An information retrieval method and device thereof
An information retrieval and information library technology, applied in the field of information processing, can solve problems such as the inability to accurately describe the advertisement information of the advertiser, the inability to accurately describe the characteristics of the advertisement, and the inability to distinguish keywords in detail.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0063] figure 2 is the flow chart of the information retrieval method described in this embodiment, as figure 2 As shown, the information retrieval method described in this embodiment includes:
[0064] Step S201, segment each information file in the information base to obtain strategic words, and score each strategic word to obtain the weight of each strategic word in each information file;
[0065] Segmentation is a basic subject in the field of information processing such as information extraction and information retrieval. Current Chinese word segmentation algorithms include rule-based word segmentation methods, understanding-based word segmentation methods, and statistical-based word segmentation methods. The present invention specifically selects which method to perform word segmentation based on Specific application aspects of the invention will vary.
[0066] Taking the application to the advertising push business as an example, a word segmentation method based on ...
Embodiment 2
[0114] Figure 5 is a structural block diagram of the information retrieval device described in this embodiment, as Figure 5 As shown, the information retrieval device described in this embodiment is located at the server end, and includes an inverted index table creation unit 501 , a screening unit 502 , a scoring unit 503 , a sorting unit 504 and a file pushing unit 505 .
[0115] Each module is introduced as follows:
[0116] The inverted index table creation unit 501 is used to pre-segment each information file in the information base to obtain strategic words, and obtain the weight of each strategic word in each information file according to the preset scoring standard. Internally create an inverted index table for each strategy word, and record the weight, occurrence times and occurrence position of each strategy word in each information file in the inverted index table.
[0117] Segmentation is a basic subject in the field of information processing such as informatio...
Embodiment 3
[0149] This embodiment proposes an information retrieval system. The information retrieval system described in this embodiment includes a client and a server, wherein the server is the information retrieval device described in Embodiment 2. For specific implementation methods, refer to Embodiment 2; Wherein the client includes a user feature word extraction module and a feature word weight calculation module.
[0150] The user feature word extraction module, when receiving a user retrieval request, is used to extract the feature words in the retrieval request, and sends the feature words to the scoring and sorting module of the server;
[0151] The scheme for extracting feature words is as follows: when receiving a search request from a user, perform word segmentation on the request information, and extract feature words in the search request.
[0152] The feature word weight calculation module is connected with the user feature word extraction module, receives the feature wor...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 