Cross-scene project recommendation method and device, electronic equipment and storage medium
A project recommendation and project technology, applied in the computer field, can solve the problems of little improvement in user acquisition efficiency and no response to the real needs of users.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0027] A cross-scenario item recommendation method disclosed in the embodiment of the present application, such as figure 1 As shown, the method includes: Step 110 to Step 150.
[0028] Step 110, according to the user's historical behavior data, determine several first item sequences corresponding to the preset user behavior.
[0029] The items described in some embodiments of the application can be catering products, hotels, tickets, beauty items, entertainment items, etc. of the e-commerce platform.
[0030] The preset user behavior described in the embodiment of the present application includes: any one or more behaviors of the user such as purchasing, clicking, browsing, and bookmarking. For example, after user 1 clicks item A, then clicks item B, and then user 1 purchases item C, the platform will record a piece of user historical behavior data, which includes the correspondence between user 1's click and purchase behavior The first item sequence composed of item A, ite...
Embodiment 2
[0072] A cross-scenario item recommendation device disclosed in this embodiment, such as Figure 4 As shown, the device includes:
[0073] The first item sequence determination module 410 is configured to determine several first item sequences corresponding to preset user behaviors according to user historical behavior data;
[0074] The second item sequence determination module 420 is configured to split and reorganize each of the first item sequences, and determine several second item sequences, so that two adjacent items in each of the second item sequences Match different scenarios;
[0075] The item word vector model training module 430 is used for training the item word vector model based on the plurality of second item sequences;
[0076] The item word vector determination module 440 is used to determine the first word vector of the target item and the second word vector of the item to be recommended that matches different scenarios with the target item through the it...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


