CN114723528A - Commodity personalized recommendation method and system based on knowledge graph - Google Patents

Commodity personalized recommendation method and system based on knowledge graph Download PDF

Info

Publication number
CN114723528A
CN114723528A CN202210373080.XA CN202210373080A CN114723528A CN 114723528 A CN114723528 A CN 114723528A CN 202210373080 A CN202210373080 A CN 202210373080A CN 114723528 A CN114723528 A CN 114723528A
Authority
CN
China
Prior art keywords
commodity
commodities
user
knowledge graph
resource information
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
Application number
CN202210373080.XA
Other languages
Chinese (zh)
Inventor
张元杰
管洪清
徐亮
王伟
张大千
尹广楹
孙浩云
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.)
Qingdao Windaka Technology Co ltd
Original Assignee
Qingdao Windaka Technology Co ltd
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 Qingdao Windaka Technology Co ltd filed Critical Qingdao Windaka Technology Co ltd
Priority to CN202210373080.XA priority Critical patent/CN114723528A/en
Publication of CN114723528A publication Critical patent/CN114723528A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • 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
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0631—Item recommendations
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2457—Query processing with adaptation to user needs
    • G06F16/24578—Query processing with adaptation to user needs using ranking
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
    • G06F16/367—Ontology
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Computational Linguistics (AREA)
  • Animal Behavior & Ethology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Development Economics (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Strategic Management (AREA)
  • General Business, Economics & Management (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention provides a commodity personalized recommendation method and system based on a knowledge graph, which comprises the following steps: acquiring historical transaction data of a user and commodity resource information data in a specific area; mapping the commodity resource information data to a knowledge graph to obtain vector representation of the commodity resource information data; obtaining a user-commodity scoring matrix based on historical data of commodities purchased by a user; calculating and acquiring similarity between users based on the similarity, recommending commodities which are not purchased and are interested by neighbor users to a target user, and realizing primary recommendation of the commodities; and determining the commodities with semantic similarity meeting a preset threshold value with the preliminarily recommended commodities by combining the vector representation of the commodity resource information data, and obtaining a final commodity recommendation list. According to the scheme, the knowledge graph and the collaborative filtering recommendation algorithm are combined, so that the requirements for recommending commodities preferred by a user are met, the associated commodities preferred by the commodities are recommended through semantic similarity, the recommendation result is enriched, the novelty of the recommendation result is improved, and the experience of the user is met.

Description

Commodity personalized recommendation method and system based on knowledge graph
Technical Field
The disclosure belongs to the technical field of commodity recommendation, and particularly relates to a commodity personalized recommendation method and system based on a knowledge graph.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
With the development of network technology and scientific technology, the amount of information is increasing dramatically, and "information overload" becomes a problem which needs to be solved urgently. Search engines and recommendation systems are representative technologies to address such issues. The working principle of the search engine is to help users filter and screen information which is valuable to the users by means of keywords and the like, the mode meets the requirements of most people, personalized services are not provided, and the search results are unexpected and lack of novelty. Compared with the traditional search engine, the recommendation system can not only provide personalized requirements for users, but also solve the problem of information overload to a certain extent. The recommendation system has the principle that the preference degree of a user to commodities is predicted according to the preference, habit, personalized demand of the user and specific attributes of the commodities, the most suitable commodities are recommended for the user, the user is helped to make a decision quickly, and the user satisfaction is improved. The application value of the recommendation system is to be able to provide choices or recommendations that are as suitable as possible for the user without the user having to explicitly provide the content they want.
The inventor finds that most of the existing commodity personalized recommendation methods adopt a neural network algorithm for prediction, although the method has higher accuracy, the prerequisite condition for ensuring the accuracy is a large amount of training sample data, and for a user, the historical transaction data of the commodity is insufficient to support the training of the neural network algorithm, so that the practical application effect of the method is poor; meanwhile, for some goods recommendation algorithms adopting collaborative filtering, the goods recommendation algorithms lack the own attribute information of the goods in the collaborative filtering, so that the diffusivity, novelty and richness of the goods recommendation are poor.
Disclosure of Invention
In order to solve the problems, the scheme combines the knowledge graph with a collaborative filtering recommendation algorithm, so that not only can the commodities preferred by the user be recommended, but also the associated commodities of the preferred commodities can be recommended through semantic similarity, the recommendation result is enriched, the novelty of the recommendation result is improved, and the experience of the user is met.
According to a first aspect of the embodiments of the present disclosure, there is provided a commodity personalized recommendation method based on a knowledge graph, including:
acquiring historical transaction data and commodity resource information data of commodities purchased by a user in a specific area;
mapping the commodity resource information data to a knowledge graph to obtain vector representation of the commodity resource information data;
obtaining a user-commodity scoring matrix based on historical data of commodities purchased by a user;
calculating and acquiring similarity between users based on the similarity, recommending commodities which are not purchased and are interested by neighbor users to a target user, and realizing primary recommendation of the commodities;
and determining the commodities with semantic similarity meeting a preset threshold value with the preliminarily recommended commodities by combining the knowledge map vector representation of the commodity resource information data, and obtaining a final commodity recommendation list.
Further, a user-commodity scoring matrix is obtained based on historical data of commodities purchased by the user, and the method specifically comprises the following steps: and carrying out weighted average processing on the scoring data in the historical transaction data to obtain a scoring matrix of the user-commodity.
Further, recommending commodities which are not purchased and are interested by the neighbor user to the target user, wherein the user with the similarity higher than a preset threshold value is taken as the neighbor user of the current user, and the commodities which are interested by the neighbor user are the commodities which are purchased by the neighbor user and the scoring result of which meets the preset threshold value.
Further, the determining of the commodity, the semantic similarity of which with the preliminarily recommended commodity meets a preset threshold value, specifically includes: and acquiring commodities with semantic similarity meeting a preset threshold value between the first cascade entity in the knowledge graph and the preliminarily recommended commodities based on the acquired commodity vector representation and similarity calculation method.
Further, mapping the commodity resource information data to a knowledge graph specifically comprises: and finally, mapping the semantically related commodity entity to a knowledge graph by a node layer to obtain a knowledge graph triple.
According to a second aspect of the embodiments of the present disclosure, there is provided a commodity personalized recommendation system based on a knowledge graph, including:
the data acquisition unit is used for acquiring historical transaction data and commodity resource information data of commodities purchased by a user in a specific area;
the map construction unit is used for mapping the commodity resource information data to a knowledge map to obtain vector representation of the commodity resource information data;
the system comprises a scoring matrix construction unit, a scoring matrix generation unit and a scoring matrix generation unit, wherein the scoring matrix construction unit is used for acquiring a user-commodity scoring matrix based on historical data of commodities purchased by a user;
the preliminary recommendation unit is used for calculating and acquiring the similarity between the users based on the similarity, recommending commodities which are not purchased and are interested by the neighbor users to the target user and realizing preliminary recommendation of the commodities;
and the recommendation list acquisition unit is used for determining the commodities with semantic similarity meeting a preset threshold with the preliminarily recommended commodities by combining the knowledge map vector representation of the commodity resource information data to obtain a final commodity recommendation list.
According to a third aspect of the embodiments of the present disclosure, there is provided an electronic device, including a memory, a processor, and a computer program stored in the memory and running on the memory, where the processor implements the method for commodity personalized recommendation based on a knowledge graph when executing the program.
According to a fourth aspect of the embodiments of the present disclosure, there is provided a non-transitory computer-readable storage medium having stored thereon a computer program, which when executed by a processor implements the method for personalized recommendation of commodities based on a knowledge-graph.
Compared with the prior art, the beneficial effect of this disclosure is:
(1) the scheme combines the knowledge map with a collaborative filtering recommendation algorithm, not only meets the requirement of recommending commodities preferred by a user, but also recommends associated commodities preferred by the commodities through semantic similarity, enriches the recommendation result, improves the novelty of the recommendation result, and meets the experience of the user.
(2) The scheme disclosed by the disclosure uses TransE to express learning, vectorizes and expresses the entities and the relations in the knowledge graph, and uses the expressed entity vectors to calculate the similarity between commodity entities. The recommendation result of collaborative filtering is innovatively utilized and is used as input data for solving commodity similarity in the knowledge graph, so that the recommendation result is richer.
Advantages of additional aspects of the disclosure will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the disclosure.
Drawings
The accompanying drawings, which are included to provide a further understanding of the disclosure, illustrate embodiments of the disclosure and together with the description serve to explain the disclosure and are not to limit the disclosure.
Fig. 1 is a diagram of a knowledge-graph-based commodity personalized recommendation method according to a first embodiment of the present disclosure;
fig. 2 is a schematic diagram illustrating a triplet representation of a knowledge-graph according to a first embodiment of the present disclosure.
Detailed Description
The present disclosure is further described with reference to the following drawings and examples.
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present disclosure. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
The embodiments and features of the embodiments in the present disclosure may be combined with each other without conflict.
The first embodiment is as follows:
the embodiment aims to provide a commodity personalized recommendation method based on a knowledge graph.
A commodity personalized recommendation method based on a knowledge graph comprises the following steps:
acquiring historical transaction data and commodity resource information data of commodities purchased by a user in a specific area;
mapping the commodity resource information data to a knowledge graph to obtain vector representation of the commodity resource information data;
obtaining a user-commodity scoring matrix based on historical data of commodities purchased by a user;
calculating and acquiring similarity between users based on the similarity, recommending commodities which are not purchased and are interested by neighbor users to a target user, and realizing primary recommendation of the commodities;
and determining the commodities with semantic similarity meeting a preset threshold value with the preliminarily recommended commodities by combining the knowledge map vector representation of the commodity resource information data, and obtaining a final commodity recommendation list.
Specifically, for ease of understanding, the embodiments of the present disclosure are described in detail below with reference to the accompanying drawings:
as shown in fig. 1, the present disclosure provides a commodity personalized recommendation method based on a knowledge graph, including: the method comprises the steps of collecting commodity resource information and historical transaction records of users, constructing a commodity resource knowledge graph, a TransE expression learning conversion knowledge graph, constructing a user-commodity scoring matrix, calculating similarity users, primarily recommending, calculating commodity semantic similarity, top-N recommending and returning to a user terminal. The commodity resource information and the user historical transaction record are obtained based on a community service platform, and meanwhile, a final commodity recommendation list is fed back to the user terminal through the community service platform.
Specifically, the commodity personalized recommendation method based on the knowledge graph comprises the following specific steps:
step 1: acquiring historical transaction data and commodity resource information data of commodities purchased by a user in a specific area;
the method specifically comprises the following steps that under a community service platform, commodity resource information data and historical transaction record data of commodities purchased by community users are collected, wherein the historical transaction record data comprise interaction information; the historical transaction record data comprises user id, commodity id, grading, evaluation, star rating and other interactive information data;
step 2: mapping the commodity resource information data to a knowledge graph to obtain vector representation of the commodity resource information data;
the step 2 specifically includes integrating commodity resource information data into the map through a three-layer structure of a commodity resource layer, a logic relation layer and a node layer; and embedding the entities and the relations in the knowledge graph into a low-dimensional vector space by using a TransE representation learning algorithm, and simultaneously converting the entities and the relations into vector representations.
Specifically, the commodity resource layer receives the commodity resource information data acquired in the step 1, data preprocessing operations such as labels and keywords are added to commodity entities, then the operations such as logic definition, relation description and label labeling are carried out on the processed commodities, and finally the commodity entities related to semantics are mapped into the knowledge graph by the node layer. The commodity knowledge-graph triplets are shown in fig. 2.
And embedding the entities and the relations in the knowledge graph into a low-dimensional vector space by using a TransE representation learning algorithm, and simultaneously converting the entities and the relations into vector representations. The specific operation is as follows: according to the definition of the TransE algorithm, for a triplet subject-relation-object in the knowledge-graph, which can be expressed as (h, r, t), it holds that h + r is t, and a defined distance d (x, y) represents the distance between two vectors, and the overfitting phenomenon is reduced by adopting an L1-normal regularization technology, wherein the smaller d (h + r, t) is, the better d (h '+ r, t') is, the larger d (h '+ r, t') is, the better d is, the larger d is, the more wrong d (h '+ r, t') is, and therefore, an objective function is obtained:
Figure BDA0003589558740000061
wherein, (h, r, t) represents the correct triplet set; (h ', r, t') represents an erroneous triplet set;
gamma represents the distance between the positive and negative samples and is a constant, and the value is empirically selected to be 1 in this embodiment;
[x]+represents max (0, x);
the final learning result is: the vector of the head node plus the relationship vector is substantially equal to the vector of the tail node.
And step 3: obtaining a user-commodity scoring matrix based on historical data of commodities purchased by a user;
step 3, specifically, performing data preprocessing on the transaction record data by performing operations such as weighted average and the like to obtain a user-commodity scoring matrix;
specifically, the scoring data in the transaction record data is subjected to data preprocessing such as weighted average and the like to obtain a user-commodity scoring matrix.
Figure BDA0003589558740000062
Wherein, x is the grade of each mode of the commodity by the user, and f is the weight corresponding to the grade. The following user-commodity scoring matrices obtained after the preprocessing are specifically shown in table 1:
table 1: user-commodity scoring matrix
Item1 Item2 ... Itemk
User1 r11 r12 ... r1k
User2 r21 r22 ... r2k
... ... ... ... ...
Userk rk1 rk2 ... rkk
And 4, step 4: calculating and acquiring similarity between users based on the similarity, recommending commodities which are not purchased and are interested by neighbor users to a target user, and realizing primary recommendation of the commodities; and taking the user with the similarity higher than the preset threshold value as a neighbor user of the current user, wherein the commodity which is interested by the neighbor user is a commodity which is purchased by the neighbor user and the scoring result of which meets the preset threshold value. Specifically, the similarity between users is calculated by using a cosine similarity calculation formula:
Figure BDA0003589558740000071
wherein A isiAnd BiRespectively representing each component of the vectors A and B, and regarding the cosine value larger than a preset threshold (0.6 is selected in the embodiment) as a neighbor user of the current user.
Based on the neighbor users of the current user, recommending commodities which are not purchased by the current user and are interested by the neighbor users to the current user, and achieving the purpose of preliminary recommendation.
And 5: calculating other commodities with semantic similarity of the preliminarily recommended commodities by combining the knowledge graph, and finally realizing an individualized commodity resource recommendation list;
specifically, according to the recommended commodity list information, the commodity entity vector obtained in step 2 represents the similar commodities calculated by using cosine similarity, in the preliminary recommended commodity set Item { x1, x 2.,. x3} obtained in step 4. Meanwhile, because the relation of knowledge graph entities is cascade connection, in order to improve the recommendation precision, only the first cascade connection entity of the commodity set in the knowledge graph is taken.
Step 6: returning to the community user terminal for the user to select; specifically, the obtained personalized commodity resource recommendation list is sorted according to the user grading result, and a preset number of commodities are selected and returned to the user terminal based on a top-N method for selection by the user.
According to the scheme, the knowledge graph and the collaborative filtering recommendation algorithm are combined, community commodity resources are managed by the knowledge graph, the knowledge graph organizes multi-source information, the defect that the attributes of commodities are not considered in the collaborative filtering algorithm is overcome, the recommendation result not only contains the preference of users, but also is added with the commodities similar to the preferred commodity semantics, and the richness and novelty of the recommendation system result are greatly improved.
Example two:
the embodiment aims to provide a commodity personalized recommendation system based on a knowledge graph.
A commodity personalized recommendation system based on knowledge graph comprises:
the data acquisition unit is used for acquiring historical transaction data and commodity resource information data of commodities purchased by a user in a specific area;
the map construction unit is used for mapping the commodity resource information data to a knowledge map to obtain vector representation of the commodity resource information data;
the system comprises a scoring matrix construction unit, a scoring matrix generation unit and a scoring matrix generation unit, wherein the scoring matrix construction unit is used for acquiring a user-commodity scoring matrix based on historical data of commodities purchased by a user;
the preliminary recommendation unit is used for calculating and acquiring the similarity between the users based on the similarity, recommending commodities which are not purchased and are interested by the neighbor users to the target user and realizing preliminary recommendation of the commodities;
and the recommendation list acquisition unit is used for determining the commodities with semantic similarity meeting a preset threshold value with the preliminarily recommended commodities by combining the knowledge map vector representation of the commodity resource information data to obtain a final commodity recommendation list.
In further embodiments, there is also provided:
an electronic device comprising a memory and a processor, and computer instructions stored on the memory and executed on the processor, the computer instructions when executed by the processor performing the method of embodiment one. For brevity, further description is omitted herein.
It should be understood that in this embodiment, the processor may be a central processing unit CPU, and the processor may also be other general purpose processors, digital signal processors DSP, application specific integrated circuits ASIC, off-the-shelf programmable gate arrays FPGA or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, and so on. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory may include both read-only memory and random access memory, and may provide instructions and data to the processor, and a portion of the memory may also include non-volatile random access memory. For example, the memory may also store device type information.
A computer readable storage medium storing computer instructions which, when executed by a processor, perform the method of embodiment one.
The method in the first embodiment may be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules in the processor. The software modules may be located in ram, flash, rom, prom, or eprom, registers, among other storage media as is well known in the art. The storage medium is located in a memory, and a processor reads information in the memory and combines hardware thereof to complete the steps of the method. To avoid repetition, it is not described in detail here.
Those of ordinary skill in the art will appreciate that the various illustrative elements, i.e., algorithm steps, described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
The commodity personalized recommendation method and system based on the knowledge graph can be realized, and have wide application prospects.
The above description is only a preferred embodiment of the present disclosure and is not intended to limit the present disclosure, and various modifications and changes may be made to the present disclosure by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present disclosure should be included in the protection scope of the present disclosure.

Claims (10)

1. The commodity personalized recommendation method based on the knowledge graph is characterized by comprising the following steps:
acquiring historical transaction data and commodity resource information data of commodities purchased by a user in a specific area;
mapping the commodity resource information data to a knowledge graph to obtain vector representation of the commodity resource information data;
obtaining a user-commodity scoring matrix based on historical data of commodities purchased by a user;
calculating and acquiring similarity between users based on the similarity, recommending commodities which are not purchased and are interested by neighbor users to a target user, and realizing primary recommendation of the commodities;
and determining the commodities with semantic similarity meeting a preset threshold value with the preliminarily recommended commodities by combining the knowledge map vector representation of the commodity resource information data, and obtaining a final commodity recommendation list.
2. The commodity personalized recommendation method based on the knowledge graph as claimed in claim 1, wherein the user-commodity scoring matrix is obtained based on historical data of commodities purchased by the user, and specifically comprises: and carrying out weighted average processing on the scoring data in the historical transaction data to obtain a scoring matrix of the user-commodity.
3. The commodity personalized recommendation method based on the knowledge graph as claimed in claim 1, wherein the commodities which are not purchased and are interested by the neighbor users are recommended to the target user, wherein the user with the similarity higher than a preset threshold is taken as the neighbor user of the current user, and the commodities which are purchased by the neighbor user and are interested by the neighbor user are commodities whose scoring result meets the preset threshold.
4. The commodity personalized recommendation method based on the knowledge graph as claimed in claim 1, wherein the determining of the commodity whose semantic similarity with the preliminarily recommended commodity satisfies a preset threshold specifically comprises: and obtaining the commodities with the semantic similarity meeting a preset threshold value between the first cascade entity in the knowledge graph and the preliminarily recommended commodities based on the obtained commodity vector representation and similarity calculation method.
5. The commodity personalized recommendation method based on the knowledge graph as claimed in claim 1, wherein the mapping of the commodity resource information data to the knowledge graph specifically comprises: and finally, mapping the semantically related commodity entity to a knowledge graph by a node layer to obtain a knowledge graph triple.
6. The commodity personalized recommendation method based on knowledge graph as claimed in claim 1, wherein the vector representation is obtained by embedding the entity and the relation in the commodity knowledge graph into a low-dimensional vector space by using a TransE representation learning method and converting the vector representation into the vector representation.
7. The commodity personalized recommendation method based on knowledge graph as claimed in claim 1, wherein said commodity resource information data comprises commodity name, attribute and category; the historical transaction data of the commodities purchased by the user comprises user id, commodity id, rating, evaluation and star rating data.
8. A commodity personalized recommendation system based on knowledge graph is characterized by comprising:
the data acquisition unit is used for acquiring historical transaction data and commodity resource information data of commodities purchased by a user in a specific area;
the map construction unit is used for mapping the commodity resource information data into a knowledge map to obtain vector representation of the commodity resource information data;
the system comprises a scoring matrix construction unit, a scoring matrix generation unit and a scoring matrix generation unit, wherein the scoring matrix construction unit is used for acquiring a user-commodity scoring matrix based on historical data of commodities purchased by a user;
the preliminary recommendation unit is used for calculating and acquiring the similarity between the users based on the similarity, recommending commodities which are not purchased and are interested by the neighbor users to the target user and realizing preliminary recommendation of the commodities;
and the recommendation list acquisition unit is used for determining the commodities with semantic similarity meeting a preset threshold with the preliminarily recommended commodities by combining the knowledge map vector representation of the commodity resource information data to obtain a final commodity recommendation list.
9. An electronic device comprising a memory, a processor and a computer program stored and executed on the memory, wherein the processor implements a method for commodity personalized recommendation based on knowledge-graph as claimed in any one of claims 1-7 when executing the program.
10. A non-transitory computer readable storage medium having stored thereon a computer program, wherein the program when executed by a processor implements a method for customized recommendation of a commodity based on a knowledge-graph according to any one of claims 1-7.
CN202210373080.XA 2022-04-11 2022-04-11 Commodity personalized recommendation method and system based on knowledge graph Pending CN114723528A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210373080.XA CN114723528A (en) 2022-04-11 2022-04-11 Commodity personalized recommendation method and system based on knowledge graph

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210373080.XA CN114723528A (en) 2022-04-11 2022-04-11 Commodity personalized recommendation method and system based on knowledge graph

Publications (1)

Publication Number Publication Date
CN114723528A true CN114723528A (en) 2022-07-08

Family

ID=82241170

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210373080.XA Pending CN114723528A (en) 2022-04-11 2022-04-11 Commodity personalized recommendation method and system based on knowledge graph

Country Status (1)

Country Link
CN (1) CN114723528A (en)

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115587875A (en) * 2022-11-10 2023-01-10 广州科拓科技有限公司 Textile e-commerce recommendation method and device based on balanced perception attention network
CN115619442A (en) * 2022-12-21 2023-01-17 北京仁科互动网络技术有限公司 Sales opportunity generation method, sales opportunity generation device, electronic equipment and storage medium
CN116308683A (en) * 2023-05-17 2023-06-23 武汉纺织大学 Knowledge-graph-based clothing brand positioning recommendation method, equipment and storage medium
CN116385048A (en) * 2023-06-06 2023-07-04 山东政信大数据科技有限责任公司 Intelligent marketing method and system for agricultural products
CN116645167A (en) * 2023-05-30 2023-08-25 阿锐巴数据科技(上海)有限公司 Commodity recommendation system and method based on intelligent decision
CN116739787A (en) * 2023-08-11 2023-09-12 深圳市艾德网络科技发展有限公司 Transaction recommendation method and system based on artificial intelligence
CN117290398A (en) * 2023-09-27 2023-12-26 广东科学技术职业学院 Course recommendation method and device based on big data
CN117350823A (en) * 2023-12-04 2024-01-05 北京国双科技有限公司 Commodity information recommendation method, system, equipment and medium for electronic mall
CN117635266A (en) * 2023-12-01 2024-03-01 深圳市瀚力科技有限公司 Platform optimization management system for commodity recommendation
CN117688251A (en) * 2024-02-04 2024-03-12 北京奥维云网大数据科技股份有限公司 Commodity retrieval method and system based on knowledge graph

Cited By (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115587875A (en) * 2022-11-10 2023-01-10 广州科拓科技有限公司 Textile e-commerce recommendation method and device based on balanced perception attention network
CN115619442A (en) * 2022-12-21 2023-01-17 北京仁科互动网络技术有限公司 Sales opportunity generation method, sales opportunity generation device, electronic equipment and storage medium
CN116308683A (en) * 2023-05-17 2023-06-23 武汉纺织大学 Knowledge-graph-based clothing brand positioning recommendation method, equipment and storage medium
CN116308683B (en) * 2023-05-17 2023-08-04 武汉纺织大学 Knowledge-graph-based clothing brand positioning recommendation method, equipment and storage medium
CN116645167A (en) * 2023-05-30 2023-08-25 阿锐巴数据科技(上海)有限公司 Commodity recommendation system and method based on intelligent decision
CN116645167B (en) * 2023-05-30 2024-03-12 阿锐巴数据科技(上海)有限公司 Commodity recommendation system and method based on intelligent decision
CN116385048A (en) * 2023-06-06 2023-07-04 山东政信大数据科技有限责任公司 Intelligent marketing method and system for agricultural products
CN116385048B (en) * 2023-06-06 2023-08-22 山东政信大数据科技有限责任公司 Intelligent marketing method and system for agricultural products
CN116739787A (en) * 2023-08-11 2023-09-12 深圳市艾德网络科技发展有限公司 Transaction recommendation method and system based on artificial intelligence
CN116739787B (en) * 2023-08-11 2023-12-26 深圳市艾德网络科技发展有限公司 Transaction recommendation method and system based on artificial intelligence
CN117290398A (en) * 2023-09-27 2023-12-26 广东科学技术职业学院 Course recommendation method and device based on big data
CN117635266A (en) * 2023-12-01 2024-03-01 深圳市瀚力科技有限公司 Platform optimization management system for commodity recommendation
CN117350823A (en) * 2023-12-04 2024-01-05 北京国双科技有限公司 Commodity information recommendation method, system, equipment and medium for electronic mall
CN117688251A (en) * 2024-02-04 2024-03-12 北京奥维云网大数据科技股份有限公司 Commodity retrieval method and system based on knowledge graph
CN117688251B (en) * 2024-02-04 2024-04-26 北京奥维云网大数据科技股份有限公司 Commodity retrieval method and system based on knowledge graph

Similar Documents

Publication Publication Date Title
CN114723528A (en) Commodity personalized recommendation method and system based on knowledge graph
CN109255586B (en) Online personalized recommendation method for e-government affairs handling
CN110704626B (en) Short text classification method and device
CN112307762B (en) Search result sorting method and device, storage medium and electronic device
US20040267686A1 (en) News group clustering based on cross-post graph
CN108573041B (en) Probability matrix decomposition recommendation method based on weighted trust relationship
CN111177559B (en) Text travel service recommendation method and device, electronic equipment and storage medium
CN106407420B (en) Multimedia resource recommendation method and system
US20200356781A1 (en) Method and apparatus for performing categorised matching of videos, and selection engine
CN113254630B (en) Domain knowledge map recommendation method for global comprehensive observation results
CN111429161B (en) Feature extraction method, feature extraction device, storage medium and electronic equipment
Bahamonde et al. Power structure in Chilean news media
WO2016009419A1 (en) System and method for ranking news feeds
CN109063171B (en) Resource matching method based on semantics
CN111125318B (en) Method for improving knowledge graph relation prediction performance based on sememe-semantic item information
CN104077288B (en) Web page contents recommend method and web page contents recommendation apparatus
CN110598126A (en) Cross-social network user identity recognition method based on behavior habits
CN111259223B (en) News recommendation and text classification method based on emotion analysis model
CN112685656A (en) Label recommendation method and electronic equipment
CN116628228A (en) RPA flow recommendation method and computer readable storage medium
CN113449200A (en) Article recommendation method and device and computer storage medium
GB2608112A (en) System and method for providing media content
CN113988060A (en) Data information recommendation method and device, terminal equipment and storage medium
CN115345687A (en) Cross-website commodity alignment method and device
CN114329167A (en) Hyper-parameter learning, intelligent recommendation, keyword and multimedia recommendation method and device

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