Text generation method, device, device and storage medium
A text and sample technology, applied in the field of information processing, can solve the problems of extracting key information, unclear and fixed text subject, and achieve the effect of improving communication efficiency, improving applicability and flexibility, and avoiding fixed patterns.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0030] figure 1 It is a flowchart of a text generation method provided by Embodiment 1 of the present invention. This embodiment is applicable to the case of converting structured data into text, and the method can be executed by a text generation device. The method specifically includes the following steps:
[0031] S110. Using each entity in the knowledge map of the target domain as an attribute, determine the current structured data in the target domain.
[0032] In a specific embodiment of the present invention, structured data may refer to data with fixed field lengths and stable items collected and stored according to preset rules, or data without rules, such as variable field lengths and / or variable items. stable data. And each entity or each project may include multiple data contents. When expressing the specific content of each entity or each project from different angles, the multiple data contents of each entity or each project are selective. Furthermore, entitie...
Embodiment 2
[0045] On the basis of the first embodiment above, this embodiment provides a preferred implementation of the text generation method, which can filter and sort structured data and generate text based on a deep learning model. figure 2 A flow chart of a text generation method provided by Embodiment 2 of the present invention, such as figure 2 As shown, the method includes the following specific steps:
[0046] S210. Using each entity in the knowledge map of the target domain as an attribute, determine the current structured data in the target domain.
[0047] In the specific embodiment of the present invention, since the attribute items of the structured data to be converted are unstable, and the information in the structured data is redundant or confusing, each entity in the knowledge map of the target field is used as an attribute, and according to the knowledge map Guidance, from which to determine the data content corresponding to each attribute, so as to determine the c...
Embodiment 3
[0064] Figure 7 It is a schematic structural diagram of a text generation device provided by Embodiment 3 of the present invention. This embodiment is applicable to the case of converting structured data into text, and the device can realize the text generation method described in any embodiment of the present invention. Specifically, the device includes:
[0065] The structured data determination module 710 is used to determine the current structured data in the target domain by using each entity in the knowledge map of the target domain as an attribute;
[0066] A data screening and sorting module 720, configured to select each attribute target data from the current structured data, and sort the selected attribute target data;
[0067] The text generation module 730 is configured to generate the current broadcast text of the target field according to the sorting results of the target data of each attribute.
[0068]Optionally, the data filtering and sorting module 720 is ...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


