CN111986006A - Product recommendation method and device based on knowledge graph, computer equipment and storage medium - Google Patents
Product recommendation method and device based on knowledge graph, computer equipment and storage medium Download PDFInfo
- Publication number
- CN111986006A CN111986006A CN202010908112.2A CN202010908112A CN111986006A CN 111986006 A CN111986006 A CN 111986006A CN 202010908112 A CN202010908112 A CN 202010908112A CN 111986006 A CN111986006 A CN 111986006A
- Authority
- CN
- China
- Prior art keywords
- product
- attribute
- user attribute
- user
- index
- 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
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000004590 computer program Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000010586 diagram Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 5
- 238000007667 floating Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000008094 contradictory effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
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]
- G06Q30/0623—Item investigation
-
- 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
- G06F16/9535—Search customisation based on user profiles and personalisation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Development Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Computational Linguistics (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 discloses a product recommendation method and device based on a knowledge graph, computer equipment and a storage medium, wherein a user attribute index and a product attribute index are generated according to a user attribute table and a product attribute table, and the user attribute table comprises historical purchase records corresponding to products in the product attribute table; generating a knowledge graph according to the user attribute indexes and the product attribute indexes, wherein the knowledge graph comprises user attribute nodes and product attribute nodes; and generating product recommendation data among different users in the user attribute table through common product attribute nodes in the product attribute nodes. According to the invention, the user information and the purchased product information are matched from the structured historical data, a plurality of product attribute combinations are obtained according to the purchased product information of different users, then the knowledge graph between the user node and the product node is established, and the recommendation data is generated through the common product attribute nodes in the knowledge graph, so that the multi-dimensional product recommendation based on the knowledge graph is realized.
Description
Technical Field
The invention relates to the field of data knowledge maps, in particular to a product recommendation method and device based on a knowledge map, computer equipment and a storage medium.
Background
In the current recommendation scheme based on the knowledge graph in the market, the construction mode of the knowledge graph is a user product mode, namely nodes in the graph usually only comprise two types of nodes, namely a user node and a product node, and then product information is pushed from historical products to the user according to the user interest.
However, for a specific type of enterprise, for example, a middle and small-sized bank, the product category tends to be single, and it is generally required that personalized product recommendation data of multiple dimensions can be generated according to the user attribute characteristics, which cannot be realized by the prior art.
Disclosure of Invention
In view of the above, the invention provides a product recommendation method, a product recommendation device, a computer device and a storage medium based on a knowledge graph, which are used for solving the problem that multi-dimensional product recommendation data cannot be generated when the product type tends to be single.
Firstly, in order to achieve the above object, the present invention provides a product recommendation method based on a knowledge graph, wherein the method comprises:
generating a user attribute index and a product attribute index according to a user attribute table and a product attribute table, wherein the user attribute table comprises product purchase history records of users, and the product attribute table comprises attribute information of corresponding products;
generating a knowledge graph according to the user attribute indexes and the product attribute indexes, wherein the knowledge graph comprises user attribute nodes and product attribute nodes;
and generating product recommendation data among different users in the user attribute table through common product attribute nodes in the product attribute nodes.
Further, the generating the user attribute index and the product attribute index according to the user attribute table and the product attribute table includes:
acquiring the user attribute table, and generating the user attribute index based on the user attribute table, wherein the user attribute index comprises user attribute data and a product name index;
and obtaining the product attribute table according to the product name index, and generating the product attribute index based on the product attribute table, wherein the product attribute index comprises a product attribute and an enumeration value corresponding to the product name index.
Further, the user attribute index and the product attribute index include node numbers of the knowledge graph, and the generating of the knowledge graph according to the user attribute index and the product attribute index includes:
generating the user attribute node according to the node number and the user attribute data;
and generating the product attribute node according to the node number and the product attribute and enumeration value corresponding to the product name index.
Further, the generating the product attribute node according to the node number, the product attribute, and the enumeration value further includes:
and when the product attributes and the enumeration values of different products in the product attribute table are the same, identifying the product attribute nodes generated by the corresponding product attributes and the corresponding enumeration values as the common product attribute nodes.
Further, the obtaining the user attribute table and generating the user attribute index based on the user attribute table further include:
converting the user attribute data in the user attribute table into numerical values to obtain user attribute values;
correspondingly, the generating of the product recommendation data among different users in the user attribute table through the common product attribute nodes in the product attribute nodes further includes:
calculating a weight value between the user attribute node and the common product attribute node according to the user attribute value;
and generating product recommendation data among different users in the user attribute table according to the weight values.
Further, the calculating a weight value between the user attribute node and the common product attribute node according to the user attribute value includes:
giving the average value of the user attribute values of the user attribute nodes to the common product attribute node as a common product attribute value;
calculating the distance between the user attribute value and the common product attribute value through an Euclidean distance calculation formula to obtain a plurality of distance values;
normalizing the plurality of distance values to obtain the weight value.
Further, after the generating of the product recommendation data among different users in the user attribute table by the common product attribute node in the product attribute nodes, the method further includes:
and uploading the product recommendation data to a blockchain.
In order to achieve the above object, the present invention further provides a product recommendation apparatus based on a knowledge graph, including:
the index module is used for generating a user attribute index and a product attribute index according to a user attribute table and a product attribute table, wherein the user attribute table comprises historical purchase records corresponding to products in the product attribute table;
the knowledge graph module is used for generating a knowledge graph according to the user attribute indexes and the product attribute indexes, and the knowledge graph comprises user attribute nodes and product attribute nodes;
and the recommending module is used for generating product recommending data among different users in the user attribute table through the common product attribute nodes in the product attribute nodes.
To achieve the above object, the present invention further provides a computer device, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the above method when executing the computer program.
To achieve the above object, the present invention also provides a computer-readable storage medium having stored thereon a computer program which, when being executed by a processor, carries out the steps of the above method.
Compared with the prior art, the product recommendation method, the product recommendation device, the computer equipment and the storage medium based on the knowledge graph of the embodiment of the invention match the user information and the purchased product information from the structured historical data, obtain a plurality of product attribute combinations according to the purchased product information of different users, establish the knowledge graph between the user node and the product node, and generate the recommendation data through the common product attribute nodes in the knowledge graph, thereby realizing the multi-dimensional product recommendation based on the knowledge graph.
Drawings
FIG. 1 is a schematic diagram of an application environment of an embodiment of the present invention;
FIG. 2 is a flowchart illustrating a knowledge-graph based product recommendation method according to a first embodiment of the present invention;
FIG. 3 is a schematic flow chart illustrating the process of generating a user attribute index and a product attribute index according to the user attribute table and the product attribute table in FIG. 2;
FIG. 4 is a schematic node diagram of a knowledge-graph according to a first embodiment of the present invention;
FIG. 5 is a partial flow chart of a knowledge-graph based product recommendation method according to a second embodiment of the present invention;
FIG. 6 is a schematic flow chart illustrating a process of calculating a weight value between the user attribute node and the common product attribute node according to the user attribute value in FIG. 5;
FIG. 7 is a diagram illustrating nodes of a knowledge graph with weighted values according to a second embodiment of the present invention;
FIG. 8 is a diagram illustrating nodes of a knowledge-graph with weighted values after updating the nodes according to a second embodiment of the present invention;
FIG. 9 is a block diagram of a third embodiment of a knowledge-graph based product recommender according to the present invention;
FIG. 10 is a diagram of a hardware configuration of a fourth embodiment of the computer apparatus according to the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the description relating to "first", "second", etc. in the present invention is for descriptive purposes only and is not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In addition, technical solutions between various embodiments may be combined with each other, but must be realized by a person skilled in the art, and when the technical solutions are contradictory or cannot be realized, such a combination should not be considered to exist, and is not within the protection scope of the present invention.
Referring to fig. 1, a schematic diagram of an implementation environment of the embodiment of the invention is shown. The implementation environment includes: a user terminal 10 and a service terminal 12.
The user terminal 10 is an electronic device with network access function, and the device may be a smart phone, a tablet computer, a personal computer, or the like.
The user terminal 10 is installed with a program 11 that can access the server terminal 12, and after the program 11 logs in to access the server terminal 12 through an account and a password, the user can perform specific operations and inputs on the server terminal 12.
The server 12 is a server, a server cluster formed by a plurality of servers, or a cloud computing center. The server 12 stores a program 13, the program 13 includes a front-end module and a back-end module, the front-end module and the back-end module can be called by an interface, and a user can perform specific operation and input on the program 13 after the program 11 logs in through an account and a password or accesses the program 13 of the server 12 through the account and the password.
In the present embodiment, the server 12 stores a plurality of databases and data tables. Different databases may obtain the data in the databases through the triggering instruction of the user 10.
In this embodiment, the database and data tables include, but are not limited to, a user attribute table and a product attribute table.
In other embodiments, the database may also be stored in different servers in the server 12 cluster, or in different network nodes connected via a network, or locally in the user segment 10.
The user terminal 10 and the service terminal 12 are connected through a network, which may include a plurality of network nodes, and the network may be the internet, a local area network, or a block chain network.
The product recommendation method based on the knowledge graph of the embodiment of the invention can be applied to the program 11 or the program 13 independently, can be applied to the program 11 and the program 13 in a distributed mode simultaneously, or can be stored in a plurality of nodes of a network in a block chain mode.
Example one
According to the product recommendation method based on the knowledge graph, user information and purchased product information are matched from the structured historical data, a plurality of product attribute combinations are obtained according to the purchased product information of different users, then the knowledge graph between the user nodes and the product nodes is established, recommendation data are generated through common product attribute nodes in the knowledge graph, and multi-dimensional product recommendation based on the knowledge graph is achieved.
Referring to fig. 2, a method for recommending a product based on a knowledge graph in the present embodiment includes the following steps:
step S100, generating a user attribute index and a product attribute index according to a user attribute table and a product attribute table, wherein the user attribute table comprises a product purchase history record of a user, and the product attribute table comprises attribute information of a corresponding product;
first, based on the user attribute table and the product attribute table, a user attribute index and a product attribute index are automatically generated by writing an independent script. The user attribute table and the product attribute table are not limited to the storage form of the table, and can be in other information storage formats.
Specifically, referring to fig. 3, in step S100, generating a user attribute index and a product attribute index according to the user attribute table and the product attribute table includes:
step S110: acquiring the user attribute table, and generating the user attribute index based on the user attribute table, wherein the user attribute index comprises user attribute data and a product name index;
the user attribute table includes user attribute information such as gender and age, and a purchase history of the user such as name identification of a purchased product.
And generating a user attribute index based on the user attribute table, and searching a user unique identification code, such as an identification number, in the user attribute table.
And according to the searched unique user identification code, carrying out identification numbering on different users in the user attribute table to obtain a user attribute index, wherein the user attribute index comprises attribute data of each user and historical purchased product information.
For example, as shown in table 1 and table 2 below, in the present embodiment, the user attribute index is generated based on the user attribute table, and the generated user attribute index includes user 1 and user 2 numbered as id1 and id2, and their corresponding historical purchased product information.
| Identity card number | Sex | Age (age) | Product name | … |
| xxxxx022 | For male | 32 | Fund product 1 | |
| xxxxx123 | Woman | 26 | |
TABLE 1 user Attribute Table
| id | Identity card number | Sex | Age (age) | Product name indexing | … |
| 1 | xxxxx022 | For male | 32 | Fund product 1 | |
| 2 | xxxxx123 | Woman | 26 | |
TABLE 2 user Attribute index Table
Step S120: and obtaining the product attribute table according to the product name index, and generating the product attribute index based on the product attribute table, wherein the product attribute index comprises a product attribute and an enumeration value corresponding to the product name index.
The product table is corresponding product information data obtained based on product information in the purchase history in the user attribute table.
And disassembling product attributes and corresponding enumerated values purchased by a product table user in history so that the indexed data table is not limited to product dimensions any more, but is in a combination form of a plurality of product attributes and enumerated values thereof, and then combining and designing a new product according to user preference.
For example, the product corresponding attributes purchased by the user in history include rate, purchase amount and income. The corresponding product attribute may include one or more enumerated values, for example, the enumerated values corresponding to the product attribute rate include 1.5% and 0.75%, the enumerated values corresponding to the purchase amount are 100 and 1000, and the enumerated value corresponding to the profit is the floating profit.
And recombining the plurality of product attributes and enumerated values thereof to obtain an indexed product attribute table and removing duplication, wherein the indexed product attribute table comprises 5 groups of data.
And then, carrying out identification numbering on different product attributes and enumeration values in the product attribute table to obtain a product attribute index.
For example, in the present embodiment, as shown in tables 3 and 4 below, in the present embodiment, the product attribute table is obtained according to the product name index, and the product attribute index is generated based on the product attribute table, where the generated product attribute index includes different product attribute indexes numbered id3-id 5.
| Product name | Product Properties | Enumerated value |
| Fund product 1 | Rate of charge | 1.5％ |
| Fund product 1 | Amount of purchase | 1000 |
| Fund product 1 | Gain of | Float |
| Fund product | ||
| 2 | Rate of charge | 0.75 |
| Fund product | ||
| 2 | Amount of purchase | 100 |
| |
Gain of | Float gain |
TABLE 3 product Attribute Table
| id | Product Properties | Enumerated value |
| 3 | Rate of charge | 1.5％ |
| 4 | Rate of charge | 0.75％ |
| 5 | Amount of purchase | 1000 |
| 6 | Amount of purchase | 100 |
| 7 | Gain of | Float gain |
TABLE 4 product Attribute index Table
Step S200, generating a knowledge graph according to the user attribute index and the product attribute index, wherein the knowledge graph comprises user attribute nodes and product attribute nodes;
and associating to the corresponding product attributes according to the user-product name, and constructing a knowledge graph.
Specifically, the user attribute index and the product attribute index include node numbers of the knowledge graph, and step S200 is performed to generate the knowledge graph according to the user attribute index and the product attribute index, where the knowledge graph includes user attribute nodes and product attribute nodes, and the step includes:
generating the user attribute node according to the node number and the user attribute data; and generating the product attribute node according to the node number and the product attribute and enumeration value corresponding to the product name index.
The generating the product attribute node according to the node number, the product attribute and the enumeration value further includes:
and when the product attributes and the enumeration values of different products in the product attribute table are the same, identifying the product attribute nodes generated by the corresponding product attributes and the corresponding enumeration values as the common product attribute nodes.
Generating a plurality of map nodes according to the user attribute numbers in the user attribute indexes, different product attributes in the product attribute indexes and identification numbers of corresponding enumeration values;
specifically, in this embodiment, seven map nodes id1-id7 may be generated according to the user attribute numbers id1 and id2 in the user attribute index, and the identification numbers id3, id4, and id5 of different product attributes and corresponding enumerated values in the product attribute index.
Associating the plurality of map nodes to obtain a knowledge map according to the product name identification in the user attribute table index and different attributes and enumeration values corresponding to the product name identification in the product attribute table index;
specifically, in this embodiment, according to the product name identifier in the user attribute table index and the different attributes and enumerated values corresponding to the product name identifier in the product attribute index, the association between id1 and id5, id3 and id7, and the association between id2 and id4, and the association between id6 and id7 are established, as shown in fig. 4.
Step S300, generating product recommendation data among different users in the user attribute table through the common product attribute nodes in the product attribute nodes.
Because the knowledge graph is not generated according to single product dimension data, but is generated by being disassembled and recombined according to product attributes and enumerated values, namely, the knowledge graph is not limited to product dimensions, but is generated in a combined mode of a plurality of product attributes and enumerated values thereof, different users of the knowledge graph can directly establish the association between the users according to the recombined product attribute indexes, for example, if products purchased by different users contain the same product attributes, the different users directly have the association, namely, the association between user nodes can be established, and then the corresponding product attributes associated between the different users can be recommended to other users through the association between the users in the knowledge graph.
Specifically, in this embodiment, because at this time, through the product attribute scheme, user 1 and user 2 can be associated through the floating profit of node 7, user 1 can be associated to the node of tariff 0.75% through shortest path id1- > id7- > id2- > id4, and thus it can be determined that user 1 may be interested in the product of tariff 0.75 as well. Similarly, the user can also associate with the node of purchase amount 100, so that a novel product 3 of "rate 0.75, purchase amount 1000, floating income" can be designed. However, if the user-product traditional map association method is adopted, since the user 1 and the user 2 purchase different products and cannot refine to specific common attribute nodes (floating income), new financial products cannot be designed.
In this embodiment, in step S300, after generating the product recommendation data between different users in the user attribute table by using the common product attribute node in the product attribute nodes, the method further includes:
and uploading the product recommendation data to a blockchain.
And obtaining corresponding digest information based on the product recommendation data, specifically, obtaining the digest information by hashing the product recommendation data, for example, by using a sha256s algorithm. Uploading summary information to the blockchain can ensure the safety and the fair transparency of the user. The user device may download the summary information from the blockchain to verify that the product recommendation data has been tampered with. The blockchain referred to in this example is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, encryption algorithm, and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
According to the product recommendation method based on the knowledge graph, the user information and the purchased product information are matched from the structured historical data, a plurality of product attribute combinations are obtained according to the purchased product information of different users, then the knowledge graph between the user nodes and the product nodes is established, the recommendation data is generated through the common product attribute nodes in the knowledge graph, and multi-dimensional product recommendation based on the knowledge graph is achieved.
Example two
In the second embodiment of the present application, more accurate recommendation data may be recommended according to weight values between different graph nodes, specifically, please refer to fig. 5, based on the first embodiment, step S110: obtaining the user attribute table, and generating the user attribute index based on the user attribute table, further comprising:
step S115, converting the user attribute data in the user attribute table into numerical values to obtain user attribute values;
the embodiment provides a method for calculating the relation weight from a user to a product attribute.
The specific method comprises the following steps: the personal attributes of the user are replaced with numerical types (except for identification numbers). For example, the gender field "male, female" is replaced with 1 and 0.
Specifically, the example provides two personal attributes of gender and age for verification, and the actual scene may have more attributes of wealth value, industry, whether vehicles exist or not, and the method has high configurability.
Correspondingly, in step S300, generating product recommendation data between different users in the user attribute table through a common product attribute node in the product attribute nodes further includes:
step S310, calculating a weight value between the user attribute node and the common product attribute node according to the user attribute value;
step S320, generating product recommendation data between different users in the user attribute table according to the weight value.
Specifically, referring to fig. 6, in step S310, calculating a weight value between the user attribute node and the common product attribute node according to the user attribute value includes:
step S311, assigning the average value of the user attribute values of the user attribute nodes to the common product attribute node as a common product attribute value;
if the id7 node associates id1 and id2, then take id1 personal attributes (1,32) and (0,26) and take their average (0.5,29) as the attribute value of id 7.
Step S312, calculating a distance between the user attribute value and the common product attribute value by using a euclidean distance calculation formula to obtain a plurality of distance values.
Adopting a Euclidean distance calculation method:
the available distance d1 from id1 to id7 is 3.04, and the distance d2 from id2 to id7 is 3.04.
Step S313, normalizing the plurality of distance values to obtain the weight value.
The two distances are normalized by dx ═ d/(d1+ d2), and the final weight values are both 0.5. The rest of the relationship calculation is the same, and thus a knowledge graph with the weight relationship can be obtained as shown in fig. 7.
At this point, the construction of the knowledge graph based on the structured data is completed, and meanwhile, the adaptivity of the embodiment is that for newly added personal product name list data, the relation weight is updated only according to the above calculation method, as shown in fig. 8.
Because the weighted value is given, the product can be recommended according to the weighted value to obtain more accurate recommendation data, for example, when the weighted value is greater than the threshold value, the direct recommendation data corresponding to the map node is generated.
In the product recommendation method based on the knowledge graph, customer information and purchased product information are matched from structured historical data, a plurality of product attribute combinations are obtained according to product attributes and corresponding enumeration values in the purchased product information of different users, then the knowledge graph between user nodes and product establishment is established, recommendation data is generated through user common attribute nodes in the knowledge graph, and multi-dimensional product recommendation based on the knowledge graph is achieved.
In addition, the embodiment can carry out map building based on the existing structured data, and can avoid the problem of inaccuracy of extraction of unstructured information. Moreover, the proposal also provides a set of self-adaptive atlas updating and weight calculating mode, and the relation weight can be gradually corrected along with the increase of the data volume of the enterprise, thereby realizing recommendation more accurately.
EXAMPLE III
With continued reference to FIG. 9, a schematic block diagram of the program modules of the knowledge-graph based product recommendation apparatus of the present invention is shown. In this embodiment, the knowledge-graph based product recommendation apparatus 20 may include or be divided into one or more program modules, which are stored in a storage medium and executed by one or more processors to implement the present invention and implement the above knowledge-graph based product recommendation method. Program modules referred to herein in the context of embodiments of the present invention are generally intended to be a series of computer program instructions that are capable of performing a specified function and that are more capable of describing, than the program itself, the processes performed by the knowledge-graph based product recommendation device 20 on a storage medium. The following description will specifically describe the functions of the program modules of the present embodiment:
the index module 202 is configured to generate a user attribute index and a product attribute index according to a user attribute table and a product attribute table, where the user attribute table includes historical purchase records corresponding to products in the product attribute table;
the graph module 204 is configured to generate a knowledge graph according to the user attribute index and the product attribute index, where the knowledge graph includes user attribute nodes and product attribute nodes;
and the recommending module 206 is configured to generate product recommendation data between different users in the user attribute table through common product attribute nodes in the product attribute nodes.
Example four
Fig. 10 is a schematic diagram of a hardware architecture of a computer device according to a fourth embodiment of the present invention. In the present embodiment, the computer device 2 is a device capable of automatically performing numerical calculation and/or information processing in accordance with a preset or stored instruction. The computer device 2 may be a rack server, a blade server, a tower server or a rack server (including an independent server or a server cluster composed of a plurality of servers), and the like. As shown in FIG. 10, the computer device 2 includes, but is not limited to, at least a memory 21, a processor 22, a network interface 23, and a knowledge-graph based product recommendation apparatus 20 communicatively coupled to each other via a system bus. Wherein:
in this embodiment, the memory 21 includes at least one type of computer-readable storage medium including a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a Read Only Memory (ROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a Programmable Read Only Memory (PROM), a magnetic memory, a magnetic disk, an optical disk, and the like. In some embodiments, the storage 21 may be an internal storage unit of the computer device 2, such as a hard disk or a memory of the computer device 2. In other embodiments, the memory 21 may also be an external storage device of the computer device 2, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), or the like provided on the computer device 2. Of course, the memory 21 may also comprise both internal and external memory units of the computer device 2. In this embodiment, the memory 21 is generally used for storing an operating system and various application software installed on the computer device 2, such as the program codes of the knowledge-graph based product recommendation apparatus 20 described in the above embodiments. Further, the memory 21 may also be used to temporarily store various types of data that have been output or are to be output.
The network interface 23 may comprise a wireless network interface or a wired network interface, and the network interface 23 is generally used for establishing communication connection between the computer device 2 and other electronic apparatuses. For example, the network interface 23 is used to connect the computer device 2 to an external terminal through a network, establish a data transmission channel and a communication connection between the computer device 2 and the external terminal, and the like. The network may be a wireless or wired network such as an Intranet (Intranet), the Internet (Internet), a Global System of Mobile communication (GSM), Wideband Code Division Multiple Access (WCDMA), a 4G network, a 5G network, Bluetooth (Bluetooth), Wi-Fi, and the like.
It is noted that fig. 10 only shows the computer device 2 with components 20-23, but it is to be understood that not all of the shown components are required to be implemented, and that more or less components may be implemented instead.
In this embodiment, the knowledge-graph based product recommendation device 20 stored in the memory 21 can also be divided into one or more program modules, which are stored in the memory 21 and executed by one or more processors (in this embodiment, the processor 22) to complete the present invention.
EXAMPLE five
The present embodiment also provides a computer-readable storage medium, such as a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, a server, an App application mall, etc., on which a computer program is stored, which when executed by a processor implements corresponding functions. The computer-readable storage medium of the present embodiment is used for storing the product recommendation device 20 based on the knowledge-graph, and when being executed by the processor, the product recommendation method based on the knowledge-graph according to the above embodiments is implemented.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A method for knowledge-graph-based product recommendation, the method comprising:
generating a user attribute index and a product attribute index according to a user attribute table and a product attribute table, wherein the user attribute table comprises product purchase history records of users, and the product attribute table comprises attribute information of corresponding products;
generating a knowledge graph according to the user attribute indexes and the product attribute indexes, wherein the knowledge graph comprises user attribute nodes and product attribute nodes;
and generating product recommendation data among different users in the user attribute table through common product attribute nodes in the product attribute nodes.
2. The knowledge-graph-based product recommendation method of claim 1, wherein generating the user attribute index and the product attribute index from the user attribute table and the product attribute table comprises:
acquiring the user attribute table, and generating the user attribute index based on the user attribute table, wherein the user attribute index comprises user attribute data and a product name index;
and obtaining the product attribute table according to the product name index, and generating the product attribute index based on the product attribute table, wherein the product attribute index comprises a product attribute and an enumeration value corresponding to the product name index.
3. The method of claim 2, wherein the user attribute index and the product attribute index comprise node numbers of the knowledge-graph, and wherein generating the knowledge-graph from the user attribute index and the product attribute index comprises:
generating the user attribute node according to the node number and the user attribute data;
and generating the product attribute node according to the node number and the product attribute and enumeration value corresponding to the product name index.
4. The knowledge-graph-based product recommendation method of claim 3, wherein the product attribute table comprises product attributes and enumerated values for different products, and wherein the generating the product attribute node according to the node number and the product attributes and enumerated values further comprises:
and when the product attributes and the enumeration values of different products in the product attribute table are the same, identifying the product attribute nodes generated by the corresponding product attributes and the corresponding enumeration values as the common product attribute nodes.
5. The knowledge-graph-based product recommendation method of claim 2 or 4, wherein the obtaining the user attribute table and generating the user attribute index based on the user attribute table further comprises:
converting the user attribute data in the user attribute table into numerical values to obtain user attribute values;
correspondingly, the generating of the product recommendation data among different users in the user attribute table through the common product attribute nodes in the product attribute nodes further includes:
calculating a weight value between the user attribute node and the common product attribute node according to the user attribute value;
and generating product recommendation data among different users in the user attribute table according to the weight values.
6. The knowledge-graph-based product recommendation method of claim 5, wherein said calculating a weight value between the user attribute node and the common product attribute node according to the user attribute value comprises:
giving the average value of the user attribute values of the user attribute nodes to the common product attribute node as a common product attribute value;
calculating the distance between the user attribute value and the common product attribute value through an Euclidean distance calculation formula to obtain a plurality of distance values;
normalizing the plurality of distance values to obtain the weight value.
7. The knowledge-graph-based product recommendation method of claim 6, wherein after generating product recommendation data between different users in the user attribute table by common ones of the product attribute nodes, further comprising:
and uploading the product recommendation data to a blockchain.
8. A knowledge-graph based product recommendation device, the knowledge-graph based product recommendation device comprising:
the index module is used for generating a user attribute index and a product attribute index according to a user attribute table and a product attribute table, wherein the user attribute table comprises historical purchase records corresponding to products in the product attribute table;
the knowledge graph module is used for generating a knowledge graph according to the user attribute indexes and the product attribute indexes, and the knowledge graph comprises user attribute nodes and product attribute nodes;
and the recommending module is used for generating product recommending data among different users in the user attribute table through the common product attribute nodes in the product attribute nodes.
9. A computer device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor when executing the computer program performs the steps of the method for knowledge-graph based product recommendation of any of claims 1-7.
10. A computer-readable storage medium having stored thereon a computer program, characterized in that: the computer program when executed by a processor performs the steps of the method for knowledge-graph based product recommendation of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010908112.2A CN111986006A (en) | 2020-09-02 | 2020-09-02 | Product recommendation method and device based on knowledge graph, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010908112.2A CN111986006A (en) | 2020-09-02 | 2020-09-02 | Product recommendation method and device based on knowledge graph, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111986006A true CN111986006A (en) | 2020-11-24 |
Family
ID=73448199
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010908112.2A Pending CN111986006A (en) | 2020-09-02 | 2020-09-02 | Product recommendation method and device based on knowledge graph, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111986006A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113190593A (en) * | 2021-05-12 | 2021-07-30 | 《中国学术期刊（光盘版）》电子杂志社有限公司 | Search recommendation method based on digital human knowledge graph |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100801662B1 (en) * | 2006-08-31 | 2008-02-05 | 에스케이 텔레콤주식회사 | Management system for recommending a goods and recommend method thereof |
| CN108733798A (en) * | 2018-05-17 | 2018-11-02 | 电子科技大学 | A kind of personalized recommendation method of knowledge based collection of illustrative plates |
| CN109241341A (en) * | 2018-05-09 | 2019-01-18 | 上海大学 | A kind of video display of knowledge based map preferentially recommender system and method |
| US20190205964A1 (en) * | 2018-01-03 | 2019-07-04 | NEC Laboratories Europe GmbH | Method and system for multimodal recommendations |
| CN110135890A (en) * | 2019-04-15 | 2019-08-16 | 深圳壹账通智能科技有限公司 | The product data method for pushing and relevant device of knowledge based relation excavation |
| CN110335112A (en) * | 2019-06-18 | 2019-10-15 | 中国平安财产保险股份有限公司 | A kind of Products Show method, apparatus and computer storage medium |
| US20190392330A1 (en) * | 2018-06-21 | 2019-12-26 | Samsung Electronics Co., Ltd. | System and method for generating aspect-enhanced explainable description-based recommendations |
| CN110955834A (en) * | 2019-11-27 | 2020-04-03 | 西北工业大学 | Knowledge graph driven personalized accurate recommendation method |
| CN111159341A (en) * | 2019-12-25 | 2020-05-15 | 中国建设银行股份有限公司 | Information recommendation method and device based on user investment and financing preference |
| CN111242774A (en) * | 2020-01-23 | 2020-06-05 | 中国建设银行股份有限公司 | Bank customer asset map construction method and device |
-
2020
- 2020-09-02 CN CN202010908112.2A patent/CN111986006A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100801662B1 (en) * | 2006-08-31 | 2008-02-05 | 에스케이 텔레콤주식회사 | Management system for recommending a goods and recommend method thereof |
| US20190205964A1 (en) * | 2018-01-03 | 2019-07-04 | NEC Laboratories Europe GmbH | Method and system for multimodal recommendations |
| CN109241341A (en) * | 2018-05-09 | 2019-01-18 | 上海大学 | A kind of video display of knowledge based map preferentially recommender system and method |
| CN108733798A (en) * | 2018-05-17 | 2018-11-02 | 电子科技大学 | A kind of personalized recommendation method of knowledge based collection of illustrative plates |
| US20190392330A1 (en) * | 2018-06-21 | 2019-12-26 | Samsung Electronics Co., Ltd. | System and method for generating aspect-enhanced explainable description-based recommendations |
| CN110135890A (en) * | 2019-04-15 | 2019-08-16 | 深圳壹账通智能科技有限公司 | The product data method for pushing and relevant device of knowledge based relation excavation |
| CN110335112A (en) * | 2019-06-18 | 2019-10-15 | 中国平安财产保险股份有限公司 | A kind of Products Show method, apparatus and computer storage medium |
| CN110955834A (en) * | 2019-11-27 | 2020-04-03 | 西北工业大学 | Knowledge graph driven personalized accurate recommendation method |
| CN111159341A (en) * | 2019-12-25 | 2020-05-15 | 中国建设银行股份有限公司 | Information recommendation method and device based on user investment and financing preference |
| CN111242774A (en) * | 2020-01-23 | 2020-06-05 | 中国建设银行股份有限公司 | Bank customer asset map construction method and device |
Non-Patent Citations (2)
| Title |
|---|
| 东升奇;: "知识图谱驱动的推荐方法及应用研究", 山西科技, no. 02 * |
| 韩慧;: "基于知识图谱的商品推荐系统", 信息通信, no. 06 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113190593A (en) * | 2021-05-12 | 2021-07-30 | 《中国学术期刊（光盘版）》电子杂志社有限公司 | Search recommendation method based on digital human knowledge graph |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107958016B (en) | Function page customization method and application server | |
| CN111966912B (en) | Recommendation method and device based on knowledge graph, computer equipment and storage medium | |
| CN112365987A (en) | Diagnostic data anomaly detection method and device, computer equipment and storage medium | |
| WO2019085463A1 (en) | Department demand recommendation method, application server, and computer-readable storage medium | |
| CN111191454A (en) | Entity matching method and device | |
| CN112507212A (en) | Intelligent return visit method and device, electronic equipment and readable storage medium | |
| CN111882399A (en) | Service information recommendation method, device, computer system and readable storage medium | |
| CN112307747A (en) | Vehicle accessory retrieval method and device, computer equipment and readable storage medium | |
| CN110162540B (en) | Block chain account book data query method, electronic device and storage medium | |
| CN114638501A (en) | Business data processing method and device, computer equipment and storage medium | |
| CN114741384A (en) | Patient information processing method and device and computer readable storage medium | |
| CN113178071B (en) | Driving risk level identification method and device, electronic equipment and readable storage medium | |
| CN111986006A (en) | Product recommendation method and device based on knowledge graph, computer equipment and storage medium | |
| CN112148880A (en) | Customer service dialogue corpus clustering method, system, equipment and storage medium | |
| CN109324963B (en) | Method for automatically testing profit result and terminal equipment | |
| CN113592529B (en) | Potential customer recommendation method and device for bond products | |
| CN113448876B (en) | Service testing method, device, computer equipment and storage medium | |
| CN113283766B (en) | Contract management method, contract management device, electronic equipment and storage medium | |
| CN113537806A (en) | Abnormal user identification method and device, electronic equipment and readable storage medium | |
| CN112733939A (en) | Similarity feature vector construction method and device, electronic equipment and storage medium | |
| CN110442656B (en) | Method and device for determining common association object | |
| CN114911983A (en) | Method and system for providing order number | |
| CN113157890A (en) | Intelligent question and answer method and device, electronic equipment and readable storage medium | |
| CN113421118A (en) | Data pushing method, system, computer equipment and computer readable storage medium | |
| CN117556474A (en) | Data processing method, device, computer equipment and storage medium |
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 |