Method and device for obtaining recommendation information and computer readable storage medium
A technology for recommending information and computer programs, applied in computing, digital data information retrieval, special data processing applications, etc., and can solve problems such as insufficient comprehensive and accurate recommended information.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0057] An embodiment of the present invention provides a method for obtaining recommendation information, such as figure 2 As shown, the method includes:
[0058] S201: Obtain the historical operation data of N users on the terminal, and obtain the feature model data of each of the N users, the feature model data of each of the N users includes: the bag of words of the N users model, the similarity between the bag-of-words model of each user among the N users and the bag-of-words model of other users among the N users; N is an integer greater than 1.
[0059] In actual implementation, the cloud server 12 communicates with the terminal 10 in real time to obtain historical operation data of N users on the terminal interaction page. The terminal interaction page can be some application programs displaying home appliance information, for example, including at least one home appliance An application store for product information; the acquired historical operation data may include...
Embodiment 2
[0072] In order to better reflect the purpose of the present invention, further illustrations are given on the basis of the above-mentioned embodiments.
[0073] An embodiment of the present invention provides a method for obtaining recommendation information, such as image 3 As shown, the method includes:
[0074] S301: When the preset recommendation information update condition is satisfied, acquire historical operation data of N users on the terminal, and obtain feature model data of each of the N users; N is an integer greater than 1.
[0075] In actual implementation, the recommendation information update condition can be preset, and the recommendation information update condition includes at least one of the following: the new operation data of N users for the terminal is acquired; the time from the current moment to the last update moment of the recommendation information The interval is greater than or equal to a preset time threshold.
[0076] Optionally, the recom...
Embodiment 3
[0102] In order to better reflect the purpose of the present invention, further illustrations are given on the basis of the above-mentioned embodiments.
[0103] An embodiment of the present invention provides a method for obtaining recommendation information, the method including:
[0104] Step A1: When the preset recommendation information update condition is satisfied, obtain the historical operation data of N users on the terminal, and obtain the feature model data of each of the N users; N is an integer greater than 1.
[0105] In actual implementation, based on the text similarity calculation algorithm, the acquired historical operation data of N users can be processed to obtain the feature model data of each of the N users, such as Figure 4 As shown, the specific steps include:
[0106] S401: Read the historical operation data of N users, and obtain the user ID of each user in the N users.
[0107] In actual implementation, the historical operation data of N users st...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


