Abstract: A method of generating a report using company data may include: collecting subscription company data related to a company subscribing to a platform; storing the collected subscription company data in association with a subscription company account; receiving consultation information through a consultation channel associated with the platform; specifying a consultee from the consultation information, and collecting consultee data related to the specified consultee; generating a report related to the specified agent, using a language model with at least some of the subscription company data and the consultee data as input; and providing the generated report to a subscriber account of the subscription company.

Abstract: A method of retrieving a document according to an embodiment of the present application includes: acquiring a user retrieval query; calculating a user inquiry vector in a unit of sentence from the user retrieval query and acquiring a first document candidate group based on similarity between the calculated user inquiry vector and an embedding vector of a document stored in a retrieval database; acquiring a second document candidate group based on similarity between a text included in the user retrieval query and a text of the document stored in the retrieval database; and determining a summarization target document based on the first document candidate group and the second document candidate group.

Abstract: A method for designing polymers includes translating polymer representations of a training dataset and a test dataset into a format comprehensible by a generative pretraining transformer (GPT)-based model, training the GPT-based model with the translated polymer representations, generating new polymer representations, in a predefined format, using the trained GPT-based model, predicting at least one property of the generated new polymer representations using a machine learning (ML) property predictive model and selecting a first subset of the generated new polymer representations as a function of the at least one predicted property, and calculating the at least one property of the first subset of the generated new polymer representations using a molecular dynamics (MD) module.

Abstract: Disclosed herein is a search method performed by an electronic device, including: receiving the plurality of similar question candidates selected by the server using a first similarity analysis model and question vectors corresponding to the plurality of similar question candidates from the server; selecting one or more similar questions from the plurality of similar question candidates by the electronic device using a second similarity analysis model; receiving the responses to the one or more similar questions from the server; and providing the one or more similar questions and the responses to the similar question together to the user.

Abstract: The present invention relates to a context-based QA generation architecture for generating diverse QA pairs from a single context. The context-based QA generation architecture includes a latent variable generating network, an answer generating network and a question generating network. The latent variable generating network comprises multiple Bi-LSTM encoders encode the a first context, the a first question and the a first answer to generate a first context vector, a first question vector and a first answer vector, respectively, a first Multi-Layer Perceptron (MLP) generate a first question latent variable based on the first context vector and the first question vector, and a second MLP generate a first answer latent variable based on the first question latent variable and the first answer vector. The answer generating network and the question generating network are trained based on the first context, the first question latent variable and the first answer latent variable.

Abstract: The present invention relates to a protective film and a polarizing plate comprising the same, and provides a protective film capable of minimizing the amount of static electricity that can be generated upon peeling the protective film.

Abstract: The present application relates to a method for preparing amino acid granules from a fermentation broth, wherein the prepared amino acid granules contain no cells.

Abstract: A semiconductor nanoparticle, a method of manufacturing the semiconductor nanoparticle, and an electronic device including the nanoparticle are provided. The semiconductor nanoparticle includes silver, indium, gallium, and sulfur, wherein the semiconductor nanoparticle is configured to emit a green light, wherein the semiconductor nanoparticle has a relative mole value of zinc as defined by Equation 1 that is greater than or equal to about 0.25 and less than or equal to about 0.9: Relative ? mole ? value ? of ? zinc = [ Zn ] / ( [ Ag ] + [ In ] + [ Ga ] + [ Zn ] ) Equation ? 1 wherein, in Equation 1, [Ag], [In], [Ga], and [Zn] are molar amounts of the silver, the indium, the gallium, and the zinc in the semiconductor nanoparticle, respectively, and wherein a mole ratio of gallium to indium is greater than about 2.5:1 and less than about 5.6:1.

Abstract: A semiconductor nanoparticle including a first semiconductor nanocrystal including silver, indium, gallium, and sulfur, and a semiconductor nanoparticle including a second semiconductor nanocrystal including zinc, gallium, and sulfur, a method of manufacturing the same, and an electronic device including the same. The semiconductor nanoparticle is configured to emit a green light. The green light has a peak emission wavelength of about 500 nanometers to about 580 nanometers. In the semiconductor nanoparticle, a molar ratio of zinc to indium is about 0.1:1 to about 10:1.

Abstract: A cadmium free quantum dot includes zinc, tellurium, and selenium, and lithium. A full width at half maximum of a maximum luminescent peak of the cadmium free quantum dot is less than or equal to about 50 nanometers and the cadmium free quantum dot has a quantum efficiency of greater than 1%.

Abstract: A quantum dot including a semiconductor nanocrystal core and a semiconductor nanocrystal shell disposed on the core and does not include cadmium, wherein the core includes a Group III-V compound, the quantum dot has a maximum photoluminescence peak in a green light wavelength region, a full width at half maximum (FWHM) of the maximum photoluminescence peak is less than about 50 nanometers (nm), and a difference between a wavelength of the maximum photoluminescence peak and a first absorption peak wavelength of the quantum dot is less than or equal to about 25 nanometers, and a production method thereof.

Abstract: Disclosed herein is a search method performed by a server, including: receiving a user question from a user terminal; generating a user question vector for the user question; selecting similar question candidates based on a similarity to the user question vector; generating an answer to the user question based on the similar question candidates; and transmitting the answer to the user question to the user terminal.

Abstract: A display device includes a display panel, a backlight unit, and a light conversion sheet between the display panel and the backlight unit. The backlight unit includes a substrate and light-emitting sections arranged on the substrate, one or more light sources are disposed in each of the light-emitting sections, the light conversion sheet includes first partition walls and light conversion sections arranged to correspond to the light-emitting sections, a first partition wall of the first partition walls is disposed between adjacent light conversion sections of the light conversion sections. Each of the light conversion sections includes first quantum dots emitting a first light and second quantum dots emitting a second light having a color different from a color of the first light, and the at least one light source provides light of a predetermined wavelength to the light conversion sheet.

Abstract: The present invention relates to a context-based QA generation architecture, and an object of the present invention is to generate diverse QA pairs from a single context. To achieve the object, the present invention includes a latent variable generating network including at least one encoder and an artificial neural network (Multi-Layer Perceptron: MLP) and configured to train the artificial neural network using a first context, a first question, and a first answer, and generate a second question latent variable and a second answer latent variable by applying the trained artificial neural network to a second context, an answer generating network configured to generate a second answer by decoding the second answer latent variable, and a question generating network configured to generate a second question based on a second context and the second answer.

Abstract: A polarizing plate and a display device including the same is disclosed herein. In some embodiments, a polarizing plate includes a polarizer which allows only light polarized in a specific direction to pass through; and a haze adhesive film disposed on a one surface of the polarizer and having a haze of 49% to 65%, wherein the haze adhesive film is configured to adhere to the display device, and reduce moire occurring in the dual cell structure of the display device.

Abstract: A quantum dot including a core including a first semiconductor nanocrystal including zinc, selenium, and tellurium, and a semiconductor nanocrystal shell disposed on the core, the semiconductor nanocrystal shell including zinc, and selenium, sulfur, or a combination thereof, wherein the quantum dot does not include cadmium, a mole ratio of tellurium relative to selenium in the first semiconductor nanocrystal is greater than about 1:1, a mole ratio of a sum of selenium and sulfur relative to in the quantum dot is greater than about 1:1, a wavelength of a maximum emission peak of the quantum dot is in a range of about 500 nanometers (nm) to about 550 nm, and the quantum dot has quantum efficiency (QY) of greater than or equal to about 30%, a quantum dot-polymer composite including the quantum dot, a display device including the quantum dot-polymer composite, and an electroluminescent device including the quantum dot.

Abstract: A quantum dot including a core including a quaternary alloy semiconductor nanocrystal and not including cadmium, a composition and a quantum dot polymer composite including the same, and an electronic device including the same. The quaternary alloy semiconductor nanocrystal comprises indium (In), phosphorous (P), zinc (Zn), and selenium (Se), and in the core, a ratio of the zinc with respect to the indium is less than or equal to about 0.5:1 and in the core, a ratio of selenium with respect to zinc is less than or equal to about 0.6:1.

Abstract: Provided are method and apparatus for data structuring of text. The apparatus for data structuring of text includes a processor; and a memory storing instructions executable by the processor, wherein the processor is configured to execute the instructions to: extract text and location information of the text from an image, set text units for the extracted text, assigning a first tag and a second tag to at least one of the text units, connect text units with related tags among the text units allocated the first tag and the second tag, label the connected text units as first text, second text, and third text respectively corresponding to an item name, an item value, and others based on a natural language processing model, and structure the extracted text by mapping the second text to the first text.

Abstract: A quantum dot composite that includes a matrix; and a plurality of quantum dots and titanium oxide particles dispersed in the matrix, wherein the quantum dots include zinc, tellurium, and selenium, the quantum dots do not comprise cadmium, lead, mercury, or a combination thereof, and in the quantum dot composite, a weight ratio of tellurium with respect to titanium is greater than or equal to about 1.5:1 and less than or equal to about 10:1.

Abstract: A core-shell quantum dot comprising zinc, a core comprising a first semiconductor nanocrystal material; and a semiconductor nanocrystal shell disposed on the core, wherein the core-shell quantum dot does not comprise cadmium, and does comprise zinc, tellurium, selenium, and aluminum.