Abstract: A method for managing a multi-task queue based on priority includes: receiving a plurality of tasks relating to data stored on a blockchain from a user, each of the plurality of tasks requiring one or more of necessary resource tickets to be executed by a processor in accordance with a burden caused by the task on the processor; identifying a priority of each of the plurality of tasks; assigning one or more of resource tickets for each of the plurality of tasks per unit time in accordance with the priority of each of the plurality of tasks; and executing one or more of the plurality of tasks per unit time if the one or more of resource tickets assigned for the one or more of the plurality of tasks is equal to more than the one or more of necessary resource tickets.

Abstract: Disclosed is a linear actuator, including a drive motor, a transmission assembly, a rotary screw, a transmission nut, a clutch device, a self-locking device and a hand-pull release assembly. The clutch device is arranged between the transmission assembly and the rotary screw. The self-locking device is configured to generate frictional resistance to the rotary screw when the rotary screw rotates reversely, and the self-locking device includes a release torsion spring. The hand-pull release assembly includes a first driving member connected with the clutch device and a second driving member connected with the self-locking device, and has an initial state and a fully released state. During the process from the initial state to the fully released state, the first driving member drives the clutch device to disconnect power, and the second driving member drives the release torsion spring to extend.

Abstract: Embodiments of the disclosure provide a method, a device, an apparatus, and a storage medium for video production. The method includes: presenting a text setup interface in a displayed video producing window; receiving a first trigger operation; displaying object attribute information corresponding to the video production object in the first information display area; receiving a second trigger operation; and displaying, in the second information display area, video related text corresponding to the video production object. According to the method, a simple and easy operation video production platform is provided for a video producer. A text setting interface of a video to be manufactured is presented on the video production platform, and a function item for video text generation is provided for the video producer.

Abstract: The disclosure relates to the field of computer security. Provided are a method for implementing a firmware root-of-trust, and an apparatus, a device, and a readable storage-medium thereof. The method includes: setting a storage-medium for storing state-data of the firmware root-of-trust; integrating a processing-logic of an instruction of the firmware root-of-trust into a system-firmware; initializing the firmware root-of-trust, according to the state-data of the firmware root-of-trust and a startup-command of the firmware root-of-trust; creating a node of a device-tree for the firmware root-of-trust, for an operating-system to load a driver-program corresponding to the firmware root-of-trust; and registering an instruction-interface of the firmware root-of-trust into an interface-list.

Abstract: Techniques are disclosed herein for contextual query rewriting. The techniques include inputting a first user utterance and a conversation history to a first language model. The first language model identifies an ambiguity in the first user utterance and one or more terms in the conversation history to resolve the ambiguity, modifies the first user utterance to include the one or more terms identified to resolve the ambiguity to generate a modified utterance, and outputs the modified utterance. The computing system provides the modified utterance as input to a second language model. The second language model performs a natural language processing task based on the input modified utterance and outputs a result. The computing system outputs a response to the first user utterance based on the result.

Abstract: Techniques are disclosed herein for executing an execution plan for a digital assistant with generative artificial intelligence (genAI). A first genAI model can generate a list of executable actions based on an utterance provided by a user. An execution plan can be generated to include the executable actions. The execution plan can be executed by performing an iterative process for each of the executable actions. The iterative process can include identifying an action type, invoking one or more states, and executing, by the one or more states, the executable action using an asset to obtain an output. A second prompt can be generated based on the output obtained from executing each of the executable actions. A second genAI model can generate a response to the utterance based on the second prompt.

Abstract: Techniques for using a LLM to detect OOS and OOD utterances. In one aspect, a method includes routing an utterance to a skill bot. The skill bot is configured to execute an action for completing a task associated with the utterance, and a workflow associated with the action includes a GenAI component state configured to facilitate completion of at least part of the task. The method further includes inputting a prompt into a GenAI model for processing. The prompt includes the utterance and scope-related elements that teach the GenAI model to output an invalid input variable when the utterance is OOS or OOD. When the GenAI model determines the utterance is OOS or OOD as part of the processing, the response is generated to include the invalid input variable, and the GenAI component state is caused to transition to a different state or workflow based on the response.

Abstract: Techniques are disclosed herein for configuring agents for use by digital assistants that use generative artificial intelligence. An agent may be in the form of a container that is configured to have one or more actions that can be executed by a digital assistant. The agent may be configured by initially defining specification parameters for the agent based on natural language input from a user. Configuration information for the one or more assets can be imported into the agent. One or more actions may then be defined for the agent based on importing of the configuration information, the natural language input from the user, or both. A specification document can be generated for the agent and can comprise various description metadata, such as agent, asset, or action metadata, or combinations thereof. The specification document may be stored in a data store that is communicatively coupled to the digital assistant.

Abstract: Techniques are disclosed herein for routing an utterance to action for a digital assistant with generative artificial intelligence. An input query comprising particular data can be received from a user. An action and a set of input argument slots within a schema associated with the action can be identified based on the input query. The input argument slots can be filled by determining whether one or more parameters are derivable from the particular data and filling the input argument slot with a version of the parameters that conforms to the schema. An execution plan that comprises the action that includes the set of filled input argument sots can be sent to an execution engine configured to execute the action for generating a response to the input query.

Abstract: Techniques are disclosed for returning references associated with an answer to a query. The techniques include accessing a text portion and identifying a plurality of sentences in the text portion. Each of the sentences is embedded to generate a respective plurality of text sentence embeddings. The text portion or a derivative thereof and a query are provided to a language model and a response to the query based on the text portion is received from the language model. A plurality of sentences are identified in the response. The plurality of sentences in the response is embedded to generate a plurality of response embeddings. The response embeddings are compared to the sentence embeddings to generate a similarity score for each sentence embedding-response embedding pair. Based on the similarity scores, an indication of a subset of the plurality of sentences is output with the response to the query.

Abstract: Techniques are disclosed herein for generating and using a knowledge base of information extracted from documents. The techniques include accessing a document comprising text and dividing the document into a plurality of chunks of text. The chunks are indexed by storing each chunk mapped to respective identifying metadata including a chunk index for each chunk. A query is received and a chunk relevant to the query is identified. A prompt is formulated including the query, the identified relevant chunk, and a subsequent chunk. The prompt is provided to a language model and output is received from the language model based on the prompt. An answer to the query is returned based on the received output.

Abstract: Techniques are disclosed herein for implementing digital assistants using generative artificial intelligence. An input prompt comprising a natural language utterance and candidate agents and associated actions can be constructed. An execution plan can be generated using a first generative artificial model based on the input prompt. The execution plan can be executed to perform actions included in the execution plan using agents indicated by the execution plan. A response to the natural language utterance can be generated by a second generative artificial intelligence model using one or more outputs from executing the execution plan.

Abstract: A method for preparing an emergency call, a device for preparing an emergency call, and a storage medium are presented. The method includes detecting that a user of a device has initiated an emergency call, obtaining an indication of a current geographical location of the device, and, in response to the detecting and based on the obtained indication, selecting an emergency number to be called for the emergency call.

Abstract: Techniques are described for invoking and switching between chatbots of a chatbot system. In some embodiments, the chatbot system is capable of routing an utterance received while a user is already interacting with a first chatbot in the chatbot system. For instance, the chatbot system may identify a second chatbot based on determining that (i) such an utterance is an invalid input to the first chatbot or (ii) that the first chatbot is attempting to route the utterance to a destination associated with the first chatbot. Identifying the second chatbot can involve computing, using a predictive model, separate confidence scores for the first chatbot and the second chatbot, and then determining that a confidence score for the second chatbot satisfies one or more confidence score thresholds. The utterance is then routed to the second chatbot based on the identifying of the second chatbot.

Abstract: Provided is a pixel circuit. The pixel circuit includes: a data writing circuit, coupled to a first gate signal terminal, a second gate signal terminal, a third gate signal terminal, a data signal terminal, a first node, a second node and a third node; a light emission control circuit, coupled to a light emission control terminal, a first power supply terminal, the first node, the third node and a light-emitting element; and a drive circuit, wherein an input terminal, a control terminal and an output terminal of the drive circuit are coupled to the first node, the second node and the third node respectively.

Abstract: An asset transfer recording system includes a node and a data storage server. The node includes a node processor programmed to generate a data processing rule according to a request by a transferor of an asset. The node processor is further programmed to store the data processing rule on the blockchain; generate a data processing command according to the data processing rule; and send the data processing command to the data storage server. The data storage server includes a server processor programmed to process the plurality of data items according to the data processing command and generate and send a processing result to the node processor. The node processor is further programmed to store the processing result on the blockchain.

Abstract: Techniques for automatically switching between chatbot skills in the same domain. In one particular aspect, a method is provided that includes receiving an utterance from a user within a chatbot session, where a current skill context is a first skill and a current group context is a first group, inputting the utterance into a candidate skills model for the first group, obtaining, using the candidate skills model, a ranking of skills within the first group, determining, based on the ranking of skills, a second skill is a highest ranked skill, changing the current skill context of the chatbot session to the second skill, inputting the utterance into a candidate flows model for the second skill, obtaining, using the candidate flows model, a ranking of intents within the second skill that match the utterance, and determining, based on the ranking of intents, an intent that is a highest ranked intent.

Abstract: Provided are a driver board, a display panel, and a display apparatus. The driver board includes a driver circuit. The driver circuit includes N pixel electrodes, N pixel switches, a data switch, and a storage capacitor, N is a positive integer, and N?2. The storage capacitor includes a reference electrode and a counter electrode. A control terminal of the pixel switch receives a gating signal, a first terminal of the pixel switch is connected to the counter electrode, and a second terminal of the pixel switch is connected to the pixel electrode. The driver board further includes data lines, and each data line is connected to the counter electrode via the data switch.

Abstract: According to various embodiments, described herein are systems and methods for training machine learning (ML) models to generate real-time scores to predict the probabilities of task completion. In one embodiment, an exemplary method includes the operations of receiving, from a data store, a set of features and a workflow for training a first type of ML models, the workflow specifying a data source, a number of stages and associated parameters for training the ML models; retrieving, from the data source, training data for the set of features; and segmenting the training data into different segments. The method further includes the operations of training a separate first type of ML model using each of the different segment of the training data in accordance with the workflow; and persisting the first type of trained ML models into the data storage. The method also includes using a trained ML model to generate probability scores and displaying the scores to users in real-time.

Abstract: Disclosed is a technique of controlling a mobile body. In the technique, a current operating state of the mobile body is analyzed, and it is determined whether a control instruction from an application is safe for the current operating state. The control instruction is allowed to be output to a control target based on the control instruction being determined to be safe in the current operating state. The control instruction is prevented from being output to the control target based on the control instruction being determined to be unsafe in the current operating state.