CN114579896A

CN114579896A - Generation method and display method of recommended label, corresponding device and electronic equipment

Info

Publication number: CN114579896A
Application number: CN202210209607.5A
Authority: CN
Inventors: 张春妮; 王怡
Original assignee: Rajax Network Technology Co Ltd
Current assignee: Rajax Network Technology Co Ltd
Priority date: 2022-03-04
Filing date: 2022-03-04
Publication date: 2022-06-03

Abstract

The application provides a generation method and a display method of a recommended label, a corresponding device and electronic equipment. The method comprises the following steps: acquiring description information of a target commodity; extracting keywords of the target commodity corresponding to at least one preset attribute from the description information; determining at least one selling point word corresponding to the target commodity according to at least one keyword corresponding to the target commodity; and generating a recommended label of the target commodity based on each keyword and each selling point word corresponding to the target commodity. The method effectively utilizes the existing description information of the commodity, extracts the key words from the description information through the preset commodity attributes, determines the selling point words according to the key words, and generates the recommended labels of the commodity based on the key words and the selling point words.

Description

Generation method and display method of recommended label, corresponding device and electronic equipment

Technical Field

The application relates to the technical field of information processing, in particular to a generation method and a display method of a recommended label, a corresponding device and electronic equipment.

Background

As is well known, the close integration with the internet has brought new opportunities for the development of the traditional industry, and the network consumption has become a popular economic state in recent years. However, after the network consumption market has been rapidly expanded for many years, the information and functions provided by each platform become increasingly homogeneous, and how to optimally design the information and functions becomes an embodiment of the competitive strength of the network consumption platform.

At present, some network consumption platforms lack the outstanding display capability of the core information of the commodities, so that when a user purchases the commodities, the core information of the commodities, such as main raw materials, specifications and the like, cannot be quickly captured, and particularly when the commodity names cannot embody the commodity contents, the decision efficiency of the user on purchasing the commodities is low.

Disclosure of Invention

The purpose of the embodiment of the application is to solve the technical problem that the core information display capability of the commodity is lacked.

According to a first aspect of embodiments of the present application, a method for generating a recommended label is provided, where the method includes:

acquiring description information of a target commodity;

extracting at least one preset keyword corresponding to the attribute from the description information;

determining a selling point word corresponding to the target commodity according to at least one keyword corresponding to the target commodity;

and generating a recommended label of the target commodity based on at least one keyword and at least one selling point word corresponding to the target commodity.

According to a second aspect of the embodiments of the present application, there is provided a method for displaying a recommended label, the method including:

responding to a triggering operation for checking commodities, acquiring recommended labels and commodity information of corresponding commodities, wherein the recommended labels of each commodity are generated based on at least one keyword and at least one selling point word corresponding to the commodity, the selling point words corresponding to the commodities are determined according to the at least one keyword corresponding to the commodities, and the keywords corresponding to the commodities are extracted from the description information of the commodities aiming at least one preset attribute;

and displaying at least one recommended label and commodity information of the corresponding commodity.

According to a third aspect of the embodiments of the present application, there is provided a method for displaying a commodity, the method including:

displaying keywords of the commodities on a commodity detail page, wherein the keywords are extracted from the description information of the corresponding commodities aiming at least one preset attribute;

and displaying a recommended label of the commodity on the commodity list page, wherein the recommended label is generated based on at least one keyword and at least one selling point word corresponding to the corresponding commodity, and the selling point word is determined according to the at least one keyword corresponding to the corresponding commodity.

According to a fourth aspect of the embodiments of the present application, there is provided an apparatus for generating a recommended label, the apparatus including:

the acquisition module is used for acquiring the description information of the target commodity;

the extraction module is used for extracting keywords of the target commodity corresponding to at least one preset attribute from the description information;

the determining module is used for determining a selling point word corresponding to the target commodity according to at least one keyword corresponding to the target commodity;

and the generation module is used for generating a recommendation label of the target commodity based on at least one keyword and at least one selling point word corresponding to the target commodity.

According to a fifth aspect of the embodiments of the present application, there is provided a display apparatus for a recommended label, the apparatus including:

the response module is used for responding to triggering operation for checking the commodities, acquiring recommended labels and commodity information of corresponding commodities, wherein the recommended labels of each commodity are generated based on at least one keyword and at least one selling point word corresponding to the commodity, the selling point words corresponding to the commodities are determined according to the at least one keyword corresponding to the commodities, and the keywords corresponding to the commodities are extracted from the description information of the commodities aiming at least one preset attribute;

and the display module is used for displaying at least one recommended label and commodity information of the corresponding commodity.

According to a sixth aspect of embodiments of the present application, there is provided a display device for goods of commerce, the device comprising:

the first display module is used for displaying keywords of the commodities on the commodity detail page, and the keywords are extracted from the description information of the corresponding commodities according to at least one preset attribute;

and the second display module is used for displaying the recommended labels of the commodities on the commodity list page, the recommended labels are generated based on at least one keyword and at least one selling point word corresponding to the corresponding commodities, and the selling point words are determined according to the at least one keyword corresponding to the corresponding commodities.

According to a seventh aspect of embodiments of the present application, there is provided an electronic apparatus, including: memory, a processor and a computer program stored on the memory, the processor executing the computer program to perform the steps of the method as provided by the first aspect of the embodiments of the present application.

According to an eighth aspect of embodiments of the present application, there is provided an electronic apparatus including: memory, a processor and a computer program stored on the memory, the processor executing the computer program to implement the steps of the method provided by the second or third aspect of the embodiments of the present application.

According to a ninth aspect of embodiments of the present application, there is provided a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method provided by the first aspect of embodiments of the present application.

According to a tenth aspect of embodiments of the present application, there is provided a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the method provided by the second or third aspect of embodiments of the present application.

According to an eleventh aspect of embodiments of the present application, there is provided a computer program product comprising a computer program which, when executed by a processor, performs the steps of the method provided by the first aspect of embodiments of the present application.

According to a twelfth aspect of embodiments of the present application, there is provided a computer program product comprising a computer program that, when executed by a processor, performs the steps of the method provided by the second or third aspect of embodiments of the present application.

According to the generation method, the display method, the corresponding device and the electronic equipment of the recommended label, the existing description information of the commodity is effectively utilized, the keyword is extracted from the description information through the preset commodity attribute, the selling point word is determined according to the keyword, the recommended label of the commodity can be generated based on the keyword and the selling point word, the recommended label is used as the highlighted display content of the core information of the commodity, a user can capture the core information of the commodity quickly through the recommended label when the user buys the commodity, and the commodity shopping efficiency of the user is improved.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings used in the description of the embodiments of the present application will be briefly described below.

Fig. 1 is a schematic flowchart of a method for generating a recommended label according to an embodiment of the present application;

FIG. 2 is a schematic diagram illustrating a recommendation tag according to a user characteristic according to an embodiment of the application;

fig. 3 is a schematic flowchart of a method for displaying a recommended label according to an embodiment of the present application;

FIG. 4 is a schematic diagram of generating and displaying a recommended label according to an embodiment of the present application;

fig. 5 is a schematic flowchart of a method for displaying a commodity according to an embodiment of the present disclosure;

fig. 6 is a schematic structural diagram of a recommended label generating apparatus according to an embodiment of the present application;

fig. 7 is a schematic structural diagram of a display device for recommending labels according to an embodiment of the present application;

fig. 8 is a schematic structural diagram of a display device for merchandise according to an embodiment of the present disclosure;

fig. 9 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

Embodiments of the present application are described below in conjunction with the drawings in the present application. It should be understood that the embodiments set forth below in connection with the drawings are exemplary descriptions for explaining technical solutions of the embodiments of the present application, and do not limit the technical solutions of the embodiments of the present application.

As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should be further understood that the terms "comprises" and/or "comprising," when used in this specification in connection with embodiments of the present application, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of other features, integers, steps, operations, elements, components, and/or groups thereof, as supported by the present technology. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may be present. Further, "connected" or "coupled" as used herein may include wirelessly connected or wirelessly coupled. The term "and/or" as used herein indicates at least one of the items defined by the term, e.g., "a and/or B" may be implemented as "a", or as "B", or as "a and B".

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

Aiming at places needing improvement in the related art, the embodiment of the application provides a generation method, a display method, a corresponding device and electronic equipment of a recommended label.

The inventor of the application realizes that a merchant end can also be directly used as a data source of a recommended label, but the merchant end lacks an entry and rule requirement for inputting rich commodity information, if the merchant background is directly optimized to increase the dimension for inputting the commodity information by the merchant end, the merchant fills in richer and more complete commodity information, and the biggest defect is that the period is long, and multiple departments are involved, for example, the operation is needed to redefine the category of the commodity and the dimension field of the commodity information; the merchant end needs to modify the product capability and redefine the commodity assessment standard; it is also an incentive for merchants and front-line BD (Business Development) to fill in or update the merchandise information in a timely manner, which is costly.

According to the technical scheme provided by the embodiment of the application, the existing description information of the commodity is utilized, the keywords are extracted from the description information through the preset commodity attributes, the selling point words are determined according to the keywords, the recommended labels of the commodity can be quickly generated based on the keywords and the selling point words, and the collection time and cost of the recommended labels are remarkably reduced.

The technical solutions of the embodiments of the present application and the technical effects produced by the technical solutions of the present application will be described below through descriptions of several exemplary embodiments. It should be noted that the following embodiments may be referred to, referred to or combined with each other, and the description of the same terms, similar features, similar implementation steps and the like in different embodiments is not repeated.

An embodiment of the present application provides a method for generating a recommended label, and as shown in fig. 1, the method includes:

step S101: and acquiring the description information of the target commodity.

For the embodiment of the present application, the execution subject may be a server, including but not limited to an independent physical server, a server cluster, a distributed system, or a cloud server.

The target product is a product for which a recommended label needs to be generated. The number of the target commodities can be one or more, each target commodity can be processed according to the scheme, and the same execution process will not be described any more.

As an example, the target product may be all products containing description information in the database, and the server performs batch processing on the description information of all the products, generates a recommendation label for each product, and updates the recommendation label to a user (Consumer) end (which may be referred to as a C end for short) to be displayed. The target commodity can also be a commodity with description information which is newly input or updated by a merchant, and the server carries out instant or timed processing on the latest description information of the commodity to generate a recommendation label of the commodity, and then updates the recommendation label to the user side for showing. In practical application, the target commodity can be determined according to actual requirements, and this is not specifically limited in the embodiment of the present application.

In the embodiment of the present application, the description information of a certain commodity may refer to information that describes the commodity and is input by a merchant, and may be displayed on a commodity detail page at a user end generally, so as to introduce information such as characteristics, materials, and specifications of the commodity. The format of the descriptive information includes, but is not limited to, text, images, audio, video, attachments, and the like. The description information of image, audio, video and attachment format can be converted or extracted into text format for subsequent processing, or can be directly used for subsequent processing.

In the embodiment of the application, the description information of the target commodity may include a commodity name in addition to a description text, a description image, a description audio, a description video, a description accessory and the like, because some characteristics or information of the commodity may be included in the commodity name, which is helpful for generating a more accurate recommendation tag.

Step S102: and extracting keywords of the target product respectively corresponding to at least one preset attribute from the description information.

The various attributes of the commodity refer to the commodity properties of the commodity in different dimensions, and are used as a reference for extracting the features of the commodity in each property dimension. For example, taking a tea-based commodity as an example, the attributes may include: base, tea top, taste, mouthfeel, dairy type, fruit variety, raw material, adjuvant, specification, preparation method, packaging method, weight, suggestion collocation, selling point/efficacy, etc., but not limited thereto. In practical application, a person skilled in the art can preset the attribute reference according to an actual situation, and the number and the content of the attributes are not specifically limited in the embodiment of the present application.

In the embodiment of the application, all or part of the preset attributes can be selected according to a predetermined rule to extract the keywords, for example, only the attribute with the importance higher than a certain threshold value is selected; or selecting an attribute with a correlation degree higher than a certain threshold value according to the characteristics or categories of the commodities. In practical applications, a machine learning algorithm may be used to select an appropriate at least one attribute for extracting the keyword.

In the embodiment of the present application, in consideration that commodities of different categories (or referred to as categories) may have different attributes, a person skilled in the art may define the attribute references for the commodities of different categories according to actual situations. Before this step is performed, the method may further include the steps of: acquiring the category of a target commodity; and determining at least one preset attribute corresponding to the category. Namely, in the embodiment of the application, the keywords with corresponding attributes are extracted based on the category of the target product.

In the embodiment of the present application, extracting the keyword from the description information may also be understood as capturing the keyword in the description information. In practical application, a person skilled in the art may extract each keyword by using a suitable capture algorithm according to an actual situation, for example, a keyword matching algorithm, a keyword extraction algorithm, a machine learning algorithm, and the like, which is not limited in the embodiment of the present application.

Table 1 shows an example of extracting keywords corresponding to partial attributes from the description information, taking a product such as a tea drink as an example.

TABLE 1

In the embodiment of the application, part of the extracted keywords can be used for directly generating the recommendation label, and part of the extracted keywords can be analyzed, reasoned or deduced and packaged into selling point words and then used for generating the recommendation label as one of important data sources of the commodity recommendation label. Those skilled in the art can determine the keywords for directly generating the recommended labels and the keywords for inferring the selling point words according to actual situations, and the embodiment of the present application is not particularly limited herein.

Step S103: and determining a selling point word corresponding to the target commodity according to at least one keyword corresponding to the target commodity.

The selling point words are words for expressing the unique sanctions or distinctive features or characteristics of the commodities. In the embodiment of the application, the determined selling point words may be one or more. Each selling point word is obtained by reasoning and packaging the keywords. Specifically, one selling point word may be inferred by one keyword or may be inferred by a plurality of keywords. Those skilled in the art can determine each selling point word by using a suitable inference algorithm according to actual conditions, for example, an intelligent semantic association, a matching algorithm, a machine learning algorithm, and the like, which is not limited in the embodiment of the present application.

It will be understood that each of the selling points has a corresponding keyword, each of the keywords has a corresponding attribute, and each of the selling points also has a corresponding attribute (which may correspond to one or more).

Table 2 shows an example of inferring a selling point word from a keyword corresponding to the extracted partial attribute, taking a tea drink product as an example.

Properties	Keyword	Selling point word
			Component(s) of	1000ml、1000cc、1L	Super-large cup
Main materials	Orange, lemon, pomelo and kiwi fruit	High-dimensional C
			Specification of	Heat, heat	Can be used for making hot beverage
Specification of	Cold and sand ice	Can be used as cold drink
			Taste of the product	0 calorie sugar, slightly sweet, desugar	Low sugar/no sugar

TABLE 2

In the embodiment of the application, when the selling point word corresponding to the target commodity is determined according to at least one keyword corresponding to the target commodity, the selling point word corresponding to the target commodity can be determined according to the attribute of the keyword, namely according to the at least one keyword corresponding to the target commodity and the attribute to which the keyword belongs.

Continuing to take table 2 as an example, when keywords such as "orange", "lemon", "grapefruit", "kiwi fruit" and the like are obtained, it is necessary to determine the attribute of the keyword as the main material to deduce the selling point word "high-dimensional C", and if the attribute of the keyword is the auxiliary material, the selling point word cannot be obtained.

Step S104: and generating a recommended label of the target commodity based on at least one keyword and at least one selling point word corresponding to the target commodity.

In the embodiment of the application, part or all of the extracted keywords and part or all of the determined attributes of the selling point words may be selected according to a predetermined rule to generate a recommendation tag, for example, only the keywords and/or the selling point words with importance higher than a certain threshold are selected, or the keywords and/or the selling point words with relevance higher than a certain threshold are selected according to characteristics or categories of goods, merchants, or users. In practical applications, a machine learning algorithm may also be used to select an appropriate at least one keyword and/or selling point word to generate the recommended label.

In the embodiment of the present application, at least one keyword (for convenience of description, abbreviated as a first keyword) used in the step S103 for determining the selling point words and at least one keyword (for convenience of description, abbreviated as a second keyword) used in the step S104 for generating the recommendation labels may be completely different. As an example, the keywords extracted in step S102 are divided into first keywords and second keywords, one or more of the first keywords are used for performing step S103, and one or more of the second keywords are used for performing step S104.

Alternatively, the at least one first keyword and the at least one second keyword may be partially identical. As an example, the keywords extracted in step S102 are determined as one or more first keywords for performing step S103, and then one or more second keywords for performing step S104. At least one of the one or more first keywords and the one or more second keywords is the same as one of the first keywords and the second keywords.

Alternatively, the at least one first keyword and the at least one second keyword may be identical. As an example, one or more first keywords are determined from the keywords extracted in step S102 for performing step S103, and the one or more first keywords are directly used as the second keywords for performing step S104.

In the embodiment of the application, for each word of at least one keyword and at least one selling point word, a corresponding recommendation label can be generated respectively. Alternatively, each recommendation tag may be generated from one or more of the at least one keyword and the at least one point word.

As will be understood by those skilled in the art, the process of generating the recommended label based on the keyword and the selling point word may be understood as converting the keyword and the selling point word into data that the user end can recognize the recommended label. After the recommendation label is generated, the recommendation label can be sent to the user side for displaying.

In the embodiment of the application, the generated recommendation label can be a short label of the commodity core information displayed to the user when the commodity is presented to the user, so as to help the user make a purchasing decision. In practical application, in order to avoid that too many recommended tags make a user not to know core information of a commodity correctly, the number of the displayed recommended tags may be controlled, for example, not more than 3 recommended tags, and a person skilled in the art may set the display number of the recommended tags according to an actual situation, which is not limited herein in the embodiment of the present application. Specifically, the recommended tags that do not exceed the predetermined display number may be determined by the server and then sent to the user side for display, or the server may also send all the generated recommended tags to the user side, and the recommended tags that do not exceed the predetermined display number are determined by the user side for display, which is not limited in the embodiment of the present application.

According to the method for generating the recommended label, the existing description information of the commodity can be effectively utilized, the keyword is extracted from the description information through the preset commodity attribute, the selling point word is determined according to the keyword, and the recommended label of the commodity can be generated based on the keyword and the selling point word.

In the embodiment of the present application, a feasible implementation manner is provided for step S102, and specifically, the implementation manner may include:

step S1021: and acquiring at least one matching word from a prefix matching word, a suffix matching word and a complete matching word which are respectively corresponding to at least one attribute.

In this embodiment of the present application, each attribute may have a corresponding matching pool, and each matching pool may include at least one matching word of a prefix matching word, a suffix matching word, and a complete matching word. This step can be understood as obtaining each matching word in the matching pool.

The prefix matching words mean that prefixes in the matching words are fixed, and contents behind the prefixes can be dynamically changed. As long as the content satisfying the matching requirement is found by the prefix, the keyword containing the prefix and other content can be found.

Similarly, the suffix matching word means that the suffix in the matching word is fixed, and the content before the suffix can be dynamically changed. The keyword containing the suffix and other contents can be found by simply searching for contents satisfying the matching requirement through the suffix.

The complete matching words are used for searching completely consistent content, and if words completely consistent with certain complete matching words exist in the description information, the words can be used as key words.

In table 3, examples of the tea products are given, and based on table 1, examples of matching words for extracting keywords from the description information are given.

Wherein, the matching words 'ox' corresponding to the attribute 'base', the matching words 'clear' corresponding to the attribute 'taste' and the like are prefix matching words; the matching words 'tea' corresponding to the attribute 'base', the matching words 'milk cover' corresponding to the attribute 'tea top' and the like are suffix matching words, and the matching words 'cheese' corresponding to the attribute 'tea top' and the like are complete matching words. In table 3, other matching words can be analogized, and will not be described again.

Step S1022: based on the obtained matching words, executing at least one of the following ways of extracting the keywords of the target commodity to obtain the keywords of at least one attribute corresponding to the target commodity:

(1) and extracting a first keyword of the target commodity from the post-content matched with the prefix matching word in the description information based on the prefix matching word.

For example, in table 3, based on the prefix matching word "clear" corresponding to the attribute "taste", the post content matching the prefix matching word in the description information is "sweet", and the first keyword "clear sweet" can be extracted.

(2) And extracting a second keyword of the target commodity from the prepositive content of the matched suffix matching words in the description information based on the suffix matching words.

For example, in table 3, based on the suffix matching word "sweet" corresponding to the attribute "taste", the post content matching the suffix matching word in the description information may be "no", "little", "clear", and the like, and the second keyword "non-sweet", "slightly sweet", "clear", and the like may be extracted.

(3) And based on the complete matching words, extracting the content matched with the complete matching words in the description information as third key words of the target commodity.

For example, in table 3, based on the complete matching word "cheese" corresponding to the attribute "tea top", the content "cheese" having the complete matching word in the description information may be extracted as the third key word.

Wherein, other keywords in table 3 can be analogized in this way, and will not be described again.

It is to be understood that the number of the first keyword, the second keyword, or the third keyword extracted based on each matching word may be one or more.

In this embodiment of the application, it is considered that if there are different types of matching words in the matching pool, the same keyword may be extracted based on different types of matching words, for example, the keyword "fresh sweet" may be extracted based on both the prefix matching word "clear" and the suffix matching word "sweet" corresponding to the attribute "taste", and the keyword "cheese" may be extracted based on both the complete matching word "cheese" and the prefix matching word "top tea" corresponding to the attribute "top tea", and after step S102, the method may further include: and carrying out duplicate removal processing on the extracted keywords.

The subsequent steps are all processed based on the de-duplicated keywords, and the specific subsequent processing steps are the same and will not be described herein again.

In practical applications, a person skilled in the art may use a suitable deduplication rule according to practical situations, for example, an algorithm deduplication, an artificial intelligence deduplication, and the like, which is not limited in this application embodiment.

In the embodiment of the present application, a feasible implementation manner is provided for step S103, and specifically, the implementation manner may include the steps of:

step S1031: and determining at least one keyword for determining a selling point word in the keywords corresponding to the target commodity.

As described above, part of the keywords extracted in step S102 may be used to directly generate the recommendation label, and part of the keywords may be subjected to inference, packaged as a selling point word, and then used to generate the recommendation label. In the embodiment of the application, at least one keyword for reasoning and packaging the selling point words is determined through the step.

Those skilled in the art can determine the at least one keyword according to the actual situation by using an appropriate rule, for example, a keyword library can be pre-constructed to distinguish the keywords for reasoning and packaging the selling point words; or, an artificial intelligence means may be adopted to distinguish keywords used for reasoning and packaging the selling point words, and the like, and the embodiment of the present application is not limited herein.

Step S1032: and determining a selling point word corresponding to the target commodity according to at least one keyword based on a preset mapping relation between the keyword and the selling point word.

In the embodiment of the application, the mapping relation between the key words and the selling point words is preset, and after the key words are obtained, the corresponding selling point words can be searched in the mapping relation by using the key words. In practical applications, a person skilled in the art may set a suitable mapping relationship according to actual situations, and the embodiment of the present application does not limit specific contents of the mapping relationship here.

In this embodiment, after step S104, the method may further include the steps of: determining the priority order of each generated recommendation label based on the attribute to which at least one keyword for generating the recommendation label belongs and the attribute to which the keyword corresponding to at least one selling point word belongs; and the priority of the recommendation label corresponding to the selling point word is higher than that of the recommendation label corresponding to the keyword.

As can be seen from the above description, each selling point word has a corresponding keyword, each keyword has a corresponding attribute, each selling point word also has a corresponding attribute, and the generated recommendation tag also has a corresponding attribute.

For the embodiment of the application, the generated recommended tags are sorted. In consideration of the fact that the selling point words can reflect the core information of the commodities, the priority of the recommendation labels corresponding to the selling point words is higher than that of the recommendation labels corresponding to the keywords. For the recommended labels corresponding to all the keywords, the priority order of the recommended labels can be determined according to the attributes to which the keywords respectively belong. For example, a keyword of the "raw material" attribute has a higher priority than a keyword of the "specification" attribute, and so on. Similarly, for the recommended labels corresponding to all the selling point words, the priority order of the recommended labels can be determined according to the attributes of the keywords corresponding to the selling point words respectively. In practical applications, a person skilled in the art may set the relationship between the attribute and the priority according to practical situations, and this is not specifically limited in the embodiment of the present application.

In the embodiment of the application, the recommended labels are sequenced, so that the most core information of the commodities can be sequenced at the front, and a user can quickly know the commodities through the recommended labels.

In the embodiment of the present application, after step S104, the method may further include the steps of: obtaining user portraits of various types; and respectively allocating corresponding recommended labels to various types of user portraits.

The user portrait refers to structuring and labeling of user information, and potential values of users are accurately mined by depicting data of multiple dimensions such as user features and user interests, so that related data can be recommended to different users in a personalized manner.

In other words, in the embodiment of the present application, different recommendation tags are displayed at corresponding user terminals according to user characteristics (obtained by means of user figures) of different users using the user terminals.

As an example, as shown in fig. 2, taking a tea-drink type takeout product as an example, after extracting corresponding keywords based on product attributes from description information (including dish names, i.e., product names) of the product by means of intelligent semantic association and the like, and reasoning and generating corresponding selling point words (for example, taking the attribute "main material" in fig. 2 as an example, the extracted keywords are "bayberry", "grape" and "juicy peach", the extracted keywords are "season", other attributes can be analogized, and the description is not repeated here), people matching can be performed, recommendation labels corresponding to users with different characteristics are intelligently displayed at the C end (for example, taking the attention function health preserving 'C type user' in fig. 2 as an example, recommendation labels such as 'hot drink can be made', 'qi and blood replenishing' and the like can be emphatically displayed, and users with other characteristics can be analogized and are not described herein again). It should be noted that the user representation and the commodity information shown in fig. 2 are only schematic, and the specific data content is based on actual implementation, and the example in fig. 2 should not be construed as limiting the application.

According to the generation method of the recommended label, the bottom layer does not need to be optimized, the recommended label of the commodity can be quickly generated only by using the information data of the commodity description on the existing line and capturing the off-line data through the algorithm for matching and reasoning based on the attributes that the different types of commodities are suitable for display and defined in advance, and the collection time and cost of the recommended label are remarkably reduced. The recommendation label is used as the highlighted display content of the commodity core information, so that the core information of the commodity can be captured quickly through the recommendation label when the user purchases the commodity, and the commodity purchasing efficiency of the user is improved.

An embodiment of the present application provides a method for displaying a recommended label, and as shown in fig. 3, the method includes:

step S301: responding to a triggering operation for checking commodities, acquiring recommended labels and commodity information of corresponding commodities, wherein the recommended labels of each commodity are generated based on at least one keyword and at least one selling point word corresponding to the commodity, the selling point words corresponding to the commodities are determined according to the at least one keyword corresponding to the commodities, and the keywords corresponding to the commodities are extracted from the description information of the commodities aiming at least one preset attribute;

for the embodiment of the present application, the execution subject may be a user side. The user side may specifically refer to a terminal device, or may refer to an application running on the terminal device, such as an application software or an applet, but is not limited thereto. In practical applications, the terminal device includes, but is not limited to, a mobile terminal, a smart terminal, and the like, such as a mobile phone, a smart phone, a tablet computer, a notebook computer, a personal digital assistant, a portable multimedia player, a navigation device, and the like. It will be understood by those skilled in the art that the configuration according to the embodiment of the present application can be applied to a fixed type terminal such as a digital television, a desktop computer, etc., in addition to elements particularly used for mobile purposes.

In the embodiment of the application, a user can view commodity-related information such as a commodity list, a commodity card or commodity details through related operations, for example, trigger a corresponding function module in a user side to generate a trigger operation for the commodity-related information. It will be appreciated that the triggering operation may vary from one terminal device to another used by the user. For example, if the terminal device used by the user includes a touch screen display screen, the user may perform a trigger operation by a touch manner such as clicking, double clicking, or gesture; for another example, if the terminal device used by the user does not include a touch screen display, the user may operate an input device such as a mouse or a keyboard, and/or an input means such as bluetooth or infrared remote control to perform a trigger operation; for example, if the terminal device used by the user includes a specific sensor, the triggering operation may also be executed by using the detected sensor signals such as the voice signal and the shake, and a person skilled in the art may set the specific content and manner of the triggering operation according to the actual situation.

In the embodiment of the application, the commodity information can be different according to whether the triggering operation is used for checking the commodity list, the commodity card or the commodity details, the specific commodity information content can be set according to the actual situation, and the embodiment of the application is not limited here.

In the embodiment of the present application, the description information of a certain commodity may refer to information that describes the commodity and is input by the affiliated merchant, and the description information may be displayed on a commodity detail page at a user end, and is used to introduce information such as characteristics, materials, and specifications of the commodity. The format of the descriptive information includes, but is not limited to, text, images, audio, video, attachments, and the like. The description information of image, audio, video and attachment format can be converted or extracted into text format for subsequent processing, or can be directly used for subsequent processing. Further, the descriptive information may also include the name of the item, since some characteristics or information of the item may also be included in the name of the item, which helps to generate a more accurate recommended label.

In the embodiment of the present application, the various attributes of the product refer to product properties of the product in different dimensions, and are used as a reference for extracting features of the product in each property dimension. For example, taking a tea-based commodity as an example, the attributes may include: base, tea top, taste, mouthfeel, dairy type, fruit variety, raw material, auxiliary material, specification, preparation method, packaging method, component, suggested collocation, selling point/efficacy and the like, but are not limited thereto. In practical application, a person skilled in the art can preset the attribute reference according to an actual situation, and the number and the content of the attributes are not specifically limited in the embodiment of the present application.

In the embodiment of the application, the extraction of the keywords may be performed by selecting part or all of the preset attributes according to a predetermined rule, for example, only selecting the attributes with importance higher than a certain threshold; or selecting an attribute with a correlation degree higher than a certain threshold value according to the characteristics or categories of the commodities. In practical applications, a machine learning algorithm may be used to select an appropriate at least one attribute for extracting the keyword.

In the embodiment of the present application, in consideration that commodities of different categories (or called categories) may have different attributes, a person skilled in the art may define the attribute references for the commodities of different categories according to actual situations.

In the embodiment of the application, extracting the keywords from the description information can also be understood as capturing the keywords from the description information. In practical application, a person skilled in the art may extract each keyword by using a suitable capture algorithm according to an actual situation, for example, a keyword matching algorithm, a keyword extraction algorithm, a machine learning algorithm, and the like, which is not limited in the embodiment of the present application.

In the embodiment of the application, part of the extracted keywords can be used for directly generating the recommendation label, and part of the extracted keywords can be analyzed and reasoned to be packaged into selling point words and then used for generating the recommendation label as one of important data sources of the commodity recommendation label. Those skilled in the art can determine the keywords for directly generating the recommended labels and the keywords for inferring the selling point words according to actual situations, and the embodiment of the present application is not particularly limited herein.

In the embodiment of the present application, the selling point word refers to a word for expressing a unique sanction or distinctive feature or characteristic of a commodity. In the embodiment of the application, the determined selling point words may be one or more. Each selling point word is obtained by reasoning and packaging the keywords. Specifically, one selling point word may be inferred by one keyword or may be inferred by a plurality of keywords. Those skilled in the art can determine each selling point word by using a suitable inference algorithm according to actual conditions, for example, an intelligent semantic association, a matching algorithm, a machine learning algorithm, and the like, which is not limited in the embodiment of the present application.

In the embodiment of the application, part or all of the extracted keywords and part or all of the determined attributes of the selling point words may be selected according to a predetermined rule to generate the recommended label, for example, only the keywords and/or the selling point words with importance higher than a certain threshold are selected, or the keywords and/or the selling point words with relevance higher than a certain threshold are selected according to the characteristics or categories of the goods, the merchants, or the users. In practical applications, a machine learning algorithm may be used to select an appropriate at least one keyword and/or selling point word to generate the recommended label.

In the embodiment of the present application, the at least one keyword for determining the selling point words and the at least one keyword for generating the recommended labels may be completely different, partially the same, or completely the same, and may specifically refer to the above description, which is not described herein again.

As will be understood by those skilled in the art, the process of generating the recommended labels based on the keywords and the selling point words may be understood as the process of converting the keywords and the selling point words into data that can be identified by the user terminal by the server terminal. And the user side responds to the trigger operation and can acquire the recommended label from the server for displaying.

Step S302: and displaying at least one recommended label and commodity information of the corresponding commodity.

In the embodiment of the application, the generated recommendation label can be a short label of the commodity core information displayed to the user when the commodity is presented to the user, so as to help the user make a purchasing decision.

In practical application, the recommended tag may be displayed in a merchandise list of a store, may also be displayed in a page of merchandise details, and may also be displayed in a merchandise card at a specific page, channel, search, or the like.

In practical applications, in order to avoid that excessive recommended tags make a user not be able to correctly know the core information of the product, the number of the displayed recommended tags may be controlled, for example, not more than 3 recommended tags, and a person skilled in the art may set the number of the displayed recommended tags according to actual situations, which is not limited herein in the embodiments of the present application. Specifically, the recommended tags not exceeding the preset display number may be determined by the server and then sent to the user side for display, or the server may also send all the generated recommended tags to the user side, and the recommended tags not exceeding the preset display number are determined by the user side for display, which is not limited in the embodiment of the present application.

In this embodiment of the present application, a feasible implementation manner is provided for the step S302, and specifically, the step of displaying at least one recommended label of each of the corresponding commodities may include: displaying at least one recommended label of the commodity according to the priority order of the recommended labels of the commodity; the priority order is determined based on the attribute to which at least one keyword used for generating the recommendation label respectively belongs and the attribute to which the keyword corresponding to at least one selling point word respectively belongs; and the priority of the recommendation label corresponding to the selling point word is higher than that of the recommendation label corresponding to the keyword.

For the embodiment of the application, the generated recommended tags are sorted. In consideration of the fact that the selling point words can reflect the core information of the commodities, the priority of the recommendation labels corresponding to the selling point words is higher than that of the recommendation labels corresponding to the keywords. For the recommended labels corresponding to all the keywords, the priority order of the recommended labels can be determined according to the attributes to which the keywords respectively belong. For example, a keyword for the "raw material" attribute has a higher priority than a keyword for the "specification" attribute, and so on. Similarly, for the recommended labels corresponding to all the selling point words, the priority order of the recommended labels can be determined according to the attributes of the keywords corresponding to the selling point words respectively. In practical applications, a person skilled in the art may set the relationship between the attribute and the priority according to practical situations, and this is not specifically limited in the embodiment of the present application.

In this embodiment of the present application, a feasible implementation manner is provided for step S301, and specifically, the step of obtaining the recommended label of the corresponding product may include: and acquiring a recommended label of a corresponding commodity corresponding to the user image of the current user.

The user portrait refers to structuring and labeling of user information, and potential values of users are accurately mined by depicting data of multiple dimensions such as user features and user interests, and the user portrait is used for recommending related data to different users in a personalized manner.

In the embodiment of the present application, an example of generating and displaying a recommendation tag is shown in fig. 4, taking a take-away product such as a tea drink as an example. As shown in fig. 4, by using the commodity description information displayed at the user end, the keyword in the original field is extracted (for example, the keyword "hot" in the description information is extracted), and the selling point word in the inference field is further obtained (the keyword "hot" can infer the selling point word "hot drink ready"), that is, the corresponding recommendation label "hot drink ready" can be displayed on both the menu page and the dish detail page of the user end. Other dishes (here, drinks) can be analogized, and are not described in detail here. It should be noted that the beverage shown in fig. 4 is only an illustration, specific commodities are subject to practical implementation, and the example in fig. 4 should not be construed as a limitation to the present application.

The embodiment of the application provides a commodity display method, as shown in fig. 5, the method includes:

step S501: displaying keywords of the commodities on a commodity detail page, wherein the keywords are extracted from the description information of the corresponding commodities aiming at least one preset attribute;

for the embodiment of the present application, the execution main body may be a user side, and for the user side, reference may be made to the above description, which is not described herein again.

The description information of a certain commodity may refer to information describing the commodity input by the affiliated merchant, and may be usually displayed on a commodity detail page at the user side. In the embodiment of the application, the extracted keywords of the commodity are used for replacing the description information to be displayed on the commodity detail page of the user side, so that the content of the description information is more visual, and the speed of reading the description information by the user is improved.

For the implementation of keyword extraction in the embodiment of the present application, reference may be specifically made to the description above, and details are not described herein again.

As an example, as shown in the content in the commodity detail on the rightmost side of fig. 4, the keyword of the attribute "tea bottom" is "black tea", and other keywords are analogized, and the extracted keyword is directly displayed in the commodity detail page, so that the content of the description information is more intuitive.

Step S502: and displaying a recommended label of the commodity on the commodity list page, wherein the recommended label is generated based on at least one keyword and at least one selling point word corresponding to the corresponding commodity, and the selling point word is determined according to the at least one keyword corresponding to the corresponding commodity.

For details of the implementation manner of the selling point word extraction, the implementation manner of the recommendation label generation, and the presentation of the recommendation label in the embodiment of the present application, reference may be specifically made to the above description, and details are not described herein again.

According to the commodity display method, the core information of the commodity is visually and prominently displayed, so that a user can quickly know the commodity when the commodity is selected, and the selection efficiency of the user is improved.

According to the display method of the recommended label, the recommended label is used as the highlighted display content of the core information of the commodity, so that the core information of the commodity can be captured quickly through the recommended label when the user buys the commodity, and the commodity shopping efficiency of the user is improved.

An embodiment of the present application provides a device for generating a recommended label, and as shown in fig. 6, the generating device 60 may include: an acquisition module 601, an extraction module 602, a determination module 603, and a generation module 604, wherein,

the obtaining module 601 is configured to obtain description information of a target commodity;

the extracting module 602 is configured to extract keywords corresponding to at least one predetermined attribute from the description information;

the determining module 603 is configured to determine, according to at least one keyword corresponding to the target product, a selling point word corresponding to the target product;

the generating module 604 is configured to generate a recommended label of the target product based on at least one keyword and at least one selling point word corresponding to the target product.

In an optional implementation manner, when the extracting module 602 is configured to extract, from the description information, the keywords of the target product corresponding to the predetermined at least one attribute, the extracting module is specifically configured to:

acquiring at least one matching word from a prefix matching word, a suffix matching word and a complete matching word which are respectively corresponding to at least one attribute;

based on the obtained matching words, executing at least one of the following ways of extracting the keywords of the target commodity to obtain the keywords of at least one attribute corresponding to the target commodity:

extracting a first keyword of the target commodity from the post-content matched with the prefix matching words in the description information based on the prefix matching words;

extracting a second keyword of the target commodity from the preposed content of the matched suffix matching words in the description information based on the suffix matching words;

and based on the complete matching words, extracting the content matched with the complete matching words in the description information as third key words of the target commodity.

In an optional implementation manner, when the determining module 603 is configured to determine, according to at least one keyword corresponding to a target product, a selling point word corresponding to the target product, specifically:

determining at least one keyword for determining a selling point word in each keyword corresponding to the target commodity;

and determining a selling point word corresponding to the target commodity according to at least one keyword based on a preset mapping relation between the keyword and the selling point word.

In an alternative embodiment, the extracting module 602, before being configured to extract the keywords corresponding to the predetermined at least one attribute respectively of the target product from the description information, is further configured to:

acquiring the category of a target commodity;

and determining at least one preset attribute corresponding to the category.

In an alternative embodiment, the generating module 604 is further configured to, after being configured to generate the recommended label of the target product based on the at least one keyword and the at least one selling point word corresponding to the target product, further:

determining the priority order of each generated recommendation label based on the attribute to which at least one keyword for generating the recommendation label belongs and the attribute to which the keyword corresponding to at least one selling point word belongs;

and the priority of the recommendation label corresponding to the selling point word is higher than that of the recommendation label corresponding to the keyword.

In an alternative embodiment, the generating module 604 is further configured to, after being configured to generate the recommended label of the target product:

obtaining user portraits of various types;

and respectively allocating corresponding recommended labels to various types of user portraits.

In an alternative embodiment, the description information of the target product includes a product name and a description text of the target product.

The apparatus in the embodiments of the present application may perform the method provided in the embodiments of the present application, and the implementation principle is similar, the actions performed by the modules in the apparatus in the embodiments of the present application correspond to the steps in the method in the embodiments of the present application, and for detailed functional description and beneficial effects generated by the modules in the apparatus, reference may be made to the description in the corresponding method shown in the foregoing specifically, and details are not repeated here.

An embodiment of the present application provides a display apparatus for a recommended label, as shown in fig. 7, the display apparatus 70 may include: a response module 701 and a presentation module 702, wherein,

the response module 701 is configured to, in response to a trigger operation for checking a commodity, obtain a recommended label and commodity information of a corresponding commodity, where the recommended label of each commodity is generated based on at least one keyword and at least one selling point word corresponding to the commodity, the selling point word corresponding to the commodity is determined according to the at least one keyword corresponding to the commodity, and the keyword corresponding to the commodity is extracted from description information of the commodity for a predetermined at least one attribute;

the display module 702 is configured to display at least one recommended label and merchandise information of a corresponding merchandise.

In an alternative embodiment, the displaying module 702, when being configured to display, for each of the corresponding commodities, at least one recommended label of the commodity, is specifically configured to:

displaying at least one recommended label of the commodity according to the priority order of the recommended labels of the commodity; the priority order is determined based on the attribute to which at least one keyword used for generating the recommendation label respectively belongs and the attribute to which the keyword corresponding to at least one selling point word respectively belongs;

In an optional implementation manner, when the response module 701 is used to obtain the recommended label of the corresponding product, it is specifically configured to:

and acquiring a recommended label of a corresponding commodity corresponding to the user image of the current user.

The apparatus of the embodiment of the present application may execute the method provided by the embodiment of the present application, and the implementation principle is similar, the actions executed by the modules in the apparatus of the embodiments of the present application correspond to the steps in the method of the embodiments of the present application, and for the detailed functional description and the beneficial effects generated by the modules of the apparatus, reference may be specifically made to the description in the corresponding method shown in the foregoing, and no further description is given here.

The present embodiment provides a display device for merchandise, as shown in fig. 8, the display device 80 may include: a first display module 801 and a second display module 802, wherein,

the first display module 801 is configured to display a keyword of a product on a product detail page, where the keyword is extracted from description information of the corresponding product for a predetermined at least one attribute;

the second display module 802 is configured to display a recommended label of a product on a product list page, where the recommended label is generated based on at least one keyword and at least one selling point word corresponding to the corresponding product, and the selling point word is determined according to the at least one keyword corresponding to the corresponding product.

An embodiment of the present application provides an electronic device, which includes a memory, a processor, and a computer program stored on the memory, where the processor executes the computer program to implement the steps of the foregoing method embodiments. Optionally, the electronic device may refer to the user side, or the electronic device may also refer to the service side.

In an alternative embodiment, an electronic device is provided, as shown in fig. 9, the electronic device 900 shown in fig. 9 comprising: a processor 901 and a memory 903. Wherein the processor 901 is coupled to the memory 903, such as via a bus 902. Optionally, the electronic device 900 may further include a transceiver 904, and the transceiver 904 may be used for data interaction between the electronic device and other electronic devices, such as transmission of data and/or reception of data. It should be noted that the transceiver 904 is not limited to one in practical applications, and the structure of the electronic device 900 is not limited to the embodiment of the present application.

The Processor 901 may be a CPU (Central Processing Unit), a general-purpose Processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other Programmable logic device, a transistor logic device, a hardware component, or any combination thereof. Which may implement or perform the various illustrative logical blocks, modules, and circuits described in connection with the disclosure. The processor 901 may also be a combination of computing functions, e.g., comprising one or more microprocessors, DSPs, and microprocessors, among others.

Bus 902 may include a path that transfers information between the above components. The bus 902 may be a PCI (Peripheral Component Interconnect) bus, an EISA (Extended Industry Standard Architecture) bus, or the like. The bus 902 may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one thick line is shown in FIG. 9, but this does not indicate only one bus or one type of bus.

The Memory 903 may be a ROM (Read Only Memory) or other type of static storage device that can store static information and instructions, a RAM (Random Access Memory) or other type of dynamic storage device that can store information and instructions, an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact disk Read Only Memory) or other optical disk storage, optical disk storage (including Compact disk, laser disk, optical disk, digital versatile disk, blu-ray disk, etc.), a magnetic disk storage medium, other magnetic storage devices, or any other medium that can be used to carry or store a computer program and that can be Read by a computer, without limitation.

The memory 903 is used for storing computer programs for executing the embodiments of the present application, and the processor 901 controls the execution. The processor 901 is adapted to execute a computer program stored in the memory 903 to implement the steps shown in the aforementioned method embodiments.

Embodiments of the present application provide a computer-readable storage medium, on which a computer program is stored, and when being executed by a processor, the computer program may implement the steps and corresponding contents of the foregoing method embodiments.

Embodiments of the present application further provide a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps and corresponding contents of the foregoing method embodiments can be implemented.

The terms "first," "second," "third," "1," "2," and the like in the description and claims of this application and in the above-described drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It should be understood that the data so used are interchangeable under appropriate circumstances such that the embodiments of the application described herein are capable of operation in other sequences than illustrated or otherwise described herein.

It should be understood that, although each operation step is indicated by an arrow in the flowchart of the embodiment of the present application, the implementation order of the steps is not limited to the order indicated by the arrow. In some implementation scenarios of the embodiments of the present application, the implementation steps in the flowcharts may be performed in other sequences as desired, unless explicitly stated otherwise herein. In addition, some or all of the steps in each flowchart may include multiple sub-steps or multiple stages based on an actual implementation scenario. Some or all of these sub-steps or stages may be performed at the same time, or each of these sub-steps or stages may be performed at different times, respectively. In a scenario where execution times are different, an execution sequence of the sub-steps or the phases may be flexibly configured according to requirements, which is not limited in the embodiment of the present application.

The foregoing is only an optional implementation manner of a part of implementation scenarios in the present application, and it should be noted that, for those skilled in the art, other similar implementation means based on the technical idea of the present application are also within the protection scope of the embodiments of the present application without departing from the technical idea of the present application.

Claims

1. A method for generating a recommendation tag is characterized by comprising the following steps:

acquiring description information of a target commodity;

extracting keywords of at least one preset attribute respectively corresponding to the target commodity from the description information;

and generating a recommendation label of the target commodity based on at least one keyword and at least one selling point word corresponding to the target commodity.

2. The generation method according to claim 1, wherein the extracting, from the description information, the keywords of the target product respectively corresponding to the predetermined at least one attribute includes:

acquiring at least one matching word from a prefix matching word, a suffix matching word and a complete matching word which are respectively corresponding to the at least one attribute;

based on the obtained matching words, executing at least one of the following ways of extracting the keywords of the target commodity to obtain the keywords of the target commodity corresponding to the at least one attribute:

extracting a first keyword of the target commodity from the post-content matched with the prefix matching word in the description information based on the prefix matching word;

extracting a second keyword of the target commodity from the prepositive content matched with the suffix matching words in the description information based on the suffix matching words;

and extracting the content matched with the complete matching words in the description information as third key words of the target commodity based on the complete matching words.

3. A display method of a recommended label is characterized by comprising the following steps:

4. A method of displaying a product, comprising:

5. An apparatus for generating a recommended label, comprising:

the extraction module is used for extracting keywords of at least one preset attribute respectively corresponding to the target commodity from the description information;

and the generating module is used for generating a recommended label of the target commodity based on at least one keyword and at least one selling point word corresponding to the target commodity.

6. A presentation device for a recommended label, comprising:

7. A display device for merchandise, comprising:

the system comprises a first display module, a second display module and a display module, wherein the first display module is used for displaying keywords of commodities on a commodity detail page, and the keywords are extracted from description information of the corresponding commodities aiming at least one preset attribute;

the second display module is used for displaying recommended labels of the commodities on the commodity list page, the recommended labels are generated based on at least one keyword and at least one selling point word corresponding to the corresponding commodities, and the selling point words are determined according to the at least one keyword corresponding to the corresponding commodities.

8. An electronic device comprising a memory, a processor and a computer program stored on the memory, characterized in that the processor executes the computer program to implement the steps of the method of any of claims 1-2 or 3 or 4.

9. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any of claims 1-2 or 3 or 4.

10. A computer program product comprising a computer program, characterized in that the computer program realizes the steps of the method of any of claims 1-2 or 3 or 4 when executed by a processor.