12 results about "Time expression" patented technology

The invention relates to the technical field of intelligent interaction, in particular to an artificial intelligence interaction robot, which comprises a statement recognition module for analyzing a statement structure, separating trunk and affiliated contents, marking a grammar role to generate a semantic structure, a time marking module for recognizing and marking a time sequence, and a path construction module for extracting a historical path for rearrangement. The expression cleaning module identifies and clears redundancy, and the output generation module is connected with the buffer area and the path to generate complete output. According to the method, trunk and affiliated components are identified through multi-round statement structure analysis, accurate separation and reconstruction of semantic elements are realized in combination with word role marking, a time arrangement list is generated according to a time expression sequence, semantic evolution judgment is improved, and a historical path is matched to construct an expression rearrangement structure to enhance semantic connection; and identifying a redundant statement optimization structure and definition, and realizing continuity and logic consistency of interaction contents.

The invention discloses a BVT format high-speed motion instruction generation method based on time expression and a related device, a tool nose displacement instruction is firstly defined, the tool nose displacement instruction is a track point sequence sampled in an equal period, and each sampling point is expressed by sampling time and an accumulated displacement value; then segmenting a tool nose displacement instruction, dividing a continuous track into a plurality of sub-segments by analyzing the geometric curvature of a time-displacement curve, and ensuring that the curvature change of each sub-segment is gentle and each sub-segment contains a preset number of sampling points; then selecting a decatic polynomial curve as a fitting model, fitting sampling points by using a least square method under set constraints, and ensuring that the curve is smooth and third-order derivatives are continuous; introducing a Lagrange multiplier to construct a function, converting a constrained curve fitting problem into an unconstrained extreme value problem, and solving a decatic polynomial coefficient; and finally, based on the fitting polynomial curve, generating a high-speed motion instruction which covers a straight line, an arc and an NURBS interpolation instruction, and each instruction comprises parameters such as polynomial times, fitting points and the like. The invention aims to solve the problems of low interpolation precision, poor track smoothness and slow response of the traditional motion instruction format in high-speed and high-precision motion control.

The invention discloses an information processing method, which comprises the following steps of: acquiring original information text data from subscribed terminal data streams, and preprocessing and outputting the original information text data; a double-layer BiLSTM-CRF neural network structure is adopted to recognize diversified time expressions, and explicit time expressions are extracted; implicit time information is captured through a multi-head self-attention mechanism, and the implicit time information is extracted in combination with a context understanding model; the relative time is converted into absolute time through time sequence graph reasoning; the reminding frequency and mode are dynamically adjusted based on the time urgency and information importance two-dimensional score; the expired information is automatically classified and archived, and the storage space is released; according to the method disclosed by the invention, the problems that text information has context ambiguity influence and depends on dates can be further solved, fuzzy expression cannot be solved, and the time extraction precision under complex expressions including nesting time entities and the like can also be improved.

A method of providing a conversation service, performed by an electronic device, includes receiving an utterance input, identifying a time expression representing a time in text obtained from the utterance input, determining a time point related to the utterance input based on the time expression, selecting a database corresponding to the determined time point from among a plurality of databases that store conversation history information of a user using the conversation service, interpreting the text based on the conversation history information of the user obtained from the selected database, generating a response message to the utterance input based on a result of the interpretation, and outputting the generated response message.

The embodiment of the invention provides a time information extraction method, a time information generation method, electronic equipment and a time information system. Relates to the technical field of artificial intelligence. The to-be-processed information is input into a preset big data processing model, so that the preset big data processing model extracts a time text included in the to-be-processed information, the time text is converted according to a preset time expression rule, and time information obtained through conversion is output; wherein the preset time expression rule at least comprises that the time corresponding to the time length expressed by the time text in a preset time unit is expressed by adopting a reverse counting mode of a time ordinal number in a time period to which the preset time unit belongs, and the time period to which the preset time unit belongs is a time period corresponding to the date expression mode. In this way, the preset big data processing model can accurately represent the time indicated by the time text.

The invention discloses a text-to-SQL (Structured Query Language) conversion system based on historical questioning and fuzzy time rewriting. Comprising a fuzzy time processing module and a historical question asking module. The fuzzy time processing module comprises the following steps: acquiring current system time as reference time; the system uses a predefined time template to analyze question pairs input by a user, and the template can recognize various common fuzzy time expressions to capture relative time expression words; performing intelligent conversion on the recognized fuzzy time expression by using a large language model, and converting relative time into accurate date and time expression; verifying and rewriting; the historical question asking module is used for calling a large model to carry out historical dialogue inquiry after inputting questions; generating a rewritten question by using the historical question-asking node; therefore, the system generates appropriate questioning content. According to the invention, the accuracy and reliability of the system in processing time and date problems and multiple rounds of conversations are improved.

The application relates to the technical field of knowledge graph and information processing, and discloses a scientific and technological innovation capability intelligent analysis method and system based on a time sequence event graph, which comprises the following steps: performing standardized processing, entity identification and event assembly on multi-source scientific and technological innovation data, and constructing a time sequence event graph containing time boundary information; establishing a subject partial order index based on an event time interval to depict the sequence of events; for newly arrived events, event merging and version management are realized through candidate alignment scoring, and event versions participating in calculation are determined through activity weight; when an activity version changes, affected subgraphs are identified and local representation is updated, and a scientific and technological innovation capability analysis result is generated in combination with an event path. The method can effectively solve the problems of inconsistency of multi-source data, uncertainty of time expression and dynamic updating of data, and improves the accuracy and stability of the analysis result.

The invention belongs to the technical field of robot repair requesting, and particularly relates to a time standardization method for a robot repair requesting scene, which comprises the following steps: S1, performing multi-round dialogue time association processing, receiving a time text provided by a user in the current round, if the time text is a fuzzy expression, extracting identification date information in the previous round, and if the time text is not a fuzzy expression, extracting identification date information in the previous round; combining the date information and the current time text into an input parameter, judging whether the input parameter contains an identified date or not, if not, entering S2, and if yes, entering S3; s2, date reasoning: matching date logic in a user text through semantic keywords, and outputting a standardized date; and S3, time reasoning: matching time logic in the user text based on the semantic keywords, and outputting initial time in combination with a preset default time point. Through the keyword processing mode and multi-round context fusion, precise analysis of complex time expression is achieved at a low-computing-power terminal, dependence on high-performance computing resources is not needed, and the method can adapt to the light-weight operation environment of edge equipment.

The invention relates to the field of natural language analysis, and provides a time entity analysis method, device and equipment, a medium and a computer program product.The method comprises the steps that a to-be-processed text is recognized through a natural language understanding model, and a time entity of the to-be-processed text is obtained; determining time expression information of the to-be-processed text based on the time entity; and analyzing the time expression information through the time analysis data structure to obtain a time analysis result. According to the method, time entity recognition is performed on the to-be-processed text through the natural language understanding model, the time entity in the to-be-processed text is obtained, the time expression information of the to-be-processed text is obtained on the basis of diversity expression on the time entity, and then the time expression information is analyzed through a structured analysis mechanism, so that the time expression efficiency is improved. And obtaining a time analysis result. According to the method, the natural language understanding model and the structured analysis rule are combined, and time analysis which is more flexible and higher in generalization ability is achieved.

The present disclosure relates to a system for interpreting and managing imprecise temporal expressions. Techniques for extracting, identifying, and consuming imprecise temporal elements ("ITE") are disclosed. User input may be received from a client device. A prediction for one or more time intervals indicated by the user input may be generated based on an ITE model. The user input may be associated with the prediction and provided to the client device.

The invention discloses a correction method and system for time type generation accuracy in a Text2SQL task, and the method comprises the steps: creating the Text2SQL task based on a received query problem inputted by a user, and executing the Text2SQL task to convert the query problem into a semantic SQL; extracting a time expression in the semantic SQL, and calling a time inference model to carry out time correction so as to generate real time based on the time expression; the semantic SQL is corrected on the basis of the real time, and the corrected semantic SQL is obtained; and correcting the information of the corrected semantic SQL, converting the corrected semantic SQL into an executable query SQL, carrying out query based on the query SQL, and returning a query result. According to the invention, reasoning of a time expression is realized by using a time conversion algorithm, real time is output, and the accuracy of time identification is improved; time expression extraction, SQL generation and time correction can be completed by calling the large model at a time, the process is simple, and the efficiency is high.

This invention discloses an internationalized time-aware recall method based on text time semantic parsing, comprising the following steps: S1. Receiving user input; S2. Complexity classification; S3. Adaptive time semantic extraction: an adaptive time semantic extraction strategy extracts time expressions from natural language text; S4. Time normalization: converting the time expressions into standardized time interval representations; S5. Time zone processing: converting the time interval representation into a timestamp of a standard time zone according to the user's time zone parameters; S6. Time-constrained memory retrieval: performing time-constrained memory retrieval in a vector database based on the time interval representation; S7. Outputting memory results: returning the memory results to the user. This invention supports multiple expression forms such as absolute time, relative time, fuzzy time, and time range, supports multilingual extensions including Chinese, English, and Japanese, supports global time zone conversion, and achieves end-to-end time-aware memory recall, significantly improving user query efficiency and user experience.