CN107464162B

CN107464162B - Commodity association method and device and computer-readable storage medium

Info

Publication number: CN107464162B
Application number: CN201710629742.4A
Authority: CN
Inventors: 宋翔宇; 江启泉
Original assignee: Tencent Technology Shenzhen Co Ltd
Current assignee: Tencent Technology Shenzhen Co Ltd
Priority date: 2017-07-28
Filing date: 2017-07-28
Publication date: 2022-12-30
Anticipated expiration: 2037-07-28
Also published as: CN107464162A

Abstract

The invention discloses a commodity association method, a commodity association device and a storage medium, and belongs to the field of information processing. The method comprises the following steps: acquiring commodity information from a plurality of E-commerce platforms to obtain the commodity information of a plurality of commodities, wherein the commodity information comprises at least one of primary attribute information, secondary attribute information and a commodity display diagram; for each commodity in the plurality of commodities, generating a commodity identification string of the commodity according to a preset generation rule based on commodity information of the commodity, wherein the commodity identification string is used for uniquely identifying the commodity; and matching the commodity identification strings of the plurality of commodities, and associating the same or similar commodities in the plurality of commodities based on the matching result. The commodity is identified by generating the commodity identification string, and the commodity is identified by the commodity identification string, so that a rule for automatically identifying and identifying the commodity is constructed, manual intervention in the association process is avoided, and the flexibility and the association efficiency of commodity association are improved.

Description

Commodity association method and device and computer-readable storage medium

Technical Field

The present invention relates to the field of information processing, and in particular, to a method and an apparatus for associating commodities, and a computer-readable storage medium.

Background

At present, a plurality of e-commerce platforms appear in the e-commerce field, different e-commerce platforms can sell the same commodity, and the price of the same commodity on different e-commerce platforms can be different. Therefore, when a user purchases at the e-commerce platform, the user usually wants to know the price of the same item on different e-commerce platforms, so as to purchase the item at a more favorable price. In order to provide the price of the same commodity on different e-commerce platforms for the user, the same commodity on different e-commerce platforms needs to be associated in advance, that is, the commodity information of the same commodity on different e-commerce platforms is combined into a commodity group.

In the related art, a commodity association method is provided, including: the method comprises the steps of firstly obtaining commodity information of all commodities from a plurality of E-commerce platforms to obtain the commodity information of a plurality of commodities. Since descriptions of different e-commerce platforms for the same commodity may be different, the same commodity needs to be determined from the plurality of commodities according to the obtained commodity information. Specifically, for the products having a standardized structure among the plurality of products, that is, the products whose product manufacturers have provided product identifiers such as standard serial numbers and product numbers for unique identification, the same products can be identified from the plurality of products by matching the product identifiers and the identified same products can be associated with each other, whereas for the remaining products having no standardized structure, it is necessary to manually determine which of the same products are the same products and which of the same products are not the same products and associate the same products with each other among the remaining products.

In the related art, the commodities without standardized structures need to be associated in a manual mode, so that manual intervention is needed in the commodity association process, the flexibility is low, and the commodity association efficiency is influenced.

Disclosure of Invention

In order to solve the problems that the commodity association process needs manual intervention, the flexibility is low, and the commodity association efficiency is influenced in the related technology, the embodiment of the invention provides a commodity association method and a commodity association device. The technical scheme is as follows:

in a first aspect, a method for associating commodities is provided, and the method includes:

acquiring commodity information from a plurality of E-commerce platforms to obtain the commodity information of a plurality of commodities, wherein the commodity information comprises at least one of main attribute information, secondary attribute information and a commodity display diagram, the main attribute information is information which is set by a commodity manufacturer and is used for uniquely identifying the commodities, and the secondary attribute information is specification parameters which are used for describing the commodities except the main attribute information;

for each commodity in the plurality of commodities, generating a commodity identification string of the commodity according to a preset generation rule based on commodity information of the commodity, wherein the commodity identification string is used for uniquely identifying the commodity;

and matching the commodity identification strings of the commodities, and associating the same or similar commodities in the commodities based on the matching result.

In a second aspect, there is provided an article association apparatus, the apparatus comprising:

the system comprises a first acquisition module, a second acquisition module and a display module, wherein the first acquisition module is used for acquiring commodity information from a plurality of E-commerce platforms to obtain the commodity information of a plurality of commodities, the commodity information comprises at least one of main attribute information, secondary attribute information and a commodity display image, the main attribute information is information which is set by a commodity manufacturer and is used for uniquely identifying the commodities, and the secondary attribute information is specification parameters which are used for describing the commodities except the main attribute information;

the generation module is used for generating a commodity identification string of each commodity in the plurality of commodities according to a preset generation rule based on commodity information of the commodity, wherein the commodity identification string is used for uniquely identifying the commodity;

and the association module is used for matching the commodity identification strings of the commodities and associating the same or similar commodities in the commodities based on the matching result.

In a third aspect, there is provided a server comprising a processor and a memory, wherein at least one instruction, at least one program, set of codes, or set of instructions is stored in the memory, and the instruction, the program, the set of codes, or the set of instructions is loaded and executed by the processor to implement the article association method of the first aspect.

In a fourth aspect, there is provided a computer readable storage medium having stored therein at least one instruction, at least one program, set of codes, or set of instructions, which is loaded and executed by a processor to implement the article association method of the first aspect.

The technical scheme provided by the embodiment of the invention has the following beneficial effects:

in the embodiment of the invention, as the commodity information comprises at least one of the primary attribute information, the secondary attribute information and the commodity display image, the primary attribute information is information which is set by a commodity manufacturer and is used for uniquely identifying a commodity, and the secondary attribute information refers to specification parameters which are used for describing the commodity except the primary attribute information, the commodity identification string generated based on at least one of the primary attribute information, the secondary attribute information and the commodity display image can flexibly and accurately identify the commodity, the commodity is identified by generating the commodity identification string, the commodity is identified by the commodity identification string, and a rule for automatically identifying and identifying the commodity is established.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the description below are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.

Fig. 1A is a flowchart of a method for associating commodities, according to an embodiment of the present invention;

fig. 1B is a schematic diagram of a product detail page provided in an embodiment of the present invention;

FIG. 2A is a flow chart of another merchandise association method according to an embodiment of the present invention;

FIG. 2B is a flow chart of another merchandise association method according to an embodiment of the present invention;

FIG. 2C is a flow chart of another merchandise association method according to an embodiment of the present invention;

fig. 3A is a block diagram of a product association apparatus according to an embodiment of the present invention;

FIG. 3B is a block diagram of another merchandise association device according to an embodiment of the invention;

FIG. 3C is a block diagram of another merchandise association apparatus according to an embodiment of the invention;

FIG. 3D is a block diagram of another merchandise association apparatus according to an embodiment of the invention;

fig. 4 is a schematic structural diagram of a server 400 according to an embodiment of the present invention;

fig. 5 is a schematic structural diagram of a terminal 500 according to an embodiment of the present invention.

Detailed Description

To make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

Before explaining the embodiments of the present invention in detail, an application scenario of the embodiments of the present invention will be explained.

The embodiment of the invention is applied to the scene that the user purchases the commodities on the E-commerce platform, and when the user purchases the commodities, the user usually wants to know the prices, the stocks or other commodity information of the same or similar commodities on different E-commerce platforms so as to purchase the commodities at a more favorable price or purchase the commodities in time. For this reason, it is also necessary to associate the same or similar goods of different e-commerce platforms.

For example, by associating a certain commodity of different e-commerce platforms, when a user uses a terminal to view the commodity on any e-commerce platform, the terminal can acquire and display the price of the commodity on other e-commerce platforms to the user, so that the user can select the e-commerce platform with a lower selling price to purchase the commodity. Alternatively, the terminal may show the price and stock of the product on other e-commerce platforms to the user so that the user comprehensively considers which e-commerce platform's associated product is purchased.

For another example, the user may also subscribe the same or similar commodities associated with different e-commerce platforms through the terminal, and when the user subscribes to a certain associated same or similar commodity, the terminal may display a reminding message to the user when the price of any one of the associated same or similar commodities is lower than a preset threshold value, so as to remind the user that the commodity is reduced in price and is low in price, and the user can purchase the commodity. The preset threshold may be a certain psychological threshold set by the user and acceptable for the commodity, or a threshold set by the terminal in a default manner.

Next, an environment in which the embodiment of the present invention is implemented will be described.

The commodity association method provided by the embodiment of the invention can be applied to a terminal and/or a server, wherein the terminal can be a mobile phone, a tablet computer, a computer and the like, and the server can be a background server of certain associated software or other servers.

For example, the commodity association method can be applied to association software installed in a terminal, and the association software is used for associating the same or similar commodities of different e-commerce platforms and displaying information such as prices, stocks and the like of the same or similar commodities on different e-commerce platforms to a user. Moreover, the association of the associated software to the commodity can be realized through the interaction of a terminal for installing the associated software and a background server of the associated software.

Next, a background server that uses a server as an execution subject and uses the server as associated software installed in a terminal will be taken as an example, and details of the commodity association method provided by the embodiment of the present invention will be described with reference to the drawings. Fig. 1A is a flowchart of a method for associating a product according to an embodiment of the present invention, and as shown in fig. 1A, the method may include the following steps:

step 101: and acquiring commodity information from the E-commerce platforms to obtain the commodity information of a plurality of commodities, wherein the commodity information comprises at least one of primary attribute information, secondary attribute information and a commodity display diagram.

The e-commerce platforms refer to platforms capable of selling goods through a network, and may specifically include an e-commerce website, social software, instant messaging software, or forum, and the like.

The primary attribute information is information which is set by a commodity manufacturer and is used for uniquely identifying a commodity, and the primary attribute information can include a commodity number, a commodity name, a brand name or a commodity model and the like, and the secondary attribute information is specification parameters which are used for describing the commodity except the primary attribute information.

Specifically, the product information may include a first title, a specification parameter, and a product display diagram, where the first title, the specification parameter, and the product display diagram may be obtained from a product detail page or product recommendation information of a corresponding product, and the primary attribute information and the secondary attribute information are included in the first title and the specification parameter.

For convenience of understanding, the following description will take the first title as the title of the product detail page, and the specification parameters include, but are not limited to, a product number, a product name, a brand name, a product model, a color, a size, a material, and the like.

Fig. 1B is a schematic diagram of a product detail page according to an embodiment of the present invention, as shown in fig. 1B, where information in a box above price information is a first title, and the first title may include information of a main attribute and/or a secondary attribute, and may also include other description information besides the main attribute and the secondary attribute. In addition, the item detail page may further include specification parameters and an item display diagram.

The obtaining of the commodity information from the plurality of e-commerce platforms may include the following two implementation manners:

the first implementation mode comprises the following steps: when an initialization instruction of the association database is received, commodity information is obtained from each e-commerce platform in the e-commerce platforms, commodity information of a plurality of commodities is obtained, and the commodity information of the commodities is stored in the association database.

The association database is used for storing commodity information of the same or similar commodities associated from different e-commerce platforms, for example, the association database may store a plurality of commodity groups, each commodity group includes commodity information of a plurality of associated commodities, and the commodities are the same or similar commodities of different e-commerce platforms.

In practical application, in order to provide information such as prices or stocks of a certain commodity on different e-commerce platforms to a user quickly, a correlation database is usually required to be established as starting data, and when information such as prices or stocks of a certain commodity on different e-commerce platforms needs to be determined, the correlated commodity of different e-commerce platforms, which is the same as or similar to the commodity, can be directly searched from the correlation database.

The initialization instruction of the association database is used for instructing to initialize the association database, that is, storing data into the association database, and the initialization instruction of the association database can be sent by a terminal which installs the association software. For example, the terminal may send an initialization instruction of the association database to the server through the association software when the association software is installed and started for the first time.

Specifically, the operation of acquiring the commodity information from each of the plurality of e-commerce platforms may include the following two operations:

1) And acquiring commodity information of all commodities in each E-commerce platform.

That is, for each of the plurality of e-commerce platforms, the merchandise information for all of the merchandise sold in the e-commerce platform may be crawled. Specifically, for each crawled commodity, a first title, specification parameters and a commodity display diagram can be extracted from a commodity detail page of the commodity as commodity information of the commodity.

It should be noted that, in the method 1), since the amount of the acquired data is large, and some crawled goods may not be paid much attention to by the user, that is, the goods information of the goods is likely not to be used by the user, a large amount of bandwidth and storage space of the server may be consumed.

2) And acquiring commodity information of all commodities in the preset edition block of each e-commerce platform.

The preset layout blocks are preset layout blocks with a high user attention, for example, hot layout blocks or promotion layout blocks of each e-commerce platform can be used, the hot layout blocks are displayed at obvious positions such as a homepage of the e-commerce platform and have a large user click amount, and the promotion layout blocks are used for displaying promotional commodities such as discounted commodities and price-reduced commodities.

Due to the fact that the attention of the user of the preset plate is high, the commodity information of the commodity needed by the user can be obtained by crawling the commodity information of all commodities in the preset plate, the accuracy of obtaining the commodity information can be improved, and the bandwidth and the storage space of the server are saved.

In another embodiment, the server may further obtain commodity information of all commodities in a preset section of the target e-commerce platform, and then obtain commodity information of commodities identical or similar to the commodities in the preset section of the target e-commerce platform from other e-commerce platforms according to all commodities in the preset section of the target e-commerce platform. Wherein, the target e-commerce platform can be any one of the plurality of e-commerce platforms.

The second implementation mode comprises the following steps: when a search instruction for a target commodity is received, acquiring commodity information of the target commodity, wherein the target commodity is a commodity in any one of the E-commerce platforms; generating a search keyword of the target commodity based on the commodity information of the target commodity; and searching in the E-commerce platforms based on the search keyword of the target commodity to obtain commodity information of the commodities, wherein the commodity information of the commodities comprises the commodity information of the target commodity.

The search instruction for the target commodity is used for instructing to search the commodity information of the target commodity from the plurality of e-commerce platforms, and the search instruction can be sent by the terminal. For example, the association software may provide an association icon in a product detail page of a target product, when a user uses a terminal to view the target product in the product detail page of the target product, if the user wants to associate a product that is the same as or similar to the target product in different e-commerce platforms, the association icon may be triggered, and when the terminal detects a trigger instruction of the user on the association icon, a search instruction for the target product may be sent to a service, so as to associate the searched product that is the same as or similar to the target product.

That is, in addition to acquiring the commodity information of a plurality of commodities by initializing the association database, the server can also provide a feedback mechanism for user participation, and through the target commodity provided by the user, the server automatically goes to each e-commerce platform to search the commodity information of the commodities which are the same as or similar to the target commodity and perform association. In another embodiment, the second manner may also be performed by the terminal.

When a search instruction for a target commodity is received, the commodity information of the target commodity can be acquired from the commodity detail page of the target commodity. When the search keyword for the target product is generated based on the product information for the target product, the search keyword for the target product may be generated based on at least one of the primary attribute information, the secondary attribute information, and the product display map included in the product information for the target product.

The operation of searching in the plurality of e-commerce platforms based on the search keyword of the target commodity to obtain the commodity information of the plurality of commodities may include: for each e-commerce platform in the plurality of e-commerce platforms, sending a search request to the e-commerce platform based on the search keyword so as to enable the e-commerce platform to display a search result page of the target commodity, wherein the search result page of the target commodity comprises search titles of a plurality of search results; selecting the search titles of N search results ranked at the top from the search titles of the plurality of search results, wherein N is a positive integer; and acquiring commodity information of N commodities corresponding to the N search results based on the link addresses corresponding to the search titles of the selected N search results.

The value of N may be set by default by the server or by the user, which is not limited in the embodiment of the present invention.

Further, when the server has completed initialization of the association database, and the association database includes a plurality of product groups, each product group includes product information of a plurality of products belonging to the same or similar products and corresponding product identification strings associated from different e-commerce platforms, when a search instruction for a target product is received, the server may further generate a product identification string of the target product based on the product information of the target product, then match the product identification string of the target product with the product identification strings of the plurality of products included in each of the plurality of product groups stored in the association database, respectively, when the product identification string of any product in the target product group matches the product identification string of the target product, the target product group may be determined as the product group corresponding to the target product, the target product group is any one of the plurality of product groups, and when the product identification strings of the product included in any one of the plurality of product groups do not match the product identification strings of the target product, the step of searching for a product in the plurality of product groups based on the keyword of the target product search platforms is performed.

That is, when a search instruction for a target commodity is received, the same or similar commodities associated with the target commodity may be determined by searching the association database, and when the same or similar commodities are not searched in the association database, the same or similar commodities may be searched from the plurality of e-commerce platforms.

It should be noted that, the method for generating the product identification string of the target product based on the product information of the target product is similar to the method for generating the product identification string of the product based on the product information of the product according to the preset generation rule in the following step 102, and the specific implementation process will be described in detail in the following

steps

102 and 103 in similar to the method for matching the product identification string of the target product with the product identification strings of a plurality of products included in each of a plurality of product groups stored in the association database in the following step 103, which is not repeated herein.

Furthermore, considering that the sensitivities of each e-commerce platform to the search keywords may be different, in order to meet the hit rate of the search keywords on the corresponding e-commerce platform, a search keyword generation rule of each e-commerce platform may be predetermined, and then the search keywords are generated according to the search keyword generation rule of the corresponding e-commerce platform, so that accurate search can be performed on the corresponding e-commerce platform in the following.

Specifically, generating the search keyword of the target product based on the product information of the target product may further include: for each e-commerce platform of the plurality of e-commerce platforms, acquiring commodity information of M commodities in the e-commerce platform and search titles of the M commodities in the e-commerce platform, wherein M is a positive integer; fitting the commodity information of the M commodities with the search titles of the M commodities in the E-commerce platform respectively; determining a search keyword generation rule of the E-commerce platform based on the fitting result; accordingly, the generating of the search keyword for the target item based on the item information for the target item includes: and for each e-commerce platform of the plurality of e-commerce platforms, generating a search keyword of the target commodity in the e-commerce platform according to the commodity information of the target commodity and the search keyword generation rule of the e-commerce platform.

The step of fitting the commodity information of the M commodities with the search titles of the M commodities in the e-commerce platform respectively refers to the step of comparing the commodity information of each commodity in the M commodities with the search titles in the e-commerce platform, determining a corresponding rule for generating the commodity information of the commodities into the search titles, further generating the search title rule according to the M commodities, and comprehensively determining the search keyword generation rule.

The value of M may be configured in advance, for example, M may be 100, 150, or 200. The M commodities may be pre-configured or randomly selected, which is not limited in the embodiment of the present invention. The search title of each commodity in the e-commerce platform refers to a title corresponding to a search result displayed in a search page when the commodity is searched on the search page of the e-commerce platform.

Further, when searching is carried out in a plurality of E-commerce platforms based on the search keywords of the target commodity, if no search result is obtained after searching, searching can be carried out again after the search keywords are reduced. Moreover, since the search results are more blurred due to the reduction of the keywords, and more search results are generated, the value of N may be appropriately reduced or increased when the top N search results are extracted from the search results.

Step 102: and for each commodity in the plurality of commodities, generating a commodity identification string of the commodity according to a preset generation rule based on the commodity information of the commodity, wherein the commodity identification string is used for uniquely identifying the commodity.

That is, a product identification string corresponding to each product may be generated according to a preset generation rule based on product information of each product, so as to identify the product through the corresponding product identification string, so as to identify the product according to the product identification string in the following.

The generation of the commodity identification string of the commodity according to the preset generation rule based on the commodity information of the commodity can include the following three implementation modes:

the first implementation mode comprises the following steps: when the commodity information of the commodity includes the main attribute information, a commodity identification string of the commodity is generated based on the main attribute information.

The main attribute information may be information for uniquely identifying a commodity, which is set by a commodity manufacturer such as a commodity number, a commodity name, a brand name, or a commodity model.

In practical application, the commodity information of the commodity may include a first title, a specification parameter and a commodity display diagram, when the commodity identification string of the commodity is generated based on the commodity information of the commodity, it may be determined whether the first title and the specification parameter include main attribute information, and if the main attribute information is included, the commodity identification string of the commodity may be generated based on the main attribute information.

Specifically, when the product identification string of the product is generated based on the master attribute information, the product identification string may be generated in a manner that the product item number > the product name > the brand name + the product model is prioritized, that is, if the master attribute information includes the product item number, the product item number is used as the product identification string of the product, if the master attribute information does not include the product identification string but includes the product name, the product name is used as the product identification string of the product, and if the master attribute information does not include the product item number and the product name but includes the brand name and the product model, the brand name and the product model are combined, and the combined information is used as the product identification string of the product.

The second implementation mode comprises the following steps: when the commodity information of the commodity does not include the primary attribute information and includes the secondary attribute information, a commodity identification string of the commodity is generated based on the secondary attribute information.

The secondary attribute information refers to specification parameters for describing the commodity except the primary attribute information, and may be, for example, color, size, material, style, or date of manufacture.

In practical application, the commodity information of the commodity may include a first title, a specification parameter and a commodity display diagram, when the commodity identification string of the commodity is generated based on the commodity information of the commodity, it may be determined whether the first title and the specification parameter include main attribute information, if not, it may be determined whether the first title and the specification parameter include secondary attribute information, and if so, the commodity identification string of the commodity may be generated based on the secondary attribute information.

Wherein generating the product identification string of the product based on the attribute information comprises: and when the commodity information of the commodity comprises a first title, generating a commodity identification string of the commodity based on the first title, the first participle set and the second participle set. The first participle set is determined based on secondary attribute information included in the commodity information of the commodities, and the second participle set is determined based on a first title and secondary attribute information included in the selected commodity information after the commodity information not including the primary attribute information is selected from the commodity information of the commodities.

Specifically, the implementation process of generating the product identification string of the product based on the first title, the first participle set and the second participle set may include the following steps 1) to 3):

1) And performing word segmentation processing on the first title included in the commodity information of the commodity to obtain a plurality of words.

For example, assume that the article is a garment and the first title of the article is: the ink-wash printed T-shirt 2017 is a new summer round-neck T-shirt with male short-sleeves HNTBJ2V020A with white patterns (20) 175/92A, and words of HLA/sea wave home/ink-wash/printed/short-sleeve/t-shirt/2017/new summer round-neck/t-shirt/male/short-sleeve/HNTBJ 2V 020A/white patterns/20/175/92A can be obtained after word segmentation processing is carried out on the first title.

The HNTBJ2V020A is a commodity number, and the terms such as printing, short-sleeve shirt, t-shirt, 2017, round collar, 175/92a and beige can be sub-attribute information.

2) A first participle phrase is generated based on the participles and the first participle set, and a second participle phrase is generated based on the participles and the second participle set.

The first word segmentation set is determined based on secondary attribute information included in the commodity information of the commodities and used for indicating the common attributes of the commodities; the second word set is determined based on the first title and the second attribute information included in the selected commodity information after selecting the commodity information not including the main attribute information from the commodity information of the plurality of commodities, and is used for indicating the independent attributes of the plurality of commodities.

Specifically, the first participle phrase is generated based on the plurality of participles and the first participle set, and the implementation process of generating the second participle phrase based on the plurality of participles and the second participle set may include: selecting at least one first participle belonging to a first participle set from the plurality of participles; determining the probability of each first participle in the first participle set, and sequencing the at least one first participle according to the probability of each first participle in the first participle set to obtain a first participle group; selecting at least one second participle belonging to a second participle set from the plurality of participles; and determining the probability of each second participle in the second participle set, and sequencing the at least one second participle according to the probability of each second participle in the second participle set to obtain a second participle group.

For example, when the at least one first word segmentation is sequenced, the at least one first word segmentation may be sequenced in a descending order according to the probability of each first word segmentation occurring in the first word segmentation set, and then the sequenced at least one first word segmentation group is used as a first word segmentation group; correspondingly, when the at least one second participle is sequenced, the at least one second participle can also be sequenced in a descending order according to the probability of each second participle appearing in the second participle set, and then the sequenced at least one second participle group is used as a second participle group.

3) And adding the first word segmentation group to the second word segmentation group to obtain the commodity identification string of the commodity.

For example, assuming that the first participle phrase is a and the second participle phrase is B, BA may be used as the item identification string of the item.

Further, before generating a first participle word group based on the multiple participles and the first participle set and generating a second participle word group based on the multiple participles and the second participle set, a first participle set and a second participle set need to be constructed, and the process of specifically constructing the first participle set and the second participle set may include the following steps 1) -5):

1) And forming the second attribute information included in the commodity information of the commodities into the first word segmentation set.

That is, the sub attribute information may be extracted from the product information of each of the plurality of products, and all the sub attribute information extracted from the product information of the plurality of products may be configured as the first segmented word set. Since the first set of partial words includes all the secondary attribute information in the commodity information of the plurality of commodities, the first set of partial words may indicate a common attribute of the plurality of commodities.

2) The product information not including the main attribute information is selected from the product information of the plurality of products.

3) And for each selected commodity information, performing word segmentation processing on a first title included in the commodity information, and generating a third word segmentation phrase.

4) And selecting at least one participle belonging to the secondary attribute information from the third participle group, and forming a fourth participle group by the selected at least one participle.

5) And determining different participles in the third participle phrase and the fourth participle phrase, and adding the different participles to the second participle set.

That is, for each selected commodity information not including the main attribute information, the processing may be performed according to the above steps 3) -5), and the different participles determined from each commodity information are all added to the second participle set, so that the second participle set may be constructed. Since the participles included in the second participle set are all different ones, the second participle set can be used for indicating the independent attribute of the commodity.

The third implementation mode comprises the following steps: and when the commodity information of the commodity does not comprise the primary attribute information and the secondary attribute information and comprises a commodity display diagram, generating a commodity identification string of the commodity based on the commodity display diagram of the commodity.

In practical application, the commodity information of the commodity may include a first title, a specification parameter and a commodity display diagram, when the commodity identification string of the commodity is generated based on the commodity information of the commodity, it may be determined whether the first title and the specification parameter include primary attribute information, if the primary attribute information is not included, it may be determined whether the first title and the specification parameter include secondary attribute information, if the secondary attribute information is not included, the commodity display diagram is obtained, and the commodity identification string of the commodity is generated based on the commodity display diagram.

Since the commodity display diagrams used by the same commodity issued by the same merchant on different e-commerce platforms are usually very similar, for the unstructured commodity without the primary attribute information and the secondary attribute information, the commodity display diagrams of the commodity can be used as entry points for association, namely, the commodity identification strings are generated based on the commodity display diagrams to compare and identify the commodity, and the association of the commodity is converted into the association matching of the commodity display diagrams.

Specifically, when the product identification string of the product is generated based on the product display diagram of the product, the picture feature may be extracted from the product display diagram, and then the product identification string of the product is generated based on the extracted picture feature, which may specifically include the following two implementation manners:

1) And extracting picture characteristics of the commodity display picture of the commodity, and determining a commodity identification string of the commodity based on the picture characteristics.

Wherein determining the product identification string of the product based on the picture feature comprises: extracting a plurality of key points from the picture characteristics, forming a picture characteristic matrix of the commodity display picture by the key points, and determining the picture characteristic matrix as a commodity identification string of the commodity.

By identifying the commodities by using the picture feature matrix formed by the key points, the association of the commodities can be converted into the problem that the feature matrix searches the nearest neighbor, so that the same or similar commodities can be determined by searching the nearest neighbor picture feature matrix.

2) And carrying out hash processing on the commodity display graph according to a first preset hash algorithm to obtain a hash value of the commodity display graph, and determining the hash value of the commodity display graph as a commodity identification string of the commodity.

The first preset hash algorithm is a hash algorithm capable of performing hash processing on the picture, and the first preset hash algorithm can be set by default by a server and can also be changed by a user. Specifically, the first preset hash algorithm may be a pHash (Perceptual hash algorithm) or a Hamming distance hash algorithm, etc.

Further, when the product display diagram of the product further includes the watermark corresponding to the e-commerce platform, before the product identification string of the product is generated based on the product display diagram of the product, the product display diagram may be preprocessed, so as to eliminate or fade the watermark in the product display diagram through a preprocessing operation.

For example, a reverse template image containing only the watermark may be prepared for the watermark of each e-commerce platform in advance, and the product display image with the watermark removed or reduced may be generated by preprocessing the product display image with the template image of the corresponding e-commerce platform. Wherein, the preprocessing the commodity display drawing based on the template drawing of the corresponding e-commerce platform may include: and matching the template drawing of the e-commerce platform with the commodity display drawing, and eliminating or fading the color of the part, which is identical to the template drawing of the e-commerce platform, in the commodity display drawing.

The watermark in the commodity display image is eliminated or diluted through preprocessing operation, so that the influence of the watermark on the commodity display image can be avoided, the commodity identification string generated based on the commodity display image can accurately identify the commodity, and the commodity association accuracy can be improved.

Step 103: and matching the commodity identification strings of the commodities, and associating the same or similar commodities in the commodities based on the matching result.

Wherein associating the same or similar ones of the plurality of items comprises: for any group of the same or similar commodities in the plurality of commodities, commodity information of all commodities included in the group of commodities is combined to obtain a commodity group. Further, the item identification strings of all items included in the group of items may also be stored in the group of items, so that subsequent other items may match the associated group of items based on the item identification strings. Further, each of the groups of commodities may be assigned a corresponding ID (identification).

The matching the product identification strings of the multiple products, and associating the same or similar products in the multiple products based on the matching result may include: for any two commodities in the plurality of commodities, matching the commodity identification strings of the two commodities; and when the commodity identification strings of the two commodities meet the preset matching rule, determining that the two commodities are the same or similar commodities, and associating the two commodities.

Specifically, matching the commodity identification strings of two commodities may include the following three implementation manners:

the first implementation mode comprises the following steps: and calculating the similarity of the commodity identification strings of the two commodities, and determining that the commodity identification strings of the two commodities meet a preset matching rule when the calculated similarity is greater than or equal to a first similarity threshold value.

Specifically, for any two product identification strings generated based on the main attribute information or any two product identification strings generated based on the product display diagram, the similarity between the two product identification strings may be directly calculated, and the similarity is used to indicate the similarity of the two product identification strings.

After the similarity is calculated, the calculated similarity may be compared with a first similarity threshold, whether the calculated similarity is greater than or equal to the first similarity threshold is determined, when the calculated similarity is greater than or equal to the first similarity threshold, it may be determined that the commodity identification strings of the two commodities satisfy a preset matching rule, and then it is determined that the two commodities are the same or similar commodities, and when the calculated similarity is less than the first similarity threshold, it may be determined that the commodity identification strings of the two commodities do not satisfy the preset matching rule, that is, the two commodities are not the same or similar commodities.

The first similarity threshold may be set as needed, the maximum value may be set to 1, when the calculated similarity is equal to 1, the two product identification strings are completely the same, and in order to ensure the accuracy of matching, the first similarity threshold may be set to a value close to 1.

The second implementation mode comprises the following steps: determining vectors corresponding to the commodity identification strings of the two commodities, calculating cosine similarity of the vectors corresponding to the commodity identification strings of the two commodities, and determining that the commodity identification strings of the two commodities meet a preset matching rule when the calculated cosine similarity is greater than or equal to a second similarity threshold.

Specifically, for any two commodity identification strings generated based on the secondary attributes, the cosine similarity of vectors corresponding to the commodity identification strings of the two commodities can be calculated. Because the commodity identification string generated based on the secondary attribute is usually a word segmentation phrase, word segmentation phrase vectors respectively corresponding to the commodity identification strings of the two commodities can be determined firstly, and then the cosine similarity of the two word segmentation phrase vectors is calculated, wherein the higher the calculated cosine similarity is, the more probable the two commodities are the same commodity.

The second similarity threshold may also be set as needed, and specifically may be determined according to a minimum value of cosine similarities of vectors corresponding to the commodity identification strings of two identical commodities measured in practical application.

The third implementation mode comprises the following steps: and performing hash processing on the commodity identification strings of the two commodities respectively according to a second preset hash algorithm to obtain hash values of the commodity identification strings of the two commodities, calculating the similarity of the hash values of the commodity identification strings of the two commodities, and determining that the commodity identification strings of the two commodities meet a preset matching rule when the calculated similarity is greater than or equal to a third similarity threshold value.

Specifically, any two commodity identification strings generated based on the primary attribute, or any two commodity identification strings generated based on the secondary attribute, or any two commodity identification strings generated based on the commodity display diagram may be matched according to the third implementation manner. The second preset hash algorithm is a hash algorithm capable of performing hash processing on the commodity identification string, and the second preset hash algorithm can be set by default by the server and can also be changed by a user.

Further, for the product identification string generated based on the secondary attribute, after the hash value of the product identification string is matched with the hash values of the product identification strings of other products, if no matched product is found, word groups corresponding to the product identification string of the product can be sequentially reduced by one word segmentation in the sequence from back to front, and then the hash values of the product identification string are generated to continue matching until all the first word segmentation groups in the product identification string are deleted. That is, after all the first term groups in the product identification string are deleted and the hash value of the product identification string is generated, if no matching product can be searched based on the hash value of the product identification string, the search may be stopped.

It should be noted that, because the matching of the hash value is relatively smaller than the matching of the whole product identification string, the hash value obtained by the matching processing can be used to implement quick matching of the product by performing hash processing on the product identification string, so that the association efficiency can be improved.

It should be noted that, in the embodiment of the present invention, only the example of matching the product identification strings of two products with respect to any two products in the multiple products is taken as an example for description, and in practical applications, when the second manner in the above step 101 is adopted and the product information of the multiple products is obtained based on the search instruction of the target product, the product identification string of the target product may be respectively matched with the product identification strings of the multiple products, so as to determine a product identical or similar to the target product from the multiple products, and associate the target product and the products identical or similar to the target product, so as to establish a product group corresponding to the target product.

The method for matching the commodity identification strings of the target commodity with the commodity identification strings of the multiple commodities is the same as the method for matching the commodity identification strings of any two commodities, and is not described again here.

Further, the commodity information of each commodity may further include a link address of a commodity detail page of the commodity, so that after the same or similar commodities in the plurality of commodities are associated, information such as price or stock may be acquired from the corresponding commodity detail page based on the link address of the commodity detail page included in the commodity information of the same or similar commodities, and presented to the user. The link address of the product detail page may be a URL or the like.

For example, after associating the same or similar commodities in the plurality of commodities, the commodity price of the same or similar commodities in the plurality of commodities can be acquired at preset time intervals based on the link address of the commodity detail page of the same or similar commodities in the plurality of commodities, and when a price display instruction for a target commodity is received, the commodity price of the commodity associated with the target commodity is displayed, or the price of the commodity with the lowest price in the associated commodities is displayed. The target product is a product of interest to the user among the plurality of products, for example, a product that can subscribe a price service for the user.

For another example, after the same or similar commodities in the multiple commodities are associated, the commodity prices of the same or similar commodities in the multiple commodities can be obtained at intervals of a preset time length based on the link addresses of the commodity detail pages of the same or similar commodities in the multiple commodities; when the price of any one commodity in the commodities associated with the target commodity is lower than a preset price threshold value, reminding information is displayed, and the reminding information is used for reminding that the price of the target commodity is lower than the preset price threshold value.

The preset price threshold may be a psychological threshold set by the user for purchasing the commodity, or a threshold set by the server by default. The preset duration can be set by default by the server, and can also be changed by the user.

In the embodiment of the invention, as the commodity information comprises at least one of the main attribute information, the secondary attribute information and the commodity display image, the main attribute information is information which is set by a commodity manufacturer and is used for uniquely identifying the commodity, and the secondary attribute information refers to the specification parameters which are used for describing the commodity except the main attribute information, the commodity can be flexibly and accurately identified based on the commodity identification string generated by at least one of the main attribute information, the secondary attribute information and the commodity display image, the commodity is identified by generating the commodity identification string, and the commodity is identified by the commodity identification string, a rule for automatically identifying and identifying the commodity is established, the commodity with a standardized structure and the commodity without the standardized structure can be accurately identified and associated, so that the manual intervention in the association process is avoided, and the flexibility and the association efficiency of the commodity association are improved.

Further, it is considered that information such as price or inventory of a commodity needs to be acquired through a link address of a commodity detail page, however, in practical applications, a link address of a commodity detail page of a certain commodity may be changed by an e-commerce platform, and when the link address of the commodity detail page is changed, if the link address of the commodity detail page included in original commodity information is still used to search the commodity detail page, the search may fail, and therefore, in order to prevent the link address of the commodity detail page from being changed, the link address of the commodity detail page may also be updated, and a detailed update process of the link address of the commodity detail page will be described below by taking a server as an execution subject and referring to fig. 2A.

Fig. 2A is a flowchart of another commodity association method according to an embodiment of the present invention, and as shown in fig. 2A, the method includes the following steps:

step 201: and acquiring commodity information from the E-commerce platforms to obtain the commodity information of a plurality of commodities, wherein the commodity information comprises at least one of primary attribute information, secondary attribute information and a commodity display diagram.

Step 202: and for each commodity in the plurality of commodities, generating a commodity identification string of the commodity according to a preset generation rule based on the commodity information of the commodity, wherein the commodity identification string is used for uniquely identifying the commodity.

Step 203: and matching the commodity identification strings of the plurality of commodities, and associating the same or similar commodities in the plurality of commodities based on the matching result.

The specific implementation process of steps 201 to 203 may refer to the related description of steps 101 to 103, which is not described herein again.

Step 204: and when the commodity information comprises the link address of the commodity detail page and the change of the link address of the commodity detail page of any one of the associated same or similar commodities is detected, searching in the corresponding e-commerce platform based on the second title of the commodity.

The second title may be a title of the product that can be searched in the corresponding e-commerce platform, and specifically may be a search title of the product in a search result page of the corresponding e-commerce platform.

When the second title is a search title of the commodity in the search result page corresponding to the e-commerce platform, before searching in the corresponding e-commerce platform based on the second title of the commodity, the commodity can be searched in the e-commerce platform corresponding to the commodity based on the commodity information of the commodity, a search title with a corresponding link address identical to the link address of the commodity detail page is selected from a plurality of search titles displayed on the search result page, and the selected search title is determined as the second title.

Further, in the process of acquiring the commodity information from the plurality of e-commerce platforms, the second title of the commodity may be acquired and added to the commodity information of each commodity. That is, the article information of each article may further include a second title.

Step 205: and determining the changed link address of the commodity detail page of the commodity based on the link address corresponding to the search title displayed in the search result page.

The determining of the link address after the change of the commodity detail page of the commodity based on the link address corresponding to the search title displayed in the search result page may include the following two implementation manners:

the first implementation mode comprises the following steps: and determining the link address corresponding to the first search title displayed in the search result page as the link address after the commodity detail page of the commodity is changed.

The second implementation mode comprises the following steps: selecting the first T search titles from the search titles displayed in the search result page, then obtaining the commodity information of the T commodities corresponding to the previous T search titles based on the link addresses corresponding to the previous T search titles, generating the commodity identification strings of the T commodities based on the commodity information of the T commodities, respectively matching the commodity identification strings of the commodities with the commodity identification strings of the T commodities, and determining the link addresses corresponding to the search titles of the commodities, of which the commodity identification strings of the T commodities and the commodity identification strings of the commodities meet the matching rules, as the link addresses of the commodity detail page of the commodities after being changed.

Step 206: and replacing the link address of the commodity detail page included in the commodity information of the commodity with the changed link address.

By replacing the link address of the commodity detail page included in the commodity information of the commodity with the changed link address, the link address of the commodity detail page included in the commodity information of the related identical or similar commodity can be updated, so that the price or inventory information of the commodity can be accurately acquired according to the link address of the commodity detail page.

Further, based on the above, the following fig. 2B and fig. 2C may also be referred to for the specific flow of the product association, which is not limited in this embodiment of the present invention.

Fig. 3A is a block diagram of a product association apparatus according to an embodiment of the present invention, where the apparatus may be a terminal or a server, and as shown in fig. 3A, the product association apparatus includes:

a first obtaining module 301, configured to perform step 101 in the embodiment described in fig. 1 and step 201 in the embodiment described in fig. 2;

a generating module 302, configured to perform step 102 in the embodiment described in fig. 1 and step 202 in the embodiment described in fig. 2;

the associating module 303 is configured to perform step 103 in the embodiment described in fig. 1 and step 203 in the embodiment described in fig. 2.

Optionally, referring to fig. 3B, the apparatus further comprises:

a second obtaining module 304, configured to obtain, for each e-commerce platform of the multiple e-commerce platforms, commodity information of M commodities in the e-commerce platform and search titles of the M commodities in the e-commerce platform, where M is a positive integer;

a fitting module 305, configured to respectively fit the commodity information of the M commodities and the search titles of the M commodities in the e-commerce platform;

a first determining module 306, configured to determine a search keyword generation rule of the e-commerce platform based on the fitting result.

Optionally, referring to fig. 3C, the apparatus further comprises:

a first searching module 307, configured to perform step 204 in the embodiment described in fig. 2;

a second determining module 308, configured to perform step 205 in the embodiment described in fig. 2;

a replacing module 309, configured to execute step 206 in the embodiment described in fig. 2.

Optionally, referring to fig. 3D, the apparatus further comprises:

the second searching module 310 is configured to search the commodity in the e-commerce platform corresponding to the commodity based on the commodity information of the commodity;

a selecting module 311, configured to select a search title with a link address that is the same as the link address of the product detail page from multiple search titles displayed on the search result page;

a third determining module 312, configured to determine the selected search title as the second title.

It should be noted that: in the above-mentioned embodiment, when the product association device associates products from different e-commerce platforms, only the division of the above-mentioned function modules is taken as an example, and in practical applications, the above-mentioned function distribution can be completed by different function modules according to needs, that is, the internal structure of the device is divided into different function modules to complete all or part of the above-mentioned functions. In addition, the commodity association apparatus provided in the above embodiment and the commodity association method embodiment belong to the same concept, and specific implementation processes thereof are detailed in the method embodiment and are not described herein again.

Fig. 4 is a schematic structural diagram of a server 400 according to an embodiment of the present invention. The server may be a server in a cluster of background servers. The server may be a server in a cluster of background servers. Specifically, the method comprises the following steps:

the server 400 includes a Central Processing Unit (CPU) 401, a system memory 404 including a Random Access Memory (RAM) 402 and a Read Only Memory (ROM) 403, and a system bus 405 connecting the system memory 404 and the central processing unit 401. The server 400 also includes a basic input/output system (I/O system) 406, which helps to transfer information between elements within the computer, and a mass storage device 407 for storing an operating system 413, application programs 414, and other program modules 415.

The basic input/output system 406 includes a display 408 for displaying information and an input device 409 such as a mouse, keyboard, etc. for a user to input information. Wherein a display 408 and an input device 409 are connected to the central processing unit 401 through an input output controller 410 connected to the system bus 405. The basic input/output system 406 may also include an input/output controller 410 for receiving and processing input from a number of other devices, such as a keyboard, mouse, or electronic stylus. Similarly, input/output controller 410 may also provide output to a display screen, a printer, or other type of output device.

The mass storage device 407 is connected to the central processing unit 401 through a mass storage controller (not shown) connected to the system bus 405. The mass storage device 407 and its associated computer-readable media provide non-volatile storage for the server 400. That is, the mass storage device 407 may include a computer readable medium (not shown) such as a hard disk or CD-ROM drive.

Without loss of generality, computer readable media may comprise computer storage media and communication media. Computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Computer storage media includes RAM, ROM, EPROM, EEPROM, flash memory or other solid state storage technology, CD-ROM, DVD, or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices. Of course, those skilled in the art will appreciate that computer storage media is not limited to the foregoing. The system memory 404 and mass storage device 407 described above may be collectively referred to as memory.

According to various embodiments of the invention, the server 400 may also operate as a remote computer connected to a network through a network, such as the Internet. That is, the server 400 may be connected to the network 412 through the network interface unit 411 connected to the system bus 405, or may be connected to other types of networks or remote computer systems (not shown) using the network interface unit 411.

In this embodiment, the server 400 further comprises at least one instruction, at least one program, code set, or instruction set stored in the memory and configured to be loaded and executed by one or more processors to implement the article association method described in the embodiment of fig. 1A or fig. 2A.

In another embodiment, a computer-readable storage medium is provided, having stored therein at least one instruction, at least one program, set of codes, or set of instructions, which is loaded and executed by a processor to implement the article association method described in the embodiment of fig. 1A or fig. 2A.

Fig. 5 is a schematic structural diagram of a terminal 500 according to an embodiment of the present invention. Referring to fig. 5, the terminal 500 may include components such as a communication unit 510, a memory 520 including one or more computer-readable storage media, an input unit 530, a display unit 540, a sensor 550, an audio circuit 560, a WIFI (Wireless Fidelity) module 570, a processor 580 including one or more processing cores, and a power supply 590. Those skilled in the art will appreciate that the terminal structure shown in fig. 5 is not intended to be limiting and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components. Wherein:

the communication unit 510 may be used for receiving and transmitting information or signals during a call, and the communication unit 510 may be an RF (Radio Frequency) circuit, a router, a modem, or other network communication devices. In particular, when the communication unit 510 is an RF circuit, downlink information of a base station is received and then processed by the one or more processors 580; in addition, data relating to uplink is transmitted to the base station. Generally, the RF circuit as a communication unit includes, but is not limited to, an antenna, at least one Amplifier, a tuner, one or more oscillators, a Subscriber Identity Module (SIM) card, a transceiver, a coupler, an LNA (Low Noise Amplifier), a duplexer, and the like. In addition, the communication unit 510 can also communicate with a network and other devices through wireless communication. The wireless communication may use any communication standard or protocol, including but not limited to GSM (Global System for Mobile communications), GPRS (General Packet Radio Service), CDMA (Code Division Multiple Access), WCDMA (Wideband Code Division Multiple Access), LTE (Long Term Evolution), email, SMS (Short Messaging Service), and the like. The memory 520 may be used to store software programs and modules, and the processor 580 executes various functional applications and data processing by operating the software programs and modules stored in the memory 520. The memory 520 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data, a phonebook, etc.) created according to the use of the terminal 500, and the like. Further, the memory 520 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device. Accordingly, the memory 520 may also include a memory controller to provide the processor 580 and the input unit 530 access to the memory 520.

The input unit 530 may be used to receive input numeric or character information and generate a keyboard, mouse, joystick, optical or trackball signal input related to user setting and function control. Preferably, the input unit 530 may include a touch-sensitive surface 531 and other input devices 532. The touch sensitive surface 531, also referred to as a touch display screen or touch pad, can collect touch operations by a user on or near the touch sensitive surface 531 (such as operations by the user on the touch sensitive surface 531 or near the touch sensitive surface 531 using a finger, a stylus, or any other suitable object or attachment) and drive the corresponding connection device according to a predetermined program. Alternatively, the touch sensitive surface 531 may comprise two parts, a touch detection means and a touch controller. The touch detection device detects the touch direction of a user, detects a signal brought by touch operation and transmits the signal to the touch controller; the touch controller receives touch information from the touch sensing device, converts the touch information into touch point coordinates, and sends the touch point coordinates to the processor 580, and can receive and execute commands sent by the processor 580. In addition, the touch sensitive surface 531 may be implemented using various types of resistive, capacitive, infrared, and surface acoustic waves. The input unit 530 may comprise other input devices 532 in addition to the touch sensitive surface 531. Preferably, other input devices 532 may include, but are not limited to, one or more of a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, a joystick, and the like.

The display unit 540 may be used to display information input by or provided to the user and various graphical user interfaces of the terminal 500, which may be made up of graphics, text, icons, video, and any combination thereof. The Display unit 540 may include a Display panel 541, and optionally, the Display panel 541 may be configured in the form of an LCD (Liquid Crystal Display), an OLED (Organic Light-Emitting Diode), or the like. Further, the touch-sensitive surface 531 can overlie the display panel 541 such that, when a touch event is detected at or near the touch-sensitive surface 531, it is passed to the processor 580 for determining the type of touch event, whereupon the processor 580 provides a corresponding visual output on the display panel 541 in dependence upon the type of touch event. Although in FIG. 5 the touch sensitive surface 531 and the display panel 541 are shown as two separate components to implement input and output functions, in some embodiments the touch sensitive surface 531 and the display panel 541 may be integrated to implement input and output functions.

The terminal 500 can also include at least one sensor 550, such as a light sensor, motion sensor, and other sensors. The light sensor may include an ambient light sensor that adjusts brightness of the display panel 541 according to brightness of ambient light, and a proximity sensor that turns off the display panel 541 and/or a backlight when the terminal 500 moves to the ear. As one of the motion sensors, the gravity acceleration sensor can detect the magnitude of acceleration in each direction (generally three axes), can detect the magnitude and direction of gravity when stationary, and can be used for applications of identifying the gesture of a mobile phone (such as horizontal and vertical screen switching, related games, magnetometer gesture calibration), vibration identification related functions (such as pedometer and tapping), and the like; as for other sensors such as a gyroscope, a barometer, a hygrometer, a thermometer, and an infrared sensor, which can be configured in the terminal 500, detailed descriptions thereof are omitted.

Audio circuitry 560, speaker 561, and microphone 562 may provide an audio interface between a user and terminal 500. The audio circuit 560 may transmit the electrical signal converted from the received audio data to the speaker 561, and convert the electrical signal into a sound signal by the speaker 561 for output; on the other hand, the microphone 562 converts the collected sound signal into an electric signal, is received by the audio circuit 560 and converted into audio data, and then outputs the audio data to the processor 580 for processing, via the communication unit 510 to be transmitted to, for example, another terminal, or outputs the audio data to the memory 520 for further processing. The audio circuit 560 may also include an earbud jack to provide communication of a peripheral headset with the terminal 500.

In order to implement wireless communication, a wireless communication unit 570 may be configured on the terminal, and the wireless communication unit 570 may be a WIFI module. WIFI belongs to a short-range wireless transmission technology, and the terminal 500 can help a user send and receive e-mails, browse web pages, access streaming media, and the like through the wireless communication unit 570, and it provides wireless broadband internet access for the user. Although the wireless communication unit 570 is shown in the drawing, it is understood that it does not belong to the essential constitution of the terminal 500 and may be omitted as needed within a scope not changing the essence of the invention.

The processor 580 is a control center of the terminal 500, connects various parts of the entire handset using various interfaces and lines, and performs various functions of the terminal 500 and processes data by operating or executing software programs and/or modules stored in the memory 520 and calling data stored in the memory 520, thereby viewing the entire handset. Optionally, processor 580 may include one or more processing cores; preferably, the processor 580 may integrate an application processor, which mainly handles operating systems, user interfaces, application programs, etc., and a modem processor, which mainly handles wireless communications. It will be appreciated that the modem processor described above may not be integrated into processor 580.

The terminal 500 further includes a power supply 590 (e.g., a battery) for powering the various components, which may preferably be logically coupled to the processor 580 via a power management system that may enable managing charging, discharging, and power consumption via the power management system. The power supply 560 may also include any component including one or more dc or ac power sources, recharging systems, power failure detection circuitry, power converters or inverters, power status indicators, and the like.

Although not shown, the terminal 500 may further include a camera, a bluetooth module, etc., which will not be described herein.

In this embodiment, the terminal 500 further comprises at least one instruction, at least one program, code set, or instruction set stored in the memory and configured to be loaded and executed by one or more processors to implement the article association method described in the embodiment of fig. 1A or fig. 2A.

It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, where the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.

The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.

Claims

1. A method of merchandise association, the method comprising:

when the commodity information of the commodity does not include the primary attribute information and includes the secondary attribute information and a first title, determining to obtain a first word segmentation set for indicating a common attribute of the commodities based on the secondary attribute information included in the commodity information of the commodities; after commodity information which does not include the primary attribute information is selected from the commodity information of the commodities, determining to obtain a second word segmentation set used for indicating independent attributes of the commodities based on the first title and the secondary attribute information included in the selected commodity information;

performing word segmentation processing on the first title to obtain a plurality of words; generating a first participle phrase based on the plurality of participles and the first participle set, and generating a second participle phrase based on the plurality of participles and the second participle set; adding the first word segmentation group to the second word segmentation group to obtain a commodity identification string of the commodity; the first title refers to a title of a commodity detail page of the commodity, and the commodity identification string is used for uniquely identifying the commodity;

and matching the commodity identification strings of the commodities, and associating the same or similar commodities in the commodities based on a matching result.

2. The method of claim 1, wherein prior to generating the item identification string for the item based on the first heading, the first set of participles, and the second set of participles, further comprising:

forming the first word set by the secondary attribute information included in the commodity information of the commodities;

selecting commodity information not including the main attribute information from the commodity information of the plurality of commodities;

for each selected commodity information, performing word segmentation processing on a first title included in the commodity information to generate a third word segmentation phrase;

selecting at least one participle belonging to secondary attribute information from the third participle group, and forming a fourth participle group by the selected at least one participle;

determining different participles in the third participle phrase and the fourth participle phrase, and adding the different participles to the second participle set.

3. The method of claim 1, wherein the generating the commodity identification string of the commodity according to a preset generation rule based on the commodity information of the commodity comprises:

when the commodity information of the commodity does not comprise the primary attribute information and the secondary attribute information and comprises a commodity display picture, extracting picture characteristics of the commodity display picture of the commodity, and determining a commodity identification string of the commodity based on the picture characteristics; or,

and when the commodity information of the commodity does not comprise the main attribute information and the secondary attribute information and comprises a commodity display graph, carrying out hash processing on the commodity display graph according to a first preset hash algorithm to obtain a hash value of the commodity display graph, and determining the hash value of the commodity display graph as a commodity identification string of the commodity.

4. The method of claim 1, wherein said matching the item identification strings of the plurality of items, associating the same or similar items of the plurality of items based on the matching results, comprises:

for any two commodities in the plurality of commodities, matching the commodity identification strings of the two commodities;

and when the commodity identification strings of the two commodities meet a preset matching rule, determining that the two commodities are the same or similar commodities, and associating the two commodities.

5. The method of claim 4, wherein said matching the item identification strings of the two items comprises at least one of:

calculating the similarity of the commodity identification strings of the two commodities, and determining that the commodity identification strings of the two commodities meet a preset matching rule when the calculated similarity is greater than or equal to a first similarity threshold;

determining vectors corresponding to the commodity identification strings of the two commodities, and determining that the commodity identification strings of the two commodities meet a preset matching rule when the cosine similarity of the vectors corresponding to the commodity identification strings of the two commodities is greater than or equal to a second similarity threshold;

and performing hash processing on the commodity identification strings of the two commodities respectively according to a second preset hash algorithm to obtain hash values of the commodity identification strings of the two commodities, and determining that the commodity identification strings of the two commodities meet a preset matching rule when the similarity of the hash values of the commodity identification strings of the two commodities is greater than or equal to a third similarity threshold value.

6. The method of claim 1, wherein obtaining the merchandise information from the plurality of e-commerce platforms to obtain the merchandise information for the plurality of merchandise comprises:

when a search instruction for a target commodity is received, acquiring commodity information of the target commodity, wherein the target commodity is a commodity in any one of the E-commerce platforms;

generating a search keyword of the target commodity based on the commodity information of the target commodity;

searching in the plurality of E-commerce platforms based on the search keyword of the target commodity to obtain commodity information of the plurality of commodities, wherein the commodity information of the plurality of commodities comprises the commodity information of the target commodity.

7. The method of claim 6, wherein before generating the search keyword for the target item based on the item information for the target item, further comprising:

for each e-commerce platform of the plurality of e-commerce platforms, acquiring commodity information of M commodities in the e-commerce platform and search titles of the M commodities in the e-commerce platform, wherein M is a positive integer;

fitting the commodity information of the M commodities and the search titles of the M commodities in the e-commerce platform respectively, and determining a search keyword generation rule of the e-commerce platform based on a fitting result;

correspondingly, the generating of the search keyword of the target commodity based on the commodity information of the target commodity comprises:

and for each e-commerce platform of the plurality of e-commerce platforms, generating a search keyword of the target commodity in the e-commerce platform according to the search keyword generation rule of the e-commerce platform based on the commodity information of the target commodity.

8. The method of claim 1, wherein the method further comprises:

when the commodity information comprises a link address of a commodity detail page and the link address of the commodity detail page of any one of related same or similar commodities is detected to be changed, searching in a corresponding e-commerce platform based on a second title of the commodity, wherein the second title refers to a title of the commodity which can be searched in the corresponding e-commerce platform;

determining a link address of the commodity after the commodity detail page is changed based on a link address corresponding to a search title displayed in a search result page;

and replacing the link address of the commodity detail page included in the commodity information of the commodity with the changed link address.

9. The method of claim 8, wherein prior to searching in the corresponding e-commerce platform based on the second title of the item, further comprising:

searching the commodities in an e-commerce platform corresponding to the commodities based on the commodity information of the commodities;

and selecting a search title with the corresponding link address identical to that of the commodity detail page from a plurality of search titles displayed on the search result page, and determining the selected search title as the second title.

10. An article association apparatus, comprising:

a generation module, configured to determine, when the product information of the product does not include the primary attribute information and includes the secondary attribute information and a first title, a first word segmentation set indicating a common attribute of the plurality of products based on the secondary attribute information included in the product information of the plurality of products; after commodity information which does not include the primary attribute information is selected from the commodity information of the commodities, determining to obtain a second word segmentation set used for indicating independent attributes of the commodities based on the first title and the secondary attribute information included in the selected commodity information;

the generating module is further configured to perform word segmentation processing on the first title to obtain a plurality of words; generating a first participle phrase based on the plurality of participles and the first participle set, and generating a second participle phrase based on the plurality of participles and the second participle set; adding the first participle word group to the second participle word group to obtain a commodity identification string of the commodity; the first title refers to a title of a commodity detail page of the commodity, and the commodity identification string is used for uniquely identifying the commodity;

and the association module is used for matching the commodity identification strings of the commodities and associating the same or similar commodities in the commodities based on matching results.

11. The apparatus of claim 10, wherein the apparatus further comprises:

the first searching module is used for searching in a corresponding e-commerce platform based on a second title of the commodity when the commodity information comprises a link address of a commodity detail page and the link address of the commodity detail page of any one of related same or similar commodities is detected to be changed, wherein the second title refers to a title of the commodity which can be searched in the corresponding e-commerce platform;

the second determining module is used for determining the link address of the commodity after the commodity detail page of the commodity is changed based on the link address corresponding to the search title displayed in the search result page;

and the replacing module is used for replacing the link address of the commodity detail page included in the commodity information of the commodity with the changed link address.

12. A server, characterized in that the server comprises a processor and a memory, in which at least one program is stored, which program is loaded and executed by the processor to implement the merchandise association method according to any one of claims 1-9.

13. A computer-readable storage medium, in which at least one program is stored, which is loaded and executed by a processor to implement the merchandise association method according to any one of claims 1 to 9.