公开(公告)号：US20220245181A1

公开(公告)日：2022-08-04

申请号：US17622930

申请日：2020-06-22

Applicant: SEMICONDUCTOR ENERGY LABORATORY CO., LTD.

Inventor： Yoshitaka DOZEN ,  Kazuki HIGASHI ,  Kunitaka YAMAMOTO

IPC: G06F16/33 ,  G06F40/40 ,  G06F40/253 ,  G06F40/279

Abstract: A reading comprehension support system or a reading comprehension support method that enables natural language to be input as query text and presents a reader with a part that is highly related to the input text is provided. The reading comprehension support system includes a document readout unit that reads out a subject document, a document division unit that divides the subject document into a plurality of blocks, a first distributed representation acquisition unit that acquires a distributed representation of a word in each of the plurality of blocks, a query text readout unit that reads out query text, a second distributed representation acquisition unit that extracts a word included in the query text and acquires a distributed representation of the word, and a similarity acquisition unit that compares distributed representations of words between the query text and each of the plurality of blocks and obtains similarity. From words included in the block, the similarity acquisition unit searches for a word that matches a word included in the query text, and obtains similarity between a distributed representation of the matching word in the block and a distributed representation of the matching word in the query text.

公开(公告)号：US20210398025A1

公开(公告)日：2021-12-23

申请号：US17292783

申请日：2019-11-06

Applicant: Semiconductor Energy Laboratory Co., Ltd.

Inventor： Kunitaka YAMAMOTO ,  Junpei MOMO ,  Kazuki HIGASHI ,  Takahiro FUKUTOME

IPC: G06N20/20

Abstract: A novel content classification method is provided. A content classification method using machine learning for a learning model and a classifier fabrication method are provided. In Step 1, a data set containing a plurality of contents is acquired. Learning labels are attached to m contents, and the learning labels are not attached to the remaining contents. In Step 2, a first learning model is created by machine learning using the m contents. In Step 3, judgment labels are attached to the plurality of contents using the first learning model and are displayed on a GUI. In Step 4, new learning labels are attached to k contents in the plurality of contents. In Step 5, a second learning model is created by the machine learning using the k contents. In Step 6, judgment labels are attached to the plurality of contents using the second learning model and are displayed on the GUI.

公开(公告)号：US20240004936A1

公开(公告)日：2024-01-04

申请号：US18265105

申请日：2021-11-29

Applicant: SEMICONDUCTOR ENERGY LABORATORY CO., LTD.

Inventor： Yoshitaka DOZEN ,  Kunitaka YAMAMOTO

IPC: G06F16/9038 ,  G06F16/93

CPC classification number: G06F16/9038 ,  G06F16/93

Abstract: A search using a plurality of search queries and a check of a result of the search are performed efficiently. A plurality of search queries are received. A plurality of documents are searched on the basis of each of the plurality of search queries. A plurality of search results are obtained for each of the plurality of documents. The document search results are output by outputting the plurality of search results for each of the plurality of documents as a first table. One of a group of items on the vertical axis and a group of items on the horizontal axis in the first table represents the documents, and the other represents the search queries. The search result can be shown with two values indicating whether or not a document satisfies a search query, with the number of blocks satisfying a search query in a document, or the like.

公开(公告)号：US20230334097A1

公开(公告)日：2023-10-19

申请号：US18030196

申请日：2021-09-28

Applicant: Semiconductor Energy Laboratory Co., Ltd.

Inventor： Yoshitaka Dozen ,  Kunitaka YAMAMOTO

IPC: G06F16/903

CPC classification number: G06F16/90335 ,  G06F2216/11

Abstract: An information retrieval system that is capable of retrieving a similar application and value information of the similar application for a designated application is provided. An information retrieval system is provided that receives a designated application, calculates a first degree of similarity between a specification of the designated application and each of specifications of a plurality of applications, extracts a plurality of first similar applications from the plurality of applications on the basis of the first degree of similarity, calculates a second degree of similarity between a support drawing corresponding to the scope of claims of at least one of the plurality of first similar applications and at least one drawing of the designated application, extracts at least one drawing similar to the support drawing of at least one of the plurality of first similar applications from the drawings of designated application on the basis of the second degree of similarity, and outputs value information, the support drawing, and the similar drawing for at least one of the plurality of first similar applications. Related product information or the like can be given as the value information.

公开(公告)号：US20150069371A1

公开(公告)日：2015-03-12

申请号：US14539117

申请日：2014-11-12

Applicant: SEMICONDUCTOR ENERGY LABORATORY CO., LTD.

Inventor： Shunpei YAMAZAKI ,  Jun KOYAMA ,  Kunitaka YAMAMOTO ,  Toshimitsu KONUMA

IPC: H01L51/52

CPC classification number: H01L51/52 ,  H01L27/12 ,  H01L27/1214 ,  H01L27/3211 ,  H01L27/3244 ,  H01L27/3258 ,  H01L51/0005 ,  H01L51/0038 ,  H01L51/0042 ,  H01L51/0059 ,  H01L51/0062 ,  H01L51/0077 ,  H01L51/0078 ,  H01L51/0081 ,  H01L51/0085 ,  H01L51/0087 ,  H01L51/5237 ,  H01L51/524 ,  H01L51/5253 ,  H01L51/529

Abstract: An object of the present invention is to provide an EL display device having high operation performance and reliability.A third passivation film 45 is disposed under the EL element 203 comprising a pixel electrode (anode) 46, an EL layer 47 and a cathode 48, and diffusion of alkali metals from the EL element 203 formed by inkjet method into TFTs is prevented. Further, the third passivation film 45 prevents penetration of moisture and oxygen from the TFTs, and suppress degradation of the EL element 203 by dispersing the heat generated by the EL element 203.

Abstract translation: 本发明的目的是提供一种具有高操作性能和可靠性的EL显示装置。 第三钝化膜45设置在包括像素电极（阳极）46，EL层47和阴极48的EL元件203的下面，并且防止了碱金属从喷墨法形成的EL元件203扩散到TFT中。 此外，第三钝化膜45防止水分和氧从TFT渗透，并且通过分散由EL元件203产生的热量来抑制EL元件203的劣化。

公开(公告)号：US20250068669A1

公开(公告)日：2025-02-27

申请号：US18945924

申请日：2024-11-13

Applicant: SEMICONDUCTOR ENERGY LABORATORY CO., LTD.

Inventor： Kunitaka YAMAMOTO ,  Junpei MOMO ,  Kazuki HIGASHI

IPC: G06F16/35 ,  G06F16/93 ,  G06F40/268

Abstract: A document search system that enables efficient document search regardless of the ability of a user is achieved. Document search is performed using a document search system in which database document data is stored. After first document data and second document data are input to the document search system, the document search system extracts a plurality of terms from the first document data. The extraction of the terms is performed using morphological analysis, for example. Next, the extracted terms are weighted on the basis of the second document data. For example, texts included in a document represented by the second document data are classified into first and second texts. Among the terms extracted from the first document data, the weight of the term included in the first text is set larger than the weights of the other terms. The classification of the texts can be performed in accordance with a rule basis or using machine learning. After that, the similarity of the database document data to the first document data is calculated on the basis of the weighted term.

公开(公告)号：US20220197935A1

公开(公告)日：2022-06-23

申请号：US17612248

申请日：2020-05-11

Applicant: SEMICONDUCTOR ENERGY LABORATORY CO., LTD.

Inventor： Kunitaka YAMAMOTO ,  Junpei MOMO ,  Kazuki HIGASHI

IPC: G06F16/35 ,  G06F40/268 ,  G06F16/93

Abstract: A document search system that enables efficient document search regardless of the ability of a user is achieved. Document search is performed using a document search system in which database document data is stored. After first document data and second document data are input to the document search system, the document search system extracts a plurality of terms from the first document data. The extraction of the terms is performed using morphological analysis, for example. Next, the extracted terms are weighted on the basis of the second document data. For example, texts included in a document represented by the second document data are classified into first and second texts. Among the terms extracted from the first document data, the weight of the term included in the first text is set larger than the weights of the other terms. The classification of the texts can be performed in accordance with a rule basis or using machine learning. After that, the similarity of the database document data to the first document data is calculated on the basis of the weighted term.

公开(公告)号：US20150194631A1

公开(公告)日：2015-07-09

申请号：US14664167

申请日：2015-03-20

Applicant: Semiconductor Energy Laboratory Co., Ltd.

Inventor： Shunpei YAMAZAKI ,  Jun KOYAMA ,  Kunitaka YAMAMOTO ,  Toshimitsu KONUMA

IPC: H01L51/52 ,  H01L27/32

CPC classification number: H01L51/5253 ,  H01L23/3171 ,  H01L27/1214 ,  H01L27/1248 ,  H01L27/322 ,  H01L27/3244 ,  H01L27/3258 ,  H01L29/78621 ,  H01L51/529 ,  H01L51/56 ,  H01L2924/0002 ,  Y10S428/917 ,  H01L2924/00

Abstract: An object of the present invention is to provide an EL display device, which has a high operating performance and reliability.A third passivation film 45 is disposed under an EL element 203 which comprises a pixel electrode (anode) 46, an EL layer 47 and a cathode 48, to make a structure in which heat generated by the EL element 203 is radiated. Further, the third passivation film 45 prevents alkali metals within the EL element 203 from diffusing into the TFTs side, and prevents moisture and oxygen of the TFTs side from penetrating into the EL element 203. More preferably, heat radiating effect is given to a fourth passivation film 50 to make the EL element 203 to be enclosed by heat radiating layers.

Abstract translation: 本发明的目的是提供一种具有高操作性能和可靠性的EL显示装置。 第三钝化膜45设置在包括像素电极（阳极）46，EL层47和阴极48的EL元件203的下方，以形成其中辐射由EL元件203产生的热量的结构。 此外，第三钝化膜45防止EL元件203内的碱金属扩散到TFT侧，并且防止TFT侧的水分和氧气渗透到EL元件203中。更优选地，将散热效果提供给第四钝化膜 钝化膜50以使EL元件203被散热层包围。

公开(公告)号：US20250094738A1

公开(公告)日：2025-03-20

申请号：US18825413

申请日：2024-09-05

Applicant: Semiconductor Energy Laboratory Co., Ltd.

Inventor： Junpei MOMO ,  Kana INAHATA ,  Kunitaka YAMAMOTO

IPC: G06F40/58 ,  G06F40/117

Abstract: An information processing system including a first information processing device and a second information processing device is provided. The first information processing device generates a first processing result including a first translation and a second translation in accordance with a first prompt and transmits the first processing result. The first information processing device generates a second processing result including a third translation and a fourth translation in accordance with a second prompt and transmits the second processing result. The second information processing device is configured to receive a document, metadata, a summary, a first processing result, and a second processing result. The second information processing device is configured to cut a character string with a predetermined length from the beginning of the document.

公开(公告)号：US20240394302A1

公开(公告)日：2024-11-28

申请号：US18791489

申请日：2024-08-01

Applicant: SEMICONDUCTOR ENERGY LABORATORY CO., LTD.

Inventor： Kengo AKIMOTO ,  Shigeru TAMAKI ,  Kunitaka YAMAMOTO ,  Isamu SHIGEMORI

IPC: G06F16/58 ,  G06F16/53 ,  G06F16/583 ,  G06F40/268 ,  G06N3/045

Abstract: An image retrieval system with high retrieval accuracy is provided. The image retrieval system includes a database and a processing portion. The database has a function of storing a plurality of pieces of database image data, and a database tag is linked to each of the plurality of pieces of database image data. The processing portion has a function of obtaining database image feature value data representing a feature value of the database image data for each piece of the database image data. The processing portion has a function of obtaining query image feature value data representing a feature value of the query image data. The processing portion has a function of calculating first similarity of the database image data to the query image data for each piece of the database image data. The processing portion has a function of obtaining a query tag linked to the query image data using some of the database tags.