yujunjun/openspg
1
0
Fork 0
mirror of https://github.com/OpenSPG/openspg.git synced 2025-11-03 11:35:18 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(docs): fix readme document (#118)

Browse Source 
Co-authored-by: baifuyu <fuyu.bfy@antgroup.com>
This commit is contained in:
yixianlzz 2024-02-19 11:33:47 +08:00 committed by GitHub
parent 9326af4180
commit e95725d470
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 24 additions and 20 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
README.md
View File

@ -6,7 +6,7 @@
[OpenSPG](https://spg.openkg.cn/en-US) is a knowledge graph engine developed by Ant Group in collaboration with OpenKG, based on the SPG (Semantic-enhanced Programmable Graph) framework, which is a summary of Ant Group's years of experience in constructing and applying diverse domain knowledge graphs in the financial scenarios.
![OpenSPG Architecture](https://mdn.alipayobjects.com/huamei_xgb3qj/afts/img/A*DmdvRKo5pyYAAAAAAAAAAAAADtmcAQ/original)
![OpenSPG Architecture](https://mdn.alipayobjects.com/huamei_xgb3qj/afts/img/A*DsIHS7Fe78AAAAAAAAAAAAAADtmcAQ/original)
# SPG Background
@ -31,7 +31,12 @@ OpenSPG Core Capabilities:
* Abstracts KGDSL (Knowledge Graph Domain Specific Language) to provide programmable symbolic representation of logic rules.
* Supports downstream tasks, such as rule inference, neural/symbolic fusion learning, KG2Prompt linked LLM knowledge extraction/knowledge reasoning, represented in machine-understandable symbolic form.
* Define dependency and transfer between knowledge through predicate semantics and logic rules, and support modeling and analysis of complex business scenarios.
* Extensible SDK framework
* Programmable Framework -- KNext
* As a programmable framework of knowledge graph, KNext offers a set of extensible, procedural, and user-friendly components;
* It abstracts the core capabilities of knowledge graphs, congealing them into componentized, framework-oriented, and engine-built-in capabilities;
* Achieves isolation between the engine and business logic, domain models, facilitating rapid definition of knowledge graph solutions for businesses;
* Constructs a controllable AI technology stack driven by knowledge, based on the OpenSPG engine, connecting deep learning capabilities such as LLM and GraphLearning.
* Cloud Adaptation Layer -- Cloudext
* Business systems build their own characteristic business front-end by interfacing with open SDKs
* Extensible/adaptable customized graph storage/graph calculation engine
* Extensible/adaptable machine learning framework suitable for their own business characteristics
@ -40,18 +45,15 @@ OpenSPG Core Capabilities:
## Get Started
* [Install OpenSPG](https://spg.openkg.cn/en-US/quick-start/install)
* [Install OpenSPG](https://openspg.yuque.com/ndx6g9/ns5nw2/yl9p847hcfpluv46)
* Quick start with examples:
* [Enterprise Supply Chain Knowledge Graph](https://spg.openkg.cn/en-US/example/enterprise-supply-chain)
* [Risk Mining Knowledge Graph](https://spg.openkg.cn/en-US/example/risk-mining)
* [Medical Knowledge Graph](https://spg.openkg.cn/en-US/example/medical)
* [Enterprise Supply Chain Knowledge Graph](https://openspg.yuque.com/ndx6g9/ns5nw2/gyd703vk4l5qqb9y)
* [Risk Mining Knowledge Graph](https://openspg.yuque.com/ndx6g9/ns5nw2/yoleogat9akvyqnz)
* [Medical Knowledge Graph](https://openspg.yuque.com/ndx6g9/ns5nw2/kadwgc3iarqqemo1)
## Advanced tutorials
* [KNext command tool and SDK Tutorial](https://spg.openkg.cn/en-US/tutorial/knext)
* [SPG-Schema tutorial](https://spg.openkg.cn/en-US/tutorial/spgschema)
* [SPG-Reasoner Tutorial](https://spg.openkg.cn/en-US/tutorial/spgreasoner)
* [Adapting a new graph database tutorial](https://spg.openkg.cn/en-US/tutorial/spg2lpg)
* [OpenSPG User Guide](https://openspg.yuque.com/ndx6g9/ns5nw2)
# How to contribute

22
README_cn.md
View File

@ -4,7 +4,7 @@
(OpenSPG)[https://spg.openkg.cn] 是蚂蚁集团结合多年金融领域多元场景知识图谱构建与应用业务经验的总结，并与OpenKG联合推出的基于SPG(Semantic-enhanced Programmable Graph)框架研发的知识图谱引擎。
![OpenSPG Architecture](https://mdn.alipayobjects.com/huamei_xgb3qj/afts/img/A*YYSpQoItezMAAAAAAAAAAAAADtmcAQ/original)
![OpenSPG Architecture](https://mdn.alipayobjects.com/huamei_xgb3qj/afts/img/A*DsIHS7Fe78AAAAAAAAAAAAAADtmcAQ/original)
# SPG背景介绍
@ -30,7 +30,12 @@ OpenSPG核心能力模型包括：
* 抽象了KGDSL(Knowledge Graph Domain Specific Language)，为逻辑规则提供可编程的符号化表示。
* 以机器可理解的符号表示支持下游规则推理、神经/符号融合学习、KG2Prompt联动LLM知识抽取/知识推理等。
* 通过谓词语义和逻辑规则来定义知识之间的依赖和传递，并且支持对复杂的业务场景的建模和分析。
* 可扩展SDK框架
* 可编程框架KNext
* KNext作为图谱可编程框架，提供了一套可扩展，流程化，对用户友好的组件化能力；
* 抽象了图谱核心能力，沉淀为组件化、框架化、引擎内置的能力；
* 实现引擎与业务逻辑、领域模型的隔离，方便业务快速定义图谱解决方案；
* 构建以OpenSPG引擎为基础，知识驱动的可控AI技术栈，链接LLM、GraphLearning等深度学习能力。
* 云适配层Cloudext
* 业务系统通过SDK对接开放引擎，构建自身特色的业务前端
* 可扩展/适配自定义的图存储/图计算引擎
* 可扩展/适配适合自身业务特点的机器学习框架
@ -39,18 +44,15 @@ OpenSPG核心能力模型包括：
## Get Started
* [安装说明](https://spg.openkg.cn/quick-start/install)
* [安装说明](https://openspg.yuque.com/ndx6g9/ooil9x/xht6kkegvs33cwwr)
* 通过案例快速上手:
* [企业供应链图谱](https://spg.openkg.cn/example/enterprise-supply-chain)
* [黑产挖掘图谱](https://spg.openkg.cn/example/risk-mining)
* [医疗知识图谱](https://spg.openkg.cn/example/medical)
* [企业供应链图谱](https://openspg.yuque.com/ndx6g9/ooil9x/bf5kppyi5w0g7se5)
* [黑产挖掘图谱](https://openspg.yuque.com/ndx6g9/ooil9x/pst9v980k2u2p17o)
* [医疗知识图谱](https://openspg.yuque.com/ndx6g9/ooil9x/odbzpk4694lc7yfd)
## 进阶教程
* [KNext命令行工具和SDK教程](https://spg.openkg.cn/tutorial/knext)
* [知识建模Schema教程](https://spg.openkg.cn/tutorial/spgschema)
* [逻辑规则推理KGDSL教程](https://spg.openkg.cn/tutorial/spgreasoner)
* [适配新的图数据库教程](https://spg.openkg.cn/tutorial/spg2lpg)
* [用户手册](https://openspg.yuque.com/ndx6g9/ooil9x)
# 如何贡献代码