CN109146296A - 一种人工智能评估人才方法 - Google Patents
一种人工智能评估人才方法 Download PDFInfo
- Publication number
- CN109146296A CN109146296A CN201810989550.9A CN201810989550A CN109146296A CN 109146296 A CN109146296 A CN 109146296A CN 201810989550 A CN201810989550 A CN 201810989550A CN 109146296 A CN109146296 A CN 109146296A
- Authority
- CN
- China
- Prior art keywords
- answer
- vector
- artificial intelligence
- interview
- trainable
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/123—DNA computing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/105—Human resources
- G06Q10/1053—Employment or hiring
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Strategic Management (AREA)
- Biophysics (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- Quality & Reliability (AREA)
- Computational Linguistics (AREA)
- Tourism & Hospitality (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Operations Research (AREA)
- Evolutionary Biology (AREA)
- Marketing (AREA)
- Educational Administration (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- General Business, Economics & Management (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Development Economics (AREA)
- Genetics & Genomics (AREA)
- Game Theory and Decision Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
本发明提供了一种人工智能评估人才方法,包括以下步骤:首先,将分好词的问题以及答案利用词典映射成编码,利用层将编码转换为特征矩阵;其次,获取到答案和问题的句子表示后,计算以答案为主的权重;最后,经过全连接层得到答案的评分。本发明的有益效果是:可以实现人工智能面试代替人工初次面试,能够对候选人进行多维度评价,提高了面试效率和效果,降低了面试成本。
Description
技术领域
本发明涉及评价方法,尤其涉及一种人工智能评估人才方法。
背景技术
目前用人单位与求职者大多是通过现场或者视频会议的方式进行面试。
现有的招聘类产品与服务,一直沿袭着粗放式的信息(简历等)分发的状况,其中存在人的驱利本能所无法规避的问题:
(1)候选人在简历中有意隐瞒缺点或作假;同时也普遍存在着无意的作假,即由于候选人的自我认知偏差而导致的自我评价失真;
(2)很多高端岗位是异地面试,因面谈而产生的成本较高。
(3)现场面试需要用人单位和求职者同时有足够的时间才能够完成,占用彼此的时间。视频面试虽然可以足不出户利用连通了互联网的电脑,通过视频摄像头和耳麦进语音、视频、文字的方式进行即时沟通交流,但还是需要约定好同一时间,浪费人力和时间。
(4)不同的面试官,对问题会有不同的评价,同一面试官,因为不同的职场经验、面试技能和面试现场的认知状态下也会有不同的判断。另外虽然从国际人力资源以及人才管理领域引入的competency(国内翻译为胜任力、素质、能力)的概念,但从不同的翻译与缺乏知识系统的应用来看,产生非常多的不同的评估标准自然在所难免,最终导致评估效果的不确定性以及不利于持续的科学研究。
因此,如何提供一种人工智能评估人才方法,可以实现人工智能面试代替人工初次面试,能够对候选人进行多维度评价是本领域技术人员所亟待解决的技术问题。
发明内容
为了解决现有技术中的问题,本发明提供了一种人工智能评估人才方法。
本发明提供了一种人工智能评估人才方法,包括以下步骤:
首先,将分好词的问题q以及答案a利用词典映射成编码,利用embedding层将编码转换为特征矩阵
ea=wemb·ca (1)
eq=wemb·cq (2)
wemb为embedding层可训练的权重矩阵,ca表示编码后的答案向量,cq表示编码后的问题向量,dw为转换后每个词向量的长度,n为序列长度;在训练过程中特征矩阵会获得词级别的特征,获取到ea和eq后,使其经过双向LSTM层,LSTM指长短记忆网络,捕捉到整个句子的信息
ft=σ(wf·[ht-1,xt]+bf) (3)
it=σ(wi·[ht-1,xt]+bi) (4)
ot=σ(wo·[ht-1,xt]+bo) (7)
ht=ot×tanh(ct) (8)
r=[h1,h2,...,hn] (9)
wf,wi,wc,wo为可训练的权重矩阵,bf,bi,bc,bo为可训练的偏置向量,σ为sigmoid函数,dr为单向LSTM层隐藏状态的向量长度,xt为序列级别的特征输入,ft为遗忘门,it为输入门,ot为输出门,ct是细胞,ht为隐层状态;
其次,获取到答案和问题的句子表示ra,rq后,计算以答案为主的attention权重
将答案的句子表示ra与watt做数乘,对每行求平均值,生成包含问题和答案信息的全局表示
最后,h经过全连接层FCN得到答案的评分
I=avg(watt×ra) (11)
s=ws·l+bs (12)
其中,ws为可训练的权重矩阵,bs为可训练的偏置向量。
本发明的有益效果是:通过上述方案,可以实现人工智能面试代替人工初次面试,能够对候选人进行多维度评价,提高了面试效率和效果,降低了面试成本。
附图说明
图1是本发明一种人工智能评估人才方法的LSTM内部计算单元结构示意图。
图2是本发明一种人工智能评估人才方法的算法工作流程图。
具体实施方式
下面结合附图说明及具体实施方式对本发明作进一步说明。
如图1至图2所示,一种人工智能评估人才方法,利用深度学习相关方法,抽取问题和答案的高阶特征,并利用这些特征对答案进行打分,具体包括以下步骤:
首先,将分好词的问题q以及答案a利用词典映射成编码,利用embedding层将编码转换为特征矩阵
ea=wemb·ca (1)
eq=wemb·cq (2)
wemb为embedding层可训练的权重矩阵,ca表示编码后的答案向量,cq为编码后的问题向量,dw为转换后每个词向量的长度,n为序列长度;在训练过程中特征矩阵会获得词级别的特征,获取到ea和eq后,使其经过双向LSTM层,LSTM指长短记忆网络,捕捉到整个句子的信息
ft=σ(wf·[ht-1,xt]+bf) (3)
it=σ(wi·[ht-1,xt]+bi) (4)
ot=σ(wo·[ht-1,xt]+bo) (7)
ht=ot×tanh(ct) (8)
r=[h1,h2,…,hn] (9)
wf,wi,wc,wo为可训练的权重矩阵,bf,bi,bc,bo为可训练的偏置向量,σ为sigmoid函数,dr为单向LSTM层隐藏状态的向量长度,xt为序列级别的特征输入,ft为遗忘门,it为输入门,ot为输出门,ct是细胞,ht为隐层状态;
其次,获取到答案和问题的句子表示ra,rq后,计算以答案为主的attention权重
将答案的句子表示ra与watt做数乘,对每行求平均值,生成包含问题和答案信息的全局表示
最后,隐层输出向量h经过全连接层FCN得到答案的评分
I=avg(watt×ra) (11)
s=ws·l+bs (12)
其中,ws为可训练的权重矩阵,bs为可训练的偏置向量
为了更好的实现本发明,提高人工智能评估人才方法的效果,本发明还包括了由以下几个关键概念模型构建而成的Talent DNA才干模型:
A)Competency=Natural&Acquired Abilities(先天才能以及后天通过学习获得的才能)×Drive&Motivation(先天因为性格和智能所产生的动力以及后天通过价值观形成的动机而成的干劲),所以competency的正确翻译为才能与干劲,简称才干。
B)6C通用的人才培养框架
Care关爱–Self个人,Family家庭,Society社会,Environment环境;
Cognition认知–Learn to Learn学习怎样学习,Self-discovery自我发现,Thinking思维,Technologies科技,Humanities人文;
Culture文化–Own Culture自己的地域文化,Other Cultures他人的地域文化,Corporate Culture企业文化;
Communication沟通–Intrapersonal Communication内在反省的沟通,Interpersonal Communication人际关系的沟通,Communication Media&Tools沟通的媒介与工具;
Co-creation共创–Collaborative Creation&Innovation协作式创造创新,Problem Solving解决问题,Results/Values Orientation结果/价值导向;
Confidence自信–Self-esteem&Dignity自尊,Trustworthiness可信,Assertiveness坚定,Attitudes(Values&Beliefs)态度(价值观与信念),Resilience坚韧;
C)PILLAR专用的职场人才评估框架
6C框架下面的不同层次的元素组成了PILLAR:
Project Performance项目绩效才干–Co-creation共创;
Innovation&Influencing创新与影响才干–Collaborative Innovation协作式创新,Cognition Diversity多元认知&Communication沟通,Values价值观,Trust信任;
Learning学习才干–Cognition Diversity多元认知,Learn to Learn学习怎样学习;
Leadership领导才干–Care关爱,Cognition认知,Communication沟通,CorporateCulture企业文化,Co-creation共创,Confidence自信;
Attitudes态度–Values价值观,Beliefs信念;
Resilience坚韧–Care关爱,Problem Solving解决问题,Results/ValuesOrientation结果/价值导向;
才干定义与概念剖析以及6C框架的不同层次元素提炼出来的PILLAR框架配合人工智能的自然语言处理(包括端到端RNN+LSTM的语义分析)能针对候选人回复面试的开放式问题所给与的答案有打分的统一标准,同时AI有更高的效率和不受个人经验和状态的影响而产生的效果优势。
本发明提供的一种人工智能评估人才方法,基于上述模型设计了一套深度学习算法来自主学习Talent DNA模型,使其能够对候选人进行多维度评价,再利用统计方法生成详细的报告。
本发明提供的一种人工智能评估人才方法,可以利用人工智能代替人工初次面试,能够对候选人进行多维度评价,再利用统计方法生成详细的报告,并且,AI有更高的效率和不受个人经验和状态的影响而产生的效果优势。
以上内容是结合具体的优选实施方式对本发明所作的进一步详细说明,不能认定本发明的具体实施只局限于这些说明。对于本发明所属技术领域的普通技术人员来说,在不脱离本发明构思的前提下,还可以做出若干简单推演或替换,都应当视为属于本发明的保护范围。
Claims (1)
1.一种人工智能评估人才方法,其特征在于,包括以下步骤:
首先,将分好词的问题q以及答案a利用词典映射成编码,利用embedding层将编码转换为特征矩阵
ea=wemb·ca (1)
eq=wemb·cq (2)
wemb为embedding层可训练的权重矩阵,ca表示编码后的答案向量,cq表示编码后的问题向量,dw为转换后每个词向量的长度,n为序列长度;在训练过程中特征矩阵会获得词级别的特征,获取到ea和eq后,使其经过双向LSTM层,LSTM指长短记忆网络,捕捉到整个句子的信息
ft=σ(wf·[ht-1,xt]+bf) (3)
it=σ(wi·[ht-1,xt]+bi) (4)
ot=σ(wo·[ht-1,xt]+bo) (7)
ht=ot×tanh(ct) (8)
r=[h1,h2,...,hn] (9)
wf,wi,wc,wo为可训练的权重矩阵,bf,bi,bc,bo为可训练的偏置向量,σ为sigmoid函数,dr为单向LSTM层隐藏状态的向量长度,xt为序列级别的特征输入,ft为遗忘门,it为输入门,ot为输出门,ct是细胞,ht为隐层状态;
其次,获取到答案和问题的句子表示ra,rq后,计算以答案为主的attention权重
将答案的句子表示ra与watt做数乘,对每行求平均值,生成包含问题和答案信息的全局表示
最后,h经过全连接层FCN得到答案的评分
I=avg(watt×ra) (11)
s=ws·I+bs (12)
其中,ws为可训练的权重矩阵,bs为可训练的偏置向量。
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810989550.9A CN109146296A (zh) | 2018-08-28 | 2018-08-28 | 一种人工智能评估人才方法 |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810989550.9A CN109146296A (zh) | 2018-08-28 | 2018-08-28 | 一种人工智能评估人才方法 |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109146296A true CN109146296A (zh) | 2019-01-04 |
Family
ID=64828698
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810989550.9A Withdrawn CN109146296A (zh) | 2018-08-28 | 2018-08-28 | 一种人工智能评估人才方法 |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109146296A (zh) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109978339A (zh) * | 2019-02-27 | 2019-07-05 | 平安科技(深圳)有限公司 | Ai面试模型训练方法、装置、计算机设备及存储介质 |
CN111126578A (zh) * | 2020-04-01 | 2020-05-08 | 阿尔法云计算(深圳)有限公司 | 一种模型训练的联合数据处理方法、装置与系统 |
WO2021151993A1 (en) * | 2020-01-29 | 2021-08-05 | Cut-E Assessment Global Holdings Limited | Systems and methods for automating validation and quantification of interview question responses |
US11093901B1 (en) | 2020-01-29 | 2021-08-17 | Cut-E Assessment Global Holdings Limited | Systems and methods for automatic candidate assessments in an asynchronous video setting |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20160342895A1 (en) * | 2015-05-21 | 2016-11-24 | Baidu Usa Llc | Multilingual image question answering |
CN107133211A (zh) * | 2017-04-26 | 2017-09-05 | 中国人民大学 | 一种基于注意力机制的作文评分方法 |
CN107256228A (zh) * | 2017-05-02 | 2017-10-17 | 清华大学 | 基于结构化注意力机制的答案选择系统及方法 |
CN107562752A (zh) * | 2016-06-30 | 2018-01-09 | 富士通株式会社 | 对实体词的语义关系进行分类的方法、装置和电子设备 |
CN107967318A (zh) * | 2017-11-23 | 2018-04-27 | 北京师范大学 | 一种采用lstm神经网络的中文短文本主观题自动评分方法和系统 |
CN108021616A (zh) * | 2017-11-06 | 2018-05-11 | 大连理工大学 | 一种基于循环神经网络的社区问答专家推荐方法 |
CN108257052A (zh) * | 2018-01-16 | 2018-07-06 | 中南大学 | 一种在线学生知识评估方法及其系统 |
-
2018
- 2018-08-28 CN CN201810989550.9A patent/CN109146296A/zh not_active Withdrawn
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20160342895A1 (en) * | 2015-05-21 | 2016-11-24 | Baidu Usa Llc | Multilingual image question answering |
CN107562752A (zh) * | 2016-06-30 | 2018-01-09 | 富士通株式会社 | 对实体词的语义关系进行分类的方法、装置和电子设备 |
CN107133211A (zh) * | 2017-04-26 | 2017-09-05 | 中国人民大学 | 一种基于注意力机制的作文评分方法 |
CN107256228A (zh) * | 2017-05-02 | 2017-10-17 | 清华大学 | 基于结构化注意力机制的答案选择系统及方法 |
CN108021616A (zh) * | 2017-11-06 | 2018-05-11 | 大连理工大学 | 一种基于循环神经网络的社区问答专家推荐方法 |
CN107967318A (zh) * | 2017-11-23 | 2018-04-27 | 北京师范大学 | 一种采用lstm神经网络的中文短文本主观题自动评分方法和系统 |
CN108257052A (zh) * | 2018-01-16 | 2018-07-06 | 中南大学 | 一种在线学生知识评估方法及其系统 |
Non-Patent Citations (4)
Title |
---|
LIU YANG 等: "aNMM:Ranking Short Answer Texts with Attention-Based Neural Matching Model", 《CIKM’16》 * |
MING TAN 等: "LSTM-based deep learning models for non-factoid answer_selection", 《UNDER REVIEW AS A CONFERENCE PAPER AT ICLR 2016》 * |
吴芳颖: "基于分布式表示的答案质量自动评价", 《中国优秀硕士学位论文全文数据库·信息科技辑》 * |
程树东 等: "基于BI_LSTM_CRF模型的限定领域知识库问答系统", 《计算机与现代化》 * |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109978339A (zh) * | 2019-02-27 | 2019-07-05 | 平安科技(深圳)有限公司 | Ai面试模型训练方法、装置、计算机设备及存储介质 |
WO2021151993A1 (en) * | 2020-01-29 | 2021-08-05 | Cut-E Assessment Global Holdings Limited | Systems and methods for automating validation and quantification of interview question responses |
US11093901B1 (en) | 2020-01-29 | 2021-08-17 | Cut-E Assessment Global Holdings Limited | Systems and methods for automatic candidate assessments in an asynchronous video setting |
US11216784B2 (en) | 2020-01-29 | 2022-01-04 | Cut-E Assessment Global Holdings Limited | Systems and methods for automating validation and quantification of interview question responses |
CN115413348A (zh) * | 2020-01-29 | 2022-11-29 | 卡宜评估全球控股有限公司 | 用于自动验证和量化面试问题回答的系统和方法 |
CN115413348B (zh) * | 2020-01-29 | 2023-09-05 | 卡宜评估全球控股有限公司 | 用于自动验证和量化面试问题回答的系统和方法 |
US11880806B2 (en) | 2020-01-29 | 2024-01-23 | Cut-E Assessment Global Holdings Limited | Systems and methods for automatic candidate assessments |
CN111126578A (zh) * | 2020-04-01 | 2020-05-08 | 阿尔法云计算(深圳)有限公司 | 一种模型训练的联合数据处理方法、装置与系统 |
CN111126578B (zh) * | 2020-04-01 | 2020-08-25 | 阿尔法云计算(深圳)有限公司 | 一种模型训练的联合数据处理方法、装置与系统 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Gan et al. | Large language models in education: Vision and opportunities | |
CN109146296A (zh) | 一种人工智能评估人才方法 | |
Klein et al. | The poverty of scientism in information systems | |
Montana et al. | The need for improved reflexivity in conservation science | |
Byrne | Reframing teacher education in England: the case for a Bildung orientated approach | |
Luo et al. | Large language model and domain-specific model collaboration for smart education | |
Chetouani et al. | Human-centered artificial intelligence: Advanced lectures | |
Zhang | [Retracted] The Quality Evaluation of Business English Classroom Teaching Using Improved DA‐BP Algorithm | |
Hodge et al. | More-than-human theorising–Inclusive communities of practice in student practice-based learning | |
Yang et al. | [Retracted] Construction of Curriculum Ideological and Political Collaborative Education Mechanism Based on Edge Computing and Neural Network Algorithm | |
Hu et al. | [Retracted] The Construction of the Development Mode of School‐Enterprise Cooperation in Higher Vocational Education with the Aid of Sensitive Neural Network | |
Li | Convolutional Neural Network‐Based Mining of Civic Science Elements and Teaching Practice | |
Li et al. | [Retracted] Multimedia Computer‐Aided Teaching Platform Based on Particle Swarm Optimization Algorithm | |
Ganga | Educational Artificial Intelligence (EAI) Connotation, Key Technology and Application Trend-Interpretation and analysis of the two reports entitled “Preparing for the Future of Artificial Intelligence” and “The National Artificial Intelligence Research and Development Strategic Plan” | |
Zheng | Combined application of employment education and big data internet technology based on the context of vocational education reform | |
Zel et al. | Improving online learning experience using facial expression analysis | |
Shi et al. | Research on the Design and Implementation of Intelligent Tutoring System Based on AI Big Model | |
Filomeno et al. | An exploration of the educational situations in the Philippines from the lenses of the basic education teachers during the year of Covid-19 pandemics | |
Soroliou et al. | Pondering Deeper, Ahead and Beyond Over the Use of ChatGPT in H (A) Igher Education | |
Chyzhykova | Development of professional communicative competence of future lawyers in the process of teaching English | |
Gao | Innovative teaching strategies for art and design based on VAR model | |
Huang et al. | Improving College English Teaching Quality Through Wireless Network Artificial Intelligence in E-Learning | |
Ade Rusman et al. | Human Resource Management for Improving Internationalization at a Private University in Yogyakarta, Indonesia | |
Shi et al. | Research on the Integration of Curriculum Civics and Politics Construction into the High-Quality Talent Cultivation System for Rural Revitalization in the Internet Era | |
Heeren et al. | Coyote Management Plans and Wildlife Watch: implications for community coaching approach to public outreach in south-ern California |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
CB02 | Change of applicant information |
Address after: 200030 Xiaomuqiao Road 528, 201, 203, Xuhui District, Shanghai Applicant after: Shanghai Jinyu Intelligent Technology Co., Ltd. Address before: 210000 New Town Science Park, 69 Olympic Sports Street, Jianye District, Nanjing City, Jiangsu Province, 01 803 Applicant before: Nanjing Grape Credit Information Technology Co., Ltd. |
|
CB02 | Change of applicant information | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20190104 |
|
WW01 | Invention patent application withdrawn after publication |