Abstract: An agent-based method for generating corpus data, an agent, a device, and a medium are provided which relate to the field of artificial intelligence technology, and in particular to the fields of deep learning, large models, and intelligent question answering technologies. The agent-based method for generating corpus data includes: acquiring a target task rule related to a page to be processed, where a semantic dependency relationship in the target task rule represents a semantic understanding logic among a plurality of item components in the page to be processed; executing a target task for the plurality of item components based on the semantic dependency relationship by using a designated agent according to the target task rule, and outputting an item response information; and generating target corpus data according to the item response information and item contents in the item components.

Abstract: A method for generating corpus data based on at least one large model is provided, which relate to the field of artificial intelligence technologies, and in particular to the fields of deep learning, large models, and intelligent question answering. The method includes: performing a content generation task by using the at least one large model based on a predetermined requirement condition to obtain a corpus content, where the content generation task includes a plurality of target tasks having dependency relationships, and the plurality of target tasks represent a reasoning process of the at least one large model for a corpus content to be generated; and determining target corpus data based on the corpus content and a reasoning process information related to the plurality of target tasks.

Abstract: An interaction method, an electronic device, and a storage medium are provided, which relate to the field of artificial intelligence technologies, and in particular to the fields such as deep learning, large models, and intelligent question answering. The interaction method includes: displaying a first corpus content in received corpus data; in response to an interaction operation performed by a target object on the first corpus content, updating the first corpus content and a second corpus content having a semantic dependency relationship with the first corpus content in the corpus data, to obtain target corpus data; and determining a feedback information related to a demand intention of the target object based on the target corpus data.

Abstract: A method for generating corpus data based on large models is provided, which relates to the field of artificial intelligence technologies, and in particular to the fields of deep learning, large models, and intelligent question answering. The method includes: conducting a dialogue on a predetermined topic by using a plurality of role-based large models to obtain an utterance content of at least one of the role-based large models; performing dialogue strategy planning based on the utterance content by using a designated large model to obtain a dialogue strategy, where the dialogue strategy constrains a speaking pattern of the role-based large models during a dialogue process; and determining target corpus data related to the predetermined topic according to a target utterance content, where the target utterance content is generated by the role-based large models conducting a dialogue based on the dialogue strategy.

Abstract: A phase encoding method includes: determining, based on a plurality of to-be-encoded phases, a quantity of a plurality of bits needed for encoding the plurality of phases; generating first-order terms and higher-order terms of the plurality of bits; constructing a bit matrix based on the plurality of phases, the first-order terms, and the higher-order terms, where the bit matrix includes a plurality of value combinations of the plurality of bits; calculating a plurality of encoding coefficients based on the bit matrix and the plurality of phases; and encoding the plurality of phases by using the plurality of encoding coefficients. This method may be performed by any encoding process in which an encoding object is a discrete value.

Abstract: The present disclosure relates to an array substrate, a display panel, and an electronic device. The array substrate includes a plurality of sub-pixel regions, a gate line layer, and a common electrode layer. Each sub-pixel region of the sub-pixel regions has two sub-pixel units disposed in a same row and two thin film transistors connected to the two sub-pixel units respectively. The gate line layer has gate lines and gate electrodes. Control electrodes of two thin film transistors of each sub-pixel region are respectively connected to two gate lines located on two ends of the sub-pixel region through corresponding gate electrodes.

Abstract: A method and apparatus for training a question solving model, a question solving method and apparatus, an electronic device and a readable storage medium are disclosed. The method for training a question solving model includes: acquiring a first sample question; inputting the first sample question and a solving step grabbing template into a large language model to obtain a first sample solving step; inputting the first sample question, the first sample solving step and an answer grabbing template into the large language model to obtain a first sample answer; pre-training a step planning model according to the first sample question and the first sample solving step; pre-training the large language model according to the first sample question, the first sample solving step and the first sample answer; and acquiring the question solving model according to the step planning model and the large language model obtained by pre-training.

Abstract: A technical solution for processing a model generation result, which relates to the field of artificial intelligence technologies is disclosed. An implementation includes: disassembling a text generation result of a generative large model to obtain a plurality of result logic units; wherein each result logic unit includes a segment in the text generation result; each segment is capable of independently identifying one premise or conclusion in a logical inference relationship of the text generation result; and the text generation result is a response result generated by the generative large model based on text input information; generating a logical inference graph capable of characterizing a logical inference relationship among the plurality of result logic units based on the plurality of result logic units; and determining whether logical inference of generation of the text generation result by the generative large model is correct or not based on the logical inference graph.

Abstract: Provided is a method for determining a light-leakage degree of a display panel, applicable to a light-leakage detecting device, wherein a display region of the display panel comprises a plurality of sub-regions, and the method includes: acquiring a brightness value of each of the sub-regions when a target color is displayed in the display region; and determining, in response to detecting that the plurality of sub-regions comprise at least one light-leakage sub-region, the light-leakage degree of the display panel based on an average of brightness values of the plurality of sub-regions and a brightness value of the light-leakage sub-region.

Abstract: A shift register circuit includes a first pull-down control sub-circuit and a first noise reduction sub-circuit. The first pull-down control sub-circuit includes a first transistor and a second transistor, and a ratio of a width-to-length ratio of a channel of the second transistor to a width-to-length ratio of a channel of the first transistor is greater than 5:1. The first pull-down control sub-circuit transmits, in response to a first voltage signal received at a first voltage signal terminal, the first voltage signal to a first pull-down node through the first transistor, and transmits a second voltage signal received at a second voltage signal terminal to the first pull-down node through the second transistor under control of a voltage of a pull-up node. The first noise reduction sub-circuit transmits the second voltage signal to the pull-up node under control of a voltage of the first pull-down node.

Abstract: The present disclosure provides a method, an apparatus and a system for determining a light-leakage degree of a display panel, and a test fixture, and relates to the field of display technologies. When a light-leakage detection device detected that the plurality of sub-regions includes at least one light-leakage sub-region, the light-leakage detection device can determine a light-leakage degree of the display panel based on an average of brightness values of the plurality of sub-regions and a brightness value of the light-leakage sub-region. Compared with a way that an inspector manually determines a light-leakage degree, the light-leakage detection device can automatically determine the light-leakage degree of the display panel based on brightness values of the sub-regions by the method according to the embodiment of the present disclosure, thereby effectively improving the reliability and accuracy of the light-leakage degree of the display panel as determined.

Abstract: A contact lens and a contact lens assembly are provided. The contact lens includes a lens and a deformation unit. The lens configured to be worn in a human eye. The deformation unit is mounted to the lens and configured to deform according to a deformation voltage to make the lens deformed.

Abstract: A shift register circuit includes a first pull-down control sub-circuit and a first noise reduction sub-circuit. The first pull-down control sub-circuit includes a first transistor and a second transistor, and a ratio of a width-to-length ratio of a channel of the second transistor to a width-to-length ratio of a channel of the first transistor is greater than 5:1. The first pull-down control sub-circuit transmits, in response to a first voltage signal received at a first voltage signal terminal, the first voltage signal to a first pull-down node through the first transistor, and transmits a second voltage signal received at a second voltage signal terminal to the first pull-down node through the second transistor under control of a voltage of a pull-up node. The first noise reduction sub-circuit transmits the second voltage signal to the pull-up node under control of a voltage of the first pull-down node.

Abstract: A touch substrate includes an optical sensor structure, a parallel light detection structure and a lens positioning structure laminated one on another. The optical sensor structure is configured to determine plane position coordinates of the floating touch point in a direction parallel to the touch substrate based on a light flux received by each opening sensor unit. The lens positioning structure is configured to adjust a focal length of a target lens unit having the plane position coordinates in a plurality of lens units, so as to enable the light flux received by the optical sensor unit corresponding to the target lens unit to reach a threshold, thereby to determine a target focal length acquired when the light flux received by the optical sensor unit reaches the threshold as a space position coordinate of the floating touch point in a normal direction of the touch substrate.

Abstract: The present application provides a display substrate, a display panel, a display device and a manufacturing method thereof. The display substrate comprising: a base substrate and a black matrix layer, a color resistance layer and an electrostatic transmission layer arranged on the base substrate, wherein the base substrate comprises a first surface and a second surface opposing to each other, the black matrix layer and the color resistance layer are arranged on the first surface of the base substrate and arranged on the same layer, and the electrostatic transmission layer for leading out static electricity generated by the base substrate is arranged on the second surface of the base substrate, and wherein an orthographic projection of the electrostatic transmission layer on the base substrate does not overlap with an orthographic projection of the color resistance layer on the base substrate.

Abstract: The present disclosure provides a common voltage compensation circuit including a feedback signal input terminal and a compensation sub-circuit. The compensation sub-circuit is configured to generate a compensation voltage for compensating a common voltage according to a feedback signal from the feedback signal input terminal and a reference common voltage. The common voltage compensation circuit also includes a first filter sub-circuit, a first terminal of the first filter sub-circuit is electrically coupled to the feedback signal input terminal, and a second terminal of the first filter sub-circuit is electrically coupled to a first clock signal line. The feedback signal line arranged is adjacent to a second clock signal line, and a first clock signal in the first clock signal line and a second clock signal in the second clock signal line are inverted relative to each other. The present disclosure also provides a display driver and a display device.

Abstract: A touch substrate includes an optical sensor structure, a parallel light detection structure and a lens positioning structure laminated one on another. The optical sensor structure is configured to determine plane position coordinates of the floating touch point in a direction parallel to the touch substrate based on a light flux received by each opening sensor unit. The lens positioning structure is configured to adjust a focal length of a target lens unit having the plane position coordinates in a plurality of lens units, so as to enable the light flux received by the optical sensor unit corresponding to the target lens unit to reach a threshold, thereby to determine a target focal length acquired when the light flux received by the optical sensor unit reaches the threshold as a space position coordinate of the floating touch point in a normal direction of the touch substrate.

Abstract: The present application provides a display substrate, a display panel, a display device and a manufacturing method thereof. The display substrate comprising: a base substrate and a black matrix layer, a color resistance layer and an electrostatic transmission layer arranged on the base substrate, wherein the base substrate comprises a first surface and a second surface opposing to each other, the black matrix layer and the color resistance layer are arranged on the first surface of the base substrate and arranged on the same layer, and the electrostatic transmission layer for leading out static electricity generated by the base substrate is arranged on the second surface of the base substrate, and wherein an orthographic projection of the electrostatic transmission layer on the base substrate does not overlap with an orthographic projection of the color resistance layer on the base substrate.

Abstract: Provided is a lens device, including a plurality of lens units arranged in an array, wherein the lens unit includes an accommodating cavity, a lens, a magnetic body, and a magnetic field generating member; the lens and the magnetic body are located inside the accommodating cavity, the magnetic field generating member is configured to provide a magnetic field, and the magnetic body is configured to move the lens in a direction perpendicular to an arrangement plane of the plurality of lens units under an action of the magnetic field provided by the magnetic field generating member. A display device and a control method is also provided.

Abstract: An adjustment structure for depth of field, a display device, and a control method thereof. The adjustment structure for depth of field includes: a first substrate, a second substrate and a lens layer located between the first substrate and the second substrate. The lens layer includes a plurality of lens units; each of the plurality of lens units includes two electrodes and a lens located between the two electrodes with an adjustable focal length; the lens includes charged particles and a first transparent insulating liquid encapsulated by a transparent flexible film; the charged particles include positively charged particles and negatively charged particles.