Order formation prediction method and device in customer service dialogue process and electronic equipment
A prediction method and single prediction technology, applied in the computer field, can solve problems such as unfavorable adjustment of dialogue behavior, the prediction rate of not having multiple sentences, and the impact of single results.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
As an example, as attached figure 1 As shown, in order to solve the above-mentioned technical problems, the present embodiment provides a method for predicting order formation in a customer service dialogue process, including the following steps:
Get historical conversation data;
Query the order log according to the historical dialogue data, and determine the buyer's order log corresponding to the historical dialogue data within the set time range;
According to the buyer's order log, classify and mark the historical dialogue data according to the result of the order within the set time range;
According to the historical dialogue data and the result of the classification and labeling, extract the characteristic parameters of the historical dialogue data, and process the characteristic parameters of the historical dialogue data;
According to the characteristic parameters of the processed historical dialogue data, a neural network model is established;
Using the historica...
Embodiment 2
[0045] Optionally, the neural network model establishment unit includes a first determination unit, a first encoding unit, a second encoding unit, a classification unit, a first calculation processing unit and a second determination unit:
[0046]Optionally, the acquiring unit further includes a filtering unit for filtering the historical dialogue data.
[0047] Optionally, the characteristic parameters include sentence information, role information and time information; the sentence information includes dialogue content; the character information includes the identity of the interlocutor; the time information includes the time data corresponding to the sentence information and the current dialogue and dialogue. The time interval between the previous sentence of the current conversation and the conversation data The time interval between adjacent conversations.
[0048] Optionally, the first feature extraction unit includes:
[0049] Optionally, the output unit, also includes...
Embodiment 3
Based on the same principle as the method shown in the embodiment of the present invention, the embodiment of the present invention further provides an electronic device, as shown in the accompanying Figure 4 As shown, the electronic device may include but is not limited to: a processor and a memory; a memory for storing a computer program; a processor for executing the method shown in any embodiment of the present invention by invoking the computer program.
[0051] In an optional embodiment, an electronic device is provided, Figure 4 The illustrated electronic device 40 includes a processor 410 and a memory 430 . The processor 410 is connected to the memory 430 , for example, through a bus 420 .
[0052] Optionally, the electronic device 40 may further include a transceiver 440, and the transceiver 440 may be used for data interaction between the electronic device and other electronic devices, such as data transmission and / or data reception. It should be noted that in pra...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


