Intelligent agent communication method, device and equipment for transmitting virtual goods and medium

Abstract

Embodiments of the present disclosure disclose an agent communication method, device, equipment and medium for transmitting virtual goods. A specific embodiment of the method comprises: in response to receiving a communication request sent by a target agent, based on the communication request, obtaining a semantic graph fragment of the target agent for a virtual good; structurally processing the semantic graph fragment to generate a structured graph fragment; performing cognitive difference detection on the structured graph fragment and a target graph fragment to generate cognitive difference information; based on the cognitive difference information, generating a temporary cognitive alignment table; based on the temporary cognitive alignment table, generating a hybrid communication protocol for the target agent; creating a communication connection with the target agent according to the hybrid communication protocol, and performing a virtual good transmission operation based on the communication connection. This embodiment avoids the situation that virtual goods cannot be transmitted under different networks.

Description

Technical Field

[0001] Embodiments of this disclosure relate to the field of computer technology, and more specifically to intelligent agent communication methods, apparatus, devices, and media for transmitting virtual items. Background Technology

[0002] AI agents are systems built upon large language models, possessing autonomous decision-making, long-term memory, task planning, and tool invocation capabilities. With the rapid development of artificial intelligence technology, AI agents are widely used in the field of virtual item transfer. However, AI agents developed based on different frameworks often form "islands," lacking a unified communication standard, leading to low collaboration efficiency. Currently, when transferring virtual items (e.g., 3D models, virtual currency) between AI agents developed on different frameworks, the common method is to use open-source AI agent communication protocols such as MCP (Model Context Protocol) for virtual item transfer.

[0003] However, when using the above method to transfer virtual items between agents developed using two different frameworks, the following technical problems often arise: MCP uses a client-server architecture, which limits communication to local machines or intranets. It lacks remote connection capabilities and multi-agent routing functions, which prevents agents on different networks from transferring virtual items.

[0004] The information disclosed in this background section is only intended to enhance the understanding of the background of the inventive concept, and therefore may contain information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0005] The summary portion of this disclosure is intended to provide a brief overview of the concepts, which will be described in detail in the detailed description portion. This summary portion is not intended to identify key or essential features of the claimed technical solutions, nor is it intended to limit the scope of the claimed technical solutions.

[0006] Some embodiments of this disclosure provide intelligent agent communication methods, apparatuses, electronic devices, and computer-readable media for transmitting virtual items to address one or more of the technical problems mentioned in the background section above.

[0007] In a first aspect, some embodiments of this disclosure provide an agent communication method for transmitting virtual items. The method includes: responding to receiving a communication request sent by a target agent; obtaining a structured graph fragment of the target agent for the virtual item based on the communication request; performing cognitive difference detection on the structured graph fragment and a target graph fragment to generate cognitive difference information; generating a temporary cognitive alignment table based on the cognitive difference information; generating a hybrid communication protocol for the target agent based on the temporary cognitive alignment table; creating a communication connection with the target agent according to the hybrid communication protocol; and performing a virtual item transmission operation based on the communication connection.

[0008] Secondly, some embodiments of this disclosure provide an intelligent agent communication device for transmitting virtual items. The device includes: an acquisition unit configured to, in response to receiving a communication request sent by a target intelligent agent, acquire a structured graph fragment of the target intelligent agent for the virtual item based on the communication request; a cognitive difference detection unit configured to perform cognitive difference detection between the structured graph fragment and the target graph fragment to generate cognitive difference information; a first generation unit configured to generate a temporary cognitive alignment table based on the cognitive difference information; a second generation unit configured to generate a hybrid communication protocol for the target intelligent agent based on the temporary cognitive alignment table; and a creation unit configured to create a communication connection with the target intelligent agent according to the hybrid communication protocol, and perform a virtual item transmission operation based on the communication connection.

[0009] Thirdly, some embodiments of this disclosure provide an electronic device, including: one or more processors; and a storage device having one or more programs stored thereon, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation of the first aspect above.

[0010] Fourthly, some embodiments of this disclosure provide a computer-readable medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method described in any of the implementations of the first aspect above.

[0011] The above embodiments of this disclosure have the following beneficial effects: The intelligent agent communication method for transmitting virtual items according to some embodiments of this disclosure avoids the situation where intelligent agents on different networks cannot transmit virtual items. Specifically, the reason why intelligent agents on different networks cannot transmit virtual items is that MCP adopts a client-server architecture, limiting communication to the local machine or intranet, lacking remote connection capabilities and multi-Agent routing functions, thus preventing intelligent agents on different networks from transmitting virtual items. Based on this, the intelligent agent communication method for transmitting virtual items according to some embodiments of this disclosure firstly, in response to receiving a communication request sent by a target intelligent agent, obtains a structured graph fragment of the target intelligent agent for virtual items based on the communication request. This allows the determination of the target intelligent agent's knowledge graph. Secondly, cognitive difference detection is performed between the structured graph fragment and the target graph fragment to generate cognitive difference information. This allows the determination of cognitive differences with the target intelligent agent. Then, a temporary cognitive alignment table is generated based on the cognitive difference information. This allows the generation of an alignment table for cognitive alignment. Finally, a hybrid communication protocol for the target intelligent agent is generated based on the temporary cognitive alignment table. This allows the generation of a communication protocol for communication between intelligent agents. Finally, based on the aforementioned hybrid communication protocol, a communication connection is established with the target intelligent agent, and a virtual item transfer operation is performed based on this communication connection. Thus, a communication connection can be established through the generated communication protocol, enabling the transfer of virtual objects. Furthermore, because the virtual item transfer is based on the generated hybrid protocol, the inability to transfer virtual items across different networks is avoided. Attached Figure Description

[0012] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and elements are not necessarily drawn to scale.

[0013] Figure 1 This is a flowchart of some embodiments of the intelligent agent communication method for transmitting virtual items according to the present disclosure; Figure 2 This is a schematic diagram of the structure of some embodiments of the intelligent agent communication device for transmitting virtual items according to the present disclosure; Figure 3 This is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. Detailed Implementation

[0014] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0015] It should also be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings. Unless otherwise specified, the embodiments and features described in this disclosure can be combined with each other.

[0016] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0017] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0018] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0019] This disclosure will now be described in detail with reference to the accompanying drawings and embodiments.

[0020] Figure 1 A flow 100 of some embodiments of an agent communication method for transmitting virtual items according to the present disclosure is shown. The agent communication method for transmitting virtual items includes the following steps: Step 101: In response to receiving a communication request from the target agent, obtain the target agent's structured graph fragment for virtual items based on the communication request.

[0021] In some embodiments, the executing entity (e.g., a server) of the agent communication method for transmitting virtual items can, in response to receiving a communication request from a target agent, obtain a structured graph fragment of the target agent related to the virtual item based on the communication request. The target agent may be an agent that needs to transmit virtual items (e.g., transfer funds) with the executing entity. As an example, the target agent may be an agent of a bank used for transmitting virtual items. The virtual items may include, but are not limited to, virtual currency and documents. The communication request may be a request representing a communication connection with the executing entity. The structured graph fragment may be a fragment of a semantic graph related to the transmission of virtual items.

[0022] As an example, the above structured graph fragment may include: {Entities: User, Account A, Account B, Amount}, {Attributes: Amount has the attributes: value (value=1000), currency unit (unit=CNY)}, {Relationships: (User)->[Initiator]->(Transfer), (Transfer)->[Involved]->(Account A, Account B, Amount)}.

[0023] In practice, based on the above communication request, the following steps can be used to obtain the structured graph fragment of the target intelligent agent for virtual items: The first step is to determine the communication intention information of the target agent based on the received communication request. In practice, the communication intention information can be obtained by extracting the fields related to communication intention included in the communication request and performing semantic analysis on these fields to determine the communication intention information of the target agent.

[0024] The second step involves generating agent capability information in response to the aforementioned communication intention information representing a transmission request for virtual items, and then sending this agent capability information to the target agent. This agent capability information may be pre-stored business information of the agent. For example, the agent capability information may include, but is not limited to, virtual item transmission, virtual item storage, and data transmission.

[0025] The third step is to receive the structured graph fragments of virtual items sent by the target intelligent agent.

[0026] In addressing the technical problems mentioned in the background section, and considering the specific application scenario of cross-chain digital art transmission, the following technical issues arise: the sender and receiver of the cross-chain digital artwork reside on different blockchains; structural differences exist in the understanding of cross-chain digital artworks, making virtual item transmission impossible using existing protocols; and the cross-chain digital artworks are associated with sensitive information (e.g., personal information and unpublished exhibition information), leading to the leakage of sensitive information during transmission. To meet the following requirements for this application scenario—namely, alignment of transmission understanding and prevention of sensitive information leakage—we have decided to adopt the following solution: In some optional implementations of certain embodiments, the above-mentioned structured atlas fragments may be generated through the following sub-steps: The first sub-step involves activating the cognitive perception layer of the target agent in response to the target agent receiving the agent's capability information. This cognitive perception layer may include the agent's perception layer and cognitive / reasoning layer. The perception layer collects raw data and transforms it into usable information. The cognitive / reasoning layer processes the perception information generated by the perception layer, makes decisions, plans actions, and maintains knowledge.

[0027] The second sub-step involves performing intent recognition on the communication intent information based on the aforementioned cognitive perception layer to generate an intent keyword set. In practice, the executing entity can extract at least one intent keyword from the communication intent information through the cognitive perception layer to obtain the intent keyword set. The intent keywords in the intent keyword set can be keywords representing one of the following: actions, entities, and attributes. As an example, the action could be the transfer of virtual items. The entity can include, but is not limited to, the initiator. The attribute can include, but is not limited to, the transfer quantity (1000) and the transfer unit (CNY).

[0028] The third sub-step involves performing the following generation steps for each intent keyword in the aforementioned intent keyword set: The first generation step involves determining at least one traversal rule for the aforementioned intent keywords. In practice, different traversal rule information can be configured for different intent keywords.

[0029] As an example, if the intent keyword is "action," then the above traversal rule information can be used to traverse entities and relationships directly related to the action. If the intent keyword is "entity," then the above traversal rule information can be used to traverse the defined attributes of the entity itself. If the intent keyword is "attribute," then the above traversal rule information can be used to traverse attributes that are related to the above communication intent information.

[0030] The second generation step involves traversing the semantic graph corresponding to the target agent, centered on the aforementioned intent keywords, based on at least one of the aforementioned traversal rule information, to generate traversal results. This traversal can be performed using a breadth-first search algorithm.

[0031] The fourth sub-step is to merge the generated traversal results into a semantic subgraph.

[0032] The fifth sub-step involves pruning the semantic subgraph to generate a pruned semantic subgraph. In practice, the execution entity can delete other parent nodes if a node has multiple parent nodes but only one required parent node exists.

[0033] The sixth sub-step involves deleting at least one edge in the pruned semantic subgraph that satisfies a preset deletion condition to generate a graph fragment. The preset deletion condition can be a pre-defined condition for deleting irrelevant edges.

[0034] The seventh sub-step involves structuring the aforementioned graph fragments to generate structured graph fragments. In practice, firstly, the format corresponding to the structuring process can be determined. Here, the format can be JSON-LD. Secondly, the nodes and edges in the graph fragments can be converted into arrays corresponding to the aforementioned format to obtain the structured graph fragments.

[0035] The first and second steps described above, as an inventive point of this disclosure, combined with step "105" below, solve the technical problem: "When transmitting cross-chain digital artworks, the following technical problem arises: the sender and receiver of the cross-chain digital artwork exist on different blockchains; there are structural differences in understanding of cross-chain digital artworks, making it impossible to transmit virtual items using existing protocols; and the cross-chain digital artwork is associated with sensitive information (e.g., personal information and unpublished exhibition information), thus leading to the leakage of sensitive information during transmission." The reasons for the inability to transmit virtual items and the leakage of sensitive information are as follows: When transmitting cross-chain digital artworks, the following technical problem arises: the sender and receiver of the cross-chain digital artwork exist on different blockchains; there are structural differences in understanding of cross-chain digital artworks, making it impossible to transmit virtual items using existing protocols; and the cross-chain digital artwork is associated with sensitive information (e.g., personal information and unpublished exhibition information), thus leading to the leakage of sensitive information during transmission. If the above factors are resolved, the normal transmission of virtual items and the avoidance of sensitive information leakage can be achieved. To achieve this effect, this disclosure firstly, in response to the target agent receiving agent capability information, activates the cognitive perception layer included in the target agent; based on the cognitive perception layer, intention recognition is performed on the communication intention information to generate an intention keyword set. Thus, intention keywords can be generated through intention recognition via the cognitive perception layer. Secondly, for each intention keyword in the intention keyword set, the following generation steps are performed: First, determine at least one traversal rule information corresponding to the intention keyword; based on the at least one traversal rule information, traverse the semantic graph corresponding to the target agent with the intention keyword as the center to generate traversal results. Thus, traversal results corresponding to each intention keyword can be generated through traversal. Then, the generated traversal results are merged into a semantic subgraph. Thus, a semantic graph corresponding to the agent's capabilities can be generated. Afterwards, the semantic subgraph is pruned to generate a pruned semantic subgraph; at least one edge in the pruned semantic subgraph that satisfies a preset deletion condition is deleted to generate a graph fragment. Thus, sensitive information can be removed through pruning and other methods, preventing the leakage of sensitive information. Finally, the aforementioned graph fragments are processed to generate structured graph fragments. Thus, structured graph fragments can be generated. Combined with step "105" below, a communication connection is established with the target intelligent agent according to the aforementioned hybrid communication protocol, and a virtual item transfer operation is performed based on this communication connection. This completes the transfer of virtual items, while pruning operations prevent the leakage of sensitive information.

[0036] Step 102: Perform cognitive difference detection between the structured map fragment and the target map fragment to generate cognitive difference information.

[0037] In some embodiments, the executing entity may perform cognitive difference detection between the structured graph fragment and the target graph fragment to generate cognitive difference information. The target graph fragment may be a pre-defined semantic graph of the executing entity stored within it.

[0038] In practice, the following steps can be used to detect cognitive differences between the above structured map fragments and the target map fragments to generate cognitive difference information: The first step is to perform the following detection steps for each node in the above structured graph fragment: The first detection step involves selecting nodes from the target graph fragment that meet preset conditions as target nodes. These preset conditions can include a semantic similarity between two nodes being greater than or equal to a preset similarity threshold. In practice, the semantic similarity between two nodes can be determined using a Natural Language Processing (NLP) model.

[0039] The second detection step involves identifying at least one associated node of the target node, forming a target associated node set. This associated node can be a node in the target graph segment that is directly associated with the target node.

[0040] The third detection step involves comparing the target-related node set with each node associated with it to generate a cognitive difference result. In practice, in response to inconsistencies in the types and constraint ranges of edge or attribute values ​​among nodes, the inconsistent edge or attribute value types and constraint ranges can be identified as cognitive difference results. As an example, the cognitive difference result could be: difference type, elements (edges, nodes, attributes) in the target graph fragment, elements in the structured graph fragment, and a difference description. The difference description can be used to characterize the differences between elements in the target graph fragment and elements in the corresponding structured graph fragment.

[0041] The second step is to combine the generated cognitive difference results into cognitive difference information.

[0042] Step 103: Generate a temporary cognitive alignment table based on cognitive difference information.

[0043] In some embodiments, the aforementioned executing entity may generate a temporary cognitive alignment table based on the aforementioned cognitive difference information.

[0044] In practice, a temporary cognitive alignment table can be generated based on cognitive difference information through the following steps: The first step is to generate an initial temporary cognitive alignment table. This initial temporary cognitive alignment table is initially empty. It can be a data table used to store the various cognitive difference results, including cognitive difference information.

[0045] The second step involves filling the initial temporary cognitive alignment table with the node names and individual difference nodes included in the cognitive difference information for each cognitive difference result. These difference nodes can be elements representing nodes.

[0046] The third step is to confirm the completed initial temporary cognitive alignment table as the temporary cognitive alignment table.

[0047] Step 104: Generate a hybrid communication protocol for the target agent based on the temporary cognitive alignment table.

[0048] In some embodiments, the aforementioned executing entity may generate a hybrid communication protocol for the aforementioned target agent based on the aforementioned temporary cognitive alignment table.

[0049] In addressing the technical problems mentioned in the background section, and considering the application scenario where intelligent agents are deployed in mountainous areas with low network transmission, the following technical issues arise: limited bandwidth in mountainous areas leads to high latency and transmission interruptions, preventing the transmission of virtual items. To meet the following requirements for this application scenario—ensuring the integrity and timeliness of virtual item data—we have decided to adopt the following solution: In some alternative implementations of certain embodiments, the aforementioned executing agent may generate a hybrid communication protocol for the target agent based on a temporary cognitive alignment table through the following steps: The first step is to initialize the communication protocol component library. This library includes at least one group of communication protocol components. Each group can correspond to a protocol type. These protocol types can include, but are not limited to, authentication, encryption, transmission, and data format. The communication protocol components within the library can be pre-defined components used for a specific protocol type. For example, the communication protocol component group corresponding to the authentication protocol type could include: the Auth_X.509 authentication component and the Auth_DID authentication component.

[0050] The second step is to determine the node keyword corresponding to each difference node in the aforementioned temporary cognitive alignment table. In practice, the node name of the difference node can be used as the node keyword.

[0051] The third step involves determining the first and second requirement information corresponding to the temporary cognitive alignment table based on the generated keywords for each node. The first requirement information can be a functional requirement, while the second requirement information can be a non-functional requirement. For example, the first requirement information could be: the protocol must support a pre-defined data structure (e.g., JSON, Protocol Buffers). The second requirement information could be: low latency.

[0052] In practice, the first and second demand information corresponding to the above temporary cognitive alignment table can be determined based on the generated keywords of each node through the following sub-steps: The first sub-step involves filtering the keywords at each node to generate a first node keyword group and a second node keyword group. In practice, for each node keyword among the above-mentioned node keywords, semantic analysis is performed based on the cognitive difference points of the above-mentioned node keywords to filter the node keywords.

[0053] The second sub-step involves determining the cognitive difference information corresponding to each node keyword in the first node keyword group and the second node keyword group, respectively, to generate a first cognitive difference information set and a second cognitive difference information set. Here, cognitive difference information corresponding to the semantic analysis results of the above semantic analysis can be selected from a preset cognitive difference information database to generate the first and second cognitive difference information sets.

[0054] The third sub-step involves combining each piece of first cognitive difference information in the aforementioned first cognitive difference information set into first demand information, and combining each piece of second cognitive difference information in the aforementioned second cognitive difference information set into second demand information.

[0055] Fourth step: For each communication protocol component group in the above communication protocol component library, select the communication protocol component that satisfies the first requirement information and the second requirement information from the above communication protocol component group, and use it as the first protocol component and the second protocol component.

[0056] The fifth step is to generate a hybrid protocol set based on the selected first protocol components and second protocol components. In practice, at least one first protocol component with a different protocol type can be selected from the first protocol components and combined with at least one second protocol component with a different protocol type from the second protocol components to generate a hybrid protocol set.

[0057] As an example, in response to selecting two first protocol components representing authentication and encryption respectively from the aforementioned first protocol components, two second protocol components representing transmission and data format respectively can be selected from the aforementioned second protocol components.

[0058] Step 6: For each hybrid protocol in the aforementioned hybrid protocol set, determine the utility evaluation value corresponding to that hybrid protocol. Here, the utility evaluation value can be determined by setting weights. For example, different weight values ​​can be set for multiple preset utility domains, along with component scores for each protocol component, and the utility evaluation value can be determined using a weighted formula. The preset utility domains can be pre-defined domains used to evaluate the utility of protocols. For example, the preset utility domains can include, but are not limited to, security, transmission efficiency, and compatibility. Protocol component A can correspond to "security 27, transmission efficiency 51, compatibility 40". Furthermore, in response to the preset utility domain representing security, the sum of the security scores for each protocol component multiplied by the weight value corresponding to "security" can be used to determine the security score. The sum of the security score, transmission efficiency score, and compatibility score can be used to determine the utility evaluation value.

[0059] The seventh step is to determine the hybrid communication protocol for the target intelligent agent based on the determined utility evaluation values. In practice, the hybrid protocol corresponding to the utility evaluation value can be selected as the hybrid communication protocol.

[0060] Steps one through seven above, as an inventive point of this disclosure, combined with step 105 below, solve the technical problem: "Bandwidth limitations in mountainous areas lead to high latency and transmission interruptions, resulting in the inability to transmit virtual items." The reasons for this inability to transmit virtual items are as follows: When transmitting cross-chain digital artworks, the following technical problem arises: bandwidth limitations in mountainous areas lead to high latency and transmission interruptions, resulting in the inability to transmit virtual items. Solving these factors can avoid the inability to transmit virtual items. To achieve this, this disclosure first initializes a communication protocol component library. This generates a database for storing communication protocol components. Second, for each difference node in the temporary cognitive alignment table, the corresponding node keyword is determined. This determines the keyword for each difference node. Then, based on the generated node keywords, the first and second requirement information corresponding to the temporary cognitive alignment table are determined. This determines the requirement information corresponding to the required hybrid communication protocol. Next, for each communication protocol component group in the aforementioned communication protocol component library, communication protocol components that satisfy the first and second requirement information are selected from the aforementioned communication protocol component group as the first protocol component and the second protocol component, respectively. Based on the selected first and second protocol components, a hybrid protocol set is generated. Thus, multiple hybrid protocols satisfying the requirement information can be generated. Finally, for each hybrid protocol in the aforementioned hybrid protocol set, the utility evaluation value corresponding to the hybrid protocol is determined. Based on the determined utility evaluation values, a hybrid communication protocol for the aforementioned target intelligent agent is determined. Thus, the hybrid protocol with the highest transmission communication utility can be selected as the hybrid communication protocol. Combined with step "Step 105" below, a communication connection with the target intelligent agent is created according to the hybrid communication protocol, and a virtual item transmission operation is performed based on the communication connection. Thus, the transmission operation of virtual items can be completed through the generated hybrid communication protocol, avoiding situations where virtual items cannot be transmitted due to network limitations.

[0061] Step 105: Based on the hybrid communication protocol, establish a communication connection with the target intelligent agent, and perform a virtual item transfer operation based on the communication connection.

[0062] In some embodiments, the aforementioned execution entity may establish a communication connection with the aforementioned target intelligent agent in accordance with the aforementioned hybrid communication protocol, and perform virtual item transfer operations based on the aforementioned communication connection.

[0063] In practice, the following steps can be used to create a communication connection with the target intelligent agent according to a hybrid communication protocol, and then perform virtual item transfer operations based on the communication connection: The first step is to send the pre-generated hybrid communication protocol certificate to the target intelligent agent based on the above hybrid communication protocol.

[0064] The second step is to receive and verify the agent protocol certificate sent by the target agent to generate a verification result.

[0065] The third step is to respond to the above verification result indicating successful verification and receive the structured virtual item transmission request sent by the target intelligent agent.

[0066] The fourth step is to generate the first state information corresponding to the above-mentioned structured virtual item transmission request.

[0067] The fifth step involves performing logical verification on the structured virtual item transmission request based on the aforementioned target map fragment, in order to generate a logical verification result.

[0068] Step 6: In response to the above logical verification result indicating verification failure, generate second status information and an error code indicating verification failure.

[0069] Step 7: Send the above error code, the above first state information, and the above second state information to the above target intelligent agent.

[0070] Optionally, after step seven, in response to the above logical verification result indicating successful verification, a virtual item transfer operation is performed based on the above communication connection.

[0071] The above embodiments of this disclosure have the following beneficial effects: The intelligent agent communication method for transmitting virtual items according to some embodiments of this disclosure avoids the situation where intelligent agents on different networks cannot transmit virtual items. Specifically, the reason why intelligent agents on different networks cannot transmit virtual items is that MCP adopts a client-server architecture, limiting communication to the local machine or intranet, lacking remote connection capabilities and multi-Agent routing functions, thus preventing intelligent agents on different networks from transmitting virtual items. Based on this, the intelligent agent communication method for transmitting virtual items according to some embodiments of this disclosure firstly, in response to receiving a communication request sent by a target intelligent agent, obtains a structured graph fragment of the target intelligent agent for virtual items based on the communication request. This allows the determination of the target intelligent agent's knowledge graph. Secondly, cognitive difference detection is performed between the structured graph fragment and the target graph fragment to generate cognitive difference information. This allows the determination of cognitive differences with the target intelligent agent. Then, a temporary cognitive alignment table is generated based on the cognitive difference information. This allows the generation of an alignment table for cognitive alignment. Finally, a hybrid communication protocol for the target intelligent agent is generated based on the temporary cognitive alignment table. This allows the generation of a communication protocol for communication between intelligent agents. Finally, based on the aforementioned hybrid communication protocol, a communication connection is established with the target intelligent agent, and a virtual item transfer operation is performed based on this communication connection. Thus, a communication connection can be established through the generated communication protocol, enabling the transfer of virtual objects. Furthermore, because the virtual item transfer is based on the generated hybrid protocol, the inability to transfer virtual items across different networks is avoided.

[0072] Further reference Figure 2 As an implementation of the methods shown in the above figures, this disclosure provides some embodiments of an intelligent agent communication device for transmitting virtual items, these device embodiments being similar to... Figure 1 Corresponding to the method embodiments shown, the intelligent agent communication device for transmitting virtual items can be specifically applied to various electronic devices.

[0073] like Figure 2As shown, an intelligent agent communication device 200 for transmitting virtual items in some embodiments includes: an acquisition unit 201, a cognitive difference detection unit 202, a first generation unit 203, a second generation unit 204, and a creation unit 205. The acquisition unit 201 is configured to, in response to receiving a communication request sent by a target intelligent agent, acquire a structured graph fragment of the target intelligent agent for the virtual item based on the communication request; the cognitive difference detection unit 202 is configured to perform cognitive difference detection between the structured graph fragment and the target graph fragment to generate cognitive difference information; the first generation unit 203 is configured to generate a temporary cognitive alignment table based on the cognitive difference information; the second generation unit 204 is configured to generate a hybrid communication protocol for the target intelligent agent based on the temporary cognitive alignment table; and the creation unit 205 is configured to create a communication connection with the target intelligent agent according to the hybrid communication protocol, and to perform a virtual item transmission operation based on the communication connection.

[0074] It is understandable that the units described in the intelligent agent communication device 200 for transmitting virtual items are related to the reference... Figure 1 The steps in the described method correspond accordingly. Therefore, the operations, features, and beneficial effects described above for the method also apply to the intelligent agent communication device 200 for transmitting virtual items and the units contained therein, and will not be repeated here.

[0075] The following is for reference. Figure 3 This document illustrates a structural schematic of an electronic device 300 suitable for implementing some embodiments of the present disclosure. The electronic devices in some embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 3 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of this disclosure.

[0076] like Figure 3 As shown, the electronic device 300 may include a processing unit 301 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 into a random access memory (RAM) 303. The RAM 303 also stores various programs and data required for the operation of the electronic device 300. The processing unit 301, ROM 302, and RAM 303 are interconnected via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0077] Typically, the following devices can be connected to I / O interface 305: input devices 306 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 307 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 308 including, for example, magnetic tapes, hard disks, etc.; and communication devices 309. Communication device 309 allows electronic device 300 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 3 An electronic device 300 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively. Figure 3 Each box shown can represent a device or multiple devices as needed.

[0078] In particular, according to some embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, some embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication device 309, or installed from storage device 308, or installed from ROM 302. When the computer program is executed by processing device 301, it performs the functions defined in the methods of some embodiments of this disclosure.

[0079] It should be noted that, in some embodiments of this disclosure, the computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In some embodiments of this disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In some embodiments of this disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0080] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0081] The aforementioned computer-readable medium may be included within the aforementioned electronic device; or it may exist independently and not assembled into the electronic device. The aforementioned computer-readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to: in response to receiving a communication request from a target intelligent agent, acquire a structured graph fragment of the target intelligent agent for virtual items based on the communication request; perform cognitive difference detection between the structured graph fragment and a target graph fragment to generate cognitive difference information; generate a temporary cognitive alignment table based on the cognitive difference information; generate a hybrid communication protocol for the target intelligent agent based on the temporary cognitive alignment table; and establish a communication connection with the target intelligent agent according to the hybrid communication protocol, and perform a virtual item transfer operation based on the communication connection.

[0082] Computer program code for performing operations of some embodiments of this disclosure can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0083] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0084] The units described in some embodiments of this disclosure can be implemented in software or hardware. The described units can also be housed in a processor; for example, a processor may be described as including an acquisition unit, a cognitive difference detection unit, a first generation unit, a second generation unit, and a creation unit. The names of these units do not necessarily limit the specific unit itself; for example, the acquisition unit may also be described as "a unit that, in response to receiving a communication request from a target agent, acquires semantic graph fragments of virtual items from the target agent based on the communication request."

[0085] The functions described above in this document can be performed at least in part by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), and so on.

[0086] The above description is merely a selection of preferred embodiments of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in the embodiments of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described inventive concept. For example, technical solutions formed by substituting the above-described features with (but not limited to) technical features with similar functions disclosed in the embodiments of this disclosure.

Claims

1. An agent communication method for transmitting virtual items, applied to an agent communication system, comprising: In response to receiving a communication request from the target agent, based on the communication request, obtain a structured graph fragment of the target agent for virtual items; The structured map fragment and the target map fragment are subjected to cognitive difference detection to generate cognitive difference information; Based on the aforementioned cognitive difference information, a temporary cognitive alignment table is generated; Based on the temporary cognitive alignment table, a hybrid communication protocol for the target agent is generated. According to the hybrid communication protocol, a communication connection is created with the target intelligent agent, and a virtual item transfer operation is performed based on the communication connection.

2. The method according to claim 1, wherein, The step of responding to a communication request received from the target agent, and based on the communication request, obtaining a structured graph fragment of the target agent for virtual items, includes: In response to receiving a communication request from a target agent, the communication intention information of the target agent is determined based on the communication request; In response to the communication intent information representing a transmission request for a virtual item, agent capability information is generated, and the agent capability information is sent to the target agent. Receive the structured graph fragments of virtual items sent by the target intelligent agent.

3. The method according to claim 1, wherein, The step of performing cognitive difference detection between the structured map fragment and the target map fragment to generate cognitive difference information includes: For each node in the structured graph fragment, the following detection steps are performed: Nodes that meet preset conditions are selected from the target map segment and used as target nodes; Identify at least one associated node of the target node, as the target associated node set; The target associated node set is compared with each node associated with the node to generate cognitive difference results. The generated cognitive difference results are combined into cognitive difference information.

4. The method according to claim 3, wherein, The step of generating a temporary cognitive alignment table based on the cognitive difference information includes: Generate an initial temporary cognitive alignment table, wherein the initial temporary cognitive alignment table is empty; For each cognitive difference result included in the cognitive difference information, the node names and each difference node included in the cognitive difference result are filled into the initial temporary cognitive alignment table; The completed initial temporary cognitive alignment table is designated as the temporary cognitive alignment table.

5. The method according to claim 1, wherein, The step of establishing a communication connection with the target intelligent agent according to the hybrid communication protocol, and performing a virtual item transfer operation based on the communication connection, includes: Based on the hybrid communication protocol, the pre-generated hybrid communication protocol certificate is sent to the target intelligent agent; Receive and verify the agent protocol certificate sent by the target agent to generate a verification result; In response to the verification result indicating successful verification, a structured virtual item transmission request sent by the target intelligent agent is received; Generate first state information corresponding to the structured virtual item transmission request; Based on the target map fragment, the structured virtual item transmission request is logically verified to generate a logical verification result; In response to the logical verification result indicating verification failure, a second status information and an error code indicating verification failure are generated. The error code, the first status information, and the second status information are sent to the target intelligent agent.

6. The method according to claim 5, wherein, The step of establishing a communication connection with the target intelligent agent according to the hybrid communication protocol, and performing a virtual item transfer operation based on the communication connection, further includes: In response to the logical verification result indicating successful verification, a virtual item transfer operation is performed based on the communication connection.

7. An intelligent agent communication device for transmitting virtual items, comprising: The acquisition unit is configured to, in response to receiving a communication request sent by a target agent, acquire a structured graph fragment of the target agent for virtual items based on the communication request; A cognitive difference detection unit is configured to perform cognitive difference detection between the structured map fragment and the target map fragment to generate cognitive difference information; The first generation unit is configured to generate a temporary cognitive alignment table based on the cognitive difference information; The second generation unit is configured to generate a hybrid communication protocol for the target agent based on the temporary cognitive alignment table. The creation unit is configured to create a communication connection with the target intelligent agent according to the hybrid communication protocol, and to perform virtual item transfer operations based on the communication connection.

8. An electronic device, comprising: One or more processors; A storage device on which one or more programs are stored; When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1 to 6.

9. A computer-readable medium having a computer program stored thereon, wherein, When the program is executed by the processor, it implements the method as described in any one of claims 1 to 6.

Images