GB/Z 185.2-2026Artificial intelligence - Agent interconnection - Part 2: Identity code (English PDF)

Foreword

This document is a standard or guiding technical document. This document conforms to GB/T 1.1-2020 "Standardization Work Guidelines Part

1.Structure and Drafting Rules of Standardization Documents". Drafting is scheduled. This document is Part 2 of GB /Z 185 "Artificial Intelligence - Interconnection of Intelligent Agents". GB /Z 185 has already published the following parts. --Part

2 Identification Code

1.Scope This document specifies the encoding rules, allocation, and management requirements for intelligent agent identity codes. This document applies to the formulation and application of intelligent agent identity codes in intelligent agent interconnection.

4.Abbreviations The following abbreviations apply to this document. OID. Object Identifier

5 Encoding Rules for Agent Identity Codes

5.1 Identification Structure The intelligent agent identification code encoding rules follow the relevant provisions of GB/T 26231 and adopt a hierarchical OID identification system. Intelligent Agent The identification code is composed of multiple layers of node identifiers in sequence, with each identifier represented by an Arabic numeral (0~9) or an English letter (A~Z). Note that letters are not case-sensitive and there are no spaces between them. The components of the identifier, from left to right, are. Agent Identity Code (OID), Agent Identity Code Version, and Agent Identity Registration Service. The components-the agent, the smart agent identity registration requester, and the custom serial number-are separated by a period ".". See Figure 1 for the specific structure. (The relationships between the components are also shown.) See Appendix A for the relevant relationships.

5.2 Agent Identity Code (OID) The agent identification code prefix is uniformly allocated and managed by the OID identification management department, and serves as the agent's identification code in the global identification system. The root identifier and starting point for resolving agent identity information are fixed at. 1.2.156.3088.There are three methods for international agents to obtain agent identity codes. Typical methods are shown in Appendix B. The agent identity code content is compiled by the operating organizations at all levels according to the agent identity code content structure defined in this document, and should be kept confidential. The certificate must be unique. See Appendix C for the implementation details of the agent's identity code encoding.

5.3 Agent Identification Code Version The version code distinguishes the identity code encoding rules of intelligent agents, with an identifier range of 1~Z, which can identify 35 versions. The intelligent agent identity code is agreed upon in the current file. The version number of the entity identification code is 1.

5.4 Intelligent Agent Identity Registration Service Provider There are usually multiple intelligent agent identity registration service providers. By combining the country/region code in the prefix, the specific service can be identified and determined. The provider of the intelligent agent identity registration service should be an organization, and its identity code should be assigned by the competent authority. The identifier range is 1~ZZZZZZ, and it can identify approximately 2 billion service providers.

5.5 Agent Identity Registration Requesting Party The identifier for each agent registration requester is assigned by the agent registration service provider. An agent registration requester can be... Organizations can also be individuals. The identifier ranges from 1 to ZZZZZZ, which can identify approximately 2 billion requesters.

5.6 Custom Serial Number The requirements for custom serial numbers are as follows:

a) The identity registration service provider sets the identifiers themselves, or they can be assigned numbers according to business type or other rules, ensuring uniqueness and... Traceability throughout the entire lifecycle.

b) After the intelligent agent identity registration service provider approves the application, it is advisable to assign the intelligent agent a serial number to distinguish the intelligent agent itself; Using an identifier range of 1 to ZZZZZZZZ, approximately 101 trillion entities can be identified.

c) The agent identity registration service provider should assign an agent instance serial number to the agent to identify whether it was created by the agent ontology. Example. When the registered object is the ontology itself, its instance serial number is identified by the specific character

0.It is advisable to use 1~ZZZZZZZZZ The identification range can identify approximately 101 trillion instances.

6.Requirements for the allocation and management of intelligent agent identity codes Regarding the allocation and management of agent identity codes.

a) Obsolete agent identity registration service provider codes should not be reassigned;

b) When the core functions of the agent ontology change, the agent identity registration requester should apply to update the agent ontology sequence. column number;

c) When multiple versions of a service coexist, different serial numbers should be assigned to the agent body.

6 Agent Interaction; --Part

7.Agent tool calls. Please note that some content in this document may involve patents. The issuing organization of this document assumes no responsibility for identifying patents. This document was proposed and is under the jurisdiction of the National Information Technology Standardization Technical Committee (SAC/TC 28). This document was drafted by: Beijing University of Posts and Telecommunications, China Electronics Technology Standardization Institute, Huawei Technologies Co., Ltd., and Ant Group. Joint-stock companies, Alibaba Cloud Computing Co., Ltd., Beijing Haohan Deep Information Technology Co., Ltd., and North China Electric Power Research Institute Co., Ltd. Limited Liability Company, China Mobile Internet Co., Ltd., Jiangsu JinFu Digital Group Artificial Intelligence Technology Co., Ltd., Xiamen Meiya Pico Information Security Research Institute Co., Ltd., Inspur Communication Information Systems Co., Ltd., China Mobile Communications Group Co., Ltd., Beijing Kuaishou Technology Co., Ltd. Kunlun Digital Technology Co., Ltd., China Electric Power Research Institute Co., Ltd., Super Fusion Digital Technology Co., Ltd., Inspur Cloud Communication Information Technology Co., Ltd., Beijing Volcano Engine Technology Co., Ltd., Zhejiang Dahua Technology Co., Ltd., Migu Culture Technology Co., Ltd. Nanjing University of Science and Technology, Inspur Software Technology Co., Ltd., AsiaInfo Technologies (China) Co., Ltd., ZTE Corporation, China Mobile (Hangzhou) Information Technology Co., Ltd., China Mobile Xiong'an Information and Communication Technology Co., Ltd., China Mobile Communications Group Guangdong Co., Ltd., Beijing Qi Tiger Technology Co., Ltd., Beijing Baolande Software Co., Ltd., Inspur General Software Co., Ltd., Chenxi Digital Intelligence (Beijing) Technology Co., Ltd. company. The main drafters of this document are. Liu Jun, Dong Jian, Gao Ge, Zhu Jintao, Lin Guotao, Xu Hao, Pang Shaomin, Xu Xiaotian, Wang Jia, Guan Junming, and Que Jinlong. Yang Yuche, Zhang Chuangang, Cao tide, Gu Chen, Shang Yunyun, Li Yan, Liu Jinnan, Zheng Jiajia, Du Ning, Kong Weisheng, Ma Limeng, Hao Guanya, Wang Kechen Zhang Lianhua, Zhao Xiaowu, Xie Xiaoyan, Zheng Qingguo, Lu Zhongda, Lan Wanshun, Ding Yifan, Yang Yingxuan, Shao Junqian, Liu Zhao.

With the rapid development of artificial intelligence technology, intelligent agents, as the key carriers for transforming artificial intelligence from a concept into actual productivity, are playing a crucial role in various fields. With increasingly widespread applications, the intelligent agent domain has played a significant role in empowering new industrialization and shaping new types of productivity. However, the current development of the intelligent agent industry faces many challenges. The challenge lies in the interoperability and interconnectivity between different intelligent agents. In the field of protocol-based agent interconnection, internationally recognized technologies include MCP and... While intelligent agent communication protocols such as A2A and ANP exist, no universally agreed-upon solution has been developed, necessitating the formulation of a solution suitable for the development of China's intelligent agent industry. An industry-wide consensus solution. To systematically address the aforementioned issues, guide and regulate the development of intelligent agent interconnection technology, and enhance the interoperability and composability of intelligent agent systems. To improve overall industry efficiency, this guiding technical document is specifically formulated. GB /Z 185 "Artificial Intelligence - Interconnection of Intelligent Agents" aims to define the interconnection of intelligent agents. The technical requirements and processes for interconnection are formulated following the principles of systematicity, advancement, and operability, enabling cross-platform and cross-architecture communication between intelligent agents. GB /Z 185 is proposed to consist of seven parts, providing a unified technical framework and standard basis for interconnection, interoperability and interoperability. --Part

1.Overall Architecture. The purpose is to provide a conceptual model and a functional model for an interconnected intelligent agent environment. --Part

2.Identity Code. The purpose is to define and apply the identity code for intelligent agents, and to provide the code structure and allocation principles. The suggestion is as follows: --Part

3.Identity Management. The aim is to provide a framework and full lifecycle process for identity management in an interconnected agent environment. Describe the technical requirements for identity management. --Part

4.Agent Description. The purpose is to provide a method for describing agents, and to provide methods for registering, modifying, and publishing agent descriptions. The reference process. --Part

5.Agent Discovery. The purpose is to provide a discovery process for agent interconnection. --Part

6.Agent Interaction. The aim is to present the interaction patterns of agents in a massive interconnected world, describing the basic elements of interaction and... Interface definition. --Part

7.Agent Tool Invocation. The aim is to provide a standardized architecture and flow for agents invoking tools based on large models. The process and tools are described, supporting seamless integration of intelligent agents with external tools. AI-powered intelligent agent interconnection Part