Method and apparatus for processing information related to an article, and electronic device

Abstract

The application discloses a kind of processing methods of information related to article, comprising: obtaining target user determined target attention element;According to the evaluation information of the recommended article of multiple categories of article of target attention element and multiple categories, determine multiple categories of recommended article, and the evaluation information of each category of recommended article is associated with target attention element;Show aggregation page, aggregation page includes recommendation information unit, and different recommendation information unit corresponds to the recommended article of different categories.This method is convenient to show article category by the real evaluation of user, to improve the authenticity of article category recommendation process, improve user experience.Another kind of processing methods of information related to article of the application, comprising showing guide page including multiple candidate information unit, each candidate information unit corresponds to article category;In response to the selection of target information unit, show aggregation page;This method uses user evaluation information.The application also provides related devices, electronic equipment, storage medium.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of data processing, in particular to a processing method and device of information related to an article, and an electronic device and a storage medium. BACKGROUND

[0002] With the development of Internet technology, the carrier of the content provided by the shopping platform has changed from a website to an application. However, the way and content of product recommendation by the shopping platform are increasingly converging.

[0003] In the process of shopping by a user through a shopping platform, the shopping platform shows the product recommendation information of each product to the user through a guide page. The product recommendation information of each product includes the image, title, and merchant information of the product. The title of the product generally includes keywords related to the product.

[0004] For the needs of sales and promotion, the image, title, and the like provided by the merchant for a product may be exaggerated or even false. The user purchases a product according to the product recommendation information of each product in the guide page of the shopping platform. Since the information provided by the merchant does not match the product, the proportion of return and exchange of the product by the user after purchase may be high, thereby reducing the trust of the user in the product recommendation information. In the case of needing to select a product or other article category, how to improve the authenticity of the information provided to the user in describing the article category and reduce the selection cost of the user is a problem to be solved at present. SUMMARY

[0005] The present application provides a processing method of information related to an article, which can improve the authenticity of the information provided to the user and reduce the selection cost of the user through optimization of the recommendation process.

[0006] The processing method of information related to an article provided by the present application includes: obtaining a target attention element determined by a target user; determining a recommended product of one or more categories from a plurality of categories of products according to the target attention element and evaluation information of the products of the plurality of categories, the evaluation information of each recommended product being associated with the target attention element; and displaying an aggregation page, the aggregation page including one or more recommendation information units, different recommendation information units corresponding to the recommended products of different categories.

[0007] Optionally, the product of each category is a product, the recommended product of each category is a recommended product, and the target attention element is a target selling point of the product.

[0008] Optionally, the method further comprises: displaying a first guide page, the first guide page comprising a plurality of candidate information units, different candidate information units corresponding to different selling points; and the obtaining of the target user-determined target attention factor comprises: in response to the target user selecting a target information unit from the plurality of candidate information units, determining that the target selling point is the selling point corresponding to the target information unit.

[0009] Optionally, each candidate information unit comprises first evaluation information of a user who has purchased a product with the selling point corresponding to the candidate information unit, the first evaluation information indicating the selling point corresponding to the candidate information unit.

[0010] Optionally, the candidate information unit comprises information of the user who made the first evaluation information in the candidate information unit.

[0011] Optionally, the first guide page further comprises evaluation guide information, the evaluation guide information being determined according to a product purchased by the target user who opened the first guide page, and the evaluation guide information being used to guide the target user to make an evaluation of the product.

[0012] Optionally, the method further comprises: querying a user attribute of the target user; and generating the first guide page according to the user attribute, at least one selling point corresponding to a candidate information unit in the first guide page matching the user attribute.

[0013] Optionally, the generating of the first guide page according to the user attribute comprises: determining at least one candidate selling point corresponding to the target user according to the user attribute; and the selling point corresponding to one or more candidate information units in the first guide page comprises the at least one candidate selling point.

[0014] Optionally, the method further comprises: displaying a second guide page, the second guide page comprising a search box; and the obtaining of the target user-indicated target attention factor comprises: obtaining the target selling point input by the target user in the search box.

[0015] Optionally, the determining of the recommended product in one or more categories of products according to the target attention factor and evaluation information of products in a plurality of categories comprises: respectively performing semantic analysis on the evaluation information of the plurality of products to obtain a product selling point of each product; and the product selling point of each recommended product comprises the target selling point.

[0016] Optionally, each recommendation information unit comprises second evaluation information of a user who has purchased a recommended product corresponding to the recommendation information unit, the second evaluation information indicating the target selling point.

[0017] Optionally, the determining one or more recommended items of one or more categories of items according to the target focus element and evaluation information of items of the plurality of categories of items comprises: determining one or more recommended items of one or more categories of items according to the target focus element, using a recall ranking algorithm based on evaluation information of goods, and ranking, the ranking being an order of the one or more recommended items in the aggregation page.

[0018] Optionally, the method further comprises: if the target user selects a target recommended information unit in the one or more recommended information units, displaying a product detail page of a target recommended product corresponding to the target recommended information unit.

[0019] Embodiments of the present application provide a method for processing information related to items, comprising: displaying a guide page, the guide page comprising a plurality of candidate information units, each candidate information unit having a recommended item of a corresponding category; in response to a target user selecting a target information unit in the plurality of candidate information units, displaying an aggregation page; the aggregation page comprising one or more recommended information units, different recommended information units corresponding to recommended items of different categories corresponding to the target information unit; each candidate information unit comprising first evaluation information, and / or each recommended information unit comprising second evaluation information; the first evaluation information representing evaluation of a user who has purchased a recommended item of the category corresponding to the candidate information unit on the recommended item of the category, and the second evaluation information representing evaluation of a user who has purchased a recommended item of the category corresponding to the recommended information unit.

[0020] Embodiments of the present application provide a device for processing information related to items, comprising: an acquisition unit configured to acquire a target focus element determined by a target user; a processing unit configured to determine one or more recommended items of one or more categories of items according to the target focus element and evaluation information of items of the plurality of categories of items, evaluation information of each recommended item being associated with the target focus element; and a display unit configured to display an aggregation page, the aggregation page comprising one or more recommended information units, different recommended information units corresponding to the recommended items of different categories.

[0021] The embodiment of the present application provides a processing device of information related to an article, comprising: a first display unit, displaying a guide page, wherein the guide page comprises a plurality of candidate information units, each candidate information unit has recommended articles of a corresponding category; a second display unit, in response to selection of a target information unit in the plurality of candidate information units by a target user, displaying an aggregation page; the aggregation page comprises one or more recommended information units, different recommended information units correspond to recommended articles of different categories corresponding to the target information unit; each candidate information unit comprises first evaluation information, and / or each recommended information unit comprises second evaluation information; the first evaluation information represents the evaluation of recommended articles of the category by a user who has purchased the recommended articles of the category corresponding to the candidate information unit, and the second evaluation information represents the evaluation of a user who has purchased the recommended articles of the category corresponding to the recommended information unit.

[0022] The embodiment of the present application provides an electronic device, comprising: a memory for storing a computer program; a processor for executing the computer program to execute the method described above.

[0023] The embodiment of the present application provides a storage medium, characterized in that the storage medium stores a program, and the program is executed by a processor to implement the method described above.

[0024] The processing method of information related to an article provided by the present application, after obtaining a target user determined target attention element, uses an aggregation page to determine one or more recommended articles of a category in a plurality of categories of articles to be displayed to the target user. For the displayed recommended articles of the category, the evaluation information is associated with the target selling point. Compared with the information provided by the article category provider, the evaluation information can more truly and accurately reflect the characteristics of the article category. In the article category recommendation process, the evaluation information of the article category is used to recommend the article category to the target user. The information used in the recommendation process is more real, and the description of the recommended article category is more real, so that the recommended article category is more in line with the needs of the target user, reduces the cost of the user's selection of the article category, and improves the user experience. BRIEF DESCRIPTION OF DRAWINGS

[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiment or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art according to these drawings.

[0026] Figure 1 is a schematic flow chart of the processing method of information related to an article provided by the first embodiment of the present application;

[0027] Figure 2 is a schematic flow chart of a method for processing information related to an item according to a second embodiment of the present application;

[0028] Figure 3 is a schematic diagram of a guide page according to the second embodiment of the present application;

[0029] Figure 4 is a schematic diagram of an aggregation page according to the second embodiment of the present application;

[0030] Figure 5 is a schematic flow chart of another method for processing information related to an item according to a third embodiment of the present application;

[0031] Figure 6 is a schematic diagram of a guide page according to the third embodiment of the present application;

[0032] Figure 7 is a schematic structural diagram of a device for processing information related to an item according to a fourth embodiment of the present application;

[0033] Figure 8 is a schematic structural diagram of another device for processing information related to an item according to a fifth embodiment of the present application;

[0034] Figure 9 is a schematic structural diagram of an electronic device according to a sixth embodiment of the present application. DETAILED DESCRIPTION

[0035] In order to make the objects, advantages and features of the present application clearer, the technical solutions in the present application will be further described in detail below with the accompanying drawings and specific embodiments. In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application. However, the present application can be implemented in many different ways than those described herein, and those skilled in the art can make similar generalizations without departing from the spirit of the present application, so the present application is not limited to the specific embodiments disclosed below.

[0036] It should be noted that in the description of the present application, the terms "first", "second" and the like are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance, and a specific order or sequence. For those of ordinary skill in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances. In addition, in the description of the present application, unless otherwise specified, the term "multiple" refers to two or more. The term "and / or" describes the association between the associated objects, which means that there can be three relationships, for example, A and / or B can represent the following three cases: A exists alone, A and B exist together, and B exists alone. The character " / " generally represents an "or" relationship between the associated objects. The terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device that includes a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0037] In the era of personal computer (PC) Internet, computers are connected to telecommunications, network, mobile, data networks, and the carrier of content is a website. In the mobile Internet, the technological progress of cellular mobile communication and the improvement of processor performance make mobile devices smaller and more powerful, and the carrier of content changes from website to application (APP).

[0038] With the development of Internet technology, the carrier of the content provided by the shopping platform has changed. However, the way and content of product recommendation are becoming more and more similar.

[0039] In the process of users shopping through the shopping platform, the shopping platform shows the product recommendation information of each product to the user through the guide page. The guide page can be understood as an aggregated shopping guide of products. The product recommendation information of each product can include the main image, title, merchant information and the like of the product. The title of the product can include multiple keywords related to the product provided by the merchant. The main image of the product can be selected by the merchant from multiple images of the product.

[0040] After obtaining the demand information input by the user, the guide page can be generated according to the demand information. The products corresponding to the product recommendation information in the guide page meet the demand information input by the user.

[0041] According to the information provided by the merchant, the display of product recommendation information is provided for the user, which improves the convenience of product recommendation. However, in order to meet the needs of sales and promotion, the main image, title and the like provided by the merchant for the product may be exaggerated or even false, and the authenticity may be low.

[0042] The goods corresponding to the commodity recommendation information in the guide page are determined according to the information provided by the merchant and meet the demand information input by the user. Since the information provided by the merchant may not match the goods, the goods displayed in the guide page may not meet the user's demand.

[0043] The user selects and purchases goods through the guide page displayed by the shopping platform, and if the goods displayed in the guide page do not meet the user's demand, the user will spend a lot of time in selecting and purchasing goods. Moreover, the user selects and purchases goods according to the guide page, and actually judges whether the goods meet his own needs according to the information provided by the merchant, which may not be true, so that the judgment result may be wrong. In this case, the user can only understand the quality and other characteristics of the purchased goods after actually purchasing the goods, and determine whether the purchased goods meet his own needs.

[0044] Therefore, the user's selection efficiency of goods is reduced, the proportion of returned and exchanged goods is large, the shopping cost is high, the user's shopping experience is reduced, the user's satisfaction with the shopping platform and the user's trust in the commodity recommendation information in the guide page are reduced.

[0045] To solve the above problems, the embodiment of the present application provides a processing method of information related to an article. By using the method, the recommended article category can be more in line with the needs of the target user, the efficiency of the user selecting the article category is improved, and the selection cost is reduced.

[0046] The processing method of information related to an article provided by the embodiment of the present application is introduced below. Figure 1 The processing method of information related to an article provided by the embodiment of the present application is introduced below.

[0047] Figure 1 is a schematic flowchart of a processing method of information related to an article provided by the first embodiment of the present application. Figure 1 The method shown in the figure can be applied to an electronic device, which can be a terminal device, a server or other electronic devices capable of data processing. The terminal device can include a desktop computer, a notebook computer, a mobile terminal (such as a smart phone), a tablet computer, a game console, a personal digital assistant, a vehicle-mounted terminal, etc., and the embodiment of the present application is not specifically limited. In a specific implementation form, the processing method of information related to an article provided by the first embodiment can be a page, an application program (APP) or a mini program located in a client terminal device. Some specific operations can be realized by a remote server. Figure 1 The method shown in the figure includes steps S101 to S103.

[0048] In step S101, a target attention element determined by a target user is obtained.

[0049] This step can determine which particular attribute of goods or services the target user expects to obtain according to the situation of the target user. The target attention element is used to indicate the attribute expected by the user.

[0050] For the scenario of the user selecting and purchasing goods, the target attention element can be the target selling point of the goods. The so-called target selling point is the type of goods or services that meets the needs of the user. The term selling point used here can basically be understood as a certain attribute of the goods or services that is particularly attractive to the target user and triggers the user's purchase motivation. The particularity of the selling point attribute is that it cannot be determined by the merchant. The selling point defined by the merchant is only used as a kind of initial promotion. In the actual transaction process of the goods, the user's real experience of the goods and the spreadable information formed by the real experience are the source of the formation of the selling point of the goods. In addition, the selling point attribute also has the characteristic of "emergence", that is, a positive cycle can be achieved in a certain experience angle through a large number of user experiences, thereby digging out a special attribute that was not known before. The description of the selling point can often be formed by the conceptual combination of multiple keywords, for example, "slim pants", which includes two keywords "slim" and "pants". The former constitutes a limiting relationship with the latter.

[0051] According to the current transaction form of the e-commerce platform, the information that can best dig out the selling point is the evaluation information of the goods or services. Through the evaluation information, the user can make the experience of the goods explicit, and through interaction, the emergence effect can be achieved.

[0052] In order to obtain the target selling point determined by the target user, the known selling point can be displayed to the user through a guided page to inspire the user to select. The user can also actively search for the target selling point expected by the user through a search bar. Of course, other ways such as using a question and answer guided way are not excluded. The specific ways to obtain the target selling point determined by the target user are described below.

[0053] For example, before S101, a guided page can be displayed. The target selling point can be determined according to the operation of the target user on the guided page.

[0054] The guided page can be provided by the shopping platform. The target user can determine the specific login account during the use of the shopping platform, and different login accounts correspond to different users.

[0055] In some examples, before S101, a first guide page can be presented. The first guide page includes a plurality of candidate information units, and different candidate information units correspond to different selling points. In S101, in response to a selection of a target information unit in the plurality of candidate information units by a target user, it is determined that the target selling point is the selling point corresponding to the target information unit.

[0056] The first guide page can be the guide page in the second embodiment, and details can be referred to the description of Figure 2 and Figure 3 .

[0057] Each candidate information unit can include first evaluation information of a user who has purchased a product with the selling point corresponding to the candidate information unit, and the first evaluation information indicates the selling point corresponding to the candidate information unit.

[0058] The size of the area in the candidate information unit for the first evaluation information is limited, and accordingly, the first evaluation information can be a complete evaluation or part of a complete evaluation. The part of the complete evaluation can be the part related to the selling point corresponding to the candidate information unit.

[0059] The first evaluation information in the candidate information unit can indicate the selling point corresponding to the candidate information unit. Through the presentation of the first evaluation information, the user can understand that the selling point corresponding to the candidate information unit is determined according to the user evaluation information, thereby improving the target user's trust in the recommended product with the target selling point corresponding to the selected candidate information unit.

[0060] In addition, the first evaluation information can properly reflect the selling point corresponding to the candidate information unit where the first evaluation information is located, that is, the first evaluation information is closely related to the recommended product corresponding to the candidate information unit, so that the user believes that the information presented on the aggregation page after selecting the target candidate information unit is more real, and the user's trust in the content presented on the first guide page and the aggregation page can be significantly improved.

[0061] The candidate information unit can include information of the user who made the first evaluation information in the candidate information unit, such as the user's avatar, nickname, etc. (The above information is presented, and the user's privacy selection needs to be considered, and only the information of the user who allows the use of these contents is presented.) By displaying the information of the user who made the first evaluation information in the candidate information unit, the target user's trust in the authenticity of the first evaluation information can be improved, thereby improving the target user's trust in the content presented on the first guide page and the aggregation page.

[0062] In view of the requirement of different users having different needs, before S101, the first guide page for a specific target user can be generated.

[0063] Exemplarily, before S101, a user attribute of the target user can be queried according to permission of the user, and a first guide page can be generated according to the user attribute. At least one candidate information unit in the first guide page corresponds to a selling point matched with the user attribute.

[0064] The first guide page generated according to the user attribute of the target user is more in line with the needs of the target user. Thus, the first guide page can fully play a guiding and recommending role in the process of the target user selecting and purchasing goods.

[0065] In the process of generating the first guide page according to the user attribute, at least one candidate selling point corresponding to the target user can be determined according to the user attribute. The selling point corresponding to one or more candidate information units in the first guide page can include the at least one candidate selling point.

[0066] The candidate selling point is determined according to the user attribute and can reflect the characteristics and preferences of the target user. The selling point corresponding to the candidate information unit in the first guide page includes the candidate selling point, so that the first guide page is more in line with the needs of the target user, and the first guide page can fully play a guiding and recommending role in the process of the target user selecting and purchasing goods.

[0067] The selling point corresponding to all or part of the candidate information units in the first guide page can also be determined according to the selling point of the goods with the largest transaction volume or browsing volume in the preset time in the shopping platform. Thus, the selling point displayed to the target user in the first guide page is more in line with the current fashion trend or demand trend, and the first guide page can fully play a guiding and recommending role in the process of the target user selecting and purchasing goods.

[0068] Another specific way of obtaining the target selling point determined by the target user is through user search.

[0069] Specifically, in some other examples, before S101, a second guide page can be displayed. The second guide page includes a search box. In S101, a target selling point input by the target user in the search box can be obtained.

[0070] Obtaining the target selling point input by the user through the search box makes the way of the target user indicating the target selling point more convenient.

[0071] The second guide page can be a guide page with a search box, which can be specifically referred to Figure 5 and Figure 6 for description.

[0072] It should be understood that the first guide page and the second guide page can also be the same guide page. That is, in the guide page displayed before S101, both the search box and the at least one candidate information unit can be included.

[0073] Each candidate information unit can include a product picture and first evaluation information to show the selling point corresponding to the candidate information unit. Alternatively, the candidate information unit can directly describe the selling point corresponding to the candidate information unit in the form of text. The description in the form of text can serve as an example of the selling point and has a certain guiding effect on the input of the target selling point by the user in the search box.

[0074] In S102, one or more recommended products of one or more categories are determined from the plurality of products of the categories according to the target attention factor and the evaluation information of the plurality of products of the categories, and the evaluation information of each recommended product of the category is associated with the target attention factor.

[0075] The category of a product is used to distinguish products with different characteristics. The degree of demand of a user for products of different categories can be different.

[0076] In different scenarios, a product can have different meanings. In a rental scenario, a product of a certain category can be one or a kind of product to be rented. In a video or audio playing scenario, a product of a certain category can be a piece of video or audio. In a product selection scenario, a product of a category can be a product. The following will be described taking the product selection scenario as an example. The recommended product of each category can be understood as a recommended product.

[0077] In order to determine the recommended product, the evaluation information of the plurality of products can be analyzed respectively to obtain the product selling point of each product. The evaluation information of a product can be understood as the after-sales evaluation of the product by a user who purchases the product. By analyzing, refining and other semantic analysis on the evaluation information of the product, the product selling point of the product can be obtained.

[0078] In the present application, the evaluation information refers to the evaluation made by a real user on a specific commodity or service; generally, these evaluation information is published on the network for a specific commodity and can be accessed by other users accessing the platform. The most typical evaluation information refers to the specific evaluation left by a user on the evaluation page of the specific commodity or service page after purchasing the specific commodity or service, especially the evaluation with specific text content; these evaluation information comes from specific users, not from merchants or robots, has authenticity, can easily arouse the resonance of target users, and can easily obtain high trust degree. The previous utilization and mining of this information is not deep enough, and the present application hopes to fully utilize this information to achieve indirect interaction and mutual assistance between users who have purchased the commodity and potential users, not only to promote commodity sales, but also to make the real feelings of users on each commodity become fully mined and utilized commodity information. Of course, the utilization of evaluation information needs to comply with relevant privacy protection regulations, which is not the focus of the present application and will not be specifically described later. In the present application, the evaluation information is generally made by a real user who purchases a specific commodity through the platform, of course, it is not excluded that the evaluation made by a user who has personal experience of using a specific commodity through other channels in some cases; but the evaluation information should exclude the evaluation information sent by robots and as far as possible exclude the evaluation information sent by the merchants themselves. Due to the diversity and non-standardization of the content of the evaluation information, various language analysis techniques can be used to analyze the evaluation information and extract the effective information therein; for example, through the analysis of multiple evaluation information of a specific commodity, the consistent evaluation of the specific commodity by the user can be obtained, thereby constructing the commodity selling point of the commodity; for a specific commodity, the commodity selling point can be one or more. For example, for a pair of trousers, through the user evaluation, it can be learned that multiple users evaluate the leg type of the trousers as good and slim, which can be abstracted as the commodity selling point "slim trousers".

[0079] According to the commodity selling point of each commodity in the plurality of commodities, at least one recommended commodity can be determined in the plurality of commodities.

[0080] The evaluation information of the recommended commodity is associated with the target selling point, which can be understood as the evaluation information of the recommended commodity being able to reflect the target selling point, i.e. the evaluation information of the recommended commodity indicating that the recommended commodity has the target selling point.

[0081] Exemplarily, in the case that the degree to which the commodity selling point of each recommended commodity conforms to the target selling point is greater than a preset value, it can be determined that the evaluation information of the recommended commodity is associated with the target selling point. The degree to which the commodity selling point conforms to the target selling point can be understood as the degree to which the commodity selling point contains the target selling point. For example, in the case that the commodity selling point of the recommended commodity includes the target selling point, it can be determined that the evaluation information of the recommended commodity is associated with the target selling point.

[0082] The evaluation information of each recommended commodity can reflect the real situation of the recommended commodity, and the recommended commodity is determined to have the target selling point according to the evaluation information of the plurality of commodities, so that the real situation of the recommended commodity meets the demand of the target user for the target selling point.

[0083] In order to make the order of the recommended commodities in the aggregation page more in line with the user demand, the recall ranking algorithm can be used for processing.

[0084] According to the target selling point, the recall ranking algorithm based on the evaluation information of the commodity can be used to determine one or more recommended commodities in the plurality of commodities and ranking, that is, the order of the one or more recommended commodities in the aggregation page.

[0085] The order of the one or more recommended commodities in the aggregation page can be understood as the order of the recommended information unit corresponding to the one or more recommended commodities in the aggregation page.

[0086] The evaluation information of the commodity can include the evaluation of the commodity by the user who has purchased the commodity.

[0087] The recall ranking algorithm includes two steps of recall and ranking. Through recall, the target object associated with the recall condition can be determined in the plurality of candidate objects. Through ranking, the relevance of the plurality of target objects in the recall result can be evaluated, and the plurality of target objects can be ranked in descending order of relevance.

[0088] The user generally browses the aggregation page from front to back. By using the recall ranking algorithm, the order of the recommended commodities in the aggregation page is determined, and the order of the recommended commodities in the aggregation page is set so that the target user can more easily find the commodity meeting the demand.

[0089] In step S103, the aggregation page is displayed, and the aggregation page includes one or more recommended information units, and different recommended information units correspond to different recommended commodities of the category.

[0090] In order to improve the trust of the user for the aggregation page, each recommended information unit can include second evaluation information of the user who has purchased the recommended commodity corresponding to the recommended information unit, and the second evaluation information indicates the target selling point.

[0091] Since the size of the area set for the second evaluation information in the recommended information unit is limited, the second evaluation information can be a complete evaluation or part of the complete evaluation. The part of the complete evaluation can be the part related to the target selling point in the complete evaluation.

[0092] The second evaluation information included in the recommendation information unit and indicating the target selling point is used to inform the target user that the recommended product corresponding to the recommendation information unit has the target selling point through user evaluation, prompt the user that the recommended product corresponding to each recommendation information unit in the aggregation page indeed has the target selling point, and these recommended products are based on evaluation information reflecting the real situation, thereby improving the trust degree of the user to the recommendation information unit, and fully playing the guiding and recommending role of the aggregation page in the target user product selection process.

[0093] To further improve the trust degree of the user to the information in the guiding page and the aggregation page, the guiding page displayed before S101 can further include evaluation guiding information determined according to the purchased product of the target user opening the guiding page, and the evaluation guiding information is used to guide the target user to make an evaluation on the purchased product.

[0094] The evaluation guiding information can be displayed together with the content related to the purchased product of the target user, thereby guiding the target user to make an evaluation on the purchased product. In the case that the user clicks the guiding information, the order interface to be evaluated can be displayed, thereby realizing the guiding of the target user to make an evaluation on the purchased product.

[0095] By setting the evaluation guiding information in the guiding page, the target user is guided to make an evaluation on the purchased product, which can improve the trust degree of the target user to the first evaluation information in each candidate information unit in the first guiding page and the second evaluation information possibly displayed in the recommendation information unit of the aggregation page, and fully play the guiding and recommending role of the first guiding page and the aggregation page in the product selection process of the user.

[0096] Moreover, by guiding the target user to make an evaluation on the purchased product, the number of evaluations of the purchased product can be increased. In the process of determining whether the product is a recommended product according to the user evaluation on the purchased product, by effectively improving the data amount of user evaluation, the basis for determining the product selling point of the purchased product can be more abundant, and the semantic analysis to obtain the product selling point of the purchased product can be more accurate, thereby improving the judgment result of whether the purchased product is a recommended product.

[0097] After S103, if the selection of the target recommendation information unit in the one or more recommendation information units by the target user is received, the product detail page of the target recommended product corresponding to the selected target recommendation information unit can be displayed.

[0098] Through the display of the product detail page, the user can have a more detailed and in-depth understanding of the target recommended product, thereby determining whether to purchase the target recommended product.

[0099] Compared with the information provided by the item category provider, the evaluation information from the specific user can more truly and accurately reflect the characteristics of the item category. Through S101 to S103, after obtaining the target user determined target attention factor, the target user is shown one or more recommended items of the category through the aggregation page, and the evaluation information of the recommended item of the category is associated with the target attention factor. In the item category recommendation process, the target user is recommended by using the evaluation information, the information used in the recommendation process is more real, the description of the recommended item category is more real, so that the recommended item category is more in line with the needs of the target user, reduces the cost of the user to select and purchase goods, and improves the user experience.

[0100] In Figure 1 In the method shown, in the process of guiding the selection of the item category of the user by using the guide page and the aggregation page, by using the evaluation information as the core guiding element, the authenticity of the information in the page can be improved, the user's selection can be disturbed by the item category provider who piles up false keywords in the introduction information of the item category in order to guide the flow, and the efficiency of the user's selection of the item category is improved.

[0101] Considering that a user who needs to purchase goods or services may not have any information to use, in many cases, a purchase process starting from 0 information needs to be established, and therefore, the second embodiment is provided, which is characterized in that the guiding process of the first step can be completely explored from 0 by the platform, and the specific user demand can be obtained as soon as possible, and similar to the first embodiment, the second embodiment also needs to fully utilize the role of the evaluation information; in addition, the embodiment does not emphasize the concept of selling point.

[0102] Figure 2 is a schematic flow chart of a method for processing item-related information provided by the second embodiment of the present application. Figure 2 The method shown can be applied to an electronic device, which can be a terminal device, a server or other electronic devices capable of data processing, wherein the terminal device can include a desktop computer, a notebook computer, a mobile terminal (such as a smart phone), a tablet computer, a game console, a personal digital assistant, a vehicle-mounted terminal, etc., and the embodiments of the present application are not specifically limited. Figure 2 The method shown includes steps S201 to S202. Please also refer to Figure 3 , Figure 4 .

[0103] Step S201, a guide page is displayed, and the guide page includes a plurality of candidate information units, each candidate information unit having a recommended item of a corresponding category.

[0104] The categories of the items are used to distinguish items with different characteristics. The degree of demand of a user for items of different categories can be different.

[0105] In different scenarios, an item can have different meanings. In a rental scenario, an item of a certain category can be one or a kind of item to be rented. In a video or audio playing scenario, an item of a certain category can be a piece of video or audio. In a commodity selection scenario, an item of a category can be a commodity.

[0106] The commodity selection scenario is taken as an example for illustration below.

[0107] The guide page can include a plurality of candidate information units 331-335, etc. as shown in Figure 3

[0108] The guide page can be the same or different for different target users; the platform showing the guide page can show a targeted guide page according to the user attributes, in accordance with the requirement of one person one face. If the user situation is completely unknown, the guide page can adopt a certain general type of page to cover the most reasonable guide path.

[0109] Specifically, the guide page can be provided by a shopping platform, and the target user can not need to log in, or the guide page can be determined according to the account logged in during the use of the shopping platform; different accounts can correspond to different users, and different guide pages can be shown.

[0110] If the user has logged in, the guide page for the specific target user can be generated before S201.

[0111] Specifically, before S201, the user attributes of the logged-in target user can be queried, and the guide page can be generated according to the user attributes of the target user. The candidate information units in the guide page match the user attributes of the target user.

[0112] The user attributes of the target user can include information such as the education and age of the target user, and can also include information such as the browsing preferences and shopping preferences of the target user on the shopping platform. The browsing preferences of the target user can be determined according to the browsing records of the target user within a preset length of time, and the shopping preferences can be determined according to the shopping records of the target user within a preset length of time.

[0113] The guide page generated according to the user attributes of the target user is more in line with the needs of the target user, and fully plays the guiding and recommending role of the guide page for the target user shopping.

[0114] The guide page, an example of which can be referred to Figure 3 ​The core part of the guide page is a plurality of candidate information units displayed through the guide page. Each candidate information unit is a carrier of an information aggregation of a recommended product. The essence of each candidate information unit is to recommend a product with a certain selling point to the user. However, in the form of expression, the candidate information unit takes the corresponding recommended product as a specific recommended product, rather than directly highlighting a certain selling point, or in other words, the recommended product is a representative product with the selling point. In this way, the information in the candidate information unit can be more specific, thereby increasing the attraction to the user.

[0115] In a specific form, the candidate information unit is generally an information display box containing a recommendation (which can be the first evaluation information described later), a picture of the recommended product, a textual description of the key attributes of the recommended product (which can be a selling point), and the like. Each guide page can display a plurality of candidate information units, or display them in a waterfall manner. At this time, the user can see a large number of candidate information units by pulling the page without jumping, different candidate information units can correspond to different selling points, and in addition, each candidate information unit corresponds to a specific product. Generally speaking, a candidate information unit implicitly corresponds to a selling point and explicitly corresponds to a recommended product, but it is not excluded that a candidate information unit corresponds to a plurality of recommended products that meet a selling point. For example, the implicit selling point of "the latest peripheral accessories of a certain mobile phone" can aggregate a plurality of recommended products such as mobile phone stickers, mobile phone cases, mobile phone holders, and matching earphones.

[0116] Each candidate information unit has a corresponding recommended product, which is a typical product embodying the selling point of the candidate information unit. The recommended product corresponding to each candidate information unit can be a product of a certain category that has the selling point of the candidate information unit.

[0117] In some cases, the selling point can also be understood as indicating the category of the product. The category of the product can also be understood as the type of the product, such as a certain type of clothing (such as sports shoes or shirts), a certain type of electronic product (such as electronic watches or tablet computers), or a certain type of food (such as green beans or biscuits), etc. These categories are actually also broad selling points.

[0118] The selling point can also indicate the characteristics of the product. The characteristics of the product can be the function, effect, material, use effect, product quality, etc. of the product, for example, the function of keeping warm, the use effect of making the skin look white, or the product quality of being sturdy and durable, etc.

[0119] Of course, the selling point can also be a combination of the characteristics and category of the product. For example, the selling point can be a white lipstick, slim pants, or a warm wool sweater, etc.

[0120] Different candidate information units can correspond to different selling points. The selling points can include product categories, product features, and the like. For example, trousers, slimming trousers, and slimming can be different selling points.

[0121] As shown in Figure 3 Each candidate information unit includes the selling point corresponding to the candidate information unit and the image of the recommended product corresponding to the candidate information unit.

[0122] According to the above various descriptions and in combination with the problem to be solved by the present application, the "selling point" refers to a product attribute that triggers the user's purchase motivation. Obviously, the selling point can be understood from many angles. As mentioned earlier, the product itself can also be a selling point, but the selling point of the present application is embodied as a descriptive sentence that focuses on arousing the user's purchase emotion. For example, "slimming trousers", such a sentence that has both product categories and product feature descriptions is a better presentation of the selling point. The candidate selling point corresponding to a certain candidate information unit can be embodied in a property field recorded in the background corresponding to the candidate information unit, rather than directly displayed on the display frame of the candidate information unit on the interface; that is, in the present embodiment, the "selling point" should be understood as a property of the candidate information unit, and the property should be displayed as an element in the display process of the candidate information unit, such as the first evaluation information described later. The display method can be a direct description or an indirect description of the selling point. For example, for the selling point "slimming trousers", the first evaluation information can actually be selected to embody the selling point "The fit of these jeans is really good, and they hide the meat!"

[0123] The selling point of the recommended product corresponding to each candidate information unit matches the selling point corresponding to the candidate information unit; that is, the recommended product corresponding to a certain candidate information unit must have the selling point corresponding to the candidate information unit.

[0124] Generally, each of the candidate information units has only one selling point, which is embodied by a typical product; or said, the candidate information unit is limited by the display area and generally includes only one recommended product, which is actually a representative product with the selling point that the candidate information unit hopes to promote.

[0125] Before S201, the user attributes of the target user can be queried first, at least one selling point for the target user is determined according to the user attributes, and the guide page for the target user is generated according to the selling point or selling points. In the generated guide page, the one or more candidate information units match the selling points of the user attributes; through the above process, the guide page is more in line with the needs of the target user, and the guiding and recommending effect of the guide page on the target user's shopping is fully played.

[0126] The part or all of the candidate information units in the guide page respectively correspond to the selling points, and the selling points of the commodities with the largest transaction volume or browsing volume in the shopping platform within a preset time can be determined. Thus, the selling points shown to the user are more in line with the current fashion trend or demand trend, and the guide page fully plays a role in guiding and recommending the target user to shop.

[0127] Each candidate information unit can include first evaluation information of a user who has purchased a recommended commodity corresponding to the candidate information unit corresponding to the candidate information unit, as shown in Figure 3 .

[0128] By showing the first evaluation information of the user in the candidate information unit, the authenticity of the candidate information unit is higher, and the trust of the user in the candidate information unit is improved. The display mode of the first evaluation information can adopt a display mode of directly quoting the user evaluation information, so as to prompt the user that this is an evaluation from a real buyer. For example, the way of a real buyer's avatar plus evaluation information is adopted, and double quotation marks indicating direct quotation are added on the evaluation information.

[0129] The first evaluation information in each candidate information unit can be used to indicate the candidate selling point corresponding to the candidate information unit; or in other words, the first evaluation information is the external manifestation of the selling point corresponding to the candidate information unit. In short, the first evaluation information can highly and appropriately reflect the selling point corresponding to the candidate information unit where the first evaluation information is located, and the first evaluation information is more closely associated with the recommended commodity corresponding to the candidate information unit, which can significantly improve the trust of the user in the candidate information unit.

[0130] As shown in Figure 3 , each candidate information unit can further include information of a user who makes the first evaluation information. The information of the user who makes the first evaluation information can include the user's avatar, nickname, etc. By showing the information of the user who makes the first evaluation information, the trust degree of the target user in the authenticity of the first evaluation information can be improved, thereby improving the trust of the target user in the candidate information unit.

[0131] The selling point of the recommended commodity can be obtained by performing sentiment analysis on the user evaluation of the recommended commodity. The first evaluation information in the candidate information unit is directly obtained from the after-sales evaluation of the recommended commodity corresponding to the candidate information unit by the user. The first evaluation information can be a complete evaluation of the recommended commodity, or part of the complete evaluation of the recommended commodity.

[0132] Generally, the first evaluation information comes from the real evaluation of a user who has purchased or paid attention to a certain product, especially the various real after-sales evaluation information collected from the purchase evaluation of the user who has purchased the product on the purchase platform. In order to obtain the selling point, the selling point of the recommended product can be determined by performing semantic analysis on the user evaluation of various recommended products, so that the authenticity of the recommended product is higher, the shopping guidance and recommendation efficiency for the target user is higher, and the shopping cost of the user is reduced.

[0133] A feasible solution is to collect user evaluation of various products, generally after-sales evaluation, from at least one sales platform, and then analyze and refine the evaluation to obtain the selling point of each product; and then according to the selling point, select the evaluation information corresponding to the selling point in the evaluation of the product as the evaluation information of the product. The specific steps are as follows:

[0134] Collect the evaluation of the target product by the user who purchases the target product; according to the evaluation, use a trained semantic analysis model to identify the selling point of the target product; according to the semantic unit related to the identified selling point, select the part that fits the selling point in the evaluation as the evaluation information of the target product.

[0135] Another possible method is to obtain common selling points in advance, and then use these selling points as the basis to obtain the evaluation information related to each selling point from the evaluation of the target product by the user who purchases the target product through a semantic recognition model, as the evaluation information of the target product. The specific implementation steps are as follows:

[0136] Obtain the common selling points prepared in advance and collect the evaluation of the target product by the user who purchases the target product; according to the evaluation, use a trained semantic analysis model to identify the selling point corresponding to the evaluation; according to the result of the selling point identification of the evaluation of the target product, select the product selling point corresponding to the target product from the multiple common selling points; according to the product selling point, select the evaluation information matching the product selling point in the evaluation of the target product as the evaluation information of the target product.

[0137] The evaluation information of the product corresponding to the candidate selling point corresponding to the candidate information unit can be used as the first evaluation information in the candidate information unit.

[0138] As shown in Figure 3 The guide page can also include evaluation guide information 310, which is determined according to the purchased products of the target user who opens the guide page, and is used to guide the user to make an evaluation of the purchased products.

[0139] In one aspect, by setting the evaluation guide information 310 on the guide page, the target user is guided to make an evaluation on the purchased commodity, which can improve the target user's trust in the first evaluation information in each candidate information unit in the guide page.

[0140] On the other hand, by guiding the target user to make an evaluation on the purchased commodity, the number of evaluations on the purchased commodity can be increased. In the process of performing semantic analysis on the user evaluation of the purchased commodity to obtain the selling point of the purchased commodity, by effectively increasing the data amount of the user evaluation, the basis for determining the selling point of the purchased commodity can be more abundant, and the determined selling point can be more accurate.

[0141] Illustratively, the guide information can display content related to the purchased commodity of the target user, thereby guiding the user to make an evaluation on the purchased commodity. Alternatively, in the case where the user clicks the evaluation guide information 310, the order interface to be evaluated can be displayed, thereby realizing the guidance of the target user to make an evaluation on the purchased commodity.

[0142] Through the above setting of the evaluation guide information 310, the guide page not only utilizes the user's evaluation as a shopping guide basis, but also promotes the generation of user evaluation, realizes the positive cycle of evaluation utilization-generation, fully plays the role of user evaluation, forms a natural development ecological process, and finally realizes the "emergence" effect through the generation and use of a large number of evaluations, and promotes the positive feedback mechanism of the shopping guide mode.

[0143] As shown in Figure 3 The guide page can further include classification information 320, and the classification information 320 includes a plurality of commodity categories. According to the selection of the target commodity category in the classification information 320 by the user, the displayed candidate information units are adjusted. Each candidate information unit displayed after adjustment corresponds to a recommended commodity belonging to the target commodity category selected by the user.

[0144] Illustratively, the plurality of commodity categories can be "all", "eat", "wear", "home life", etc. respectively. The commodity category "eat" can be represented as "good to eat" in the classification information, the commodity category "wear" can be represented as "good-looking" in the classification information, and the commodity category "home life" can be represented as "comfortable home" in the classification information.

[0145] Step S202: In response to the target user's selection of a target information unit from the plurality of candidate information units, an aggregation page is displayed; the aggregation page includes one or more recommended information units, and different recommended information units correspond to recommended items of different categories corresponding to the target information unit; each candidate information unit includes first evaluation information, and / or each recommended information unit includes second evaluation information; the first evaluation information represents the evaluation of the recommended items of the category corresponding to the candidate information unit by the user who has purchased them, and the second evaluation information represents the evaluation of the user who has purchased the recommended items of the category corresponding to the recommended information unit.

[0146] A recommended item corresponding to a candidate information unit can be understood as a category of recommended items belonging to the candidate information unit pair. In other words, the first evaluation information can represent the evaluation of the recommended item category by users who have purchased the item corresponding to their respective candidate information unit. A candidate information unit can correspond to one or more recommended item categories, with each candidate information unit corresponding to one recommended item category.

[0147] Taking the product selection scenario as an example, such as Figure 4 As shown, the aggregation interface may include multiple recommendation information units 421 to 426, etc. Each recommendation information unit in the aggregation interface includes product information of the recommended product corresponding to that recommendation information unit, such as images, prices, merchant information, etc.

[0148] Different candidate information units can correspond to different selling points. In other words, different candidate information units correspond to recommended products with different selling points.

[0149] The recommended products corresponding to the recommended information units on the aggregation page possess the selling points corresponding to the target information unit. That is, each recommended information unit on the aggregation page has specific selling points that match the selling points of the target information unit. The aggregation page, based on the target information unit selected by the user from the candidate information units, determines the selling points the user needs, and then pushes relevant products to the user based on those selling points, thus achieving an organic unity of directional selection and diversity selection in the user's shopping guidance process.

[0150] As mentioned earlier, a product's selling points can indicate one or more of its type, features, etc.

[0151] By guiding the various candidate information units in the page to divide the goods according to the selling points, the user's selection and purchase of the goods can be provided with a large direction; through the aggregation page of this step, the user can further filter from the various goods that meet the direction, and the autonomous selection and machine recommendation are combined to obtain a good user experience.

[0152] As shown in Figure 4 The second evaluation information is an evaluation of the recommended goods corresponding to the recommendation information unit by a user who has purchased the recommended goods. The second evaluation information can be a complete evaluation of the recommended goods by the user, or a part of the complete evaluation.

[0153] The second evaluation information can indicate a specific selling point of the recommended goods corresponding to the recommendation information unit where the second evaluation information is located; the specific selling point first conforms to the selling point of the target information unit, and is more detailed in details.

[0154] Similar to the candidate information unit, the specific selling point of the recommended goods corresponding to the recommendation information unit can be determined according to the user evaluation of the recommended goods. The specific selling point is displayed by using the second evaluation information of the recommendation information unit, so that the information displayed by the recommendation information unit is more real, and the trust degree of the user for the recommendation information unit is improved.

[0155] Specifically, before S202, user evaluations of various recommended goods can be obtained, and the user evaluations are semantically analyzed to obtain at least one specific selling point of the recommended goods. Thus, according to the specific selling point of the recommended goods, a recommendation information unit corresponding to the recommended goods can be generated, and the second evaluation information included in the recommendation information unit is used to indicate at least one specific selling point of the recommended goods. The specific selling point and the selling point of the candidate information unit of the guide page are related and have clear differences. The specific selling point can be completely the same as the corresponding selling point, but more generally, the specific selling point is a more detailed and specific selling point of the selling point to which it belongs. For example, in step S101, the selling point of the target information unit selected by the user in the candidate information unit of the guide page is “slim pants”, and the specific selling point corresponding to the first recommendation information unit in the recommendation information unit can be “famous, slim jeans”; the specific selling point corresponding to the second recommendation information unit can be “thin straight version jeans”; these specific selling points are further refinements of the selling point of the target information unit. The relationship between the specific selling point and the second recommendation information is similar to the relationship between the selling point and the first recommendation information above, and the acquisition method is also similar.

[0156] The process of generating and applying the second evaluation information may include the following steps: obtaining user reviews of the recommended product; performing semantic analysis on the user reviews to obtain at least one selling point of the recommended product; generating a recommendation information unit corresponding to the recommended product based on the selling point of the recommended product, wherein the second evaluation information included in the recommendation information unit corresponding to the recommended product is used to indicate the at least one selling point.

[0157] The recommendation information unit may also include information about the user who provides the second evaluation information, such as avatar, nickname, etc.

[0158] Compared to information provided by merchants, user reviews offer greater credibility in reflecting product quality. The second review within a recommendation unit indicates that the recommended product in that unit possesses the same potential selling points as the target unit, increasing target users' trust in these points. The recommendation unit also includes information about the user providing the second review, further reinforcing target users' belief that the second review was determined based on feedback from users who have already purchased the recommended product within that unit.

[0159] The second evaluation information can indicate that the recommended product belongs to the candidate selling point corresponding to the target information unit.

[0160] When a target user selects a target information unit, it indicates their interest in the candidate selling points corresponding to that unit. Secondary evaluation information can further highlight these candidate selling points. The closer connection between secondary and primary evaluation information increases user attention to the recommended information unit containing the secondary evaluation, and enhances user confidence that the recommended products within that unit possess the same candidate selling points as the target unit. This fully leverages the aggregation page's role in guiding and recommending products, ultimately improving the efficiency of the user's product selection process.

[0161] like Figure 4 As shown, the aggregation page can also directly include selling point information 410. Selling point information 410 is used to indicate the selling point corresponding to the target recommended information unit. For example, if the selling point corresponding to the target recommended information unit is "lipstick that makes your skin look whiter", the selling point information in the aggregation page can be expressed as "Family members, which color of lipstick makes your skin look whiter?"; the relationship between the selling point corresponding to the target recommended information unit and the selling point information in the aggregation page can be understood as the relationship between substance and expression.

[0162] For the purposes of this application, the users who provide the first and second evaluation information are considered real users. To determine whether a user who provides evaluation information is a real user, their historical shopping behavior can be analyzed, and users whose shopping behavior meets the preset criteria for real users can be identified as real users.

[0163] The specific selling point of the commodity can be obtained by performing semantic analysis on the user evaluation provided by the real user. The selling point can be obtained in the same manner as the foregoing, and thus will not be described herein again.

[0164] After step S202, if the target user selects a target recommendation information unit from the at least one recommendation information unit, a commodity detail page of a target recommendation commodity corresponding to the selected target recommendation information unit can be displayed.

[0165] The commodity detail page of the target recommendation commodity can be used to introduce the target recommendation commodity in detail.

[0166] The commodity detail page can display detailed pictures of the commodity to the user. The commodity detail page can use the detailed pictures of the commodity in combination with textual descriptions to enable the user to have a more comprehensive understanding of the commodity, thereby enabling the user to have a desire to purchase the commodity.

[0167] The commodity detail page of the target recommendation commodity can include a price of the target recommendation commodity, sales activity information, commodity evaluation, and merchant information of the target recommendation commodity, and the like. The commodity detail page can be clicked to select the target recommendation commodity for purchase.

[0168] Through S201 to S202, the evaluation information of the user is introduced into the guide page and / or the aggregation page. The shopping guide information is formed based on the real evaluation content of the user on the article category. The user can easily see the purchase or use feedback of other users on the article category before selecting the article category. The user can understand the real information of the article category. The user can select the article category based on the real and efficient article category guide method. The user can be provided with the guide recommendation of the article category. The article category provider can avoid interference of the user's selection caused by piling up unreal keywords on the introduction information of the article category for the purpose of attracting traffic. The efficiency of the selection of the article category by the user is improved, and the selection cost is reduced.

[0169] In the case where S201 to S202 are executed by the terminal, the display of the guide page, the aggregation page, and the commodity detail page can be understood as a display process of the guide page, the aggregation page, and the commodity detail page in a display interface.

[0170] In the case where S201 to S202 are executed by the server, the display of the guide page, the aggregation page, and the commodity detail page can be respectively understood as sending the guide page, the aggregation page, and the commodity detail page to the terminal, so that the terminal displays the guide page, the aggregation page, and the commodity detail page.

[0171] The selection of the target information unit, the target recommendation information unit by the target user can be understood as the operation of the user on the terminal. In the case of performing by the server in S201 to S202, the server can receive the information sent by the terminal to indicate the operation of the user on the terminal.

[0172] The display of the aggregation page can be performed in the case of obtaining the target selling point. The obtaining manner of the target selling point can be that the target selling point is obtained by obtaining the selection of the target user on the target recommendation unit. Or, the obtaining manner of the target selling point can also be that the input information of the user is obtained, and the input information of the user indicates the target selling point. Specifically, refer to the description of Figure 5 and Figure 6 .

[0173] Figure 5 is a schematic flow chart of a method for processing information related to an article provided by the third embodiment of the present application. Figure 5 The method shown in the figure includes steps S501 to S503, and please refer to Figure 6 This embodiment focuses on the guiding page in the search mode based on the first embodiment and the second embodiment, taking the scenario of selecting and purchasing goods as an example.

[0174] In step S501, the target selling point determined by the target user is obtained.

[0175] As in the second embodiment, the target information unit is obtained according to the selection of the target user on the candidate information unit in the guiding page, and the target selling point can be determined according to the target information unit. The guiding page includes at least one candidate information unit, and different candidate information units correspond to different selling points. The selected candidate information unit is the target information unit, and the selling point corresponding to the target information unit is the target selling point. That is, the target selling point is the selling point corresponding to the target information unit selected by the target user in the at least one candidate information unit in the guiding page. The guiding page can refer to the description of Figure 2 and Figure 3 .

[0176] Unlike the second embodiment, the guiding page in this embodiment can adopt a search page, that is, the page includes at least a search bar, and at this time, the target selling point can be the input information of the target user in the search bar.

[0177] In response to the selection operation of the user on the search box in the guiding page, the user can be prompted to perform the search operation. In response to the input operation of the user on the target selling point in the search bar, step S402 can be performed.

[0178] The guiding page with the search box, that is, the search page, can be Figure 6The search page can include a search bar 610. The search page can also include a plurality of selling point example units 621-624, etc. Each selling point example unit can show a target user an example selling point in text to guide the user to input a target selling point in the search bar of the search page. The selling point example unit can be understood as a guide label, which can directly describe a certain selling point in text. The user can directly select the selling point example unit as the target selling point. For example, the selling point example unit "skinny pants" displayed in the form of a text box directly prompts the user to click the selling point example unit, which has the same effect as the selling point described in text by the user in the search bar selling point example unit.

[0179] At step S502, an aggregation page is displayed according to the target selling point, the aggregation page including one or more recommendation information units, each recommendation information unit corresponding to a recommended product whose user evaluation indicates that the recommended product has the target selling point.

[0180] Each recommendation information unit can include second evaluation information. The second evaluation information in each recommendation information unit is determined according to the evaluation of the purchased users of the recommended product corresponding to the recommendation information unit. The aggregation page can refer to the description of Figure 1 、 Figure 2 and Figure 4 .

[0181] The semantic analysis of the user evaluations of the plurality of products respectively can obtain the product selling points of each product. The product selling points of the plurality of products are compared with the target selling point respectively, and the products corresponding to the product selling points matching the target selling point can be used as recommended products. For the plurality of products, the determination of the product selling points can be performed before S501.

[0182] Since the user evaluations of the products are constantly updated, the product selling points can also be updated periodically or non-periodically. For example, the user evaluations of the products are periodically or non-periodically subjected to semantic analysis, thereby updating the product selling points of the products.

[0183] The recommendation information units displayed in the aggregation page of the present embodiment can use a recall ranking algorithm to determine the plurality of recommendation information units and the display position or display order for the guide page in the form of a search page.

[0184] Matching refers to determining a target object associated with a matching condition from a plurality of candidate objects in an object set according to the matching condition, i.e., determining as many target objects as possible in the object set that are related to the matching condition, and using the target objects as the basis for ranking. Through matching, the target objects associated with the matching condition can be found out as much as possible. Ranking refers to uniformly evaluating the target objects, and ranking the target objects in order of relevance from large to small according to the evaluation results.

[0185] On the aggregation page, the order of the various recommended information units can be sorted based on recall. Recommended products that appear earlier in the order are more in line with the user's target selling points, making it easier for the user to find the products they need.

[0186] S503, upon receiving the target user's selection of a target recommendation information unit, display the product details page of the target recommended product corresponding to the selected target recommendation information unit.

[0187] By mining user reviews for various products, and using steps S501 to S503 to incorporate the mined product selling points into product information, the product information becomes more authentic. Based on the selling points obtained from user reviews, product recommendations are made to users, resulting in more accurate descriptions of the recommended products, reducing the user's purchasing costs, and improving the user experience.

[0188] The above text combined Figures 1 to 6 The present application describes a method for processing article-related information provided in its embodiments. The following is a summary of the method. Figures 7 to 9 This section describes the apparatus embodiments of the present application. It should be understood that the processing methods related to article-related information correspond to the descriptions of the apparatus embodiments; therefore, any parts not described in detail can be referred to the above description.

[0189] Figure 7 This is a schematic structural diagram of a processing device for information related to articles provided in the fourth embodiment of this application. Figure 7 The processing device for item-related information shown includes: an acquisition unit 701, a processing unit 702, and a display unit 703.

[0190] The acquisition unit 701 is used to acquire the target attention elements determined by the target user; the processing unit 702 is used to determine one or more recommended items from the multiple categories of items based on the target attention elements and the evaluation information of multiple categories of items, wherein the evaluation information of each recommended item in each category is associated with the target attention elements; the display unit 703 is used to display an aggregation page, wherein the aggregation page includes one or more recommendation information units, and different recommendation information units correspond to different recommended items in the categories.

[0191] Optionally, each category of items is a product, and each category of recommended items is a recommended product, with the target focus element being the product's target selling point.

[0192] Optionally, the display unit 703 is further configured to display a first guide page, the first guide page comprising a plurality of candidate information units, different candidate information units corresponding to different selling points; the obtaining unit 701 is specifically configured to determine that the target selling point is a selling point corresponding to a target information unit in the plurality of candidate information units, in response to selection of the target information unit by the target user.

[0193] Optionally, each candidate information unit comprises first evaluation information of a user who has purchased a product with a selling point corresponding to the candidate information unit, the first evaluation information indicating the selling point corresponding to the candidate information unit.

[0194] Optionally, the candidate information unit comprises information of a user who makes the first evaluation information in the candidate information unit.

[0195] Optionally, the first guide page further comprises evaluation guide information, the evaluation guide information being determined according to a product purchased by the target user who opens the first guide page, and the evaluation guide information being used to guide the target user to make an evaluation of the product.

[0196] Optionally, the apparatus further comprises an inquiring unit and a generating unit; the inquiring unit is configured to inquire a user attribute of the target user; and the generating unit is configured to generate the first guide page according to the user attribute, a selling point corresponding to at least one candidate information unit in the first guide page matching the user attribute.

[0197] Optionally, the generating unit is specifically configured to determine at least one candidate selling point corresponding to the target user according to the user attribute; and a selling point corresponding to one or more candidate information units in the first guide page comprises the at least one candidate selling point.

[0198] Optionally, the display unit 703 is further configured to display a second guide page, the second guide page comprising a search box; and the obtaining unit 701 is specifically configured to obtain the target selling point input by the target user in the search box.

[0199] Optionally, the processing unit 702 is specifically configured to perform semantic analysis on evaluation information of the plurality of products respectively, to obtain a product selling point of each product; and the product selling point of each recommended product comprises the target selling point.

[0200] Optionally, each recommendation information unit comprises second evaluation information of a user who has purchased a recommended product corresponding to the recommendation information unit, the second evaluation information indicating the target selling point.

[0201] Optionally, the processing unit 702 is specifically configured to determine the one or more recommended commodities from the plurality of commodities according to the target selling point and a recall ranking algorithm based on commodity evaluation information, and rank the one or more recommended commodities.

[0202] Optionally, the display unit 703 is further configured to display a commodity detail page of a target recommended commodity corresponding to a target recommended information unit selected by the target user from the one or more recommended information units.

[0203] Figure 8 FIG. 5 is a schematic structural diagram of a processing device for information related to an article according to a fifth embodiment of the present application. Figure 8 The processing device for information related to an article shown in the figure includes a first display unit 801 and a second display unit 802.

[0204] The first display unit 801 is configured to display a guide page including a plurality of candidate information units, each candidate information unit having a recommended article of a corresponding category. The second display unit 802 is configured to display an aggregation page in response to a target information unit selected by a target user from the plurality of candidate information units; the aggregation page includes one or more recommended information units, different recommended information units corresponding to recommended articles of different categories corresponding to the target information unit; each candidate information unit includes first evaluation information, and / or each recommended information unit includes second evaluation information; the first evaluation information represents the evaluation of a user who has purchased the recommended article of the category corresponding to the candidate information unit, and the second evaluation information represents the evaluation of a user who has purchased the recommended article of the category corresponding to the recommended information unit.

[0205] Optionally, the recommended article of each category is a recommended commodity.

[0206] Optionally, different candidate information units correspond to different selling points; the recommended commodity corresponding to the recommended information unit of the aggregation page has the selling point corresponding to the target information unit.

[0207] Optionally, each recommended information unit includes the second evaluation information indicating that the recommended commodity has the selling point corresponding to the target information unit.

[0208] Optionally, the selling point of the recommended commodity included in each candidate information unit is consistent with the selling point corresponding to the candidate information unit, and the selling point of the recommended commodity is obtained by performing semantic analysis on user evaluation of the recommended commodity.

[0209] Optionally, the candidate information unit comprises information of a user who makes the first evaluation information.

[0210] Optionally, the apparatus further comprises a first processing unit configured to determine one or more target recommended products from the plurality of products according to the target information unit corresponding to a selling point and evaluation information of the plurality of products, wherein the evaluation information of each recommended product is associated with the target selling point.

[0211] Optionally, the first processing unit is specifically configured to determine the one or more target recommended products from the plurality of products by using a recall ranking algorithm based on the evaluation information of the products, and rank the one or more target recommended products in the aggregated page.

[0212] Optionally, the guide page further comprises evaluation guide information, wherein the evaluation guide information is determined according to a purchased product of the target user who opens the guide page, and the evaluation guide information is used to guide the user to make an evaluation on the purchased product.

[0213] Optionally, the apparatus further comprises a query unit and a first generation unit, wherein the query unit is configured to query a user attribute of the target user, and the first generation unit is configured to generate the guide page according to the user attribute, wherein the one or more candidate information units in the guide page have a selling point matched with the user attribute.

[0214] Optionally, the second evaluation information is obtained by: obtaining a user evaluation of the recommended product; performing semantic analysis on the user evaluation to obtain at least one selling point of the recommended product; and generating a recommended information unit corresponding to the recommended product according to the selling point of the recommended product, wherein the second evaluation information included in the recommended information unit corresponding to the recommended product is used to indicate the at least one selling point.

[0215] Optionally, different candidate information units correspond to different selling points, and the first evaluation information in each candidate information unit is used to indicate the selling point corresponding to the candidate information unit.

[0216] Optionally, the apparatus further comprises a first processing unit and a second generation unit, wherein the first processing unit is configured to determine at least one candidate selling point for the target user according to a user attribute of the target user, and the second generation unit is configured to generate the guide page for the target user according to the at least one candidate selling point, wherein the guide page comprises one or more candidate information units having candidate selling points.

[0217] Figure 9 is a schematic structural diagram of an electronic device provided by the sixth embodiment of the present application. The electronic device is used to implement Figure 2 ,Figure 5 or Figure 6 a method for processing information related to an article.

[0218] As Figure 9 shown, the electronic device includes: including: including memory 901, processor 902, communication interface 903 and communication bus 904. Among them, the memory 901, the processor 902, the communication interface 903 are communicated with each other through the communication bus 904.

[0219] The memory 901 can be a read only memory (ROM), a static storage device, a dynamic storage device or a random access memory (RAM). The memory 901 can store programs, and when the programs stored in the memory 901 are executed by the processor 902, the processor 902 and the communication interface 903 are used to execute each step of the method for processing information related to an article according to the embodiments of the application.

[0220] The processor 902 can adopt a general central processor (CPU), a microprocessor, an application specific integrated circuit (ASIC), a graphics processor (GPU) or one or more integrated circuits, which is used to execute related programs to realize the functions required by the units in the processing device of the information related to the article according to the embodiments of the application, or execute the method for processing information related to an article according to the method embodiments of the application.

[0221] The processor 902 can also be an integrated circuit chip on which resides an entirety of the processing capability of the electronic device. In implementation, various steps of the method for processing information related to an article according to the present application can be completed by integrated logic circuit of hardware in the processor 902 or by instructions in the form of software. The processor 902 described above can also be a general-purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware component. The methods, steps and logical block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in conjunction with the embodiments of the present application can be directly embodied as a hardware code processor to execute, or be executed by a combination of hardware and software modules in the code processor. The software module can be located in a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, or other mature storage medium in the art. The storage medium is located in the memory 901, and the processor 902 reads the information in the memory 901, and combines the hardware to complete the functions required by the units included in the processing device for information related to an article according to the embodiments of the present application, or executes the processing method for information related to an article according to the method embodiments of the present application.

[0222] The communication interface 903 uses a transceiver such as, but not limited to, a transceiver to implement Figure 9 communication between the electronic device shown and other devices or communication networks.

[0223] The communication bus 904 can include a path for transmitting information between various components (for example, the memory 901, the processor 902, the communication interface 903) of the electronic device shown. Figure 9

[0224] The embodiments of the present application also provide a storage medium, which stores a program, and the program is executed by a processor to implement the processing method for information related to an article.

[0225] The embodiments of the present application can involve the use of user data. In actual application, user-specific personal data can be used in the schemes described herein within the scope allowed by applicable laws and regulations, for example, with the explicit consent of the user, with the actual notification to the user, etc.

[0226] ​It is noted that, although several modules or units for performing actions are mentioned in the above detailed description, such division is not mandatory. Indeed, according to the specific implementation of the present application, the features and functionalities of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functionalities of one module or unit described above can be further divided into several modules or units embodied.

[0227] Furthermore, although the various steps of the methods of the present application are described in a particular order in the figures, this is not required or implied, nor is it necessary to perform all of the steps shown in order to achieve the desired result. Additionally or alternatively, certain steps can be omitted, several steps can be combined into one step, one step can be broken into several steps, etc.

[0228] It should be noted that the embodiments of the present application can be realized by hardware, software, or a combination of software and hardware. The hardware part can be realized by special logic; the software part can be stored in a memory and executed by an appropriate instruction execution system, such as a microprocessor or a specially designed hardware. Those skilled in the art can understand that the above-mentioned devices and methods can be realized by computer executable instructions and / or included in processor control codes, such as carrier media, such as magnetic disk, CD or DVD-ROM, programmable memory, such as read-only memory (firmware), or data carrier, such as optical or electronic signal carrier. The devices of the present application and their modules can be realized by hardware circuit, such as ultra-large scale integrated circuit or gate array, semiconductor, such as logic chip, transistor, or programmable hardware device, such as field programmable gate array, programmable logic device, etc., or by software executed by various types of processors, or by a combination of the above hardware circuit and software, such as firmware.

[0229] The above description is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any modification, equivalent replacement and improvement made by those skilled in the art within the technical scope disclosed in the present application, which is within the spirit and principle of the present application, should be covered by the protection scope of the present application.

Claims

1. A method of processing information associated with an article, characterized by, The method comprises: obtaining a target attention element determined by a target user; determining one or more recommended items of a plurality of categories of items according to the target attention element and evaluation information of the plurality of categories of items, wherein each recommended item is associated with the target attention element, each item of a category is a commodity, each recommended item of a category is a recommended commodity, and the target attention element is a target selling point of a commodity; performing semantic analysis on the evaluation information of the plurality of commodities respectively to obtain a commodity selling point of each commodity, and the commodity selling point of each recommended commodity includes the target selling point; displaying an aggregation page, wherein the aggregation page comprises one or more recommended information units, and different recommended information units correspond to the recommended items of different categories.

2. The method of claim 1, wherein, The method further comprises displaying a first guide page, wherein the first guide page comprises a plurality of candidate information units, and different candidate information units correspond to different selling points. The method further comprises determining the target selling point as a selling point corresponding to a target information unit in the plurality of candidate information units in response to selection of the target information unit by the target user.

3. The method of claim 2, wherein, Each candidate information unit comprises first evaluation information of a user who has purchased a commodity having a selling point corresponding to the candidate information unit, and the first evaluation information indicates the selling point corresponding to the candidate information unit.

4. The method of claim 3, wherein, The candidate information unit comprises information of a user who makes the first evaluation information in the candidate information unit.

5. The method according to any one of claims 2-4, characterized in that, The first guide page further comprises evaluation guide information, wherein the evaluation guide information is determined according to a purchased commodity of the target user who opens the first guide page, and the evaluation guide information is used to guide the target user to make an evaluation of the purchased commodity.

6. The method according to any one of claims 2-4, characterized in that, The method further comprises: inquiring a user attribute of the target user; generating the first guide page according to the user attribute, wherein at least one selling point corresponding to a candidate information unit in the first guide page matches the user attribute.

7. The method of claim 6, wherein, The method further comprises determining at least one candidate selling point corresponding to the target user according to the user attribute when generating the first guide page according to the user attribute. The selling point corresponding to one or more candidate information units in the first guide page includes the at least one candidate selling point.

8. The method of claim 1, wherein, The method further comprises displaying a second guide page, wherein the second guide page comprises a search box. The method further comprises obtaining the target selling point input by the target user in the search box.

9. The method according to any one of claims 1-4, 8, characterized in that, Each recommended information unit comprises second evaluation information of a user who has purchased a recommended commodity corresponding to the recommended information unit, and the second evaluation information indicates the target selling point.

10. The method according to any one of claims 1-4, 8, characterized in that, The method further comprises determining one or more recommended items of a plurality of categories of items according to the target attention element and evaluation information of the plurality of categories of items, wherein each recommended item is associated with the target attention element, each item of a category is a commodity, each recommended item of a category is a recommended commodity, and the target attention element is a target selling point of a commodity; performing semantic analysis on the evaluation information of the plurality of commodities respectively to obtain a commodity selling point of each commodity, and the commodity selling point of each recommended commodity includes the target selling point; According to the target selling point, one or more recommended commodities are determined from a plurality of commodities by using a recall ranking algorithm based on commodity evaluation information, and ranking, which is the order of the one or more recommended commodities in the aggregation page.

11. The method according to any one of claims 1-4, 8, characterized in that, The method further includes: if the target user selects a target recommendation information unit from the one or more recommendation information units, displaying a commodity detail page of a target recommended commodity corresponding to the selected target recommendation information unit.

12. A method of processing information associated with an article, characterized by, The method comprises: displaying a guide page, the guide page comprising a plurality of candidate information units, each candidate information unit having a corresponding category of recommended items; in response to a target user selecting a target information unit from the plurality of candidate information units, displaying an aggregation page; the aggregation page comprises one or more recommendation information units, different recommendation information units corresponding to different categories of recommended items corresponding to the target information unit; each candidate information unit includes first evaluation information, and / or each recommendation information unit includes second evaluation information; the first evaluation information represents the evaluation of the recommended items of the category by the user who has purchased the recommended items of the category corresponding to the candidate information unit, and the second evaluation information represents the evaluation of the user who has purchased the recommended items of the category corresponding to the recommendation information unit.

13. A processing apparatus for information related to articles, characterized in that, The method comprises: an acquisition unit configured to acquire a target focus element determined by a target user; a processing unit configured to determine one or more recommended items of a category from a plurality of items of the category based on the target focus element and evaluation information of the items of the plurality of categories, wherein the evaluation information of each recommended item is associated with the target focus element, wherein each item of the category is a commodity, each recommended item of the category is a recommended commodity, and the target focus element is a target selling point of the commodity; and performing semantic analysis on the evaluation information of the plurality of commodities respectively to obtain a commodity selling point of each commodity, wherein the commodity selling point of each recommended commodity includes the target selling point; a display unit configured to display an aggregation page, the aggregation page comprising one or more recommendation information units, different recommendation information units corresponding to different categories of recommended items.

14. A processing apparatus for information related to articles, characterized in that, The method comprises: a first display unit configured to display a guide page, the guide page comprising a plurality of candidate information units, each candidate information unit having a corresponding category of recommended items; a second display unit configured to display an aggregation page in response to a target user selecting a target information unit from the plurality of candidate information units; the aggregation page comprises one or more recommendation information units, different recommendation information units corresponding to different categories of recommended items corresponding to the target information unit; each candidate information unit includes first evaluation information, and / or each recommendation information unit includes second evaluation information; the first evaluation information represents the evaluation of the recommended items of the category by the user who has purchased the recommended items of the category corresponding to the candidate information unit, and the second evaluation information represents the evaluation of the user who has purchased the recommended items of the category corresponding to the recommendation information unit.

15. An electronic device, comprising: The method comprises: a memory configured to store a computer program; A processor is configured to execute the computer program to perform the method of any one of claims 1 to 12.

16. A storage medium, characterized by The storage medium stores a program, and the program is executed by a processor to implement the method of any one of claims 1 to 12.

Images