CN113704627A - Session recommendation method based on time interval graph - Google Patents

Session recommendation method based on time interval graph Download PDF

Info

Publication number
CN113704627A
CN113704627A CN202111036181.XA CN202111036181A CN113704627A CN 113704627 A CN113704627 A CN 113704627A CN 202111036181 A CN202111036181 A CN 202111036181A CN 113704627 A CN113704627 A CN 113704627A
Authority
CN
China
Prior art keywords
graph
item
time interval
user
vector
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202111036181.XA
Other languages
Chinese (zh)
Other versions
CN113704627B (en
Inventor
顾盼
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhejiang Zhiduo Network Technology Co ltd
Original Assignee
China Jiliang University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by China Jiliang University filed Critical China Jiliang University
Priority to CN202111036181.XA priority Critical patent/CN113704627B/en
Publication of CN113704627A publication Critical patent/CN113704627A/en
Application granted granted Critical
Publication of CN113704627B publication Critical patent/CN113704627B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9536—Search customisation based on social or collaborative filtering
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/01—Social networking

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Databases & Information Systems (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Computational Linguistics (AREA)
  • Business, Economics & Management (AREA)
  • Evolutionary Computation (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Molecular Biology (AREA)
  • Economics (AREA)
  • Human Resources & Organizations (AREA)
  • Marketing (AREA)
  • Primary Health Care (AREA)
  • Strategic Management (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The invention discloses a conversation recommendation method based on a time interval diagram. The method models the user interests given the current session and recommends the items that are most likely to be of interest to the current user in the next step. Mainly comprises four parts: the first part is to construct a conversation graph with time interval attribute according to the item sequence in the current conversation of the user; the second part is to use the neural network of the time interval graph to update the object vector representation; the third part is to obtain the user interest vector representation according to the item sequence in the current session of the user; and finally, recommending the item according to the user interest representation.

Description

Session recommendation method based on time interval graph
Technical Field
The invention belongs to the technical field of internet services, and particularly relates to a session recommendation method based on a time interval diagram.
Background
A Session (Session) is an interactive activity of a user over a period of time, and a Session-based recommendation is a recommendation of an item next clicked by the user based on the current Session. The sequence of items within a session is ordered and it is necessary to model the sequence of items. For example, buying green plants may result in the need to buy pots. Traditional conversational recommendation systems employ recurrent neural networks to model user interests, but recurrent neural networks ignore the more complex context of items in a conversation. The last clicked item and the next clicked item of an item in the session are called the context (context) of the item. In the E-commerce platform, in the same session, a user can perform repeated click browsing on the same item. The same article has a plurality of contexts, such as modeling the conversation only through a recurrent neural network, the plurality of contexts of one article are not connected, and the conversation needs to be constructed into a conversation graph when the connection between the contexts is modeled. The conversation graph can capture rich item transfer relationships in the conversation.
It is not enough to consider the sequence of the items in the session, and the different time intervals between the items in the session will result in different recommendation results. Such as: the impact of the same behavior occurring two hours ago and half an hour ago on the current must be different. Thus, the time interval between item interactions is taken into account when constructing the session graph. Firstly, the time interval is normalized by adopting a minimum maximization normalization mode, and then the time interval is discretized to learn the influence of the time interval on the user interest representation. The method comprises the steps of firstly constructing a session graph with time interval attributes based on a session, and updating item vector representations based on the session graph; then, modeling a session by using a gate control recurrent neural network (GRU) to obtain a user interest vector representation; and finally recommending the next item which is possibly interested by the user according to the user interest representation.
Disclosure of Invention
The technical problem to be solved by the invention is to model the user interest given the current session and recommend the most likely items of interest to the current user in the next step. To capture the rich item transfer relationships in a session, the current session is constructed as a session graph. And when constructing the conversation graph, the time interval between the article interactions is taken into account to learn the influence of the time interval on the user interest modeling.
A conversation recommendation method based on a time interval graph comprises the following steps:
and constructing a conversation graph with a time interval attribute according to the item sequence in the current conversation of the user. Given a session s ═ v1,v2，…,v|s|}, any item vjIs a node of the session graph T, (v)j-1，vj) Representing a user clicking on an item v for a directed edge of the graph network Tj-1Later pointHit an article vj. And the edge attribute of the graph is click item vj-1And click on an item vjThe time interval in between.
The item vector characterization is updated using a time interval graph neural network. The edge attribute time interval in the conversation graph is normalized by adopting a minimum maximization normalization mode, and then the time interval is discretized. When transmitting article node information in a session graph, the node information and the side information are connected into a whole for transmission, and the specific formula is as follows:
Figure BDA0003247036340000011
Figure BDA0003247036340000012
Figure BDA0003247036340000013
wherein, tjRepresenting click items vjThe time of occurrence of the reaction is,
Figure BDA0003247036340000014
and
Figure BDA0003247036340000015
respectively representing the maximum and minimum of the time interval in the session, ti→jRepresenting the time interval after the minimum maximum normalization. Function bucketid(ti→jDenotes the time interval t {. The) }i→jSubscripts in set parameters, e.g. ti→j0.15, then
Figure BDA0003247036340000016
Meaning 0.15 falls within interval 2 [0.1, 0.2). emb (t)i→j) Represents ti→jVector characterization of (c), emb (v)j) Representing an article viThe characterization of the vector is carried out,
Figure BDA0003247036340000017
representing the concatenation of vectors.
Then, the object vector representation is updated by adopting a two-layer graph network, and finally, an object v is obtainedjThe vector of (2) characterizes xjUpdating the results for the graph network, i.e.
Figure BDA0003247036340000018
The concrete formula is as follows:
Figure BDA0003247036340000019
Figure BDA00032470363400000110
wherein, WpoolAnd WhIs the transition matrix, b is the vector, σ is the sigmoid function, max represents the max operation at the element level,
Figure BDA00032470363400000111
representing the concatenation of vectors. k represents the search depth in the graph network T, the maximum value of k being the search depth L,
Figure BDA00032470363400000112
representative node vjVector characterization at layer k, B (j) is item v in conversation graph TjIs selected.
Figure BDA0003247036340000021
Representing an item node xjV of a neighbor nodekThe information that is transmitted to the user,
Figure BDA0003247036340000022
fuse article nodes vjAll neighbor node information.
Figure BDA0003247036340000023
Fuse the article vjVector of the previous layerCharacterizing information and an article vjAnd (4) neighbor node information.
And obtaining the user interest vector representation according to the item sequence in the current session of the user. And characterizing the session by adopting a gate control recurrent neural network (GRU) to obtain an interest characterization. Namely, the current session is used as the input of the gate control recurrent neural network (GRU), and the output of the gate control recurrent neural network (GRU) is obtained as the interest p of the useru：
zi＝σ(Wxz·xi+Whz·hi-1)
ri＝σ(Wxr·xi+Whr·hi-1)
Figure BDA0003247036340000024
Figure BDA0003247036340000025
Wherein r isiIs a reset gate, ziTo update the gates (update gate), these two gating vectors determine which information can be used as the output of the gated loop unit.
Figure BDA0003247036340000026
Is the current memory content. x is the number ofiIs the node input of the current layer, i.e. the item viIs used for vector characterization. Wxa、Wha、WxrAnd WhrRespectively, control the update gate ziAnd a reset gate riThe parameter (c) of (c). WxhAnd WhhIs to control the pre-memory content
Figure BDA0003247036340000027
The parameter (c) of (c). As is the element-level matrix multiplication, σ is the sigmoid function. The output of the last hidden layer of the gated recurrent neural network (GRU) is the user interest pu。
Recommending the item according to the user interest characterization. Articles are put invjVector v ofjMultiplying the representation by the final vector of the user, and then calculating the item v by applying a softmax functionjThe fraction of (c):
Figure BDA0003247036340000028
wherein p isuAn interest vector representing the user is generated by the user,
Figure BDA0003247036340000029
representative article vjThe possibility of becoming the next interactive item. At the same time according to
Figure BDA00032470363400000210
The log-likelihood function value of (a), calculating a loss function:
Figure BDA00032470363400000211
wherein, yjRepresents vjThe one-hot code of (a) is,
Figure BDA00032470363400000212
the function is optimized using a gradient descent method.
The invention has the following beneficial technical effects:
(1) the invention relates to a recommendation method based on a conversation graph, which constructs the conversation into the conversation graph and enables a model to learn more complex article transfer relations in the conversation.
(2) The invention relates to a recommendation method based on a time interval conversation graph, which can learn not only the complex article transfer relation in the conversation, but also the influence of the article time interval on the user interest.
Drawings
FIG. 1 is a flow chart of a session recommendation method based on a time interval graph according to the present invention;
FIG. 2 is a model framework diagram of a session recommendation method based on a time interval diagram according to the present invention.
Detailed Description
For further understanding of the present invention, the following describes a conversation recommendation method based on time interval diagram with reference to specific embodiments, but the present invention is not limited thereto, and those skilled in the art can make insubstantial modifications and adjustments under the core teaching of the present invention, and still fall within the scope of the present invention.
First, the variables and formulas used need to be given relevant definitions.
Definition 1. V: set of articles, and V ═ V1,v2,…,v|V|And V represents the number of items in the collection of items.
Definition 2. s: current session of current user, session is all interactive item set s ═ v in current time period1,v2,…,v|s|And | s | represents the number of items in the conversation.
Definition 3. S: set of sessions in a system, S ═ S1,s2,…,s|S|And | S | represents the number of sessions in the session set.
Definition 4. T: and constructing a conversation graph with a time interval attribute based on the item sequence interacted in the current conversation.
Definition 5, B (j) items v in conversation graph T with time interval attributejIs selected.
Definition 6.
Figure BDA0003247036340000031
Article vjThe initialized vector characterization of (1).
Definition 7.
Figure BDA0003247036340000032
Article vjThe updated vector representation of the session map.
Definition 8.
Figure BDA0003247036340000033
And (4) characterizing the user interest vector.
In conjunction with the above variable definitions, the final problem is defined as: given the current session, user interests are modeled and items are recommended that are most likely to be of interest to the current user in the next step, the items being a subset of the set V. To capture the rich item transfer relationships in a session, the current session is constructed as a session graph. And when constructing the conversation graph, the time interval between the article interactions is taken into account to learn the influence of the time interval on the user interest representation.
To this end, the present invention proposes a session recommendation method based on a time interval graph, as shown in fig. 2, a forward propagation (forward propagation) part of the method is mainly composed of four parts. The first part is to construct a conversation graph with time interval attribute according to the item sequence in the current conversation of the user; the second part is to use the neural network of the time interval graph to update the object vector representation; the third part is to obtain the user interest vector representation according to the item sequence in the current session of the user; and finally, recommending the item according to the user interest representation.
As shown in fig. 1, according to one embodiment of the present invention in an e-commerce, the method includes the steps of:
s100, constructing a conversation graph with time interval attributes according to the item sequence in the current conversation of the user. Given a session s ═ v1,v2,…,v|s|}, any item vjIs a node of the session graph T, (v)j-1,vj) Representing a user clicking on an item v for a directed edge of the graph network Tj-1After clicking on item vj. And the edge attribute of the graph is click item vj-1And click on an item vjThe time interval in between.
And S200, updating the item vector representation by using the time interval diagram neural network. The edge attribute time interval in the conversation graph is normalized by adopting a minimum maximization normalization mode, and then the time interval is discretized. When transmitting article node information in a session graph, the node information and the side information are connected into a whole for transmission, and the specific formula is as follows:
Figure BDA0003247036340000034
Figure BDA0003247036340000035
Figure BDA0003247036340000036
wherein, tjRepresenting click items vjThe time of occurrence of the reaction is,
Figure BDA0003247036340000037
and
Figure BDA0003247036340000038
respectively representing the maximum and minimum of the time interval in the session, ti→jRepresenting the time interval after the minimum maximum normalization. Function bucketid(ti→jDenotes the time interval t {. The) }i→jSubscripts in set parameters, e.g. ti→j0.15, then
Figure BDA0003247036340000039
Meaning 0.15 falls within interval 2 [0.1, 0.2). emb (t)i→j) Represents ti→jVector characterization of (c), emb (v)j) Representing an article viThe characterization of the vector is carried out,
Figure BDA00032470363400000310
representing the concatenation of vectors.
Then, the object vector representation is updated by adopting a two-layer graph network, and finally, an object v is obtainedjThe vector of (2) characterizes xjUpdating the results for the graph network, i.e.
Figure BDA00032470363400000311
The concrete formula is as follows:
Figure BDA00032470363400000312
Figure BDA00032470363400000313
wherein, WpoolAnd WhIs the transition matrix, b is the vector, σ is the sigmoid function, max represents the max operation at the element level,
Figure BDA00032470363400000314
representing the concatenation of vectors. k represents the search depth in the graph network T, the maximum value of k being the search depth L,
Figure BDA00032470363400000315
representative node vjVector characterization at layer k, B (j) is item v in conversation graph TjIs selected.
Figure BDA00032470363400000316
Representing an item node vjV of a neighbor nodekThe information that is transmitted to the user,
Figure BDA00032470363400000317
fuse article nodes vjAll neighbor node information.
Figure BDA00032470363400000318
Fuse the article vjVector characterization information and article v of the previous layerjAnd (4) neighbor node information. In the method, a two-layer graph network is adopted, so that the search depth L is 2.
And S300, obtaining the user interest vector representation according to the item sequence in the current session of the user. And characterizing the session by adopting a gate control recurrent neural network (GRU) to obtain an interest characterization. Namely, the current session is used as the input of the gate control recurrent neural network (GRU), and the output of the gate control recurrent neural network (GRU) is obtained as the interest p of the useru：
zi＝σ(Wxz·xi+Whz·hi-1)
ri＝σ(Wxr·xi+Whr·hi-1)
Figure BDA00032470363400000319
Figure BDA00032470363400000320
Wherein r isiIs a reset gate, ziTo update the gates (update gate), these two gating vectors determine which information can be used as the output of the gated loop unit.
Figure BDA00032470363400000321
Is the current memory content. x is the number ofiIs the node input of the current layer, i.e. the item viIs used for vector characterization. Wxa、Wna、WxrAnd WhrRespectively, control the update gate ziAnd a reset gate riThe parameter (c) of (c). WxhAnd WhhIs to control the pre-memory content
Figure BDA0003247036340000041
The parameter (c) of (c). As is the element-level matrix multiplication, σ is the sigmoid function. The output of the last hidden layer of the gated recurrent neural network (GRU) is the user interest pu。
And S400, recommending the item according to the user interest representation. Article vjVector v ofjMultiplying the representation by the final vector of the user, and then calculating the item v by applying a softmax functionjThe fraction of (c):
Figure BDA0003247036340000042
wherein p isuAn interest vector representing the user is generated by the user,
Figure BDA0003247036340000043
representative article vjBecome intoThe likelihood of the next interactive item. At the same time according to
Figure BDA0003247036340000044
The log-likelihood function value of (a), calculating a loss function:
Figure BDA0003247036340000045
wherein, yjRepresents vjThe one-hot code of (a) is,
Figure BDA0003247036340000046
the function is optimized using a gradient descent method.
The foregoing description of the embodiments is provided to facilitate understanding and application of the invention by those skilled in the art. It will be readily apparent to those skilled in the art that various modifications to the above-described embodiments may be made, and the generic principles defined herein may be applied to other embodiments without the use of inventive faculty. Therefore, the present invention is not limited to the above embodiments, and those skilled in the art should make improvements and modifications to the present invention based on the disclosure of the present invention within the protection scope of the present invention.

Claims (2)

1. A conversation recommendation method based on a time interval graph is characterized in that:
constructing a conversation graph with a time interval attribute according to an article sequence in the current conversation of a user; given a session s ═ v1，v2，…，v|s|}, any item vjIs a node of the session graph T, (v)j-1，vj) Representing a user clicking on an item v for a directed edge of the graph network Tj-1After clicking on item vj(ii) a And the edge attribute of the graph is click item vj-1And click on an item vjThe time interval in between;
updating the item vector representation using a time interval graph neural network; normalizing the edge attribute time interval in the conversation graph by adopting a minimum maximization normalization mode, and then discretizing the time interval; when transmitting article node information in a session graph, the node information and the side information are connected into a whole for transmission, and the specific formula is as follows:
Figure FDA0003247036330000011
Figure FDA0003247036330000012
Figure FDA0003247036330000013
wherein, tjRepresenting click items vjThe time of occurrence of the reaction is,
Figure FDA0003247036330000014
and
Figure FDA0003247036330000015
respectively representing the maximum and minimum of the time interval in the session, ti→jRepresenting the time interval after the minimum and maximum normalization; function bucketid(ti→jDenotes the time interval t {. The) }i→jSubscripts in the set parameters; emb (t)i→j) Represents ti→jVector characterization of (c), emb (v)j) Representing an article viThe characterization of the vector is carried out,
Figure FDA0003247036330000016
representing a concatenation of vectors;
then, the object vector representation is updated by adopting a two-layer graph network, and finally, an object v is obtainedjThe vector of (2) characterizes xjUpdating the results for the graph network, i.e.
Figure FDA0003247036330000017
In particular toThe formula is as follows:
Figure FDA0003247036330000018
Figure FDA0003247036330000019
wherein, WpoolAnd WhIs the transition matrix, b is the vector, σ is the sigmoid function, max represents the max operation at the element level,
Figure FDA00032470363300000110
representing a concatenation of vectors; k represents the search depth in the graph network T, the maximum value of k being the search depth L,
Figure FDA00032470363300000111
representative node vjVector characterization at layer k, B (j) is item v in conversation graph TjA neighbor set of (2);
Figure FDA00032470363300000112
representing an item node vjV of a neighbor nodekThe information that is transmitted to the user,
Figure FDA00032470363300000113
fuse article nodes vjAll neighbor node information;
Figure FDA00032470363300000114
fuse the article vjVector characterization information and article v of the previous layerjNeighbor node information;
obtaining a user interest vector representation according to an article sequence in a current session of a user; a gate control cyclic neural network is adopted to characterize the session to obtain an interest characterization; namely, the current conversation is used as the input of the gate control cyclic neural network to obtain the gate control cyclic neural networkOutput of the network as interest p of the useru；
Recommending the item according to the user interest representation; article vjVector v ofjMultiplying the representation by the final vector of the user, and then calculating the item v by applying a softmax functionjThe fraction of (c):
Figure FDA00032470363300000115
wherein p isuAn interest vector representing the user is generated by the user,
Figure FDA00032470363300000116
representative article vjThe possibility of becoming the next interactive item; at the same time according to
Figure FDA00032470363300000117
The log-likelihood function value of (a), calculating a loss function:
Figure FDA00032470363300000118
wherein, yjRepresents vjThe one-hot code of (a) is,
Figure FDA00032470363300000119
the function is optimized using a gradient descent method.
2. The conversation recommendation method based on the time interval graph as claimed in claim 1, wherein: the gate control cyclic neural network comprises the following components:
zi＝σ(Wxz·xi+Whz·hi-1)
ri＝σ(Wxr·xi+Whr·hi-1)
Figure FDA00032470363300000120
Figure FDA00032470363300000121
wherein r isiIs a reset gate (resetgate), ziTo update the gate (update gate), these two gating vectors determine which information can be used as the output of the gated loop unit;
Figure FDA00032470363300000122
is the current memory content; x is the number ofiIs the node input of the current layer, i.e. the item viThe vector characterization of (2); wxz、Whz、WxrAnd WhrRespectively, control the update gate ziAnd a reset gate riThe parameters of (1); wxhAnd WhhIs to control the pre-memory content
Figure FDA00032470363300000123
The parameters of (1); as a matrix multiplication at the element level, σ is a sigmoid function; the output of the last hidden layer of the gated recurrent neural network (GRU) is the user interest pu。
CN202111036181.XA 2021-09-06 2021-09-06 Session recommendation method based on time interval graph Active CN113704627B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111036181.XA CN113704627B (en) 2021-09-06 2021-09-06 Session recommendation method based on time interval graph

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111036181.XA CN113704627B (en) 2021-09-06 2021-09-06 Session recommendation method based on time interval graph

Publications (2)

Publication Number Publication Date
CN113704627A true CN113704627A (en) 2021-11-26
CN113704627B CN113704627B (en) 2022-05-17

Family

ID=78660218

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111036181.XA Active CN113704627B (en) 2021-09-06 2021-09-06 Session recommendation method based on time interval graph

Country Status (1)

Country Link
CN (1) CN113704627B (en)

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120036037A1 (en) * 2010-08-03 2012-02-09 Alibaba Group Holding Limited Product reccommendation system
US10210860B1 (en) * 2018-07-27 2019-02-19 Deepgram, Inc. Augmented generalized deep learning with special vocabulary
CN110008408A (en) * 2019-04-12 2019-07-12 山东大学 A kind of session recommended method, system, equipment and medium
CN111125537A (en) * 2019-12-31 2020-05-08 中国计量大学 Session recommendation method based on graph representation
CN111460331A (en) * 2020-04-07 2020-07-28 中国计量大学 Conversation recommendation method based on space-time diagram
US20200401661A1 (en) * 2019-06-19 2020-12-24 Microsoft Technology Licensing, Llc Session embeddings for summarizing activity
CN112765461A (en) * 2021-01-12 2021-05-07 中国计量大学 Session recommendation method based on multi-interest capsule network
CN112765493A (en) * 2021-01-04 2021-05-07 武汉大学 Method for obtaining time preference fusion sequence preference for point of interest recommendation
CN112819575A (en) * 2021-01-26 2021-05-18 中国计量大学 Session recommendation method considering repeated purchasing behavior
WO2021169361A1 (en) * 2020-09-18 2021-09-02 平安科技（深圳）有限公司 Method and apparatus for detecting time series data, and computer device and storage medium

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120036037A1 (en) * 2010-08-03 2012-02-09 Alibaba Group Holding Limited Product reccommendation system
US10210860B1 (en) * 2018-07-27 2019-02-19 Deepgram, Inc. Augmented generalized deep learning with special vocabulary
CN110008408A (en) * 2019-04-12 2019-07-12 山东大学 A kind of session recommended method, system, equipment and medium
US20200401661A1 (en) * 2019-06-19 2020-12-24 Microsoft Technology Licensing, Llc Session embeddings for summarizing activity
CN111125537A (en) * 2019-12-31 2020-05-08 中国计量大学 Session recommendation method based on graph representation
CN111460331A (en) * 2020-04-07 2020-07-28 中国计量大学 Conversation recommendation method based on space-time diagram
WO2021169361A1 (en) * 2020-09-18 2021-09-02 平安科技（深圳）有限公司 Method and apparatus for detecting time series data, and computer device and storage medium
CN112765493A (en) * 2021-01-04 2021-05-07 武汉大学 Method for obtaining time preference fusion sequence preference for point of interest recommendation
CN112765461A (en) * 2021-01-12 2021-05-07 中国计量大学 Session recommendation method based on multi-interest capsule network
CN112819575A (en) * 2021-01-26 2021-05-18 中国计量大学 Session recommendation method considering repeated purchasing behavior

Non-Patent Citations (6)

* Cited by examiner, † Cited by third party
Title
YUPU GUO等: "A Time-Aware Graph Neural Network for Session-Based Recommendation", 《IEEE ACCESS》 *
吴金盛: "基于知识图谱的会话型推荐系统的研究与实现", 《中国优秀硕士学位论文全文数据库 (信息科技辑)》 *
夏永生等: "基于时序和距离的门控循环单元兴趣点推荐算法", 《计算机工程》 *
孙鑫等: "基于图神经网络和时间注意力的会话序列推荐", 《计算机工程与设计》 *
岳新玉等: "基于会话信息的多粒度循环神经网络推荐模型", 《山西大学学报(自然科学版)》 *
袁涛等: "一种基于CW-RNN的多时间尺度序列建模推荐算法", 《中文信息学报》 *

Also Published As

Publication number Publication date
CN113704627B (en) 2022-05-17

Similar Documents

Publication Publication Date Title
CN110490717B (en) Commodity recommendation method and system based on user session and graph convolution neural network
CN111460331B (en) Conversation recommendation method based on space-time diagram
CN111125537B (en) Session recommendation method based on graph representation
CN110910218B (en) Multi-behavior migration recommendation method based on deep learning
CN111222054A (en) Session social contact recommendation method based on context neighbor relation modeling
CN111523047A (en) Multi-relation collaborative filtering algorithm based on graph neural network
CN110245285B (en) Personalized recommendation method based on heterogeneous information network
CN112528165A (en) Session social recommendation method based on dynamic routing graph network
CN115186097A (en) Knowledge graph and reinforcement learning based interactive recommendation method
CN113505924B (en) Information propagation prediction method and system based on cascading space-time characteristics
CN112685657A (en) Conversation social recommendation method based on multi-mode cross fusion graph network
CN112765461A (en) Session recommendation method based on multi-interest capsule network
CN110738314B (en) Click rate prediction method and device based on deep migration network
CN112256916B (en) Short video click rate prediction method based on graph capsule network
CN112559904B (en) Conversational social recommendation method based on door mechanism and multi-modal graph network
CN113704438B (en) Conversation recommendation method of abnormal picture based on layered attention mechanism
CN112819575B (en) Session recommendation method considering repeated purchasing behavior
CN114820139A (en) Multi-user recommendation system based on knowledge graph path reasoning
CN112256918A (en) Short video click rate prediction method based on multi-mode dynamic routing
CN113704627B (en) Session recommendation method based on time interval graph
CN116257691A (en) Recommendation method based on potential graph structure mining and user long-short-term interest fusion
CN114428912A (en) Session recommendation method based on capturing long-term and short-term interest heterogeneous hypergraph of user
CN113704439B (en) Conversation recommendation method based on multi-source information heteromorphic graph
CN116304289A (en) Information chain recommendation method and device for supply chain based on graphic neural network
CN113688974B (en) Mobile application recommendation method based on lightweight graph convolutional network

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
TR01 Transfer of patent right
TR01 Transfer of patent right

Effective date of registration: 20231016

Address after: Room 407-10, floor 4, building 2, Haichuang science and technology center, Cangqian street, Yuhang District, Hangzhou City, Zhejiang Province, 311100

Patentee after: Zhejiang Zhiduo Network Technology Co.,Ltd.

Address before: 310018, No. 258, source street, Xiasha Higher Education Park, Hangzhou, Zhejiang

Patentee before: China Jiliang University