oriented data comprises space-time basic data, internet of things perception data, business application data and the like from the source perspective, a plurality of data are needed to be gathered together, analysis and research are carried out according to task demands, and finally a disposal decision is put forward. The task-oriented data are often diverse in sources, huge in volumes, various in types and various in data formats, the task disposal speed is affected, a task-oriented multi-source data aggregation and disposal mechanism is needed to be provided, relevant data are converged according to task demands, auxiliary disposal decisions are provided according to the task demands, and the task emergency processing capacity is improved.
Disclosure of Invention
The invention provides a method and a device for processing a rail transit task based on multi-data source processing, which solve the problem that a proper processing decision scheme is difficult to select according to a task scene in the rail transit task.
A method of handling rail transit tasks based on multi-data source processing, comprising:
extracting key semantics in a task, and performing association expansion on the key semantics according to different semantic relations to obtain association semantics;
acquiring a multi-source data set associated with the associated semantics, calculating an associated metric value between the multi-source data sets, and screening multi-source data of the multi-semantics according to the associated metric value;
based on the multi-source data, constructing a semantic data association structure tree according to the association metric value;
dividing task grades according to the associated semantics, and determining a treatment decision scheme of a corresponding grade according to the task grades;
and simulating according to the semantic data association structure tree and the treatment decision scheme by a digital twin simulation technology so as to simulate the task, and determining an optimal treatment decision scheme according to a simulation result.
In one embodiment of the present invention, the extracting key semantics in the task, and performing association expansion on the key semantics according to different semantic relationships to obtain association semantics specifically includes: determining a dataset included in a task, the dataset including text data; extracting key semantics contained in the text data by intercepting key words or extracting machine learning features; and determining different semantic relations through a semantic information association dictionary, and carrying out association expansion on the key semantics according to the different semantic relations.
In one embodiment of the present invention, the calculating the association metric value between the multi-source data sets specifically includes: determining a preset minimum support degree; wherein, the support degree is the frequency of occurrence of an item set in the multi-source data set, each row of records in the multi-source data set corresponds to a transaction, the element in each transaction is called an item, the item set is a set containing one or more items, and if the item set contains k items, the item set is called a k item set; s1, scanning the multi-source data set to obtain a first candidate data item set, wherein the first candidate data item set is 1 item set; screening the first candidate data item set to obtain a frequent 1 item set meeting the minimum support; s2, scanning the multi-source data set, and determining a 2-item set containing the frequent 1-item set as a second candidate data item set; screening the second candidate data item set to obtain a frequent 2 item set meeting the minimum support; circularly scanning the multi-source data set according to the scanning steps S1-S2 until a frequent n-item set is obtained; wherein a frequent n+1 item set satisfying the minimum support cannot be regenerated from the frequent n item set.
In one embodiment of the present invention, the building a semantic data association structure tree according to the association metric value specifically includes: the association metric includes a support and a confidence, the confidence being a ratio of a number of transactions comprising the item set { Y, X } to a number of transactions comprising the item set { Y } or the item set { X }; constructing a semantic data association structure tree according to the support degree and the confidence degree; the semantic data association structure tree comprises a semantic aggregation node layer and a data operation node layer; the semantic aggregation node layer comprises semantic information nodes corresponding to tasks, and the relation among the semantic information nodes corresponds to the actual application relation; the data manipulation node layer includes one or more data manipulation nodes associated with tasks and corresponding semantics.
In one embodiment of the present invention, the simulating by digital twin simulation technique according to the semantic data association structure tree and the treatment decision specifically includes: the task is a rail transit task, and the treatment decision comprises a treatment flow in an experience library and expert treatment experience; acquiring multidirectional operation data of a track traffic task, and constructing a digital twin model according to the multidirectional operation data; based on the digital twin model, according to the multi-azimuth operation data, the disposal flow, the expert disposal experience and the aggregate semantics and data obtained through the semantic data association structure tree, performing simulation on a task disposal decision scheme of the current task scene of the track traffic task.
In one embodiment of the present invention, the determining an optimal treatment decision scheme according to the simulation result specifically includes: determining a measurement dimension of a treatment decision scheme, wherein the measurement dimension comprises operation time, economic benefit and safety performance; determining the weight of each measuring dimension, wherein the sum of the weights of the measuring dimensions is equal to 1; calculating the priority of each treatment decision scheme according to the weight of each measurement dimension; and determining an optimal treatment decision scheme according to the priority.
In one embodiment of the invention, the semantic relationships include causal relationships, sequential relationships, concurrent relationships, containment relationships; the multi-source data set comprises space-time basic data, internet of things perception data, business application data and operation evaluation data.
A handling device for track traffic tasks based on multi-data source processing, comprising:
the semantic information acquisition module is used for extracting key semantics in the task, and carrying out association expansion on the key semantics according to different semantic relations to obtain association semantics;
the screening module is used for acquiring the multi-source data sets associated with the associated semantics, calculating the association metric values among the multi-source data sets, and screening the multi-source data of the multi-semantics according to the association metric values;
the semantic data association structure tree construction module is used for constructing a semantic data association structure tree according to the association metric value based on the multi-source data;
the task grade classification module is used for classifying task grades according to the associated semantics and determining a treatment decision scheme of a corresponding grade according to the task grades;
and the simulation module is used for simulating the task according to the semantic data association structure tree and the treatment decision scheme by a digital twin simulation technology, and determining an optimal treatment decision scheme according to a simulation result.
A track traffic task handling device based on multi-data source processing, comprising:
at least one processor; the method comprises the steps of,
a memory communicatively coupled to the at least one processor via a bus; wherein,,
the memory stores instructions executable by the at least one processor to implement:
extracting key semantics in a task, and performing association expansion on the key semantics according to different semantic relations to obtain association semantics;
acquiring a multi-source data set associated with the associated semantics, calculating an associated metric value between the multi-source data sets, and screening multi-source data of the multi-semantics according to the associated metric value;
based on the multi-source data, constructing a semantic data association structure tree according to the association metric value;
dividing task grades according to the associated semantics, and determining a treatment decision scheme of a corresponding grade according to the task grades;
and simulating according to the semantic data association structure tree and the treatment decision scheme by a digital twin simulation technology so as to simulate the task, and determining an optimal treatment decision scheme according to a simulation result.
A non-volatile storage medium storing computer executable instructions for execution by a processor to perform the steps of:
extracting key semantics in a task, and performing association expansion on the key semantics according to different semantic relations to obtain association semantics;
acquiring a multi-source data set associated with the associated semantics, calculating an associated metric value between the multi-source data sets, and screening multi-source data of the multi-semantics according to the associated metric value;
based on the multi-source data, constructing a semantic data association structure tree according to the association metric value;
dividing task grades according to the associated semantics, and determining a treatment decision scheme of a corresponding grade according to the task grades;
and simulating according to the semantic data association structure tree and the treatment decision scheme by a digital twin simulation technology so as to simulate the task, and determining an optimal treatment decision scheme according to a simulation result.
The invention provides a method and a device for processing a rail transit task based on multi-data source processing, which at least comprise the following beneficial effects: the method of the invention obtains a proper treatment decision scheme, can control the task site by means of the sensor, the controller and the like preferentially, ensures the rapid response to the task and the accuracy of the task execution by the sensor control and the manual dual response mechanism according to the decision by the staff. By adopting a multi-data source aggregation strategy, relevant data are gathered aiming at task demands, and an auxiliary treatment decision scheme is given according to the task demands, so that the emergency processing capacity of the task is improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention and do not constitute a limitation on the invention. In the drawings:
fig. 1 is a schematic diagram of steps of a method for handling a track traffic task based on multi-data source processing according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of a multi-source data aggregation method for track traffic tasks according to an embodiment of the present invention;
FIG. 3 is a flowchart of mining multi-source data information aggregation according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a tree for constructing a semantic data structure according to an embodiment of the present invention;
fig. 5 is a schematic diagram of a handling device for a track traffic task based on multi-data source processing according to an embodiment of the present invention;
fig. 6 is a schematic diagram of a treatment device for a track traffic task based on multi-data source processing according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be clearly and completely described in connection with the following specific embodiments of the present invention. It will be apparent that the described embodiments are only some, but not all, embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be noted that those skilled in the art explicitly and implicitly understand that the described embodiments of the invention can be combined with other embodiments without conflict. Unless defined otherwise, technical or scientific terms used herein should be given the ordinary meaning as understood by one of ordinary skill in the art to which this invention belongs. The terms "a," "an," "the," and similar referents in the context of the invention are not to be construed as limiting the quantity, but rather as singular or plural. The terms "comprising," "including," "having," and any variations thereof, are intended to cover a non-exclusive inclusion; the terms "first," "second," "third," and the like, as used herein, are merely distinguishing between similar objects and not representing a particular ordering of objects.
The invention provides a method and a device for processing a rail transit task based on multi-data source processing. By utilizing a data analysis method, tasks, scene understanding and data analysis are combined, a multisource data analysis aggregation method for track traffic tasks is researched, and an auxiliary decision is provided for an actual application scene by combining a digital twin technology simulation technology. The following is a detailed description.
Fig. 1 is a schematic step diagram of a method for handling a rail transit task based on multi-data source processing according to an embodiment of the present invention, which may include the following steps:
s110: extracting key semantics in the task, and carrying out association expansion on the key semantics according to different semantic relations to obtain association semantics.
In one embodiment of the present invention, as shown in fig. 2, the overall flow of the scheme extracts key semantics in the task, and performs association expansion on the key semantics according to different semantic relationships to obtain association semantics, which specifically includes: determining a data set included in the task, the data set including text data; extracting key semantics contained in the text data by intercepting key words or extracting machine learning features; and determining different semantic relations through a semantic information association dictionary, and carrying out association expansion on key semantics according to the different semantic relations.
Further, extracting key semantics in the task, carrying out association subdivision on the key semantics according to different semantic relations, wherein the specific relations comprise:
causal relationships, representing that generating semantic A occurs to trigger semantic B;
sequential relation, meaning that semantic A is generated according to normal theory and sequential semantic B;
concurrent relationship, meaning that semantic A is generated while semantic B is generated;
containing relationships, meaning that semantic A includes semantic B, semantic C, etc.
Further, for a given track traffic task scene, key semantics contained in the task are extracted by means of keyword interception or machine learning feature extraction.
For example, given the task of "ensuring operational safety in severe weather", the extracted keywords "severe weather", "operation", "safety" are extracted by intercepting the keywords or a machine learning semantic extraction method.
Specifically, according to the extracted key semantics, expanding according to different association relations, and finding out related semantic information through realizing a constructed track traffic semantic information association dictionary.
For example, semantic information related to "bad weather" is storm, rain, snow weather, geography, geological disasters, etc.; semantic information related to operation includes driving schedule, train safe driving, large passenger flow event and the like; the semantic information related to the safety is 'passenger abnormal behavior detection', 'escalator abnormal scene detection', and the like.
S120: and acquiring the multi-source data sets associated with the associated semantics, calculating the association metric values among the multi-source data sets, and screening the multi-source data of the multi-semantics according to the association metric values.
Specifically, according to the expanded association semantics, a multi-source data set associated with the multi-source data set is mined, wherein the multi-source data set comprises different source data such as space-time basic data, internet-of-things sensing data, business application data, operation evaluation data and the like, and the different source data comprises structured data, unstructured data and the like.
For example, storm weather may include wind speed level records over a period of time at different time intervals, may include information data about the storm collected by different devices inductively, and may include pre-warning data given by a monitoring pre-warning system.
The found multi-source data set is used for determining the association degree between tasks and data and between the tasks and the data through an association measurement algorithm, such as an Apriori algorithm, and the data with different sources and different formats are screened out through comparison of a preset threshold value and an association measurement value.
In one embodiment of the present invention, calculating a correlation metric value between multiple source data sets, and screening multiple source data of multiple semantics according to the correlation metric value, specifically including: determining a preset minimum support degree; the support degree is the frequency of occurrence of an item set in a multi-source data set, each row of records in the multi-source data set corresponds to a transaction, elements in each transaction are called items, the item set is a set containing one or more items, and if the item set contains k items, the item set is called a k item set; s1, scanning a multi-source data set to obtain a first candidate data item set, wherein the first candidate data item set is a 1 item set; screening the first candidate data item set to obtain a frequent 1 item set meeting the minimum support; s2, scanning the multi-source data set, and determining a 2-item set containing frequent 1-item sets as a second candidate data item set; screening the second candidate data item set to obtain a frequent 2 item set meeting the minimum support degree; circularly scanning the multi-source data set according to the scanning steps S1-S2 until a frequent n-item set is obtained; wherein the frequent n+1 item set satisfying the minimum support cannot be regenerated from the frequent n item set.
In particular, multi-source datasets with respect to semantics represent data associations in different directions, enabling the effectiveness of subsequent analysis to be increased to some extent. It is therefore necessary to screen out multi-source data that is closely related to the task.
As shown in fig. 3, which is a multi-source data aggregation flow chart, firstly, by scanning a multi-semantic multi-source data set mined in advance, calculating the support degree of each candidate data item in the multi-source data set in a history record of a data source to which the candidate data item belongs, and then generating a frequent 1 item set L1 based on a preset minimum support degree; then based on the L1 and the data in the multi-source data set, generating a frequent 2 item set L2 meeting the preset minimum support and minimum confidence; then, the operation is circulated, a frequent n item set is generated automatically, the frequent n item set cannot be regenerated into an (n+1) item set meeting the minimum support degree, and finally multi-source data closely related to the task is determined.
The support degree refers to the number of occurrence of a transaction of a certain item set containing A and B and the percentage of all transactions in the data set, and is expressed as S (AB) =support_count (AB)/B=P (AB); confidence refers to the percentage of the set containing a that also contains B, denoted C (AB) =support_count (AB)/support_count (a) =p (b|a).
S130: based on the multi-source data, a semantic data association structure tree is constructed according to the association metric value.
In one embodiment of the present invention, the construction of the semantic data association structure tree according to the association metric value specifically includes: the association metric includes a support and a confidence, the confidence being a ratio of the number of transactions comprising the item set { Y, X } to the number of transactions comprising the item set { Y } or the item set { X }; constructing a semantic data association structure tree according to the support degree and the confidence degree; the semantic data association structure tree comprises a semantic aggregation node layer and a data operation node layer; the semantic aggregation node layer comprises semantic information nodes corresponding to tasks, and the relation among the semantic information nodes corresponds to the actual application relation; the data manipulation node layer includes one or more data manipulation nodes associated with tasks and corresponding semantics.
Further, a semantic data association structure tree is constructed according to the association metric values between tasks and data and between data and data. A schematic diagram of the construction of a semantic data structure tree is shown in fig. 4. The semantic data association structure tree includes a semantic aggregation node layer and a data manipulation node layer. The semantic aggregation node layer comprises semantic information nodes corresponding to task association, and the relation among the semantic information nodes corresponds to the actual application relation. The data manipulation node layer includes one or more data manipulation nodes associated with tasks and corresponding semantics. All nodes are associated with tasks and semantics and can correspond to operations in the actual application.
Specifically, according to the screened multi-semantic multi-source data, a semantic data association structure tree is constructed by using the support and the confidence.
For example, the task nodes ensure operation safety in severe weather, the first layer comprises weather such as "strong wind", "heavy rain", "heavy snow", "debris flow", "collapse", and the second layer comprises weather such as "wind level", "wind speed", "direction", "duration", and speed of vehicle running in different time periods, and the complete semantic data association structure tree is finally constructed according to the screened data and the calculated support and confidence of each set.
S140: and dividing task grades according to the associated semantics, and determining a treatment decision scheme of the corresponding grade according to the task grades.
Further, according to the key semantics and the associated semantics extracted from the task, the task grades are divided, and corresponding treatment decisions are given according to expert experience of the corresponding grade and the event processing library.
Specifically, aiming at the mined key semantics and associated semantics, event handling is divided into different grades, and handling flows and expert handling experiences in experience libraries of different grades are given.
For example, the severity of "strong wind" is divided into one, two and three levels, and the three levels are the most serious, and correspond to different devices and data under the track traffic task scene and different disposal modes respectively. For example, the bridge vibration frequency obtained by the sensor and other equipment under the primary high wind is small, the vehicle speed is high, the passenger flow density in the vehicle body is high, and the bridge vibration frequency obtained by the sensor and other equipment under the tertiary high wind is large, the vehicle speed is low, and the passenger flow density in the vehicle body is low.
S150: and simulating according to the semantic data association structure tree and the treatment decision scheme by a digital twin simulation technology to simulate tasks, and determining an optimal treatment decision scheme according to simulation results.
In one embodiment of the invention, the digital twin simulation technology is used for simulation according to the semantic data association structure tree and the treatment decision, and the method specifically comprises the following steps: the task is a rail traffic task, and the treatment decision comprises a treatment flow in an experience library and expert treatment experience; acquiring multidirectional operation data of a track traffic task, and constructing a digital twin model according to the multidirectional operation data; based on the digital twin model, according to multi-azimuth operation data, treatment flow, expert treatment experience and aggregated semantics and data obtained through semantic data association structure tree, performing simulation on a task treatment decision scheme of a current task scene of the rail transit task.
Specifically, a digital twin model is built by combining multidirectional operation data of rail transit, the operation states and data interaction conditions of various devices and infrastructures under the rail transit operation field are simulated by utilizing a multi-source data experimental simulation model and field collected data, and specific details and technologies of model construction can be realized by adopting the existing digital twin technology.
In one embodiment of the present invention, determining an optimal treatment decision scheme according to a simulation result specifically includes: determining a measurement dimension of a treatment decision scheme, wherein the measurement dimension comprises operation time, economic benefit and safety performance; determining the weight of each measuring dimension, wherein the sum of the weights of the measuring dimensions is equal to 1; calculating the priority of each treatment decision scheme according to the weight of each measurement dimension; and determining an optimal treatment decision scheme according to the priority.
Further, the aggregated data in the constructed semantic data association structure tree is combined, a corresponding disposal decision scheme is given according to expert experience and an event processing library, the current task scene is simulated on line by combining digital twin simulation technology and digital twin history data corresponding to multidirectional operation data, the semantic data association structure tree and the disposal decision scheme are simulated, and the priority evaluation formula of the construction scheme is measured from three angles of operation time, economic benefit and safety performance according to a simulation result, and is as follows:
score=αs (operating time) +βs (economic benefit) +γs (safety performance)
And quickly determining the most suitable treatment decision scheme according to the priority evaluation formula.
The operation time, economic benefit and safety performance are normalized, and alpha, beta and gamma are parameter values obtained through experimental verification, wherein alpha+beta+gamma=1.
In one embodiment of the invention, the data of auxiliary digital twinning of various sensors, controllers and the like arranged on the task site can be given corresponding measures in preference to manual work, so that the rapid execution of the task and the accuracy of the task execution can be ensured.
According to the finally obtained proper treatment decision, the task site is controlled by the sensor, the controller and other components preferentially, the staff quickly performs on-site execution according to the decision, and the quick response to the task and the accuracy of the task execution are ensured by the sensor control and the manual dual-response mechanism.
For example, in severe weather conditions, passenger evacuation is first guided by controlling the escalator, roller shutter door, broadcast, etc. in accordance with the final disposal decision, avoiding panic. Meanwhile, workers are arranged to arrive at the scene, problems are checked, passenger flow is evacuated, and the task is guaranteed to be completed rapidly and accurately in a combined mode.
The method for processing the track traffic task based on the multi-data source processing provided by the embodiment of the invention is based on the same thought of the invention, and the embodiment of the invention also provides a corresponding device for processing the track traffic task based on the multi-data source processing, as shown in fig. 5.
The semantic information acquisition module 510 is configured to extract key semantics in a task, and perform association expansion on the key semantics according to different semantic relationships to obtain associated semantics; the screening module 520 is configured to obtain a multi-source data set associated with the associated semantics, calculate an association metric value between the multi-source data sets, and screen multi-source data of the multi-semantics according to the association metric value; a semantic data association structure tree construction module 530, configured to construct a semantic data association structure tree according to the association metric based on the multi-source data; the task grade classification module 540 is configured to classify task grades according to the associated semantics, and determine a treatment decision scheme of a corresponding grade according to the task grades; the simulation module 550 is configured to perform simulation according to the semantic data association structure tree and the treatment decision scheme by using a digital twin simulation technology, so as to simulate a task, and determine an optimal treatment decision scheme according to a simulation result.
The embodiment of the invention also provides corresponding track traffic task treatment equipment based on multi-data source processing, which comprises the following steps:
at least one processor 610, a communication interface (Communications Interface) 620, a memory 630, and a communication bus 640; wherein processor 640, communication interface 620, memory 630 communicate with each other via communication bus 640; processor 640 may invoke logic instructions stored in memory 630 to cause at least one processor 610 to perform:
extracting key semantics in the task, and performing association expansion on the key semantics according to different semantic relations to obtain association semantics; acquiring multi-source data sets associated with the associated semantics, calculating association metric values among the multi-source data sets, and screening multi-source data of the multi-semantics according to the association metric values; based on the multi-source data, constructing a semantic data association structure tree according to the association metric value; dividing task grades according to the associated semantics, and determining a treatment decision scheme of the corresponding grade according to the task grades; and simulating according to the semantic data association structure tree and the treatment decision scheme by a digital twin simulation technology to simulate tasks, and determining an optimal treatment decision scheme according to simulation results.
Based on the same thought, some embodiments of the present invention also provide a medium corresponding to the above method.
Some embodiments of the invention provide a storage medium storing computer executable instructions for execution by a processor to perform the steps of:
extracting key semantics in the task, and performing association expansion on the key semantics according to different semantic relations to obtain association semantics; acquiring multi-source data sets associated with the associated semantics, calculating association metric values among the multi-source data sets, and screening multi-source data of the multi-semantics according to the association metric values; based on the multi-source data, constructing a semantic data association structure tree according to the association metric value; dividing task grades according to the associated semantics, and determining a treatment decision scheme of the corresponding grade according to the task grades; and simulating according to the semantic data association structure tree and the treatment decision scheme by a digital twin simulation technology to simulate tasks, and determining an optimal treatment decision scheme according to simulation results.
The embodiments of the present invention are described in a progressive manner, and the same and similar parts of the embodiments are all referred to each other, and each embodiment is mainly described in the differences from the other embodiments. In particular, for the apparatus and medium embodiments, the description is relatively simple, as it is substantially similar to the method embodiments, with reference to the section of the method embodiments being relevant.
The devices and media provided in the embodiments of the present invention are in one-to-one correspondence with the methods, so that the devices and media also have similar beneficial technical effects as the corresponding methods, and since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media are not repeated here.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process article or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process article or method. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process method article or method comprising the element.
The foregoing is merely exemplary of the present invention and is not intended to limit the present invention. While the invention has been described in detail in the foregoing general description and with reference to specific embodiments thereof, it will be apparent to one skilled in the art that modifications and improvements can be made thereto. Accordingly, such modifications or improvements may be made without departing from the spirit of the invention and are intended to be within the scope of the invention as claimed.
Claims (10)
1. A method for handling a rail transit mission based on multi-data source processing, comprising:
extracting key semantics in a task, and performing association expansion on the key semantics according to different semantic relations to obtain association semantics;
acquiring a multi-source data set associated with the associated semantics, calculating an associated metric value between the multi-source data sets, and screening multi-source data of the multi-semantics according to the associated metric value;
based on the multi-source data, constructing a semantic data association structure tree according to the association metric value;
dividing task grades according to the associated semantics, and determining a treatment decision scheme of a corresponding grade according to the task grades;
and simulating according to the semantic data association structure tree and the treatment decision scheme by a digital twin simulation technology so as to simulate the task, and determining an optimal treatment decision scheme according to a simulation result.
2. The method of claim 1, wherein the extracting key semantics in the task, and performing association expansion on the key semantics according to different semantic relationships, to obtain association semantics, specifically comprises:
determining a dataset included in a task, the dataset including text data;
extracting key semantics contained in the text data by intercepting key words or extracting machine learning features;
and determining different semantic relations through a semantic information association dictionary, and carrying out association expansion on the key semantics according to the different semantic relations.
3. The method according to claim 1, wherein the calculating the correlation metric between the multisource data sets and screening the multisource data of the multisystem according to the correlation metric specifically comprises:
determining a preset minimum support degree;
wherein, the support degree is the frequency of occurrence of an item set in the multi-source data set, each row of records in the multi-source data set corresponds to a transaction, the element in each transaction is called an item, the item set is a set containing one or more items, and if the item set contains k items, the item set is called a k item set;
s1, scanning the multi-source data set to obtain a first candidate data item set, wherein the first candidate data item set is 1 item set;
screening the first candidate data item set to obtain a frequent 1 item set meeting the minimum support;
s2, scanning the multi-source data set, and determining a 2-item set containing the frequent 1-item set as a second candidate data item set;
screening the second candidate data item set to obtain a frequent 2 item set meeting the minimum support;
circularly scanning the multi-source data set according to the scanning steps S1-S2 until a frequent n-item set is obtained;
wherein a frequent n+1 item set satisfying the minimum support cannot be regenerated from the frequent n item set.
4. A method according to claim 3, wherein said constructing a semantic data association structure tree according to said association metric values comprises:
the association metric includes a support and a confidence, the confidence being a ratio of a number of transactions comprising the item set { Y, X } to a number of transactions comprising the item set { Y } or the item set { X };
constructing a semantic data association structure tree according to the support degree and the confidence degree;
the semantic data association structure tree comprises a semantic aggregation node layer and a data operation node layer;
the semantic aggregation node layer comprises semantic information nodes corresponding to tasks, and the relation among the semantic information nodes corresponds to the actual application relation;
the data manipulation node layer includes one or more data manipulation nodes associated with tasks and corresponding semantics.
5. The method according to claim 1, wherein the simulating by digital twin simulation technique according to the semantic data association structure tree and the treatment decision scheme comprises:
the task is a rail transit task, and the treatment decision scheme comprises a treatment flow in an experience library and expert treatment experience;
acquiring multidirectional operation data of a track traffic task, and constructing a digital twin model according to the multidirectional operation data;
based on the digital twin model, according to the multi-azimuth operation data, the disposal flow, the expert disposal experience and the aggregate semantics and data obtained through the semantic data association structure tree, performing simulation on a task disposal decision scheme of the current task scene of the track traffic task.
6. The method according to claim 1, wherein the determining an optimal treatment decision scheme according to the simulation result, in particular comprises:
determining a measurement dimension of a treatment decision scheme, wherein the measurement dimension comprises operation time, economic benefit and safety performance;
determining the weight of each measuring dimension, wherein the sum of the weights of the measuring dimensions is equal to 1;
calculating the priority of each treatment decision scheme according to the weight of each measurement dimension;
and determining an optimal treatment decision scheme according to the priority.
7. The method of claim 1, wherein the semantic relationships comprise causal relationships, sequential relationships, concurrency relationships, and inclusion relationships;
the multi-source data set comprises space-time basic data, internet of things perception data, business application data and operation evaluation data.
8. A track traffic task handling device based on multi-data source processing, comprising:
the semantic information acquisition module is used for extracting key semantics in the task, and carrying out association expansion on the key semantics according to different semantic relations to obtain association semantics;
the screening module is used for acquiring the multi-source data sets associated with the associated semantics, calculating the association metric values among the multi-source data sets, and screening the multi-source data of the multi-semantics according to the association metric values;
the semantic data association structure tree construction module is used for constructing a semantic data association structure tree according to the association metric value based on the multi-source data;
the task grade classification module is used for classifying task grades according to the associated semantics and determining a treatment decision scheme of a corresponding grade according to the task grades;
and the simulation module is used for simulating the task according to the semantic data association structure tree and the treatment decision scheme by a digital twin simulation technology, and determining an optimal treatment decision scheme according to a simulation result.
9. A track traffic task handling device based on multi-data source processing, comprising:
at least one processor; the method comprises the steps of,
a memory communicatively coupled to the at least one processor via a bus; wherein,,
the memory stores instructions executable by the at least one processor to implement:
extracting key semantics in a task, and performing association expansion on the key semantics according to different semantic relations to obtain association semantics;
acquiring a multi-source data set associated with the associated semantics, calculating an associated metric value between the multi-source data sets, and screening multi-source data of the multi-semantics according to the associated metric value;
based on the multi-source data, constructing a semantic data association structure tree according to the association metric value;
dividing task grades according to the associated semantics, and determining a treatment decision scheme of a corresponding grade according to the task grades;
and simulating according to the semantic data association structure tree and the treatment decision scheme by a digital twin simulation technology so as to simulate the task, and determining an optimal treatment decision scheme according to a simulation result.
10. A non-volatile storage medium storing computer executable instructions, wherein the computer executable instructions are executed by a processor to perform the steps of:
extracting key semantics in a task, and performing association expansion on the key semantics according to different semantic relations to obtain association semantics;
acquiring a multi-source data set associated with the associated semantics, calculating an associated metric value between the multi-source data sets, and screening multi-source data of the multi-semantics according to the associated metric value;
based on the multi-source data, constructing a semantic data association structure tree according to the association metric value;
dividing task grades according to the associated semantics, and determining a treatment decision scheme of a corresponding grade according to the task grades;
and simulating according to the semantic data association structure tree and the treatment decision scheme by a digital twin simulation technology so as to simulate the task, and determining an optimal treatment decision scheme according to a simulation result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310289185.1A CN116502904A (en) | 2023-03-22 | 2023-03-22 | Rail transit task handling method and device based on multi-data source processing |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310289185.1A CN116502904A (en) | 2023-03-22 | 2023-03-22 | Rail transit task handling method and device based on multi-data source processing |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116502904A true CN116502904A (en) | 2023-07-28 |
Family
ID=87315704
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310289185.1A Pending CN116502904A (en) | 2023-03-22 | 2023-03-22 | Rail transit task handling method and device based on multi-data source processing |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116502904A (en) |
-
2023
- 2023-03-22 CN CN202310289185.1A patent/CN116502904A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11852778B2 (en) | Static engine and neural network for a cognitive reservoir system | |
EP3889652A1 (en) | Performance-level seismic motion hazard analysis method based on three-layer dataset neural network | |
CN109508827B (en) | Drilling accident early warning method based on time recursion neural network | |
Sajedi et al. | A data‐driven framework for near real‐time and robust damage diagnosis of building structures | |
CN102567464B (en) | Based on the knowledge resource method for organizing of expansion thematic map | |
Yu et al. | Rapid visual screening of soft-story buildings from street view images using deep learning classification | |
CN111078868A (en) | Knowledge graph analysis-based equipment test system planning decision method and system | |
CN111159249A (en) | Target identification method, device and system based on knowledge graph and storage medium | |
CN113704956A (en) | Urban road online microscopic simulation method and system based on digital twin technology | |
CN114201920A (en) | Laser cutting numerical control system fault diagnosis method based on digital twinning and deep transfer learning | |
CN113688169A (en) | Mine potential safety hazard identification and early warning system based on big data analysis | |
Mousavi et al. | BIM and machine learning in seismic damage prediction for non-structural exterior infill walls | |
Lei et al. | Prediction of PM2. 5 concentration considering temporal and spatial features: A case study of Fushun, Liaoning Province | |
US20230141334A1 (en) | Systems and methods of modeling geological facies for well development | |
Karthikeyan | Prediction of climate change using SVM and Naïve Bayes machine learning algorithms | |
CN116502904A (en) | Rail transit task handling method and device based on multi-data source processing | |
Elenas et al. | Classification of seismic damages in buildings using fuzzy logic procedures | |
Zhihan et al. | Complexity problems handled by big data technology | |
CN111221704B (en) | Method and system for determining running state of office management application system | |
Xiao et al. | New Risk Control Technology for Port Channel Construction Operations Based on BIM | |
Mahsuli | Resilience of civil infrastructure by optimal risk mitigation | |
KR20210107402A (en) | Deep learning based rainwater pumping station simulation operation program | |
AU2021100003A4 (en) | A deep transportation model to predict the human mobility for autonomous vehicle | |
Sun et al. | Research on bridge structural damage identification | |
Li | Construction and Verification of Academic Performance Early Warning Model based on PSO-XGBoost Algorithm |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |