A long text generation method, device and electronic equipment
A long text and text technology, applied in the field of devices and electronic equipment, long text generation methods, can solve the problems of high labor cost and low efficiency, and achieve the effects of improving efficiency, strong professionalism and logic, and saving manpower and cost
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0100] This embodiment provides a long text generation method, which can generate a long text reply content according to the question asked by the user. The generation of the long text can be realized through the first model and the second model. Correspondingly, the method can include the model A training process and a model using process, wherein the model training process specifically includes training of the first model and training of the second model.
[0101] 1. Model training process:
[0102] (1) Refer to figure 1 , the training process of the first model includes the following steps:
[0103] S11. Obtain a plurality of first question training texts for training the first model, and a first human answer text corresponding to the first question training text; the first human answer text includes at least one second sentence.
[0104] First of all, a large number of user questions and corresponding human answers can be obtained, and a question-manual answer text libra...
Embodiment 2
[0167] refer to Figure 4 , which shows a block diagram of a long text generation device 400, which may specifically include:
[0168] The first obtaining module 401 is used to obtain the target question text;
[0169] The first retrieval module 402 is configured to retrieve relevant texts of the target question text from a preset article database; the relevant texts include at least one candidate sentence;
[0170] The first determination module 403 is used to determine the importance parameter in the text of the candidate sentence in the relevant text;
[0171] The second determining module 404 is configured to determine associated text of the associated text from the preset article database;
[0172] The third determination module 405 is used to determine the inter-text importance parameter of the candidate sentence appearing in the associated text;
[0173] The first output module 406 is used to take the candidate sentence as input, and output the probability parameter ...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


