Commodity recommendation method and device, nonvolatile storage medium and electronic equipment

Abstract

The invention discloses a commodity recommendation method and device, a nonvolatile storage medium and electronic equipment. The method comprises the steps of obtaining keywords of a browsed commodity corresponding to a target account, and a category to which the browsed commodity belongs; the keyword and the category to which the keyword belongs are input into a target large language model, the target large language model outputs a first commodity set and a second commodity set, the first commodity set comprises commodity identifiers matched with the keyword, the second commodity set comprises commodity identifiers in the category matched with the category to which the second commodity set belongs, and the commodity identifiers in the category matched with the category to which the second commodity set belongs are input into the target large language model; the target large language model is obtained by finely adjusting a pre-trained large language model through a first training sample; solving a union set of the first commodity set and the second commodity set to obtain a third commodity set; and sorting the commodity identifiers included in the third commodity set, and selecting a plurality of commodities recommended for the target account in sequence. The technical problem that commodities cannot be accurately and efficiently recommended to users in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the field of commodity recommendation, and in particular to a commodity recommendation method, device, non-volatile storage medium and electronic device. Background Art

[0002] Existing product recommendation technologies are often limited to the platform's user behavior data and product information, and lack the ability to utilize external knowledge, such as user reviews in the public domain, social media discussions, etc. This results in the limited knowledge boundaries of the recommendation system, making it difficult to explore more potential matching relationships. Moreover, the manually configured matching rules are highly dependent on the experience of business personnel for judgment, which requires a lot of time and manpower costs. Manual rules are also difficult to capture the complex and subtle matching logic between products, especially on e-commerce platforms with a huge number of products and a wide variety of products. In addition, in the face of rapidly changing market trends and user preferences, there is a certain lag in the update and adjustment of product matching rules, making it difficult to recommend suitable products to users.

[0003] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0004] The embodiments of the present invention provide a product recommendation method, device, non-volatile storage medium and electronic device to at least solve the technical problem in the prior art that products cannot be accurately and efficiently recommended to users.

[0005] According to one aspect of an embodiment of the present invention, a product recommendation method is provided, comprising: obtaining keywords for browsing products corresponding to a target account, and categories to which the browsed products belong; inputting the keywords and the categories to which the browsed products belong into a target large language model, and outputting a first product set and a second product set by the target large language model, wherein the first product set includes product identifiers matching the keywords, and the second product set includes product identifiers within categories matching the categories to which the products belong, wherein the target large language model is obtained by fine-tuning a pre-trained large language model using a first training sample, and the first training sample includes sample keywords of the sample product and the categories to which the samples belong; obtaining a union of the first product set and the second product set to obtain a third product set; sorting the product identifiers included in the third product set, and selecting multiple products recommended to the target account in order.

[0006] Optionally, the target large language model is obtained in the following manner: obtaining the product name of the sample product; determining the sample keyword corresponding to the sample product and the sample category corresponding to the sample product based on the product name of the sample product; generating a first training sample based on the sample keyword and the sample category; and fine-tuning the pre-trained large language model based on the first training sample to obtain the target large language model.

[0007] Optionally, based on the product name of the sample product, determine the sample keywords corresponding to the sample product and the category to which the sample corresponds to the sample product, including: segmenting the product name of the sample product to obtain the sample keywords corresponding to the sample product; matching the sample keywords with a predetermined category database to determine the category to which the sample corresponds to the sample product.

[0008] Optionally, the product identifiers included in the third product set are sorted, and multiple products recommended for the target account are selected in sequence, including: the third product set is input into a target deep learning model, and the target deep learning model outputs multiple products recommended for the target account, wherein the target deep learning model is obtained by training the original deep learning model with a second training sample, and the second training sample includes historically recommended product identifiers, and historically browsed product identifiers that have been browsed in the historically recommended product identifiers.

[0009] Optionally, the third product set is input into the target deep learning model, and the target deep learning model outputs multiple products recommended for the target account, including: inputting the third product set into the target deep learning model, and predicting the browsing probability of each product included in the third product set by the target deep learning model; sorting the products included in the third product set in descending order of browsing probability, and using the products with arrangement numbers before a predetermined threshold as the multiple products recommended to the target account.

[0010] Optionally, the third product set is input into the target deep learning model, and the target deep learning model predicts the browsing probability of each product included in the third product set, including: obtaining product feature parameters of each product included in the third product set, and account feature parameters corresponding to the target account, wherein the product feature parameters include at least one of the following: price, sales volume, number of evaluations, and evaluation results; the account feature parameters include at least one of the following: historical purchase records, historical search records, and historical browsing records; the product feature parameters of each product included in the third product set, and the account feature parameters corresponding to the target account, are input into the target deep learning model, and the target deep learning model predicts the browsing probability of each product included in the third product set.

[0011] According to another aspect of an embodiment of the present invention, a product recommendation device is provided, including: an acquisition module, used to acquire keywords for browsing products corresponding to a target account, and categories to which the browsed products belong; an output module, used to input the keywords and the categories to which the browsed products belong into a target large language model, and the target large language model outputs a first product set and a second product set, wherein the first product set includes product identifiers matching the keywords, and the second product set includes product identifiers within categories matching the categories to which they belong, wherein the target large language model is obtained by fine-tuning a pre-trained large language model through a first training sample, and the first training sample includes sample keywords of the sample product and the categories to which the samples belong; a calculation module, used to obtain a union of the first product set and the second product set to obtain a third product set; and a recommendation module, used to sort the product identifiers included in the third product set, and select multiple products recommended to the target account in order.

[0012] According to another aspect of an embodiment of the present invention, a non-volatile storage medium is provided, wherein the non-volatile storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing any one of the commodity recommendation methods.

[0013] According to another aspect of an embodiment of the present invention, there is provided an electronic device, comprising: one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement any one of the product recommendation methods.

[0014] According to yet another aspect of an embodiment of the present invention, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, any one of the above-mentioned commodity recommendation methods is implemented.

[0015] In an embodiment of the present invention, keywords for browsing products corresponding to a target account and categories to which the browsed products belong are obtained; the keywords and categories are input into a target large language model, and the target large language model outputs a first product set and a second product set, wherein the first product set includes product identifiers matching the keywords, and the second product set includes product identifiers within categories matching the categories, wherein the target large language model is obtained by fine-tuning a pre-trained large language model through a first training sample, and the first training sample includes sample keywords of sample products and categories to which the samples belong; the first product set and the second product set are unioned to obtain a third product set; the product identifiers included in the third product set are sorted, and a plurality of products recommended to the target account are sequentially selected, thereby solving the technical problem in the prior art that products cannot be accurately and efficiently recommended to users, achieving the purpose of using a large model for recommendation and being able to use knowledge in the public domain to mine the relationship between products, thereby achieving the technical effect of improving the accuracy and efficiency of product recommendations. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0017] Figure 1 is a flow chart of a commodity recommendation method provided according to an embodiment of the present invention;

[0018] Figure 2 is a schematic diagram of a commodity recommendation device provided according to an embodiment of the present invention;

[0019] Figure 3 A schematic diagram of an electronic device provided according to an embodiment of the present invention. DETAILED DESCRIPTION

[0020] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0021] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0022] According to an embodiment of the present invention, a method embodiment for product recommendation is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0023] Figure 1 is a flowchart of a commodity recommendation method according to an embodiment of the present invention. Figure 1 As shown, the method comprises the following steps:

[0024] Step S102, obtaining keywords for browsing products corresponding to the target account, and the categories to which the browsed products belong;

[0025] In this step, all the browsed product information is first obtained from the user's browsing history. This information usually includes product ID, browsing time, browsed product title, etc. Keyword extraction is performed for each browsed product, that is, the core product words or attribute words of the product that can accurately reflect the type, purpose, style and other key information of the product are identified. In addition, it is also necessary to determine the category to which the browsed product belongs based on the product title or other information, as well as the product category system preset by the platform. For example, if the product browsed by the user is a down jacket, the category described for the browsed product is clothing.

[0026] Step S104, inputting the keywords and the categories to which they belong into the target large language model, and the target large language model outputs a first product set and a second product set, wherein the first product set includes product identifiers matching the keywords, and the second product set includes product identifiers within the category matching the categories to which they belong, wherein the target large language model is obtained by fine-tuning the pre-trained large language model through the first training sample, and the first training sample includes sample keywords of the sample product and the category to which the sample belongs;

[0027] In this step, the keywords and categories of the products in the user's browsing history are input into the large language model to obtain a first product set matching the keywords of the products in the browsing history and a second product set matching the categories of the products in the browsing history. The products included in the first product set are similar or complementary to the products browsed by the user at the keyword level and may be products that the user is interested in. The products included in the second product set are products in the same or related categories that have the potential to match the products browsed by the user.

[0028] In an optional embodiment, the target large language model is obtained in the following manner: obtaining the product name of the sample product; determining the sample keyword corresponding to the sample product and the sample category corresponding to the sample product based on the product name of the sample product; generating a first training sample based on the sample keyword and the sample category; and fine-tuning the pre-trained large language model based on the first training sample to obtain the target large language model.

[0029] Optionally, a series of sample products are collected first. These products can be combinations that are frequently purchased together in historical sales data, products in the matching rules configured by experts, or matching products mentioned in user reviews. Extract the key attribute words of each sample product, and determine the category to which each sample product belongs according to the product classification system preset by the platform. The keywords and categories of each sample product are used as a set of training samples, and the pre-trained large language model is fine-tuned. After the fine-tuning is completed, the pre-trained large language model becomes a "target large language model" that is more focused on the task of product matching recommendation. The pre-trained large language model refers to a model that has been trained on massive text data and has strong language understanding and generation capabilities. However, these models may lack professionalism and pertinence in specific fields, such as e-commerce product matching recommendations. Therefore, by using the first training sample to fine-tune the pre-trained large language model, the model can better understand the matching rules and user preferences in the product field and improve its performance in the task of product matching recommendation.

[0030] In an optional embodiment, based on the product name of the sample product, the sample keyword corresponding to the sample product and the category to which the sample corresponds to the sample product are determined, including: segmenting the product name of the sample product to obtain the sample keyword corresponding to the sample product; matching the sample keyword with a predetermined category database to determine the category to which the sample corresponds to the sample product.

[0031] Optionally, word segmentation is a basic task in natural language processing, which aims to segment continuous text into independent vocabulary units. Based on word segmentation, the obtained vocabulary units are analyzed to determine which words best represent the core attributes or characteristics of the product. The extracted "sample keywords" are matched with the predetermined "category database" to determine the category to which the sample product belongs. The category database is a structured data set containing a large number of product categories and their description information.

[0032] Step S106, finding the union of the first product set and the second product set to obtain a third product set;

[0033] In this step, the first product set and the second product set are unioned to integrate all products in the two sets to create a comprehensive product set, which can capture more potential products that may match the products browsed by the user, avoid missing important combinations, and avoid repeated combinations.

[0034] Step S108, sorting the commodity identifiers included in the third commodity set, and selecting a plurality of commodities recommended to the target account in order.

[0035] Optionally, the products in the third product set are sorted, and the sorting process may involve consideration of multiple features, including product similarity scores, users' past behaviors on similar products (such as clicks, purchases, and favorites), product ratings, prices, promotional information, etc. Through sorting, the products that are most likely to arouse the user's interest can be screened out from the third product set. This personalized sorting takes into account the user's historical behaviors and preferences, as well as the comprehensive characteristics of the products, so that a highly relevant and attractive recommendation list can be generated for the user.

[0036] In an optional embodiment, a third product set is input into a target deep learning model, and the target deep learning model outputs a plurality of products recommended for a target account, wherein the target deep learning model is obtained by training an original deep learning model using a second training sample, and the second training sample includes historically recommended product identifiers and historically browsed product identifiers that have been browsed in the historically recommended product identifiers.

[0037] Optionally, historical recommended product identifiers, i.e., a collection of products recommended to the user in the past, which may not have been viewed or purchased by the user. Historically browsed product identifiers, i.e., identifiers of products that the user has actually viewed or purchased, represent the user's interest and preference for the product. By comparing historically recommended product identifiers and historically browsed product identifiers, the system can construct a dataset for training a deep learning model. The model will learn which features or attributes are associated with user interests, and how to predict the user's potential interest in the product based on these features. After the third product set is input into the target deep learning model, the model will recommend products to the user based on the user preferences and product features learned during the training process.

[0038] In an optional embodiment, the third product set is input into the target deep learning model, and the target deep learning model outputs multiple products recommended for the target account, including: inputting the third product set into the target deep learning model, and predicting the browsing probability of each product included in the third product set by the target deep learning model; sorting the products included in the third product set in descending order of browsing probability, and using the products with arrangement numbers before a predetermined threshold as the multiple products recommended to the target account.

[0039] Optionally, after the third product set is input into the target deep learning model, the model will output a predicted recommendation score or probability for each product identifier based on the user preferences and product features learned during the training process. The product identifiers are sorted in descending order based on these scores or probabilities, thereby forming a list with decreasing relevance to the user's interests. Then, the system will start from the top of the list and select a certain number of product identifiers in order as the final product set recommended to the target account, for example, select the top 10 products to recommend to the user.

[0040] In an optional embodiment, the third product set is input into the target deep learning model, and the target deep learning model predicts the browsing probability of each product included in the third product set, including: obtaining product feature parameters of each product included in the third product set, and account feature parameters corresponding to the target account, wherein the product feature parameters include at least one of the following: price, sales volume, number of evaluations, and evaluation results; the account feature parameters include at least one of the following: historical purchase records, historical search records, and historical browsing records; the product feature parameters of each product included in the third product set, and the account feature parameters corresponding to the target account, are input into the target deep learning model, and the target deep learning model predicts the browsing probability of each product included in the third product set.

[0041] Optionally, for each product in the third product set, the system collects a series of product feature parameters, which may include the price, sales volume, number of reviews, and review results of the product. The product feature parameters provide objective information about the product, helping the model to make recommendations based on the market performance and feedback of the product. At the same time, the system also collects the feature parameters of the target account, which reflect the user's past shopping behavior and preferences, and may include historical purchase records, historical search records, historical browsing records, etc., to help the model make recommendations based on the user's preferences. The product feature parameters and account feature parameters are combined and input into the target deep learning model as input data. The target deep learning model is a trained model that can process and integrate these multi-dimensional feature data to learn the association between users and products and user preferences. After receiving the input feature parameters, the target deep learning model uses its learned patterns to predict the probability of each product being browsed by the target account. This prediction process comprehensively considers the attributes of the product and the user's historical behavior, and the output probability value reflects the probability of the product being browsed by the user in the current context.

[0042] Through the above, keywords for browsing products corresponding to the target account and the categories to which the browsed products belong are obtained; the keywords and the categories to which they belong are input into the target large language model, and the target large language model outputs a first product set and a second product set, wherein the first product set includes product identifiers matching the keywords, and the second product set includes product identifiers within the categories matching the categories to which they belong, wherein the target large language model is obtained by fine-tuning a pre-trained large language model through a first training sample, and the first training sample includes sample keywords of sample products and the categories to which the samples belong; the first product set and the second product set are unioned to obtain a third product set; the product identifiers included in the third product set are sorted, and a plurality of products recommended to the target account are selected in sequence, thereby solving the technical problem in the prior art that products cannot be accurately and efficiently recommended to users, and achieving the purpose of using a large model for recommendation and being able to use knowledge in the public domain to mine the relationship between products, thereby achieving the technical effect of improving the accuracy and efficiency of product recommendations.

[0043] Based on the above embodiments and optional embodiments, the present invention proposes the following optional implementation manner.

[0044] Step S1, obtaining keywords for browsing products corresponding to the target account and the categories to which the browsed products belong;

[0045] Optionally, first obtain all browsed product information from the user's browsing history, which usually includes product ID, browsing time, browsed product title, etc., and perform keyword extraction for each browsed product, that is, identify the core product words or attribute words that can accurately reflect the product's type, purpose, style and other key information. In addition, it is also necessary to determine the category to which the browsed product belongs based on the product title or other information, as well as the product category system preset by the platform. For example, if the user browses a down jacket, the category described for the browsed product is clothing.

[0046] Step S2, inputting the keywords and the categories to which they belong into the target large language model, and the target large language model outputs a first product set and a second product set, wherein the first product set includes product identifiers matching the keywords, and the second product set includes product identifiers within the category matching the categories to which they belong, wherein the target large language model is obtained by fine-tuning the pre-trained large language model through the first training sample, and the first training sample includes sample keywords of the sample product and the category to which the sample belongs;

[0047] In this step, the keywords and categories of the products in the user's browsing history are input into the large language model to obtain a first product set matching the keywords of the products in the browsing history and a second product set matching the categories of the products in the browsing history. The products included in the first product set are similar or complementary to the products browsed by the user at the keyword level and may be products that the user is interested in. The products included in the second product set are products in the same or related categories that have the potential to match the products browsed by the user.

[0048] In step S21, the target large language model is obtained by: obtaining the product name of the sample product; determining the sample keyword corresponding to the sample product and the sample category corresponding to the sample product according to the product name of the sample product; generating a first training sample according to the sample keyword and the sample category; and fine-tuning the pre-trained large language model according to the first training sample to obtain the target large language model.

[0049] Optionally, a series of sample products are collected first. These products can be combinations that are frequently purchased together in historical sales data, products in the matching rules configured by experts, or matching products mentioned in user reviews. Extract the key attribute words of each sample product, and determine the category to which each sample product belongs according to the product classification system preset by the platform. The keywords and categories of each sample product are used as a set of training samples, and the pre-trained large language model is fine-tuned. After the fine-tuning is completed, the pre-trained large language model becomes a "target large language model" that is more focused on the task of product matching recommendation. The pre-trained large language model refers to a model that has been trained on massive text data and has strong language understanding and generation capabilities. However, these models may lack professionalism and pertinence in specific fields, such as e-commerce product matching recommendations. Therefore, by using the first training sample to fine-tune the pre-trained large language model, the model can better understand the matching rules and user preferences in the product field and improve its performance in the task of product matching recommendation.

[0050] Step S22, based on the product name of the sample product, determine the sample keyword corresponding to the sample product and the category to which the sample corresponding to the sample product belongs, including: segmenting the product name of the sample product to obtain the sample keyword corresponding to the sample product; matching the sample keyword with a predetermined category database to determine the category to which the sample corresponding to the sample product belongs.

[0051] Optionally, word segmentation is a basic task in natural language processing, which aims to segment continuous text into independent vocabulary units. Based on word segmentation, the obtained vocabulary units are analyzed to determine which words best represent the core attributes or characteristics of the product. The extracted "sample keywords" are matched with the predetermined "category database" to determine the category to which the sample product belongs. The category database is a structured data set containing a large number of product categories and their description information.

[0052] Step S3, obtaining a union of the first product set and the second product set to obtain a third product set;

[0053] Optionally, in this step, the first product set and the second product set are unioned to integrate all products in the two sets to create a comprehensive product set, which can capture more potential products that may match the products browsed by the user, avoid missing important combinations, and avoid repeated combinations.

[0054] Step S4, sorting the commodity identifiers included in the third commodity set, and selecting a plurality of commodities recommended for the target account in order.

[0055] Optionally, the products in the third product set are sorted, and the sorting process may involve consideration of multiple features, including product similarity scores, users' past behaviors on similar products (such as clicks, purchases, and favorites), product ratings, prices, promotional information, etc. Through sorting, the products that are most likely to arouse the user's interest can be screened out from the third product set. This personalized sorting takes into account the user's historical behaviors and preferences, as well as the comprehensive characteristics of the products, so that a highly relevant and attractive recommendation list can be generated for the user.

[0056] Step S41, sorting the product identifiers included in the third product set, and selecting multiple products recommended for the target account in order, including: inputting the third product set into the target deep learning model, and the target deep learning model outputs multiple products recommended for the target account, wherein the target deep learning model is obtained by training the original deep learning model through the second training sample, and the second training sample includes historically recommended product identifiers, and historically browsed product identifiers that have been browsed in the historically recommended product identifiers.

[0057] Optionally, historical recommended product identifiers, i.e., a collection of products recommended to the user in the past, which may not have been viewed or purchased by the user. Historically browsed product identifiers, i.e., identifiers of products that the user has actually viewed or purchased, represent the user's interest and preference for the product. By comparing historically recommended product identifiers and historically browsed product identifiers, the system can construct a dataset for training a deep learning model. The model will learn which features or attributes are associated with user interests, and how to predict the user's potential interest in the product based on these features. After the third product set is input into the target deep learning model, the model will recommend products to the user based on the user preferences and product features learned during the training process.

[0058] Step S42, inputting the third product set into the target deep learning model, and the target deep learning model outputs multiple products recommended for the target account, including: inputting the third product set into the target deep learning model, and the target deep learning model predicts the browsing probability of each product included in the third product set; sorting the products included in the third product set in descending order of browsing probability, and using the products with arrangement numbers before a predetermined threshold as the multiple products recommended to the target account.

[0059] Optionally, after the third product set is input into the target deep learning model, the model will output a predicted recommendation score or probability for each product identifier based on the user preferences and product features learned during the training process. The product identifiers are sorted in descending order based on these scores or probabilities, thereby forming a list with decreasing relevance to the user's interests. Then, the system will start from the top of the list and select a certain number of product identifiers in order as the final product set recommended to the target account, for example, select the top 10 products to recommend to the user.

[0060] Step S43, input the third product set into the target deep learning model, and the target deep learning model predicts the browsing probability of each product included in the third product set, including: obtaining product feature parameters of each product included in the third product set, and account feature parameters corresponding to the target account, wherein the product feature parameters include at least one of the following: price, sales volume, number of evaluations, and evaluation results; the account feature parameters include at least one of the following: historical purchase records, historical search records, and historical browsing records; input the product feature parameters of each product included in the third product set, and the account feature parameters corresponding to the target account, into the target deep learning model, and the target deep learning model predicts the browsing probability of each product included in the third product set.

[0061] Optionally, for each product in the third product set, the system collects a series of product feature parameters, which may include the price, sales volume, number of reviews, and review results of the product. The product feature parameters provide objective information about the product, helping the model to make recommendations based on the market performance and feedback of the product. At the same time, the system also collects the feature parameters of the target account, which reflect the user's past shopping behavior and preferences, and may include historical purchase records, historical search records, historical browsing records, etc., to help the model make recommendations based on the user's preferences. The product feature parameters and account feature parameters are combined and input into the target deep learning model as input data. The target deep learning model is a trained model that can process and integrate these multi-dimensional feature data to learn the association between users and products and user preferences. After receiving the input feature parameters, the target deep learning model uses its learned patterns to predict the probability of each product being browsed by the target account. This prediction process comprehensively considers the attributes of the product and the user's historical behavior, and the output probability value reflects the probability of the product being browsed by the user in the current context.

[0062] The above optional implementation achieves at least the following effects: solves the technical problem in the prior art that products cannot be accurately and efficiently recommended to users, achieves the purpose of accurately and efficiently recommending products to users, and further achieves the technical effect of improving the accuracy and efficiency of product recommendations.

[0063] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0064] In this embodiment, a commodity recommendation device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and will not be repeated hereafter. As used below, the terms "module" and "device" can implement a combination of software and / or hardware for a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0065] According to an embodiment of the present invention, a device embodiment for implementing a commodity recommendation method is also provided. Figure 2 is a schematic diagram of a commodity recommendation device according to an embodiment of the present invention. Figure 2 As shown, the above-mentioned commodity recommendation device includes an acquisition module 21, an output module 22, a calculation module 23, and a recommendation module 24. The device is described below.

[0066] The acquisition module 21 is used to acquire the keywords of the browsed products corresponding to the target account and the categories to which the browsed products belong;

[0067] The output module 22 is connected to the acquisition module 21 and is used to input the keywords and the categories to which they belong into the target large language model, and the target large language model outputs a first product set and a second product set, wherein the first product set includes product identifiers matching the keywords, and the second product set includes product identifiers within the category matching the categories to which they belong, wherein the target large language model is obtained by fine-tuning the pre-trained large language model through the first training sample, and the first training sample includes sample keywords of the sample product and the category to which the sample belongs;

[0068] A calculation module 23, connected to the output module 22, is used to obtain a union of the first product set and the second product set to obtain a third product set;

[0069] The recommendation module 24 is connected to the calculation module 23 and is used to sort the commodity identifiers included in the third commodity set and select multiple commodities recommended for the target account in order.

[0070] In a product recommendation device provided by an embodiment of the present invention, an acquisition module is set to acquire keywords for browsing products corresponding to a target account and categories to which the browsed products belong; an output module is used to input keywords and categories to which the keywords belong into a target large language model, and the target large language model outputs a first product set and a second product set, wherein the first product set includes product identifiers matching the keywords, and the second product set includes product identifiers within categories matching the categories to which the keywords belong, wherein the target large language model is obtained by fine-tuning a pre-trained large language model through a first training sample, and the first training sample includes sample keywords of sample products and categories to which the samples belong; a calculation module is used to obtain a union of the first product set and the second product set to obtain a third product set; and a recommendation module is used to sort the product identifiers included in the third product set, and select multiple products recommended for the target account in order, thereby solving the technical problem that the prior art cannot accurately and efficiently recommend products to users, and achieving the purpose of using a large model for recommendation and being able to use knowledge in the public domain to mine the relationship between products, thereby achieving the technical effect of improving the accuracy and efficiency of product recommendations.

[0071] It should be noted that the above modules can be implemented by software or hardware. For example, for the latter, it can be implemented in the following ways: the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0072] It should be noted that the acquisition module 21, output module 22, calculation module 23, and recommendation module 24 correspond to steps S102 to S108 in the embodiment, and the examples and application scenarios implemented by the modules and the corresponding steps are the same, but are not limited to the contents disclosed in the embodiment. It should be noted that the modules as part of the device can be run in a computer terminal.

[0073] It should be noted that the optional or preferred implementation of this embodiment can refer to the relevant description in the embodiment, which will not be repeated here.

[0074] The above-mentioned product recommendation may also include a processor and a memory. The acquisition module 21, the output module 22, the calculation module 23, the recommendation module 24, etc. are all stored in the memory as program units, and the processor executes the above-mentioned program units stored in the memory to realize the corresponding functions.

[0075] The processor includes a kernel, which retrieves the corresponding program unit from the memory. There can be one or more kernels. The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one storage chip.

[0076] An embodiment of the present invention provides a non-volatile storage medium on which a program is stored. When the program is executed by a processor, a commodity recommendation method is implemented.

[0077] like Figure 3 As shown, an embodiment of the present invention provides an electronic device, the electronic device 10 includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, the following steps are implemented: the memory is used to store a computer program, wherein when the computer program is executed by the processor, the processor implements the above-mentioned commodity recommendation method. The device in this article may be a server, a PC, etc.

[0078] The present invention also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program that initializes the following method steps: computer instructions are executed by a processor to perform the above-mentioned product recommendation method.

[0079] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0080] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0081] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0082] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0083] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0084] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0085] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0086] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0087] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0088] The above are only embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.

Claims

1. A product recommendation method, characterized in that: include: Obtaining keywords of browsed products corresponding to the target account and the categories to which the browsed products belong; Inputting the keyword and the category to which it belongs into a target large language model, the target large language model outputting a first product set and a second product set, wherein the first product set includes product identifiers matching the keyword, and the second product set includes product identifiers within a category matching the category to which it belongs, wherein the target large language model is obtained by fine-tuning a pre-trained large language model using a first training sample, wherein the first training sample includes sample keywords of sample products and the category to which the samples belong; Calculate the union of the first product set and the second product set to obtain a third product set; The commodity identifiers included in the third commodity set are sorted, and a plurality of commodities recommended for the target account are selected in sequence.

2. The method according to claim 1, characterized in that The target large language model is obtained in the following way: Obtain the product name of the sample product; Determine, according to the product name of the sample product, the sample keyword corresponding to the sample product and the category to which the sample corresponding to the sample product belongs; Generate the first training sample according to the sample keyword and the category to which the sample belongs; The pre-trained large language model is fine-tuned according to the first training sample to obtain the target large language model.

3. The method according to claim 2, characterized in that The determining, according to the product name of the sample product, the sample keyword corresponding to the sample product and the category to which the sample corresponding to the sample product belongs includes: Segmenting the product name of the sample product to obtain sample keywords corresponding to the sample product; The sample keywords are matched with a predetermined category database to determine the category to which the sample corresponds to the sample commodity.

4. The method according to any one of claims 1 to 3, characterized in that The step of sorting the commodity identifiers included in the third commodity set and sequentially selecting a plurality of commodities recommended for the target account includes: The third product set is input into a target deep learning model, and the target deep learning model outputs the multiple products recommended for the target account, wherein the target deep learning model is obtained by training an original deep learning model using a second training sample, and the second training sample includes historically recommended product identifiers and historically browsed product identifiers that have been browsed among the historically recommended product identifiers.

5. The method according to claim 4, characterized in that The step of inputting the third commodity set into a target deep learning model, and having the target deep learning model output the plurality of commodities recommended for the target account, comprises: Inputting the third product set into the target deep learning model, and predicting the browsing probability of each product included in the third product set by the target deep learning model; The commodities included in the third commodity set are sorted in descending order of browsing probability, and the commodities whose arrangement numbers are before a predetermined threshold are used as the multiple commodities recommended to the target account.

6. The method according to claim 5, characterized in that The step of inputting the third product set into the target deep learning model, and predicting the browsing probability of each product included in the third product set by the target deep learning model, includes: Acquire commodity characteristic parameters of each commodity included in the third commodity set, and account characteristic parameters corresponding to the target account, wherein the commodity characteristic parameters include at least one of the following: price, sales volume, number of reviews, and review results, and the account characteristic parameters include at least one of the following: historical purchase records, historical search records, and historical browsing records; The product feature parameters of each product included in the third product set and the account feature parameters corresponding to the target account are input into the target deep learning model, and the target deep learning model predicts the browsing probability of each product included in the third product set.

7. A commodity recommendation device, characterized in that: include: An acquisition module, used to acquire keywords of browsed products corresponding to a target account, and the categories to which the browsed products belong; an output module, configured to input the keyword and the category to which the keyword belongs into a target large language model, and the target large language model outputs a first commodity set and a second commodity set, wherein the first commodity set includes commodity identifiers matching the keyword, and the second commodity set includes commodity identifiers within a category matching the category to which the keyword belongs, wherein the target large language model is obtained by fine-tuning a pre-trained large language model through a first training sample, and the first training sample includes sample keywords of sample commodities and the category to which the samples belong; a calculation module, configured to obtain a union of the first commodity set and the second commodity set to obtain a third commodity set; The recommendation module is used to sort the commodity identifiers included in the third commodity set and select multiple commodities recommended for the target account in order.

8. A non-volatile storage medium, characterized in that: The non-volatile storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the commodity recommendation method described in any one of claims 1 to 6.

9. An electronic device, characterized in that: include: One or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the product recommendation method described in any one of claims 1 to 6.

10. A computer program product comprising computer instructions, characterized in that: The computer instructions are executed by the processor to execute the commodity recommendation method described in any one of claims 1 to 6.

Images