Model generation method and device, entity identification method and device and electronic equipment
A technology of entity recognition and model generation, applied in the field of entity recognition, which can solve the problems of low accuracy of entity recognition and less entity information stored in vectors
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
no. 1 example
[0043] Such as figure 1 As shown, the embodiment of the present application provides a method for generating a model, which specifically includes the following steps:
[0044] Step S100: Generate feature image information according to the target sentence to be trained, the feature image information includes a feature image composed of a plurality of regional blocks and the category label of the target sentence, the target sentence includes a plurality of characters, each character corresponds to A region tile.
[0045] Step S102: using a preset neural network model to extract feature vectors of feature images.
[0046] Step S104: Calculate the corresponding training loss according to the feature vector and the corresponding category label.
[0047] Step S106: Iteratively updating the neural network model according to the training loss to obtain a trained entity recognition model.
[0048] In step S100, the target sentence to be trained is the entity recognition sentence to ...
no. 2 example
[0083] This application provides an entity recognition method, such as Figure 11 As shown, the method specifically includes the following steps:
[0084] Step S200: Generate a feature image according to the entity sentence to be recognized, the feature image information includes a feature image composed of a plurality of region blocks, the entity sentence to be recognized includes a plurality of characters, and each character corresponds to a region block.
[0085] Step S202: Input the feature image into an entity recognition model, where the entity recognition model is an entity recognition model generated in any optional implementation manner in the first embodiment.
[0086] Step S204: Obtain the predicted label of the entity sentence to be recognized output by the entity recognition model.
[0087] The method of generating the feature image in step S200 of the above steps according to the entity sentence of the model to be recognized is consistent with the method of step...
no. 3 example
[0091] Figure 12 A schematic structural block diagram of the model generation device provided by the present application is shown, and it should be understood that the device is different from the above-mentioned Figure 1 to Figure 10 The method embodiment in the corresponding method can execute the steps involved in the method performed by the server in the first embodiment. The specific functions of the device can refer to the above description. To avoid repetition, the detailed description is omitted here appropriately. The device includes at least one software function module that can be stored in a memory in the form of software or firmware (firmware) or solidified in an operating system (operating system, OS) of the device. Specifically, the device includes: a generating module 300, configured to generate feature image information according to the target sentence to be trained, the feature image information including a feature image composed of a plurality of area bloc...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More