417 results about "Dialog box" patented technology

As part of a dialog session between a user and an automated assistant, implementations can receive a stream of audio data that captures a spoken utterance including an assistant query, determine, based on processing the stream of audio data, a set of assistant outputs that are each predicted to be responsive to the assistant query, process, using large language model (LLM) output(s), the assistant outputs and context of the dialog session to generate a set of modified assistant outputs, and cause given modified assistant output, from among the set of modified assistant outputs, to be provided for presentation to the user in response to the spoken utterance. In some implementations, the LLM output(s) can be generated in an offline manner for subsequent use in an online manner. In additional or alternative implementations, the LLM output(s) can be generated in an online manner when the spoken utterance is received.

Generative artificial intelligence-based techniques are disclosed herein to conduct conversations of various types with multiple Large Language Model Services at once. In one aspect, a method is provided that includes identifying large language model services that qualify to take part in the conversation based, at least in part, on a conversation type and profile information provided by a user, user-selected terms selected by the user specific to the conversation, or both, rendering a conversation screen in a graphical user interface, receiving a prompt input into a dialog box of the conversation screen, communicating the prompt input to each of the large language model services, receiving responses from the large language model services based on the prompt input, and rendering the responses in a dialog box of the conversation screen with an indication of which of the large language model services provided each of the responses.

Systems and methods are provided for facilitating management of interactions and training for AI (artificial intelligence) agents. Systems generate and display interfaces for training AI agents and for receiving user instructions. The systems parse user instructions to identify tasks to be performed by the AI agents. The systems cause the tasks to be split into subtasks to be performed by the AI agent. The systems also display a dialog frame that presents the user instructions along with AI agent responses that identify the subtasks. The systems also display a graph that visually identifies a processing flow of the subtasks and that dynamically updates the processing flow to reflect a status of progress for the AI agent performing the subtasks.

A computer-implemented method comprises receiving a first chat message at a server computer from a chat interface of a reservation application executing on a mobile computing device; determining, by the server computer, from the first chat message, whether the first chat message specifies an intent for a recommendation of a travel item by programmatically classifying the first chat message to output the intent; in response to determining that the first chat message specifies the intent, generating a first plurality of travel items and a second chat message comprising one or more descriptors of the intent, outputting the first plurality of travel items and the second chat message in the chat interface, and including, in each travel item of the first plurality of travel items, a graphical user interface (GUI) widget that is programmed when selected to initiate a reservation dialog based on the travel item; in response to determining that the first chat message does not specify the intent, outputting in the chat interface a third chat message comprising a prompt for contextual information, receiving, in the chat interface, a fourth chat message specifying the contextual information, executing an inference stage of one or more trained machine-learning models over the contextual information to output one or more named entities, deriving the intent from the first chat message and the one or more named entities, generating, using the server computer, the intent, and the one or more named entities, a second plurality of travel items and a fifth chat message comprising one or more descriptors of the intent, outputting in the chat interface the second plurality of travel items and the fifth chat message, and including, in each of the second travel items, a second GUI widget that is programmed when selected to initiate the reservation dialog based on one or more of the second travel items.

Methods and apparatuses are described for dialog control flow in information retrieval applications. A server establishes a chat-based communication session between an information retrieval application and a client device. The server determines a user intent from utterances received from a user of the client device and initiates a first dialog workflow associated with the user intent. The server invokes NLP services using the utterances to determine a comprehension score for the user intent and identifies a first one of the NLP services to continue the first dialog workflow when the comprehension score is at or above a threshold value, including generating a response to the utterances using the first NLP service. The server delegates the communication session to a second dialog workflow when the comprehension score is below the threshold value, including invoking a generalized language processing service associated with the second dialog workflow using the user intent to generate a response to the utterances. The server transmits the generated response to the client device as part of the chat-based communication session.

The intelligent automated assistant system engages with the user in an integrated, conversational manner using natural language dialog, and invokes external services when appropriate to obtain information or perform various actions. The system can be implemented using any of a number of different platforms, such as the web, email, smartphone, and the like, or any combination thereof. In one embodiment, the system is based on sets of interrelated domains and tasks, and employs additional functionally powered by external services with which the system can interact.

The invention relates to the related technical field of digital data processing, in particular to an intelligent ancient book information processing method and device based on artificial intelligence, and the method comprises the steps: scanning an ancient book, constructing a knowledge graph, dividing a domain database, and training a vertical processing model; introducing a multi-form historical carrier to form a multi-mode sensing set, establishing a multi-information network, and embedding a processing model; the method comprises the following steps: establishing a dialog box, realizing multi-round interaction and combining threshold optimization output, solving the technical problems of digitization and fragmentation limitation in ancient book information processing and incapability of effectively integrating and utilizing ancient book information due to diversity and complexity of ancient books and literatures, and realizing construction of a knowledge graph and division of a domain database. A knowledge system with a hierarchical structure and logic association is formed, deep learning and optimization are performed according to specific requirements in the field of ancient books by training a vertical processing model, a dialog box is established, multi-round interactive feedback with the user is performed, and the user is assisted to quickly and deeply explore the ancient books.

The invention discloses a dynamic interactive prompt sequence control method for chemical production, and relates to the field of flow industrial processes. Based on a state transition rule of a Phase functional block, linear execution and conditional jump of sequential control steps in a polymerization reaction temperature step control scene are realized through SFC programming, interactive processing and SFC logic steps are bound, and an interactive dialog box is triggered in a unified manner through an operation guide window. And the main program and the subprogram realize abnormal state linkage through an FAILIDX mark, and automatically detect a fault clearing state when the abnormity is recovered. The interactive processing dynamically generates an option list, supports multi-language switching, verifies input values in real time, and provides historical suggested values. The method aims at solving the problems that in a traditional sequence control system, the coupling degree of interaction logic and a core control program is high, operation interfaces are not uniform, and the misoperation risk is high, transplanting of cross-control systems and cross-process packages is supported, and the secondary development cost is remarkably reduced.

Embodiments of the disclosed technologies include generating a search prompt based on an input portion of an online dialog involving a user of a computing device. The search prompt includes a dialog summarization instruction configured to instruct a generative artificial intelligence model to generate and output a dialog summary. The search prompt is sent to a first generative model. In response to the search prompt, a search query is generated and output by the first generative model based on the dialog summary. The search query is sent to a search system. Search result data is determined based on an execution of the search query by the search system. At least some of the search result data is included in an output portion of the online dialog. The output portion is configured to be displayed at the computing device in response to the input portion of the online dialog.

Systems and methods are described for hiding a primary user's sensitive information in collaborative virtual desktop sessions where multiple secondary users access the primary user's virtual desktop. In particular, embodiments described herein leverage a mechanism for monitoring when designated sensitive applications are opened in the virtual desktop. After the primary user sets up a collaborative session on their virtual desktop, if a sensitive application opens in the virtual desktop during the collaborative session, the sharing of the desktop graphical user interface (GUI) can be stopped and the user can be prompted (e.g., via a warning dialog that pops up) to choose how to proceed. For example, the user can choose to hide the entire desktop, to minimize or close the sensitive application, or to continue sharing the desktop but pop-out the sensitive application from the remote desktop in a separate window that is not shared with the collaborators.

The invention belongs to the technical field of large language models, and discloses a time sequence card generation method and device based on a large language model, and the method comprises the steps: receiving a card creation instruction, and obtaining a card data type in the card creation instruction; extracting target text data in a dialog box of the large language model based on the card data type; converting the target text data into target card data corresponding to the card data type; generating a card title corresponding to the target card data according to the target text data; combining the target card data and the corresponding card titles to obtain time sequence cards; and putting the time sequence card into a tool window adjacent to the dialog box for displaying. According to the method, the manual operation of the user can be reduced, and the co-creation work efficiency and convenience of the large language model and the user are improved.

An implementation method supporting a Kiosk mode and remote control, comprising: a main process of a TMS client establishing a connection with a TMS main server; when a remote control instruction is received, enabling an Android device in a Kiosk mode to temporarily quit the Kiosk mode; starting a remote control interface of the TMS client, setting the remote control interface to be transparent, setting a screen capture permission of the remote control interface, and enabling the Android device to enter the Kiosk mode; the remote control interface being connected to a remote control server and broadcasting connection information; the main process acquiring login information from detected connection success information and uploading the login information to the TMS main server; the TMS main server popping up a login dialog box of the remote control interface by means of a browser and automatically filling in the login information; and when login confirmation information triggered by a user is received, capturing the screen of the Android device and displaying same on the remote control server, so that the server end starts to synchronously display the screen with the Android device and performs operations. According to the present invention, a device in a Kiosk mode can be operated, and the use is convenient.

Examples of the present disclosure describe systems and methods for enterprise search that leverage periodically updated user context of an enterprise user for intent understanding and treat a search session as a dialog between the user and a digital assistant to allow multi-modal interaction. For example, a query input by the user may be received from a client application having search functionality and an integrated assistant. A current state of the user context may be leveraged to understand the query. Based on the understanding, one or more responsive entities may be retrieved from an enterprise search index as results. Based on the results, a response may be generated that includes the results and a prompt to cause the user to further refine the query and / or provide feedback. The response may be provided to the client application for output as part of a search session dialog between the user and assistant.

A computer system is disclosed that provides purpose-based control of user actions and access to electronic data assets. For example, the computer system may perform operations including: receiving, from a user, a request to perform an action; determining any checkpoint config objects associated with the action; displaying checkpoint dialog based on checkpoint config object; determining whether criteria associated with the checkpoint object are satisfied; and in response to determining that the criteria associated with the checkpoint object are satisfied: generating a checkpoint record object; and proceeding to perform the action.

The invention provides a continuous fiber reinforced composite material mould pressing numerical simulation method and system, and the method comprises the steps: S1, building a mould pressing simulation parameterized model based on numerical simulation secondary development by using a programming script; s2, based on the established model, creating an interactive plug-in interface by using a dialog box constructor; s3, the simulation parameters are input into the plug-in to run mould pressing simulation, and a mould pressing simulation result is obtained; s4, establishing a performance analysis model and a warping analysis model according to a mould pressing simulation result and an asymmetrical grid mapping method; and S5, setting corresponding boundary conditions according to actual working conditions, and completing structural performance analysis and warping analysis by using the performance analysis model and the warping analysis model. According to the method, the formed fiber orientation and wrinkle information is mapped into the performance analysis model by using the asymmetrical grid mapping, a set of complete analysis process from manufacturing to response is constructed, and the prediction precision is remarkably improved.

Embodiments described herein are generally directed to training of classification models and their use by a chatbot to identify a customer-specified product support issue and provide appropriate troubleshooting guidance. According to an example, text describing an issue associated with a product line of a vendor is received via the chatbot. A vector representation of the issue is created using a word association model corresponding to the product line and trained based on a set of historical support cases relating to multiple supported issue categories for the product line. It is determined whether the issue matches a category within the supported issue categories for the product line by applying a classification model to the vector representation. When the determination is affirmative, an automated, interactive, conversational troubleshooting dialog is initiated with the user via the chatbot and guided based on a decision tree for the category within the product line.

The invention relates to the technical field of civil engineering teaching, and discloses a three-dimensional modeling and calculation document automatic generation method and system based on artificial intelligence assistance, a terminal and a storage medium, and the method comprises the steps: obtaining a natural language text input in a preset dialog box, and analyzing the natural language text through a natural language processing model, identifying and extracting component parameters; automatically generating a corresponding three-dimensional model by utilizing a three-dimensional modeling tool based on the component parameters; generating a corresponding calculation document based on the three-dimensional model, and typesetting the calculation document according to a preset typesetting rule; and outputting and displaying the three-dimensional model and the typeset calculation document. According to the method, natural language processing and three-dimensional modeling technologies are fused, three-dimensional modeling and calculation document automatic generation are achieved, the structural design efficiency and accuracy of the three-dimensional model and the calculation document are improved, arrangement, connection details and the construction process of the three-dimensional model are intelligently displayed, and the efficiency and expressive force of civil engineering teaching are improved.

The invention provides a dialogue method and device based on a large language model, a medium and equipment, and relates to the field of large language models and the field of financial science and technology. The method comprises the following steps: firstly, acquiring a current input instruction and context information of a user in a dialog box, and sensing the context information of the user by utilizing a context sensing module; then inputting the sensing result and the current input instruction into a large language model for analysis to obtain a target demand, and determining a target function corresponding to the target demand in a pre-constructed business function knowledge graph by using the large language model; and finally, determining a target service module corresponding to the target demand based on the large language model, calling the target service module to generate response information according to an execution result of the target function, and returning the response information to the user in a dialog box. According to the embodiment, the dialogue accuracy and naturalness are remarkably improved, the user experience is enhanced, and meanwhile the interaction quality and efficiency are greatly improved.

The invention discloses a business intelligent analysis method, system and device and a storage medium, belongs to the technical field of computer science and information, and solves the technical problem that a traditional BI system usually needs professional data analysts and developers to perform complex programming and configuration. The method comprises a low-code platform, an AI Agent agent and a BI system. The method comprises the steps that a service model, a service interface, a service trend display mode and a dialog box for interaction between a user and the AI Agent agent are created through the low-code platform; acquiring data through the service interface and the dialog box; synchronizing the service model and the data through the BI system to form a data analysis data set; importing a business model and data through an AI Agent agent, and creating a large model; obtaining the content asked by the user for the AI Agent agent and a text input by the user; data analysis is carried out based on the large model, and a data analysis result is fed back to the BI system for further analysis; and the BI system returns analysis result data to the low-code platform for data display.

The embodiment of the invention provides a service promotion method and device based on a large model, in the method, a target terminal triggers a consultation component of a target service based on a target merchant to send a consultation request to a third-party payment platform, and the third-party payment platform sends the consultation request to the third-party payment platform according to the consultation request and merchant information in the consultation request. Determining an actual participation state of the target merchant in the target service; further, according to the actual participation state, corresponding initial inquiry information is determined and returned to the target terminal, and after the target merchant inputs reply information in a consultation dialog box based on the initial inquiry information, the target terminal sends the reply information to the third-party payment platform; further, the third-party payment platform determines a target intention corresponding to the reply information through the first large model according to the reply information; and further, according to the corresponding target intention, guide information is generated through a second big model and returned to the target terminal, and the target terminal outputs the guide information in a consultation dialog box in a text-to-voice mode to guide the target merchant to participate in the target service.

1. Name of the product of this design: A search dialog box and display unit of a graphical user interface for searching information of an electronic device. 2. Purpose of the product of this design: an electronic device. 3. The key design features of this design product are the part of the graphical user interface for which protection is requested. 4. The picture or photo that best illustrates the key points of the design: main view. 5. Purpose of the graphical user interface: The interface is divided into three areas, which are used to provide users with a search input bar and display search results. When users want to further search for a certain content, they can enter the search question through the search dialog in the interface, or click to select the commonly used questions in the middle of the interface to search. Users can also click the function buttons at the bottom of the interface to reserve or purchase related products that users searched for. Local uses of the interface: the runway-shaped box with pointed corners at the top of the interface is a search dialog box, and the text in the dialog box is the content entered and searched by the user; the runway-shaped box with pointed corners in the middle of the interface is common search questions generated by artificial intelligence, and the user can click on one of the dialog boxes to select the content they want to search from these listed questions and start further search; the picture box in the middle of the interface displays product content related to the user's search, and the user can browse related content by clicking on the picture box; the runway-shaped box with a right arrow icon at the bottom of the interface is the "Book Now" function button, and the user clicks this button to book or purchase the related products the user searched for. 6. Other situations that need to be explained Other explanations: The dotted part in the figure is the content that is not requested for protection, and the solid line part and dot matrix area in the interface are the content that the interface is requested to protect.

A vehicle control system executing a voice control system for facilitating voice-based dialog with a driver to enable the driver or autonomous vehicle to control certain operational aspects of an autonomous vehicle is provided. Using environmental and sensor input, the vehicle control system can select optimal routes for operating the vehicle in an autonomous mode or choose a preferred operational mode. Occupants of the autonomous vehicle can change a destination, route or driving mode by engaging with the vehicle control system in a dialog enabled by the voice control system.

A method for displaying information, a computer device and a storage medium are provided. The method includes: in response to receiving questioning information on a dialog page, displaying a generated result content in an answer result matched with the questioning information according to a generation progress of the answer result; in a process of displaying the generated result content, stopping generating the answer result in response to receiving a generation stopping instruction; and in response to acquiring an answer result modification instruction, displaying an updated answer result, the updated answer result being obtained by modifying the answer result according to a target content question under a question dimension indicated by the answer result modification instruction.

Various systems and methods are presented regarding implementing one or more capabilities into a dialog flow occurring at an automated interface (e.g., a chatbot). A capability can be invoked at the interface in accordance with a user's requirements, e.g., the capability is a function to review data. An application programming interface (API) can be generated from the capability, wherein the API has features, parameters, metadata, etc., generated based on those of the capability. The API can be incorporated into a dialog, wherein the dialog can be subsequently presented on the interface (e.g., as part of a dialog flow). Interaction between the user and the dialog can cause the capability to be executed. Based upon the API features, etc., the API can be incorporated into a dialog, for example, by cloning a dialog, appending a dialog with the API, replacing a pre-existing API with the API in a dialog, and suchlike.

The invention discloses a train working diagram station track adjustment method and system fused with multi-dimensional inspection. The method comprises the steps that train operation adjustment result data containing station track change information are received; generating an adjustment result dialog box which can be switched between a simplified version and a detailed version according to the adjustment result data; in the adjustment result dialog box, in response to a screening condition input by a user, screening the adjustment result data, and carrying out statistics on the screened data; displaying station track change entries in the adjustment result dialog box, and highlighting the unconfirmed station track change entries with a first visual identifier; in response to an interaction operation of a user on the station track change item, providing a station track adjustment option; and based on the station track adjustment option selected by the user, executing a corresponding station track adjustment operation or multi-dimensional feasibility check, and updating a station track adjustment result. The railway transportation quality can be improved, and the working intensity of dispatchers is relieved.

The invention discloses a structure optimization method for prolonging the fatigue life of a crankshaft of a marine diesel engine. The structure optimization method comprises the following steps: developing a single-throw crankshaft modeling analysis plug-in; design parameters are selected, a three-dimensional geometric model of the single-throw crankshaft is dynamically constructed, and finite element analysis is carried out; developing a graphical interface for the dialog box script; seamless connection between the plug-in and the ABAQUS software is realized through development of the registration script; adopting optimal Latin hypercube sampling in a defined range to obtain a pre-calculation sample, developing a batch processing file and a Python script, and using an instruction to drive a single-throw crankshaft modeling analysis plug-in; a Pareto graph is adopted to analyze parameter sensitivity, a pre-calculation sample is screened, a high-precision Kriging proxy model is built, and then the optimal maximum bending stress value of the single-throw crankshaft and the corresponding optimal structure size are searched in combination with a particle swarm algorithm. According to the invention, the problem of low efficiency caused by frequent man-machine interaction when large samples are processed in the prior art is solved.

A medical imaging system (1) includes an electronic controller (10) including a display (24), the electronic controller configured to implement an imaging workflow graphical user interface (GUI) (26) enabling an associated user to set up an imaging workflow, execute the imaging workflow to acquire imaging data of the associated imaging subject using a medical imaging device (2), and display at least one medical image of the associated imaging subject generated by processing of the imaging data acquired by the execution of the imaging workflow; a problem reporting GUI dialog (28) hosted on the electronic controller and integrated with the workflow UI, wherein the problem reporting GUI is configured to receive a problem report indicating a problem with the medical imaging device; and a problem remediation tool (30) configured to perform at least one remedial action in response to receiving the problem report via the problem reporting GUI dialog.

The present disclosure describes techniques for implementing dialog-based image editing. Text indicating a task of editing an image is received. A list of objects and attributes associated with each of the objects is generated based on the text and the image. The objects are comprised in the image. Operations to be performed on each of the objects are determined. An order of performing the operations on an object-by-object basis are determined. A plan of implementing the task is generated based on the text and the order of performing the operations. The plan comprises information indicating a set of algorithm tools selected for the task. Executable code is generated based at least in part on the plan. The code is executed to generate an edited image.

The invention discloses an intelligent dialogue project management method and computer equipment, and relates to the field of artificial intelligence, and the method comprises the steps: obtaining a user question; performing semantic analysis on the user question to obtain a user demand; matching the user demand with a question set in a preset question and answer knowledge base to obtain a target question; determining a corresponding target answer in a preset question and answer knowledge base according to the target question; returning the target answer to the user and obtaining user feedback; in response to user confirmation in the user feedback to trigger an automatic process operation in the project system, determining a target request operation for triggering the project system according to the target problem; determining a corresponding target interface parameter in a preset program interface request library according to the target request operation; and returning the target operation result to the user. By implementing the method, the question and answer dialog box can be associated with the project system, a link from dialogue to execution is opened, data sharing and interaction are realized, and the efficiency is improved.

The invention discloses an intelligent question and answer method for an educational scene, and belongs to the technical field of data processing, and the method comprises the steps: collecting a multi-source data set, extracting a core ontology based on the multi-source data set, and filling the core ontology into a knowledge graph frame to generate a knowledge graph; and constructing a subject dialogue framework based on the knowledge graph, and training a question and answer model by using the subject dialogue framework to generate a trained question and answer model. According to the method, the subject knowledge graph is constructed, the question and answer model is trained on the basis of the subject knowledge graph, structured knowledge and natural language processing capacity are deeply fused, and accuracy and reliability of question and answer content are ensured. Through a semantic enhancement strategy and a heuristic classification method, the system can accurately understand a complex query intention of a user, retrieve highly related structured information from a knowledge graph, generate logical strict and interpretable answers, and improve user experience. The problems of factual errors and information omission easily occurring when a traditional method depends on a single model are effectively solved.