139 results about "User expectations" patented technology

Provided are a video generation method, an electronic device, and a computer readable storage medium, relating to the technical fields of computers and video processing. The video generation method comprises: acquiring a target text, wherein the target text is used for describing video content to be generated (S21); and using a target video generation model to perform video generation processing on the target text to obtain a target video, wherein the target video generation model is a model obtained by performing model alignment on an initial video generation model and a preset reward model in a fine-tuning manner (S22). The present invention solves the technical problems in the related art that a video generated by a video generation model obtained by training based on network data has poor quality and does not meet user expectations.

The invention discloses a vehicle control method, a server and a computer readable storage medium. The method comprises the steps that current perception information is acquired, the current perception information comprises user perception information and vehicle perception information, and the user perception information comprises user voice and / or user behaviors; according to the current perception information, determining an intention label, a user intention and candidate function points; and determining a vehicle control instruction according to the intention label, the user intention and the candidate function points. And issuing a vehicle control instruction to the vehicle to complete vehicle control. Thus, by combining the multi-mode current perception information, distinguishing the intention label of the user intention and understanding and reasoning the user intention, the service meeting the user expectation can be actively provided, and the driving experience of the user is improved.

The invention provides a mechanical arm control method based on a visual language model and human feedback. The method comprises the following steps: a) acquiring scene information: acquiring states of a mechanical arm and objects in a scene in real time through a camera; b) generating a control code according to the user instruction: decomposing the user instruction into a plurality of subtasks by utilizing a large language model, and combining and calling a predefined API (Application Program Interface) to generate the control code; c) verifying the generated control code: verifying the code through a visual language model, and judging that the control code completes a user instruction; d) executing the control codes: sequentially executing the control codes according to the sequence of the subtasks, and judging whether the step is successfully executed or not; and e) fault repair and man-machine interaction: feeding back reasons that tasks are not completed according to expectations, and regenerating control codes according to user feedback. According to the invention, the mechanical arm can understand and execute the natural language instruction of the user, and can communicate with the user when an abnormal condition occurs, so that the mechanical arm can complete various tasks in accordance with the expectation of the user.

A language model is used to generate autosuggestions to complete or revise a user's partial search query. An initial partial query is applied to the language model to generate query candidates for completing the search query. The language model may generate the query candidates as additional or alternate tokens for the partial search query. When the user revises the partial query, the previously-generated candidates can be re-used to reduce subsequent processing time for generating additional candidates. The previously-generated candidates are compared with the revised partial query to select which of the candidates to be re-used and expanded for generating additional tokens. Additional tokens can be generated in parallel for the previously-generated candidates or with model values from the previous generation, enabling the tokens to be generated effectively with reduced latency consistent with user expectations for search-related autosuggestions.

The invention discloses a generative AI-driven physiological-music following response intelligent emotion regulation system. The system mainly comprises a physiological signal acquisition module, a signal preprocessing module, an emotion real-time decoding module, a music-emotion response calibration module and a music generation and emotion regulation module. On the basis of the generative AI technology, music expectation, a music tension release mode and other music psychology theories are fused, music capable of directionally adjusting the emotional state of the user is generated through real-time accurate decoding of the emotional state of the user through multi-mode physiological signals, the user expectation is gradually established and released at the high point, roller coaster-like emotional changes of the user are caused, and the user experience is improved. And the user can subjectively obtain pleasant and satisfied positive emotions and the like.

Embodiments of the present application provide an operating parameter recommendation method and apparatus, used for in a big data processing scenario, recommending operating parameters for a computing device on the basis of the resource consumption under different operating parameters, without depending on historical data. The method comprises: first, on the basis of information obtained during the processing of historical tasks in a big data system, establishing a first relationship among the corresponding data information, parameters of a computing device processing the tasks, and time required to process the tasks, and a second relationship among the data information, the parameters, and resources of the computing device consumed for processing the tasks; inputting data information of a task to be processed, and the first relationship and the second relationship to a genetic algorithm, and outputting multiple sets of time values and resource values, i.e., modeling the process of the computing device executing data processing tasks, so as to fit the relationship between the time and resource consumption of the computing device and the operating parameters of the computing device; and determining operating parameters on the basis of actual available resources of the computing device or resource consumption that a user desires.

The invention provides a presentation document generation method and device and a medium, and relates to the technical field of artificial intelligence, and the method comprises the steps: comparing active input information of a user with a preset theme in a local database, and determining a user expected theme for generating a presentation document; obtaining preset sub-themes under the user expected theme in the local database, generating a user question according to the sub-themes, and determining a plurality of user expected sub-themes for generating the presentation document through conversation between the user question and the user; generating a main title and a plurality of sub titles of the presentation document according to the user expected theme and the plurality of user expected sub-themes; obtaining content data corresponding to each user expected sub-topic in a local database, generating sub-contents of each sub-title according to the corresponding content data, and generating main contents of the main title according to all the sub-contents; the main title and the main content and the sub-title and the sub-content are combined to generate a presentation document. According to the method, comprehensive and professional demonstration documents are generated in combination with database multi-level classification.

The invention discloses a big language model dialogue optimization method, device and equipment and a computer storage medium, and the method comprises the steps: responding to the entering of a current dialogue round, and obtaining configuration information corresponding to the current dialogue round based on the type of the current dialogue round; obtaining user input information corresponding to the current dialogue round; on the basis of a dialogue round switching judgment strategy corresponding to the dialogue round switching strategy configuration information, whether the current dialogue round needs to be switched or not is judged; if switching is needed, determining a next dialogue round corresponding to the current dialogue round based on a dialogue round switching strategy corresponding to the dialogue round switching strategy configuration information, and entering the next dialogue round; if switching is not needed, a reply task is generated based on a reply prompt word corresponding to the reply strategy configuration information and the user input information, the reply task is executed through a large language model, and reply information is generated; reply information is output in the current dialogue round, and user expectation is met.

The invention relates to the technical field of artificial intelligence, in particular to a verbal skill confrontation training generation method and device based on a large model, equipment and a storage medium, and the method comprises the steps: generating a simulation inquiry based on a preset user portrait, then obtaining a response of a service large model, and comprehensively evaluating the response quality; and the specific defect type of the service model in logic understanding or verbal skill expression is diagnosed through the cognitive deviation between the response and the user expectation by another evaluation model, so that a targeted optimization strategy is generated, the service model is finally driven to carry out directional reinforcement learning, and the verbal skill ability of the large service model is iteratively improved. According to the method, an adversarial sample is dynamically generated, and deep diagnosis is carried out in combination with cognitive deviation, so that a service model can understand deep intentions and emotion demands of different user groups fundamentally. Therefore, the strain capacity and the communication accuracy of the service model in a real interaction scene are remarkably improved, and the user satisfaction is effectively improved.

The embodiment of the invention provides an interaction method and device, equipment, a storage medium and a program product. The method includes, in response to receiving a user input, generating a first text based on the user input. And obtaining first rich media content corresponding to at least one part of the first text at least based on the first text. The first text and the first rich media content are presented as at least part of a reply to the user input. In this way, the rich media content corresponding to the reply content can be added based on the reply content to respond to the user input, so that the expected rich media content can be provided as far as possible when the user expects to respond to the rich media content, and the user experience and satisfaction are improved.

The invention discloses a product engineering change execution management method based on a PLM system, relates to the technical field of product management, and has the functions of acquiring changed data through a datamation technology, a development management system and an automatic series PLM system, automatically establishing tasks according to engineering, automatically providing an SOP operation instruction change application form, automatically managing overdue and the like. Platform-based, transparent and intelligent management is realized; the automatic series PLM system obtains the changed data, performs automatic modeling on the changed data, performs automatic conversion and transmission on the changed data, automatically generates task decision arrangements in different environments based on the association rule base, effectively conforms to user expectations, and improves the user experience. Trouble steps, labor cost and time delay of manually transferring the changed data are greatly reduced, efficient feature extraction is performed on the changed data, the relation between the changed data and original data is deeply sensed, generated task decision arrangement has higher robustness, and environment, cost, resources and user requirements are met in multiple aspects.

The invention provides a method and device for making a diversified analysis chart based on a UE engine, and belongs to the technical field of charts.According to the embodiment of the invention, based on source data, a service index weight matrix conforming to a service scene can be obtained, and based on the source data and demand description information, the diversified analysis chart is made. The method comprises the following steps: obtaining a chart type weight matrix which accords with data characteristics and user expectations through a business index weight matrix and a business index weight matrix, further recommending an appropriate chart type to a user while realizing deep analysis of data by comprehensively considering the business index weight matrix and the chart type weight matrix, and further improving the user experience by converting a multi-dimensional matrix into executable parameters of a UE engine. According to the embodiment of the invention, the powerful computing power support of the cloud server and the powerful graphic rendering capability of the UE engine can be utilized to provide a more visual and comprehensive diversified analysis chart for the user, so that the display efficiency is improved, and the use experience of the user is remarkably improved.

The invention discloses a trajectory planning method and device, electronic equipment and a storage medium, and relates to the computer technology, and the method comprises the steps: determining a target region according to obtained region information, and carrying out the feature extraction of map data corresponding to the target region, and obtaining region map features; performing feature extraction on the received image information to obtain required track features; and performing feature matching according to the regional map features and the demand track features to obtain a planned track of the demand path. According to the method and the device, the pattern expected by the user is combined with the real geographical environment in a mode of performing feature matching on the regional map features and the demand track features, an accurate and feasible planning track can be generated according to conditions such as actual roads and terrains, the track planning efficiency is improved, and the user experience is improved. And the beneficial effect of improving the precision and the aesthetic degree of the planned trajectory and the pattern required by the user is further achieved.

The invention provides a model updating method, device and system, in the model updating method, computer equipment displays a first processing result obtained by processing system data of a network system according to a model, and a user can perform knowledge data input operation after seeing the first processing result. The computer device obtains target knowledge data obtained after format conversion is conducted on the knowledge data, then the computer device responds to the model updating instruction, a model is updated through the target knowledge data, an updated model is obtained, and finally system data of the network system is processed according to the updated model to obtain a second processing result. And displaying the second processing result. The user can directly participate in the model adjusting and optimizing process, and the model of the user can be updated in real time to meet changing business requirements and personalized expectation of the user.

Described is a method for instilling the haptic dimension of texture to virtual and holographic objects using mid-air ultrasonic technology. A set of features is extracted from imported images using their associated displacement maps. Textural qualities such as the micro and macro roughness are then computed and fed to a haptic mapping function together with information about the dynamic motion of the user's hands during holographic touch. Mid-air haptic textures are then synthesized and projected onto the user's bare hands. Further, mid-air haptic technology enables tactile exploration of virtual objects in digital environments. When a user's prior and current expectations and rendered tactile texture differ, user immersion can break. A study aims at mitigating this by integrating user expectations into the rendering algorithm of mid-air haptic textures and establishes a relationship between visual and mid-air haptic roughness.

The embodiment of the invention provides an alarm information processing method, device and system, and an alarm information auxiliary processing method, device and system, and the method can comprise the steps: receiving first alarm information reported by a first camera device, and the first alarm information comprises a first alarm video; performing multi-modal feature extraction on the first alarm video to generate a first multi-modal feature vector; and based on the first multi-modal feature vector and a decision matching object, generating a push decision of the first alarm information, the decision matching object being determined according to a labeled visual sample uploaded by the client, and the labeled visual sample being obtained by labeling a visual sample by a user at the client. In this way, more accurate alarm content which better conforms to the expectation of the user can be provided.

The invention discloses a space computing power network task migration method and system based on dynamic environment perception, and relates to spaceflight electronics and data processing technologies, and the method comprises the steps: determining that a user node obtains a computing resource needed by a computing power service from a satellite node in a space computing power network; calculating a task migration moment caused by satellite node movement and an alternative satellite set capable of receiving tasks according to the dynamic environment information; based on a candidate satellite set, an optimal satellite is screened out according to different user expected targets, before the migration moment arrives, a calculation task is migrated to the selected satellite in advance, and seamless continuity of services is guaranteed; and for the high-priority task, carrying out redundancy migration on the alternative scheme without computing resource intersection. According to the method, the problems of low efficiency, service interruption caused by sudden faults, multi-target optimization conflicts, resource shortage scene migration failure and the like of a traditional migration algorithm in a spatial network topology dynamic scene can be effectively solved.

The invention relates to the technical field of shoe product customization, in particular to a shoe product management system for big data processing shoe material customization, which comprises a data collection and preprocessing unit, a natural language processing core unit, a quantitative index generation unit and a customization process fusion unit, a data collection and preprocessing unit collects and standardizes expected text data of a user for shoe materials, a natural language processing core unit identifies user intentions, keywords and modifiers and analyzes demand priorities, a quantitative index generation unit converts functional demands and style preferences into quantitative indexes and feature vectors, and the quantitative indexes and the feature vectors are stored in a database. The customization process fusion unit inputs quantitative indexes into a computer aided design model, screens shoe materials, adjusts design parameters and generates a design scheme, defines a design direction by using a quantification means, reduces errors between user expectations and design results, considers shoe material cost and supply conditions, meets diversified requirements of users, and improves design efficiency. And the shoe product customization quality and the user satisfaction are improved.

The invention relates to the technical field of advertisement design, and discloses an AI virtual human interaction method and system, and the method comprises the steps: receiving original demand data inputted by a user, generating a brand feature vector, and generating first virtual human data, first line data and first product model data based on the brand feature vector; and performing cooperative adjustment based on the ith interaction instruction to generate a virtual human image. By implementing the method and the system, the functions of full-process intelligent design, data processing, collaborative generation, interactive response, scene adaptation and the like are improved, an efficient and complete virtual human image customization scheme is formed, and the problem that multi-source heterogeneous data are difficult to comprehensively analyze when user requirements are processed by a traditional method is solved. The problems of large deviation between generated content and user expectation and poor scene adaptability caused by lack of a collaborative adjustment mechanism of a virtual human image, lines and a product model, low processing efficiency of a modification instruction and incapability of ensuring cross-modal consistency in the prior art are solved.

The invention belongs to the technical field of big data processing, and discloses an operation and maintenance data management platform based on generative artificial intelligence, which comprises an operation and maintenance data storage unit, an interaction unit, a display unit, an external field working efficiency evaluation unit and a contract operation and maintenance evaluation unit, according to the method, the user intention is analyzed through the generative model and the thinking chain, and the data source through which the user demand needs to be answered is judged, so that the problems of overlong reply time, overlarge calculation amount and excessive system resource consumption caused by searching a large amount of invalid reference data are avoided; and a more specific and accurate information retrieval result and a final reply result conforming to the expectation of the user are obtained. According to the embodiment, the stability and the operation efficiency of the system are greatly improved.

The invention provides an adaptive test case generation method and system based on a large model, and the method comprises the steps: calling a pre-constructed cue word generation agent in response to an instruction for generating a test case, and generating a matched target cue word and a recommended target test case generation model based on data input by a user; generating a first test case based on the target cue word by using the target test case generation model; displaying the first test case, and obtaining a first label input by a user for the displayed first test case; the target test case generation model is called, a second test case is generated in combination with the user intention and the first test case, and the matching degree of the second test case and the test case expected by the user is higher than the matching degree of the first test case and the test case expected by the user.

The present disclosure relates generally to systems and methods for updating an input prompt for a generative AI model (e.g., an LLM) based on feedback that is provided in connection with an output from the generative AI model that is unsatisfactory. For example, where a user indicated that an output from the generative AI model is incorrect, inaccurate, or is an otherwise unsatisfactory response to an input prompt, this disclosure describes models to facilitate generation of feedback hints and / or additional information that can be included within an updated prompt that, when provided as an input to the generative AI model, has an improved likelihood to return an output that is in-line with user expectations. Indeed, features of the systems and methods described herein provide a framework for improving outputs of generative AI models that are more accurate or otherwise responsive to the input prompts.

The embodiment of the invention provides a text generation method and device, equipment, a medium and a program product. The method comprises the following steps: displaying an original text and a first control in a first page; in response to a trigger operation of the first control, displaying a second page, the second page comprising at least one candidate title corresponding to the original text; in response to a trigger operation of a target title in the at least one candidate title, displaying content key points of at least one hierarchy of the target title, the content key points of the at least one hierarchy representing nodes of different depths of a hierarchical stacking structure corresponding to the target title; and in response to a selection operation of the candidate titles and the content key points, generating a target text based on the selected candidate titles and the selected content key points. According to the embodiment of the invention, the text meeting the expectation of the user can be efficiently and accurately generated, and the problem that the text meeting the expectation is difficult to accurately generate based on creative inspiration is solved.

The invention discloses a three-dimensional model generation method based on interactive editing, a computer medium and equipment. The method comprises the following steps: acquiring an initial three-dimensional model; modification parameters of the user for the initial three-dimensional model are obtained, the modification parameters are parameters of simulation modification performed by the user under target rendering characterization, the target rendering characterization comprises at least one of dominant rendering characterization and invisible rendering characterization, and the user can perform simulation modification under appropriate rendering characterization; the modification parameters are converted into modification constraints of the target three-dimensional model generation process; the modification constraint is used for guiding the modification direction of the initial three-dimensional model; and finally, based on the modification constraint and the initial three-dimensional model, generating a target three-dimensional model expected by the user. According to the method, the modification effect of the initial three-dimensional model can be restrained to conform to the expectation of a user, unreasonable modification in simulation modification can be corrected, the detail modification degree of the user can be reduced, and the accuracy of three-dimensional model generation can be improved.

The invention relates to the field of vehicles, and provides a vehicle-mounted man-machine interaction method, a vehicle-mounted man-machine interaction device and electronic equipment aiming at the problem of how to enable a vehicle-mounted terminal to accurately respond to the intention of a user and realize an application function expected by the user. The method comprises the steps that any one or a combination of more of vehicle data, driver data and environment and context data serves as a data source, a semantic text sequence is obtained according to the data source, and the semantic text sequence comprises one or more feature texts; the feature text is used for describing any one or a combination of more of a vehicle feature, a driver feature, an environment feature and a context feature, and the feature text is a text character string described by referring to a natural language; taking the semantic text sequence as the input of an intelligent model, and obtaining a prediction result output by the intelligent model; and calling the corresponding application service according to the prediction result. According to the method provided by the embodiment of the invention, the prediction accuracy of the intelligent model can be improved, and the user experience of man-machine interaction is improved.

The invention provides a perceptual engineering-based vehicle body selection design method. The perceptual engineering-based vehicle body selection design method comprises the following steps of: acquiring vehicle body data and comment information of a whole vehicle from data permitted to be accessed; analyzing and sorting the obtained comment text data by using a natural language processing technology to form a database; collecting user expectations, and performing semantic reasoning and analysis on the collected user expectations based on the formed database to obtain product performance semantic weights of the user expectations; and performing quantitative matching on the obtained product performance semantic weight expected by the user and the obtained vehicle body data by using the perceptual engineering model, and determining the vehicle body data corresponding to the vehicle model most conforming to the user expectation. And finally, the product with the highest customer expectation score is determined to correspondingly obtain the target product, the designed optimal product scheme is determined, and the vehicle body design efficiency and reliability are improved.

This application provides a model training method, training system, and related equipment. The method includes the following steps: acquiring positive sample data, wherein the positive sample data includes input samples and positive labels, the input samples include questions, and the positive labels include the answers corresponding to the questions; inputting the input samples into a first large model to be fine-tuned, obtaining the first negative label corresponding to the input sample; determining the first score of the first negative label based on the relevance of the first negative label to the question and the quality of the response to the first negative label based on a scoring model; inputting the input samples into the first large model; and fine-tuning the first large model based on a loss function to obtain a second large model. The loss function is used to guide the first large model to improve the prediction probability of positive labels and the prediction probability of negative labels with scores greater than a threshold, so that the model can not only learn standard answers that meet user expectations, but also generate more diverse answers, thereby improving the fine-tuning effect of the large model.

Disclosed are an online talk game method and system in which a plurality of users interacts and match composition rates by sharing opinions. A server unit announces a talk topic and receives and announces opinions of the users. The server unit receives the user's answer to the question and the expecting rate, calculates the composition rate of the answer, and determines that the smaller a difference between the composition rate and the user's expecting rate, the more advantageous it is, and the larger the difference, the more disadvantageous it is. This talk game can provide an interactive game that allows users to become immersed when a large number of users participate in the talk game, and prevent many ties, prevent collusion between the users, and reduce user confusion.

The invention provides a pairing method of smart home equipment and a control terminal and the smart home equipment. According to the method, user figure data, user hand data and hand holder data in a target room are obtained by adopting a millimeter wave detection technology, and the data are processed by adopting a neural network model technology to determine whether a target control terminal exists in the target room; compared with the prior art, the pertinence of wireless communication pairing between the smart home device and the control terminal is improved, so that the pairing result conforms to the user expectation, and the problem that the pairing result does not conform to the user expectation due to the poor pertinence of wireless communication pairing between the smart home device and the control terminal in the prior art is solved.

The invention relates to the field of terminals, in particular to a video generation method, electronic equipment and a computer readable storage medium. The method comprises the steps that when a user instruction is monitored, first character information contained in the user instruction is recognized; obtaining a confidence coefficient corresponding to the first character information, wherein the confidence coefficient is used for representing a credibility degree of an identified character; if it is determined that a figure confirmation process is executed according to the confidence coefficient corresponding to the first figure information, confirming a figure corresponding to the first figure information to obtain a confirmation result; and generating a video according to the confirmation result. Through the method, the problem that the generated video does not conform to user expectation due to inaccurate material acquisition in the prior art is solved.