Deep retrieval matching classification method and device and terminal equipment
A classification method and in-depth technology, applied in the field of data processing, can solve problems affecting user experience, poor correlation of returned results, and low matching accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0044] The following describes a deep search matching classification method provided by Embodiment 1 of the present application, please refer to the attached figure 1 , the deep search matching classification method in Embodiment 1 of the present application includes:
[0045]Step S101. Obtain the first question input by the user and the first category of the first question, and perform word segmentation on the first question, and then form the input question with each preset second question corresponding to the first category Group;
[0046] Questions consulted by users can be classified into multi-level categories. For example, three levels of classification can be set up. The first category is the product category, the second category is the direction of consultation (such as basic knowledge, app questions, etc.), and the third category is the refinement of the consultation direction (For example, app problems can be subdivided into App operation, construction process and ...
Embodiment 2
[0132] Embodiment 2 of the present application provides a device for in-depth search and matching classification. For the convenience of description, only the parts related to the present application are shown, such as Figure 8 As shown, the deep search matching classification device includes,
[0133] The input processing module 201 is configured to obtain the first question input by the user and the first category of the first question, and perform word segmentation processing on the first question to obtain the preset second questions respectively corresponding to the first category. Question composition Input question groups;
[0134] The word vector module 202 is used to convert the words of the first question and the second question in the input question group into word vectors through a preset word vector model;
[0135] A dot product calculation module 203, configured to dot-multiply each word vector of the first question with the word vector matrix of the second que...
Embodiment 3
[0156] Figure 9 It is a schematic diagram of a terminal device provided in Embodiment 3 of the present application. like Figure 9 As shown, the terminal device 3 in this embodiment includes: a processor 30 , a memory 31 , and a computer program 32 stored in the memory 31 and operable on the processor 30 . When the processor 30 executes the computer program 32, it realizes the steps in the embodiment of the above-mentioned deep search matching classification method, for example figure 1 Steps S101 to S105 are shown. Alternatively, when the processor 30 executes the computer program 32, it realizes the functions of the modules / units in the above-mentioned device embodiments, for example Figure 8 The functions of modules 201 to 205 are shown.
[0157] Exemplarily, the computer program 32 can be divided into one or more modules / units, and the one or more modules / units are stored in the memory 31 and executed by the processor 30 to complete this application. The one or mor...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More