6 results about "Matched sample" patented technology

The present application relates to an entity matching method, device and medium based on meta-rule induction and retrieval, which comprises: obtaining a label data set containing matching / mismatching label pairs; obtaining a representative sample subset by using a sampling method based on label balance and semantic diversity; for each label pair in the subset, generating matching reasoning basis and checking and correcting by a large language model, and refining into an instance-level natural language matching rule; embedding the instance-level rule into a semantic vector and clustering, each cluster synthesizes a meta-rule to form a rule base; rewriting the meta-rule into a task-adaptive rule according to the target scene; encoding the to-be-matched sample pair into a query vector, calculating the semantic similarity with the rule vector, and retrieving K rules by the maximum edge correlation criterion; inputting the to-be-matched sample pair and the retrieved rule into the large language model, and outputting the matching label. The present application refines the scarce supervision into the retrievable rewritten meta-rule, and realizes the stable generalization of the cross-entity matching task.

This invention provides a method, apparatus, device, and storage medium for inferring a single-sample ncRNA regulatory network, relating to the field of gene identification technology. The specific implementation includes: acquiring ncRNA and target gene transcriptome data of a matched sample; for each target sample in the matched sample, calculating a first regulatory relationship strength matrix and a second regulatory relationship strength matrix of ncRNA and target gene before and after removing the target sample using a preset statistical algorithm; obtaining the fusion regulatory relationship strength matrix of ncRNA and target gene corresponding to the target sample based on the first and second regulatory relationship strength matrices; and inferring the single-sample ncRNA regulatory network of the target sample based on the fusion regulatory relationship strength matrix of ncRNA and target gene corresponding to the target sample. This invention can reflect the regulatory relationship strength between ncRNA and target gene at the single-sample level by constructing statistical correlation values, thereby inferring the single-sample ncRNA regulatory network.

The invention discloses an address data processing method and a geocoding method, and the address data processing method comprises the steps: processing sample data, and obtaining partial order relation sample data for sample target address data; according to the preset correlation index data and correlation index data between multiple pieces of specified sample candidate address data contained in the partial order relation sample data and the sample target address data, obtaining matched sample candidate address data of which the correlation index data with the sample target address data is greater than the preset correlation index data. The initial model is trained through the partial order relation sample data, so that the association index data between the target recall address data predicted by the trained address association index model in the multiple recall address data of the to-be-queried address data and the to-be-queried address data is greater than the preset association index data; and the accuracy of the target recall address data obtained by the model is improved.

The present disclosure provides a data processing model training method and device, and a data processing method and device, relates to the technical field of data processing, and in particular to large model technology and content recommendation technology. The implementation scheme is as follows: determining a training sample set, wherein each training sample in the training sample set comprises spliced sample content and a review text for the sample content; determining at least one matching sample matched with the training sample; encoding the training sample by using a data processing model having current parameters to obtain a representation vector of the training sample; encoding the at least one matching sample by using the data processing model having the current parameters to obtain a representation vector of the matching sample; and adjusting the current parameters of the data processing model to minimize the loss between the representation vector of the training sample and the representation vector of the matching sample.

The invention discloses a training method of a semantic analysis model for recalled positions and resumes. The training method of the semantic analysis model used for recalled positions and resumes comprises the steps that delivery behavior data, user resume data and position description data of a user are obtained, and the delivery behavior data comprise positions where the user delivers the resumes; based on the positions of the resumes delivered by the user, constructing matching samples of the positions of the resumes; based on a pre-configured language analysis model, identifying the delivery behavior data, the user resume data and the position description data corresponding to the matching samples, and screening out the matching samples corresponding to the user resume data which does not meet the position constraint requirements to obtain positive matching samples; in the samples which do not meet the position constraint requirements, negative matching samples are extracted; and performing fine tuning training on a pre-constructed semantic analysis model based on the positive matching sample and the negative matching sample to generate a semantic analysis model of the position and the resume.

The application provides a data matching method and a data matching device, which are applied to the field of data processing and are beneficial to improving data processing efficiency. The method comprises the following steps: matching sample data by using a first matching rule to obtain a first matching result; determining a first evaluation index based on the first matching result; adjusting a preset field of the first matching rule to obtain a second matching rule in the case that the first evaluation index does not satisfy a preset condition, and the adjustment comprises at least one of the following: adding the preset field, deleting the preset field, changing a matching range of the preset field or changing matching content of the preset field; matching the sample data by using the second matching rule to obtain a second matching result; determining a second evaluation index based on the second matching result; and matching to-be-matched data by using the second matching rule in the case that the second evaluation index satisfies the preset condition.