A pragmatic interoperability model construction method and device supporting edge intelligence collaboration

Abstract

The application relates to the technical field of electronic information engineering, in particular to a pragmatic interoperability model construction method and device supporting edge intelligent collaboration, which changes the pragmatic interoperability mode of separating data interaction and data application in a heterogeneous information system into an integrated pragmatic interoperability mode of data interaction, understanding and application by constructing an integrated pragmatic interoperability model covering an ontology knowledge base, a formatted instruction set and a collaborative driving engine, thereby improving the data interaction efficiency and timeliness in the task collaboration process and providing support for real-time and reliable edge intelligent collaborative control. While sharing data transmission, each subsystem can optimize the length of interactive data content and the data interaction process by understanding the semantics of the interactive data and the processing rules and processes of the interactive data in the collaborative task, thereby simplifying the content and / or the process without significantly reducing the efficiency of the collaborative task, and improving the efficiency and success rate of the task collaboration.

Description

Technical Field

[0001] The present application relates to the field of electronic information engineering technology, and in particular to a method and device for constructing a pragmatic interoperability model that supports edge intelligent collaboration. Background Art

[0002] Communication, broadly defined, requires addressing three fundamental issues: grammar (accurate transmission of symbols), semantics (consistent understanding of meaning), and pragmatics (precise control of behavior). Interoperability refers to the ability of two or more information systems to exchange and use information. While the two concepts overlap somewhat, they focus on different areas. The former focuses on information exchange between humans and information systems. With human involvement, information systems can ignore semantic and pragmatic issues. As a result, Shannon's grammatical information theory achieved significant success, significantly promoting the development of modern communication technology. The latter focuses on information exchange between machines. With the increasing autonomy and intelligence of machines, the issues of grammatical, semantic, and pragmatic interoperability between heterogeneous machines urgently need to be addressed.

[0003] In terms of syntactic interoperability, existing technologies define standard interfaces between universal ground control stations and different drones and payloads. On the other hand, the existing Joint Unmanned Systems (JAUS) establishes message sets and data protocols for unmanned ground vehicles, and later expands to more unmanned systems such as drones and unmanned ships to achieve syntactic interoperability between different unmanned systems and payloads.

[0004] In terms of semantic interoperability, existing technologies can, on the one hand, realize the automated application configuration and dynamic integration of multiple drones; on the other hand, they can enable machines to understand and reason about the meaning of sensor data, elevating the interoperability of various systems to the semantic level.

[0005] In terms of pragmatic interoperability, existing technologies, on the one hand, realize intelligent control problems in uncertain environments; on the other hand, realize the pragmatic combination construction of large-scale, diversified, and dynamic simulation systems through formal descriptions of behaviors and simulation context constraints.

[0006] In view of this, how to provide a pragmatic interoperability model construction method that supports edge intelligent collaboration, streamline content or simplify processes without significantly reducing the effectiveness of collaborative tasks, and improve task collaboration rate and success rate has become a technical problem that urgently needs to be solved. Summary of the Invention

[0007] The embodiments of the present application provide a method for constructing a pragmatic interoperability model that supports edge intelligent collaboration, a device for constructing a pragmatic interoperability model that supports edge intelligent collaboration, an electronic device, and a computer storage medium, which are used to solve the current problems of low task collaboration rate and success rate.

[0008] In a first aspect of an embodiment of the present application, a method for constructing a pragmatic interoperability model supporting edge intelligence collaboration is provided, comprising:

[0009] In the case where at least two devices collaborate to perform a target task, a task collaboration knowledge base and a task collaboration instruction set are created based on the target task, and the task collaboration knowledge base and the task collaboration instruction set are shared with each device, wherein the task collaboration knowledge base carries at least two ontology knowledge bases containing entity features corresponding to each device and entity relationships between the devices; the task collaboration instruction set is composed of a header and instruction content, and the content of each field in the instruction content is determined based on the field content in the interaction data format specified by metadata in the task collaboration knowledge base, and the length of the field content is adjustable;

[0010] Based on the task collaboration knowledge base and the task collaboration instruction set, each device is managed and controlled in terms of pragmatic behavior, and a task collaboration driving engine is created for each device based on the pragmatic behavior;

[0011] Based on the task collaboration driving engine, determining the interaction instructions corresponding to each device according to the instruction sending rules and instruction receiving rules carried in the task collaboration instruction set;

[0012] Based on the task collaboration driving engine, processing the instruction features of the interaction instructions corresponding to each device participating in the collaborative task to generate a new instruction, wherein the instruction features include field content and field length carried in the interaction instruction, and / or the instruction interaction process;

[0013] Based on the new instructions, each device is controlled to collaboratively execute the target task.

[0014] In a second aspect of an embodiment of the present application, a device for constructing a pragmatic interoperability model supporting edge intelligence collaboration is provided, comprising:

[0015] A first creation module is configured to, when at least two devices collaborate to perform a target task, create a task collaboration knowledge base and a task collaboration instruction set based on the target task, and share the task collaboration knowledge base and the task collaboration instruction set with each device, wherein the task collaboration knowledge base carries at least two ontology knowledge bases containing entity features corresponding to each device and entity relationships between the devices; the task collaboration instruction set is composed of a header and instruction content, the content of each field in the instruction content is determined based on the field content in the interaction data format specified by metadata in the task collaboration knowledge base, and the length of the field content is adjustable;

[0016] A second creation module is configured to perform pragmatic behavior management on each device based on the task collaboration knowledge base and the task collaboration instruction set, and create a task collaboration driving engine for each device based on the pragmatic behavior;

[0017] a determination module configured to determine, based on the task collaboration driving engine and in accordance with the instruction sending rules and instruction receiving rules carried in the task collaboration instruction set, the interaction instructions corresponding to each device;

[0018] a generation module configured to process, based on the task collaboration driving engine, instruction features of the interaction instructions corresponding to each device participating in the collaborative task, and generate a new instruction, wherein the instruction features include field content and field length carried in the interaction instruction, and / or the instruction interaction process;

[0019] The execution module is configured to control each device to collaboratively execute the target task based on the new instruction.

[0020] According to a third aspect of an embodiment of the present application, there is provided a computing device, including:

[0021] memory and processor;

[0022] The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the above-mentioned method for constructing a pragmatic interoperability model that supports edge intelligent collaboration are implemented.

[0023] According to the fourth aspect of the embodiment of the present application, a computer-readable storage medium is provided, which stores computer-executable instructions. When the instructions are executed by a processor, the steps of the above-mentioned method for constructing a pragmatic interoperability model that supports edge intelligent collaboration are implemented.

[0024] This application provides a method for constructing a pragmatic interoperability model that supports edge intelligent collaboration. First, a corresponding task collaboration knowledge base and task collaboration instruction set are created for heterogeneous system devices to collaboratively execute target tasks; then, based on the created task collaboration knowledge base and task collaboration instruction set, a task collaboration driving engine is created for each device; secondly, based on the created task collaboration driving engine, the instruction features of the interaction instructions of each device are processed to generate new instructions; finally, based on the new instructions, each device is controlled to collaboratively execute the target task.

[0025] By applying the method provided in the embodiment of the present application, by constructing an integrated pragmatic interoperability model covering an ontology knowledge base, a formatting instruction set, and a collaborative driving engine, the pragmatic interoperability mode in which data interaction and data application are separated in heterogeneous information systems is transformed into a joint grammatical semantic pragmatic interoperability mode that integrates data interaction, understanding, and application, thereby improving the efficiency and timeliness of data interaction in the task collaboration process and providing support for real-time, reliable edge intelligent collaborative control. While sharing data transmission, each subsystem can optimize the length of the interactive data content and the data interaction process by understanding the semantics of the interactive data and its processing rules and processes in the collaborative task, streamlining the content or (and) simplifying the process without significantly reducing the effectiveness of the collaborative task, thereby improving the efficiency of task collaboration and the success rate of completion.

[0026] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, which can be implemented in accordance with the contents of the specification, and to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Various other advantages and benefits will become apparent to those skilled in the art upon reading the detailed description of the preferred embodiment below. The accompanying drawings are for illustration purposes only and are not to be considered as limiting the present application. The same reference symbols are used throughout the drawings to represent the same components. In the drawings:

[0028] Figure 1 A flowchart of a method for constructing a pragmatic interoperability model supporting edge intelligence collaboration provided in an embodiment of the present application;

[0029] Figure 2 A schematic diagram of a pragmatic interoperability model in a method for constructing a pragmatic interoperability model supporting edge intelligence collaboration provided in an embodiment of the present application;

[0030] Figure 3 A schematic diagram of another pragmatic interoperability model in a method for constructing a pragmatic interoperability model supporting edge intelligence collaboration provided in an embodiment of the present application;

[0031] Figure 4 A schematic diagram of an ontology knowledge base in a method for constructing a pragmatic interoperability model supporting edge intelligence collaboration provided in an embodiment of the present application;

[0032] Figure 5 A schematic diagram of an interactive instruction set in a method for constructing a pragmatic interoperability model supporting edge intelligence collaboration provided in an embodiment of the present application;

[0033] Figure 6A flowchart of instruction interaction and behavior control in a method for constructing a pragmatic interoperability model supporting edge intelligence collaboration provided in an embodiment of the present application;

[0034] Figure 7 A schematic diagram of a simplified instruction set in a method for constructing a pragmatic interoperability model supporting edge intelligence collaboration provided in an embodiment of the present application;

[0035] Figure 8 A schematic diagram of a simplified task process in a method for constructing a pragmatic interoperability model supporting edge intelligence collaboration provided in an embodiment of the present application;

[0036] Figure 9 A schematic diagram of a new instruction interaction process in a method for constructing a pragmatic interoperability model supporting edge intelligence collaboration provided in an embodiment of the present application;

[0037] Figure 10 A schematic diagram of the structure of a pragmatic interoperability model construction device supporting edge intelligent collaboration provided in an embodiment of the present application;

[0038] Figure 11 A structural block diagram of a computing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0039] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0040] The embodiments of the present application provide a method for constructing a pragmatic interoperability model that supports edge intelligent collaboration, a device for constructing a pragmatic interoperability model that supports edge intelligent collaboration, an electronic device, and a computer storage medium, which are used to address the information interaction, understanding, and application problems of heterogeneous unmanned systems in the process of collaborative task execution, and improve the pragmatic data interaction efficiency and task success rate in the task collaboration process.

[0041] See also Figure 1 , Figure 1 A flowchart of a method for constructing a pragmatic interoperability model supporting edge intelligence collaboration provided in an embodiment of the present application. Figure 1 As shown, the specific steps include the following steps.

[0042] Step S102: In the case where at least two devices collaborate to perform a target task, a task collaboration knowledge base and a task collaboration instruction set are created based on the target task, and the task collaboration knowledge base and the task collaboration instruction set are shared with each device, wherein the task collaboration knowledge base carries at least two ontology knowledge bases containing entity features corresponding to each device and entity relationships between each device; the task collaboration instruction set is composed of a header and instruction content, and the content of each field in the instruction content is determined based on the field content in the interactive data format specified by the metadata in the task collaboration knowledge base, and the length of the field content is adjustable.

[0043] It should be noted that the embodiment of the present application can monitor the various devices participating in the collaborative task based on the monitoring and control platform; it can also designate one of the devices participating in the collaborative task as the monitoring and control platform to monitor all devices.

[0044] Taking the example of UAV A and UAV B performing a collaborative search and attack mission for target D, and monitoring and control platform C monitoring all interaction information between UAV A and UAV B during the mission execution, it should be noted that when UAV A and / or UAV B encounter abnormal situations, the management personnel can send control instructions to UAV A and / or UAV B through monitoring and control platform C, and ensure the safety of the unmanned platform through human intervention.

[0045] In the embodiment of the present application, the number of unmanned equipment is not limited to two, and the type of unmanned platform is not limited to drones and unmanned vehicles, but can also be unmanned boats, underwater unmanned submersibles, etc.

[0046] In the embodiment of the present application, the monitoring and control platform C is not necessary. In the case where the monitoring and control platform C exists, a simplified model including the ontology knowledge base and the task coordination instruction set is deployed on the monitoring and control platform C. Figure 2 , Figure 2 A schematic diagram of a pragmatic interoperability model in a method for constructing a pragmatic interoperability model that supports edge intelligent collaboration provided in an embodiment of the present application.

[0047] Specifically, in the case where at least two devices collaborate to perform a target task, a task collaboration knowledge base and a task collaboration instruction set are created based on the target task, including: in the case where at least two devices collaborate to perform a target task, the interaction information of each device in the process of collaboratively performing the target task is monitored through a monitoring and control platform; based on the interaction information, a task collaboration knowledge base and a task collaboration instruction set are created in the monitoring and control platform, and the task collaboration knowledge base and the task collaboration instruction set are shared with each device participating in the collaborative task.

[0048] In the absence of a monitoring and control platform C, we first determine one of the devices involved in the collaborative task as the monitoring and control platform, and then deploy the simplified model of the ontology knowledge base and the task collaborative instruction set on each device. Figure 3 , Figure 3 A schematic diagram of another pragmatic interoperability model in a method for constructing a pragmatic interoperability model that supports edge intelligent collaboration provided in an embodiment of the present application.

[0049] Specifically, in the case where at least two devices collaborate to perform a target task, a task collaboration knowledge base and a task collaboration instruction set are created based on the target task, including: in the case where at least two devices collaborate to perform a target task, the first device is used as a monitoring and control platform to monitor the interaction information of each device in the process of collaboratively performing the target task; based on the interaction information, an ontology knowledge base and a task collaboration instruction set are created in each device respectively, and the ontology knowledge base and the task collaboration instruction set are shared with each device participating in the collaborative task.

[0050] Therefore, the contents of the completed task collaboration knowledge base (or ontology knowledge base) and task collaboration instruction set need to be shared with UAV A and UCAV B in advance.

[0051] In an embodiment of the present application, creating a task collaboration knowledge base based on the target task includes: using the first device as a decision-making platform, creating a task collaboration knowledge base based on the target task, wherein the task collaboration knowledge base includes a first ontology knowledge base and a second ontology knowledge base; according to the first ontology knowledge base, triggering the first device to execute a first position reporting instruction, a target identification instruction, and a target reporting instruction; according to the second ontology knowledge base, triggering the second device to execute a second position reporting instruction, an electromagnetic interference instruction, and a fire strike instruction.

[0052] It should be noted that the task collaboration knowledge base here is generated by ontological modeling of the entities and inter-entity relationships that require data exchange during the collaborative task. This task collaboration knowledge base contains the ontological knowledge bases corresponding to all devices participating in the collaborative task. For example, drone A supports commands such as position reporting, target identification, and target reporting; unmanned vehicle B supports commands such as position reporting, electromagnetic interference, and fire strike. Position reporting commands are generated periodically and autonomously; target reporting commands are generated periodically after a target is identified; and target identification commands, electromagnetic interference commands, and fire strike commands are triggered by collaborative decision-making by the unmanned device platform.

[0053] The ontology knowledge base here includes but is not limited to entity name, entity description, entity type, entity state, entity behavior, entity relationship and entity capability; by instantiating the specific unmanned platforms and payloads in each ontology knowledge base, a collaborative ontology knowledge base is formed.

[0054] In the embodiment provided by the present application, the target D of the collaborative mission is not a self-propelled artillery, the target recognition function of the drone A can identify the target D, and the electromagnetic interference and firepower strike of the unmanned vehicle B have the ability to interfere with and strike the target D.

[0055] It should be noted that UAV A and UAV B use satellite navigation positioning with a positioning accuracy of 10 meters. After UAV A identifies target D, the positioning accuracy of target D is 30 meters. The electromagnetic interference range of UAV B is a hemisphere with a radius of 1000 meters centered on the target point. The damage range of UAV B to target D is a sphere with a radius of 500 meters centered on the target point. The ontology knowledge base constructed based on the above information can be found in Figure 4 ,in, Figure 4 A schematic diagram of an ontology knowledge base in a method for constructing a pragmatic interoperability model that supports edge intelligent collaboration provided in an embodiment of the present application.

[0056] In an embodiment of the present application, creating a task coordination instruction set based on the target task includes: using the first device as a decision-making platform, creating a task coordination instruction set based on the target task, wherein the task coordination instruction set includes a first task coordination instruction set and a second task coordination instruction set; according to the first task coordination instruction set, controlling the first device to periodically send first position report information and control command information to the second device; according to the second task coordination instruction set, controlling the second device to periodically send second position report information and control command response information to the first device.

[0057] It should be noted that in the process of creating a task collaboration instruction set, the data content that needs to be interacted in the collaborative task process is formatted and defined, and the metadata in the knowledge base is used to specify the arrangement order of each field in the interactive data format, but the length of the content of each field is not mandatory. At the same time, sending rules and receiving rules are specified for different types of interactive data, including but not limited to status instructions, control instructions, request instructions, etc., to form a task collaboration instruction set.

[0058] In the embodiment provided in this application, drone A needs to send its own position report information, target report information obtained by target recognition, and control command information to the unmanned vehicle. Unmanned vehicle B needs to send its own position report information and control command response information.

[0059] In addition, in the embodiment of the present application, the interactive information between drone A and unmanned vehicle B is designed using the instruction format of "header + instruction content", and each field in the instruction content is defined using metadata in the ontology knowledge base.

[0060] It should be noted that the header stipulates both the order and length of the fields, while the instruction content only stipulates the order of the fields and does not forcibly specify the length of each field. Therefore, the actual length of the instruction can be flexibly adjusted according to different tasks, different types of unmanned platforms or payloads.

[0061] For ease of use, the initial default length of each field can be given when agreeing on the field order. At the same time, according to the different types of instructions, the sending and receiving rules of each type of instruction are specified. For the interactive instruction set designed based on the knowledge base, see Figure 5 ,in, Figure 5 A schematic diagram of an interactive instruction set in a method for constructing a pragmatic interoperability model that supports edge intelligent collaboration provided in an embodiment of the present application.

[0062] Step S104: Based on the task collaboration knowledge base and the task collaboration instruction set, pragmatic behavior management is performed on each device, and based on the pragmatic behavior, a task collaboration driving engine is created for each device.

[0063] Step S106: Based on the task collaboration driving engine, the interaction instructions corresponding to each device are determined according to the instruction sending rules and instruction receiving rules carried in the task collaboration instruction set.

[0064] In an embodiment of the present application, the task collaboration driving engine is based on the instruction sending rules and instruction receiving rules carried in the task collaboration instruction set to determine the interaction instructions corresponding to each device, including: the first task collaboration driving engine corresponding to the first device generates a corresponding instruction according to the instruction sending rules and sends it to the second device, wherein the corresponding instruction carries the entity characteristics corresponding to the first device; the second device processes the received corresponding instruction according to the instruction receiving rules and executes the corresponding instruction.

[0065] It should be noted that the initial content and state of the collaborative driving engine here are the same, but during the operation of the collaborative driving engine, it learns and infers new content due to algorithm calls, so collaborative driving engine A and collaborative driving engine B are used to distinguish them.

[0066] However, if one collaborative driving engine, say, Collaborative Driving Engine A, infers new content, another collaborative driving engine, say, Collaborative Driving Engine B, can also infer the same content. This inconsistency can occur simply due to different algorithm execution times. For example, after understanding the mission intent, Collaborative Driving Engine A optimizes the length of the position report instruction, creating a new position report instruction format. At this point, Collaborative Driving Engine A contains this content, while Collaborative Driving Engine B does not. However, when Drone A sends the instruction using the new format to Unmanned Vehicle B, Collaborative Driving Engine B cannot decode it using its default instruction format. However, Collaborative Driving Engine B can infer the new instruction format used by Collaborative Driving Engine A and correctly decode it. Collaborative Driving Engine B then updates and stores the new instruction format, making the content of Collaborative Driving Engines A and B consistent.

[0067] In practical applications, the task collaboration engine is constructed and operated, managing its own pragmatic behavior based on a shared task collaboration knowledge base and task collaboration instruction set. This includes instruction sending, instruction receiving, payload control, and instruction optimization (e.g., instruction format and instruction interaction process), forming a collaborative driving engine. During operation, the collaborative driving engine understands and learns task intent from instruction interactions and streamlines the content and length of interactive instructions or simplifies the instruction interaction process based on the entity capabilities and behaviors of each participating node.

[0068] In the embodiment provided in this application, pragmatic behaviors such as instruction generation and sending, instruction reception and processing, and platform and payload behavior control are performed based on the ontology knowledge base and collaborative instruction set to promote the collaborative execution of tasks by drone A and unmanned vehicle B.

[0069] The collaborative driving engine of UAV A periodically sends position report instructions according to the knowledge in the ontology knowledge base. The period is 1 second, and the length of each field in the instruction content adopts the default length of the field with instruction type 01 in the collaborative instruction set. Similarly, UAV B periodically sends position report instructions with a period of 5 seconds, and each field in the instruction format adopts the default length.

[0070] When drone A is numbered 1001 and its latitude and longitude altitude is (longitude, latitude, altitude) = (128.24, 35.45, 350), the position report command sent by drone A is 0x000E0001FFFF03E90003E95B31612A326AF37C0000015E (hexadecimal);

[0071] When the unmanned vehicle B is numbered 1002 and its latitude and longitude altitude is (longitude, latitude, altitude) = (127.38, 34.54, 0), the position report command sent by the unmanned vehicle B is 0x000E0001FFFF03EA0003EA5A94D242311FA156 (hexadecimal).

[0072] After UAV B and UAV A receive each other's position report commands, their collaborative drive engines decode them according to the default command format of command type 01, and obtain UAV A's number 1001 and position (longitude, latitude, altitude) = (128.24, 35.45, 350), and UAV B's number 1002 and position (127.38, 34.54, 0).

[0073] During the mission execution process, the pragmatic behaviors involved by UAV A and UAV B mainly include starting target recognition, starting electromagnetic interference, and starting fire strikes.

[0074] Since UAV A and UAV B are equal roles, it is necessary to designate UAV A or UAV B as the decision-making platform in advance, or during the mission, UAV A and UAV B use a certain negotiation process to determine the decision-making platform in this mission.

[0075] For example, drone A is designated as the decision-making platform, and control commands are issued at the appropriate time. In this example, target recognition can be initiated as soon as drone A takes off. This is information exchange within drone A and does not involve information exchange with unmanned vehicle B.

[0076] When UAV A identifies target D, collaborative driving engine A generates a target report instruction and sends it periodically with a cycle of 10 seconds. The fields in the instruction format use the default length.

[0077] If the target D is between 10 km and 20 km away from the unmanned vehicle B, the drone A sends a coordinated control instruction to the unmanned vehicle B, and the control command is electromagnetic interference. If the target D is less than 10 km away from the unmanned vehicle B, the drone A sends a coordinated control instruction to the unmanned vehicle B for a fire strike.

[0078] The target report command and cooperative control command sent by UAV A all adopt the default command format of the corresponding type in the cooperative command set. The command interaction and behavior control process during the mission execution is as follows: Figure 6 As shown, Figure 6 A flowchart of command interaction and behavior control in a method for constructing a pragmatic interoperability model that supports edge intelligent collaboration is provided in an embodiment of the present application. Through this command interaction process, drone A and unmanned vehicle B can collaboratively complete target identification, electromagnetic interference and firepower strikes on target D.

[0079] In the above-mentioned process of identifying, interfering with and striking target D, collaborative driving engines A and B autonomously learn the mission intent (not necessarily the complete mission intent) through the interactive command content, that is, drone A and unmanned vehicle B should collaborate to complete target identification, electromagnetic interference and fire strike on targets of artillery type, thereby shortening the command length and simplifying the command interaction process.

[0080] Step S108: Based on the task collaboration driving engine, the instruction features of the interaction instructions corresponding to each device participating in the collaborative task are processed to generate new instructions, wherein the instruction features include the field content and field length carried in the interaction instruction, and / or the instruction interaction process.

[0081] In an embodiment of the present application, the task collaboration driving engine is based on which the instruction features of the interaction instructions corresponding to each device participating in the collaborative task are processed to generate new instructions, including: based on the task collaboration driving engine, the instruction interaction situations corresponding to each device participating in the collaborative task are understood and learned to determine the instruction features of the interaction instructions; according to the entity features corresponding to each device participating in the task collaboration, the instruction features corresponding to the interaction instructions are processed to generate a first new instruction, wherein the first new instruction is an instruction obtained by simplifying the field content and field length corresponding to the instruction; according to the entity features corresponding to each device participating in the task collaboration, the instruction interaction process corresponding to the interaction instruction is processed to generate a second new instruction, wherein the second new instruction is an instruction obtained by simplifying the instruction interaction process.

[0082] In the embodiment provided by the present application, for the collaborative driving engine A, it can be obtained from the ontology knowledge base that the satellite guidance positioning accuracy of the drone A is 10 meters, and the positioning accuracy of the drone A to the target D is 30 meters. Therefore, the lengths of the longitude, latitude, and altitude fields in the position report instruction can be shortened to 22 bits, 21 bits, and 10 bits, respectively, and the corresponding position accuracy is about 9.5 meters (the longitude range is -180° to 180°, the latitude range is -90° to 90°, and the altitude range is 0 to 10,000 meters); the target report can be The lengths of the longitude, latitude, and altitude fields in the target reporting instruction are shortened to 21 bits, 20 bits, and 9 bits, respectively, and the corresponding position accuracy is about 19.1 meters (the longitude, latitude, and altitude ranges are the same as above); considering that the electromagnetic interference range of the unmanned vehicle B is 1000 meters and the fire strike damage range is 500 meters, the lengths of the longitude, latitude, and altitude fields in the target reporting instruction can be further shortened to 17 bits, 16 bits, and 5 bits, respectively, and the corresponding position accuracy is about 312.5 meters (the longitude, latitude, and altitude ranges are the same as above).

[0083] Therefore, the collaborative driving engine A can generate a new reduced instruction set by reasoning. Figure 7 As shown, Figure 7 A schematic diagram of a simplified instruction set in a method for constructing a pragmatic interoperability model that supports edge intelligence collaboration provided in an embodiment of the present application.

[0084] For the collaborative driving engine B, it can be obtained by combining the task intent and the ontology knowledge base. In the collaborative task, the unmanned vehicle B is responsible for implementing electromagnetic interference and fire strikes on targets of artillery type. Therefore, once the location information of the corresponding target is obtained, the collaborative driving engine B can autonomously start electromagnetic interference or fire strikes according to its own electromagnetic interference range and fire strike range, without having to implement the corresponding behavior after receiving a collaborative control instruction with an electromagnetic interference control command or a collaborative control instruction with a fire strike control command. The collaborative driving engine B infers and generates a new simplified task process or instruction interaction process such as Figure 8 As shown, Figure 8 A schematic diagram of a simplified task process in a method for constructing a pragmatic interoperability model that supports edge intelligent collaboration provided in an embodiment of the present application.

[0085] Step S110: Based on the new instruction, control each device to collaboratively execute the target task.

[0086] In actual applications, each system or subsystem uses a streamlined new instruction format or a simplified new instruction interaction process to perform tasks. The collaborative driving engines of other members infer and decode the instruction format of the received instructions based on the collaborative knowledge base and the task collaborative instruction set, and record and store the new instruction format for use in subsequent task processes; the new instruction format and new interaction process can also continue to be iteratively optimized in subsequent task processes.

[0087] In the embodiment provided in this application, instruction sending and receiving are processed according to the new reduced instruction set. Figure 7 In the example, the simplified length 1 in the collaborative instruction set is used to send a position report command. In this case, Collaborative Drive Engine B cannot correctly decode the command using the default length. Therefore, it can be inferred that Collaborative Drive Engine A uses a new command format to send the command. In this case, logical reasoning can be used to determine the position report command format in Collaborative Drive Engine A. Alternatively, a fuzzy matching method can be used to infer the new command format by matching the optimal length field by field based on the field order, field meaning, and typical value range of the position report command in the collaborative instruction set, combined with UAV A's previous latitude, longitude, and altitude information. Similarly, other commands, such as the new target report command format, can be inferred using the same method.

[0088] In another embodiment of the present application, when there is a new collaborative task or an existing collaborative task is optimized, the task collaboration knowledge base, the task collaboration instruction set and the task collaboration driving engine can be iteratively updated simultaneously or separately, including but not limited to adding new entities or relationships to the collaborative ontology knowledge base, adding new interactive data formats to the task collaboration instruction set, adding new instruction optimization algorithms to the task collaboration driving engine, etc., to enhance the pragmatic interoperability capabilities of heterogeneous information systems.

[0089] In the embodiment provided by the present application, the mission is continued according to the new instruction interaction process. UAV A recognizes a new target E, and unmanned vehicle B is subject to electromagnetic interference from target E. Its wireless link with UAV A is unstable, and communication is intermittent. At this time, according to the previous mission process, unmanned vehicle B may fail the mission due to failure in transmission of collaborative control instructions. However, since UAV A periodically sends target report instructions for target E, as long as unmanned vehicle B receives a target report instruction once, the collaborative drive engine B can autonomously start electromagnetic interference and fire strikes at the appropriate location, reducing instruction interaction time and improving mission success rate. Figure 9 As shown, Figure 9 A schematic diagram of the new instruction interaction process in a method for constructing a pragmatic interoperability model that supports edge intelligent collaboration provided in an embodiment of the present application.

[0090] By constructing an integrated pragmatic interoperability model covering an ontology knowledge base, a formatting instruction set, and a collaborative driving engine, the pragmatic interoperability mode in which data interaction and data application are separated in heterogeneous information systems is transformed into a joint grammatical semantic pragmatic interoperability mode that integrates data interaction, understanding, and application. This makes the information interaction content more refined and the information interaction process simpler during task collaboration, thereby improving the efficiency of intelligent collaborative control.

[0091] The pragmatic interoperability model construction method provided in the embodiment of the present application constructs an integrated pragmatic interoperability model covering an ontology knowledge base, a formatting instruction set and an algorithm-driven engine. While sharing data transmission, each subsystem can understand the semantics of the interactive data and its processing rules and processes in collaborative tasks, and optimize the interactive data content length and data interaction process based on the task collaboration instruction set and the task collaboration driving engine, streamlining the content or (and) simplifying the process without significantly reducing the effectiveness of the collaborative task, thereby improving the efficiency and success rate of task collaboration.

[0092] Corresponding to the above method embodiment, this specification also provides an embodiment of a pragmatic interoperability model construction device supporting edge intelligent collaboration, Figure 10 This is a schematic diagram of a structure of a pragmatic interoperability model construction device supporting edge intelligence collaboration provided by an embodiment of the present application. Figure 10 As shown, the device includes:

[0093] The first creation module 1002 is configured to, when at least two devices collaborate to perform a target task, create a task collaboration knowledge base and a task collaboration instruction set based on the target task, and share the task collaboration knowledge base and the task collaboration instruction set with each device, wherein the task collaboration knowledge base carries at least two ontology knowledge bases containing entity features corresponding to each device and entity relationships between the devices; the task collaboration instruction set is composed of a header and instruction content, the content of each field in the instruction content is determined based on the field content in the interaction data format specified by metadata in the task collaboration knowledge base, and the field content length is adjustable;

[0094] The second creation module 1004 is configured to perform pragmatic behavior management on each device based on the task collaboration knowledge base and the task collaboration instruction set, and create a task collaboration driving engine for each device based on the pragmatic behavior;

[0095] The determination module 1006 is configured to determine the interaction instructions corresponding to each device based on the task collaboration driving engine and in accordance with the instruction sending rules and instruction receiving rules carried in the task collaboration instruction set;

[0096] The generation module 1008 is configured to process the instruction features of the interaction instructions corresponding to each device participating in the collaborative task based on the task collaboration driving engine to generate a new instruction, wherein the instruction features include the field content and field length carried in the interaction instruction and / or the instruction interaction process;

[0097] The execution module 1010 is configured to control each device to collaboratively execute the target task based on the new instruction.

[0098] In an optional embodiment, the first creation module 1002 is further configured to:

[0099] Using the first device as a decision-making platform, and based on the target task, creating a task collaboration knowledge base, wherein the task collaboration knowledge base includes a first ontology knowledge base and a second ontology knowledge base;

[0100] triggering the first device to execute a first position reporting instruction, a target identification instruction, and a target reporting instruction according to the first ontology knowledge base;

[0101] According to the second ontology knowledge base, the second device is triggered to execute the second position reporting instruction, the electromagnetic interference instruction and the fire strike instruction.

[0102] In an optional embodiment, the first creation module 1002 is further configured to:

[0103] Using the first device as a decision-making platform, creating a task coordination instruction set based on the target task, wherein the task coordination instruction set includes a first task coordination instruction set and a second task coordination instruction set;

[0104] controlling the first device to periodically send first location report information and control command information to the second device according to the first task coordination instruction set;

[0105] According to the second task coordination instruction set, the second device is controlled to periodically send second position report information and control command response information to the first device.

[0106] In an optional embodiment, the determining module 1006 is further configured to:

[0107] The first task collaborative driving engine corresponding to the first device generates a corresponding instruction according to the instruction sending rule and sends it to the second device, wherein the corresponding instruction carries the entity characteristics corresponding to the first device;

[0108] The second device processes the received corresponding instruction according to the instruction receiving rule and executes the corresponding instruction.

[0109] In an optional embodiment, the generating module 1008 is further configured to:

[0110] Based on the task collaboration driving engine, the command interaction corresponding to each device participating in the collaborative task is understood and learned, and the command characteristics of the interactive command are determined;

[0111] Processing, based on entity characteristics corresponding to each device participating in the task collaboration, instruction characteristics corresponding to the interaction instruction to generate a first new instruction, wherein the first new instruction is an instruction obtained by simplifying field content and field length corresponding to the instruction;

[0112] The instruction interaction process corresponding to the interaction instruction is processed according to the entity characteristics corresponding to each device participating in the task collaboration to generate a second new instruction, wherein the second new instruction is an instruction obtained by simplifying the instruction interaction process.

[0113] In an optional embodiment, the first creation module 1002 is further configured to:

[0114] In the case where at least two devices collaborate to perform a target task, the first device is used as a monitoring and control platform to monitor interaction information during the collaborative execution of the target task by each device;

[0115] Based on the interaction information, an ontology knowledge base and a task collaboration instruction set are created in each device respectively, and the ontology knowledge base and the task collaboration instruction set are shared with each device participating in the collaborative task.

[0116] In an optional embodiment, the first creation module 1002 is further configured to:

[0117] In the case where at least two devices collaborate to perform a target task, monitoring the interaction information of each device in the process of collaboratively performing the target task through the monitoring and control platform;

[0118] Based on the interaction information, a task collaboration knowledge base and a task collaboration instruction set are created in the monitoring and control platform, and the task collaboration knowledge base and the task collaboration instruction set are shared with each device participating in the collaborative task.

[0119] By constructing an integrated pragmatic interoperability model covering an ontology knowledge base, a formatting instruction set, and a collaborative driving engine, the pragmatic interoperability mode in which data interaction and data application are separated in heterogeneous information systems is transformed into a joint grammatical semantic pragmatic interoperability mode that integrates data interaction, understanding, and application. This makes the information interaction content more refined and the information interaction process simpler during task collaboration, thereby improving the efficiency of intelligent collaborative control.

[0120] Figure 11 This is a block diagram of a computing device according to an embodiment of the present application. The components of the computing device 1100 include, but are not limited to, a memory 1110 and a processor 1120. The processor 1120 is connected to the memory 1110 via a bus 1130, and a database 1150 is used to store data.

[0121] The computing device 1100 also includes an access device 1140 that enables the computing device 1100 to communicate via one or more networks 1160. Examples of these networks include a public switched telephone network (PSTN), a local area network (LAN), a wide area network (WAN), a personal area network (PAN), or a combination of communication networks such as the Internet. The access device 1140 may include one or more of any type of network interface (e.g., a network interface card (NIC)) whether wired or wireless, such as an IEEE 802.11 wireless local area network (WLAN) wireless interface, a Worldwide Interoperability for Microwave Access (Wi-MAX) interface, an Ethernet interface, a universal serial bus (USB) interface, a cellular network interface, a Bluetooth interface, or a near field communication (NFC) interface.

[0122] In one embodiment of the present specification, the above components of the computing device 1100 and Figure 11 Other components not shown in the figure may also be connected to each other, for example, via a bus. Figure 11 The computing device structure block diagram shown is for illustrative purposes only and is not intended to limit the scope of this specification. Those skilled in the art may add or replace other components as needed.

[0123] Computing device 1100 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., a tablet computer, personal digital assistant, laptop computer, notebook computer, netbook computer, etc.), a mobile phone (e.g., a smartphone), a wearable computing device (e.g., a smartwatch, smart glasses, etc.), or other types of mobile devices, or a stationary computing device such as a desktop computer or personal computer (PC). Computing device 1100 may also be a mobile or stationary server.

[0124] Among them, the processor 1120 is used to execute the following computer-executable instructions, which, when executed by the processor, implement the steps of the above-mentioned method for constructing a pragmatic interoperability model that supports edge intelligent collaboration.

[0125] Each embodiment in this specification is described in a progressive manner. The same or similar parts between the embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the computing device embodiment, since it is basically similar to the embodiment of the method for constructing a pragmatic interoperability model that supports edge intelligent collaboration, the description is relatively simple. For relevant parts, please refer to the partial description of the embodiment of the method for constructing a pragmatic interoperability model that supports edge intelligent collaboration.

[0126] An embodiment of the present specification also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the method for constructing a pragmatic interoperability model that supports edge intelligent collaboration.

[0127] Each embodiment in this specification is described in a progressive manner. The same or similar parts between the embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the computer-readable storage medium embodiment, since it is basically similar to the embodiment of the pragmatic interoperability model construction method supporting edge intelligent collaboration, the description is relatively simple. For relevant parts, please refer to the partial description of the embodiment of the pragmatic interoperability model construction method supporting edge intelligent collaboration.

[0128] An embodiment of the present specification also provides a computer program, wherein when the computer program is executed in a computer, the computer is caused to execute the steps of the above-mentioned method for constructing a pragmatic interoperability model that supports edge intelligent collaboration.

[0129] Each embodiment in this specification is described in a progressive manner. The same or similar parts between the embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the computer program embodiment, since it is basically similar to the embodiment of the method for constructing a pragmatic interoperability model that supports edge intelligent collaboration, the description is relatively simple. For relevant parts, please refer to the partial description of the embodiment of the method for constructing a pragmatic interoperability model that supports edge intelligent collaboration.

[0130] The foregoing description of this specification describes specific embodiments. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0131] The computer instructions include computer program code, which may be in source code form, object code form, executable file, or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal, and software distribution medium. It should be noted that the content contained in the computer-readable medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0132] It should be noted that the above description is of a specific embodiment of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-tasking and parallel processing are also possible or may be advantageous. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the embodiments of this specification.

[0133] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0134] The preferred embodiments disclosed above are intended only to help illustrate this specification. The optional embodiments do not exhaustively describe all details, nor do they limit the invention to the specific embodiments described. Obviously, many modifications and variations can be made based on the content of the embodiments of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the embodiments of this specification, so that those skilled in the art can better understand and utilize this specification. This specification is limited only by the claims and their full scope and equivalents.

Claims

1. A method for constructing a pragmatic interoperability model supporting edge intelligence collaboration, characterized in that: include: In the case where at least two devices collaborate to perform a target task, a task collaboration knowledge base and a task collaboration instruction set are created based on the target task, and the task collaboration knowledge base and the task collaboration instruction set are shared with each device, wherein the task collaboration knowledge base carries at least two ontology knowledge bases containing entity features corresponding to each device and entity relationships between the devices; the task collaboration instruction set is composed of a header and instruction content, and the content of each field in the instruction content is determined based on the field content in the interaction data format specified by metadata in the task collaboration knowledge base, and the length of the field content is adjustable; Based on the task collaboration knowledge base and the task collaboration instruction set, each device is managed and controlled in terms of pragmatic behavior, and a task collaboration driving engine is created for each device based on the pragmatic behavior; Based on the task collaboration driving engine, determining the interaction instructions corresponding to each device according to the instruction sending rules and instruction receiving rules carried in the task collaboration instruction set; Based on the task collaboration driving engine, processing the instruction features of the interaction instructions corresponding to each device participating in the collaborative task to generate a new instruction, wherein the instruction features include field content and field length carried in the interaction instruction, and / or the instruction interaction process; Based on the new instructions, control each device to collaboratively execute the target task; The step of creating a task collaboration knowledge base based on the target task includes: Using the first device as a decision-making platform, and based on the target task, creating a task collaboration knowledge base, wherein the task collaboration knowledge base includes a first ontology knowledge base and a second ontology knowledge base; triggering the first device to execute a first position reporting instruction, a target identification instruction, and a target reporting instruction according to the first ontology knowledge base; triggering the second device to execute the second position reporting instruction, the electromagnetic interference instruction, and the fire strike instruction according to the second ontology knowledge base; The step of creating a task coordination instruction set based on the target task includes: Using the first device as a decision-making platform, creating a task coordination instruction set based on the target task, wherein the task coordination instruction set includes a first task coordination instruction set and a second task coordination instruction set; controlling the first device to periodically send first location report information and control command information to the second device according to the first task coordination instruction set; controlling the second device to periodically send second location report information and control command response information to the first device according to the second task coordination instruction set; The step of processing the instruction features of the interaction instructions corresponding to the devices participating in the collaborative task based on the task collaborative driving engine to generate new instructions includes: Based on the task collaboration driving engine, the command interaction corresponding to each device participating in the collaborative task is understood and learned, and the command characteristics of the interactive command are determined; Processing, based on entity characteristics corresponding to each device participating in the task collaboration, instruction characteristics corresponding to the interaction instruction to generate a first new instruction, wherein the first new instruction is an instruction obtained by simplifying field content and field length corresponding to the instruction; The instruction interaction process corresponding to the interaction instruction is processed according to the entity characteristics corresponding to each device participating in the task collaboration to generate a second new instruction, wherein the second new instruction is an instruction obtained by simplifying the instruction interaction process.

2. The method according to claim 1, characterized in that The determining, based on the task collaboration driving engine and in accordance with the instruction sending rules and instruction receiving rules carried in the task collaboration instruction set, of the interaction instructions corresponding to each device includes: The first task collaborative driving engine corresponding to the first device generates a corresponding instruction according to the instruction sending rule and sends it to the second device, wherein the corresponding instruction carries the entity characteristics corresponding to the first device; The second device processes the received corresponding instruction according to the instruction receiving rule and executes the corresponding instruction.

3. The method according to claim 1, characterized in that In the case where at least two devices collaborate to perform a target task, creating a task collaboration knowledge base and a task collaboration instruction set based on the target task includes: In the case where at least two devices collaborate to perform a target task, the first device is used as a monitoring and control platform to monitor interaction information during the collaborative execution of the target task by each device; Based on the interaction information, an ontology knowledge base and a task collaboration instruction set are created in each device respectively, and the ontology knowledge base and the task collaboration instruction set are shared with each device participating in the collaborative task.

4. The method according to claim 1, wherein In the case where at least two devices collaborate to perform a target task, creating a task collaboration knowledge base and a task collaboration instruction set based on the target task includes: In the case where at least two devices collaborate to perform a target task, monitoring the interaction information of each device in the process of collaboratively performing the target task through the monitoring and control platform; Based on the interaction information, a task collaboration knowledge base and a task collaboration instruction set are created in the monitoring and control platform, and the task collaboration knowledge base and the task collaboration instruction set are shared with each device participating in the collaborative task.

5. A pragmatic interoperability model construction device supporting edge intelligence collaboration, characterized in that: include: A first creation module is configured to, when at least two devices collaborate to perform a target task, create a task collaboration knowledge base and a task collaboration instruction set based on the target task, and share the task collaboration knowledge base and the task collaboration instruction set with each device, wherein the task collaboration knowledge base carries at least two ontology knowledge bases containing entity features corresponding to each device and entity relationships between the devices; the task collaboration instruction set is composed of a header and instruction content, the content of each field in the instruction content is determined based on the field content in the interaction data format specified by metadata in the task collaboration knowledge base, and the length of the field content is adjustable; A second creation module is configured to perform pragmatic behavior management on each device based on the task collaboration knowledge base and the task collaboration instruction set, and create a task collaboration driving engine for each device based on the pragmatic behavior; a determination module configured to determine, based on the task collaboration driving engine and in accordance with the instruction sending rules and instruction receiving rules carried in the task collaboration instruction set, the interaction instructions corresponding to each device; a generation module configured to process, based on the task collaboration driving engine, instruction features of the interaction instructions corresponding to each device participating in the collaborative task, and generate a new instruction, wherein the instruction features include field content and field length carried in the interaction instruction, and / or the instruction interaction process; an execution module, configured to control each device to collaboratively execute a target task based on the new instruction; The step of creating a task collaboration knowledge base based on the target task includes: Using the first device as a decision-making platform, and based on the target task, creating a task collaboration knowledge base, wherein the task collaboration knowledge base includes a first ontology knowledge base and a second ontology knowledge base; triggering the first device to execute a first position reporting instruction, a target identification instruction, and a target reporting instruction according to the first ontology knowledge base; triggering the second device to execute the second position reporting instruction, the electromagnetic interference instruction, and the fire strike instruction according to the second ontology knowledge base; The step of creating a task coordination instruction set based on the target task includes: Using the first device as a decision-making platform, creating a task coordination instruction set based on the target task, wherein the task coordination instruction set includes a first task coordination instruction set and a second task coordination instruction set; controlling the first device to periodically send first location report information and control command information to the second device according to the first task coordination instruction set; controlling the second device to periodically send second location report information and control command response information to the first device according to the second task coordination instruction set; The step of processing the instruction features of the interaction instructions corresponding to the devices participating in the collaborative task based on the task collaborative driving engine to generate new instructions includes: Based on the task collaboration driving engine, the command interaction corresponding to each device participating in the collaborative task is understood and learned, and the command characteristics of the interactive command are determined; Processing, based on entity characteristics corresponding to each device participating in the task collaboration, instruction characteristics corresponding to the interaction instruction to generate a first new instruction, wherein the first new instruction is an instruction obtained by simplifying field content and field length corresponding to the instruction; The instruction interaction process corresponding to the interaction instruction is processed according to the entity characteristics corresponding to each device participating in the task collaboration to generate a second new instruction, wherein the second new instruction is an instruction obtained by simplifying the instruction interaction process.

6. A computer device, characterized in that: The computer device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program implements the steps of the method according to any one of claims 1 to 4 when executed by the processor.

7. A computer-readable storage medium, characterized in that The computer-readable storage medium stores an information transmission implementation program, and when the program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

Images