Got it, let me try it, thanks Pat & Vag.


刘尹伟 David
技术总监 Technology Head
电话 / Tel: 13651876010
电邮 / Email: [email protected]
上海驹旗网络科技有限公司 Shanghai Juqi Network Technology Co., Ltd.

On 10/26/2017 12:02Vaghawan Ojha<[email protected]> wrote:
Hi, Yes as Pat put it clearly as he always does, recommender doesn't do that, if you really need that maybe you wanna map the events data of the event server with the user_id and fetch their properties/profile. 

Thanks
Vaghawan

On Wed, Oct 25, 2017 at 9:28 AM, liuyinwei <[email protected]> wrote:
Thanks Vaghawan. We tried UR but it doesn't return recommended User Label/Properties, instead it only return recommended items. 
Am I miss anything here?

Here is the UR query we use to get user data: query: { "user": "U 2" ,"num":4}

Here is the UR response, however, it doesn't have properties we want, ideally, we want it return user's properites, e.g. 70s
{
    "itemScores": [
        {
            "item": "Iphone 4",
            "score": 0.11071484535932541
        },
        {
            "item": "Ipad-retina",
            "score": 0.011783885769546032
        },
        {
            "item": "Surface",
            "score": 0
        }
    ]
}

David

On 10/23/2017 19:37Vaghawan Ojha<[email protected]> wrote:
Hi, you could use the labels as properties, templates like UR supports multiple properties, you can set the properties for that user. 

https://predictionio.incubator.apache.org/datacollection/eventapi/ you can see the uses of properties in the events here. 

Thanks

On Mon, Oct 23, 2017 at 4:32 PM, liuyinwei <[email protected]> wrote:
Hi there,

 Could someone know which PIO template can do customer label/profile inference according to the product label?

 We want to use PIO to infer the user profile and user labels according to the products they viewed or bought,  our customers could listen and buy some songs in our website, and then we can know the preference of customer. 

 here is one example:  one Customer A listened song:  
  * Numb -- (labels: linkin park, Rock , Pop ), 
  * New Divided -- (labels: linkin park, Rock, Pop ), 
  *  Hotel California -- (lables: The Eagles, Rock , 70's)

Then, we know Customer A should have user label (Rock) in its user profile.

Is there a PIO Template which can do User Lable Inference?

David




Reply via email to