CN111984737A - Intelligent main body and transaction capability construction system - Google Patents
Intelligent main body and transaction capability construction system Download PDFInfo
- Publication number
- CN111984737A CN111984737A CN201910434874.0A CN201910434874A CN111984737A CN 111984737 A CN111984737 A CN 111984737A CN 201910434874 A CN201910434874 A CN 201910434874A CN 111984737 A CN111984737 A CN 111984737A
- Authority
- CN
- China
- Prior art keywords
- event
- model
- transaction
- data
- intelligent
- 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
- 238000010276 construction Methods 0.000 title claims abstract description 52
- 238000012545 processing Methods 0.000 claims abstract description 36
- 238000004891 communication Methods 0.000 claims abstract description 17
- 230000007613 environmental effect Effects 0.000 claims abstract description 14
- 230000000694 effects Effects 0.000 claims abstract description 12
- 238000000034 method Methods 0.000 claims description 62
- 230000008569 process Effects 0.000 claims description 50
- 238000007726 management method Methods 0.000 claims description 17
- 230000009471 action Effects 0.000 claims description 14
- 230000010354 integration Effects 0.000 claims description 10
- 241000282414 Homo sapiens Species 0.000 claims description 9
- 238000010586 diagram Methods 0.000 claims description 9
- 238000001228 spectrum Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000006399 behavior Effects 0.000 claims description 5
- 230000008859 change Effects 0.000 claims description 5
- 230000000750 progressive effect Effects 0.000 claims description 2
- 230000003993 interaction Effects 0.000 abstract description 7
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 230000003044 adaptive effect Effects 0.000 abstract 1
- 238000004458 analytical method Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/285—Clustering or classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/288—Entity relationship models
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
An intelligent subject and affair ability construction system belongs to the technical field of artificial intelligence, and is an intelligent affair system composed of an intelligent subject system service end and an environment activity scene, wherein the environment activity scene is in signal connection with the intelligent subject system service end, and signals are transmitted according to an event data communication protocol; the object classification is realized through object characteristic difference through the object characteristic relation graph database, the connection and adaptive processing capacity of the equipment to the objects is enhanced, and in addition, the human-computer interaction capacity of the equipment and an environmental activity scene is constructed.
Description
Technical Field
The invention belongs to the technical field of artificial intelligence, and particularly relates to an intelligent agent and a transaction capability construction system.
Background
Along with the social development and the improvement of the scientific and technical level, various intelligent agents are more popular and applied in various fields, such as: intelligent lamp pole, intelligent door and window, intelligent cleaning machines people etc, but these intelligent agent realize these intelligent actions in scene separately, it is the inside model data who stores in advance of intelligent agent to rely on, carry out the event processing, consequently, this type of intelligent agent system just can only handle to single predetermined event, can not open carry out autonomous identification study and processing to the event, and can not carry out intercommunication and coprocessing event to different intelligent agent equipment, and can not be different to the processing affair between each other, can not carry out information interaction and mutual study adaptation.
Disclosure of Invention
It is an object of the present invention to overcome the above-mentioned drawbacks and deficiencies and to provide an intelligent agent and a transaction capability building system.
In order to solve the technical problems, the following technical scheme is adopted:
an intelligent agent and transaction capability construction system is an intelligent transaction system which is composed of an intelligent agent system service end and an environment activity scene, wherein the environment activity scene is composed of at least one intelligent agent device, environment things, environment events and environment transactions, and the intelligent agent system service end comprises an object characteristic relation chart database, an event model database, an event task database, an object identification definition module, an event model integration processing module and an event task management module; the object identification definition module: defining object data; object feature relationship atlas: carrying out feature classification and feature information storage on the object data after identification and definition; event task database: storing event task data defining a manner of processing event tasks; the event task management module: receiving the transaction data to be executed, comparing the transaction data with an event task definition or an event task framework in an event task database, if the transaction data is matched with the event task definition or the event task framework, processing the event task, and if the event task definition or the event task framework is not matched with the event task definition or the event task framework in the event task database, defining and constructing the event task to set an event task processing mode in a working scene so as to meet the event task processing requirement in the working scene; the event model integration processing module: receiving event data to construct an event model, and constructing and realizing intelligent subject event behaviors and system transaction capability output by combining the object model data fed back by the object identification definition module and the transaction data of the event task management module; an event model database: storing the identification definition and constructing an event model for realizing construction; the intelligent main body system server communicates with the intelligent main body equipment in the environment activity scene through an event data communication protocol, and the construction of the transaction capability of the intelligent main body equipment or the intelligent equipment needing the transaction capability is realized.
The system is installed on the intelligent main body equipment, and the intelligent main body equipment acquires event data of other equipment or human beings, carries out recognition and interpretation by the system and carries out appropriate feedback.
The object feature relational graph database is a knowledge graph which defines object types according to object features and can present progressive evolutionary relations, namely adjacent object features are combined into homogeneous items, starting from object element categories, rear object categories comprise main features of front object categories, and when the rear object categories have unique features, objects become a new category, so that the object feature relational graph database is added with the specific working steps as follows:
(1) the intelligent agent identifies and stores the definition object;
(2) calling object feature knowledge obtained in the past in an object feature relational graph database to realize the identification of object objects;
(3) if the definition object has the category unique characteristics under the premise of inheriting the object category characteristics, the unique characteristics are added into the object characteristic relation map database.
The object identification definition module comprises an object identification module and an object model identification definition module.
The object identification module is mainly used for receiving object characteristic data information obtained by the Internet of things or intelligent main body equipment, carrying out object modeling on the object data collected by the obtained sensor or other information channels, and carrying out characteristic identification calculation processing on the object on the basis of the object characteristic data information, and comprises the following specific processes:
(1) making a thing object hypothesis for the thing object;
(2) marking the feature definition of the object on the basis of the object assumption;
(3) and matching the object type characteristics in the marked event object and object relation knowledge map database, wherein the matching process is to query and compare the characteristics of the objects and compare and match the characteristics from the low-level classification level type of the knowledge map to the end object type, if the object characteristics are completely the same, the object types which are defined in the past are found, and if the object characteristics are not completely the same, a new object type is established in the object characteristic relation map database.
The object model identification and definition module is mainly a process that after the intelligent main body equipment identifies and defines object objects in the environment under the action of the object identification module, the relation characteristics among the objects are identified and defined, the state of the object relation characteristics is identified, the relation among the objects is judged according to the state, and the object model is identified and calculated on the basis of the state, and the specific process is as follows:
(1) Identifying an environmental object;
(2) identifying objects in a scene environment;
(3) and presuming the relationship characteristics among the things;
meanwhile, in the process, 2 corresponding object relation features need to be identified and the states of the object relation features need to be identified respectively.
The event model integration processing module comprises an event model identification definition module, an object relation model identification definition module, an event model construction realization module, an event relation model construction realization module and an event model construction realization module,
the event model identification definition module realizes identification definition of the event model on the basis that the intelligent agent can identify the object model, namely, the intelligent agent carries out identification definition on the single action event occurrence process, namely, the characteristic change information between the objects presented by the single-step event model can be used as a record and an identification mark of the event model.
The event relation model identification and definition module is mainly used for identifying the action relation among the multi-step event models and the optimal implementation planning mode for implementing the multi-step event models under different conditions on the basis of the event model identification and definition module.
Further, the specific steps of the event model identification definition module are as follows:
(1) identifying an event model process and storing data;
(2) carrying out event model feature identification;
(3) matching the event model with an event model database;
(4) if the event model is matched with the event model database, ending the process;
(5) and if not, adding the newly added event model into the event model database.
Further, the specific steps of the event relation model identification definition module are as follows:
(1) event process identification and data storage are carried out;
(2) the event relation model is arranged in cooperation with the event relation model reference;
(3) matching the sorted event relation model with an event model database;
(4) and if the event relation model is not matched, adding a new event relation model into the event model database, naming the new event relation model, and then ending.
The event model identification definition module is used for identifying different events which occur simultaneously in the environment and the relationship among the events, the process mainly defines the event environment, identifies and defines an event relationship model in the environment, identifies and defines the characteristics of the event model, identifies the association characteristics of the event model, and finally identifies the association content among the event relationship models.
And the event model construction implementation module implements the event model process meeting the characteristic requirements according to the conditions in the existing event model and by referring to the existing event model in the event model database.
The event relation model construction implementation module determines the evolution process of the event model according to the existing object model and the target object model.
The event model construction implementation module fully utilizes the existing resources to construct and implement a plurality of event relation models with incidence relations under the condition of identifying and defining the existing environment, things and events, and if the event model does not exist in the event model database, the event characteristic relation knowledge graph database is called to realize the event action by inference and matching.
Further, the specific process of the event model construction implementation module is as follows:
(1) calling an event model database to perform event model query, and performing comprehensive analysis on event tasks;
(2) matching and sorting the event models;
(3) determining an event model implementation process by combining an event model database, and leading the execution of the event model process;
(4) and finishing the process.
Further, the specific steps of the event relation model construction implementation module are as follows:
(1) Comprehensively analyzing the event tasks to obtain event relation model characteristic requirements and the existing object model, wherein the existing main body can identify and detect four aspects of activity and event relation model;
(2) the event relation model is organized and realized by adopting the following modes, and the specific contents are as follows:
firstly, realizing an event relation model by using a query method: trying to match an object model in a real environment according to an event relation model in an event model database, and gradually completing the event relation model through the existing event data;
secondly, realizing a learning method event relation model: and obtaining the event relation model information from the outside, and receiving the outside event model implementation steps by the intelligent main body to implement the corresponding event relation model. The specific mode is that the external event relation model teaching is identified by an event relation model identification definition module, or the event relation model is directly obtained from an external event information data communication interface;
realizing the exploration method event relation model: when the intelligent agent cannot inquire the corresponding event model in the event model database. Then, some attempts and deductions need to be made on the evolution process of the object model, and the main process is that according to the characteristics of the target object model and the characteristics of the existing object model, a traversing attempt main body can actively drive the change of the characteristics of the object model, the evolution approaches of the object model are exhausted, and the event relation model is sorted to obtain event model data;
(3) Performing event model query on the step (1) and the step (2) through an event model database;
(4) then, carrying out event relation model arrangement;
(5) thereby realizing the construction of an event model;
(6) the whole process is ended.
Further, the concrete steps of the event model construction implementation module are as follows:
(1) comprehensively analyzing event tasks, mainly analyzing from three aspects of situation model characteristic requirements, environment situation model identification and situation model identification detection;
(2) the method comprises the following steps of constructing an event model, wherein the intelligent agent equipment utilizes existing resources to construct a plurality of associated event relation models under the condition of identifying and defining the existing environment, things and events, namely constructing a supplementary event model;
(3) performing event model query matching on the step (1) and the step (2) through an event model database;
(4) if the matched model in the existing event model database, the situation model is sorted;
(5) then, realizing the construction of an event relation model;
(6) the whole process is ended.
(7) And if the existing event model database does not have a matched model, adding a new event model into the event model database, wherein the new event model is constructed by calling the models in the object characteristic knowledge map database and the event task database at the same time.
(8) And (5) repeating the step (4), the step (5) and the step (6).
Further, the event task management module comprises the following specific steps:
(1) firstly, receiving a task of acquiring an event;
(2) matching the received event task with an event task database;
(3) judging whether the acquired event task needs to be defined or not;
(4) judging the definition to be defined, entering an event task definition construction link, and adding the event task definition construction link to an event task database;
(5) if the definition is not needed, the event task is directly operated and executed, and the event task state needs to be monitored in the event task execution process by combining with an event task database;
(6) and when the event task is executed, the event model is required to be inquired through the event model database.
The event data communication protocol comprises thing data, event data and transaction data, wherein the thing data is a data stream formed by defining the thing identification in an environmental scene, and the method comprises the following steps: firstly, sensor data are obtained and uploaded to an object identification definition module to carry out an object identification process, objects and characteristics are matched and defined after the objects are defined, and the transmitted data are data transmitted by the object data. Things can be refined and enriched in features in the knowledge graph database through various ways so that intelligent agents can better use the data of the things. In addition, the data of the main body is also one kind of object data, and the data comprises main body active data, main body sensing data and action and behavior mode data of the main body in specific events; the event data is: the actual event state data and the event model data are mainly used for communicating the event operation condition and the event characteristic state to be realized; the transaction data is: the aspect model feature state which needs to be realized by the intelligent main body equipment is an aspect model which needs to be realized. The event task operation management module feeds back event data according to the existing environment situation conditions and is executed by the intelligent main body equipment. The transaction data can be transmitted to the intelligent agent by human language, common intelligent equipment and other intelligent agents, and the intelligent agent transmits the data to the event task operation management module for processing.
Due to the adoption of the technical scheme, the method has the following beneficial effects:
an intelligent agent and a transaction capability construction system adopt an event data communication protocol to realize mutual decoding communication with human languages and easily perform data interaction on events or events, so that the intelligent system and human-related transactions can be combined together in a better quality manner, and human-computer cooperation and cooperative work are facilitated; the object classification is realized through object feature difference through the object feature relational graph database, the object classification and the evolution characteristics are embodied, the connection and degradation processing capacity of equipment to the objects is enhanced, in addition, the information interaction with an environmental activity scene is enhanced, and the event is defined and processed in an open mode through a system.
Drawings
FIG. 1 is an overall schematic diagram of an intelligent agent and transaction capability building system of the present invention;
FIG. 2 is a schematic diagram of an event data communication protocol in the present invention;
FIG. 3 is a flow diagram of the object model identification definition module of the present invention;
FIG. 4 is a flowchart of the event model identification definition module operation of the present invention;
FIG. 5 is a flow diagram of the business object identification definition module of the present invention;
FIG. 6 is a flow diagram of the object model identification definition module of the present invention;
FIG. 7 is a flow diagram of the object relationship model identification definition module of the present invention;
FIG. 8 is a flowchart illustrating the operation of the event model identification definition module according to the present invention;
FIG. 9 is a flow diagram of the business model construction implementation module of the present invention;
FIG. 10 is a flowchart of the event relationship model construction implementation module work of the present invention;
FIG. 11 is a flowchart illustrating the operation of the event model construction module of the present invention;
FIG. 12 is an event task management module workflow diagram of the present invention.
In the figure: 1-intelligent agent system server; 2-environmental activity scenario; 3-event data communication protocol; 4-object identification definition module; 5-object feature relationship map database; 6-an event model integration processing module; 7-an event model database; 8-an event task database; 9-event task management module; 10-smart agent device; 11-environmental transactions; 12-environmental situation; 13-environmental things; 14-transaction data; 15-event data; 16-transaction data; 17-object identification definition module; 18-object model identification definition module; 19-an event model identification definition module; 20-object relation model identification definition module; 21-an event model construction implementation module; 22-an implementation module of the state model construction; 23-a situation model identification definition module; and 24-an event relation model construction implementation module.
Detailed Description
The technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.
As shown in fig. 1 to 12, an intelligent agent and transaction capability building system is an intelligent transaction system composed of an intelligent agent system server 1 and an environmental activity scene 2.
The environment activity scene 2 is in signal connection with the intelligent main body system server 1, and the signals are transmitted according to the event data communication protocol 3, wherein the event data communication protocol 3 can realize mutual decoding communication with human languages, and can easily perform data interaction on events or events, so that the intelligent system and human-related transactions can be combined together in a better quality manner, human-computer cooperation and cooperative work are facilitated, and the self capability of the intelligent device for understanding the events is enhanced.
The environmental activity scenario 2 is composed of at least one intelligent agent device 10, environmental matters 13, environmental matters 12 and environmental matters 11.
The system is installed on the intelligent main body device 10, and the intelligent main body device 10 acquires event data of other devices or human beings, performs recognition and interpretation by the system, and makes appropriate feedback, thereby realizing interaction between machines and interaction between human-machines.
The intelligent main body system service end 1 comprises an object characteristic relation chart database 5, an event model database 7, an event task database 8, an object identification definition module 4, an event model integration processing module 6 and an event task management module 9.
The object identification definition module 4: defining object data;
the object feature relation spectrum database 5: carrying out feature classification and feature information storage on the defined object data;
the event task database 8: storing event task data defining a manner of processing event tasks;
the event task management module 9: receiving the transaction data to be executed, comparing the transaction data with the event task definition or the event task framework in the event task database 8, processing the event task, and if the event task definition or the event task framework is not matched in the event task database 8, defining and constructing the event task to set an event task processing mode in a working scene and meet the event task processing requirement in the working scene;
the event model integration processing module 6: receiving event data to construct an event model, and combining the object model data fed back by the object identification definition module 4 and the transaction data of the event task management module 9 to construct and realize the event behavior of the intelligent main device 10 and realize the output of the system transaction capability;
The event model database 7: the recognition definitions are stored and the event model that implements the build is constructed.
Preferably, the object identification definition module 4 includes an object identification definition module 17 and an object model identification definition module 18, where the object identification definition module 17 is mainly used to receive object feature data information obtained by the internet of things or the intelligent main device 10, perform object modeling on the object data 16 collected by the acquired sensors or other information channels, and perform feature identification calculation processing on the object based on the object feature data information, and the specific process is as follows:
(1) making a thing object hypothesis for the thing object;
(2) marking the feature definition of the object on the basis of the object assumption;
(3) and matching the object type characteristics in the marked event object and object characteristic relation knowledge map database 5, wherein the matching process is to query and compare the characteristics of the objects and perform characteristic comparison and matching from the low-level classification level type of the object characteristic relation knowledge map database 5 to the terminal object type, the object types which are defined in the past are found if the object characteristics are completely the same, and a new object type is established in the object characteristic relation knowledge map database 5 if the object characteristics are not completely the same.
The object model identification definition module 18 is mainly a process in which after the intelligent subject device 10 identifies object objects in the definition environment under the action of the object identification module 17, the relationship characteristics between the objects are identified and defined, and the states of the object relationship characteristics are identified, so as to judge the relationship between the objects, and realize the feature identification calculation processing of the object model on the basis of the relationship characteristics, and the specific process is as follows:
(1) identifying an environmental object;
(2) identifying objects in a scene environment;
(3) and presuming the relationship characteristics among the things;
meanwhile, in the process, 2 corresponding object relation features need to be identified and the states of the object relation features need to be identified respectively.
Preferably, the object feature relationship spectrum database 5 is a knowledge spectrum which defines object categories according to object features and can present a gradual evolutionary relationship, that is, adjacent object features merge homogeneous items, starting from an object element category, a back-end object category includes main features of a front-end object category, and a unique feature of a back-end object makes objects a new category, and the specific working steps are as follows:
(1) The intelligent agent device 10 recognizes the definition thing and stores it;
(2) calling object feature knowledge obtained in the past in the object feature relational graph database 5 to realize the identification of object objects;
(3) if the definition object has the category unique characteristics under the premise of inheriting the object category characteristics, the unique characteristics are added into the object characteristic relation map database.
Preferably, the event task management module 9 specifically includes the following steps:
(1) firstly, receiving a task of acquiring an event;
(2) matching the received event task with the event task database 8;
(3) judging whether the acquired event task needs to be defined or not;
(4) judging the definition to be defined, entering an event task definition construction link, and adding the event task definition construction link to an event task database 8;
(5) if definition is not needed, the event task is directly operated and executed, and the event task state needs to be monitored in the event task execution process by combining the event task database 8;
(6) when the event task is executed, the event model is required to be inquired through the event model database 7.
Preferably, the event model integration processing module 6 includes an event model identification definition module 19, an object relationship model identification definition module 20, an event model identification definition module 23, an event model construction realization module 21, an event relationship model construction realization module 24, and an event model construction realization module 22.
The event model identification definition module 19 implements identification definition on an event model based on that the intelligent subject device 10 can identify a thing model, that is, the intelligent subject device 10 performs identification definition on a single action event occurrence process, that is, feature change information between things presented by a single-step event model can be used as a record and an identification mark of the event model, and the specific steps are as follows:
(1) identifying an event model process and storing data;
(2) carrying out event model feature identification;
(3) matching the event model with an event model database;
(4) if the event model is matched with the event model database, ending the process;
(5) if not, the new event model is added to the event model database 7.
The object relationship model identification and definition module 20 is mainly used for identifying action relationships among multi-step event models and an optimal implementation planning mode for implementing the multi-step event models under different conditions, and comprises the following specific steps:
(1) event process identification and data storage are carried out;
(2) the event relation model is arranged in cooperation with the event relation model reference;
(3) Matching the sorted event relation model with an event model database 7;
(4) and if the event relation model can be matched, ending the process, and if the event relation model can not be matched, adding a new event relation model to the event model database 7, naming the new event relation model, and ending.
The event model identification definition module 23 identifies different events occurring simultaneously in the environment and the relationship between the events, and includes the following steps:
(1) firstly, identifying an event model in an environment;
(2) then identifying the event model association characteristics;
(3) finally, event model elements are required to be subjected to correlation identification;
(4) and then stores the event model association features in the event model database 7.
The event model construction implementation module 21 implements a process meeting the characteristic requirements of the event model according to the conditions in the existing event model and by referring to the existing event model in the event model database 7, and the specific process is as follows:
(1) calling an event model database 7 to perform event model query, and performing comprehensive analysis on event tasks;
(2) matching and sorting the event models;
(3) determining an event model implementation process by combining the event model database 7, and leading the execution of the event model process;
(4) And finishing the process.
The event relationship model construction implementation module 24 is to determine an evolution process of an event model according to an existing object model and a target object model, and includes the following specific steps:
(1) comprehensively analyzing the event tasks to obtain event relation model characteristic requirements and the existing object model, wherein the existing main body can identify and detect four aspects of activity and event relation model;
(2) the event relation model is organized and realized by adopting the following modes, and the specific contents are as follows:
firstly, realizing an event relation model by using a query method: according to the event relation model in the event model database 7, trying to match the object model in the real environment, and completing the event relation model step by step through the existing event data 15;
secondly, realizing a learning method event relation model: the method comprises the steps that event relation model information is obtained to the outside, and the intelligent main body equipment 10 receives a mode method that the outside realizes an event model to realize a corresponding event relation model, wherein the specific mode is that the teaching of the external event relation model is realized through an event relation model recognition definition module, or the event relation model is directly obtained from an external event information data communication interface;
Realizing the exploration method event relation model: when the intelligent agent apparatus 10 cannot query the event model database 7 for the corresponding event model. Then, some attempts and deductions need to be made on the evolution process of the object model, and the main process is that according to the characteristics of the target object model and the characteristics of the existing object model, a traversing attempt main body can actively drive the change of the characteristics of the object model, the evolution approaches of the object model are exhausted, and the event relation model is sorted to obtain event model data;
(3) performing an event model query for the step (1) and the step (2) through an event model database 7;
(4) then, carrying out event relation model arrangement;
(5) thereby realizing the construction of an event model;
(6) and finishing the process.
The event model construction implementation module 22, under the condition of identifying and defining existing environments, things and events, fully utilizes these existing resources to construct and implement a plurality of event relationship models having association relationships, specifically:
(1) comprehensively analyzing event tasks, mainly analyzing from three aspects of situation model characteristic requirements, environment situation model identification and situation model identification detection;
(2) The intelligent agent device 10 utilizes the existing resources to construct a plurality of associated event relation models, namely construct supplementary state models, under the condition of identifying and defining the existing environment, things and events;
(3) performing event model query matching on the step (1) and the step (2) through an event model database 7;
(4) if the matched model in the existing event model database 7, the situation model is sorted;
(5) then, realizing the construction of an event relation model;
(6) and finishing the process.
The event data communication protocol 3 comprises thing data 16, event data 15 and transaction data 14, wherein the thing data 16 is a data stream formed by defining the thing identification in an environmental scene, and the method comprises the following steps: firstly, acquiring sensor data and uploading the sensor data to an object identification definition module 4 for object identification process, and after object definition, mutually matching and defining objects and characteristics, and at this time, transmitting object data 16; the system can improve and enrich the characteristics in the object characteristic relation knowledge map database 5 through various ways, so that the intelligent subject device 10 can better use the object data 16. In addition, the data of the intelligent main device 10 itself is also one of the object data 16, and there are main active and main sensing data, and action and behavior mode data of the intelligent main device 10 in a specific event; wherein the event data 15: the actual event state data and the event model data are mainly used for communicating the event operation condition and the event characteristic state to be realized; the transaction data 14: the situation model feature state to be realized by the intelligent agent device 10 is a situation model to be realized. The event task operation management module 9 feeds back the event data 15 according to the existing environmental situation condition, and is executed by the intelligent agent device 10. Of course, the transaction data 14 may be human language or machine language, and when the data is transmitted to the intelligent agent device 10, the intelligent agent device 10 transmits the data to the event task operation management module 9 for processing.
The working principle of the invention is as follows: the real-time collection of environmental matters and event data is realized through an intelligent main body device 10, wherein, under the condition that the intelligent main body device 10 is mounted under the system, the working affairs are identified, defined and modeled, the characteristics of the matters in the event, the relation among the matters, the event mode and the affairs in the environment are collected, information collection is continuously carried out on a certain affair and the event learning is carried out on the affair processing mode, so as to become an expert system in a certain affair field, then, the intelligent main body device 10 is uploaded to an intelligent main body system service terminal 1 through an event data communication protocol 3 and carries out identification processing and calculation on the data, wherein, an object characteristic relation spectrum database 5 is established, characteristic hypothesis classification and robust learning are carried out on the collected matters, thereby realizing the object classification and the evolution characteristics, and feeds back to the intelligent agent device 10 to enable it to make appropriate actions in the environment and thereby complete the event task.
The present invention has been described in terms of embodiments, and several variations and modifications can be made to the device without departing from the principles of the present invention. It should be noted that all the technical solutions obtained by means of equivalent substitution or equivalent transformation, etc., fall within the protection scope of the present invention.
Claims (11)
1. An intelligent subject and transaction capability construction system is an intelligent transaction system composed of an intelligent subject system server and an environment activity scene, and is characterized in that the environment activity scene is in signal connection with the intelligent subject system server, the signal connection is transmitted according to an event data communication protocol (3), the environment activity scene is composed of at least one intelligent subject device (10), an environment object (13), an environment state (12) and an environment transaction (11), the system is installed on the intelligent subject device (10), the intelligent subject device (10) acquires event data of other devices or human beings, identifies and explains the event data by the system and gives appropriate feedback, and the intelligent subject system server comprises a subject characteristic relation diagram database (5), an event model database (7), an event task database (8), The system comprises a thing identification definition module (4), an event model integration processing module (6) and an event task management module (9);
object identification definition module (4): defining object data;
object feature relation spectrum database (5): receiving and carrying out feature classification and feature information storage on the defined object data;
Event task database (8): storing event task data defining a manner of processing event tasks;
event task management module (9): receiving the transaction data to be executed, comparing the transaction data with the event task definition or the event task framework in the event task database (8), processing the event task, and if the event task definition or the event task framework is not matched in the event task database (8), defining and constructing the event task to set an event task processing mode in a working scene and meet the event task processing requirement in the working scene;
an event model integration processing module (6): receiving event data to construct an event model, and constructing and realizing intelligent subject event behaviors by combining the object model data fed back by the object identification definition module (4) and the transaction data of the event task management module (9), thereby realizing system transaction capability output and realizing transaction capability construction;
event model database (7): storing the identification definition and constructing an event model for realizing construction;
the intelligent main body system server communicates with the intelligent main body equipment (10) through the event data communication protocol (3), and the construction of the transaction capability of the intelligent main body equipment (10) or the intelligent equipment needing the transaction capability is realized.
2. An intelligent agent and transaction capability building system according to claim 1, wherein the transaction characteristic relationship spectrum database (5) is a knowledge-graph which defines transaction categories according to transaction characteristics and can exhibit progressive evolutionary relationships, that is, adjacent transaction characteristics merge homogeneous items, starting from a category of matter elements, a category of back-end transaction includes main characteristics of a category of front-end transaction, and when a category of back-end transaction has unique characteristics, a transaction is made into a new category, and then is added to the transaction characteristic relationship spectrum database (5).
3. An intelligent agent and transaction capability construction system according to claim 1, wherein the object identification definition module (4) comprises an object identification module (17) and an object model identification definition module (18), the object identification module (17) mainly receives object characteristic data information obtained by the internet of things or the intelligent agent device (10), performs object modeling on the object data (16) collected by the acquired sensors or other information channels, and performs identification calculation processing on the characteristics of the object on the basis of the object characteristic data information; the object model identification and definition module (18) is mainly used for identifying and defining the relation characteristics among objects by the intelligent main body equipment (10) after identifying and defining the object objects in the environment under the action of the object identification module (17), identifying the states of the object relation characteristics, judging the relation among the objects according to the relation characteristics, and realizing the characteristic identification and calculation processing of the object model on the basis of the judgment.
4. An intelligent agent and transaction capability construction system according to claim 1, wherein the event model integration processing module (6) comprises an event model identification definition module (19), a transaction relationship model identification definition module (20), an event model identification definition module (23), an event model construction realization module (21), an event relationship model construction realization module (24) and an event model construction realization module (22).
5. An intelligent agent and transaction capability building system according to claim 6, wherein the event model identification definition module (19) implements identification definition of the event model based on that the intelligent agent device (10) can identify the transaction model, that is, the intelligent agent device (10) performs identification definition on a single action event occurrence process, that is, feature change information between transactions represented by a single-step event model can be used as a record and identification mark of the event model.
6. An intelligent agent and transaction capability building system according to claim 6, wherein the transaction relationship model identification and definition module (20) is mainly used for identifying the action relationship between the multi-step event models and the optimal implementation planning way for implementing the multi-step event models under different conditions.
7. The system for building intelligent agent and transaction capability according to claim 6, wherein the event model identification definition module (23) is used for identifying different events and relationships between the events occurring simultaneously in the environment, and the process mainly defines the event environment, identifies and defines the event relationship model in the environment, then identifies and defines the characteristics of the event model, then identifies the associated characteristics of the event model, and finally identifies the associated content between the event relationship models.
8. An intelligent agent and transaction capability construction system according to claim 6, wherein the event model construction implementation module (21) implements the process meeting the feature requirement of the event model according to the condition in the existing event model and referring to the existing event model in the event model database (7), and if the event model is not in the event model database (7), the event model is implemented by invoking the object feature relational knowledge graph database (5) to perform inference matching.
9. The system for building the intelligent agent and the transaction capability according to claim 6, wherein the event relationship model construction implementation module (24) determines the evolution process of the event model according to the existing transaction model and the target transaction model, and the main process is to match the current situation to implement the step of completing the event task, if the implementation process of the relevant event relationship model cannot be queried, the construction implementation of the event relationship model needs to be implemented in other ways.
10. An intelligent agent and transaction capability construction system according to claim 6, wherein the event model construction implementation module (22) is configured to implement a plurality of event relationship models with association relationships by making full use of existing resources when identifying and defining existing environments, things and events.
11. An intelligent agent and transaction capability building system according to claim 1, wherein the event data communication protocol (3) comprises transaction data (16), event data (15) and transaction data (14), wherein the transaction data (16) is a data stream formed by defining the identification of a transaction in an environmental scene, and the event data (15): the actual event state data and the event model data are mainly used for communicating the event operation condition and the event characteristic state to be realized; the transaction data (14): the aspect model feature state which needs to be realized by the intelligent main body equipment is an aspect model which needs to be realized.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910434874.0A CN111984737A (en) | 2019-05-23 | 2019-05-23 | Intelligent main body and transaction capability construction system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910434874.0A CN111984737A (en) | 2019-05-23 | 2019-05-23 | Intelligent main body and transaction capability construction system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111984737A true CN111984737A (en) | 2020-11-24 |
Family
ID=73436558
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910434874.0A Pending CN111984737A (en) | 2019-05-23 | 2019-05-23 | Intelligent main body and transaction capability construction system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111984737A (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107783973A (en) * | 2016-08-24 | 2018-03-09 | 慧科讯业有限公司 | The methods, devices and systems being monitored based on domain knowledge spectrum data storehouse to the Internet media event |
| CN109710701A (en) * | 2018-12-14 | 2019-05-03 | 浪潮软件股份有限公司 | A kind of automated construction method for public safety field big data knowledge mapping |
-
2019
- 2019-05-23 CN CN201910434874.0A patent/CN111984737A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107783973A (en) * | 2016-08-24 | 2018-03-09 | 慧科讯业有限公司 | The methods, devices and systems being monitored based on domain knowledge spectrum data storehouse to the Internet media event |
| CN109710701A (en) * | 2018-12-14 | 2019-05-03 | 浪潮软件股份有限公司 | A kind of automated construction method for public safety field big data knowledge mapping |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7840515B2 (en) | System architecture and process for automating intelligent surveillance center operations | |
| CN110688454A (en) | Method, device, equipment and storage medium for processing consultation conversation | |
| US11687822B2 (en) | Automated functional understanding and optimization of human/machine systems | |
| CN107895011A (en) | Processing method, system, storage medium and the electronic equipment of session information | |
| CN107844914B (en) | Risk management and control system based on group management and implementation method | |
| CN113037783B (en) | Abnormal behavior detection method and system | |
| CN1577352A (en) | Consulting assessment environment | |
| CN116233902B (en) | Wireless communication network anomaly identification system and method based on big data | |
| CN118132626B (en) | Rural information service management platform based on data analysis | |
| CN114637884B (en) | Method, device and equipment for matching cable-stayed cable-computed space-time trajectory with road network | |
| CN115063746A (en) | Vehicle warehousing management method and device, computer equipment and storage medium | |
| CN111931186B (en) | Software risk identification method and device | |
| CN116128413B (en) | Intelligent warehouse material statistics system based on Bluetooth communication | |
| CN116452212B (en) | Intelligent customer service commodity knowledge base information management method and system | |
| CN111984737A (en) | Intelligent main body and transaction capability construction system | |
| CN111062827B (en) | Engineering supervision method based on artificial intelligence mode | |
| KR102511561B1 (en) | Method, device and system for providing expert dispatch service based on artificial intelligence | |
| CN116796894A (en) | Construction method of efficient deep learning weather prediction model | |
| CN116703346A (en) | Attendance management system and method based on big data and artificial intelligence | |
| CN115967730A (en) | Data acquisition method and system based on Internet of things | |
| CN115696169A (en) | Data acquisition method of MES production management system | |
| CN115169588A (en) | Electrographic computation space-time trajectory vehicle code correlation method, device, equipment and storage medium | |
| CN115327942A (en) | Intelligent environment monitoring system | |
| CN117151906B (en) | Financial accounting audit supervision collaborative supervision method based on association network establishment | |
| CN118097198B (en) | Automatic dressing compliance management and control system and method based on artificial intelligence |
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 |