49 results about "Seed entity" patented technology

The invention provides a recognition method of named entities in microblog messages. The recognition method includes that a few named entities are specified as seeds; a certain number of microblog messages from the original microblog message set to be processed are automatically marked as a training data set; and then the training data set is utilized to train a named entity identifier and the trained named entity recognizer is utilized to recognize the named entities in the microblog messages. According to the recognition method of the named entities in the microblog messages, only a few existing seed entities need to be specified to enable a high quality training set to be automatically marked; the labor costs are significantly reduced for the microblog messages which are texts capable of being updated rapidly; and an iterative mode is utilized to generate high quality marked data step by step and each time first N newly named entities which can most reflect the appearing law of the named entities in real microblog data are selected to add into a seed bank, so that finally generated marked data can well cover the integral microblog message set.

The invention provides an entity alignment method and device. The method and device aim to solve the problem that traditional knowledge alignment method usually requires cumbersome manual labor or elaborate manual construction. The method comprises the steps of acquiring vector representations of entities in a first knowledge graph and vector representations of the entities in a second knowledge graph separately, binding vector representations, with the same meanings, of the entities in the first knowledge graph and the second knowledge graph according to an input alignment seed entity pair set so as to acquire a third knowledge graph, performing iterative calculation of the similarity among the vector representations of the entities according to the third knowledge graph, the vector representations of the entities in the first knowledge graph and the vector representations of the entities in the second knowledge graph, in the process of iterative calculation, if the distance between a certain pair of vector representations of the entities is less than a threshold, adding the entity corresponding to the pair of vector representations to the third knowledge graph until the number of entities in the third knowledge graph is no longer increased. The entity alignment method and device are good in practicality.

The invention provides a method for synthesizing Chinese truffles and mycorhiza of China pinus montana. The steps related are as follows: filtration of China pinus montana seeds and truffle seed entities; culture of aseptic seedlings; preparation of microbial inoculum; arrangement, optimal selection and inoculation of culture substrates; culture of mycorrhizal seedlings; anatomization of mycorhiza forms; detection and confirmation of molecules and transplanting culture, and finally, the culture of truffles is realized.

The invention discloses a method for extracting an open category named entity by means of random walking on a map. The method comprises the steps that 1, a context, on a corpus, of a seed is analyzed to obtain a template; 2, the template is used for extracting a candidate entity from the corpus; 3, a map is structured according to the relation among a seed entity, the template and the candidate entity; 4, the confidence coefficient of the candidate entity is computed through the random walking algorithm on the map. The method can overcome the adverse effects on the computation of confidence coefficient of the candidate entity caused by different qualities of the template, and effectively improve the accuracy of extraction of the open category named entity. Experiments prove that the average accuracy of an extraction result is improved by 4.36%.

The invention provides an entity set extension method. The method comprises the steps that a seed entity set input by a user is acquired, and attribute information corresponding to each seed entity is determined in an RDF knowledge base according to the entity name of each seed entity in the seed entity set; according to the attribute information corresponding to each seed entity, same attributive characters corresponding to the seed entity set are determined, and other entities with the same attributive characters in the RDF knowledge base are determined to form an extension entity set; entities of the extension entity set are added to the seed entity set to obtain an extended entity set. According to the entity set extension method, the entity set extension method based on the RDF knowledge base is provided, due to the fact that the RDF knowledge base uses structured XML data, a server can excavate out semantic information among the seed entities, the extension result becomes more intelligent and accurate, and the extension efficiency of the entity set can be guaranteed.

The invention discloses a Grifola frondosa culture material. Forest land surface soil with content in weight percent being 10-30% is added in regular culture material. Due to adding forest land surface soil, the culture material in the invention can prevent Grifola frondosa from yield reduction owing to yellow water exudation, can keep moisture in the culture material well, thus increasing yield of Grifola frondosa seed entity, enhancing biological efficiency and having good popularization value.

The invention discloses a nested entity data identification method and device, and electronice equipment, and relates to the technical field of data identification. The method comprises the steps of permutating and combining seed entity vocabularies of different entity categories to generate a short text data set; defining at least one entity category label for a short text in the short text dataset, and index information of starting and ending of a sub-text, corresponding to each entity category label, in the short text; training a deep learning recognition model by using the defined short text data set as a training set; and recognizing the nested entity data by using the recognition model which is trained to reach the standard. According to the method, the entity labeling information is defined for the statement according to the start and end indexes and the entity category label, so that the multi-nested entity content labeling is simpler to implement, the labeling process and workload of nested entity recognition are optimized, the time cost and the labor cost are saved. And thus, the identification efficiency and accuracy of the nested entity data can be improved.

Embodiments of the invention provide an entity set expansion method and apparatus. The method comprises the steps of extracting candidate entities from a target knowledge graph to form a candidate entity set according to a pre-determined seed entity set; determining meta-paths between seed entities from a heterogeneous information network corresponding to the target knowledge graph, wherein each meta-path is a connection path, consisting of an entity type and a relational type, between two node types in the heterogeneous information network, and the two node types are node types corresponding to different seed entities; determining a first importance degree of each meta-path according to a quantity of seed entity pairs connected by each meta-path; according to the first importance degree of each meta-path, determining a second importance degree of each candidate entity in the candidate entity set; and determining the candidate entity with the second importance degree meeting a first preset condition in the candidate entity set as a to-be-expanded entity, and adding the to-be-expanded entity to the seed entity set. By applying the method and the apparatus, effective entity set expansion can be carried out.

The invention discloses an entity reference item recognition method based on a topic model and semantic analysis, and the method comprises the following steps: 1, carrying out the sentence segmentation, word segmentation, part-of-speech tagging and dependency analysis of an input corpus; step 2, based on syntactic analysis, obtaining noun phrases with complete boundaries as a candidate set of entity reference items, and then comprehensively utilizing an LDA topic model and a TF-IDF statistical algorithm to filter non-entity reference items from the candidate set; and step 3, measuring semanticsimilarity between the entity reference items and the seed entities, selecting seed categories with high similarity as entity categories, and then classifying the entity reference items of each entity category into corresponding reference item categories by utilizing shallow syntactic knowledge setting rules. The effectiveness of the entity boundary detection and classification method can be improved.

The invention discloses a named entity identification method and device, equipment and a storage medium, and relates to the fields of natural language processing, semantic analysis and understanding,artificial intelligence and the like. The method comprises the steps of performing entity identification on new domain text data to obtain new domain seed entity words; labeling the new domain text data according to the new domain seed entity words to obtain labeled new domain text data; training a named entity recognition model by using the labeled new domain text data to obtain a named entity recognition model suitable for the new domain; and identifying entity words in other text data of the new domain by utilizing the named entity identification model suitable for the new domain. Accordingto the embodiment of the invention, the data annotation workload can be reduced, the model migration training threshold is reduced, and the field universality of the algorithm is improved.

The invention discloses an entity alignment method based on weighted neighbor information coding, and the method specifically comprises the steps: 1), carrying out the preprocessing of data in two knowledge bases needing to be aligned, and extracting two knowledge base triples, entities and neighbor information thereof, and entities and type information thereof; 2) based on all currently discovered matching entity pairs, obtaining a vector representation corresponding to each entity through triple-based knowledge representation learning, weighted neighbor information coding and cross-knowledge-base entity-type graph embedding; 3) reasoning matching entity pairs in combination with three different vector representations of the entity; and 4) forming new training data by the discovered matching entity pairs and the priori aligned seed entity pairs, repeating the steps 1)-4) until the specified iteration times are reached, and outputting the discovered matching entity pairs. According tothe method, fewer entities appearing in the triad can be more accurately matched, and the method has a wide application prospect in the fields of knowledge fusion, knowledge questions and answers andthe like.

The invention provides a word classification model training method and device based on artificial intelligence, a word processing method and device, electronic equipment and a storage medium. The method comprises the steps: obtaining a seed entity word set composed of a plurality of seed entity words, wherein the plurality of seed entity words belong to a to-be-mined entity type; combining any twoseed entity words in the seed entity word set to obtain a positive example sample pair; obtaining a historical text including the seed entity words, and constructing a negative example sample pair according to the seed entity words and the historical text excluding the seed entity words; updating a word classification model through the positive example sample pair and the negative example samplepair, wherein the updated word classification model is used for determining the probability that the entity words to be recognized belong to the entity types to be mined. Through the method and the device, the richness of model training samples can be improved, the corpus annotation cost required by entity mining is reduced, and meanwhile, the training effect of the word classification model can also be improved.

The invention discloses a knowledge graph fusion method based on entity sequence coding. The method comprises the steps of 1, knowledge graph entity representation learning; 2, selecting a path code and an alignment model; 3, performing cross-language entity alignment on the model, wherein in the source language knowledge graph space, a two-hop sequence corresponding to other seed entities is constructed for one entity, a sequence possibly corresponding to the entity is constructed in the target language knowledge graph space, an alignment sequence with the highest probability is found out, and then a node at the same position is found out from the alignment sequence to serve as an alignment node of the node; 4, adding a new candidate seed node. Aiming at the problem of insufficient training corpus of a deep learning model in the prior art, the method based on entity path representation learning is put forward.

The invention discloses a pumpkin-glossy ganoderma intercropping method for repairing organic polluted soil, which comprises the following steps of: making a furrow on the organic polluted soil, arranging drainage ditches on four sides of the furrow, digging a glossy ganoderma bed in the furrow, opening a culture bag, vertically arranging the culture bag in the furrow bed in a mode that the inoculation surface is upward, covering the bag with soil, filling gaps by using soil, and keeping the soil moist; continuously culturing the culture bag in the open air and promoting the culture bag to grow the glossy ganoderma naturally; and transplanting vigorous pumpkin seedlings on two sides of the glossy ganoderma bed, constructing a pergola by using a plurality of pumpkin seedlings, shading the glossy ganoderma seed entities by the grown pumpkin stems and leaves, and providing CO2 by the glossy ganoderma seed entities to promote the photosynthesis of the pumpkin plants. The intercropping system promotes degradation or removes the organic polluted soil by using the pumpkin roots, the glossy ganoderma culture bag and the spore powder till the glossy ganoderma seed entities are mature and the growth period of the pumpkin is finished. The method can effectively realize efficient repair of the organic polluted soil, realizes safe production of the pumpkin and the glossy ganoderma at the same time of repairing, and is particularly suitable for control of repair of the polycyclic aromatic hydrocarbon, polychlorinated biphenyl and phthalate ester polluted soil.

The invention discloses a gradually-increased knowledge graph entity extraction method and system for electric power customer service questions and answers, and the method comprises the steps: takingelectric power customer service historical question and answer record data as a basic corpus, and forming a basic data set; extracting named entities and event entities on the basic data set and setting a coexistence relationship between the entities to form an initial seed entity set; extracting named entities and event entities on the corpus data of the electric power customer service field andconstructing a coexistence relationship between the entities to form an entity set corresponding to each data source; screening entities from the entity set corresponding to each power customer service corpus data source to expand the seed entity set, and forming an entity set oriented to the power customer service question and answer knowledge graph. The invention has the capability of autonomously selecting corpus data and entities.

The invention discloses a north cordyceps sinensis herba epimedii compound tea bag product and a producing method thereof. The producing method comprises the steps of: uniformly mixing 88% of rice, 9.6-10% of crushed corn particles, 0.4% of yeast powder, 0.4% of peptone, 0.15% of KH2PO4, 0.05% of MgSO4 and 1% of cane sugar or 0.4% of herba epimedii powder; adding stilled water according to a ratio by weight of 1: 1.3; after cooking and sterilizing at a high pressure, inoculating north cordyceps sinensis strains; freezing and drying seed entities after being cultured for 50 days; crushing the seed entities and sieving the seed entities with a 60-mesh sieve to be combined with the herba epimedii of 60 meshes according to a ratio of 1: (0.5-1); and filling the mixture in a filtering bag of 80 meshes, wherein each bag is 3-5 g; sealing, bagging and sterilizing by irradiation to obtain the north cordyceps sinensis herba epimedii compound tea bag finished product. The north cordyceps sinensis herba epimedii compound tea bag product, disclosed by the invention, has the advantages of enhancing immunity, preventing tumor, resisting to bacteria and diminishing inflammation, defying aging and the like and playing the function of berberidaceae perennial herb epimedii of tonifying kidney and strengthening yang as well as dispelling wind and eliminating dampness effectively.

The invention discloses a text entity detection method, and the method comprises the steps: carrying out the matching of each statement instance in a target statement through a seed entity set to obtain a matching result, and generating annotation data corresponding to the target statement according to the matching result; querying a statement instance matched with an unlabeled corpus word frequency table in the target statement, and modifying the labeled data according to a query result to obtain local labeled data; training a sequence annotation neural model by utilizing the local annotationdata; and performing sequence annotation on the unannotated corpus in the target statement by utilizing the trained sequence annotation neural model so as to obtain an entity set of the target statement. According to the method, high-quality entity mining can be realized on the premise of not being limited by the quality and the scale of the unlabeled corpus. The invention further discloses a text entity detection system, a computer readable storage medium and electronic equipment, which have the above beneficial effects.

Embodiments of the present invention provide an information mining method and apparatus. The method comprises the following steps of: mining each query statement of each specific category from a search log; giving the particular class of seed entities; generating an expression template corresponding to each query statement of the specific category according to the seed entity of the specific category and each query statement; according to various query sentences and corresponding expression templates, extracting high-frequency query sentences and high-frequency expression templates from the search log; By using the search log of the user as the data source, the obtained high-frequency expression of high-frequency sentences are rich and can cover all kinds of expression habits of users, which can include the content that cannot be covered by artificial enriched templates such as colloquial expression.

The invention discloses an unsupervised knowledge graph entity alignment method and equipment. The method comprises the following steps: acquiring data of two knowledge graphs; generating a text distance matrix by using the auxiliary information of the entities in the knowledge graph; generating an initial alignment result as a seed entity pair set by using threshold bidirectional nearest neighbor search; on the basis that the seed entity pair set is marked data, learning a structure distance matrix of the entity by using a graph convolutional network; fusing the text distance matrix and the structure distance matrix of the entity to obtain a fused distance matrix; performing progressive learning to obtain a newly generated alignment entity pair, merging the newly generated alignment entity pair into a seed entity pair set, and using the merged seed entity pair set to iteratively update structure embedding; and repeating the first three steps until the number of the newly generated alignment entity pairs is lower than a preset value, and obtaining a final entity alignment result.

An example system can comprise a closed group of member financial institution servers. The system can comprise a data feed manager configured to communicate amongst the closed group of member financial institution servers over a network. The system can comprise a data aggregator configured to aggregate data related to transactions conducted by the closed group of member financial institution servers. The aggregated data can comprise an aggregated interest from the transactions. The system can comprise a distribution manager configured to determine one or more distribution levels for the member financial institutions and one or more seeding entities based on the aggregated data.

The invention discloses a Chinese medicine preparation, especially a preparing method for an auxiliary medicine in treatment of leucopenia diseases. The main technology of the invention comprises: taking the tremella seed entity; making tremella polysaccharide dried paster by submerged fermentating, concentrating, ethanol eluting, separating and drying; smashing the dried paster; performing maturation and sterilization to obtain the powder of the invention, in which the powder can be put into capsules for the convenience in taking. The medicine in the invention achieves immunization stimulation function, can improve specific or non specific immunological reaction, and is used mainly for treating leucopenia caused by actinotherapy, chemotherapy or other reasons of tumor patient in clinic.