CN108920527A - A kind of personalized recommendation method of knowledge based map - Google Patents
A kind of personalized recommendation method of knowledge based map Download PDFInfo
- Publication number
- CN108920527A CN108920527A CN201810580952.3A CN201810580952A CN108920527A CN 108920527 A CN108920527 A CN 108920527A CN 201810580952 A CN201810580952 A CN 201810580952A CN 108920527 A CN108920527 A CN 108920527A
- Authority
- CN
- China
- Prior art keywords
- user
- vector
- recommended project
- recommended
- attribute
- 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.)
- Pending
Links
Abstract
The present invention discloses a kind of personalized recommendation method of knowledge based map, the semantic association between arbitrary node is measured out using the linking relationship between conceptual entity in knowledge mapping, and the expression vector of network structure interior joint is obtained in conjunction with a kind of network representation learning method, by realizing the accurate recommendation between user and recommended project to the calculating of node similarity.The present invention is based on the project recommendations of knowledge mapping feature learning, to substance feature in efficiently Extracting Knowledge map, to preferably model user and recommended feature, make full use of various dimensions feature.
Description
Technical field
The present invention relates to knowledge mapping and machine learning techniques fields, and in particular to a kind of personalization of knowledge based map
Recommended method.
Background technique
With internet the relevant technologies high speed development, extensive data sharing bring is the exponential growth of data.So
And user wants to find their information of needs in the data of magnanimity and becomes to be increasingly difficult to.Therefore for a user, they
Need to be more in line with the result of personal preference.Many factors have pushed the flow of research of personalized recommendation technology jointly as a result,.
In traditional personalized recommendation research, according to the rule-based recommendation of user's history data, prediction is new for majority work
User interest.Wherein, proposed algorithm can be divided into following a few classes:Content-based recommendation, the recommendation based on correlation rule, based on association
With the recommendation of filtering.Conventional recommendation algorithm needs to carry out numerous calculation amounts, by obtain accurately user behavior characteristics come reality
Existing personalized recommendation.In practical applications, this kind of proposed algorithm, which exists, recommends the problems such as precision is not high, user satisfaction is low.
Summary of the invention
The present invention uses user and recommended feature for less present in existing personalized recommendation method, and pushes away
Recommend the characteristic dimension used it is less the problem of, a kind of personalized recommendation method of knowledge based map is provided.
To solve the above problems, the present invention is achieved by the following technical solutions:
A kind of personalized recommendation method of knowledge based map, specifically includes that steps are as follows:
Step 1 obtains user, recommended project, the association attributes of recommended project and user to pushing away from existing knowledge library
The favorable rating of project is recommended, a recommended project knowledge mapping is thus established;
Step 2, the recommended project knowledge mapping to building carry out corresponding attribute according to the attribute classification of recommended project
Figure extracts, and obtains the attribute subgraph of the recommended project knowledge mapping under each attribute;
Step 3 is carried out in each attribute subgraph of recommended project knowledge mapping by the random walk strategy with biasing
Migration generates a series of sequence node in migration paths;
Step 4, using the sequence node in migration path as the input based on neural network language model, pass through maximization
Objective function reaches training objective, obtains vector expression and user vector of the recommended project under every attribute;
Step 5, the vector by recommended project under every attribute indicates respectively and user vector merges, and obtains final
Recommended project vector sum end user's vector;
Step 6 calculates the cosine similarity of consequently recommended project vector sum end user's vector, obtains recommendation items
The correlation vector of mesh and user, and calculate user accordingly and score the prediction of recommended project, and then prediction scoring is arranged
The recommendation list of each user can be obtained in sequence.
In the recommended project knowledge mapping that step 1 is established, user and recommended project are pushed away as its conceptual entity node
The association attributes for recommending project describe the feature tag node of recommended project, favorable rating conduct of the user to recommended project as it
The semantic information that its user node embodies.
In above-mentioned steps 5, consequently recommended project vector v (attract) is:
Wherein,The vector for being recommended project under the i-th attribute indicates that m is the class number of attribute.
In above-mentioned steps 5, end user's vector v (user) is:
V (user)=vu
Wherein, vuIndicate the feature vector of user.
In above-mentioned steps 6, the Relevance scores vector of user and recommended project is:
Rel (attract, user)=sim (v (attract), v (user))
Wherein, sim is cosine similarity, and v (attract) is indicated in consequently recommended project vector, and v (user) indicates final
User vector.
A kind of above-mentioned personalized recommendation method of knowledge based map according to claim 1, characterized in that step
In 6, user is to prediction scoring Pre (attract, user) vector of recommended project:
Wherein, θ is scheduled scoring upper limit value, and Pre (attract, user) indicates the correlation of recommended project and user
Score vector, Max (Rel ((attract, user)) indicates the maximum value of all recommended projects and the Relevance scores of user,
Min (Rel (attract, user)) indicates the minimum value of recommended project and the Relevance scores of user.
Compared with prior art, the present invention measures out arbitrary node using the linking relationship between conceptual entity in knowledge mapping
Between semantic association, and the expression vector of network structure interior joint is obtained in conjunction with a kind of network representation learning method, by section
The calculating of point similarity is to realize the accurate recommendation between user and recommended project.The present invention is based on knowledge mapping feature learnings
Project recommendation, to preferably model user and recommended feature, is filled to substance feature in efficiently Extracting Knowledge map
Divide and utilizes various dimensions feature.
Detailed description of the invention
Fig. 1 is a kind of flow chart of the personalized recommendation method of knowledge based map.
Specific embodiment
It to make the objectives, technical solutions, and advantages of the present invention clearer, by restaurant of recommended project is below tool
Body example, and referring to attached drawing, the present invention is described in more detail.
Referring to Fig. 1, a kind of personalized recommendation method of knowledge based map specifically includes that steps are as follows:
Step 1, acquisition user, restaurant, the association attributes in restaurant and user like journey to restaurant from existing knowledge library
Degree, thus establishes cuisines field restaurant knowledge mapping.
So-called knowledge mapping is one there are many network graph structure of point and side composition, wherein user and restaurant, restaurant with
Correlativity between attribute is mapped to network edge, and the side in map, which represents, has connection between two connected nodes.Knowledge
Map is the data structure based on figure, is a kind of generic representation mode of knowledge mapping, the fundamental form of triple based on triple
Formula mainly includes (entity 1- relation-entity 2) and (entity-attribute-attribute value) etc..
Existing knowledge library includes the cuisines Vertical Websites such as public comment net, Meituan net.It will be grabbed from these websites
Restaurant and user as the conceptual entity node in the knowledge mapping of cuisines field restaurant, restaurant association attributes and user are to restaurant
Favorable rating respectively as described in the knowledge mapping of cuisines field restaurant restaurant feature tag node and user node embody
Semantic information.
Step 2 carries out corresponding attribute according to the attribute classification in restaurant to the restaurant knowledge mapping in the cuisines field of building
Extracting of wordNet subgraph.
Extracting of wordNet subgraph is done to restaurant knowledge mapping according to the attribute classification in restaurant, i.e., extracts all meal under every attribute respectively
The restaurant knowledge mapping subgraph under each attribute can be obtained in shop pertinent triplets, so that the attributive character in restaurant will be respectively
It is embodied in each attribute subgraph.
Step 3 carries out migration in each attribute subgraph in knowledge mapping at the restaurant by the random walk strategy with biasing,
A series of sequence node in migration paths is generated, the spy of learning network figure interior joint is carried out using the arrangement set of generation as training set
Sign.
Step 31 passes through a series of node sequences of random walk strategy generation with biasing for each subgraph being drawn into
Column.
The source node u given for one, simulates the random walk of a regular length L, ujIndicate jth in walk process
A node, start node u0=u.Node ujIt is generated by probability distribution below:
Wherein, D indicates the set on side in knowledge mapping, πvxIt is the transition probability between node v and x, Z is a regularization
Parameter.
Random walk has traversed side (t, v), and rests on node v.By calculating the transition probability π on side (v, x)vxTo sentence
Next node in disconnected sequence.Calculation formula is as follows:
πvx=αpq(t,x)*wvx
Wherein, wvxIt is the weight (1 is defaulted as when no weight) on side, αpqIndicate bigoted on the side between node.Meter
It calculates as follows:
Wherein, dtxBelong to the minimum hop count between (0,1,2) expression node t and x.dtx=0 indicates that x is exactly t itself, dtx
=1 indicates that x is x1 or x3, dtx=2 expression x are the parameters that x2, p and q are two supervision random walks.
Step 32, using sequence node as the input based on the word2vec model in neural network language model, pass through
Objective function is maximized, training objective is reached, obtains vector expression and user vector of the restaurant under every attribute.
Objective function is:
Wherein E indicates the node set in knowledge mapping, TuIndicate the sequence node set generated since node u, NtIt is
The length of each sequence t, N indicate the number of current sequence interior joint,A feature vector is indicated, by destination node uj
Context (i.e. context information) node composition.Each venn diagram show specific context node.For simple,
Assuming thatIt is a non-negative vector, wherein each single item all indicates the frequency of occurrence of a node in respective contexts.In form
On, we are with a d dimensional vectorFor each node modeling in sequence.Defining u-th of context node feature is
One d dimensional vector vu∈Rd。
Semantic restaurant vector and user vector under step 33, each attribute of fusion,
V (user)=vu
Wherein, v (attract) indicates the restaurant feature vector comprising each attribute semantemes, and m indicates the meal in knowledge mapping
The number of shop attribute,Indicate the restaurant feature vector under the i-th attribute, v (user) indicates the feature vector of user.
Restaurant and the correlation of user is calculated by the cosine similarity to user vector and restaurant vector in step 4,
And user is calculated accordingly and is scored the prediction in restaurant.
Step 41, the correlation for calculating restaurant and user are:
Rel (attract, user)=sim (v (attract), v (user))
Wherein, sim is cosine similarity.
Step 42, the maximum Max (Rel (attract, user)) for finding out correlation between restaurant and user respectively and minimum
The value of Min (Rel (attract, user)) by following formula by between correlation specification to 1 to 5, and rounds up to obtain
User scores to the prediction in restaurant:
Wherein, Max () expression takes max function in all relevance values, and Min () expression takes in all relevance values most
Small value function.
A certain user is carried out sequence from high to low to the prediction scoring in each restaurant by step 43, obtains the user's
Recommendation list.In this way by the way that user, personalized recommendation is can be completed in the restaurant recommendation being arranged in front in recommendation list.
The present embodiment is available using knowledge mapping mainly by carrying out knowledge mapping building to cuisines field restaurant
More perfect restaurant portrait and user's portrait, fusion various dimensions Feature Semantics, accurate assurance restaurant feature and user preference
Matching degree for user so that accurately provide personalized restaurant recommendation.
It should be noted that although the above embodiment of the present invention be it is illustrative, this be not be to the present invention
Limitation, therefore the invention is not limited in above-mentioned specific embodiment.Without departing from the principles of the present invention, all
The other embodiment that those skilled in the art obtain under the inspiration of the present invention is accordingly to be regarded as within protection of the invention.
Claims (6)
1. a kind of personalized recommendation method of knowledge based map, characterized in that specifically include that steps are as follows:
Step 1 obtains user, recommended project, the association attributes of recommended project and user to recommendation items from existing knowledge library
Thus purpose favorable rating establishes a recommended project knowledge mapping;
Step 2, the recommended project knowledge mapping to building carry out corresponding attribute subgraph according to the attribute classification of recommended project and take out
It takes, obtains the attribute subgraph of the recommended project knowledge mapping under each attribute;
Step 3 carries out migration in each attribute subgraph of recommended project knowledge mapping by the random walk strategy with biasing,
Generate a series of sequence node in migration paths;
Step 4, using the sequence node in migration path as the input based on neural network language model, pass through and maximize target
Function reaches training objective, obtains vector expression and user vector of the recommended project under every attribute;
Step 5, the vector by recommended project under every attribute indicates respectively and user vector merges, and obtains consequently recommended
Project vector sum end user's vector;
Step 6 calculates the cosine similarity of consequently recommended project vector sum end user's vector, obtain recommended project and
The correlation vector of user, and calculate user accordingly and score the prediction of recommended project, and then prediction scoring is ranked up i.e.
The recommendation list of each user can be obtained.
2. a kind of personalized recommendation method of knowledge based map according to claim 1, characterized in that in step 1 institute
In the recommended project knowledge mapping of foundation, user and recommended project are as its conceptual entity node, the association attributes of recommended project
The feature tag node of recommended project is described as it, user embodies the favorable rating of recommended project as its user node
Semantic information.
3. a kind of personalized recommendation method of knowledge based map according to claim 1, characterized in that in step 5, most
Whole recommended project vector v (attract) is:
Wherein,The vector for being recommended project under the i-th attribute indicates that m is the class number of attribute.
4. a kind of personalized recommendation method of knowledge based map according to claim 1, characterized in that in step 5, most
Whole user vector v (user) is:
V (user)=vu
Wherein, vuIndicate the feature vector of user.
5. a kind of personalized recommendation method of knowledge based map according to claim 1, characterized in that in step 6, use
The Relevance scores vector of family and recommended project is:
Rel (attract, user)=sim (v (attract), v (user))
Wherein, sim is cosine similarity, and v (attract) indicates in consequently recommended project vector that v (user) indicates end user
Vector.
6. a kind of personalized recommendation method of knowledge based map according to claim 1, characterized in that in step 6, use
Family is to prediction scoring Pre (attract, user) vector of recommended project:
Wherein, θ is scheduled scoring upper limit value, and Pre (attract, user) indicates the Relevance scores of recommended project and user
Vector, (Rel ((attract, user)) indicates the maximum value of all recommended projects and the Relevance scores of user, Min to Max
(Rel (attract, user)) indicates the minimum value of recommended project and the Relevance scores of user.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810580952.3A CN108920527A (en) | 2018-06-07 | 2018-06-07 | A kind of personalized recommendation method of knowledge based map |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810580952.3A CN108920527A (en) | 2018-06-07 | 2018-06-07 | A kind of personalized recommendation method of knowledge based map |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108920527A true CN108920527A (en) | 2018-11-30 |
Family
ID=64419707
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810580952.3A Pending CN108920527A (en) | 2018-06-07 | 2018-06-07 | A kind of personalized recommendation method of knowledge based map |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108920527A (en) |
Cited By (29)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109726747A (en) * | 2018-12-20 | 2019-05-07 | 西安电子科技大学 | Recommend the data fusion sort method of platform based on social networks |
CN109739970A (en) * | 2018-12-29 | 2019-05-10 | 联想(北京)有限公司 | Information processing method and device and electronic equipment |
CN109885700A (en) * | 2019-02-26 | 2019-06-14 | 扬州制汇互联信息技术有限公司 | A kind of unstructured data analysis method based on industrial knowledge mapping |
CN110175299A (en) * | 2019-05-28 | 2019-08-27 | 腾讯科技(上海)有限公司 | A kind of method and server that recommendation information is determining |
CN110245204A (en) * | 2019-06-12 | 2019-09-17 | 桂林电子科技大学 | A kind of intelligent recommendation method based on positioning and knowledge mapping |
CN110275964A (en) * | 2019-06-26 | 2019-09-24 | 程淑玉 | The recommended models of knowledge based map and Recognition with Recurrent Neural Network |
CN110287335A (en) * | 2019-06-17 | 2019-09-27 | 桂林电子科技大学 | The personalized recommending scenery spot method and device of knowledge based map and user's shot and long term preference |
CN110287336A (en) * | 2019-06-19 | 2019-09-27 | 桂林电子科技大学 | A kind of tourist's portrait construction method recommended towards tourist attractions |
CN110334221A (en) * | 2019-07-18 | 2019-10-15 | 桂林电子科技大学 | A kind of interpretation recommended method in knowledge based map path |
CN110489540A (en) * | 2019-08-21 | 2019-11-22 | 合肥天源迪科信息技术有限公司 | A kind of learning Content recommended method of knowledge based map |
CN110795569A (en) * | 2019-10-08 | 2020-02-14 | 北京百度网讯科技有限公司 | Method, device and equipment for generating vector representation of knowledge graph |
CN110807153A (en) * | 2019-11-06 | 2020-02-18 | 深圳墨世科技有限公司 | Recommendation method and device based on incremental updating, computer equipment and storage medium |
CN110955834A (en) * | 2019-11-27 | 2020-04-03 | 西北工业大学 | Knowledge graph driven personalized accurate recommendation method |
CN111091454A (en) * | 2019-11-05 | 2020-05-01 | 新华智云科技有限公司 | Financial public opinion recommendation method based on knowledge graph |
CN111125540A (en) * | 2019-11-12 | 2020-05-08 | 华侨大学 | Recommendation method integrating knowledge graph representation learning and bias matrix decomposition |
CN111190968A (en) * | 2019-12-16 | 2020-05-22 | 北京航天智造科技发展有限公司 | Data preprocessing and content recommendation method based on knowledge graph |
CN111353106A (en) * | 2020-02-26 | 2020-06-30 | 贝壳技术有限公司 | Recommendation method and device, electronic equipment and storage medium |
CN111581516A (en) * | 2020-05-11 | 2020-08-25 | 中国银行股份有限公司 | Investment product recommendation method and related device |
CN111651678A (en) * | 2020-06-18 | 2020-09-11 | 达而观信息科技(上海)有限公司 | Knowledge graph-based personalized recommendation method |
CN111723179A (en) * | 2020-05-26 | 2020-09-29 | 湖北师范大学 | Feedback model information retrieval method, system and medium based on concept map |
CN111949885A (en) * | 2020-08-27 | 2020-11-17 | 桂林电子科技大学 | Personalized recommendation method for scenic spots |
CN112115358A (en) * | 2020-09-14 | 2020-12-22 | 中国船舶重工集团公司第七0九研究所 | Personalized recommendation method using multi-hop path features in knowledge graph |
CN112184341A (en) * | 2020-11-10 | 2021-01-05 | 电子科技大学 | Gourmet recommending method based on archive network |
CN112784152A (en) * | 2019-11-11 | 2021-05-11 | 北京沃东天骏信息技术有限公司 | Method and device for marking user |
CN113254550A (en) * | 2021-06-29 | 2021-08-13 | 浙江大华技术股份有限公司 | Knowledge graph-based recommendation method, electronic device and computer storage medium |
CN113254630A (en) * | 2021-07-07 | 2021-08-13 | 浙江大学 | Domain knowledge map recommendation method for global comprehensive observation results |
CN113792163A (en) * | 2021-08-09 | 2021-12-14 | 北京达佳互联信息技术有限公司 | Multimedia recommendation method and device, electronic equipment and storage medium |
CN113901319A (en) * | 2021-10-18 | 2022-01-07 | 桂林电子科技大学 | Site recommendation method based on sequence semantics and attribute graph feature learning |
WO2022069958A1 (en) * | 2020-09-29 | 2022-04-07 | International Business Machines Corpofiation | Automatic knowledge graph construction |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103488724A (en) * | 2013-09-16 | 2014-01-01 | 复旦大学 | Book-oriented reading field knowledge map construction method |
US20160357844A1 (en) * | 2015-06-03 | 2016-12-08 | Kabushiki Kaisha Toshiba | Database apparatus, search apparatus, method of constructing partial graph, and search method |
CN107391542A (en) * | 2017-05-16 | 2017-11-24 | 浙江工业大学 | A kind of open source software community expert recommendation method based on document knowledge collection of illustrative plates |
CN107729444A (en) * | 2017-09-30 | 2018-02-23 | 桂林电子科技大学 | Recommend method in a kind of personalized tourist attractions of knowledge based collection of illustrative plates |
-
2018
- 2018-06-07 CN CN201810580952.3A patent/CN108920527A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103488724A (en) * | 2013-09-16 | 2014-01-01 | 复旦大学 | Book-oriented reading field knowledge map construction method |
US20160357844A1 (en) * | 2015-06-03 | 2016-12-08 | Kabushiki Kaisha Toshiba | Database apparatus, search apparatus, method of constructing partial graph, and search method |
CN107391542A (en) * | 2017-05-16 | 2017-11-24 | 浙江工业大学 | A kind of open source software community expert recommendation method based on document knowledge collection of illustrative plates |
CN107729444A (en) * | 2017-09-30 | 2018-02-23 | 桂林电子科技大学 | Recommend method in a kind of personalized tourist attractions of knowledge based collection of illustrative plates |
Non-Patent Citations (2)
Title |
---|
刘峤等: "基于双层随机游走的关系推理算法", 《计算机学报》 * |
王次臣: "基于深度学习的大规模图数据挖掘", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (45)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109726747A (en) * | 2018-12-20 | 2019-05-07 | 西安电子科技大学 | Recommend the data fusion sort method of platform based on social networks |
CN109726747B (en) * | 2018-12-20 | 2021-09-28 | 西安电子科技大学 | Data fusion ordering method based on social network recommendation platform |
CN109739970A (en) * | 2018-12-29 | 2019-05-10 | 联想(北京)有限公司 | Information processing method and device and electronic equipment |
CN109739970B (en) * | 2018-12-29 | 2021-07-16 | 联想(北京)有限公司 | Information processing method and device and electronic equipment |
CN109885700A (en) * | 2019-02-26 | 2019-06-14 | 扬州制汇互联信息技术有限公司 | A kind of unstructured data analysis method based on industrial knowledge mapping |
CN110175299B (en) * | 2019-05-28 | 2023-06-06 | 腾讯科技(上海)有限公司 | Recommendation information determining method and server |
CN110175299A (en) * | 2019-05-28 | 2019-08-27 | 腾讯科技(上海)有限公司 | A kind of method and server that recommendation information is determining |
CN110245204A (en) * | 2019-06-12 | 2019-09-17 | 桂林电子科技大学 | A kind of intelligent recommendation method based on positioning and knowledge mapping |
CN110287335A (en) * | 2019-06-17 | 2019-09-27 | 桂林电子科技大学 | The personalized recommending scenery spot method and device of knowledge based map and user's shot and long term preference |
CN110287335B (en) * | 2019-06-17 | 2021-08-27 | 桂林电子科技大学 | Personalized scenic spot recommendation method and device based on knowledge map and long-term and short-term preference of user |
CN110287336A (en) * | 2019-06-19 | 2019-09-27 | 桂林电子科技大学 | A kind of tourist's portrait construction method recommended towards tourist attractions |
CN110287336B (en) * | 2019-06-19 | 2021-08-27 | 桂林电子科技大学 | Tourist map construction method for tourist attraction recommendation |
CN110275964B (en) * | 2019-06-26 | 2023-07-14 | 程淑玉 | Recommendation model based on knowledge graph and cyclic neural network |
CN110275964A (en) * | 2019-06-26 | 2019-09-24 | 程淑玉 | The recommended models of knowledge based map and Recognition with Recurrent Neural Network |
CN110334221A (en) * | 2019-07-18 | 2019-10-15 | 桂林电子科技大学 | A kind of interpretation recommended method in knowledge based map path |
CN110334221B (en) * | 2019-07-18 | 2022-12-09 | 桂林电子科技大学 | Interpretability recommendation method based on knowledge graph path |
CN110489540A (en) * | 2019-08-21 | 2019-11-22 | 合肥天源迪科信息技术有限公司 | A kind of learning Content recommended method of knowledge based map |
CN110795569A (en) * | 2019-10-08 | 2020-02-14 | 北京百度网讯科技有限公司 | Method, device and equipment for generating vector representation of knowledge graph |
CN111091454A (en) * | 2019-11-05 | 2020-05-01 | 新华智云科技有限公司 | Financial public opinion recommendation method based on knowledge graph |
CN110807153A (en) * | 2019-11-06 | 2020-02-18 | 深圳墨世科技有限公司 | Recommendation method and device based on incremental updating, computer equipment and storage medium |
CN112784152A (en) * | 2019-11-11 | 2021-05-11 | 北京沃东天骏信息技术有限公司 | Method and device for marking user |
WO2021093423A1 (en) * | 2019-11-11 | 2021-05-20 | 北京沃东天骏信息技术有限公司 | Method and device for tagging user |
CN111125540A (en) * | 2019-11-12 | 2020-05-08 | 华侨大学 | Recommendation method integrating knowledge graph representation learning and bias matrix decomposition |
WO2021103789A1 (en) * | 2019-11-27 | 2021-06-03 | 西北工业大学 | Personalized accurate recommendation method driven by knowledge graph |
CN110955834B (en) * | 2019-11-27 | 2023-07-07 | 西北工业大学 | Knowledge graph driven personalized accurate recommendation method |
CN110955834A (en) * | 2019-11-27 | 2020-04-03 | 西北工业大学 | Knowledge graph driven personalized accurate recommendation method |
CN111190968A (en) * | 2019-12-16 | 2020-05-22 | 北京航天智造科技发展有限公司 | Data preprocessing and content recommendation method based on knowledge graph |
CN111353106B (en) * | 2020-02-26 | 2021-05-04 | 贝壳找房(北京)科技有限公司 | Recommendation method and device, electronic equipment and storage medium |
CN111353106A (en) * | 2020-02-26 | 2020-06-30 | 贝壳技术有限公司 | Recommendation method and device, electronic equipment and storage medium |
CN111581516A (en) * | 2020-05-11 | 2020-08-25 | 中国银行股份有限公司 | Investment product recommendation method and related device |
CN111581516B (en) * | 2020-05-11 | 2024-04-12 | 中国银行股份有限公司 | Investment product recommending method and related device |
CN111723179A (en) * | 2020-05-26 | 2020-09-29 | 湖北师范大学 | Feedback model information retrieval method, system and medium based on concept map |
CN111651678B (en) * | 2020-06-18 | 2023-12-22 | 达观数据有限公司 | Personalized recommendation method based on knowledge graph |
CN111651678A (en) * | 2020-06-18 | 2020-09-11 | 达而观信息科技(上海)有限公司 | Knowledge graph-based personalized recommendation method |
CN111949885A (en) * | 2020-08-27 | 2020-11-17 | 桂林电子科技大学 | Personalized recommendation method for scenic spots |
CN112115358B (en) * | 2020-09-14 | 2024-04-16 | 中国船舶重工集团公司第七0九研究所 | Personalized recommendation method utilizing multi-hop path characteristics in knowledge graph |
CN112115358A (en) * | 2020-09-14 | 2020-12-22 | 中国船舶重工集团公司第七0九研究所 | Personalized recommendation method using multi-hop path features in knowledge graph |
WO2022069958A1 (en) * | 2020-09-29 | 2022-04-07 | International Business Machines Corpofiation | Automatic knowledge graph construction |
GB2613999A (en) * | 2020-09-29 | 2023-06-21 | Ibm | Automatic knowledge graph construction |
CN112184341A (en) * | 2020-11-10 | 2021-01-05 | 电子科技大学 | Gourmet recommending method based on archive network |
CN113254550A (en) * | 2021-06-29 | 2021-08-13 | 浙江大华技术股份有限公司 | Knowledge graph-based recommendation method, electronic device and computer storage medium |
CN113254630A (en) * | 2021-07-07 | 2021-08-13 | 浙江大学 | Domain knowledge map recommendation method for global comprehensive observation results |
CN113792163A (en) * | 2021-08-09 | 2021-12-14 | 北京达佳互联信息技术有限公司 | Multimedia recommendation method and device, electronic equipment and storage medium |
CN113901319A (en) * | 2021-10-18 | 2022-01-07 | 桂林电子科技大学 | Site recommendation method based on sequence semantics and attribute graph feature learning |
CN113901319B (en) * | 2021-10-18 | 2024-03-26 | 桂林电子科技大学 | Site recommendation method based on sequence semantics and attribute map feature learning |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108920527A (en) | A kind of personalized recommendation method of knowledge based map | |
Wang et al. | Billion-scale commodity embedding for e-commerce recommendation in alibaba | |
CN108363804B (en) | Local model weighted fusion Top-N movie recommendation method based on user clustering | |
Richardson et al. | Mining knowledge-sharing sites for viral marketing | |
CN104199896B (en) | The video similarity of feature based classification is determined and video recommendation method | |
CN105320719B (en) | A kind of crowd based on item label and graphics relationship raises website item recommended method | |
CN106484764A (en) | User's similarity calculating method based on crowd portrayal technology | |
CN106802956A (en) | A kind of film based on weighting Heterogeneous Information network recommends method | |
CN103577549A (en) | Crowd portrayal system and method based on microblog label | |
Wang et al. | Social recommendation with optimal limited attention | |
CN104572797A (en) | Individual service recommendation system and method based on topic model | |
CN106708953A (en) | Discrete particle swarm optimization based local community detection collaborative filtering recommendation method | |
CN109190030A (en) | Merge the implicit feedback recommended method of node2vec and deep neural network | |
Li et al. | Overlap community detection using spectral algorithm based on node convergence degree | |
CN111522886B (en) | Information recommendation method, terminal and storage medium | |
CN110119478A (en) | A kind of item recommendation method based on similarity of a variety of user feedback datas of combination | |
Xiong et al. | Affective impression: Sentiment-awareness POI suggestion via embedding in heterogeneous LBSNs | |
Najafabadi et al. | Tag recommendation model using feature learning via word embedding | |
CN109408643B (en) | Fund similarity calculation method, system, computer equipment and storage medium | |
CN112883289B (en) | PMF recommendation method based on social trust and tag semantic similarity | |
Li et al. | Graph-based relation-aware representation learning for clothing matching | |
Partyka et al. | Enhanced geographically typed semantic schema matching | |
CN112446739B (en) | Click rate prediction method and system based on decomposition machine and graph neural network | |
CN109857928A (en) | User preference prediction technique based on polynary credit evaluation | |
Mao et al. | A fuzzy content matching-based e-commerce recommendation approach |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181130 |