5 results about "String analysis" patented technology

A computerized method of assigning a building automation system point type to a plurality of unclassified data points is provided. The method includes receiving unclassified data points and attributes for each data point. The method includes receiving classifications for a first subset of the unclassified data points. Each classification associates a data point with a building automation system point type. The method includes generating a term set containing substrings that appear in the attributes. The method includes generating a first matrix describing a frequency that the substrings appear in the attributes. The method includes calculating an indicator of a probability that the presence of the selected substring results in the data point belonging to the selected point type. The method includes assigning a point type to a second subset by finding the substring and potential point type pair having the greatest indication of probability.

The invention relates to the technical field of artificial intelligence and data processing, in particular to a data format conversion and import method and device based on artificial intelligence. The method comprises the following steps: acquiring a source data file containing a plurality of fields, wherein the names, formats or units of the fields are not uniform; analyzing semantics of the source data through a large language model (LLM) or other artificial intelligence models, and determining a mapping relation with a target data structure; deducing or complementing missing or non-direct corresponding fields, including unit or format conversion, character string analysis, numerical calculation, time conversion and deduction based on external knowledge or business rules; and generating target data meeting the requirements of the target system, and importing the target data into a database or outputting the target data as a file in a specified format. The method can be suitable for various scenes, such as reckoning the year of birth according to the age, deriving the city according to the postcode, analyzing the packaging information to calculate the weight of a single piece, converting the exchange rate, reckoning the natural language time and the like. According to the method and the device, the intelligent import of the open data file can be realized without a fixed template, the manual operation cost is remarkably reduced, the data processing efficiency and accuracy are improved, and the method and the device have good universality and expansibility.

The invention discloses an automatic workshop AGV intelligent transfer system, and relates to the field of material transfer automatic control. The invention aims to solve the problem that an existing workshop material transfer method is high in error rate in the transfer process. The method comprises the following steps: receiving a task information character string sent by a workshop control center and analyzing the task information character string; obtaining an AGV scheduling scheme based on a workshop data twinborn model; a task instruction is generated according to the task information character string analysis result, the task number and the flying bar number in the skip car state data table and the task execution information JSON format, and the task instruction is sent to the AGV control system; and the AGV control system feeds back a task execution state and AGV position data, and writes the task execution state and the AGV position data into the skip state data table and the AGV state data table. The AGV material transfer device is used for achieving AGV material transfer in the workshop.

Create a timeline that displays the relationships between a specific subject and their associates, based on information about that subject obtained from multiple documents. [Solution] The information acquisition means acquires subject-related information related to a specific subject from multiple documents. The extraction means extracts multiple strings that meet predetermined criteria from the subject-related information. The analysis means organizes the multiple strings according to a predetermined format for the specific subject and for people other than the specific subject, and detects strings that have a predetermined relationship among the multiple strings, and outputs the organized strings and information indicating the relationship. The timeline creation means creates a timeline that displays strings related to the specific subject and strings related to people other than the specific subject in parallel on a timeline, and also displays information indicating the strings that have a relationship among the multiple strings.

This involves organizing the information about a specific individual obtained from multiple documents and examining their relationships. [Solution] The information acquisition means acquires subject-related information related to a specific subject from multiple texts. The extraction means extracts multiple strings that meet predetermined criteria from the subject-related information. The analysis means organizes the multiple strings according to a predetermined format, detects strings that have a predetermined relationship among the multiple strings, and outputs output information that includes the organized strings and information indicating the relationship.