Click model generation method and device
A model generation and model technology, applied in the field of search engines, can solve the problem that the search results cannot accurately predict the user's click behavior, and achieve the effect of accurate click behavior
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0020] According to an embodiment of the present invention, a method for generating a click model is provided, such as figure 1 As shown, the method includes:
[0021] Step S102 , respectively acquiring historical click information of users in multiple pre-divided geographical areas, and obtaining multiple sets of historical click information corresponding to the multiple geographical areas.
[0022] The user's historical click information is the data information generated by the user through the click behavior. Wherein, the click behavior of the user includes but is not limited to: what document the user clicks on, the time when the click occurs, and the display position of the document at that time. The above-mentioned behaviors can be reflected in the form of data, for example, there is data information reflecting the characteristics of the above-mentioned behaviors in the user's click log. The user's historical click information may be obtained from the user's click log....
Embodiment 2
[0085] According to an embodiment of the present invention, a click model generation device for implementing the above click model generation method is also provided, such as Figure 6 As shown, the device includes: a first acquisition unit 10 , a calculation unit 20 , a clustering unit 30 and a generation unit 40 .
[0086] The first acquiring unit 10 is configured to respectively acquire historical click information of users in multiple pre-divided geographical areas, and obtain multiple sets of historical click information corresponding to the multiple geographical areas.
[0087] The user's historical click information is the data information generated by the user through the click behavior. Wherein, the click behavior of the user includes but is not limited to: what document the user clicks on, the time when the click occurs, and the display position of the document at that time. The above-mentioned behaviors can be reflected in the form of data, for example, there is da...
Embodiment 3
[0112] According to an embodiment of the present invention, a server for implementing the above click model generation method is also provided, such as Figure 7 As shown, the server includes: a processor 702 , a memory 704 and a network interface 706 . The device for processing messages in this embodiment of the present invention may be implemented by a server.
[0113] Wherein the processor 702 can be used to perform the following steps:
[0114] Step S31 , respectively acquiring historical click information of users in multiple pre-divided geographical areas, and obtaining multiple sets of historical click information corresponding to the multiple geographical areas.
[0115] Step S33 , calculating the overlap rate of historical click information among multiple historical click information sets, and the overlap rate is used to represent the proportion of multiple historical click information sets having the same click behavior.
[0116] Step S35, using the overlap rate of...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


