CN115129897A

CN115129897A - Method, apparatus, device and medium for analyzing perceptual data using a knowledge graph

Info

Publication number: CN115129897A
Application number: CN202211050212.1A
Authority: CN
Inventors: 李瑾; 肖益; 李宝东; 刘韶辉; 张菁; 贾若; 穆显显; 郭妮妮
Original assignee: Taiji Computer Corp Ltd
Current assignee: Taiji Computer Corp Ltd
Priority date: 2022-08-31
Filing date: 2022-08-31
Publication date: 2022-09-30
Anticipated expiration: 2042-08-31
Also published as: CN115129897B

Abstract

The invention provides a method, a device, equipment and a medium for analyzing perception data by using a knowledge graph, wherein the method comprises the following steps: acquiring perception data, and analyzing the perception data to obtain clue information and/or event information; according to a preset conversion rule, converting the clue information and/or the event information to obtain triple data, and storing the triple data into a knowledge graph; and respectively creating a mapping according to the triple data obtained after the conversion of each clue information and/or event information, and performing association analysis in the knowledge graph by combining each mapping and the clue information and/or event information to obtain an analysis result. The method creates mapping for the triple of the perception data, further forms the map on the basis of the mapping relation in the knowledge map, displays the analysis of the perception data in a visual data mode, is favorable for making correct decision analysis, and can obtain clue events with great value from the analysis result.

Description

Method, apparatus, device and medium for analyzing perceptual data using a knowledge graph

Technical Field

The invention relates to the technical field of computer information processing, in particular to a method, a device, equipment and a medium for analyzing perception data by using a knowledge graph.

Background

With the generation of mass data, the knowledge extraction is carried out from mass data, a large-scale domain knowledge graph is constructed, the requirements of various scenes such as intelligent question answering, intelligent recommendation, graph relation analysis, knowledge construction management, knowledge semantic retrieval, intelligent text extraction, geospatial analysis and the like are met, and the unified knowledge graph capability is required to be provided. The concept of Knowledge Graph (Knowledge Graph) was formally proposed in 2012 by ***, aiming to realize a more intelligent search engine, and started to be popularized in academia and industry after 2013, and playing an important role in applications such as intelligent question and answer, intelligence analysis, anti-fraud and the like.

A knowledge graph is essentially a knowledge base called semantic network (semantic network), i.e. a knowledge base with a directed graph structure, where nodes of the graph represent entities (entries) or concepts (concepts), and edges of the graph represent various semantic relationships between entities/concepts, such as similarity between two entities.

At present, digital government affairs are in a development stage, but the types of data involved in digital government affairs are various, and although there are methods for classifying and grading the data, in some special scenarios, such as prevention and control data of a coastline, monitoring data of a port, etc., how to analyze the perception data to obtain useful clues and perform further analysis, there is no corresponding analysis method or device in the industry.

Along with the continuous improvement of the knowledge of the basic level user on the information system, the big data retrieval application has new interpretation and understanding. The traditional clue search is only the retrieval of data resources, the retrieval result is also only the display of a resource list, the problems of poor search intention understanding capability, fragmentation of the search result, weak relevance and the like are increasingly highlighted, the requirements of current basic level users cannot be met, and the analysis requirements of the artificial intelligence era on big data cannot be supported.

Therefore, if knowledge-graph techniques are introduced or combined during the development of digital government affairs to promote the analysis of clue data, the problem of fragmentation of data analysis in a specific scene may be solved.

The above is only for the purpose of assisting understanding of the technical aspects of the present invention, and does not represent an admission that the above is prior art.

Disclosure of Invention

In view of the above, the present invention is directed to a method, an apparatus, a device and a medium for analyzing perceptual data using a knowledge-graph.

In view of the above, the present invention provides a method for analyzing perceptual data using a knowledge-graph, the method comprising:

acquiring perception data, and analyzing the perception data to obtain clue information and/or event information;

according to a preset conversion rule, converting the clue information and/or the event information to obtain triple data, and storing the triple data into a knowledge graph;

and respectively creating a mapping according to the triple data obtained after the conversion of each clue information and/or event information, and performing association analysis in the knowledge graph by combining each mapping and the clue information and/or event information to obtain an analysis result.

With reference to the foregoing description, in another possible implementation manner of the embodiment of the present invention, the converting, according to a preset conversion rule, the cue information and/or the event information to obtain triple data, and storing the triple data in a knowledge graph includes:

analyzing the clue information and the event information to obtain relationship information, wherein the relationship information comprises: relationship information between the cue information and the cue, relationship information between the event information and the event information, and relationship information between the cue information and the event information;

and converting the relationship information, the clue information and the event information into triple data according to a preset conversion rule and storing the triple data into a knowledge graph.

In combination with the above description, in another possible implementation manner of the example of the present invention, the creating a mapping according to the triplet data obtained after the conversion of each piece of cue information and/or event information, and performing association analysis in the knowledge graph by combining each mapping, the cue information, and/or event information to obtain an analysis result further includes:

and adding the relationship information into the correlation analysis process of the knowledge graph, and performing mining analysis by combining the relationship information, the clue information and the attribute values of the event information to obtain a mining analysis result.

In another possible implementation manner of the example of the present invention, in combination with the above description, the method further includes:

calculating the weight of entity information in each triple data by an information entropy weighting method, and determining a clue label of the triple data according to the priority of the weight value sorting;

and taking the clue tag as a mapping name created by the triple data, and calling the corresponding mapping according to the clue tag.

acquiring a plurality of attribute information of entities related to the perception data;

adding each attribute information to the entity portrait related to the perception data;

and performing association analysis on the entity portrait and each mapping in the knowledge graph to obtain an analysis result.

constructing an association graph of the perception data according to each mapping;

judging whether abnormal clue information and/or event information exists in the association graph;

when the side relation coefficient quantity formed by the clue information and/or the event information is larger than or equal to an abnormal threshold value, marking the corresponding clue information and/or the event information as an abnormal clue event;

further mining and analyzing the abnormal clue events to obtain mining and analyzing results of the abnormal clue events;

and when the side relation coefficient quantity formed by the clue information and/or the event information is smaller than an abnormal threshold value, combing the development context of the clue information and/or the event information to obtain a combing analysis result.

In another possible implementation manner of the example of the present invention, the performing, in combination with each of the mappings, association analysis in the knowledge graph includes:

any one or a combination of two or more of association search, association map analysis, and joining map analysis.

In a second aspect, the present invention also provides an apparatus for analyzing perceptual data using a knowledge-graph, the apparatus comprising:

the analysis module is used for acquiring perception data and analyzing the perception data to obtain clue information and/or event information;

the conversion module is used for converting the clue information and/or the event information according to a preset conversion rule to obtain triple data and storing the triple data into a knowledge graph;

and the analysis module is used for respectively creating mapping according to the triple data obtained after the conversion of each clue information and/or event information, and performing association analysis in the knowledge graph by combining each mapping, the clue information and/or the event information to obtain an analysis result.

In a third aspect, the present invention also provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-mentioned method for analyzing perceptual data using a knowledge graph.

In a fourth aspect, the present invention also provides a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the above-described method for analyzing perceptual data using a knowledge-graph.

From the above, it can be seen that the method, device, equipment and medium for analyzing sensing data by using a knowledge graph provided by the invention analyze sensing data into clue information and/or event information which can be identified by the knowledge graph, and further convert the sensing data into ternary data which is easy to store, and further analyze the mapping relation in a knowledge graph framework by creating a mapping mode, so that the analysis of the sensing data can be displayed in a visual data mode, thereby being beneficial to making correct decision analysis, and clue events with great value can be obtained from an analysis result.

Drawings

In order to more clearly illustrate the technical solutions of the present invention or related technologies, the drawings used in the description of the embodiments or related technologies will be briefly introduced below, it is obvious that the drawings in the description below are only embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.

FIG. 1 is a schematic diagram of a basic flow chart of a method for analyzing perceptual data using a knowledge-graph according to an embodiment of the present invention;

FIG. 2 is a diagram illustrating triple data field attribute selection according to an embodiment of the present invention;

FIG. 3 is a diagram illustrating the basic building blocks of a map created by triple data according to an embodiment of the present invention;

FIG. 4 is a diagram illustrating the composition of a mapping into which perceptual data is transformed, in accordance with an embodiment of the present invention;

FIG. 5 is a diagram illustrating an example correlation analysis according to an embodiment of the present invention;

FIG. 6 is a diagram illustrating changes in case correlation analysis according to an embodiment of the present invention;

FIG. 7 is a basic flowchart illustrating the exception event determination according to an embodiment of the present invention;

FIG. 8 is a schematic diagram of the basic structure of an apparatus for analyzing perceptual data using a knowledge-graph according to an embodiment of the present invention;

FIG. 9 is a diagram of an electronic device implementing a method for analyzing perceptual data using a knowledge-graph 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 is further described in detail with reference to the following embodiments and the accompanying drawings.

It should be noted that technical terms or scientific terms used in the embodiments of the present invention should have a general meaning as understood by those having ordinary skill in the art to which the present invention belongs, unless otherwise defined. The use of "first," "second," and similar language in the embodiments of the present invention does not denote any order, quantity, or importance, but rather the terms "first," "second," and similar language are used to distinguish one element from another. The word "comprising" or "comprises", and the like, means that the element or item listed before the word covers the element or item listed after the word and its equivalents, but does not exclude other elements or items. The terms "connected" or "coupled" and the like are not restricted to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "upper", "lower", "left", "right", and the like are used merely to indicate relative positional relationships, and when the absolute position of the object being described is changed, the relative positional relationships may also be changed accordingly.

In the current mode, a graph database management system is usually adopted for pictures or videos sensed by sensing equipment, and a data model generally adopts the form of an attribute graph, but the storage of the structural form causes the global operation of the graph to become lower and lower along with the upgrading of the sensing equipment, the increasing of the content of sensing events or pictures and the increasing of the volume, the query language adopted by the graph is less, developers face the sensing event query in the form of unsuccessfully and the query efficiency after the query is started is lower, and the disadvantage is particularly obvious when the graph database management system is applied to a social management information platform.

The invention relates to a sensing data, a device, equipment and a medium which are analyzed by using a knowledge graph, which are mainly applied to a scene of sensing and analyzing related information obtained by a defense and control circle in an island, a port and a shore line, and the basic idea is as follows: suspicious information is obtained from sensing equipment related to the island, the port and the shoreline defense and control circle, pictures or videos are stored, the stored pictures or videos are converted based on a preset rule to obtain triple data, correlation analysis, thermodynamic diagram analysis or map analysis are carried out on the obtained triple data through a knowledge graph, and an analysis result is obtained, so that the sensing events can be analyzed more accurately and efficiently, and the sensing events can be displayed more intuitively.

The invention utilizes knowledge map to analyze sensing data, device, equipment and medium, can be applied to a social management information platform, or can be used as a subsystem of the social information management platform, information intercommunication authority can be set among the subsystems of the social information management platform to realize information transmission and sharing, the social management information platform is a comprehensive platform for digital government affairs, and can connect business systems for various auxiliary social management implementation of government affairs, such as port office and the like, and certain basic hardware is set in each business system and the like according to requirements to obtain corresponding information, and the expected result is obtained after the information is collected or uploaded and processed according to corresponding processing strategies.

The embodiment of the present invention may be applied to a case with a knowledge-graph analysis apparatus for performing cue analysis, where the apparatus may be implemented by software and/or hardware, and may be generally integrated in a server, or controlled by a central control module of a terminal, as shown in fig. 1, which is a basic flow diagram of the method for performing cue event analysis by using a knowledge-graph of the present invention, and the method specifically includes the following steps:

in step 110, obtaining perception data, and analyzing the perception data to obtain clue information and/or event information;

in one implementation of the exemplary embodiments of the present invention, the perception data may be obtained through the following channels:

the monitoring equipment is arranged on one or a plurality of shoreline control rings;

monitoring equipment installed on the signal tower;

shooting equipment arranged at a port;

carrying out satellite remote sensing imaging;

……

in a feasible implementation manner of the exemplary embodiment of the present invention, the perception data may also be obtained from other scenes, for example, when analyzing a clue event of the road information, the perception data may be obtained from a shooting device arranged on the road, and when performing control and judgment on an epidemic person in a commercial facility related to an epidemic situation, the perception data may be obtained through a monitoring device in the commercial facility, or a code scanning device arranged at an entrance, and the like.

The sensing data may be electronic information in various formats such as a shot picture, a video, and the like, or may be structured data information directly obtained through other devices, for example, basic information of a user person stored in a document or table structure.

Parsing the perceptual event, including:

analyzing the information such as the shot pictures, videos and video records, for example, carrying out image recognition and/or combining text recognition;

in an implementation manner of the exemplary embodiment of the present invention, the sensing data may be obtained by taking a picture, for example, a monitoring/sensing device installed in a certain port may obtain and store corresponding information according to analysis of the sensing data when sensing that a corresponding event occurs, and generally needs to perform corresponding preprocessing to enable the information to meet a requirement for being usable, for example, when the sensing data is downloaded cue document data, it needs to extract keywords, authors, organizations, dates, titles, and the like from the cue document data, and remove stop words, repeated items, and the like.

In one implementation of an exemplary embodiment of the invention, in particular:

when a sensing device monitors that a ship leaves the port, the ship leaves the port and is called a sensing event, other sensing devices capable of maximally shooting pictures of a ship identification number or an IMO number of the ship can be called to shoot according to a shooting cooperative mechanism of the sensing device so as to obtain pictures which can be used for later prejudgment or early warning, wherein the pictures are suitable for obtaining a large amount of information related to the ship after picture identification, for example, the shot pictures can obtain a ship identification number, an IMO number or a calling code and the like, a ship identification number (a unique code for permanently identifying the ship, generally consisting of English letters and a plurality of Arabic numbers) or a unique number of the IMO (international maritime organization) (including an IMO identification and seven Arabic numbers) or a calling code (a unique wireless communication code for calling the ship by the IMO), these identification numbers are unique identification marks of the ship, identification marks of persons can be identified by face matching when the object to be photographed is a person, and the like.

Then, at this time, parsing the sensing data includes:

and analyzing the perception picture, and acquiring departure time, arrival time, airline flight number, airline flight date, affiliated ship company, passenger entry and exit record, departure station, ship name and the like of the ship from related subsystems of the social management information platform at the upper stage through the ship identification number obtained by analysis.

The information obtained by analysis, such as the ship identification number, the name of the ship, the affiliated ship company and the like, is clue information; event information is event information such as departure time, arrival time, airline flight number, airline flight date, etc., and event information is generally triggered according to behavior of clue information, for example, when a ship in IMO1234567 leaves a port, event information such as "departure time" and "airline flight number" is triggered.

It can be understood that the above steps of the present invention can simultaneously acquire and analyze a plurality of pieces of sensing data, and perform parallel processing according to the computing power of the corresponding computer device or server.

In step 120, according to a preset conversion rule, converting the cue information and/or the event information to obtain triple data, and storing the triple data into a knowledge graph;

and the preset conversion rule is used for converting the clue information and/or the event information obtained by analysis into ternary group data which can be stored in the knowledge graph.

Specifically, the preset conversion rule is used for defining entity types and information of the ternary group of data, and the information of the ternary group of data includes an association relationship between the entity types and attributes and attribute values corresponding to the entity types. The incidence relation between the entity types corresponds to the ternary group data in the form of (entity 1-relation-entity 2) and is used for respectively defining the entity 1 and the entity 2 and the relation between the entity 1 and the entity 2; the attributes and attribute values corresponding to each entity type correspond to the form of triple data (entity-attribute values) that define the entity, the attribute, and the corresponding attribute value.

More specifically, when the IMO number of the ship is taken as the tag type clue information, corresponding to the acquired sensing data, the IMO number is taken as an entity, other clue information and/or event information obtained by analyzing the IMO number can be stored in a field and attribute mode, the stored triple data is combined with the triple data converted from a certain sensing data shown in fig. 2, some attributes of the obtained clue information are shown, the attributes of the clue information can be modified through field storage of the clue information, so that the corresponding attributes of the clue information or event information under different types of different scenes can be modified, for example, the field "qfsj" represents "departure time", "hkgs" represents "affiliated ship company", the field "ddsj" represents "arrival time", the field "hbh" represents "airline flight number", the field "qfs" represents "departure port name", and the like, and the special symbols in the diagram are respectively represented as "set clue tag", set clue, tag, and/event number, and the sequence from left to right is respectively, "favorites", "deletes", and "splits", each of which may represent some modification operations to an attribute of an entity or relationship in the triple data, respectively.

In an optional implementation manner of the exemplary embodiment of the present invention, the preset conversion rule may be implemented in a manner of generating a template by a custom rule, and the relationship between the cue information and/or the event information obtained by analyzing the same type of sensing data and the entity name, the attribute, and the attribute value that may be related to the cue information and/or the event information is input into the custom rule generation template, so that automatic analysis may be completed, and the corresponding conversion rule may be obtained.

In another alternative embodiment, the acquired cue information and/or event information may also be written into a preset conversion rule by a professional according to a requirement, so as to provide for further conversion and analysis of the same type of perception data.

In the embodiment of the present application, a generation manner of the conversion rule related to the triple data is not specifically limited.

The type of the database adopted by the knowledge graph is not limited, and in the implementation manner of the exemplary embodiment of the invention, the setting of the universal interface can be adopted when the social management information platform is accessed, so that the triple data obtained after the sensing data conversion can be stored in the knowledge graph based on various types of databases, and interfaces do not need to be respectively set for each type of database, so that the efficiency of obtaining the analysis result is greatly improved when the different types of sensing data are uploaded by each accessed subsystem for analysis.

In step 130, a map is created according to the triple data obtained after each cue information and/or event information is converted, and association analysis is performed in the knowledge graph by combining the maps to obtain an analysis result.

In a feasible implementation manner of the exemplary embodiment of the present invention, when analysis is required, since an original data source is sensing data, it is required to query corresponding cue information and/or event information according to the sensing data, and further create mappings for corresponding triple data respectively, where the mappings may be various relationships between entities, for example:

referring to fig. 3, as a relationship diagram serving as the simplest mapping, when an object to be analyzed is a person, relationship attributes between persons need to be configured as a mapping relationship, and the data representation in the mapping may be a relationship primary key, a relationship type, a relationship field, and the like, and the relationship field may be reusable, when a relationship field already stores various relationship attribute values in a data table, the relationship field may be directly configured as a link field, and when the link field is directly used in other mapping relationships, the relationship between persons may be represented by the relationship field, and a special symbol in the diagram indicates that the part of content is selectable.

When analyzing one or more groups of sensing data, the mapping of the object may include many groups, for example, the mapping diagram shown in fig. 4 obtained by analyzing and converting one sensing data may be a mapping relationship obtained from one sensing data, and on the basis that the basic mapping has been clearly described, the mapping relationships in fig. 4 are not described again.

Performing association analysis in the knowledge graph in combination with each of the mappings to obtain an analysis result, specifically:

fig. 5 is a schematic diagram of association analysis, which shows an analysis result of association analysis using mapping, but of course, the result in the diagram may be further analyzed again on the basis of the analysis result, in this process, it is necessary to:

the first acquired perception data is summarized and transmitted text data, such as: the ship A drives into the port A, the vehicle A goes to relevant personnel on the receiving and delivering ship after the ship A enters the port, the vehicle B goes to the port A to deliver the goods of the ship A, after inquiry, the ship A stops at the island A and is connected with the ship B, the ship B enters the port B, the vehicle C goes to the port B to receive and deliver the relevant personnel, the vehicle C also goes to and fro the port C for multiple times and comes and goes with the warehouse A, and the vehicle B has personnel D.

After analysis, the ships, vehicles, personnel and the like can form clue information, the round trip of the vehicles and ports or ships or warehouses can form event information, and the event information is converted into ternary group data according to a preset conversion rule, wherein the ternary group data can be:

(vessel a, drive-in, port a), (vehicle a, pick-up, vessel a), (vehicle B, pick-up, vessel a), (vessel a, dock, island a) … …

The mapping created by the triple data formed by the above sensing data can be combined with that shown in fig. 4, and each adjacent arrow and entity can form a mapping, which is not shown in a decomposition.

Each mapping can be used for subsequent data analysis in the knowledge-graph.

Each connected body in the map may be used to add or delete a new map, for example, when there is a relationship between the owner Y company of one of the ships B and the owner D, and the Y company is all the persons in the warehouse a at the same time, a new relationship analysis is added to the relationship diagram shown in fig. 5, and the added relationship analysis diagram is shown in fig. 6.

In some possible embodiments of the exemplary embodiments of the present invention, different types of rule templates may be preset for matching during preprocessing of the sensing data, so as to facilitate quick use, for example: ship files, berthing and berthing records, household registration, ship basic information, automatic generation of ship files and the like.

In a feasible implementation manner of the exemplary embodiment of the present invention, the converting, according to a preset conversion rule, the cue information and/or the event information to obtain triple data, and storing the triple data in a knowledge graph, further includes a manner of converting relationship information formed by the cue information and the event information into triple data, and this process includes:

in conjunction with the correlation diagrams shown in fig. 5 and fig. 6, when the ship a stays at the island a and the ship B is docked with the ship a at the island a, the company information of the ship a/B is analyzed, so that the ship a and the ship B belong to the same company X for control, and the obtained relationship information is converted into the triple data (ship a, company, ship B).

The created mapping can be the mapping shown in fig. 5, and the mapping relationship can be used in the above query case, and the effect shown in fig. 6 is also shown.

The knowledge base of the knowledge graph with the larger scale in the traditional mode cannot contain all information, and some entities, categories, attributes or the relationship among the entities, the categories, the attributes or the three are not captured.

In a possible implementation manner of the exemplary embodiment of the present invention, the creating a mapping according to the triplet data obtained after each transformation of the cue information and/or the event information, and performing association analysis in the knowledge graph by combining each mapping, the cue information, and/or the event information to obtain an analysis result further includes:

With reference to the mapping relationships created in fig. 5 and fig. 6, when a plurality of entities include a plurality of mapping relationships, the mapping relationships are added to the analysis process of the original knowledge graph for association analysis, the generated relationship information is further associated with the previous analysis result, so that the association graph changes, and the changed analysis result is the mining analysis result.

According to the method, by adding the relation information, the result obtained when the knowledge graph is used for correlating and analyzing the perception data is further mined, and the analysis result displayed by the knowledge graph is deeper and more approximate to essence.

In one possible implementation of the exemplary embodiment of the present invention, the method further includes:

Calculating the weight of each ternary group of data and the keywords thereof by using an information entropy weighting method, storing the weight into a knowledge graph database, calculating similar ternary group data of each ternary group of data respectively through a ternary similarity formula, carrying out priority ranking according to the similarity, and determining the keywords corresponding to the ternary group of data with the highest priority as clue labels of the ternary group of data, such as: after the calculation, the determined clue label can be 'ship A' and the mapping name can be determined as 'ship A', and in the subsequent analysis process, corresponding ternary group data and mapping created according to the clue label can be called at any time according to the clue label so as to simplify the analysis decision process of the knowledge graph.

adding each attribute information to the entity portrait related to the perception data respectively;

In combination with the above case, one entity related to the sensing data analysis may include "ship a", "ship B", "vehicle a", "vehicle B", "person C", and the like, and the attribute information related to "ship a" is the attribute of the analyzed clue information, such as the control company, the registered place, the ship owner, the co-owner, and the like, to which ship a belongs.

The attribute information is added into the portrait of the ship A, the entity portrait is a user model formed by at least one clue information and/or event information, the user model can be continuously updated and enriched along with the continuous change or accumulation of clue events, the process of adding the attribute information enriches the entity portrait, and in the subsequent correlation analysis process, the portrait can be combined with mapping for performing correlation analysis in a knowledge graph, so that the analysis result is further mined, and the obtained analysis result is more accurate.

In a possible implementation manner of the exemplary embodiment of the present invention, in combination with the schematic flow chart of determining an abnormal clue shown in fig. 7, the method further includes a process of determining and further analyzing an abnormal clue:

in step 710, constructing a correlation map of the perception data according to each mapping;

the mapping obtained according to the same perception data can be directly used for constructing a correlation diagram;

in step 720, determining whether there is abnormal clue information and/or event information in the association graph;

performing abnormity judgment and early warning according to whether the side relation coefficient quantity formed by the clue information and/or the event information is larger than or equal to an abnormity threshold value;

in step 730, when the amount of the edge relation coefficient formed by the cue information and/or the event information is greater than or equal to an abnormal threshold, marking the corresponding cue information and/or the event information as an abnormal cue event;

in the step, further mining and analyzing the abnormal clue event to obtain a mining and analyzing result of the abnormal clue event;

referring to fig. 6, if the edge relation data between the vehicle C and the port C is 3 and the anomaly threshold is 2, the vehicle C and the port C can be determined as the anomalous event.

In step 740, after the abnormal clue event is determined, further mining analysis is performed on the abnormal clue event, for example, whether all persons of the mining warehouse a and the vehicle C are the same person or not is determined, so as to find out whether the inherent association exists or not, and the mining process and the mining result further assist in analysis and decision making;

in step 750, when the amount of the edge relation coefficient formed by the cue information and/or the event information is smaller than the abnormal threshold value, the development context of the cue information and/or the event information is combed to obtain a combing analysis result.

If the correlation coefficient between the vehicle C and the warehouse a is 1 and the anomaly threshold is 2, the vehicle C and the warehouse a are normal clue events.

At this time, the clue events formed by the vehicle C and the warehouse a can be normally combed, for example, the side relation generated by the normal passenger pick-up behavior of the user is added to the relation formed by the knowledge graph to perform vein combing, and the combing analysis result can also be used for assisting analysis and decision making.

According to the method provided by the exemplary embodiment of the invention, the abnormal clue event can be focused in the analysis process through the judgment and determination of the abnormal clue event, so that the rule determination and the deep exploration of the abnormal clue event are realized.

In a possible implementation manner of the exemplary embodiment of the present invention, the performing, in the knowledge-graph, association analysis by combining the mappings includes:

The association search is the association search analysis based on the triple data, the association graph analysis is the search analysis based on the created mapping, and the association analysis is carried out according to the geographic position after the triple data and the created mapping are all added into the map based on the map.

The method of the exemplary embodiment of the invention provides a plurality of modes suitable for analyzing the perception data, so that the suitable modes can be selected under different application scenes, or the modes are mutually combined to carry out reasoning analysis, thereby greatly enriching the application scenes of the method of the invention.

The method, the device, the equipment and the medium for analyzing the sensing data by using the knowledge graph, which are provided by the exemplary embodiment of the invention, expand a data model of the knowledge graph by fusing the mapping data and the knowledge graph, correspondingly provide a triple data query and analysis mode, are greatly different from the traditional query model, realize more effective query of the expanded knowledge graph, and aim at an analysis result, the materialized mapping is used for carrying out reanalysis such as addition and deletion on a primary analysis result, so that the accuracy of the analysis result is greatly improved.

In the correlation analysis stage, the method can be handed to special professionals for manual processing, and the information transmission and distribution channels, the perception data analysis, conversion and the mapping creation are also completed by the cooperation of a plurality of subsystems of the social management information platform in the process.

It should be noted that the method of the embodiment of the present invention may be executed by a single device, such as a computer or a server. The method of the embodiment can also be applied to a distributed scene and is completed by the mutual cooperation of a plurality of devices. In such a distributed scenario, one of the multiple devices may perform only one or more steps of the method of the embodiments of the present invention, and the multiple devices interact with each other to complete the method for analyzing the sensing data by using the knowledge graph.

It should be noted that the above describes some embodiments of the invention. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments described above and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.

Based on the same inventive concept, corresponding to the method for analyzing sensing data by using a knowledge graph in any of the above embodiments, the present invention further provides an apparatus for analyzing sensing data by using a knowledge graph, which, in conjunction with the schematic diagram of the apparatus shown in fig. 8, includes:

the analysis module 810 is configured to obtain sensing data and analyze the sensing data to obtain clue information and/or event information;

a conversion module 820, configured to convert the cue information and/or the event information according to a preset conversion rule to obtain triple data, and store the triple data in a knowledge graph;

the analysis module 830 is configured to respectively create a mapping according to the triple data obtained after the transformation of each clue information and/or event information, and perform association analysis in the knowledge graph by combining each mapping, the clue information, and/or the event information to obtain an analysis result.

For convenience of description, the above devices are described as being divided into various modules by functions, which are described separately. Of course, the functionality of the various modules may be implemented in the same one or more software and/or hardware implementations of the invention.

The apparatus of the foregoing embodiment is used to implement the method for analyzing sensing data by using a knowledge graph in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiment, which are not described herein again.

Based on the same inventive concept, corresponding to any of the above-mentioned embodiments, the invention further provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method for analyzing perceptual data using a knowledge graph according to any of the above-mentioned embodiments.

Fig. 9 is a schematic diagram illustrating a more specific hardware structure of an electronic device according to this embodiment, where the electronic device may include: a processor 1010, a memory 1020, an input/output interface 1030, a communication interface 1040, and a bus 1050. Wherein the processor 1010, memory 1020, input/output interface 1030, and communication interface 1040 are communicatively coupled to each other within the device via bus 1050.

The processor 1010 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an Application Specific Integrated Circuit (ASIC), or one or more Integrated circuits, and is configured to execute related programs to implement the technical solutions provided in the embodiments of the present disclosure.

The Memory 1020 may be implemented in the form of a ROM (Read Only Memory), a RAM (Random Access Memory), a static storage device, a dynamic storage device, or the like. The memory 1020 may store an operating system and other application programs, and when the technical solutions provided by the embodiments of the present specification are implemented by software or firmware, the relevant program codes are stored in the memory 1020 and called by the processor 1010 for execution.

The input/output interface 1030 is used for connecting an input/output module to input and output information. The i/o module may be configured as a component in a device (not shown) or may be external to the device to provide a corresponding function. The input devices may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output devices may include a display, a speaker, a vibrator, an indicator light, etc.

The communication interface 1040 is used for connecting a communication module (not shown in the drawings) to implement communication interaction between the present apparatus and other apparatuses. The communication module can realize communication in a wired mode (such as USB, network cable and the like) and also can realize communication in a wireless mode (such as mobile network, WIFI, Bluetooth and the like).

Bus 1050 includes a path that transfers information between various components of the device, such as processor 1010, memory 1020, input/output interface 1030, and communication interface 1040.

It should be noted that although the above-mentioned device only shows the processor 1010, the memory 1020, the input/output interface 1030, the communication interface 1040 and the bus 1050, in a specific implementation, the device may also include other components necessary for normal operation. In addition, those skilled in the art will appreciate that the above-described apparatus may also include only those components necessary to implement the embodiments of the present description, and not necessarily all of the components shown in the figures.

The electronic device of the foregoing embodiment is used to implement the method for analyzing perceptual data using a knowledge graph in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiment, which are not described herein again.

Based on the same inventive concept, the present invention also provides a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the method for analyzing perceptual data using a knowledge graph as described in any of the above embodiments, corresponding to any of the above-described embodiment methods.

Computer-readable media of the present embodiments, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device.

The storage medium of the above embodiments stores computer instructions for causing the computer to execute the method for analyzing perceptual data by using a knowledge graph according to any of the above embodiments, and has the beneficial effects of corresponding method embodiments, which are not described herein again.

Those of ordinary skill in the art will understand that: the discussion of any embodiment above is meant to be exemplary only, and is not intended to intimate that the scope of the disclosure, including the claims, is limited to those examples; features from the above embodiments or different embodiments may also be combined, steps may be implemented in any order, and there are many other variations of the different aspects of the embodiments of the invention described above which are not provided in detail for the sake of brevity.

In addition, well-known power/ground connections to Integrated Circuit (IC) chips and other components may or may not be shown within the provided figures for simplicity of illustration and discussion, and so as not to obscure the embodiments of the invention. Furthermore, apparatus may be shown in block diagram form in order to avoid obscuring embodiments of the invention, and also in view of the fact that specifics with respect to implementation of such block diagram apparatus are highly dependent upon the platform within which the embodiments of the present invention are to be implemented (i.e., specifics should be well within purview of one skilled in the art). Where specific details (e.g., circuits) are set forth in order to describe example embodiments of the invention, it should be apparent to one skilled in the art that embodiments of the invention can be practiced without, or with variation of, these specific details. Accordingly, the description is to be regarded as illustrative instead of restrictive.

While the present invention has been described in conjunction with specific embodiments thereof, many alternatives, modifications, and variations of these embodiments will be apparent to those of ordinary skill in the art in light of the foregoing description. For example, other memory architectures (e.g., dynamic ram (dram)) may use the discussed embodiments.

The present embodiments are intended to embrace all such alternatives, modifications and variances which fall within the broad scope of the appended claims. Therefore, any omissions, modifications, substitutions, improvements and the like that may be made without departing from the spirit or scope of the embodiments of the present invention are intended to be included within the scope of the present invention.

Claims

1. A method for analyzing perceptual data using a knowledge-graph, the method comprising:

2. The method for analyzing perceptual data using a knowledge-graph as defined in claim 1, wherein the transforming the cue information and/or the event information according to a predetermined transformation rule to obtain triple data, and storing the triple data into the knowledge-graph comprises:

3. The method for analyzing perceptual data using a knowledge-graph as defined in claim 2, wherein the creating of the mapping according to the triplet data obtained after the transformation of each of the cue information and/or the event information, and performing the association analysis in the knowledge-graph according to the mapping and the cue information and/or the event information to obtain the analysis result further comprises:

4. The method for analyzing perceptual data using a knowledge-graph of claim 1, the method further comprising:

5. The method for analyzing perceptual data using a knowledge-graph of claim 1, the method further comprising:

6. The method for analyzing perceptual data using a knowledge-graph of claim 1, the method further comprising:

7. The method of using a knowledge-graph to analyze perceptual data as defined in claim 1, wherein the associating analysis in the knowledge-graph in conjunction with each of the mappings comprises:

8. An apparatus for analyzing perceptual data using a knowledge-graph, the apparatus comprising:

9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the method of analyzing perceptual data using a knowledge graph according to any one of claims 1 to 7 when executing the program.

10. A non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the method of analyzing perceptual data using a knowledge graph of any one of claims 1 to 7.