| 序号 | 专利名 | 申请号 | 申请日 | 公开（公告）号 | 公开（公告）日 | 发明人 |
|---|---|---|---|---|---|---|
| 341 | 一种智能语音客服系统 | CN201910538666.5 | 2019-06-20 | CN110351444A | 2019-10-18 | 陈奇峰 |
| 本发明公开了一种智能语音客服系统，包括用于储存语音交互的历史数据的后台数据库；用于与客户进行语音交互的语音系统；用于录取语音系统与客户的交互数据的录音系统；用于储存交互数据的云平台；用于对云平台储存的交互数据进行下载和分析的数据分析系统。采用上述技术方案，该智能电话机器人可以通过自然人声影带，并与用户进行多轮语音交流，主动向客户介绍产品，代替人工坐席，成功完成外呼工作；在标准话术的支持下，不会受情绪影响，能够准确的理解用户的回答及聊天意图，达到无障碍畅快交流；针对不同的场景进行批量规范的语音外呼操作，在保证语音外呼的质量及数量前提下大幅提升效率并显著降低人工通话中的诸多不可控因素。 | ||||||
| 342 | 一种基于WebGL对3D数字虚拟人实时行为渲染的方法 | CN202010775516.9 | 2020-08-05 | CN111882628A | 2020-11-03 | 梁宇淇; 付姝娟; 胡一博; 彭成; 刘成飞; 郭昱彤; 王蓉; 寇智博 |
| 本发明涉及3D数字虚拟人(又称“A.I数字人”、“3D数字人”、“虚拟形象”、“虚拟偶像”)实时渲染领域，主要通过WebGL技术在浏览器中实现仿真、模拟和学习人类真实的沟通与互动，大幅提升通用智能对话系统(俗称“对话机器人”或“聊天机器人”)的效率和质量，从而解决3D数字虚拟人实时渲染技术兼容性差、适应能力差的问题，大幅应用部署门槛及使用成本。1.使用WebGL技术实现3D数字虚拟人在各种浏览器上的行为渲染；2.通过智能仿生算法实时模拟人类真实沟通和互动过程中的表情、嘴型及肢体行为；3.具备极强的跨平台能力，通过对各种主流浏览器的兼容，轻松实现3D渲染技术在iOS、Android、Windows、Mac OS及Linux等平台的应用，摆脱对终端硬件性能的依赖，大幅降低应用部署门槛及使用成本。本发明通过一系列技术方法，最大限度地提升3D数字虚拟人的应用能力与范围，并可仿真、模拟和还原人类真实的互动与对话，以达到使用3D人物角色与人类进行无接触沟通与互动的目的。 | ||||||
| 343 | 一种智能陪伴机器人 | CN201521113984.0 | 2015-12-29 | CN205325695U | 2016-06-22 | 蔡东青 |
| 一种智能陪伴机器人，涉及智能玩具技术领域，其结构包括头部、躯干部、第一舵机、语言模块和控制器，头部设有显示屏和摄像头，第一舵机、语言模块、显示屏和摄像头均与控制器电连接，在控制器的控制下，第一舵机、语音模块和摄像头可单独动作也可协同动作，第一舵机驱动显示屏相对于躯干部做上下方向的转动，摄像头可对显示屏的上方和/或者下方的空间范围进行搜索，以对儿童的位置或者儿童的眼部视线进行定位，进而使显示屏转动至正对儿童或者儿童的眼部视线，这样不仅可多方位多角度地对儿童进行视频监控，而且能够更好地实现包括儿童与家人的视频聊天、儿童与机器人的智能语音交流、早教视频和图片的播放等在内的人机交互。 | ||||||
| 344 | 머신러닝을 활용한 정해진 시나리오로 고객과 상담하는 로봇 자동 상담 방법 및 시스템 | PCT/KR2017/007954 | 2017-07-24 | WO2018030672A1 | 2018-02-15 | 김우섭 |
머신러닝을 활용한 정해진 시나리오로 고객과 상담하는 로봇 자동 상담 방법 및 시스템이 개시된다. 본 발명의 일 실시예에 따른 로봇 상담 서비스에 가입한 고객이 소지한 고객 단말과 채팅 형식으로 상담을 진행하는 로봇 상담 시스템은, 상기 고객 단말과의 채팅 형식으로 대화 내용을 주고 받는 채팅 서버; 및 상기 채팅 서버에서 수신한 대화 내용을 머신러닝 기법으로 분석하고 분석 결과에 기초하여 대응되는 인트로노드가 존재하는 경우 정해진 상담 시나리오를 재생하여 상기 고객 단말과 시나리오 상담을 수행하고 대응되는 인트로노드가 존재하지 않는 경우 일반 상담을 수행하는 상담 서버를 포함할 수 있다. |
||||||
| 345 | FORMING CHATBOT OUTPUT BASED ON USER STATE | PCT/US2017/050297 | 2017-09-06 | WO2018063758A1 | 2018-04-05 | HORLING, Bryan; KOGAN, David; GARRETT, Maryam; KUNKLE, Daniel; QUAH, Wan Fen Nicole; HE, Ruijie; YUAN, Wangqing; CHEN, Wei; ITZ, Michael |
Techniques are described herein for chatbots to achieve more understandable communication with users by tracking users' states and providing corresponding dialog. In various implementations, input may be received from a user at a client device operating a chatbot, e.g., during a first session between the user and the chatbot. The input may be semantically processed to determine a state expressed by the user to the chatbot. An indication of the state expressed by the user may be stored in memory for future use by the chatbot. It may then be determined, e.g., by the chatbot based on various signals, that a second session between the user and the chatbot is underway. In various implementations, as part of the second session, the chatbot may output a statement formed from a plurality of candidate words, phrases, and/or statements based on the stored indication of the state expressed by the user. |
||||||
| 346 | 一种智能玩具 | CN201620335709.1 | 2016-04-20 | CN205796525U | 2016-12-14 | 杨再贵 |
| 本实用新型涉及玩具技术领域，具体涉及一种智能玩具，包括玩具壳体，还包括位于玩具壳体内部的中央处理器、语音控制芯片、供电电源器件、送话器和扬声器，所述供电电源器件分别与中央处理器、语音控制芯片、送话器和扬声器连接，所述送话器的信号输出端与所述语音控制芯片的信号输入端连接，所述中央控制器和所述语音控制芯片之间形成信号反馈控制电路，所述语音控制芯片的信号输出端与所述扬声器的信号输入端连接。本实用新型将传统玩具与智能机器人技术相结合，能够实现人机互动，通过网络云端服务器进行连接学习，实现唱歌、讲故事、聊天、游戏等趣味性功能。 | ||||||
| 347 | 一种可持续学习的智能客服回访系统 | CN202311304628.6 | 2023-10-09 | CN118411990A | 2024-07-30 | 赵胜; 张立斌; 丁卓 |
| 本发明公开了一种基于可持续学习的智能客服回访系统及方法,属于人工智能和客服领域。本发明通过构建专家系统、知识库、语音交互和自然语言处理模块,实现智能、自动化并可持续学习的客户回访和服务。本发明通过语音识别模块,实现语音信号到文本的转换,文本再通过语音合成模块转换为语音信号输出；这两者构成了完整的语音交互链路。接着,基于词向量和文本编码算法,将文本数据映射为数值向量表示,图像数据也通过卷积神经网络获得向量表示,完成多模态数据的向量化。在获得向量化表示的数据基础上,本发明构建了专家系统模块,运用基于知识图谱的问答匹配技术,准确解析用户需求及意图,实现对自然语言的深入理解。同时,依托预先构建的知识库,提供问答型对话服务。而对于无法匹配的问题,本发明使用基于Seq2Seq框架的聊天机器人技术实现流畅的开放域对话。此外,本发明还会分析用户对对话服务的反馈,持续更新完善知识库,实现系统能力的可持续进化。 | ||||||
| 348 | 一种深度模拟人类性格的大语言模型塑造方法 | CN202410297848.9 | 2024-03-15 | CN118113848A | 2024-05-31 | 赵玉良; 肖啟军; 吕晓永; 王婉越 |
| 本发明公开了一种深度模拟人类性格的大语言模型塑造方法，属于自然语言处理技术领域。该方法的实施包括以下步骤：本地化部署开源大语言模型；搜集“大五人格”性格工程知识库并进行数据处理，创建豆瓣小组进行人格对话语料库收集，撰写性格工程提示词；高效参数LoRA微调大语言模型；通过LangChain组件连接知识库、提示词、微调后的人格大语言模型进行人格文本输出；基于“大五人格”评价标准通过对话语聊评估大语言模型模拟人类性格的实验效果。本发明解决了传统对话聊天机器人单调无趣，难以定制独特语言风格的问题。它旨在通过使用提示词设定角色结合文本嵌入方法，利用外部数据微调大语言模型，使大语言模型输出文本具有人类性格特点，从而构造出能改变深度模拟人类特定性格特点的大语言模型。这一发明在提供精准对话、情感陪伴、心理治疗和安慰等方面可以发挥良好的效果，同时在医疗领域落地应用中具有广泛前景。 | ||||||
| 349 | PERSONALIZING DATA SYSTEM COMPONENTS AND DATA SOURCES AS CHATBOTS IN A GROUP CHAT SESSION | US14702096 | 2015-05-01 | US20160094492A1 | 2016-03-31 | Jeff J. Li; Ivan M. Milman; Wendi L. Nusbickel |
| Provided are techniques for personalizing data system components and data sources as chatbots in a group chat session. A social media gateway interface with a chat adapter for a chat application is provided. One or more chatbots that each represent a corresponding component of a data system are created. The one or more chatbots and the chatbot adapter are used to manage each corresponding component of the data system. | ||||||
| 350 | 智能护理机器人 | CN201520914698.8 | 2015-11-17 | CN205386819U | 2016-07-20 | 马国庆; 曹国华; 董新宇; 徐泽辉; 毕富国; 李国鹏; 曹晓捷 |
| 本实用新型智能护理机器人，属于机械制造及其自动化技术领域，解决了从传染源头切断病毒传播途径的技术问题；本实用新型外形似人体构造，包括头部、颈部、躯干和足部；头部通过颈部与躯干连接，躯干与足部固定连接；采用红外体温传感器，远程遥控完成体温数据的采集；利用躯干两侧的紫外线杀菌灯，实现杀菌消毒作用；云台摄像头在连网的状态下，能够进行点对点视频聊天，进行实时交流通过控制驱动电机，实现对物品的运送；机器人在行走的过程中当两只漫反射红外光电开关检测到前面有人时，把信号传给51单片机，51单片机控制电机停下并且使照明灯发光，主动轮停止转动，氙气灯和照明灯发出灯光指示，扩音器发出语音提示，实现自动避障；本实用新型替代了护理人员完成相关工作，避免了护理人员和患者的直接接触，从源头阻断疾病传播，有效地控制了病情的扩散。 | ||||||
| 351 | SYSTEMS AND PROCESSES FOR OPERATING AND TRAINING A TEXT-BASED CHATBOT | US15720234 | 2017-09-29 | US20180131645A1 | 2018-05-10 | Andrew Magliozzi; Charles DeTar; Brandon Horst; Peter Corey; Buruk Aregawi |
| Current chatbot systems cannot understand enough different topics to converse with students who have questions about college admissions, financial aid, courses, and other topics on the path to and through college. Current chatbots also have a hard time understanding misspellings, slang, and context-specific language, e.g., like the language used by students. “Learning” new topics is very time-consuming for current chatbots. And it is difficult for administrators to participate in student conversations carried out in part by current chatbots. To address these technical problems, an inventive chatbot uses a natural language processor (e.g., a neural network) to receive, classify, and respond to queries on thousands of different topics. An inventive chatbot can also request real-time assistance from an administrator when faced with a difficult query and learn on-the-fly from the administrator's response. This ability to learn on-the-fly gives inventive chatbots significant performance advantages over current chatbots. | ||||||
| 352 | FORMING CHATBOT OUTPUT BASED ON USER STATE | US15277954 | 2016-09-27 | US20180090137A1 | 2018-03-29 | Bryan Horling; David Kogan; Maryam Garrett; Daniel Kunkle; Wan Fen Nicole Quah; Ruijie He; Wangqing Yuan; Wei Chen; Michael Itz |
| Techniques are described herein for chatbots to achieve greater social grace by tracking users' states and providing corresponding dialog. In various implementations, input may be received from a user at a client device operating a chatbot, e.g., during a first session between the user and the chatbot. The input may be semantically processed to determine a state expressed by the user to the chatbot. An indication of the state expressed by the user may be stored in memory for future use by the chatbot. It may then be determined, e.g., by the chatbot based on various signals, that a second session between the user and the chatbot is underway. In various implementations, as part of the second session, the chatbot may output a statement formed from a plurality of candidate words, phrases, and/or statements based on the stored indication of the state expressed by the user. | ||||||
| 353 | Forming chatbot output based on user state | US15277954 | 2016-09-27 | US09947319B1 | 2018-04-17 | Bryan Horling; David Kogan; Maryam Garrett; Daniel Kunkle; Wan Fen Nicole Quah; Ruijie He; Wangqing Yuan; Wei Chen; Michael Itz |
| Techniques are described herein for chatbots to achieve greater social grace by tracking users' states and providing corresponding dialog. In various implementations, input may be received from a user at a client device operating a chatbot, e.g., during a first session between the user and the chatbot. The input may be semantically processed to determine a state expressed by the user to the chatbot. An indication of the state expressed by the user may be stored in memory for future use by the chatbot. It may then be determined, e.g., by the chatbot based on various signals, that a second session between the user and the chatbot is underway. In various implementations, as part of the second session, the chatbot may output a statement formed from a plurality of candidate words, phrases, and/or statements based on the stored indication of the state expressed by the user. | ||||||
| 354 | Method for personalizing chat bots | US12586851 | 2009-09-29 | US08818926B2 | 2014-08-26 | Richard Scot Wallace |
| A system and method for automatically building chat bot content from scripts of conversations. A script is parsed into query-response pairs, so that a computerized device may be programmed to give the same responses when given similar queries. Each query is converted into canonical form and then matched against patterns, as in prior art chat bots. The response is then linked to the matched pattern. A new chat bot is constructed out of the canonical form conversions and the set of pattern-response links. The chat bot is further improved by adding interactive human conversations, provided that those conversations are rated highly. The resulting chat bot can run on a computer server that responds to public queries, and the server can also display context-sensitive advertisements. | ||||||
| 355 | Method for personalizing chat bots | US12586851 | 2009-09-29 | US20110078105A1 | 2011-03-31 | Richard Scot Wallace |
| A system and method for automatically building chat bot content from scripts of conversations. A script is parsed into query-response pairs, so that a computerized device may be programmed to give the same responses when given similar queries. Each query is converted into canonical form and then matched against patterns, as in prior art chat bots. The response is then linked to the matched pattern. A new chat bot is constructed out of the canonical form conversions and the set of pattern-response links. The chat bot is further improved by adding interactive human conversations, provided that those conversations are rated highly. The resulting chat bot can run on a computer server that responds to public queries, and the server can also display context-sensitive advertisements. | ||||||
| 356 | 陪伴机器人 | CN201230570925.1 | 2012-11-23 | CN302351285S | 2013-03-13 | 卢秋红; 顾怡; 杜国斌; 卢飞宏; 杨建彬 |
| 1．本外观设计产品的名称：陪伴机器人。2．本外观设计产品的用途：用于个人和家庭中的娱乐陪伴，可以播放音乐、课件、跟人聊天对话等，属于机器人技术领域。3．本外观设计的设计要点：形状。4．最能表明设计要点的图片或者照片：主视图。 | ||||||
| 357 | 服务机器人（硬件） | CN201630143608.X | 2016-04-25 | CN303826604S | 2016-08-31 | 关岱松; 景鲲; 孙艳虎; 李佳霖 |
| 1．本外观设计产品的名称：服务机器人（硬件）。2．本外观设计产品的用途：本外观设计产品用于公众场合或餐厅、商铺等商业场所中，实现基于自然语言交互的点餐、信息咨询、聊天、娱乐等功能，属于人工智能机器人技术领域。3．本外观设计产品的设计要点：在于产品的外观设计。4．最能表明本外观设计设计要点的图片或照片：主视图。 | ||||||
| 358 | 服务机器人 | CN202230490944.7 | 2022-07-29 | CN307875826S | 2023-02-28 | 王相伟 |
| 1.本外观设计产品的名称：服务机器人。 2.本外观设计产品的用途：本外观设计产品用于公众场合或餐厅、商铺等商业场所中，实现基于自然语言交互的点餐、信息咨询、聊天、娱乐等功能，属于人工智能机器人技术领域。 3.本外观设计产品的设计要点：在于形状。 4.最能表明设计要点的图片或照片：立体图。 | ||||||
| 359 | 머신러닝을 활용한 정해진 시나리오로 고객과 상담하는 로봇 자동 상담 방법 및 시스템 | KR20160101041 | 2016-08-09 | KR20180017342A | 2018-02-21 | 김우섭 |
| 머신러닝을활용한정해진시나리오로고객과상담하는로봇자동상담방법및 시스템이개시된다. 본발명의일 실시예에따른로봇상담서비스에가입한고객이소지한고객단말과채팅형식으로상담을진행하는로봇상담시스템은, 상기고객단말과의채팅형식으로대화내용을주고받는채팅서버; 및상기채팅서버에서수신한대화내용을머신러닝기법으로분석하고분석결과에기초하여대응되는인트로노드가존재하는경우정해진상담시나리오를재생하여상기고객단말과시나리오상담을수행하고대응되는인트로노드가존재하지않는경우일반상담을수행하는상담서버를포함할수 있다. | ||||||
| 360 | 智能语音音响 | CN201630531643.9 | 2016-10-27 | CN304072743S | 2017-03-15 | 孙艳虎 |
| 1．本外观设计产品的名称：智能语音音响。 2．本外观设计产品的用途：本外观设计产品用于家庭场景，实现基于人工智能和自然 语言的语音指令点歌，交互问答、信息咨询、聊天、娱乐等功能，属于人工智能机器人技术领 域。 3．本外观设计产品的设计要点：在于本产品的形状。 4．最能表明本外观设计设计要点的图片或照片：立体图。 | ||||||
QQ群二维码
意见反馈
意见反馈