Aiming at the problem that the key entity information in the police field is difficult to recognize， a neural network model based on BERT （Bidirectional Encoder Representations from Transformers）， namely BERT-BiLSTM-Attention-CRF， was proposed to recognize and extract related named entities， in the meantime， the corresponding entity annotation specifications were designed for different cases. In the model ，the BERT pre-trained word vectors were used to replace the word vectors trained by the traditional methods such as Skip-gram and Continuous Bag of Words （CBOW）， improving the representation ability of the word vector and solving the problem of word boundary division in Chinese corpus trained by the character vectors. And the attention mechanism was used to improve the architecture of classical Named Entity Recognition （NER） model BiLSTM-CRF. BERT-BiLSTM-Attention-CRF model has an accuracy of 91% on the test set， which is 7% higher than that of CRF++ Baseline， and 4% higher than that of BiLSTM-CRF model. The F1 values of the entities are all higher than 0.87.

The conformity and sharing management of information resource is one of the difficult problems in present E-government construction. This paper applied Dee Hocks chaordic organization idea and method to make up a kind of resource sharing information management model for the sake of providing a practice way to the conformity and sharing of E-government information resource. By means of analyzing the principle of chaordic organization and the cooperated relation among the chaordic organization members, the authors constructed the management model for information connection and resource shareing. This common model was applied to the system design in the E-government information resource conformity and sharing, and further a common information resource conformity and sharing management model was created with which we have also constructed the system frame and analyzed the problems of information resource conformity and sharing such as the administration examine and approve system at government department and the management system for social trustworthiness. So by linking theory with practice this paper has established a kind of soft system frame model and technology method for E-government information resource conformity and sharing management with the feature of chaordic organization.