WO2020114151A1

WO2020114151A1 - Clothing knowledge graph display method and apparatus, and graph server and storage medium

Info

Publication number: WO2020114151A1
Application number: PCT/CN2019/114079
Authority: WO
Inventors: 曹禹; 黄轩; 吕旭涛; 王孝宇
Original assignee: 深圳云天励飞技术有限公司
Priority date: 2018-12-06
Filing date: 2019-10-29
Publication date: 2020-06-11
Also published as: CN109739993A

Abstract

A clothing knowledge graph display method and apparatus, and a graph server and a storage medium. The method comprises: the graph server receives a touch instruction input for clothing nodes comprised in a plurality of commodity nodes in a brand knowledge graph (S11); in response to the touch instruction, the graph server obtains a pre-stored picture storage address, clothing text information, and clothing relationship information from a graph database (S12); the graph server obtains a target picture matching the clothing indicated by the clothing node from a storage server indicated by the picture storage address (S13); the graph server uses the target picture, the clothing text information and the clothing relationship information to generate a clothing knowledge graph (S14); and the graph server outputs the clothing knowledge graph (S15), wherein the target picture is displayed on a node of the clothing knowledge graph. According to the method, the clothing classification and the clothing picture can be conveniently checked on the clothing knowledge graph.

Description

Apparel knowledge graph display method, device, graph server and storage medium

[0001] The present invention relates to the field of picture information technology, and in particular, to a clothing knowledge graph display method, device, graph server, and storage medium.

[0002] This application requires the priority of the Chinese patent application filed on December 6, 2018, with the application number 201811489316.6 and the invention titled "Apparel knowledge graph display method, device, graph server and storage medium", which The entire contents are incorporated by reference in this application.

Background technique

[0003] At present, online shopping has become a consumption trend for people to purchase commodities. On shopping websites, people can easily search for the products they want according to the product classification.

[0004] However, although the classification of commodities on shopping websites is relatively comprehensive, they are usually based on the classification of commodities, and there are many types of classifications and complex standards. For example, for a specific product: apparel, the user cannot view the apparel classification and the detailed sample images of apparel from the existing product categories, which brings great inconvenience to users online shopping.

Summary of the invention

technical problem

Solution to the problem

Technical solution

[0005] In view of the above, it is necessary to provide a clothing knowledge graph display method, device, graph server, and storage medium, which can conveniently view clothing categories and clothing pictures on the clothing knowledge graph.

[0006] A first aspect of the present invention provides a clothing knowledge graph display method, the method including:

[0007] receiving a touch instruction input to a clothing node included in a plurality of commodity nodes in the brand knowledge graph;

[0008] In response to the touch instruction, obtain a pre-stored picture storage address, clothing text information, and clothing relationship information from the graph database;

[0009] obtaining a target picture matching the clothing indicated by the clothing node from the storage server indicated by the picture storage address; [0010] use the target picture, the clothing text information and the clothing relationship information to generate a clothing knowledge map;

[0011] outputting the clothing knowledge graph, wherein the target picture is displayed on a node of the clothing knowledge graph.

[0012] A second aspect of the present invention provides a clothing knowledge graph display device, the device comprising:

[0013] a receiving module, configured to receive a touch instruction input to a clothing node included in a plurality of commodity nodes in the brand knowledge map;

[0014] a first acquiring module, configured to acquire a pre-stored picture storage address, clothing text information, and clothing relationship information from a graph database in response to the touch instruction;

[0015] a second obtaining module, configured to obtain a target picture matching the clothing indicated by the clothing node from the storage server indicated by the image storage address;

[0016] a generating module, configured to generate a clothing knowledge map using the target picture, the clothing text information, and the clothing relationship information;

[0017] The output module is configured to output the apparel knowledge map, wherein the target picture is not displayed on a node of the apparel knowledge map.

[0018] A third aspect of the present invention provides a graph server, the graph server includes a processor and a memory, and the processor is used to implement the clothing knowledge graph display method when executing a computer program stored in the memory.

[0019] A fourth aspect of the present invention provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the clothing knowledge map display method is implemented.

[0020] According to the above technical solution, in the present invention, a touch instruction input to an apparel node included in a plurality of commodity nodes in a brand knowledge graph may be received first; in response to the touch instruction, a pre-stored image storage address is acquired from a graph database , Apparel text information and apparel relationship information; further, from the storage server indicated by the picture storage address, obtain a target picture matching the apparel indicated by the apparel node, and use the target picture and the apparel The text information and the clothing relationship information generate a clothing knowledge map, and finally, the clothing knowledge map can be output, where the target picture is displayed on a node of the clothing knowledge map. It can be seen that through the present invention, the graph database is pre-stored in Picture storage address, when a user needs to query a certain clothing item, he can input a touch instruction by touching the clothing node on the brand knowledge map, and then trigger the graph server to obtain the clothing node address from the storage server indicated by the image storage address The target picture of the indicated clothing match, and then after the clothing knowledge map is generated, the target picture can be displayed on the node of the clothing knowledge map, so that the clothing classification and the clothing picture can be conveniently viewed to meet user needs.

Beneficial effects of invention

Brief description of the drawings

BRIEF DESCRIPTION

[0021] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the embodiments or

5 See the drawings required in the technical description for a brief introduction. Obviously, the drawings in the following description are only embodiments of the present invention. For those of ordinary skill in the art, the premise of not paying creative work Below, other drawings can also be obtained based on the provided drawings.

[0022] FIG. 1 is a flowchart of a preferred embodiment of a clothing knowledge graph display method disclosed in the present invention.

[0023] FIG. 2 is a schematic diagram of a garment knowledge graph structure disclosed in the present invention.

[0024] FIG. 3 is a functional block diagram of a preferred embodiment of a clothing knowledge graph display device disclosed in the present invention.

[0025] FIG. 4 is a schematic structural diagram of a graph server for implementing a preferred embodiment of a clothing knowledge graph display method of the present invention.

Invention Example

Embodiments of the invention

[0026] Please refer to FIG. 1. FIG. 1 is a flowchart of a preferred embodiment of a clothing knowledge graph display method disclosed in the present invention. According to different requirements, the order of the steps in the flowchart can be changed, and some steps can be omitted.

[0027] S11. The graph server receives a touch instruction input to a clothing node included in a plurality of commodity nodes in the brand knowledge graph.

[0028] Among them, the Knowledge Graph (Knowledge Graph/Vault) is also known as the scientific knowledge graph, which is called the knowledge domain visualization or knowledge domain mapping map in the library and information industry. The knowledge graph is a series of various relationships that show the relationship between the development process and structure of knowledge Different graphics, use visualization techniques to describe knowledge resources and their carriers, and mine , Analysis, construction, drawing and display of knowledge and their interrelationships.

[0029] In the embodiment of the present invention, the graph server is a Neo4j server. When a user needs to access the Neo4j server, the user can input the address of the Neo4j server on the local browser, and then open the Neo4j browser of the Neo4j server through the address and browse in Neo4j On the relevant page of the device, the user can enter the pre-registered user name and password to log in to the Neo4j server. After that, users can perform search queries on the Neo4j server, etc.

[0030] In the embodiment of the present invention, the user may first input a certain brand, and the graph server outputs a brand knowledge map according to the certain brand. Further, the user may include a certain node included in multiple commodity nodes in the brand knowledge map Touch (such as an apparel node) to generate a touch instruction, so as to subsequently generate a knowledge graph for the certain node, such as an apparel knowledge graph.

[0031] Wherein, the brand knowledge graph includes multiple commodity nodes, and the multiple commodity nodes may be various commodity nodes, such as apparel nodes, household appliance nodes, fresh fruit nodes, and grain and oil nodes. The user can touch any one of the commodity nodes.

[0032] S12. In response to the touch instruction, the picture server obtains a pre-stored picture storage address, clothing text information, and clothing relationship information from the picture database.

[0033] In the embodiment of the present invention, clothing text information, clothing relationship information, and picture storage addresses (ie, url) are stored in a graph database (ie, Neo4j database), and pictures are stored in a storage server (ie, intranet server)

).

[0034] Among them, the graph database may also be referred to as a graph-oriented database, the corresponding English is Graph database. The basic meaning of a graph database is to store and query data in the form of a "graph" data structure, not a database for storing pictures. The basic storage unit of graph database is: node, relationship, attribute.

[0035] Wherein, the apparel text information may include, but is not limited to, information related to major categories, apparel, fine classification, details, and sample images, and the apparel relationship information may be hierarchical relationships or subordinate relationships. The picture storage address is the address of the server where the picture is stored. In the embodiment of the present invention, the pictures are stored in the intranet server to facilitate picture access, and at the same time, the intranet server built on the intranet can provide more stable picture access services.

[0036] Among them, the data in the graph database comes from major websites (such as Taobao, JD.com, Amazon, Wal-Mart Global Shopping and Wanda Mall, etc.) and professional encyclopedia of clothing knowledge. Data classification in graph database The categories of goods and products can be sorted out according to the information from the major websites. After sorting and summarizing, they are integrated into the knowledge map. There are more than 500 detailed names and 45 clothing types.

[0037] S13. The picture server obtains a target picture matching the clothing indicated by the clothing node from the storage server indicated by the picture storage address.

[0038] Wherein, the target image matching the clothing indicated by the clothing node may be a traditional standard image of the clothing, or a currently popular style image of the clothing, or may be the highest selling current. The pictures of clothing are not limited in the embodiments of the present invention.

[0039] As an optional implementation manner, after step S12, the method further includes:

[0040] acquiring the personal interests and hobbies of the user from the registration information of the user pointed to by the touch instruction;

[0041] according to the personal interests and hobbies, determine the clothing hobby characteristics of the user;

[0042] In step S13, the acquiring, from the storage server indicated by the picture storage address, the target picture matching the clothing indicated by the clothing node includes:

[0043] From the storage server indicated by the picture storage address, obtain a target picture that matches the clothing indicated by the clothing node and that matches the characteristics of the clothing hobby.

[0044] In this optional embodiment, the user needs to register in advance on the graph server, enter the registration information, after the registration is successful, you can obtain a user name and password, and you can log in to the graph server with the user name and password next time. Wherein, the registration information may include but not limited to the user name, user ID number, user home address, user's personal interests and hobbies, etc.

[0045] After the user touches the apparel node, the graph server can obtain the personal interests and hobbies of the user from the registration information of the user of the apparel node pointed to by the touch instruction, and determine the user according to the personal interests and hobbies For example, if the user often wears a red tight skirt, it can be determined that the user's clothing preference characteristics are red and obvious. When the clothing node touched by the user is a skirt, a picture of a red and slim-fitting skirt can be obtained from the storage server.

[0046] As an optional implementation manner, after step S12, the method further includes:

[0047] acquiring multiple types of apparel indicated by the apparel node;

[0048] From the plurality of types of apparel, determine a target apparel whose popularity is greater than a preset popularity threshold within a preset time before the current time;

[0049] In step S13, the server acquires the server from the storage server indicated by the picture storage address The target pictures of costume matching indicated by the decoration node include:

[0050] From the storage server indicated by the picture storage address, obtain a target picture matching the target clothing.

[0051] In this optional embodiment, generally, there are many types of clothing, namely style types, and the popularity of different styles of clothing is different, some styles are more popular, and some styles are outdated, A preset time can be set, for example, within a month before the current time, a preset popularity threshold value such as 100.

[0052] If there are multiple types of apparel indicated by the apparel node touched by the user, the target apparel whose popularity is greater than a preset popularity threshold within a preset time before the current time may be determined from the multiple types of apparel For example, the styles of shirts are slim, loose, professional, casual, etc. You can count the sales volume of various styles of shirts in the most recent month. Generally, the more sales, the more Popularity, the higher the popularity, you can determine the sales within a month as the popularity.

[0053] When the clothing node touched by the user is a shirt, if the popularity of the slim-fit shirt is greater than a preset popularity threshold, a picture of the slim-fit shirt can be obtained from the storage server.

[0054] S14. The image server uses the target picture, the clothing text information, and the clothing relationship information

, Generate clothing knowledge map.

[0055] In the embodiment of the present invention, after acquiring the target picture, the graph server may use the target picture and the stored clothing text information and the clothing relationship information to generate a clothing knowledge map.

[0056] Wherein, the apparel knowledge graph is a tree structure, and the apparel knowledge graph is used to reflect the subordinate relationship and hierarchical structure between apparel. Wherein, the target picture is displayed on the node of the clothing knowledge graph

[0057] Please also refer to FIG. 2, FIG. 2 is a schematic diagram of a clothing knowledge graph structure disclosed in the present invention. Among them, what is described in FIG. 2 is only the structure of the apparel knowledge graph, but the sample diagram is not shown. As shown in Fig. 2, through the apparel knowledge graph, you can clearly see the hierarchical structure and affiliation between the major categories, apparel, fine classification, details, and sample images. After touching the apparel node on the brand knowledge graph, the user can see the sample images corresponding to the classification, fine classification, and details of the apparel from the output apparel knowledge graph, and can also see the relationship between the apparel. The obtained target picture may be displayed on the sample diagram shown in FIG. 2, which is not shown in FIG. [0058] It can be seen from FIG. 2 that the data in the clothing knowledge graph is expressed in a tree structure. There are four layers from top to bottom: the main categories (men's clothing/women's clothing), the names of clothing (such as shirts, suits), the sub-categories (such as sleeve length, placket of clothing) and the details (such as 3/4 sleeves, 3/4 sleeves). Among them, the tree structure can clearly express the affiliation and hierarchical structure, and graphically display the professional knowledge of clothing classification. In addition, in some details, sample drawings of the details are also introduced (each detail can have multiple sample drawings, such as 2-4), which is helpful for assisting users to understand the style of details.

[0059] As an optional implementation manner, after step S14 and before step S15, the method further includes

[0060] If the target picture does not match the node size of the clothing knowledge map, adjust the size of the target picture according to the node size of the clothing knowledge map.

[0061] In this optional embodiment, if the storage space occupied by the target picture is different from the storage space occupied by the nodes of the apparel knowledge map, the target picture and the apparel knowledge map may be determined 'S node size does not match. Wherein, the size of each node of the clothing knowledge map (that is, the size of the circle) may be a preset fixed value, such as a circle with a radius of 2 cm.

[0062] After the clothing knowledge map is generated, if the node size of the target picture and the clothing knowledge map does not match, the graph server may adjust the size of the target picture according to the node size, so that the adjusted The size of the target picture is consistent with the size of the node, for example, the size of the adjusted target picture is the same as the size of the node, or, between the adjusted size of the target picture and the size of the node The difference is less than the preset threshold.

[0063] Optionally, the adjusted target picture may also be placed in a preset position of the node, such as a centered position, which is beneficial for the target picture to be in the middle of the node, improving the overall Beauty

[0064] As an optional implementation manner, after step S14 and before step S15, the method further includes

[0065] If the target picture does not match the node size of the clothing knowledge map, determine the target size of the target node corresponding to the target picture from the preset multiple node sizes according to the size of the target picture ;

[0066] Using the target size, adjust the size of the target node. [0067] In this optional embodiment, if the storage space occupied by the target picture is different from the default storage space occupied by the nodes of the apparel knowledge graph, the target picture and the apparel knowledge may be determined The node size of the graph does not match. Among them, the size of each node of the clothing knowledge map (that is, the size of the circle) can have multiple different options, for example, there are 3 options, a circle with a radius of lcm, a circle with a radius of 1.5cm, and a radius of 2cm circle. A default option may be set, such as a circle with a radius of 1.5 cm, that is, the default storage space of the nodes of the clothing knowledge map is the size occupied by a circle with a radius of 1.5 cm.

[0068] After the clothing knowledge map is generated, if the node size of the target picture and the clothing knowledge map does not match, the graph server may determine the size from the preset multiple node sizes according to the size of the target picture The target size of the target node corresponding to the target picture, and using the target size to adjust the size of the target node so that the adjusted size of the target node is consistent with the size of the target picture, specifically, adjust The size of the target node after that is the same as the size of the target picture, or the difference between the adjusted size of the target node and the size of the target picture is less than a preset threshold. For example: The size of the target picture is a circle with a radius of 2cm, and the node size of the current clothing knowledge map is a circle with a radius of lcm. The preset multiple node sizes include 4 options. A circle with a radius of lcm and a radius of For a 1.5cm circle, a circle with a radius of 2cm and a circle with a radius of 2.5cm, the target node corresponding to the target picture can be adjusted to a circle with a radius of 2cm or a radius of 2.5cm circle, and other nodes except the target node do not need to adjust the size.

[0069] Optionally, the target picture may also be placed in a preset position of the target node after adjustment, such as a centered position, which is advantageous for the target picture to be in the middle of the target node, improving Overall aesthetics.

[0070] S15. The graph server outputs the clothing knowledge graph.

[0071] Wherein, the target picture is displayed on a node of the apparel knowledge graph.

[0072] Where, what type of target picture is obtained, that is, the target picture is displayed on the corresponding node, for example, if the lapel picture is obtained, the lapel picture is displayed on the node corresponding to the lapel, and the other The node does not display pictures, only display clothing text information.

[0073] In the embodiment of the present invention, from the apparel knowledge graph, users can clearly see the connections between different apparel categories, including some attributes they have in common, which is instructive for the training of the algorithm, because Clothing categories with the same fine classification can promote each other in training. [0074] In addition, the apparel knowledge graph integrates a large amount of apparel information from different information sources, so that dispersed apparel professional knowledge can be effectively aggregated.

[0075] As an optional implementation, the method further includes:

[0076] receiving an input parameter setting instruction, the parameter setting instruction carries script information, and the script information is used to indicate that when a node of the clothing knowledge map has a picture address attribute, a picture is displayed on the node of the clothing knowledge map ;

[0077] In response to the parameter setting instruction, add the script information to the script file.

[0078] In this optional embodiment, the Neo4j server has its own graphical interface, but does not support picture display. In the original version, all nodes are displayed in circles, and pictures cannot be displayed. In order to display pictures on the node, you need to change the parameters on the open source Neo4j browser. Specifically, the user can add script information in the coffee script file (that is, the script file) of the Neo4j browser, similar to a javascript statement. The script information specifies that when the node has the im _a g _e _url attribute (that is, the image address attribute), The pictures can be retrieved from the storage server corresponding to the url (namely the picture storage address) for display.

[0079] In addition, optionally, the script information may also specify that the position of the picture in the circle of the node is displayed in the center.

Optionally, in order to enable the Neo4j browser to display the picture in the original picture quality, the script information may also specify that the size of the picture can be adjusted according to the size of the selected node, or the size of the node can be determined according to the size of the picture.

[0080] In the method flow described in FIG. 1, a touch instruction input to an apparel node included in a plurality of commodity nodes in a brand knowledge graph may be received first; in response to the touch instruction, a pre-stored picture storage is acquired from a graph database Address, clothing text information, and clothing relationship information; further, from the storage server indicated by the picture storage address, obtain a target picture matching the clothing indicated by the clothing node, and use the target picture, the The clothing text information and the clothing relationship information generate a clothing knowledge map, and finally, the clothing knowledge map can be output, where the target picture is displayed on a node of the clothing knowledge map. It can be seen that, according to the present invention, a picture storage address is pre-stored in the picture database. When a user needs to query a certain garment, he can input a touch instruction by touching a garment node on the brand knowledge map, and then trigger the graph server to indicate from the picture storage address In the storage server, obtain the target picture matching the clothing indicated by the clothing node, and then after generating the clothing knowledge map, the target picture can be displayed on the node of the clothing knowledge map, which can be convenient View apparel categories and apparel pictures to meet user needs.

[0081] Please refer to FIG. 3, which is a functional module diagram of a preferred embodiment of a clothing knowledge graph display device disclosed in the present invention.

[0082] In some embodiments, the apparel knowledge graph display device runs on a graph server. The may include a plurality of function modules composed of program code segments. The program codes of each program segment in the apparel knowledge graph display device may be stored in a memory and executed by at least one processor to perform some or all of the steps in the apparel knowledge graph display method described in FIG. 1.

[0083] In this embodiment, the apparel knowledge graph display device may be divided into multiple functional modules according to the functions performed by it. The functional module may include: a receiving module 401, a first acquiring module 402, a second acquiring module 403, a generating module 404, and an output module 405. The module referred to in the present invention refers to a series of computer program segments that can be executed by at least one processor and can perform fixed functions, and are stored in a memory. In some embodiments, the functions of each module will be detailed in subsequent embodiments

[0084] The apparel knowledge graph display device includes:

[0085] The receiving module 401 is configured to receive a touch instruction input to a clothing node included in a plurality of commodity nodes in the brand knowledge map;

[0086] In the embodiment of the present invention, the user may first input a certain brand, and the graph server outputs the brand knowledge map according to the certain brand. Further, the user may include a certain node included in multiple commodity nodes in the brand knowledge map Touch (such as an apparel node) to generate a touch instruction, so as to subsequently generate a knowledge graph for the certain node, such as an apparel knowledge graph.

[0087] Wherein, the brand knowledge graph includes multiple commodity nodes, and the multiple commodity nodes may be various commodity nodes, such as apparel nodes, household appliance nodes, fresh fruit nodes, and grain and oil nodes. The user can touch any one of the commodity nodes.

[0088] The first obtaining module 402 is configured to obtain a pre-stored image storage address, clothing text information, and clothing relationship information from the image database in response to the touch instruction;

[0089] In the embodiment of the present invention, clothing text information, clothing relationship information, and picture storage addresses (ie, url) are stored in a graph database (ie, Neo4j database), and pictures are stored in a storage server (ie, intranet server)

). [0090] Among them, the graph database may also be called a graph-oriented/graph-based database, and the corresponding English is Graph database. The basic meaning of a graph database is to store and query data in the form of a "graph" data structure, not a database for storing pictures. The basic storage unit of graph database is: node, relationship, attribute.

[0091] Wherein, the apparel text information may include, but is not limited to, information related to categories, apparel, fine classification, details, and sample images, and the apparel relationship information may be a hierarchical relationship or a subordinate relationship. The picture storage address is the address of the server where the picture is stored. In the embodiment of the present invention, the pictures are stored in the intranet server to facilitate picture access, and at the same time, the intranet server built on the intranet can provide more stable picture access services.

[0092] Among them, the data in the graph database comes from major websites (such as Taobao, JD.com, Amazon, Wal-Mart Global Shopping and Wanda Mall, etc.) and professional encyclopedia of clothing knowledge. The data classification methods and product categories in the graph database can be sorted out according to the information from the major websites. After sorting and summarizing, they are integrated into the knowledge map. There are more than 500 detailed names and 45 clothing types.

[0093] The second obtaining module 403 is configured to obtain a target picture matching the clothing indicated by the clothing node from the storage server indicated by the image storage address;

[0094] Wherein, the target picture matching the clothing indicated by the clothing node may be a traditional standard picture of the clothing, or a currently popular style picture of the clothing, or may be the highest selling current The pictures of clothing are not limited in the embodiments of the present invention.

[0095] The generation module 404 is configured to generate a clothing knowledge map using the target picture, the clothing text information, and the clothing relationship information;

[0096] In the embodiment of the present invention, after acquiring the target picture, the image server may use the target picture and the stored clothing text information and the clothing relationship information to generate a clothing knowledge map.

[0097] Wherein, the apparel knowledge graph is a tree structure, and the apparel knowledge graph is used to reflect the subordinate relationship and hierarchical structure between apparel. Wherein, the target picture is displayed on the node of the clothing knowledge graph

[0098] The output module 405 is configured to output the clothing knowledge map.

[0099] Wherein, the target picture is displayed on the node of the clothing knowledge map.

[0100] Wherein, the apparel knowledge graph is a tree structure, and the apparel knowledge graph is used to reflect the affiliation and hierarchical structure between apparel. [0101] Among them, what type of target picture is acquired, that is, the target picture is displayed on the corresponding node, for example, if the lapel picture is acquired, the lapel picture is displayed on the node corresponding to the lapel, and the other The node does not display pictures, only display clothing text information.

[0102] In the embodiment of the present invention, from the apparel knowledge graph, users can clearly see the connections between different apparel categories, including some attributes they have in common, which is instructive for algorithm training, because Clothing categories with the same fine classification can promote each other in training.

[0103] In addition, the clothing knowledge graph integrates a large amount of clothing information from different information sources, so that dispersed clothing professional knowledge can be effectively aggregated.

[0104] As an optional implementation manner, the first acquiring module 402 is further configured to acquire the personal interests and hobbies of the user from the registration information of the user pointed to by the touch instruction;

[0105] The apparel knowledge graph display device further includes:

[0106] a determining module, configured to determine the clothing and hobby characteristics of the user according to the personal interests and hobbies;

[0107] The second obtaining module 403 is further configured to obtain, from the storage server indicated by the picture storage address, a target picture that matches the clothing indicated by the clothing node and matches the clothing hobby feature.

[0108] As an optional implementation manner, the first acquiring module 402 is further configured to acquire multiple types of apparel indicated by the apparel node;

[0109] The determining module is further configured to determine, from the plurality of types of apparel, target apparel whose popularity is greater than a preset popularity threshold within a preset time before the current time;

[0110] The second obtaining module 403 is further configured to obtain a target picture matching the target clothing from the storage server indicated by the picture storage address.

[0111] As an optional implementation manner, the apparel knowledge graph display device further includes:

[0112] an adjustment module, configured to use the target picture, the clothing text information, and the clothing relationship information to generate a clothing knowledge map in the generation module 404, and the output module 405 to output the clothing knowledge map Before, if the target picture does not match the node size of the clothing knowledge map, the size of the target picture is adjusted according to the node size of the clothing knowledge map.

[0113] As an optional implementation manner, the determination module is further configured to, after the generation module 404 uses the target picture, the clothing text information, and the clothing relationship information to generate a clothing knowledge map, And before the output module 405 outputs the clothing knowledge map, if the target picture and the If the node sizes of the clothing knowledge map do not match, determine the target size of the target node corresponding to the target picture from the preset multiple node sizes according to the size of the target picture;

[0114] The adjustment module is further configured to adjust the size of the target node using the target size.

[0115] As an optional implementation manner, the receiving module 401 is further configured to receive an input parameter setting instruction, where the parameter setting instruction carries script information, and the script information is used to indicate when the apparel knowledge map When the node has a picture address attribute, display a picture on the node of the clothing knowledge map;

[0116] The apparel knowledge graph display device further includes:

[0117] an adding module, configured to add the script information in a script file in response to the parameter setting instruction.

[0118] In the apparel knowledge graph display device described in FIG. 3, a picture storage address is pre-stored in the graph database. When a user needs to query a certain apparel, the user may input a touch instruction by touching an apparel node on the brand knowledge graph, Then, the graph server is triggered to obtain a target picture matching the clothing indicated by the clothing node from the storage server indicated by the image storage address, and then, after generating the clothing knowledge map, the node of the clothing knowledge map can be displayed Target pictures, so that you can easily view clothing categories and clothing pictures to meet user needs.

[0119] As shown in FIG. 4, FIG. 4 is a schematic structural diagram of a graph server according to a preferred embodiment of a method for displaying a clothing knowledge graph of the present invention. The graph server 5 includes a memory 51, at least one processor 52, a computer program 53 stored in the memory 51 and executable on the at least one processor 52, and at least one communication bus 54.

[0120] Persons skilled in the art may understand that the schematic diagram shown in FIG. 5 is only an example of the graph server 5, and does not constitute a limitation on the graph server 5, and may include more or fewer components than illustrated. , Or combine some components, or different components, for example, the graph server 5 may further include an input and output device, a network access device, a bus, and the like.

[0121] The graph server 5 is a Neo4j server.

[0122] The at least one processor 52 may be a central processing unit (Central Processing Unit, CPU)

, Can also be other general-purpose processors, digital signal processors (Digital Signal Processor, DSP)

, Application Specific Integrated Circuit (ASIC), ready-made programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware component, etc. The processor 52 may be a microprocessor or the The processor 52 may also be any conventional processor, etc. The processor 52 is the control center of the graph server 5 and connects various parts of the entire graph server 5 by using various interfaces and lines.

[0123] The memory 51 may be used to store the computer program 53 and/or module/unit, the processor 52 executes or executes the computer program and/or module/unit stored in the memory 51, and calls The data stored in the memory 51 realizes various functions of the graph server 5. The memory 51 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, application programs required by at least one function (such as a sound playback function, an image playback function, etc.), etc.; the storage data area may Store data (such as audio data, phone book, etc.) created according to the usage of the graph server 5 and so on. In addition, the memory 51 may include a high-speed random access memory, and may also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (Smart Media Card, SMC), and Secure Digital (Secure Digital, SD) card, flash memory card (Flash Card), at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0124] With reference to FIG. 1, the memory 51 in the graph server 5 stores multiple instructions to implement an expression detection method, and the processor 52 may execute the multiple instructions to implement the above clothing knowledge map display method

[0125] In the graph server 5 described in FIG. 4, a touch instruction input to a clothing node included in a plurality of commodity nodes in the brand knowledge map may be received first; in response to the touch instruction, a pre-stored picture is obtained from a graph database Storage address, clothing text information, and clothing relationship information; further, from the storage server indicated by the picture storage address, obtain a target picture matching the clothing indicated by the clothing node, and use the target picture, Generating the apparel knowledge graph by using the apparel text information and the apparel relationship information, and finally, outputting the apparel knowledge graph, where the target picture is displayed on a node of the apparel knowledge graph. It can be seen that, according to the present invention, a picture storage address is pre-stored in the picture database. When a user needs to query a certain garment, he can input a touch instruction by touching a garment node on the brand knowledge map, and then trigger the graph server to indicate from the picture storage address In the storage server, obtain the target picture matching the clothing indicated by the clothing node, and then after generating the clothing knowledge map, the target picture can be displayed on the node of the clothing knowledge map, so that the clothing classification can be conveniently viewed And clothing pictures to meet user needs.

[0126] If the module/unit integrated in the graph server 5 is implemented in the form of a software functional unit and acts as an independent When the product is sold or used, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention can implement all or part of the processes in the methods of the above embodiments, and can also be completed by a computer program instructing relevant hardware. The computer program can be stored in a computer-readable storage medium. When the program is executed by the processor, the steps of the foregoing method embodiments may be implemented. Wherein, the computer program includes computer program code, and the computer program code may be in a source code form, an object code form, an executable file, or some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM, Read-Only Memory) , Random Access Memory (RAM, Random Access Memory), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in jurisdictions. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media Does not include electrical carrier signals and telecommunications signals.

Claims

[Claim 1] A clothing knowledge graph display method, characterized in that the method comprises:

Receive touch instructions for clothing nodes included in multiple commodity nodes in the brand knowledge graph;

In response to the touch instruction, obtain a pre-stored picture storage address, clothing text information, and clothing relationship information from the picture database;

Obtaining a target picture matching the clothing indicated by the clothing node from the storage server indicated by the picture storage address;

Use the target picture, the clothing text information, and the clothing relationship information to generate a clothing knowledge map;

Outputting the clothing knowledge map, wherein the target picture is displayed on a node of the clothing knowledge map.

[Claim 2] The method according to claim 1, wherein the apparel knowledge graph is a tree structure, and the apparel knowledge graph is used to reflect the affiliation and hierarchy between apparel.

[Claim 3] The method according to claim 1, wherein after the pre-stored picture storage address, clothing text information, and clothing relationship information are acquired from the graph database, the method further includes:

Acquiring the personal interests and hobbies of the user from the registration information of the user pointed to by the touch instruction; determining the clothing and hobby characteristics of the user according to the personal interests and hobbies;

The obtaining, from the storage server indicated by the picture storage address, the target picture matching the clothing indicated by the clothing node includes:

From the storage server indicated by the picture storage address, obtain a target picture that matches the clothing indicated by the clothing node and matches the characteristics of the clothing hobby.

[Claim 4] The method according to claim 1, characterized in that after the pre-stored picture storage address, clothing text information and clothing relationship information are acquired from the graph database, the method further comprises:

Acquiring multiple types of clothing indicated by the clothing node;

From the plurality of types of clothing, determine the popularity within a preset time before the current time Target clothing greater than the preset popularity threshold;

Obtain a target picture matching the target clothing from the storage server indicated by the picture storage address.

[Claim 5] The method according to any one of claims 1 to 4, wherein after using the target picture, the clothing text information, and the clothing relationship information to generate a clothing knowledge map, And before outputting the clothing knowledge map, the method further includes: if the node size of the target picture does not match the clothing knowledge map, adjusting the target picture's size according to the node size of the clothing knowledge map size.

[Claim 6] The method according to any one of claims 1 to 4, characterized in that after using the target picture, the clothing text information, and the clothing relationship information to generate a clothing knowledge map, And before outputting the clothing knowledge map, the method further includes: if the node sizes of the target picture and the clothing knowledge map do not match, according to the size of the target picture, from a plurality of preset node sizes In determining the target size of the target node corresponding to the target picture;

Using the target size, adjust the size of the target node.

[Claim 7] The method according to any one of claims 1 to 4, characterized in that the method further comprises:

Receiving an input parameter setting instruction, where the parameter setting instruction carries script information, and the script information is used to indicate that when a node of the clothing knowledge map has a picture address attribute, a picture is displayed on the node of the clothing knowledge map;

In response to the parameter setting instruction, add the script information to the script file.

[Claim 8] A clothing knowledge graph display device, characterized in that the device comprises:

A receiving module, configured to receive a touch instruction input for clothing nodes included in multiple commodity nodes in the brand knowledge graph;

A first obtaining module, configured to obtain a pre-stored image storage address, clothing text information, and clothing relationship information from the picture database in response to the touch instruction; A second obtaining module, configured to obtain a target picture matching the clothing indicated by the clothing node from the storage server indicated by the image storage address; a generating module, configured to use the target picture and the clothing text Information and the clothing relationship information to generate a clothing knowledge map;

The output module is configured to output the apparel knowledge graph, wherein the target picture is displayed on a node of the apparel knowledge graph.

[Claim 9] The apparel knowledge graph display device according to claim 8, wherein: the first acquisition module is further used to acquire the personal interests and hobbies of the user from the registration information of the user pointed to by the touch instruction; Wherein, the apparel knowledge graph display device further includes a determination module, the determination module is configured to determine the apparel hobby characteristics of the user according to the personal hobbies;

The second obtaining module is further used to obtain, from the storage server indicated by the picture storage address, a target picture matching the clothes indicated by the clothes node and conforming to the characteristics of the clothes hobby.

[Claim 10] The apparel knowledge graph display device according to claim 8, wherein the first acquiring module is further used to acquire a plurality of types of apparel indicated by the apparel node; the determining module further For determining the target apparel whose popularity is greater than a preset popularity threshold within a preset time before the current time from the plurality of types of apparel; the second obtaining module is also used to determine the address from the picture storage address In the indicated storage server, obtain a target picture matching the target clothing.

[Claim 11] The apparel knowledge graph display device according to any one of claims 8 to 10, wherein the apparel knowledge graph display device further includes an adjustment module, the adjustment module The picture does not match the node size of the clothing knowledge map, and the size of the target picture is adjusted according to the node size of the clothing knowledge map.

[Claim 12] The apparel knowledge graph display device according to any one of claims 8 to 10, characterized in that the determination module is further used to determine the size of the node between the target picture and the apparel knowledge graph. Matching, determining the target size of the target node corresponding to the target picture from the preset multiple node sizes according to the size of the target picture; the adjustment module also uses In order to use the target size, the size of the target node is adjusted.

[Claim 13] The apparel knowledge graph display device according to any one of claims 8 to 10, wherein the receiving module is further configured to receive an input parameter setting instruction, and the parameter setting instruction carries a script Information, the script information is used to indicate that when a node of the apparel knowledge graph has a picture address attribute, display a picture on the node of the apparel knowledge graph; the apparel knowledge graph display device further includes an adding module for responding to the The parameter setting instruction adds the script information to the script file.

[Claim 14] A graph server, characterized in that the graph server includes a processor and a memory, and the processor is used to execute a computer program stored in the memory to implement any one of claims 1 to 7. Display method of clothing knowledge map.

[Claim 15] A computer-readable storage medium, characterized in that the computer-readable storage medium stores at least one instruction, and when the at least one instruction is executed by a processor, it is implemented as any one of claims 1 to 7. The display method of the clothing knowledge graph.