Abstract: Described herein are technologies related to constructing supplemental content items that summarize electronic landing pages. A sequence to sequence model that is configured to construct supplemental content items is trained based upon a corpus of electronic landing pages and supplemental content items that have been constructed by domain experts, wherein each landing page has a respective supplemental content item assigned thereto. The sequence to sequence model is additionally trained using self critical sequence training, where estimated click through rates of supplemental content items generated by the sequence to sequence model are employed to train the sequence to sequence model.

Abstract: The present application describes a system and method for converting a natural language query to a standard query using a sequence-to-sequence neural network. As described herein, when a natural language query is receive, the natural language query is converted to a standard query using a sequence-to-sequence model. In some cases, the sequence-to-sequence model is associated with an attention layer. A search using the standard query is performed and various documents may be returned. The documents that result from the search are scored based, at least in part, on a determined conditional entropy of the document. The conditional entropy is determined using the natural language query and the document.

Abstract: The present application describes a system and method for converting a natural language query to a standard query using a sequence-to-sequence neural network. As described herein, when a natural language query is receive, the natural language query is converted to a standard query using a sequence-to-sequence model. In some cases, the sequence-to-sequence model is associated with an attention layer. A search using the standard query is performed and various documents may be returned. The documents that result from the search are scored based, at least in part, on a determined conditional entropy of the document. The conditional entropy is determined using the natural language query and the document.

Abstract: An automated optical inspection (AOI) image classification method includes sending a plurality of NG information of a plurality of samples from an AOI device into an Artificial Intelligence (AI) module; performing discrete output calculation on the NG information of the samples by the AI module to obtain a plurality of classification information of the samples; performing kernel function calculation on the classification information of the samples by the AI module to calculate respective similarity distances of the samples and performing weighting analysis; based on weighting analysis results of the samples, judging classification results of the samples; and based on the classification results of the samples, performing classification of the samples.

Abstract: Images are encoded into multidimensional vectors in a high-dimensional space utilizing an image model and textual content utilizing a text model. At least one of the image model and/or the text model are tuned such that the point within the multidimensional space pointed to by a vector encoded from an image is proximate to, as determined within the context of that multidimensional space, a point pointed to by a vector encoded from correlated textual content. Received images and textual content are encoded into image vectors and text vectors, respectively, and stored in an image graph and text graph, respectively. An input image can then be encoded as an input image vector and utilized to find close vectors in both the image graph and the text graph, thereby enabling an input image to be utilized to search textual content without using classifiers to deduce textual content therefrom.

Abstract: An industrial image inspection method includes: generating a test latent vector of a test image; measuring a distance between a training latent vector of a normal image and the test latent vector of the test image; and judging whether the test image is normal or defected according to the distance between the training latent vector of the normal image and the test latent vector of the test image.

Abstract: A taxonomy of categories, attributes, and values can be conflated with new data triplets by identifying one or more conflation candidates among the attribute-value pairs within a category of the taxonomy that matches the category of the data triplet, and determining a suitable merge action for conflating the data triplet with each conflation candidate. The task of determining merge actions may be cast as a classification problem, and may be solved by an ensemble classifier.

Abstract: A technique of scoring a query against a document using sequence to sequence neural networks. The technique comprises: receiving a query comprising a plurality of words from a user; performing a search for a document comprising words based on the query; feeding the words of the document as the input of an encoder of a multilayer sequence to sequence converter; generating a plurality of vectors at a decoder of the multilayer sequence to sequence converter, each vector comprising a probability associated with a respective word in the query; looking up in the respective vector each word's probability of being associated with the document; multiplying every word's probability together to determine an overall probability of the query being associated with the document; and returning the document to the user if the overall probability of the query being associated with the document is greater than a threshold value.

Abstract: Images are encoded into multidimensional vectors in a high-dimensional space utilizing an image model and textual content utilizing a text model. At least one of the image model and/or the text model are tuned such that the point within the multidimensional space pointed to by a vector encoded from an image is proximate to, as determined within the context of that multidimensional space, a point pointed to by a vector encoded from correlated textual content. Received images and textual content are encoded into image vectors and text vectors, respectively, and stored in an image graph and text graph, respectively. An input image can then be encoded as an input image vector and utilized to find close vectors in both the image graph and the text graph, thereby enabling an input image to be utilized to search textual content without using classifiers to deduce textual content therefrom.

Abstract: A computer-implemented technique is described herein for identifying one or more content items that are relevant to an input linguistic item (e.g., an input query) using a deep-structured neural network, trained based on a corpus of click-through data. The input linguistic item has a collection of input tokens. The deep-structured neural network includes a first part that produces word embeddings associated with the respective input tokens, a second part that generates state vectors that capture context information associated with the input tokens, and a third part which distinguishes important parts of the input linguistic item from less important parts. The second part of the deep-structured neural network can be implemented as a recurrent neural network, such as a bi-directional neural network. The third part of the deep-structured neural network can generate a concept vector by forming a weighted sum of the state vectors.

Abstract: A detecting method for a workpiece surface includes the following steps. Firstly, a workpiece is provided with a first environment, wherein the first environment has a first environmental temperature higher than a first saturation temperature corresponding to an environmental-relative humidity. Then, the workpiece is provided with a second environment, wherein the second environment has a second environmental temperature lower than the first environmental temperature, such that a itself-temperature of the workpiece reduces to a mist temperature, wherein the mist temperature is substantially equal to or higher than the second environmental temperature. Then, the workpiece is provided with a mist environment, wherein the mist environment has a mist-saturation temperature corresponding to a mist-environmental relative humidity is equal to or higher than the mist temperature for misting a surface of the workpiece. Then, the surface of the misted workpiece is detected.

Abstract: An automated optical inspection (AOI) image classification method includes sending a plurality of NG information of a plurality of samples from an AOI device into an Artificial Intelligence (AI) module; performing discrete output calculation on the NG information of the samples by the AI module to obtain a plurality of classification information of the samples; performing kernel function calculation on the classification information of the samples by the AI module to calculate respective similarity distances of the samples and performing weighting analysis; based on weighting analysis results of the samples, judging classification results of the samples; and based on the classification results of the samples, performing classification of the samples.

Abstract: A detecting method for a workpiece surface includes the following steps. Firstly, a workpiece is provided with a first environment, wherein the first environment has a first environmental temperature higher than a first saturation temperature corresponding to an environmental-relative humidity. Then, the workpiece is provided with a second environment, wherein the second environment has a second environmental temperature lower than the first environmental temperature, such that a itself-temperature of the workpiece reduces to a mist temperature, wherein the mist temperature is substantially equal to or higher than the second environmental temperature. Then, the workpiece is provided with a mist environment, wherein the mist environment has a mist-saturation temperature corresponding to a mist-environmental relative humidity is equal to or higher than the mist temperature for misting a surface of the workpiece. Then, the surface of the misted workpiece is detected.

Abstract: A technique of scoring a query against a document using sequence to sequence neural networks. The technique comprises: receiving a query comprising a plurality of words from a user; performing a search for a document comprising words based on the query; feeding the words of the document as the input of an encoder of a multilayer sequence to sequence converter; generating a plurality of vectors at a decoder of the multilayer sequence to sequence converter, each vector comprising a probability associated with a respective word in the query; looking up in the respective vector each word's probability of being associated with the document; multiplying every word's probability together to determine an overall probability of the query being associated with the document; and returning the document to the user if the overall probability of the query being associated with the document is greater than a threshold value.

Abstract: The present application describes a system and method for converting a natural language query to a standard query using a sequence-to-sequence neural network. As described herein, when a natural language query is receive, the natural language query is converted to a standard query using a sequence-to-sequence model. In some cases, the sequence-to-sequence model is associated with an attention layer. A search using the standard query is performed and various documents may be returned. The documents that result from the search are scored based, at least in part, on a determined conditional entropy of the document. The conditional entropy is determined using the natural language query and the document.

Abstract: A detecting method for a workpiece surface includes the following steps. Firstly, a workpiece is provided with a first environment, wherein the first environment has a first environmental temperature higher than a first saturation temperature corresponding to an environmental-relative humidity. Then, the workpiece is provided with a second environment, wherein the second environment has a second environmental temperature lower than the first environmental temperature, such that a itself-temperature of the workpiece reduces to a mist temperature, wherein the mist temperature is substantially equal to or higher than the second environmental temperature. Then, the workpiece is provided with a mist environment, wherein the mist environment has a mist-saturation temperature corresponding to a mist-environmental relative humidity is equal to or higher than the mist temperature for misting a surface of the workpiece. Then, the surface of the misted workpiece is detected.

Abstract: A computer-implemented technique is described herein for identifying one or more content items that are relevant to an input linguistic item (e.g., an input query) using a deep-structured neural network, trained based on a corpus of click-through data. The input linguistic item has a collection of input tokens. The deep-structured neural network includes a first part that produces word embeddings associated with the respective input tokens, a second part that generates state vectors that capture context information associated with the input tokens, and a third part which distinguishes important parts of the input linguistic item from less important parts. The second part of the deep-structured neural network can be implemented as a recurrent neural network, such as a bi-directional neural network. The third part of the deep-structured neural network can generate a concept vector by forming a weighted sum of the state vectors.

Abstract: The present disclosure discloses a method for suturing 3D coordinate information. The method includes disposing a correction block on a test platform; capturing first 3D coordinate information represented by a first viewing angle and second 3D coordinate information represented by a second viewing angle from the correction block; determining a first center coordinate of the first 3D coordinate information and a second center coordinate of the second 3D coordinate information; superimposing the first 3D coordinate information to the second 3D coordinate information to form first overlap 3D coordinate information; suturing the first 3D coordinate information into the second 3D coordinate information to form a first 3D coordinate suturing result according to an iterative closet point algorithm; and determining a first transformation relation of the first viewing angle versus the second viewing angle according to the first 3D coordinate information and the first 3D coordinate suturing result.

Abstract: The present invention provides a transceiver for a radio frequency identification (RFID) reader. The transceiver includes an RF front end, a transmitting component, a receiving component, a power divider and a micro control unit (MCU). The power divider has three terminals. The first terminal of the power divider is connected to the transmitting component. The second terminal of the power divider is connected to the receiving component. The third terminal is connected to the RF front end. Moreover, the MCU is connected to the transmitting component and the receiving component, and generates a transmitted signal and receives a retrieved data. According to the present invention, the transceiver further includes an RF switch, a matching circuit and a receiving circuit.

Abstract: The present invention discloses a biological measuring device with auto coding capabilities. In accordance with one embodiment of the present invention, the biological measuring device with auto coding capabilities may include a test strip associated with a code pattern; and a code reader electrically coupled to the test strip to read the code pattern, wherein the code reader is configured to read an output from the code pattern consisted of a first logical value, a second logical value, and a third logical value.