Method for generating and displaying recommended tags, corresponding device and electronic device

Abstract

The present application provides a method for generating and displaying a recommendation tag, a corresponding device, and an electronic device. The method includes: obtaining the description information of the target product; extracting keywords corresponding to at least one predetermined attribute of the target product from the description information; determining at least one selling point word corresponding to the target product based on at least one keyword corresponding to the target product; and generating a recommendation tag for the target product based on each keyword and each selling point word corresponding to the target product. This method effectively utilizes the existing description information of the product, extracts keywords from the description information through predetermined product attributes, and determines selling point words based on the keywords, so that the recommendation tag of the product can be generated based on the keywords and selling point words. This method uses the recommendation tag as the prominent display content of the core information of the product, which helps users quickly capture the core information of the product through the recommendation tag when purchasing the product, thereby improving the user's product selection efficiency.

Description

Technical Field

[0001] The present application relates to the field of information processing technology. Specifically, the present application relates to a method for generating and displaying recommendation tags, a corresponding device, and an electronic device. Background Art

[0002] As we all know, the close integration of the internet has brought new opportunities for the development of traditional industries, and online consumption has become a popular economic form in recent years. However, after years of rapid expansion, the online consumer market has become increasingly homogenized in the information and functions provided by various platforms. How to optimize the design of this information and functions has become a reflection of the competitive strength of online consumer platforms.

[0003] At present, some online consumption platforms lack the ability to prominently display the core information of products, resulting in users being unable to quickly capture the core information of products, such as main raw materials, specifications, etc. when purchasing products. Especially when the product name cannot reflect the content of the product, the user's decision-making efficiency in purchasing products is low. Summary of the Invention

[0004] The purpose of the embodiments of this application is to solve the technical problem of the lack of ability to display core information of goods.

[0005] According to a first aspect of an embodiment of the present application, a method for generating a recommendation tag is provided, the method comprising:

[0006] Get the description information of the target product;

[0007] Extracting at least one predetermined keyword of the attribute corresponding to the target product from the description information;

[0008] Determine a selling point word corresponding to the target product based on at least one keyword corresponding to the target product;

[0009] Based on at least one keyword and at least one selling point word corresponding to the target product, a recommendation tag for the target product is generated.

[0010] According to a second aspect of an embodiment of the present application, a method for displaying a recommendation tag is provided, the method comprising:

[0011] In response to a trigger operation for viewing a product, obtaining a recommended tag and product information for the corresponding product, wherein the recommended tag for each product is generated based on at least one keyword and at least one selling point word corresponding to the product, the selling point word corresponding to the product is determined based on the at least one keyword corresponding to the product, and the keyword corresponding to the product is extracted from the product description information based on at least one predetermined attribute;

[0012] At least one recommended tag and product information of the corresponding product is displayed.

[0013] According to a third aspect of the embodiments of the present application, a method for displaying goods is provided, the method comprising:

[0014] Displaying product keywords on the product details page, where the keywords are extracted from the product description information for at least one predetermined attribute;

[0015] The recommended tags of the products are displayed on the product list page. The recommended tags are generated based on at least one keyword and at least one selling point word corresponding to the corresponding product. The selling point word is determined based on the at least one keyword corresponding to the corresponding product.

[0016] According to a fourth aspect of an embodiment of the present application, a device for generating a recommendation tag is provided, the device comprising:

[0017] The acquisition module is used to obtain the description information of the target product;

[0018] An extraction module, configured to extract keywords corresponding to at least one predetermined attribute of the target product from the description information;

[0019] a determination module, configured to determine a selling point word corresponding to the target product based on at least one keyword corresponding to the target product;

[0020] The generating module is used to generate a recommendation tag for the target product based on at least one keyword and at least one selling point word corresponding to the target product.

[0021] According to a fifth aspect of an embodiment of the present application, a device for displaying recommendation labels is provided, the device comprising:

[0022] a response module, configured to obtain, in response to a trigger operation for viewing a product, a recommended tag and product information for the corresponding product, wherein the recommended tag for each product is generated based on at least one keyword and at least one selling point word corresponding to the product, wherein the selling point word corresponding to the product is determined based on the at least one keyword corresponding to the product, and wherein the keyword corresponding to the product is extracted from the product description information based on at least one predetermined attribute;

[0023] The display module is used to display at least one recommended tag and product information of the corresponding product.

[0024] According to a sixth aspect of the embodiments of the present application, there is provided a commodity display device, the device comprising:

[0025] A first display module is used to display product keywords on the product details page, where the keywords are extracted from the description information of the corresponding product based on at least one predetermined attribute;

[0026] The second display module is used to display the recommended tags of the products on the product list page. The recommended tags are generated based on at least one keyword and at least one selling point word corresponding to the corresponding product. The selling point word is determined based on the at least one keyword corresponding to the corresponding product.

[0027] According to the seventh aspect of the embodiments of the present application, an electronic device is provided, which includes: a memory, a processor and a computer program stored on the memory, and the processor executes the computer program to implement the steps of the method provided in the first aspect of the embodiments of the present application.

[0028] According to the eighth aspect of the embodiments of the present application, an electronic device is provided, which includes: a memory, a processor and a computer program stored on the memory, and the processor executes the computer program to implement the steps of the method provided in the second aspect or the third aspect of the embodiments of the present application.

[0029] According to the ninth aspect of the embodiment of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method provided in the first aspect of the embodiment of the present application are implemented.

[0030] According to the tenth aspect of the embodiments of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method provided in the second aspect or the third aspect of the embodiments of the present application are implemented.

[0031] According to an eleventh aspect of the embodiments of the present application, a computer program product is provided, which includes a computer program, and when the computer program is executed by a processor, the steps of the method provided in the first aspect of the embodiments of the present application are implemented.

[0032] According to the twelfth aspect of the embodiments of the present application, a computer program product is provided, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the method provided by the second aspect or the third aspect of the embodiments of the present application.

[0033] The recommendation tag generation method, display method, corresponding device and electronic device provided in the embodiments of the present application effectively utilize the existing description information of the product. Through predetermined product attributes, keywords are extracted from the description information, and selling points are determined based on the keywords. Recommendation tags for the product can be generated based on the keywords and selling points. The recommendation tags are used as the prominent display content of the core information of the product. This helps users to quickly capture the core information of the product through the recommendation tags when purchasing the product, thereby improving the user's product selection efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for describing the embodiments of the present application.

[0035] Figure 1 A flowchart of a method for generating a recommendation tag provided in an embodiment of the present application;

[0036] Figure 2 A schematic diagram of displaying recommended tags based on user characteristics provided in an embodiment of the present application;

[0037] Figure 3 A flowchart of a method for displaying recommended tags provided in an embodiment of the present application;

[0038] Figure 4 A schematic diagram of generating and displaying recommended tags provided in an embodiment of the present application;

[0039] Figure 5 A flowchart of a method for displaying goods provided in an embodiment of the present application;

[0040] Figure 6 A schematic diagram of the structure of a device for generating recommended tags provided in an embodiment of the present application;

[0041] Figure 7 A schematic diagram of the structure of a display device for recommendation labels provided in an embodiment of the present application;

[0042] Figure 8 A schematic structural diagram of a commodity display device provided in an embodiment of the present application;

[0043] Figure 9 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0044] The following describes the embodiments of the present application in conjunction with the accompanying drawings. It should be understood that the embodiments described below in conjunction with the accompanying drawings are exemplary descriptions for explaining the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions of the embodiments of the present application.

[0045] Those skilled in the art will understand that, unless otherwise stated, the singular forms "a", "an" and "the" used herein may also include plural forms. It should be further understood that the terms "including" and "comprising" used in the embodiments of the present application mean that the corresponding features can be implemented as the information, data, steps, operations, elements and / or components presented, but do not exclude implementation as other features, information, data, steps, operations, elements, components and / or combinations thereof supported by the present technical field. It should be understood that when we say that an element is "connected" or "coupled" to another element, the element can be directly connected or coupled to the other element, or it can refer to that the element and the other element establish a connection relationship through an intermediate element. In addition, the "connection" or "coupling" used here can include wireless connection or wireless coupling. The term "and / or" used here indicates at least one of the items defined by the term, for example, "A and / or B" can be implemented as "A", or as "B", or as "A and B".

[0046] In order to make the objectives, technical solutions and advantages of this application clearer, the implementation methods of this application will be further described in detail below with reference to the accompanying drawings.

[0047] In response to the areas that need improvement in the relevant technologies, the embodiments of the present application propose a method for generating and displaying recommendation tags, a corresponding device and an electronic device. This solution uses the existing descriptive information of the product to generate recommendation tags for the product, and uses the recommendation tags as the prominent display content of the core information of the product, which helps to improve the decision-making efficiency of users when purchasing products.

[0048] The inventors of this application realized that the merchant side can also be directly used as the data source for recommendation tags, but there is a lack of entry and rule requirements for entering rich product information on the merchant side. If the merchant backend is directly optimized to increase the dimensions of product information entered by the merchant side, allowing merchants to fill in richer and more complete product information, the biggest disadvantage is that the cycle is long and involves multiple departments. For example, operations need to redefine the product categories and dimensional fields of product information; the merchant side needs to transform product capabilities and redefine product assessment standards; and merchants and first-line BD (Business Development) must be encouraged to fill in or update product information in a timely manner, which is costly.

[0049] The technical solution provided in the embodiment of the present application utilizes the existing description information of the product, extracts keywords from the description information through predetermined product attributes, and determines selling points based on the keywords. Based on the keywords and selling points, recommended tags for the product can be quickly generated, significantly reducing the time and cost of collecting recommended tags.

[0050] The following describes several exemplary embodiments to illustrate the technical solutions of the embodiments of the present application and the technical effects produced by the technical solutions of the present application. It should be noted that the following embodiments can refer to, draw on, or combine with each other, and the same terms, similar features, and similar implementation steps in different embodiments will not be repeated.

[0051] The present application provides a method for generating a recommendation tag. Figure 1 As shown, the method includes:

[0052] Step S101: Obtain description information of the target product.

[0053] For the embodiments of the present application, the execution entity may be a server, including but not limited to an independent physical server, a server cluster, a distributed system or a cloud server.

[0054] The target product refers to the product for which a recommendation tag is to be generated. There can be one or more target products, and each target product can be processed according to this solution. The same execution process will not be repeated here.

[0055] As an example, the target product can be all products containing description information in the database. The server processes the description information of all products in batches, generates a recommendation tag for each product, and then updates it to the user (Consumer) end (which can be referred to as the C end) for display. The target product can also be the product for which the merchant has recently entered description information or updated description information. The server processes the latest description information of the product immediately or periodically, generates a recommendation tag for the product, and then updates it to the user end for display. In actual applications, the target product can be determined according to actual needs, and the embodiments of this application do not specifically limit this.

[0056] In the embodiments of the present application, the descriptive information of a product may refer to the information describing the product entered by the merchant, which may typically be displayed on the product details page on the user's end to introduce the product's features, materials, specifications, and other information. The formats of the descriptive information include, but are not limited to, text, images, audio, video, attachments, etc. Descriptive information in the format of images, audio, video, and attachments may be converted or extracted into text format for subsequent processing, or may be used directly for subsequent processing.

[0057] In an embodiment of the present application, the description information of the target product may include not only description text, description image, description audio, description video, description attachment, etc., but also the product name, because the product name may also contain certain characteristics or information of the product, which helps to generate more accurate recommendation tags.

[0058] Step S102: extracting keywords corresponding to at least one predetermined attribute of the target product from the description information.

[0059] Among them, the various attributes of a product refer to the properties of the product in different dimensions, which are used as a benchmark for extracting the characteristics of the product in each dimension of the property. For example, taking tea beverages as an example, the attributes may include: base, tea top, flavor, taste, dairy type, fruit variety, raw materials, auxiliary materials, specifications, production method, packaging method, quantity, recommended combination, selling point / effect, etc., but are not limited to these. In actual applications, those skilled in the art can preset the attribute benchmark according to actual conditions, and the embodiment of this application does not specifically limit the number and content of the attributes.

[0060] In the embodiments of the present application, all or part of the preset attributes may be selected for keyword extraction according to predetermined rules, for example, only attributes with an importance above a certain threshold may be selected; or attributes with a relevance above a certain threshold may be selected based on the characteristics or category of the product. In practical applications, a machine learning algorithm may also be used to select at least one appropriate attribute for keyword extraction.

[0061] In the embodiments of the present application, considering that products of different categories (or categories) may have different attributes, those skilled in the art may define attribute benchmarks for different categories of products based on actual circumstances. Prior to executing this step, the following steps may also be included: obtaining the category of the target product; and determining at least one predetermined attribute corresponding to the category. In other words, the embodiments of the present application extract keywords for corresponding attributes based on the category of the target product.

[0062] In the embodiments of the present application, extracting keywords from the description information can also be understood as crawling keywords in the description information. In practical applications, those skilled in the art can use appropriate crawling algorithms to extract each keyword based on actual conditions, such as keyword matching algorithms, keyword extraction algorithms, machine learning algorithms, etc., and the embodiments of the present application do not limit this.

[0063] Table 1 takes tea beverages as an example and shows an example of extracting keywords corresponding to some attributes from description information.

[0064]

[0065]

[0066] Table 1

[0067] In the embodiments of this application, some of the extracted keywords can be used to directly generate recommendation tags, while others can be parsed, inferred, or derived, packaged as selling points, and then used to generate recommendation tags, serving as an important data source for product recommendation tags. Those skilled in the art can determine the keywords used to directly generate recommendation tags and the keywords used to infer selling points based on actual circumstances, and this embodiment of the application does not specifically limit this.

[0068] Step S103: Determine a selling point word corresponding to the target product based on at least one keyword corresponding to the target product.

[0069] Among them, selling point words refer to words used to express the unique or distinctive features or characteristics of a product. In the embodiment of the present application, the determined selling point words can be one or more. Each selling point word is obtained by reasoning and packaging from a keyword. Specifically, a selling point word can be inferred from one keyword, or it can be inferred from multiple keywords. Those skilled in the art can use appropriate reasoning algorithms to determine each selling point word according to actual circumstances, such as intelligent semantic association, matching algorithm, machine learning algorithm, etc., and the embodiment of the present application does not limit this.

[0070] It is understandable that each selling point word has a corresponding keyword, and each keyword has a corresponding attribute, so each selling point word also has a corresponding attribute (which may correspond to one or more).

[0071] Table 2 takes tea beverages as an example and shows an example of inferring selling point words from keywords corresponding to some extracted attributes.

[0072] property Keywords Selling point words Quantity 1000ml, 1000cc, 1L Extra large cup Main ingredients Oranges, lemons, grapefruits, kiwis High-dimensional C Specification Hot***ml, hot Can be made into hot drinks Specification Cold ***ml, smoothie Can be used for cold drinks taste 0 calorie sugar, slightly sweet, low sugar, sugar-free Low sugar / sugar-free

[0073] Table 2

[0074] In an embodiment of the present application, when determining the selling point words corresponding to the target product based on at least one keyword corresponding to the target product, the attributes of the keyword can also be combined, that is, the selling point words corresponding to the target product can be determined based on at least one keyword corresponding to the target product and its attributes.

[0075] Continuing with Table 2 as an example, when obtaining the keywords "orange", "lemon", "pomelo", "kiwi", etc., it is necessary to determine that their attributes are main ingredients before the selling point word "high-dimensional C" can be introduced. If their attributes are auxiliary ingredients, this selling point word cannot be obtained.

[0076] Step S104: Generate a recommendation tag for the target product based on at least one keyword and at least one selling point word corresponding to the target product.

[0077] In embodiments of the present application, some or all of the extracted keywords and some or all of the determined selling point word attributes may be selected according to predetermined rules to generate recommended tags. For example, only keywords and / or selling point words whose importance exceeds a certain threshold may be selected, or keywords and / or selling point words whose relevance exceeds a certain threshold may be selected based on the characteristics or categories of the product, merchant, or user. In practical applications, a machine learning algorithm may also be used to select at least one appropriate keyword and / or selling point word to generate a recommended tag.

[0078] In this embodiment of the present application, the at least one keyword used to determine the selling point in step S103 (referred to as the first keyword for ease of description) and the at least one keyword used to generate the recommendation tag in step S104 (referred to as the second keyword for ease of description) can 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 to execute step S103, and one or more of the second keywords are used to execute step S104.

[0079] Alternatively, at least one first keyword and at least one second keyword may be partially identical. As an example, one or more first keywords are determined from the keywords extracted in step S102 to execute step S103, and then one or more second keywords are determined to execute step S104. At least one of the one or more first keywords and the one or more second keywords is identical.

[0080] Alternatively, at least one first keyword and 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 to execute step S103, and the one or more first keywords are directly used as second keywords to execute step S104.

[0081] In the embodiment of the present application, a corresponding recommendation tag may be generated for each word of at least one keyword and at least one selling point word. Alternatively, each recommendation tag may be generated from one or more words of at least one keyword and at least one selling point word.

[0082] Those skilled in the art will appreciate that the process of generating recommendation tags based on keywords and selling points can be understood as converting keywords and selling points into data that can be recognized by the user terminal. After the recommendation tags are generated, they can be sent to the user terminal for display.

[0083] In an embodiment of the present application, the generated recommendation tag can be a short tag of the core information of the product displayed to the user when the product is presented to the user, to help the user make a purchasing decision. In actual applications, in order to avoid too many recommendation tags that prevent users from correctly knowing the core information of the product, the number of displayed recommendation tags can be controlled, for example, not more than 3, etc. Those skilled in the art can set the display number of recommendation tags according to actual conditions, and the embodiment of the present application does not limit this. Specifically, the server can determine the recommendation tags that do not exceed the predetermined display number, and then send them to the user end for display, or the server can also send all generated recommendation tags to the user end, and the user end can determine the recommendation tags that do not exceed the predetermined display number for display, and the embodiment of the present application does not limit this.

[0084] The method for generating recommendation tags provided in the embodiment of the present application can effectively utilize the existing descriptive information of the product. Through predetermined product attributes, keywords are extracted from the descriptive information, and selling points are determined based on the keywords. Then, recommendation tags for the product can be generated based on the keywords and selling points. This method uses the recommendation tags as the prominent display content of the core information of the product, which helps users quickly capture the core information of the product through the recommendation tags when purchasing the product, thereby improving the user's product purchasing efficiency.

[0085] In the embodiment of the present application, a feasible implementation method is provided for step S102, which may specifically include:

[0086] Step S1021: Obtain at least one matching word among a prefix matching word, a suffix matching word, and a complete matching word corresponding to at least one attribute.

[0087] In the embodiment of the present application, each attribute may have a corresponding matching pool, and each matching pool may contain at least one matching word among prefix matching words, suffix matching words, and complete matching words. This step can be understood as obtaining each matching word in the matching pool.

[0088] Prefix matching refers to a term where the prefix is fixed, while the content following the prefix can change dynamically. By searching for content that meets the matching requirements based on the prefix, you can find keywords that contain the prefix and other content.

[0089] Similarly, suffix matching refers to a matching term where the suffix is fixed, while the content preceding the suffix can change dynamically. By searching for content that meets the matching requirements using the suffix, you can find keywords that contain the suffix and other content.

[0090] Exact match words are used to find exactly the same content. If there is a word in the description information that is exactly the same as an exact match word, then the word can be used as a keyword.

[0091] Taking the products of the tea drink category as an example in Table 3, based on Table 1, it is an example of matching words used to extract keywords from the description information.

[0092]

[0093] Among them, the matching words corresponding to the attribute "base", such as "cow*", and the matching words corresponding to the attribute "taste", such as "clear*", are prefix matching words; the matching words corresponding to the attribute "base", such as "**tea", and the matching words corresponding to the attribute "tea topping", such as "**milk cap", are suffix matching words, and the matching word corresponding to the attribute "tea topping", such as "cheese", is a complete matching word. Among them, other matching words in Table 3 can be deduced by analogy and will not be elaborated here.

[0094] Step S1022: Based on the obtained matching words, perform at least one of the following methods to extract keywords of the target product, and obtain keywords corresponding to at least one attribute of the target product:

[0095] (1) Based on the prefix matching words, extract the first keyword of the target product from the postfix content that matches the prefix matching words in the description information.

[0096] For example, in Table 3, based on the prefix matching word "clear*" corresponding to the attribute "taste", the postfix content that matches this prefix matching word in the description information is "sweet", so the first keyword "sweet and clear" can be extracted.

[0097] (2) Based on the suffix matching words, extract the second keyword of the target product from the prefix content that matches the suffix matching words in the description information.

[0098] For example, in Table 3, based on the suffix matching word "*sweet" corresponding to the attribute "taste", the postfix content that matches this suffix matching word in the description information can be "not", "slightly", "clear", etc., so the second keywords "not sweet", "slightly sweet", "sweet and clear", etc. can be extracted.

[0099] (3) Based on the complete matching words, extract the content that matches the complete matching words in the description information as the third keyword of the target product.

[0100] For example, in Table 3, based on the complete matching word "cheese" corresponding to the attribute "tea topping", and there is the content "cheese" that matches this complete matching word in the description information, it can be extracted as the third keyword.

[0101] Among them, other keywords in Table 3 can be deduced by analogy and will not be elaborated here.

[0102] It can be understood that the number of the first keyword, the second keyword or the third keyword extracted based on each matching word can be one or more.

[0103] In an embodiment of the present application, considering that there are different types of matching words in the matching pool, the same keywords may be extracted based on different types of matching words. For example, the prefix matching word "clear*" and the suffix matching word "*sweet" corresponding to the attribute "taste" can both extract the keyword "clear and sweet". For another example, the complete matching word "cheese" and the prefix matching word "tea top**" corresponding to the attribute "tea top" can both extract the keyword "cheese". After step S102, it can also include: deduplication processing of the extracted keywords.

[0104] The subsequent steps are all based on the removed keywords. The specific subsequent processing steps are the same and will not be repeated here.

[0105] In actual applications, those skilled in the art can adopt appropriate deduplication rules according to actual conditions, such as algorithmic deduplication, artificial intelligence deduplication, etc., and the embodiments of this application do not limit this.

[0106] In the embodiment of the present application, a feasible implementation method is provided for step S103, which may specifically include the following steps:

[0107] Step S1031: Determine at least one keyword for determining a selling point word from among the keywords corresponding to the target product.

[0108] As described above, some of the keywords extracted in step S102 can be used to directly generate recommendation tags, while others can be inferred and packaged into selling point words and then used to generate recommendation tags. In this embodiment of the present application, at least one keyword is determined through this step to be used for inferring and packaging selling point words.

[0109] Those skilled in the art may adopt appropriate rules to determine the at least one keyword according to actual circumstances. For example, a keyword library may be pre-built to distinguish keywords used to infer packaging selling point words; or artificial intelligence means may be used to distinguish keywords used to infer packaging selling point words, etc. The embodiments of the present application are not limited here.

[0110] Step S1032: Based on the preset mapping relationship between keywords and selling point words, determine the selling point word corresponding to the target product according to at least one keyword.

[0111] In the embodiment of the present application, a mapping relationship between keywords and selling point words is pre-set. After obtaining a keyword, the keyword can be used to search for the corresponding selling point word in the mapping relationship. In actual application, those skilled in the art can set an appropriate mapping relationship based on actual conditions. The embodiment of the present application does not limit the specific content of the mapping relationship.

[0112] In an embodiment of the present application, after step S104, the following step may also be included: determining the priority order of each generated recommendation tag based on the attributes of at least one keyword used to generate the recommendation tag and the attributes of the keyword corresponding to at least one selling point word; wherein the priority of the recommendation tag corresponding to the selling point word is higher than the recommendation tag corresponding to the keyword.

[0113] From the introduction above, we can know that each selling point word has a corresponding keyword, and each keyword has a corresponding attribute, so each selling point word also has a corresponding attribute, and the generated recommendation tag also has a corresponding attribute.

[0114] For the embodiment of the present application, the generated recommended tags will be sorted. Among them, considering that the selling point words can better reflect the core information of the product, the priority of the recommended tags corresponding to the selling point words is higher than the recommended tags corresponding to the keywords. For the recommended tags corresponding to all keywords, the priority order of the recommended tags can be determined according to the attributes to which these keywords respectively belong. For example, the priority of the keyword with the "raw material" attribute is higher than the keyword with the "specification" attribute, etc. Similarly, for the recommended tags corresponding to all selling point words, the priority order of the recommended tags can be determined according to the attributes to which the keywords corresponding to these selling point words respectively belong. In actual applications, those skilled in the art can set the relationship between attributes and priorities according to actual conditions, and the embodiment of the present application does not make specific limitations on this.

[0115] In the embodiment of the present application, by sorting the recommended tags, the most core information of the product can be sorted at the front, which helps users quickly understand the product through the recommended tags.

[0116] In the embodiment of the present application, after step S104, the following steps may be included: obtaining user portraits of various types; and assigning corresponding recommendation tags to user portraits of various types.

[0117] Among them, user profiling refers to the structuring and labeling of user information. By depicting data from multiple dimensions such as user characteristics and user interests, the user's potential value can be accurately mined and used to recommend relevant data to different users in a personalized manner.

[0118] That is, in the embodiment of the present application, different recommendation tags will be displayed on the corresponding user terminal based on the user characteristics of different users using the user terminal (obtained with the help of user portraits).

[0119] As an example, Figure 2 As shown in the figure, taking tea takeaway products as an example, by using intelligent semantic association and other means, the corresponding keywords are extracted from the product description information (including the dish name, i.e. the product name) based on the product attributes, and the corresponding selling point words are inferred and generated (for example, Figure 2Taking the attribute "main ingredient" in the example, the extracted keywords are "bayberry", "grape", and "peach", and the corresponding selling point word is inferred to be "seasonal". Other attributes can be deduced by analogy and will not be repeated here. After that, crowd matching can be performed and the recommended tags corresponding to users with different characteristics can be intelligently displayed on the C-end (for example, Figure 2 For example, for users who are interested in health-related functions, the recommended tags such as "can be made into hot drinks" and "replenish qi and blood" can be displayed. The same can be applied to users with other characteristics. I will not elaborate on this here.) It should be noted that Figure 2 The user portraits and product information shown in the are for reference only. The specific data content is subject to actual implementation. Figure 2 The examples in the accompanying drawings should not be construed as limiting the present application.

[0120] The method for generating recommended tags provided in the embodiments of this application does not require underlying optimization. Instead, it simply uses existing online product description data based on predefined attributes suitable for display in different product categories, and then uses algorithms to capture offline data for matching and inference. This method can quickly generate recommended tags for products, significantly reducing the time and cost of collecting recommended tags. Using recommended tags as prominent display content for core product information helps users quickly capture the core information of products through recommended tags when purchasing, thereby improving their product selection efficiency.

[0121] The present invention provides a method for displaying recommended tags. Figure 3 As shown, the method includes:

[0122] Step S301: In response to a trigger operation for viewing a product, obtaining a recommended tag and product information for the corresponding product. The recommended tag for each product is generated based on at least one keyword and at least one selling point word corresponding to the product. The selling point word corresponding to the product is determined based on the at least one keyword corresponding to the product. The keyword corresponding to the product is extracted from the product description information based on at least one predetermined attribute.

[0123] For the embodiments of the present application, the execution subject may be a user terminal. The user terminal may specifically refer to a terminal device, or may refer to an application running on the terminal device, such as application software or an application applet, but is not limited thereto. In practical applications, terminal devices include but are not limited to mobile terminals, smart terminals, and the like, such as mobile phones, smart phones, tablet computers, laptop computers, personal digital assistants, portable multimedia players, navigation devices, and the like. It will be understood by those skilled in the art that, in addition to components specifically for mobile purposes, the structure according to the embodiments of the present application can also be applied to fixed-type terminals, such as digital televisions, desktop computers, and the like.

[0124] In an embodiment of the present application, a user can view product-related information such as a product list, product cards or product details through relevant operations, such as triggering a corresponding functional module in the user terminal to generate a trigger operation for product-related information. It is understandable that the trigger operation may be different depending on the terminal device used by the user. For example, if the terminal device used by the user includes a touch screen display, the user can perform a trigger operation through touch methods such as clicking, double-clicking, and gestures; for another example, if the terminal device used by the user does not include a touch screen display, the user can manipulate input devices such as a mouse, keyboard, and / or input means such as Bluetooth and infrared remote control to perform a trigger operation; for another example, if the terminal device used by the user includes a specific sensor, the trigger operation can also be performed using detected voice signals, shaking and other sensor signals. Those skilled in the art can set the specific content and method of the trigger operation according to actual conditions.

[0125] In the embodiment of the present application, the product information may be different depending on whether the triggering operation is used to view the product list, product card or product details. The specific product information content can be set according to actual conditions, and the embodiment of the present application does not limit this.

[0126] In an embodiment of the present application, the descriptive information of a certain product may refer to the information describing the product entered by the merchant to which it belongs, which can usually be displayed on the product details page of the user end to introduce the characteristics, materials, specifications and other information of the product. The format of the descriptive information includes but is not limited to text, images, audio, video, attachments, etc. Among them, the descriptive information in the format of images, audio, video, and attachments can be converted or extracted into text format before subsequent processing, or it can be directly used for subsequent processing. Furthermore, the descriptive information can also include the name of the product, because the product name may also contain certain characteristics or information of the product, which helps to generate more accurate recommendation tags.

[0127] In the embodiments of the present application, the various attributes of a product refer to the properties of the product in different dimensions, which are used as a benchmark for extracting the characteristics of the product in each dimension of the property. For example, taking tea beverages as an example, the attributes may include: base, tea top, flavor, mouthfeel, dairy type, fruit variety, raw materials, auxiliary materials, specifications, production method, packaging method, quantity, recommended combination, selling point / effect, etc., but are not limited to these. In actual applications, those skilled in the art can preset the attribute benchmark according to actual conditions, and the embodiments of the present application do not specifically limit the number and content of the attributes.

[0128] In the embodiments of the present application, keyword extraction can be performed by selecting some or all of the preset attributes according to predetermined rules, such as selecting only attributes whose importance exceeds a certain threshold, or selecting attributes whose relevance exceeds a certain threshold based on the characteristics or category of the product. In practical applications, a machine learning algorithm can also be used to select at least one appropriate attribute for keyword extraction.

[0129] In the embodiments of the present application, considering that commodities of different categories (or categories) may have different attributes, those skilled in the art may define attribute benchmarks for commodities of different categories respectively according to actual conditions.

[0130] In the embodiments of the present application, extracting keywords from the description information can also be understood as crawling keywords from the description information. In practical applications, those skilled in the art can use appropriate crawling algorithms to extract each keyword based on actual conditions, such as keyword matching algorithms, keyword extraction algorithms, machine learning algorithms, etc., and the embodiments of the present application do not limit this.

[0131] In the embodiments of this application, some of the extracted keywords can be used to directly generate recommendation tags, while others can be parsed and inferred, packaged into selling points, and then used to generate recommendation tags, serving as an important data source for product recommendation tags. Those skilled in the art can determine the keywords used to directly generate recommendation tags and the keywords used to infer selling points based on actual circumstances, and this embodiment of the application does not specifically limit this.

[0132] In the embodiment of the present application, a selling point word refers to a word used to express the unique or distinctive features or characteristics of a product. In the embodiment of the present application, the determined selling point words may be one or more. Each selling point word is obtained by reasoning and packaging from a keyword. Specifically, a selling point word may be inferred from a single keyword or from multiple keywords. Those skilled in the art may use appropriate reasoning algorithms to determine each selling point word according to actual circumstances, such as intelligent semantic association, matching algorithms, machine learning algorithms, etc., and the embodiment of the present application does not limit this.

[0133] In an embodiment of the present application, when determining the selling point words corresponding to the target product based on at least one keyword corresponding to the target product, the attributes of the keyword can also be combined, that is, the selling point words corresponding to the target product can be determined based on at least one keyword corresponding to the target product and its attributes.

[0134] In embodiments of the present application, a recommended tag may be generated by selecting some or all of the extracted keywords and some or all of the determined selling point word attributes according to predetermined rules. For example, only keywords and / or selling point words whose importance exceeds a certain threshold may be selected, or keywords and / or selling point words whose relevance exceeds a certain threshold may be selected based on the characteristics or categories of the product, merchant, or user. In practical applications, a machine learning algorithm may also be used to select at least one appropriate keyword and / or selling point word to generate a recommended tag.

[0135] In an embodiment of the present application, at least one keyword used to determine the selling point word and at least one keyword used to generate the recommendation tag may be completely different, partially the same, or completely the same. For details, please refer to the above introduction and will not be repeated here.

[0136] In the embodiment of the present application, a corresponding recommendation tag may be generated for each word of at least one keyword and at least one selling point word. Alternatively, each recommendation tag may be generated from one or more words of at least one keyword and at least one selling point word.

[0137] Those skilled in the art will appreciate that the process of generating recommendation tags based on keywords and selling points can be understood as the server converting keywords and selling points into data that can be recognized by the user. In response to the above triggering operation, the user can obtain the recommendation tags from the server for display.

[0138] Step S302: Display at least one recommended tag and product information of the corresponding product.

[0139] In an embodiment of the present application, the generated recommendation tag can be a short tag of the core information of the product displayed to the user when the product is presented to the user, to help the user make a purchasing decision.

[0140] In actual applications, recommendation tags can be displayed in the store's product list, or at the same time displayed on the product details page, and can also be displayed in product cards in specific pages, channels, searches, etc. The embodiment of this application does not specifically limit the display location of recommendation tags.

[0141] In actual applications, in order to avoid too many recommended tags that prevent users from correctly understanding the core information of the product, the number of recommended tags displayed can be controlled, for example, not more than 3, etc. Those skilled in the art can set the number of recommended tags displayed according to actual conditions, and this embodiment of the present application does not limit this. Specifically, the server can determine the recommended tags that do not exceed the predetermined number of displays and then send them to the user end for display, or the server can also send all generated recommended tags to the user end, and the user end can determine the recommended tags that do not exceed the predetermined number of displays for display, and this embodiment of the present application does not limit this.

[0142] In an embodiment of the present application, a feasible implementation method is provided for step S302. Specifically, for each product in the corresponding products, the step of displaying at least one recommended tag for the product may include: displaying at least one recommended tag for the product in the order of priority of the various recommended tags for the product; the priority order is determined based on the attributes to which at least one keyword used to generate the recommended tag belongs and the attributes to which the keyword corresponding to at least one selling point word belongs; wherein, the priority of the recommended tag corresponding to the selling point word is higher than the recommended tag corresponding to the keyword.

[0143] For the embodiment of the present application, the generated recommended tags will be sorted. Among them, considering that the selling point words can better reflect the core information of the product, the priority of the recommended tags corresponding to the selling point words is higher than the recommended tags corresponding to the keywords. For the recommended tags corresponding to all keywords, the priority order of the recommended tags can be determined according to the attributes to which these keywords respectively belong. For example, the priority of the keyword with the "raw material" attribute is higher than the keyword with the "specification" attribute, etc. Similarly, for the recommended tags corresponding to all selling point words, the priority order of the recommended tags can be determined according to the attributes to which the keywords corresponding to these selling point words respectively belong. In actual applications, those skilled in the art can set the relationship between attributes and priorities according to actual conditions, and the embodiment of the present application does not make specific limitations on this.

[0144] In an embodiment of the present application, a feasible implementation method is provided for step S301. Specifically, the step of obtaining the recommended tags of the corresponding products may include: obtaining the recommended tags of the corresponding products corresponding to the user portrait of the current user.

[0145] Among them, user profiling refers to the structuring and labeling of user information. By depicting data from multiple dimensions such as user characteristics and user interests, the user's potential value can be accurately mined and used to recommend relevant data to different users in a personalized manner.

[0146] That is, in the embodiment of the present application, different recommendation tags will be displayed on the corresponding user terminal based on the user characteristics of different users using the user terminal (obtained with the help of user portraits).

[0147] In the embodiment of this application, taking tea-based takeaway products as an example, Figure 4 Shows an example of generating and displaying recommended tags. Figure 4As shown, through the product description information displayed on the user side, the keywords of the original field are extracted (for example, the keyword "hot" in the description information is extracted), and the selling point words of the inference field are further obtained (the keyword "hot" can be inferred as the selling point word "can make hot drinks"), and the corresponding recommended label "can make hot drinks" can be displayed on the menu page and the dish details page on the user side. Other dishes (here are drinks) can be deduced in this way, which will not be repeated here. It should be noted that Figure 4 The drinks shown are for reference only. The specific products are subject to actual implementation. Figure 4 The examples in the accompanying drawings should not be construed as limiting the present application.

[0148] The present invention provides a method for displaying goods. Figure 5 As shown, the method includes:

[0149] Step S501: Displaying product keywords on the product details page, where the keywords are extracted from the description information of the corresponding product based on at least one predetermined attribute;

[0150] For the embodiment of the present application, the execution subject may be a user terminal. For details about the user terminal, please refer to the above introduction and will not be repeated here.

[0151] The description of a product may refer to the information entered by the merchant describing the product, which is usually displayed on the product details page on the user's end. In the embodiment of the present application, the extracted product keywords are used instead of the description information to display on the product details page on the user's end, making the description information more intuitive and improving the user's reading speed.

[0152] For the implementation of keyword extraction in the embodiments of the present application, please refer to the above introduction and will not be repeated here.

[0153] As an example, Figure 4 As shown in the content of the product details on the far right, the keyword for the attribute "tea base" is "black tea", and the same goes for other keywords. The extracted keywords are directly displayed on the product details page, making the description information more intuitive.

[0154] Step S502: Display the recommended tag of the product on the product list page. The recommended tag is generated based on at least one keyword and at least one selling point word corresponding to the corresponding product. The selling point word is determined based on the at least one keyword corresponding to the corresponding product.

[0155] For the implementation method of selling point word extraction, the implementation method of recommendation tag generation, and the details of displaying recommendation tags in the embodiments of this application, please refer to the introduction above and will not be repeated here.

[0156] The product display method provided in the embodiment of the present application helps users quickly understand the products when purchasing them by displaying the core information of the products in an intuitive and prominent manner, thereby improving the user's purchasing efficiency.

[0157] The method for displaying recommended tags provided in the embodiment of the present application uses recommended tags as prominent display content of the core information of the product, which helps users quickly capture the core information of the product through recommended tags when purchasing the product, thereby improving the user's product purchasing efficiency.

[0158] The embodiment of the present application provides a device for generating a recommendation tag, such as Figure 6 As shown, the generating device 60 may include: an acquisition module 601, an extraction module 602, a determination module 603 and a generation module 604, wherein:

[0159] The acquisition module 601 is used to obtain the description information of the target product;

[0160] The extraction module 602 is used to extract keywords corresponding to at least one predetermined attribute of the target product from the description information;

[0161] The determination module 603 is configured to determine a selling point word corresponding to the target product based on at least one keyword corresponding to the target product;

[0162] The generating module 604 is configured to generate a recommendation tag for the target product based on at least one keyword and at least one selling point word corresponding to the target product.

[0163] In an optional embodiment, when the extraction module 602 is used to extract keywords corresponding to at least one predetermined attribute of the target product from the description information, it is specifically used to:

[0164] Obtain at least one matching word among a prefix matching word, a suffix matching word, and a complete matching word corresponding to at least one attribute;

[0165] Based on the obtained matching words, perform at least one of the following methods to extract keywords for the target product to obtain keywords corresponding to at least one attribute of the target product:

[0166] Based on the prefix matching word, extract the first keyword of the target product from the content after the prefix matching word in the description information;

[0167] Based on the suffix matching word, extract the second keyword of the target product from the preceding content matching the suffix matching word in the description information;

[0168] Based on the complete matching words, the content matching the complete matching words in the description information is extracted as the third keyword of the target product.

[0169] In an optional implementation, when determining the selling point word corresponding to the target product based on at least one keyword corresponding to the target product, the determining module 603 is specifically configured to:

[0170] Determining at least one keyword for determining a selling point word from among the keywords corresponding to the target product;

[0171] Based on the preset mapping relationship between keywords and selling point words, the selling point word corresponding to the target product is determined according to at least one keyword.

[0172] In an optional embodiment, before extracting keywords corresponding to at least one predetermined attribute of the target product from the description information, the extraction module 602 is further configured to:

[0173] Get the category of the target product;

[0174] At least one predetermined attribute corresponding to the category is determined.

[0175] In an optional embodiment, after being configured to generate a recommendation tag for the target product based on at least one keyword and at least one selling point word corresponding to the target product, the generation module 604 is further configured to:

[0176] Determining the priority order of each generated recommendation tag based on the attributes of the at least one keyword used to generate the recommendation tag and the attributes of the keyword corresponding to the at least one selling point word;

[0177] Among them, the priority of the recommended tags corresponding to the selling point words is higher than the recommended tags corresponding to the keywords.

[0178] In an optional embodiment, after generating the recommendation tag for the target product, the generating module 604 is further configured to:

[0179] Obtain user portraits of various types;

[0180] Assign corresponding recommendation tags to various types of user portraits.

[0181] In an optional implementation, the description information of the target product includes the product name and description text of the target product.

[0182] The device of the embodiment of the present application can execute the method provided by the embodiment of the present application, and its implementation principle is similar. The actions performed by each module in the device of each embodiment of the present application correspond to the steps in the method of each embodiment of the present application. For the detailed functional description of each module of the device and the beneficial effects produced, please refer to the description of the corresponding method shown in the previous text, and will not be repeated here.

[0183] The present application embodiment provides a display device for recommendation labels, such as Figure 7 As shown, the display device 70 may include: a response module 701 and a display module 702, wherein:

[0184] Response module 701 is configured to obtain, in response to a trigger operation for viewing a product, a recommended tag and product information for the corresponding product. The recommended tag for each product is generated based on at least one keyword and at least one selling point word corresponding to the product. The selling point word corresponding to the product is determined based on the at least one keyword corresponding to the product. The keyword corresponding to the product is extracted from the product description information based on at least one predetermined attribute.

[0185] The display module 702 is used to display at least one recommendation tag and product information of the corresponding product.

[0186] In an optional embodiment, when the display module 702 is used to display at least one recommended tag for each of the corresponding products, it is specifically used to:

[0187] Displaying at least one recommended tag for the product in order of priority of the recommended tags; the priority order is determined based on the attributes of the at least one keyword used to generate the recommended tag and the attributes of the keyword corresponding to the at least one selling point word;

[0188] Among them, the priority of the recommended tags corresponding to the selling point words is higher than the recommended tags corresponding to the keywords.

[0189] In an optional embodiment, when the response module 701 is used to obtain the recommendation tag of the corresponding product, it is specifically used to:

[0190] Get the recommended tags for the corresponding products corresponding to the current user's user profile.

[0191] The device of the embodiment of the present application can execute the method provided by the embodiment of the present application, and its implementation principle is similar. The actions performed by each module in the device of each embodiment of the present application correspond to the steps in the method of each embodiment of the present application. For the detailed functional description of each module of the device and the beneficial effects produced, please refer to the description of the corresponding method shown in the previous text, and will not be repeated here.

[0192] The present application provides a product display device, such as Figure 8 As shown, the display device 80 may include: a first display module 801 and a second display module 802, wherein:

[0193] The first display module 801 is used to display product keywords on the product details page. The keywords are extracted from the description information of the corresponding product based on at least one predetermined attribute.

[0194] The second display module 802 is used to display the recommended tags of the products on the product list page. The recommended tags are generated based on at least one keyword and at least one selling point word corresponding to the corresponding product. The selling point word is determined based on the at least one keyword corresponding to the corresponding product.

[0195] The device of the embodiment of the present application can execute the method provided by the embodiment of the present application, and its implementation principle is similar. The actions performed by each module in the device of each embodiment of the present application correspond to the steps in the method of each embodiment of the present application. For the detailed functional description of each module of the device and the beneficial effects produced, please refer to the description of the corresponding method shown in the previous text, and will not be repeated here.

[0196] In an embodiment of the present application, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the aforementioned method embodiments. Optionally, the electronic device may refer to the aforementioned user terminal, or the electronic device may also refer to the aforementioned server terminal.

[0197] In an alternative embodiment, an electronic device is provided, such as Figure 9 As shown, Figure 9 The electronic device 900 shown includes: a processor 901 and a memory 903. The processor 901 and the memory 903 are connected, for example, via a bus 902. Optionally, the electronic device 900 may further include a transceiver 904, which may be used for data exchange between the electronic device and other electronic devices, such as data transmission and / or data reception. It should be noted that in actual applications, the number of transceivers 904 is not limited to one, and the structure of the electronic device 900 does not constitute a limitation on the embodiments of the present application.

[0198] 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 devices, transistor logic devices, hardware components, or any combination thereof. It may implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. The processor 901 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like.

[0199] The bus 902 may include a path for transmitting information between the above components. The bus 902 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 902 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 9 Only one thick line is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0200] The memory 903 can be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disk storage media, other magnetic storage devices, or any other medium that can be used to carry or store computer programs and can be read by a computer, without limitation here.

[0201] The memory 903 is used to store the computer program for executing the embodiments of the present application, and the execution is controlled by the processor 901. The processor 901 is used to execute the computer program stored in the memory 903 to implement the steps shown in the above method embodiments.

[0202] An embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps and corresponding contents of the aforementioned method embodiment can be implemented.

[0203] An embodiment of the present application also provides a computer program product, including a computer program, which can implement the steps and corresponding contents of the aforementioned method embodiment when executed by a processor.

[0204] The terms "first," "second," "third," "1," "2," etc., in the specification and claims of this application and in the accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a particular order or sequential sequence. It should be understood that the terms used in this manner are interchangeable where appropriate, such that the embodiments of the application described herein can be practiced in an order other than that shown or described.

[0205] It should be understood that, although each operation step is indicated by arrows in the flowchart of the embodiment of the present application, the order of implementation of these steps is not limited to the order indicated by the arrows. Unless otherwise clearly stated herein, in some implementation scenarios of the embodiment of the present application, the implementation steps in each flowchart can be performed in other orders according to demand. In addition, some or all of the steps in each flowchart can include multiple sub-steps or multiple stages based on actual implementation scenarios. Some or all of these sub-steps or stages can be executed at the same time, and each sub-step or stage in these sub-steps or stages can also be executed at different times respectively. Under different scenarios at the execution time, the execution order of these sub-steps or stages can be flexibly configured according to demand, and the embodiment of the present application does not limit this.

[0206] The above are only optional implementation methods for some implementation scenarios of this application. It should be pointed out that for ordinary technicians in this technical field, without departing from the technical concept of the solution of this application, the use of other similar implementation methods based on the technical ideas of this application also falls within the protection scope of the embodiments of this application.

Claims

1. A method for generating a recommendation tag, characterized in that: include: Get the description information of the target product; Extracting keywords corresponding to at least one predetermined attribute of the target product from the description information; Determining a selling point word corresponding to the target product based on at least one keyword corresponding to the target product; generating a recommendation tag for the target product based on at least one keyword and at least one selling point word corresponding to the target product; Determining a priority order of each generated recommendation tag based on the attributes of the at least one keyword used to generate the recommendation tag and the attributes of the keyword corresponding to the at least one selling point word; Among them, the priority of the recommended tags corresponding to the selling point words is higher than the recommended tags corresponding to the keywords.

2. The generation method according to claim 1, characterized in that Extracting keywords corresponding to at least one predetermined attribute of the target product from the description information includes: Obtain at least one matching word among a prefix matching word, a suffix matching word, and a complete matching word corresponding to the at least one attribute; Based on the obtained matching words, at least one of the following methods is executed to extract keywords of the target product to obtain keywords corresponding to the at least one attribute of the target product: Based on the prefix matching word, extracting the first keyword of the target product from the post-position content matching the prefix matching word in the description information; Based on the suffix matching word, extracting a second keyword of the target product from the preceding content matching the suffix matching word in the description information; Based on the complete matching word, content matching the complete matching word in the description information is extracted as a third keyword of the target product.

3. The generation method according to claim 2, characterized in that The determining, based on at least one keyword corresponding to the target product, a selling point word corresponding to the target product, includes: Determining at least one keyword for determining a selling point word from among the keywords corresponding to the target product; Based on a preset mapping relationship between keywords and selling point words, the selling point word corresponding to the target product is determined according to the at least one keyword.

4. The generation method according to claim 1, characterized in that Before extracting keywords of at least one predetermined attribute of the target product from the description information, the method further includes: Obtaining the category of the target product; At least one predetermined attribute corresponding to the category is determined.

5. The generation method according to claim 1, characterized in that After generating the recommendation tag for the target product, the method further includes: Obtain user portraits of various types; Corresponding recommendation tags are assigned to various types of user portraits.

6. The generation method according to claim 1, characterized in that The description information of the target product includes the product name and description text of the target product.

7. A method for displaying a recommended tag, characterized in that: include: In response to a trigger operation for viewing a product, obtaining a recommended tag and product information for the corresponding product, wherein the recommended tag for each product is generated based on at least one keyword and at least one selling point word corresponding to the product, the selling point word corresponding to the product is determined based on the at least one keyword corresponding to the product, and the keyword corresponding to the product is extracted from the product description information based on at least one predetermined attribute; Displaying at least one recommended tag and product information of the corresponding product; For each of the corresponding products, at least one recommended tag for the product is displayed, including: Displaying at least one recommended tag for the product in order of priority of the recommended tags, wherein the order of priority is determined based on the attributes of the at least one keyword used to generate the recommended tag and the attributes of the keyword corresponding to the at least one selling point word; Among them, the priority of the recommended tags corresponding to the selling point words is higher than the recommended tags corresponding to the keywords.

8. The display method according to claim 7, characterized in that: The step of obtaining the recommended tags for the corresponding products includes: Get the recommended tags of the corresponding products corresponding to the user profile of the current user.

9. A method for displaying goods, characterized in that: include: Displaying product keywords on the product details page, wherein the keywords are extracted from the description information of the corresponding product based on at least one predetermined attribute; Displaying recommended tags for products on a product list page, where the recommended tags are generated based on at least one keyword and at least one selling point word corresponding to the product, where the selling point word is determined based on the at least one keyword corresponding to the product; Display recommended tags for products on the product list page, including: Displaying at least one recommended tag for a corresponding product on a product list page according to a priority order of each recommended tag for the corresponding product, wherein the priority order is determined based on the attributes of the at least one keyword used to generate the recommended tag and the attributes of the keyword corresponding to the at least one selling point word; Among them, the priority of the recommended tags corresponding to the selling point words is higher than the recommended tags corresponding to the keywords.

10. A device for generating a recommendation tag, characterized in that: include: The acquisition module is used to obtain the description information of the target product; an extraction module, configured to extract keywords corresponding to at least one predetermined attribute of the target product from the description information; a determination module, configured to determine a selling point word corresponding to the target product based on at least one keyword corresponding to the target product; a generating module, configured to generate a recommendation tag for the target product based on at least one keyword and at least one selling point word corresponding to the target product; The generating module is further configured to determine a priority order of each generated recommendation tag based on the attributes of the at least one keyword used to generate the recommendation tag and the attributes of the keyword corresponding to the at least one selling point word; Among them, the priority of the recommended tags corresponding to the selling point words is higher than the recommended tags corresponding to the keywords.

11. A display device for recommendation labels, characterized in that: include: a response module, configured to obtain, in response to a trigger operation for viewing a product, a recommended tag and product information for the corresponding product, wherein the recommended tag for each product is generated based on at least one keyword and at least one selling point word corresponding to the product, wherein the selling point word corresponding to the product is determined based on the at least one keyword corresponding to the product, and wherein the keyword corresponding to the product is extracted from the product description information based on at least one predetermined attribute; A display module, configured to display at least one recommended tag and product information of the corresponding product; When the display module is used to display at least one recommended tag for each of the corresponding commodities, the display module is specifically used to: Displaying at least one recommended tag for the product in order of priority of the recommended tags, wherein the order of priority is determined based on the attributes of the at least one keyword used to generate the recommended tag and the attributes of the keyword corresponding to the at least one selling point word; Among them, the priority of the recommended tags corresponding to the selling point words is higher than the recommended tags corresponding to the keywords.

12. A commodity display device, characterized in that: include: A first display module is used to display product keywords on the product details page, where the keywords are extracted from the description information of the corresponding product based on at least one predetermined attribute; A second display module is configured to display a recommended tag for a product on a product list page, wherein the recommended tag is generated based on at least one keyword and at least one selling point word corresponding to the corresponding product, wherein the selling point word is determined based on the at least one keyword corresponding to the corresponding product; When the second display module is used to display the recommended tags of products on the product list page, it is specifically used to: Displaying at least one recommended tag for a corresponding product on a product list page according to a priority order of each recommended tag for the corresponding product, wherein the priority order is determined based on the attributes of the at least one keyword used to generate the recommended tag and the attributes of the keyword corresponding to the at least one selling point word; Among them, the priority of the recommended tags corresponding to the selling point words is higher than the recommended tags corresponding to the keywords.

13. An electronic device comprising a memory, a processor, and a computer program stored in the memory, wherein: The processor executes the computer program to implement the steps of the method according to any one of claims 1 to 6, claims 7 to 8, or claim 9.

14. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6, claims 7 to 8, or claim 10 are implemented.

15. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6, claims 7 to 8, or claim 10 are implemented.

Images