US 2024/0177009 A1 · SEQUENCE RECOMMENDATION METHOD BASED ON EXTRACTING AND MODELING OF COMPLEX MULTI-MODE USER INTERESTS

Abstract

A sequence recommendation method based on extraction and modeling of complex multi-mode user interests is provided, including: obtaining long-term and short-term embedding sequences; obtaining updated long-term and short-term embedding sequences through the long-term and short-term embedding sequences; with embedding vectors of last items in the updated long-term and short-term embedding sequences as long-term and short-term dynamic interests of a user, obtaining long-term and short-term static interests of the user through weighted calculation; concatenating the long-term and short-term dynamic interests and the long-term and short-term static interests, and performing nonlinear change to obtain long-term and short-term evolutionary interests of the user; obtaining a dynamic interest, a static interest and an evolutionary interest of the user through element-wise summation; performing weighted summation to obtain a fused user interest; calculating a product of the fused interest with embedding of each item as a recommendation score of each item.

A sequence recommendation method based on extracting and modeling of complex multi-mode user interests, comprising:

Step 1, acquiring a historical item interaction sequence of a user, and obtaining a long-term embedding sequence Fl=(fl1, fl2, . . . , flm) and a short-term embedding sequence Fs=(fs1, fs2, . . . , fsn) through a self-learning item embedding matrix, where m>n;
Step 2, inputting the long-term embedding sequence and the short-term embedding sequence into two independent multi-head self-attention modules, respectively, to obtain an updated long-term embedding sequence and an updated short-term embedding sequence;
Step 3, with an embedding vector of a last item in the updated long-term embedding sequence as a long-term dynamic interest of the user, calculating attention weights of the updated long-term embedding sequence to the embedding vector of the last item, and performing weighted summation to obtain a long-term static interest of the user, and similarly, obtaining a short-term dynamic interest and a short-term static interest based on the updated short-term embedding sequence, wherein:
the long-term dynamic interest pld of the user is the embedding vector êlm of the last item in the updated long-term embedding sequence Êl=(êl1, êl2, . . . , êlm), that is, the long-term dynamic interest is pld=êlm, and the long-term static interest is defined as:
p
l
x
=
∑
i
=
1
m
α
i
⁢
ê
l
i
α
i
=
exp
⁡
(
ê
ι
m
T
⁢
Re
⁢
LU
⁡
(
W
l
⁢
ê
l
i
)
)
Σ
j
∈
{
1
,
2
,
…
,
m
}
⁢
exp
⁡
(
e
ˆ
l
m
T
⁢
Re
⁢
LU
⁡
(
W
l
⁢
ê
l
j
)
)
where Wl∈(o×d′)×(o×d′) is a parameter to be trained, ReLU is an activation function, and êlm the embedding vector of the last item;
with an embedding vector êsn of a last item in the updated short-term embedding sequence Ês=(ês1, ês2, . . . , êsn) as a short-term dynamic interest psd of the user, calculating attention weights of the updated short-term embedding sequence Ês to the embedding vector êsn of the last item, and performing weighted summation to obtain a short-term static interest psx of the user, specifically:
the short-term dynamic interest psd and the short-term static interest psx are obtained based on the short-term embedding sequence Ês:
p
s
d
=
ê
s
n
p
s
x
=
∑
i
=
1
n
β
i
⁢
ê
s
i
β
i
=
exp
⁡
(
ê
s
n
T
⁢
Re
⁢
LU
⁡
(
W
s
⁢
ê
s
i
)
)
Σ
j
∈
{
1
,
2
,
…
,
n
}
⁢
exp
⁡
(
e
ˆ
s
n
T
⁢
Re
⁢
LU
⁡
(
W
s
⁢
e
ˆ
s
j
)
)
where Ws∈(o×d′)×(o×d′) is a parameter to be trained;
Step 4, concatenating the long-term dynamic interest pld and the long-term static interest plx, and performing nonlinear change to obtain a long-term evolutionary interest ply of the user;
and similarly, obtaining a short-term evolutionary interest psy of the user based on the short-term dynamic interest psd and the short-term static interest psx;
Step 5, obtaining a dynamic interest, a static interest and an evolutionary interest of the user through element-wise summation, wherein:
the dynamic interest of the user is obtained through element-wise summation of the long-term dynamic interest and the short-term dynamic interest;
the static interest of the user is obtained through element-wise summation of the long-term static interest and the short-term static interest;
the evolutionary interest of the user is obtained through element-wise summation of the long-term evolutionary interest and the short-term evolutionary interest;
Step 6, calculating attention weights of the dynamic interest, the static interest and the evolutionary interest to the embedding vector of the last item, and performing weighted summation to obtain a fused user interest;
Step 7, calculating a product of the fused user interest with embedding of each item as a recommendation score of each item, and recommending top items with highest scores for the user.

169 more elements

Sequence recommendation method based on extracting and modeling of complex multi-mode user interests

Life of this patent

Sequence recommendation method based on extracting and modeling of complex multi-mode user interests

Life of this patent

Abstract

Claims6