Method and device for feedback answer
An answer, the technology of the best answer, applied in the computer field, can solve problems such as low matching possibility, low accuracy rate, and low frequency of words
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0024] The embodiment of the present invention provides a method for feeding back answers, such as figure 1 As shown, the processing flow of the method may include the following steps:
[0025] Step 101, according to the corresponding relationship between the question, the best answer and other answers stored in the training sample database, based on the training condition that the semantic proximity between the question and the corresponding best answer is greater than the semantic proximity between the question and the corresponding other answers, to The semantic extraction parameters in the preset semantic extraction formula are trained to obtain the training values of the semantic extraction parameters.
[0026] Step 102, when an answer request carrying a target question is received, according to the target question, each answer in the answer query library, the semantic extraction formula, and the training value of the semantic extraction parameters, respectively determi...
Embodiment 2
[0030] The embodiment of the present invention provides a method for feeding back answers. The execution subject of the method may be a server, and the server may be a community question-and-answer website or an application server, and the server may be provided with a processor, a memory, a transceiver, and the processor It can be used for the training of semantic extraction parameters and the processing of feedback answers to questions. The memory can be used to store the data required and generated during the following processing. The transceiver can be used to receive and send data. The following will combine specific implementation methods, figure 1 The processing flow shown is described in detail, and the content can be as follows:
[0031] Step 101, according to the corresponding relationship between the question, the best answer and other answers stored in the training sample database, based on the training condition that the semantic proximity between the question and...
Embodiment 3
[0083] Based on the same technical idea, the embodiment of the present invention also provides a device for feeding back answers, such as image 3 As shown, the device includes:
[0084] The training module 310 is used for training based on the correspondence between the question, the best answer and other answers stored in the training sample library, based on the semantic proximity between the question and the corresponding best answer is greater than the semantic proximity between the question and other corresponding answers condition, training the semantic extraction parameters in the preset semantic extraction formula to obtain the training value of the semantic extraction parameters;
[0085] The determining module 320 is configured to, when receiving an answer request carrying a target question, determine respectively according to the target question, each answer in the answer query database, the semantic extraction formula, and the training value of the semantic extrac...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


