Commodity searching method and electronic equipment

Abstract

The embodiment of the invention discloses a commodity searching method and electronic equipment, and the method comprises the steps that after a commodity searching request input by a first user is received, an interaction area is provided in a commodity searching result page, the interaction area is used for providing a plurality of decision parameters, part or all of the decision parameters are associated with parameter value options, and the parameter value options are selected from the parameter value options; the decision parameters displayed in the interaction area comprise a part of professional decision parameters related to commodity batch purchase or customization in the category or industry to which the currently searched commodity belongs; the professional decision parameter is generated by an artificial intelligence (AI) large model through reasoning and analyzing commodity information and / or user behavior data of the category or the industry; and after a parameter value setting result of the first user for the plurality of decision parameters is received, updating a commodity search result. Through the embodiment of the invention, the user can be more effectively helped to obtain a more accurate search result.

Description

Technical Field

[0001] The present application relates to the technical field of commodity search, and in particular to a commodity search method and electronic equipment. Background Art

[0002] In a product information service system (also known as an e-commerce platform), product search is an important way for users to obtain product information. Users can initiate product searches by entering keywords, etc. The system can return a list of products that match the keywords, from which users can select products of interest, etc. However, in actual applications, after users enter a keyword to initiate a search, they often need to narrow the search scope. For example, a user enters "dress" to initiate a search, but since there are many products under the "dress" category, the user may need to narrow the search scope, for example, modify the keyword to "French court style dress", etc. In addition, some systems also provide users with "filtering" or "screening" functions, for example, filtering by category, etc. However, the above filters may involve operations such as step-by-step selection of categories during use, which have operational difficulties and usability issues, and the usage rate is not high. Summary of the invention

[0003] The present application provides a product search method and an electronic device that can more effectively help users obtain more accurate search results.

[0004] This application provides the following solutions:

[0005] A commodity search method, comprising:

[0006] After receiving a product search request input by a first user, an interactive area is provided in the product search result page, the interactive area is used to provide multiple decision parameters, wherein some or all of the decision parameters are associated with parameter value options, and the decision parameters displayed in the interactive area include: a part of professional decision parameters related to bulk purchase or customization of products in the category or industry to which the currently searched product belongs; the professional decision parameters are generated by the artificial intelligence AI big model through reasoning and analysis of product information and / or user behavior data in the category or industry;

[0007] After receiving the parameter value setting results completed by the first user for the plurality of decision parameters, the product search results are updated.

[0008] Among them, it also includes:

[0009] In the process of updating the product search results, the decision parameter information displayed in the interactive area is updated, wherein the updated decision parameters are selected and determined from the decision parameter set except for the decision parameters whose parameter values ​​have been set, so as to further narrow the product search range.

[0010] Among them, the updated product search results are generated with the assistance of the AI ​​big model.

[0011] The updated product search results are obtained in the following ways:

[0012] Determining the search requirements of the first user according to the parameter value settings of the multiple decision parameters, and generating product search results according to the set of matching products corresponding to the search requirements;

[0013] The matching product set is generated in the following manner: based on the multiple decision parameters and parameter value options corresponding to the category or industry, a variety of possible product search needs are enumerated, and the AI ​​big model performs matching calculations based on the multimodal product information of multiple products in the product library, and then generates and saves a matching product set corresponding to the multiple product search needs.

[0014] The decision parameters also include: decision parameters related to the service capability, level or attitude of the second user, where the second user is a wholesaler or production supplier of the goods.

[0015] The parameter values ​​set by the first user for multiple decision parameters during multiple rounds of interaction are saved, so that when the first user initiates a product search request for the same category or industry again, the product search results can be obtained by applying the set parameter values.

[0016] The commodity search request input by the first user includes: a commodity search request initiated by inputting a sentence expressed in a natural language.

[0017] A commodity information processing method, comprising:

[0018] Use artificial intelligence (AI) big models to perform reasoning and analysis on product information and / or user behavior data of multiple categories or industries, and determine multiple professional decision-making parameters and parameter value options related to bulk purchase or customization of products in the same category or industry;

[0019] By combining multiple parameter value options of multiple decision parameters corresponding to the same category or industry, multiple possible user search needs are determined;

[0020] Use the AI ​​big model to perform reasoning analysis on the multimodal product information in the product library, determine the product set that matches multiple possible user search needs in the same category or industry, and save the matching results;

[0021] After receiving the first user's product search request and parameter value setting information for multiple decision parameters under a certain category or industry, the first user's search needs are determined, and product search results are generated according to the matching product set corresponding to the search needs.

[0022] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of any of the methods described above.

[0023] An electronic device, comprising:

[0024] one or more processors; and

[0025] A memory associated with the one or more processors, the memory being used to store program instructions, wherein the program instructions, when read and executed by the one or more processors, execute the steps of any of the methods described above.

[0026] A computer program product comprises a computer program / computer executable instructions, wherein the computer program / computer executable instructions implement the steps of any of the aforementioned methods when executed by a processor in an electronic device.

[0027] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0028] Through the embodiment of the present application, in the process of the first user who is mainly a Class B buyer searching for goods, an interactive area can be provided in the product search result page, and the interactive area is used to display multiple decision parameters, wherein some or all of the decision parameters can also be associated with parameter value options, wherein the displayed decision parameters can be part of the professional decision parameters related to bulk purchase or customization of goods in the category or industry to which the currently searched goods belong, and these professional decision parameters can be generated by the AI ​​big model through reasoning and analysis of the product information and / or user behavior data of the category or industry. After the first user completes the parameter value setting for multiple decision parameters, the product search results can be updated. In this way, AI technology can be applied to the product search scenario for Class B users, providing users with professional decision parameters related to bulk purchase or customization of goods in specific product categories or industries, and effectively helping users to narrow the search scope by setting the parameter values ​​of professional decision parameters to obtain more accurate search results.

[0029] In a preferred manner, the decision parameter information displayed in the interactive area can also be updated during the display of the updated product search results, wherein the updated decision parameters are selected and determined from the remaining decision parameters after removing the decision parameters for which parameter values ​​have been set from the entire set of decision parameters, so as to further narrow the product search range. In this way, through multiple rounds of interaction, the number of parameter setting operations performed by the user in the same interaction can be avoided.

[0030] In addition, in a preferred manner, the specific decision parameters provided may include not only parameters related to product attributes, but also decision parameters related to the capabilities, levels, services, etc. of the first user, i.e., the supplier, so that the first user can screen according to the first user's situation.

[0031] Of course, any product implementing the present application does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0033] Figure 1 It is a schematic diagram of the system architecture provided by the embodiment of the present application;

[0034] Figure 2 is a flowchart of a client-side method provided in an embodiment of the present application;

[0035] Figure 3 is a schematic diagram of a first interface provided in an embodiment of the present application;

[0036] Figure 4 is a schematic diagram of a second interface provided in an embodiment of the present application;

[0037] Figure 5 is a schematic diagram of a third interface provided in an embodiment of the present application;

[0038] Figure 6 is a flow chart of the server-side method provided in an embodiment of the present application;

[0039] Figure 7 It is a schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0040] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments in the present application belong to the scope of protection of this application.

[0041] First of all, it should be noted that with the emergence of AI (Artificial Intelligence) models, especially AI large-scale parameter models (AI large models for short), they have been applied in multiple scenarios, and also provide a new idea for product search. In fact, related attempts have been made in some systems. In their specific solutions, users can express their search needs by entering natural language, for example, "I want to buy a smart watch." After that, the AI ​​assistant can help users narrow the search scope. For example, the AI ​​assistant can display some options for users to choose, including: buying for men, women or children, what is the approximate price range, whether fitness tracking functions are needed, whether there are high requirements for intelligence, and so on. Users can make choices for these options respectively, and then give the corresponding product search results.

[0042] Compared with the method of providing filters through the sidebar, the above scheme is more conducive to obtaining more accurate search results. However, the inventor of the present application found that the above scheme still has at least the following problems in the process of realizing the present application: First, the above scheme is mainly designed for the shopping scenarios of Class C buyers. The so-called Class C buyers refer to individual consumers or terminal buyers. Such Class C buyers mainly use the goods for personal consumption when purchasing. Therefore, the required decision factors are usually relatively few, generally focusing on who uses it, price, performance (conclusive expressions are sufficient, for example, high, medium, low, etc.), and usually there are no very professional decision factors. Therefore, when guiding users to narrow the search scope, AI assistants generally only need to list a few simple decision factors for users to choose, and then give search results. The specific decision factors can be directly configured manually in advance.

[0043] However, in e-commerce scenarios related to cross-border trade, buyers usually belong to Class B buyers. Unlike Class C buyers, Class B buyers usually refer to bulk buyers or corporate buyers. They purchase a large number of goods and may even need to customize the goods from some factory-type merchants. In addition, the purchase of goods is mainly for commercial purposes, such as wholesale, resale, etc. Therefore, the shopping mode and interaction mode of Class B buyers in e-commerce platforms will also be different from those of Class C buyers. This difference can be specifically reflected in that the decision factors that Class B buyers need to consider when purchasing goods are usually highly professional and may be large in number. Moreover, for different commodity categories or industries, the specific decision factors will also vary greatly. At this time, if the specific decision factors are still manually configured, the workload will be too large, and the professional requirements for the configuration personnel will also be very high. The configuration personnel need to have a deep understanding of the professional knowledge of all walks of life, which will obviously incur great labor costs and time costs. In addition, since the number of specific decision factors may be relatively large, if all decision factors are listed for users to choose, as in the prior art, it may cause user disgust.

[0044] Therefore, considering the above situation, in the embodiment of the present application, in the process of using AI technology to help users search for goods, the AI ​​assistant can interact with the user for multiple rounds. Specifically, after the user enters the search request and gives the search results, an interactive area can be provided in the search results page, and multiple decision parameters can be displayed in the interactive area. These decision parameters can be professional decision parameters related to bulk purchase or customization of goods in the category or industry to which the currently searched goods belong, but they do not have to be all decision parameters, but only part of them. In other words, in the process of multiple rounds of interaction, each round may only require the user to set the parameter values ​​of some decision parameters. After the user sets the parameter values ​​of some parameters, the search results can be updated, and then the next round of interaction with the user can be carried out. At this time, in a preferred manner, other decision parameters that have not yet been set can be displayed in the interactive area. In this way, through multiple rounds of interaction, users can gradually narrow their search scope and gradually obtain more accurate search results.

[0045] Of course, the specific decision parameters displayed in each round can be determined by selecting from the total set of decision parameters associated with the category or industry to which the currently searched product belongs. Among them, since the specific decision parameters are relatively professional, they can be generated by means of an AI big model. That is to say, in specific implementation, the product information and user behavior information related to the specific category or industry (of course, the user behavior information can also be user behavior data related to bulk purchase or processing customization, including purchase order information issued by the buyer user, inquiry information, and conversation record information during the online dialogue and communication between the buyer and the seller on a certain procurement demand, etc.) can be input into the AI ​​big model in advance, and the AI ​​big model performs reasoning and analysis to give the professional decision parameters that users usually pay attention to when making bulk purchases or customizing goods in this category or industry. In addition, the AI ​​big model can also generate parameter value options under specific decision parameters. For example, the decision parameter "pattern type" can include specific parameter values: flowers, stripes, solid colors, etc. The above process can be completed in advance by performing offline reasoning using a large AI model, so as to obtain a total set of decision parameters corresponding to multiple different categories or industries, and can also provide corresponding parameter value options for some or all of the decision parameters.

[0046] In this way, after receiving a product search request from a buyer user (which can be referred to as the first user in the embodiment of the present application, and the merchant user can be referred to as the second user accordingly), when it is specifically necessary to display decision parameters in the interactive area of ​​the product search results page, some decision parameters can be selected for display from the above-mentioned decision parameter set pre-produced for the category or industry to which the currently searched product belongs. When selecting, the decision parameters can be selected based on the personalized preference data of the current first user, or the group preference data of the group to which the current first user belongs. For example, assuming that the historical transaction data of a first user shows that each of them pays attention to price attributes, the price-related decision parameters can be displayed to the first user first in the first round of interaction, and so on.

[0047] After the first user completes the parameter value setting of some or all of the decision parameters through the above-mentioned interactive area, the search results can be regenerated based on the parameter value setting results and displayed to the first user. Among them, in specific implementation, this regenerated search result can be generated in multiple ways. For example, in one way, the user's parameter value configuration of multiple decision parameters can be used as more keywords, and then the search results can be given by keyword search. However, in specific implementation, since the specific decision parameters and parameter value options are generated by AI, these parameter value information may not appear directly in the text description information such as the title of the product. Therefore, it may be difficult to obtain accurate search results by directly searching the parameter value as a keyword. For this reason, in a preferred manner, after the user completes the parameter value setting of multiple decision parameters, the AI ​​big model can specifically perform natural language understanding on the user's search request and the parameter value setting situation, and give the corresponding product search results based on the understanding of the user's specific needs. In other words, this product matching method is no longer a keyword matching, but the AI ​​big model completes the matching of products and user needs through natural language understanding, so as to give more accurate and comprehensive search results.

[0048] In addition, since only part of the decision parameters are displayed in the first round of interaction, the specific displayed decision parameters can be updated in the interactive area of ​​the search results page while updating the search results. Among them, when updating the decision parameters, the decision parameters that have completed the parameter value setting before may no longer appear, but only the decision parameters that have not yet been set can be displayed. That is, after the decision parameters corresponding to the current commodity category or industry are removed from the entire set of decision parameters, the decision parameters that have completed the parameter value setting can be selected and determined from the remaining decision parameters to further narrow the commodity search range. In other words, after each round of interaction is completed, while obtaining the updated search results, a batch of decision parameters can be changed for the user to set the parameter value to further narrow the search range. For example, assuming that the user has selected the parameter value for the parameter "pattern type" in the first round of interaction, the "pattern type" parameter will not appear in the interactive area in the next round of interaction.

[0049] It should be noted that in the embodiment of the present application, since it is mainly aimed at Class B buyers for wholesale purchases or customized processing of goods, Class B buyers, in the process of purchasing, in addition to considering the factors of the goods themselves, usually also consider the factors of the second user, that is, the service capabilities, level, attitude, etc. of the specific merchant or supplier. Therefore, in the preferred implementation of the present application, the specific decision parameters may also include: decision parameters related to the service capabilities, level or attitude of the second user. In this way, the parameter value can be set from the dimension of the second user, and the product search range can be further narrowed.

[0050] Of course, in the process of gradually providing multiple decision parameters through multiple rounds of interaction, options such as "more parameters" can also be provided to users, so that when users need to select parameter values ​​of more parameters in one interaction, more decision parameters and parameter value options related to the current product category or industry can be displayed through this option for users to choose.

[0051] In addition, during the process of setting parameter values ​​in multiple rounds of interaction, the specific parameter value setting results of the user in each round of interaction can also be saved. In this way, when the user initiates a product search request for the same category or industry next time, the previously saved results can be directly applied for search without repeating the process of multiple rounds of interaction, thereby improving efficiency.

[0052] From the perspective of system architecture, the embodiment of the present application can provide a product search function based on AI interaction in the product information service system, wherein the specific product information service system can be a system that provides cross-border e-commerce services for Class B buyers, etc. For details, see Figure 1 , the system may include a client and a server. The client is a client for Class B buyers, which can mainly run on the buyer's mobile phone, personal computer and other terminal devices, while the server can run on the server. Among them, the client is mainly used to interact with the user, including providing a search portal for the user so that the user can initiate a product search request and display the search results. In the embodiment of the present application, in the process of displaying the search results, an interactive area can also be provided for interacting with the AI ​​assistant, and refreshing and displaying the search results after the interaction, etc. The server is mainly used to provide specific data, including the generation of search results, the call of AI large models, the storage of related data (for example, decision parameters and parameter option information corresponding to multiple categories or industries, etc.), and so on.

[0053] The specific solutions provided in the embodiments of the present application are described in detail below.

[0054] Embodiment 1

[0055] First, the first embodiment of the present application provides a commodity search method from the perspective of the client, see Figure 2 , the method may specifically include:

[0056] S201: After receiving a product search request input by a first user, an interactive area is provided in the product search result page, wherein the interactive area is used to provide multiple decision parameters, wherein some or all of the decision parameters are associated with parameter value options, and the decision parameters displayed in the interactive area include: a part of professional decision parameters related to bulk purchase or customization of products in the category or industry to which the currently searched product belongs; the professional decision parameters are generated by an artificial intelligence AI big model through reasoning and analysis of product information and / or user behavior data in the category or industry.

[0057] In the embodiment of the present application, after the first user generates a commodity search demand, he can first initiate a search request by inputting keywords, or, in a preferred manner, since the commodity search can be performed by AI interaction, the user can also initiate a specific commodity search request by inputting a long sentence expressed in natural language. In other words, the information input when initiating a specific search request may no longer be words or phrases in the traditional keyword search method, but may be a long sentence. For example, assuming that the user needs to search for commodities related to smart watches, according to the traditional search method, the keyword input can be "smart watches", while in the search method that supports AI interaction, the user can enter a longer sentence to express his needs more completely, for example, "I want to buy a smart watch for my daughter, which does not require too many functions, but is convenient for contacting the child", etc. Correspondingly, after receiving the user's search request, the natural language long sentence input by the user can also be understood by the AI ​​large model, and then the corresponding commodity search results are given.

[0058] Among them, in the embodiment of the present application, while displaying the product search results, an interactive area can also be provided in the product search results page, and the interactive area can be used to display multiple decision parameters, and the specific decision parameters can be part of the professional decision parameters related to bulk purchase or customization of the product in the category or industry to which the currently searched product belongs. Specifically, such professional decision parameters can be generated by the AI ​​big model through reasoning and analysis of the product information and / or user behavior data of the category or industry.

[0059] For example, Figure 3As shown in the figure, it shows a part of the search result page displayed after the first user inputs the search request in the embodiment of the present application, wherein 31 shows the information of some products in the specific search results, and 32 shows the interactive area in the search result page. As can be seen from the figure, the interactive area displays multiple decision parameters, including pattern type, supplier country / region, service, etc. The first user can narrow the search scope by setting the parameter values ​​of these decision parameters. Of course, since in one round of interaction, only some decision parameters are usually displayed in the interactive area, if the user needs to set the parameter values ​​of more parameters in one interaction, he can do so by clicking Figure 3 , and then click on the "Set all requirements" option shown in the figure to display more decision parameters and set them accordingly. Figure 3 In the example shown, if you click this option, the displayed interface can be as follows Figure 4 As shown, the parameters and parameter values ​​that the user has used (parameters that have been set in the previous round or a historical interaction round, and the corresponding parameter values) can be displayed, and more decision parameters to be set can also be displayed.

[0060] It should be noted that when displaying specific decision parameters, parameter value options may be provided for some decision parameters. For example, for the parameter "pattern type", parameter value options may include flowers, stripes, solid colors, etc.; while some decision parameters do not need to provide parameter value options. For example, for parameters such as price range, the first user may set them by inputting specific values, etc. When providing specific parameter value options, each parameter value option may be displayed in a "capsule-style" manner, so that the user can intuitively know that these options can be clicked and selected, thereby reducing the user's understanding cost of the operation method.

[0061] It should also be noted that in the embodiment of the present application, the specific decision parameters may include not only parameters related to the attributes of the product, but also decision parameters related to the second user (i.e., the supplier user of the wholesale or production of the product, also referred to as the supplier). In other words, in the process of purchasing by Class B buyers, in addition to considering whether the product itself meets their needs, they will also examine the service capabilities, level or attitude of the second user. Therefore, in the embodiment of the present application, such decision parameters related to the second user may also be provided to the first user during the search process. For example, Figure 4As shown in 41, it may include two label items, namely, "Product Attributes" and "Supplier Services and Capabilities". The first user may choose to set the decision parameters related to the product attributes or the decision parameters related to the supplier services and capabilities by switching the label items. If "Product Attributes" is selected, the interface display may be as follows: Figure 4 If you select "Supplier Services and Capabilities", the specific interface can be displayed as follows Figure 5 As shown, parameter value options may include "Design-based customization", "Fully customized", "Minor customization", etc.

[0062] S202: After receiving the parameter value setting results completed by the first user for multiple decision parameters, update the product search results.

[0063] After the first user completes the parameter value setting for multiple decision parameters, the product search results can be updated. Among them, as mentioned above, in a preferred manner, specifically when the search results are updated, the AI ​​big model can infer the search needs of the first user based on the product search request input by the first user and the parameter value setting of multiple decision parameters to generate product search results. In other words, specifically when the search results are updated, since parameter values ​​may be set for multiple decision parameters, and these parameter values ​​do not necessarily appear directly in the text description content such as the title and detailed information of the product, the multimodal information processing and understanding capabilities of the AI ​​big model can be used to infer the specific needs of the first user and search for matching products. Among them, when matching the needs of the first user with the product information, the AI ​​big model can be used to understand the various different contents such as text, images, user reviews, etc. associated with the product, and on this basis, matching calculations are performed with the first user's demand information.

[0064] It should be noted here that since the AI ​​big model may take a long time to match the search needs of the first user with the products, in order to avoid the first user waiting too long, the various search needs that the first user may generate can be enumerated in advance, and the AI ​​big model can infer the matching product sets corresponding to the various search needs through offline calculation (where the identification information such as the product ID can be saved), and save them on the server. In this way, when the first user initiates a specific search request and sets the parameter values ​​of the decision parameters, and the AI ​​big model determines the search needs, the matching product set corresponding to the search needs can be determined by querying the data pre-stored on the server, and then the search results can be determined from the matching product set (including re-screening or sorting some personalized information of the first user). After the user sets the parameter values ​​for some decision parameters, the search needs are updated. Accordingly, the matching product set corresponding to the new search needs can be queried from the server again, and new search results can be determined from it.

[0065] Specifically, when enumerating various search demands that may be generated by the first user offline, since the complete set of professional decision parameters corresponding to specific product categories or industries can be determined, and most decision parameters can provide parameter value options, various search demands can be enumerated by permuting and combining the various parameter values ​​of these decision parameters. Of course, in the process of permutation and combination, some obviously unreasonable combinations can also be removed through manual verification, and then the AI ​​large model can determine the corresponding matching product sets for various combinations.

[0066] In addition, since only some decision parameters are displayed by default during the first round of interaction, other decision parameter information for which parameter values ​​have not yet been set can be re-displayed in the interactive area of ​​the search results page while the search results are updated, so that the first user can further narrow his search scope by setting parameter values ​​for these decision parameters and obtain search results that better meet his needs.

[0067] It should be noted here that, in a specific implementation, the interaction between the first user and the AI ​​assistant may be carried out in multiple rounds, and parameter values ​​may be set for more decision parameters in each round until the first user obtains a satisfactory product position.

[0068] In addition, since the first user in the embodiment of the present application is usually a Class B buyer, when searching for goods, it is usually for a certain purchasing demand, and the purchasing demand usually means wholesale of goods, or even entrusting factories to process and customize, etc. Therefore, it may be necessary to repeatedly compare goods and so on before a specific product or supplier can be selected. It is also because of this that the same first user may search for goods in the same category or industry at different times, and the specific search needs may be the same. Therefore, in the specific implementation, in order to facilitate the improvement of search efficiency in the above situation, the parameter values ​​set by the first user for multiple decision parameters during multiple rounds of interaction can also be saved. In this way, when the first user initiates a search request for goods in the same category or industry again, the product search results can be obtained by directly applying the set parameter values. For example, a first user needs to search for products in a certain category or industry, and sets parameter values ​​of 12 decision parameters through multiple rounds of interaction. The parameter value setting results of the 12 decision parameters can be saved on the server; when the first user initiates a product search request for the category or industry again, an option can be provided in the interface to allow the first user to directly apply the parameter values ​​previously set for the 12 decision parameters. In this way, the first user does not need to conduct multiple rounds of interactions with the AI ​​assistant, nor does he need to re-set the parameter values ​​of these decision parameters, and can directly obtain the corresponding search results.

[0069] In summary, through the embodiments of the present application, in the process of searching for goods by the first user who is mainly a Class B buyer, an interactive area can be provided in the product search result page, and the interactive area is used to display multiple decision parameters, wherein some or all of the decision parameters can also be associated with parameter value options, wherein the displayed decision parameters can be part of the professional decision parameters related to bulk purchase or customization of goods in the category or industry to which the currently searched goods belong, and these professional decision parameters can be generated by the AI ​​big model through reasoning and analysis of the product information and / or user behavior data of the category or industry. After the first user completes the parameter value setting for multiple decision parameters, the product search results can be updated. In this way, AI technology can be applied to product search scenarios for Class B users, providing users with professional decision parameters related to bulk purchase or customization of goods in specific product categories or industries, and effectively helping users to narrow the search scope by setting the parameter values ​​of professional decision parameters to obtain more accurate search results.

[0070] In a preferred manner, the decision parameter information displayed in the interactive area can also be updated during the display of the updated product search results, wherein the updated decision parameters are selected and determined from the remaining decision parameters after removing the decision parameters for which parameter values ​​have been set from the entire set of decision parameters, so as to further narrow the product search range. In this way, through multiple rounds of interaction, the number of parameter setting operations performed by the user in the same interaction can be avoided.

[0071] In addition, in a preferred manner, the specific decision parameters provided may include not only parameters related to product attributes, but also decision parameters related to the capabilities, levels, services, etc. of the first user, i.e., the supplier, so that the first user can screen according to the first user's situation.

[0072] Embodiment 2

[0073] This second embodiment provides a method for processing commodity information from the perspective of the server. Figure 6 , the method may specifically include:

[0074] S601: Use an artificial intelligence (AI) big model to perform reasoning analysis on product information and / or user behavior data of multiple categories or industries, and determine multiple professional decision parameters related to bulk purchase or customization of products in the same category or industry, as well as parameter value options;

[0075] S602: Determine multiple possible user search needs by combining multiple parameter value options of multiple decision parameters corresponding to the same category or industry;

[0076] S603: Use the AI ​​big model to perform reasoning analysis on the multimodal product information in the product library, determine a set of products that match multiple possible user search needs in the same category or industry, and save the matching results;

[0077] S604: After receiving the product search request from the first user and parameter value setting information for multiple decision parameters under a certain category or industry, the search requirements of the first user are determined, and product search results are generated according to a set of matching products corresponding to the search requirements.

[0078] For the parts not described in detail in the second embodiment, please refer to the description of the first embodiment and other parts of this specification, which will not be repeated here.

[0079] It should be noted that the embodiments of the present application may involve the use of user data. In actual applications, user-specific personal data can be used in the scheme described herein within the scope permitted by applicable laws and regulations, subject to the requirements of applicable laws and regulations of the country where the user is located (for example, with the user's explicit consent, effective notification to the user, etc.).

[0080] Corresponding to the first embodiment, the embodiment of the present application further provides a commodity search device, which may include:

[0081] An interactive area providing unit is used to provide an interactive area in the product search result page after receiving a product search request input by a first user, wherein the interactive area is used to provide multiple decision parameters, wherein some or all of the decision parameters are associated with parameter value options, and the decision parameters displayed in the interactive area include: a part of professional decision parameters related to bulk purchase or customization of products in the category or industry to which the currently searched product belongs; the professional decision parameters are generated by an artificial intelligence AI big model through reasoning and analysis of product information and / or user behavior data in the category or industry;

[0082] The search result updating unit is used to update the product search results after receiving the parameter value setting results completed by the first user for multiple decision parameters.

[0083] In a specific implementation, the device may further include:

[0084] A decision parameter updating unit is used to update the decision parameter information displayed in the interactive area during the process of updating the product search results, wherein the updated decision parameter is selected and determined from other decision parameters in the entire set of decision parameters except for the decision parameters whose parameter values ​​have been set, so as to further narrow the product search range.

[0085] Among them, the updated product search results can be generated with the assistance of an AI big model.

[0086] In specific implementation, the updated product search results can be obtained in the following ways:

[0087] Determining the search requirements of the first user according to the parameter value settings of the multiple decision parameters, and generating product search results according to the set of matching products corresponding to the search requirements;

[0088] The matching product set is generated in the following manner: based on the multiple decision parameters and parameter value options corresponding to the category or industry, a variety of possible product search needs are enumerated, and the AI ​​big model performs matching calculations based on the multimodal product information of multiple products in the product library, and then generates and saves a matching product set corresponding to the multiple product search needs.

[0089] In addition, the decision parameters may also include: decision parameters related to the service capability, level or attitude of the second user, where the second user is a wholesale or production supplier of the commodity.

[0090] Furthermore, the device may further include:

[0091] A parameter value saving unit is used to save the parameter values ​​set by the first user for multiple decision parameters during multiple rounds of interaction, so that when the first user initiates a product search request for the same category or industry again, the product search results can be obtained by applying the set parameter values.

[0092] The commodity search request input by the first user includes: a commodity search request initiated by inputting a sentence expressed in a natural language.

[0093] Corresponding to the second embodiment, the embodiment of the present application further provides a commodity information processing device, which may include:

[0094] A decision parameter determination unit is used to use an artificial intelligence (AI) big model to perform reasoning analysis on product information and / or user behavior data of multiple categories or industries, and determine multiple professional decision parameters related to bulk purchase or customization of products in the same category or industry, as well as parameter value options;

[0095] A demand enumeration unit is used to determine multiple possible user search demands by combining multiple parameter value options of multiple decision parameters corresponding to the same category or industry;

[0096] A storage unit, used to use the AI ​​big model to perform reasoning analysis on the multimodal product information in the product library, determine a set of products that match multiple possible user search needs in the same category or industry, and save the matching results;

[0097] The query unit is used to determine the search requirements of the first user after receiving the product search request of the first user and the parameter value setting information of multiple decision parameters under a category or industry, and generate product search results based on the matching product set corresponding to the search requirements.

[0098] In addition, an embodiment of the present application further provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the steps of any one of the methods in the aforementioned method embodiments are implemented.

[0099] And an electronic device, comprising:

[0100] one or more processors; and

[0101] A memory associated with the one or more processors, the memory being used to store program instructions, wherein the program instructions, when read and executed by the one or more processors, execute the steps of the method described in any one of the aforementioned method embodiments.

[0102] A computer program product includes a computer program / computer executable instructions, which, when executed by a processor in an electronic device, implement the steps of the method described in the aforementioned method embodiment.

[0103] in, Figure 7 The architecture of the electronic device is shown as an example, which may include a processor 710, a video display adapter 711, a disk drive 712, an input / output interface 713, a network interface 714, and a memory 720. The processor 710, the video display adapter 711, the disk drive 712, the input / output interface 713, the network interface 714, and the memory 720 may be communicatively connected via a communication bus 730.

[0104] Among them, the processor 710 can be implemented by a general-purpose CPU (Central Processing Unit, processor), a microprocessor, an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), or one or more integrated circuits, etc., to execute relevant programs to implement the technical solution provided in this application.

[0105] The memory 720 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 720 can store an operating system 721 for controlling the operation of the electronic device 700, and a basic input and output system (BIOS) for controlling the low-level operation of the electronic device 700. In addition, a web browser 723, a data storage management system 724, and a commodity search processing system 725, etc. can also be stored. The above-mentioned commodity search processing system 725 can be an application program that specifically implements the operations of the aforementioned steps in the embodiment of the present application. In short, when the technical solution provided by the present application is implemented by software or firmware, the relevant program code is stored in the memory 720 and is called and executed by the processor 710.

[0106] The input / output interface 713 is used to connect the input / output module to realize information input and output. The input / output module can be configured in the device as a component (not shown in the figure), or it can be externally connected to the device to provide corresponding functions. The input device may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device may include a display, a speaker, a vibrator, an indicator light, etc.

[0107] The network interface 714 is used to connect to a communication module (not shown) to realize communication interaction between the device and other devices. The communication module can realize communication through a wired mode (such as USB, network cable, etc.) or a wireless mode (such as mobile network, WIFI, Bluetooth, etc.).

[0108] The bus 730 comprises a pathway for transmitting information between the various components of the device (eg, the processor 710, the video display adapter 711, the disk drive 712, the input / output interface 713, the network interface 714, and the memory 720).

[0109] It should be noted that, although the above device only shows a processor 710, a video display adapter 711, a disk drive 712, an input / output interface 713, a network interface 714, a memory 720, a bus 730, etc., in the specific implementation process, the device may also include other components necessary for normal operation. In addition, it can be understood by those skilled in the art that the above device may also only include components necessary for implementing the solution of the present application, and does not necessarily include all the components shown in the figure.

[0110] It can be known from the description of the above implementation methods that those skilled in the art can clearly understand that the present application can be implemented by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present application can be essentially or partly contributed to the prior art in the form of a software product, which can be stored in a storage medium such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in the various embodiments of the present application or certain parts of the embodiments.

[0111] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can refer to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system or system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiment. The system and system embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0112] The above is a detailed introduction to the commodity search method and electronic device provided by the present application. This article uses specific examples to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and its core idea of ​​the present application. At the same time, for those skilled in the art, according to the idea of ​​the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present application.

Claims

1. A commodity search method, characterized in that: include: After receiving a product search request input by a first user, an interactive area is provided in the product search result page, the interactive area is used to provide multiple decision parameters, wherein some or all of the decision parameters are associated with parameter value options, and the decision parameters displayed in the interactive area include: a part of professional decision parameters related to bulk purchase or customization of products in the category or industry to which the currently searched product belongs; The professional decision parameters are generated by the artificial intelligence AI model through reasoning and analysis of the product information and / or user behavior data of the category or industry; After receiving the parameter value setting results completed by the first user for the plurality of decision parameters, the product search results are updated.

2. The method according to claim 1, characterized in that Also includes: In the process of updating the product search results, the decision parameter information displayed in the interactive area is updated, wherein the updated decision parameters are selected and determined from the entire set of decision parameters except for the decision parameters whose parameter values ​​have been set, so as to further narrow the product search scope.

3. The method according to claim 1, characterized in that: The updated product search results are generated with the assistance of an AI big model.

4. The method according to claim 1, characterized in that: Get updated product search results by: Determining the search requirements of the first user according to the parameter value settings of the multiple decision parameters, and generating product search results according to the set of matching products corresponding to the search requirements; The matching product set is generated in the following manner: based on the multiple decision parameters and parameter value options corresponding to the category or industry, a variety of possible product search needs are enumerated, and the AI ​​big model performs matching calculations based on the multimodal product information of multiple products in the product library, and then generates and saves a matching product set corresponding to the multiple product search needs.

5. The method according to claim 1, characterized in that The decision parameters also include: decision parameters related to the service capability, level or attitude of the second user, where the second user is a wholesale or production supplier of the commodity.

6. The method according to claim 1, characterized in that The parameter values ​​set by the first user for multiple decision parameters during multiple rounds of interaction are saved, so that when the first user initiates a product search request for the same category or industry again, the product search results can be obtained by applying the set parameter values.

7. The method according to claim 1, characterized in that The commodity search request input by the first user includes: a commodity search request initiated by inputting a sentence expressed in a natural language.

8. A commodity information processing method, characterized in that: include: Use artificial intelligence (AI) big models to perform reasoning and analysis on product information and / or user behavior data of multiple categories or industries, and determine multiple professional decision-making parameters and parameter value options related to bulk purchase or customization of products in the same category or industry; By combining multiple parameter value options of multiple decision parameters corresponding to the same category or industry, multiple possible user search needs are determined; Use the AI ​​big model to perform reasoning analysis on the multimodal product information in the product library, determine the product set that matches multiple possible user search needs in the same category or industry, and save the matching results; After receiving the first user's product search request and parameter value setting information for multiple decision parameters under a certain category or industry, the first user's search needs are determined, and product search results are generated according to the matching product set corresponding to the search needs.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method described in any one of claims 1 to 8 are implemented.

10. An electronic device, characterized in that: include: one or more processors; as well as A memory associated with the one or more processors, the memory being used to store program instructions, wherein the program instructions, when read and executed by the one or more processors, execute the steps of the method described in any one of claims 1 to 8.

11. A computer program product comprising a computer program / computer executable instructions, characterized in that: When the computer program / computer executable instructions are executed by a processor in an electronic device, the steps of the method according to any one of claims 1 to 8 are implemented.

Images