Commodity package generation method and device, storage medium and computer device

Abstract

The application discloses a commodity package generation method and device, a storage medium and a computer device, and relates to the technical field of Internet. The method comprises the following steps: a client sends a commodity package generation request to a server in response to the commodity package generation request; the server acquires user information and merchant information corresponding to the commodity package generation request in response to receiving the commodity package generation request, selects at least one commodity from a commodity list corresponding to the merchant information based on the user information and a preset commodity package combination strategy through a large model, and generates at least one commodity package based on the selected commodities; the server sends package information of the commodity package to the client; and the client receives and displays the commodity package. The above method can customize the commodity package for the user, so that the generated commodity package is more in line with the actual needs and preferences of the user, thereby improving the generation efficiency of the commodity package, the ordering efficiency of the user and the experience of the user.

Description

Technical Field

[0001] This application relates to the field of Internet technology, and in particular to a method, apparatus, storage medium and computer equipment for generating product packages. Background Technology

[0002] In e-commerce, the product packages offered by merchants are often pre-set. These packages are typically created by merchants based on their understanding of the products and users. Specifically, merchants consider factors such as product popularity, cost, and seasonality to combine several products into different packages to attract users and improve order efficiency.

[0003] However, different users often have different product choices and preferences, and the package deals are decided unilaterally by the merchant, lacking effective communication with the user. Therefore, the packages created by merchants often fail to meet users' personalized needs and do not provide sufficient choice, resulting in low user satisfaction. In this scenario, users often need to repackage multiple items to order according to their needs, which reduces ordering efficiency and also diminishes the user experience. Summary of the Invention

[0004] In view of this, the present application provides a product package generation method, apparatus, storage medium and computer equipment, the main purpose of which is to solve the technical problem that the product packages combined by merchants cannot meet the personalized needs of users, resulting in low ordering efficiency and poor user experience.

[0005] According to one aspect of this application, a method for generating a product package is provided, the method comprising:

[0006] The client responds to the product package generation request by sending the product package generation request to the server;

[0007] In response to receiving the product package generation request, the server obtains the user information and merchant information corresponding to the product package generation request, and based on the user information and a preset product package combination strategy, selects at least one product from the product list corresponding to the merchant information through a large model, and generates at least one product package based on the selected product.

[0008] The server sends the package information of the product package to the client;

[0009] The client receives and displays the product package.

[0010] Optionally, the client displays the product package, including: the client displays package information for at least one product package and product information for at least one product in the product package, wherein the package information includes at least one of package label, package prompt, package price, and package order control; the product information includes at least one of product image, product name, product specifications, product price, and product editing control.

[0011] Optionally, the method further includes: the client responding to an editing request for any product in the product package, performing a product editing operation on the product, wherein the product editing operation includes at least one of deletion, replacement, and specification modification operations; and / or, the client responding to an order request for the product package, displaying an order submission page, and displaying the package information of the product package and the product information of at least one product in the product package on the order submission page.

[0012] Optionally, the method further includes: the client displays order remarks information in the remarks information input box on the order submission page, wherein the order remarks information is generated based on the order remarks information in the user's historical orders.

[0013] Optionally, the method further includes: the client receiving and displaying at least one historical order record and / or at least one product keyword, wherein the historical order record is generated based on the user information and the merchant information, and the product keyword is generated based on the historical order record through a large model.

[0014] Optionally, the client displays at least one historical order record and / or at least one product keyword, including: the client displays the historical order record and / or the product keyword in a structured manner; and / or, the client displays at least one product in the historical order record and the number of times the product was ordered; and / or, the client displays the product keyword through a keyword control, wherein the keyword control is used to update the display of the product package in response to a keyword selection operation.

[0015] Optionally, the client responds to the keyword selection operation by updating the displayed product packages, including: the client responds to the keyword selection operation by sorting at least one of the product packages based on the selected product keywords to obtain updated displayed product packages; and / or, the client receives and displays at least one regenerated product package, wherein the product packages are generated based on the user information, the merchant information, and the selected product keywords through a large model.

[0016] Optionally, the method further includes: the client, in response to receiving the product demand information input by the user, receiving and displaying the updated product package, wherein the package information is regenerated based on the user information, the merchant information, and the product demand information; and / or, the client displays a package generation control at at least one location on the current page, wherein the package generation control consists of at least one element among images, icons, and text, and the package generation control is used to send the product package generation request to the server in response to the product package generation request.

[0017] Optionally, the server, based on the user information and a preset product package combination strategy, selects at least one product from the product list corresponding to the merchant information using a large model, and generates at least one product package based on the selected product. This includes: the server obtaining current environmental information and generating the user's historical behavior information based on the user information, wherein the historical behavior information includes behavioral habit information and at least one historical order; the server extracting product combination data matching the behavioral habit information and the environmental information from a knowledge base in a preset domain, and replacing the products in the historical orders based on the product combination data to obtain at least one product package; and / or, the server selecting at least one product from the product list corresponding to the merchant information based on the historical order and the environmental information to obtain at least one product package; and / or, the server selecting at least one product from the product list corresponding to the merchant information based on the merchant information and a preset product combination strategy to obtain at least one product package.

[0018] Optionally, the server obtains the current environmental information and generates the user's historical behavior information based on the user information, including: the server calls an environmental information query tool through a large model to obtain the current environmental information, wherein the environmental information includes at least one of time information, location information, and season information; the server calls a user information query tool through a large model to obtain the user's historical behavior information, wherein the historical behavior information includes behavioral habit information and historical orders within a preset time period.

[0019] Optionally, the server extracts product combination data matching the behavioral habit information and the environmental information from a knowledge base in a preset domain, and replaces the products in the historical orders based on the product combination data to obtain at least one product package. This includes: the server extracting product combination data matching the behavioral habit information and the environmental information from a knowledge base in a preset domain, wherein the product combination data includes at least one of product type combination data, product specification combination data, product quantity combination data, and product avoidance data; and the server replacing at least one product in at least one historical order based on the product combination data to obtain at least one product package.

[0020] Optionally, the historical orders are multi-product orders and / or package orders; then the server, based on the product combination data, replaces at least one product in at least one historical order to obtain at least one product package, including: the server, based on the product combination data, replaces at least one product in the multi-product order and / or the package order to obtain at least one product package, wherein the replaced product is a product with an order rate lower than a preset threshold, and / or, the product specifications of the replaced product are determined according to the product specifications of the products in the historical order.

[0021] Optionally, the server selects at least one product from the product list corresponding to the merchant information based on the historical orders and the environmental information to obtain at least one product package, including: the server determines at least one alternative order from the historical orders based on the environmental information, wherein the alternative order is a multi-product order and / or package order within a preset time period; the server selects at least one product based on the products in the multi-product order and the product specifications of the products, and combines the selected products into at least one product package; and / or, the server selects at least one product based on the products in the package order and the product specifications of the products, and combines the selected products into at least one product package.

[0022] Optionally, the merchant information includes at least one of the following: product discount rules, product production speed, product listing time, and product type. Then, based on the merchant information and a preset product combination strategy, the server selects at least one product from the product list corresponding to the merchant information to obtain at least one product package, including: the server selecting at least one product from the product list corresponding to the merchant information based on the product discount rules and the product combination strategy to obtain at least one product package; and / or, the server selecting at least one product from the product list corresponding to the merchant information based on the product production speed and the product combination strategy to obtain at least one product package; and / or, the server selecting at least one product from the product list corresponding to the merchant information based on the product listing time and the product combination strategy to obtain at least one product package; and / or, the server selecting at least one product from the product list corresponding to the merchant information based on the product type and the product combination strategy to obtain at least one product package.

[0023] Optionally, the method further includes: the server calculating the matching degree between the product package and the user information, and sorting the product packages according to the matching degree to obtain sorted product packages; and / or, the server setting package tags and / or package prompts for the product packages according to the product package combination strategy corresponding to the product packages, and setting the package tags and / or the package prompts in the package information of the product packages.

[0024] Optionally, the method further includes: the server determining the package price of the product package based on the product price of the product in the product package and the product discount rules in the merchant information, and setting the package price in the package information of the product package; and / or, the server determining the package price of the product package based on the product price of the product in the product package and a preset package price calculation strategy, and setting the package price in the package information of the product package after the package price is confirmed by the merchant.

[0025] Optionally, the method further includes: the merchant receiving a product package and its price from the server; the merchant sending a confirmation instruction to the server in response to a confirmation operation of the package price, so that the server sets the package price in the package information of the product package after receiving the confirmation instruction; and / or sending a modified package price to the server in response to a modification operation of the package price, so that the server sets the modified package price in the package information of the product package after receiving the modified package price; and / or sending the product package and its price to the server, so that the server confirms the package price through a large model, and sets the package price in the package information of the product package after confirmation; and / or sending the product package and its price to the server, so that the server adjusts the package price through a large model, and sets the adjusted package price in the package information of the product package.

[0026] Optionally, the method further includes: the server generating first order summary data for the product package and second order summary data for the products in the product package based on the order data of the product package within a preset time period, and sending the first order summary data and the second order summary data to the merchant terminal; the merchant terminal receiving and displaying the first order summary data and the second order summary data.

[0027] According to another aspect of this application, a method for generating a product package is provided, the method comprising:

[0028] In response to the request to generate a product package, the request to generate the product package is sent;

[0029] Receive and display at least one product package, wherein the product package is composed of at least one product from the product list of the merchant information corresponding to the product package generation request, based on the user information corresponding to the product package generation request and a preset product package combination strategy, through a large model.

[0030] Optionally, displaying at least one product package includes: displaying package information of at least one product package and product information of at least one product in the product package, wherein the package information includes at least one of package label, package prompt, package price and package order control; and the product information includes at least one of product image, product name, product specifications, product price and product editing control.

[0031] Optionally, the method further includes: in response to an editing request for any product in the product package, performing a product editing operation on the product, wherein the product editing operation includes at least one of deletion, replacement, and specification modification operations; and / or, in response to an order request for the product package, displaying an order submission page, and displaying the package information of the product package and the product information of at least one product in the product package on the order submission page.

[0032] Optionally, the method further includes: receiving and displaying at least one historical order record and / or at least one product keyword, wherein the historical order record is generated based on the user information and the merchant information, and the product keyword is generated based on the historical order record through a large model.

[0033] Optionally, displaying at least one historical order record and / or at least one product keyword includes: displaying the historical order record and / or the product keyword in a structured manner; and / or displaying at least one product in the historical order record and the number of times the product was ordered; and / or displaying the product keyword through a keyword control, wherein the keyword control is used to update the display of the product package in response to a keyword selection operation.

[0034] Optionally, updating the product package in response to the keyword selection operation includes: sorting at least one of the product packages based on the selected product keywords to obtain an updated product package; and / or receiving and displaying at least one regenerated product package, wherein the product package is generated based on the user information, the merchant information, and the selected product keywords through a large model.

[0035] Optionally, the method further includes: in response to receiving product demand information input by the user, receiving and displaying an updated product package, wherein the package information is regenerated based on the user information, the merchant information, and the product demand information; and / or, displaying a package generation control at at least one location on the current page, wherein the package generation control consists of at least one element selected from images, icons, and text, and the package generation control is used to send the product package generation request in response to the product package generation request.

[0036] According to another aspect of this application, a method for generating a product package is provided, the method comprising:

[0037] In response to receiving a product package generation request, the system obtains the user information and merchant information corresponding to the product package generation request, and based on the user information and a preset product package combination strategy, selects at least one product from the product list corresponding to the merchant information through a large model, and generates at least one product package based on the selected product.

[0038] The package information of the product package is sent to the client so that the client can receive and display the product package.

[0039] Optionally, the step of selecting at least one product from the product list corresponding to the merchant information based on the user information and a preset product package combination strategy, and generating at least one product package based on the selected product, includes: obtaining current environmental information and generating the user's historical behavior information based on the user information, wherein the historical behavior information includes behavioral habit information and at least one historical order; extracting product combination data matching the behavioral habit information and the environmental information from a knowledge base in a preset domain, and replacing the products in the historical orders based on the product combination data to obtain at least one product package; and / or, selecting at least one product from the product list corresponding to the merchant information based on the historical order and the environmental information to obtain at least one product package; and / or, selecting at least one product from the product list corresponding to the merchant information based on the merchant information and a preset product combination strategy to obtain at least one product package.

[0040] Optionally, the step of extracting product combination data matching the behavioral habit information and the environmental information from a knowledge base in a preset domain, and replacing the products in the historical orders based on the product combination data to obtain at least one product package, includes: extracting product combination data matching the behavioral habit information and the environmental information from a knowledge base in a preset domain, wherein the product combination data includes at least one of product type combination data, product specification combination data, product quantity combination data, and product avoidance data; and replacing at least one product in at least one historical order based on the product combination data to obtain at least one product package.

[0041] Optionally, the historical orders are multi-product orders and / or package orders; then, the step of replacing at least one product in at least one historical order with the product combination data to obtain at least one product package includes: replacing at least one product in the multi-product order and / or the package order with the product combination data to obtain at least one product package, wherein the replaced product is a product with an order rate lower than a preset threshold, and / or, the product specifications of the replaced product are determined according to the product specifications of the products in the historical orders.

[0042] The step of selecting at least one product from the product list corresponding to the merchant information based on the historical orders and the environmental information to obtain at least one product package includes: determining at least one alternative order from the historical orders based on the environmental information, wherein the alternative order is a multi-product order and / or a package order within a preset time period; selecting at least one product based on the products in the multi-product order and the product specifications of the products, and combining the selected products into at least one product package; and / or selecting at least one product based on the products in the package order and the product specifications of the products, and combining the selected products into at least one product package.

[0043] Optionally, the merchant information includes at least one of the following: product discount rules, product production speed, product listing time, and product type. Then, the step of selecting at least one product from the product list corresponding to the merchant information based on the merchant information and a preset product combination strategy to obtain at least one product package includes: selecting at least one product from the product list corresponding to the merchant information based on the product discount rules and the product combination strategy to obtain at least one product package; and / or, selecting at least one product from the product list corresponding to the merchant information based on the product production speed and the product combination strategy to obtain at least one product package; and / or, selecting at least one product from the product list corresponding to the merchant information based on the product listing time and the product combination strategy to obtain at least one product package; and / or, selecting at least one product from the product list corresponding to the merchant information based on the product type and the product combination strategy to obtain at least one product package.

[0044] Optionally, the method further includes: calculating the matching degree between the product package and the user information, and sorting the product packages according to the matching degree to obtain sorted product packages; and / or, setting package tags and / or package prompts for the product packages according to the product package combination strategy corresponding to the product packages, and setting the package tags and / or the package prompts in the package information of the product packages.

[0045] Optionally, the method further includes: determining the package price of the product package based on the product price of the products in the product package and the product discount rules in the merchant information, and setting the package price in the package information of the product package; and / or, determining the package price of the product package based on the product price of the products in the product package and a preset package price calculation strategy, and setting the package price in the package information of the product package after the package price is confirmed by the merchant.

[0046] Optionally, the method further includes: generating first order summary data for the product package and second order summary data for the products in the product package based on the order data of the product package within a preset time period, and sending the first order summary data and the second order summary data to the merchant.

[0047] According to another aspect of this application, a product package generation apparatus is provided, the apparatus comprising:

[0048] The user request response module is used to respond to the product package generation request and send the product package generation request;

[0049] The product package display module is used to receive and display at least one product package, wherein the product package is composed of at least one product from the product list of the merchant information corresponding to the product package generation request, based on the user information corresponding to the product package generation request and a preset product package combination strategy, through a large model.

[0050] According to another aspect of this application, a product package generation apparatus is provided, the apparatus comprising:

[0051] The product package generation module is used to respond to a received product package generation request, obtain the user information and merchant information corresponding to the product package generation request, and select at least one product from the product list corresponding to the merchant information through a large model based on the user information and a preset product package combination strategy, and generate at least one product package based on the selected product.

[0052] The product package sending module is used to send the package information of the product package to the client so that the client can receive and display the product package.

[0053] According to another aspect of this application, a storage medium is provided that stores a computer program thereon, which, when executed by a processor, implements the above-described method for generating commodity packages.

[0054] According to another aspect of this application, a computer device is provided, including a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, wherein the processor executes the program to implement the above-described product package generation method.

[0055] By employing the above technical solutions, the present application provides a product package generation method, apparatus, storage medium, and computer device that, in response to a user-initiated product package generation request, selects at least one product from a merchant's product list based on user information and a preset product package combination strategy, using a large model to combine them into at least one product package. This method can generate customized product packages for users. Compared to merchant-created product packages, customized product packages better meet users' actual needs and preferences, thereby improving the user experience. Furthermore, automatically generating product packages using a large model effectively improves the efficiency of product package generation, making it easier for users to select suitable product packages for ordering, without requiring users to select products one by one on the merchant's page, thus improving ordering efficiency.

[0056] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0057] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0058] Figure 1 A flowchart illustrating a product package generation method provided in an embodiment of this application is shown;

[0059] Figure 2 A flowchart illustrating another method for generating product packages provided in an embodiment of this application is shown;

[0060] Figure 3 The illustration shows a scenario diagram of a product package generation method provided in an embodiment of this application;

[0061] Figure 4 The illustration shows a scenario diagram of a product package generation method provided in an embodiment of this application;

[0062] Figure 5 This paper shows a schematic diagram of the structure of a product package generation device provided in an embodiment of this application;

[0063] Figure 6 A schematic diagram of another product package generation device provided in an embodiment of this application is shown. Detailed Implementation

[0064] The present application will be described in detail below with reference to the accompanying drawings and embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in the embodiments of the present application can be combined with each other.

[0065] In e-commerce, the product packages offered by merchants are often pre-set by the merchants based on their own understanding of the products and users. However, these merchant-defined packages often fail to meet users' personalized needs and may even reduce ordering efficiency. For example, in the food delivery sector, if merchants offer too few product packages, it is usually difficult to cover the needs of most users, who still need to select items themselves before ordering, resulting in low ordering efficiency. On the other hand, if merchants offer too many product packages, it can overwhelm users with choices and prolong the time they spend reading the menu, similarly reducing ordering efficiency.

[0066] To address the issue that merchant-set product packages fail to meet users' personalized needs, existing technologies have proposed two solutions: the first is to generate product package recommendations based on the user's historical order history; the second is to generate product package recommendations based on the order probability of each product in the merchant's list and the matching rate between the products. However, the product packages generated by these methods are usually limited to the user's historical behavior data and lack diverse recommendation strategies, resulting in inflexible product packages.

[0067] To address the aforementioned technical problems, in one embodiment, such as Figure 1 As shown, a method for generating product packages is provided. Taking the application of this method to computer devices such as client, server, and merchant terminals as an example, the method includes the following steps:

[0068] Step 101: The client responds to the product package generation request by sending the product package generation request to the server.

[0069] Specifically, when a user browses products on an e-commerce platform, they can initiate a product package generation request through a page or control displayed on the client. In response to the product package generation request, the client can send the product package generation request to the server. The product package generation request is used to instruct the server to combine the products of the merchant currently being browsed into a product package and display it to the user so that the user can place an order.

[0070] In this embodiment, users can initiate a product package generation request by clicking a control on the page, or the request can be automatically initiated when entering a certain page. The control used to respond to the product package generation request can be displayed in one or more preset locations on various pages, and its display method can be designed according to actual conditions, without specific limitations. It is understood that this embodiment does not specifically limit the method of initiating a product package generation request.

[0071] Step 102: Upon receiving the product package generation request, the server obtains the user information and merchant information corresponding to the product package generation request. Based on the user information and the preset product package combination strategy, the server selects at least one product from the product list corresponding to the merchant information through a large model, and generates at least one product package based on the selected product.

[0072] In this context, "user" refers to the user who initiates the request to generate a product bundle. "User information" refers to various information related to the user who initiated the request, such as user profile information, user historical behavior information, user behavior habit information, and user preference information, all authorized by the user. "Merchant" refers to the merchants displayed on the page where the user initiates the product bundle request. For example, when a user initiates a product bundle request on a merchant's page, the merchant refers to the merchant corresponding to that page; when a user initiates a product bundle request on a merchant list page or a product list page, the merchant refers to at least one merchant displayed on the current page. "Merchant information" refers to various information related to the merchant, such as the merchant's product list information, merchant discount information, product review information, and the merchant's delivery distance from the user. Furthermore, "large model" refers to generative models such as large language models and multimodal models.

[0073] Specifically, after receiving a request to generate a product package, the server can obtain the corresponding user and merchant information. This user and merchant information can be obtained through a query tool called by the large model, or it can be retrieved from the database by the server and then input into the large model. Further, after obtaining the user and merchant information, the large model can select at least one product from the product list corresponding to the merchant information based on the user information and the product package combination strategy recorded in the large model's prompts, and then combine the selected products into at least one product package.

[0074] In this embodiment, the large model used to generate product packages can be a general-domain large model or a large model pre-trained with a knowledge base of a preset domain. When combining product packages, the large model can select and combine products into product packages based on multiple strategies. For example, product package combination strategies may include at least one of the following: extracting product pairing data based on a knowledge base of a preset domain, and selecting products and forming product packages based on the product pairing data; combining products based on the user's historical orders; combining products based on the characteristics of each product in the product list, such as combining new product packages, quick-service packages, special offer packages, weight-loss packages, children's packages, etc. These various product package combination strategies can be executed individually or in combination, and the product package combination strategies can be recorded in the prompts of the large model in the form of processing steps for the large model to execute. It is understood that this embodiment does not specifically limit the specific method by which the large model generates product packages.

[0075] In this embodiment, by leveraging the text understanding and logical processing capabilities of a large-scale model, product package recommendations are generated and presented to users. This approach improves the accuracy of product package recommendations by ensuring a better match between the generated packages and user information. Furthermore, it allows for the generation of different types of product packages by combining various combination strategies, expanding the flexibility of the packages beyond the user's historical behavior and increasing user satisfaction. Traditional product package combination methods require complex algorithms and significant computational resources to evaluate the matching degree between products and set combination rules. In contrast, the large-scale model, based on deep learning and natural language processing technologies, can automatically learn the correlations and combination patterns between products, generating product packages more efficiently and reducing computational overhead. Moreover, traditional methods, limited by preset rules and algorithms, generate relatively simple product packages lacking innovation and diversity; while the large-scale model, based on rich user information, can generate more diverse and personalized product packages to meet the needs of different users.

[0076] Step 103: The server sends the package information of the product to the client.

[0077] Specifically, after generating a product package, the server can send the package information and the product information of each item within the package to the client. The package information may include package tags, package prompts, package prices, and other details. The product information of each item within the package may include product images, product names, product specifications, product prices, and other details. It is understood that this embodiment does not specifically limit the scope of the package information.

[0078] Step 104: The client receives and displays the product package.

[0079] Specifically, after receiving the package information of the product bundles sent by the server, the client can display the received product bundles. In this embodiment, the client can display some or all of the product bundles received from multiple bundles. When displaying each product bundle, the client can show some or all of the products within the bundle. Furthermore, the product bundles can be displayed on a newly opened page or directly on the current page. It is understood that this embodiment does not specifically limit the display method of product bundles or the individual products within them.

[0080] By applying the technical solution of this embodiment, in response to a user-initiated request to generate a product package, based on user information and a preset product package combination strategy, at least one product is selected from the merchant's product list using a large model to form at least one product package. This allows for customized product package generation for users. Compared to product packages created by merchants, customized product packages better meet the actual needs and preferences of users, thereby improving the user experience. Furthermore, automatically generating product packages using a large model effectively improves the efficiency of product package generation, making it easier for users to select suitable product packages and place orders, eliminating the need for users to select products one by one on the merchant's page, thus improving ordering efficiency.

[0081] Furthermore, as a refinement and extension of the specific implementation of the above embodiments, and to fully illustrate the specific implementation process of this embodiment, another method for generating product packages is provided, such as... Figure 2 As shown, the method includes:

[0082] Step 201: The client responds to the product package generation request by sending the product package generation request to the server.

[0083] Specifically, users can initiate a product package generation request through a page or control displayed on the client. In response, the client can send the product package generation request to the server. In this embodiment, users can initiate the request by clicking a control on the page, or the request can be automatically initiated when entering a specific page. It is understood that this embodiment does not specifically limit the method of initiating the product package generation request.

[0084] In an optional implementation, the client may display a package generation control at at least one location on the current page. This package generation control may consist of at least one element selected from images, icons, and text. The control can be used to respond to a package generation request by sending the request to the server. In this embodiment, the current page refers to a page related to functions such as product display and merchant display, such as a merchant page, product list page, merchant list page, product recommendation page, merchant recommendation page, etc. This embodiment does not impose a specific limitation.

[0085] In the above embodiments, refer to Figure 3 As shown by the dashed box in the scene diagram on the left, the client can display a package generation control at a preset location on the merchant's page. This control can be composed of at least one element: text, image, or icon. In this embodiment, the package generation control can be displayed statically at a fixed preset location on the merchant's page, dynamically as other components on the page change, or its display can change according to the dynamic display rules of the components themselves. This method effectively improves the recognizability of the package generation control, thereby increasing user efficiency and engagement with the bundled product package function. Furthermore, the flexible design of the package generation control gives the bundled product package function good scalability and portability, allowing it to be better applied to different products or pages.

[0086] Step 202: Upon receiving the product package generation request, the server obtains the user information and merchant information corresponding to the product package generation request. Based on the user information and the preset product package combination strategy, the server selects at least one product from the product list corresponding to the merchant information through a large model, and generates at least one product package based on the selected product.

[0087] Specifically, after receiving a request to generate a product package, the server can obtain the corresponding user and merchant information. This user and merchant information can be obtained through a query tool called by the large model, or it can be retrieved from the database by the server and then input into the large model. Further, after obtaining the user and merchant information, the large model can select at least one product from the product list corresponding to the merchant information based on the user information and the product package combination strategy recorded in the large model's prompts, and then combine the selected products into at least one product package.

[0088] In this embodiment, the large model used to generate the product package can be a general-domain large model or a large model pre-trained with a knowledge base of a preset domain. When combining product packages, the large model can select and combine products based on multiple strategies. These various product package combination strategies can be executed individually or in combination, and these strategies can be recorded in the large model's prompts in the form of processing steps for easy execution. Specifically, the product package combination strategies can be implemented using the following methods.

[0089] In an optional implementation, step 202 can be achieved by the following method: The server obtains the current environmental information and generates the user's historical behavior information based on the user information. The historical behavior information may include behavioral habit information and at least one historical order. After obtaining the historical behavior information and environmental information, a product package can be generated based on at least one of the following product package combination strategies: Method 1: Extract product combination data that matches the behavioral habit information and environmental information from the knowledge base of the preset domain, and replace the products in the historical order based on the product combination data to obtain at least one product package; Method 2: Select at least one product from the product list corresponding to the merchant information based on the historical order and environmental information to obtain at least one product package; Method 3: Select at least one product from the product list corresponding to the merchant information based on the merchant information and the preset product combination strategy to obtain at least one product package.

[0090] In the above implementation, when generating product packages, the large-scale model can first obtain the user's historical behavior information and environmental information. By obtaining historical behavior information, the large-scale model can fully understand the user's consumption preferences and needs, thereby generating product packages that better meet the user's personalized needs, thus improving the accuracy of product package recommendations and the user experience. Furthermore, by obtaining environmental information, the product packages generated by the large-scale model are no longer limited to the user's personal preferences, but incorporate various external environmental factors, such as weather, season, and geographical location, making the generated product packages more suitable for the user's current scenario. In this implementation, by combining multiple pieces of information to generate product packages, the generated product packages become more accurate and practical.

[0091] Furthermore, after acquiring users' historical behavior and environmental information, the large model can utilize knowledge bases, historical orders, product characteristics, and other information to create various types of product packages to meet users' actual needs. Specifically, firstly, product combination data matching user behavior habits and environmental information is extracted from the knowledge base of a preset domain, and product packages are generated based on this data. This considers not only the complementarity and coordination between products but also the user's context, thus improving the practicality of the product packages. Secondly, by directly selecting products from the merchant's product list using historical orders and environmental information, the generated product packages can better align with users' consumption habits and product preferences, thereby enhancing the user experience. Finally, by combining product feature information to generate product packages, the flexibility of product combinations can be improved, providing users with a wider range of choices. By applying the technical solution provided in this implementation method, users can be provided with more accurate, practical, and personalized product packages. This not only saves users time and effort but also improves their ordering efficiency and overall experience.

[0092] For example, in a food delivery scenario, the prompts set for large models can include the following:

[0093] 1. First determine whether the user has historically purchased more set meals (A) or more individual dishes (B).

[0094] 1-A

[0095] 1. If a user purchases multiple meal packages, do they frequently modify or replace the meal items within the package?

[0096] 2. Extract nutritional data from the knowledge base that matches the user's dietary habits and current environment to help the user automatically replace frequently changed options in the meal plan, including but not limited to food type, food size, preferences (no cilantro, less chili, etc.), and removing allergenic items, etc.

[0097] 3. Extract dishes based on users' daily meal preferences and combine them into set meals to display to users;

[0098] 1-B

[0099] 1. If a user buys a single item or multiple items, does the user frequently buy certain items, and do certain items have a high replacement rate?

[0100] 2. Extract nutritional data from the knowledge base that matches the user's dietary habits and current environment; retain the items that the user frequently purchases; and try to replace some of the dishes that the user frequently substitutes with nutritionally balanced options; retain the options that the user frequently selects.

[0101] 3. Extract dishes based on users' daily meal preferences and combine them into set meals to display to users;

[0102] As can be seen from the above examples, by setting prompts in the large model according to the data processing logic provided in this implementation method, the large model can generate product packages that are more in line with user habits and actual application environments. Specifically, in the above examples, for users who habitually purchase packages, the large model can replace frequently changed items in the package based on product combination data provided by the knowledge base (such as beverage type, food and beverage specifications, remarks preferences, removal of allergenic foods, etc.), thereby achieving the goal of nutritional balance and also meeting the user's personalized needs (such as removing allergenic foods, etc.). For users who prefer to purchase individual items, the large model can replace products based on the user's purchasing habits and the replacement rate of individual items, thereby ensuring that the product packages retain the individual items that the user frequently purchases. At the same time, by using the large model to obtain nutritional data from the knowledge base that matches the user's dietary habits and current environment, it is also possible to replace some frequently changed dishes in a more nutritious and balanced way, thus ensuring both the user's taste preferences and providing a healthier and more reasonable dietary combination. Based on the above examples, the server can intelligently extract dishes and combine them into packages to display to the user according to the user's daily meal selection preferences. This dynamic, user-behavior-based approach to package deals not only improves the accuracy of product recommendations but also increases the diversity of product packages.

[0103] In an optional implementation, user information and environmental information can be obtained in the following ways: The server can call an environmental information query tool through the large model to obtain the current environmental information, which may include at least one of time information, location information, and season information; At the same time, the server can also call a user information query tool through the large model to obtain the user's historical behavior information, which may include behavioral habit information (including the user's purchasing behavior habits, as well as the user's preferences for merchants, products, etc.) and historical orders within a preset time period.

[0104] In the above implementation, by using tools to query information through the large model, the large model can obtain current environmental information and users' historical behavior information in real time and accurately. By combining environmental information and users' historical behavior information, the large model can make more accurate decisions that meet users' personalized needs. At the same time, using tools to obtain information can improve the real-time performance and accuracy of information acquisition, avoiding illusions or biases caused by inaccurate information in the large model, thereby improving the accuracy of product recommendations.

[0105] Taking food delivery as an example again, the prompts in the large model can also include the following:

[0106] Target:

[0107] You are the store's meal selection assistant, mainly helping customers choose set meals;

[0108] Your analysis consists of a plugin comprised of data provided by "tools" and a nutritional knowledge system provided by "knowledge base";

[0109] Your analysis should include (but is not limited to) the following:

[0110] The data provided by "tools" can be analyzed to understand users' eating habits, preferences, consumption habits, and spatiotemporal environment.

[0111] If a user performs certain actions and makes choices after using the automatic menu creation function, you need to remember their preferences and continue to consider them in subsequent solution suggestions.

[0112] For any questions, please refer to the knowledge base first.

[0113] tools:

[0114] The user's purchasing habits, preferences for products, brands, etc., can be retrieved using the `get_data_form_name_data` function.

[0115] The system retrieves user time, location, and other relevant spatiotemporal environment data using the get_data_form_name_report method.

[0116] Retrieve a user's dietary records for a specific period of time using the get_data_form_name_record method;

[0117] As the examples above demonstrate, by setting preset tools and a preset domain knowledge base in the prompts of the large model, the large model can quickly and accurately obtain relevant user and environmental information, thereby generating more accurate product packages that meet user requirements. Furthermore, by limiting the scope of data acquisition by the large model to the preset tool and knowledge base, it is possible to prevent the generated product packages from deviating from the settings or exhibiting illusions, thus ensuring the stability of the product package combinations.

[0118] In one optional implementation, the product package combination strategy is as follows: extract product combination data that matches behavioral habit information and environmental information from a knowledge base in a preset domain. The product combination data may include at least one of the following: product type combination data, product specification combination data, product quantity combination data, and product avoidance data. Then, based on the product combination data, replace at least one product in at least one historical order to obtain at least one product package.

[0119] In the above implementation, the knowledge base can be set up according to the product's domain. For example, in the catering industry, a knowledge base for nutrition can be set up; in the clothing industry, a knowledge base for clothing matching can be set up, and so on. Furthermore, product pairing data can be flexibly combined based on various data extracted from the knowledge base. For example, in the catering industry, product pairing data can include the type of beverage in the set meal, the type and specifications of the food and beverages, the user's noted product preferences (such as extra spice), and related pairing data such as excluding food items that the user is allergic to. By extracting relevant product pairing data to replace products in historical orders, it is possible to avoid selecting products that the user does not like and to make the selected products more in line with relevant nutritional requirements, thereby improving the practicality of the product set meal and its matching degree with the user.

[0120] This implementation method establishes a knowledge base for a pre-defined domain within a large model, and then extracts matching product combination data based on user behavior and environmental information. This provides a more scientific and reasonable basis for generating product packages, ensuring more reasonable combinations and avoiding unreasonable product pairings, thus improving the practicality and accuracy of the product packages. Furthermore, this implementation method replaces products in historical orders with product combination data to obtain new product packages, fully utilizing product information from historical orders, thereby reducing computational overhead, improving the efficiency of product package generation, and enhancing the matching degree between product packages and users.

[0121] In one optional implementation, the product package combination strategy is as follows: based on product combination data extracted from a knowledge base in a preset domain, at least one product in a multi-product order and / or package order is replaced to obtain at least one product package, wherein the replaced product is a product with an order rate lower than a preset threshold, and / or the product specifications of the replaced product are determined according to the product specifications of products in historical orders.

[0122] In the above embodiments, a multi-product order refers to an order containing multiple products, and a package order refers to an order containing a package. These two types of orders can also be cross-combined. Furthermore, the product order rate can include the order rate of the requesting user and / or the order rate of other users. A product order rate below a preset threshold refers to various situations, such as the requesting user's order rate or number of orders for that product being lower than the set threshold, or the requesting user's order rate or number of orders for that product ranking low, or other users' order rate or number of orders for that product being lower than the set threshold, or other users' order rate or number of orders for that product ranking low, etc., which will not be listed here.

[0123] This implementation method avoids selecting unwanted items for product packages by replacing items below a preset threshold in multi-item orders and / or bundled orders, thereby improving the accuracy of package combinations. Furthermore, by setting the product specifications in bundled orders based on historical order specifications, it avoids the tedious process of users modifying product specifications, improving ordering efficiency and user experience.

[0124] In one optional implementation, the product package combination strategy is as follows: Based on environmental information, at least one alternative order is determined from historical orders, wherein the alternative order is a multi-product order and / or a package order within a preset time period. Then, based on the products and product specifications in the multi-product order, at least one product is selected, and the selected product is combined into at least one product package; and / or, based on the products and product specifications in the package order, at least one product is selected, and the selected product is combined into at least one product package.

[0125] In the above implementation, by determining alternative orders from historical orders based on environmental information, orders that are relevant to external environmental factors such as the current time, location, and season can be selected, thereby improving the accuracy of product package generation and recommendation. Furthermore, by determining product packages based on the individual products and specifications within multi-product orders and / or package orders, the generated product packages can better meet the user's personalized needs, thereby enhancing the user experience.

[0126] For example, suppose that based on the current environment information, two historical orders from the user at the current merchant are obtained: one order containing three items, and the other a package order where three items are selected from eight items. Based on this scenario, when generating a product package, one package can be generated based on the three items from the multi-item order and the user's selected item specifications. Then, another package can be generated based on the three items selected by the user in the package order and their corresponding item specifications. Finally, both packages are pushed to the user for preview and selection. The product combination strategy described above is relatively simple and direct. Furthermore, the generated product packages have a higher matching degree with the user, and users are generally more efficient at placing orders when they see the same historical orders.

[0127] In one optional implementation, the product package combination strategy is as follows: based on product discount rules and product combination strategy, at least one product is selected from the product list corresponding to the merchant information to obtain at least one product package; and / or, the server selects at least one product from the product list corresponding to the merchant information based on product production speed and product combination strategy to obtain at least one product package; and / or, the server selects at least one product from the product list corresponding to the merchant information based on product listing time and product combination strategy to obtain at least one product package; and / or, the server selects at least one product from the product list corresponding to the merchant information based on product type and product combination strategy to obtain at least one product package.

[0128] In the above embodiments, when generating product packages, in addition to combining user information and current environmental information, product packages can also be generated by combining merchant information and information on the various products sold by the merchant. This provides users with more choices and increases the diversity and richness of product packages. Specifically, by combining product packages using product discount rules, special offer packages can be generated; by combining product packages using product preparation speed, quick-service packages can be generated; by combining product packages using product listing time, new product packages can be generated; and by combining product packages using product type, weight-loss packages or children's packages, etc., can be generated for specific groups. This embodiment, by acquiring various product characteristic information such as product discount information, preparation speed information, listing time information, and product type, and combining them with product combination strategies, can create various types of product packages, thereby meeting users' diversified needs and long-tail needs, and providing more possibilities for product packages.

[0129] In this embodiment, the various product package combination strategies described above can be combined in combination with each other, or they can be used individually. Furthermore, after generating multiple product packages, all types of product packages can be pushed to the user, or the product packages can be sorted according to their relevance to the user, and then the top-ranked product packages can be selected and pushed to the user. It is understood that this embodiment does not impose specific limitations on the combination methods of the product package combination strategies or the selection methods of the product packages.

[0130] Step 203: The server determines the package price of the product package based on the product prices of the products in the product package and the preset package price calculation strategy, and sends the package price to the merchant.

[0131] Specifically, after the product package is generated, the price of each product in the package can be determined based on the prices of the individual items and the merchant's set product discount rules or package price calculation strategy. The calculated package price is then set in the product package information. In this embodiment, the package price can be calculated based on a preset algorithm or rule, or it can be calculated using a large model calling tool. Furthermore, the package price can be calculated based on the merchant's existing product discount rules or a pre-set package price calculation strategy. The calculated package price can be directly set in the product package information, or it can be set after confirmation or adjustment by the merchant. It is understood that this embodiment does not specifically limit the calculation method, calculation rules, or setting method of the product package price.

[0132] In an optional implementation, the server can determine the package price of a product package based on the individual product prices and the discount rules set in the merchant's information, and then set the package price in the package information. For example, assuming a product package contains three products priced at 16 yuan, 5 yuan, and 8 yuan respectively, and the merchant sets a discount rule of 3 yuan off for purchases over 20 yuan, the calculated package price is 26 yuan. Since the discount rules are pre-set by the merchant and the calculation method is the same for each order, the package price determined according to the discount rules does not need to be reconfirmed by the merchant and can be directly set in the package information. This implementation improves the efficiency of package price calculation by using discount rules to calculate the package price. Furthermore, in the prior art, users need to submit multiple selected products to the order submission page to see the discounted price, while this implementation improves the efficiency of discounted price display by moving the discount calculation step forward.

[0133] In another optional implementation, the server can determine the package price based on the prices of the items in the package and a preset package price calculation strategy. After the package price is confirmed by the merchant, it is set in the package information. For example, suppose the package contains three items priced at 16 yuan, 5 yuan, and 8 yuan respectively. The preset package price calculation strategy is to offer a discount of 4-6 yuan when the total package price reaches 25 yuan or more. After calculation using this strategy, the discount is determined to be 5 yuan, and the package price is 24 yuan. Since the package price calculation strategy has a certain degree of fluctuation and change, the package price determined according to the strategy can be sent to the merchant for confirmation first. After confirmation by the merchant, the calculated package price is then set in the package information. In this implementation, the package price calculation strategy can be uniformly set by the operations personnel for multiple merchants, or it can be set by the merchants themselves. If the strategy is set by the merchants themselves, the confirmation step by the merchants can be omitted.

[0134] In the above embodiments, confirmation of the package price from the merchant can mean that the merchant assumes the package price calculated according to the package price calculation strategy meets the merchant's requirements. Therefore, the calculated package price can be directly set in the package information of the product package without merchant-side interaction. Alternatively, it can mean that the calculated package price is sent to the merchant, who then initiates a confirmation command based on the package price. After receiving the confirmation command from the merchant, the server sets the package price in the package information of the product package. Another possibility is that the calculated package price is sent to the merchant, who forwards it to the server. The server verifies the price's reasonableness using a large model. If the price is deemed reasonable according to the set logic, the server sends a price confirmation command to the merchant, who then forwards it to the server that calculates the package price. After receiving the confirmation command from the merchant, the server sets the package price in the package information of the product package. It is understood that this embodiment does not impose specific restrictions on the method and path of merchant-side confirmation of package prices.

[0135] The above implementation method calculates the package price of a product package through a package price calculation strategy. This not only improves the efficiency of package price calculation and display, but also allows for more flexible price ranges for product packages, thereby stimulating users' interest in using the package deal function and improving the user experience.

[0136] Step 204: Upon receiving the package price, the merchant adjusts and / or confirms the package price, and sends the adjusted and / or confirmed package price to the server.

[0137] Specifically, if the package price calculated by the server requires confirmation from the merchant before being set in the product package information, an additional step is needed: sending the information of each product in the package, along with the calculated package price, to the merchant for confirmation. Once the merchant receives this information, they can determine if the server-calculated package price meets their expectations. If the merchant believes the package price meets their expectations, they can send a confirmation instruction to the server, allowing the server to set the calculated package price in the product package information. If the merchant believes the package price does not meet their expectations, they can adjust the package price and send the adjusted package price to the server, allowing the server to set the adjusted package price in the product package information.

[0138] In this embodiment, the client can also use a merchant intelligent assistant to handle the confirmation and adjustment of package prices, thereby improving the response speed on the merchant's side. The front-end interface of the merchant intelligent assistant can be set on the merchant's side, while the back-end can be set on a server. The back-end intelligent assistant can be implemented through various methods such as rule matching, machine learning models, and large-scale models. In this embodiment, the strategy executed by the merchant intelligent assistant is similar to that executed by the merchant; both make reasonable judgments and adjustments to the package prices based on the merchant's actual situation to achieve the final setting of the package prices. This embodiment, by setting up a merchant intelligent assistant on the merchant's side to help the merchant confirm or adjust the package prices of goods, can effectively improve the efficiency of pushing package prices to the client for display and reduce the workload of the merchant.

[0139] In one optional implementation, step 204 can be implemented in at least one of the following ways: Method 1: The merchant receives the product package and its price from the server. In response to the confirmation operation of the package price, the merchant sends a confirmation instruction to the server, so that the server sets the package price in the product package information after receiving the confirmation instruction. Method 2: In response to the modification operation of the package price, the merchant sends the modified package price to the server, so that the server sets the modified package price in the product package information after receiving the modified package price. Method 3: The merchant sends the product package and its price to the server, so that the server confirms the package price using a large model and sets the package price in the product package information after confirmation. Method 4: The merchant sends the product package and its price to the server, so that the server adjusts the package price using a large model and sets the adjusted package price in the product package information.

[0140] In the above embodiments, the four methods can be used interchangeably or independently. This embodiment uses multiple methods to confirm or adjust the package price calculated by the server, which can improve the accuracy and rationality of package price setting, and balance the needs of both users and merchants.

[0141] Step 205: The server determines the package information of the product package based on the product information and package price of the products in the product package.

[0142] Specifically, after the package prices for each product bundle are determined, the server can set the package price for each bundle in the corresponding bundle information. In addition, the bundle information can also include bundle tags, bundle prompts, bundle order controls, and product information for each item included in the bundle. Furthermore, after the bundle information is set up, the server can send the bundle information to the client for display.

[0143] In one optional implementation, the server can set corresponding package tags and / or package prompts for product packages according to the product package combination strategy, and set the determined package tags and / or package prompts in the package information of the corresponding product package. In this implementation, the server can automatically match package tags and package prompts for product packages according to the product package combination strategy. This matching process can be implemented through various methods such as rule algorithms, machine learning models, and large models.

[0144] For example, when the product bundle strategy is "set product bundles based on items in historical orders," product bundles can be tagged with labels such as "You've bought this before," and prompts such as "Helper helps you create your favorite dish combination" can be added. This reminds users that the product bundle contains items they have previously purchased, thereby improving user experience and order efficiency. When the product bundle strategy is "set product bundles based on product listing time," product bundles can be tagged with labels such as "Try New Arrivals," and prompts such as "Helper helps you create the latest dish combination" can be added. This reminds users that the product bundle contains the latest listed items, thereby improving user experience and order efficiency.

[0145] The above-described implementation, by setting package labels and / or package prompts for product packages, enables users to intuitively understand the characteristics of each product package, thereby improving the efficiency of users identifying the features of each product package and thus enhancing the user experience. Furthermore, automatically setting package labels and prompts for product packages using a large model can reduce the manual labeling operation, thereby lowering operating costs.

[0146] Step 206: The server calculates the matching degree between the product packages and the user information, and sorts the product packages according to the matching degree.

[0147] Step 207: The server sends the package information of the sorted product packages to the client.

[0148] Specifically, the server can sort the various product packages generated by the large model based on the matching degree between the product packages and user information, and then send the sorted product package information to the client. In this embodiment, the matching degree between the product packages and user information can be calculated using traditional machine learning models, or it can be calculated using matching strategies recorded in the prompts of the large model. This embodiment sorts product packages by matching degree between product packages and user information, which can improve the relevance between product packages and users, thereby increasing user favorability and attention. For example, product packages generated by the strategy "set product packages based on products in historical orders" have a higher matching degree than product packages generated by the strategy "set product packages based on product listing time". Therefore, product packages generated by the former strategy will be ranked higher than product packages generated by the latter strategy, thereby improving user experience, meeting users' personalized needs, and improving users' ordering efficiency.

[0149] In an optional implementation, the server may also skip step 206 and directly push the package information of each generated product package to the client, thereby improving the efficiency of information push.

[0150] Step 208: The client receives and displays the product package.

[0151] Specifically, after receiving the package information for each product package from the server, the client can display this information. In this embodiment, the client can display some or all of the received product packages. When displaying each product package, the client can show some or all of the products within the package. Furthermore, the product packages can be displayed on a newly opened page or directly on the current page. It is understood that this embodiment does not specifically limit the display method of product packages or the individual products within them.

[0152] In one optional implementation, the client can display package information for at least one product package and product information for at least one product within the product package. The package information may include at least one of the following: package label, package prompt, package price, and package order control. The product information may include at least one of the following: product image, product name, product specifications, product price, and product editing control.

[0153] In the above embodiments, refer to Figure 3 As shown in the diagram on the right, the client can display package information for at least one product package. For example, the client can display package tags, package prompts, package prices, package order controls, product images, names, specifications, prices, and editing controls for each product included in the package. In this embodiment, some package information or product information for some products within a package may be hidden on the page. Users can view the hidden package or product information by swiping up, down, left, or right. This embodiment, by displaying comprehensive package information, allows users to learn more about package options, thereby improving the efficiency of reading package information and enhancing the user experience.

[0154] In one optional implementation, the client can display at least one historical order record and / or at least one product keyword while showing the product package. The historical order record can be generated based on user information and merchant information through a large model, and the product keyword can be generated based on the historical order record.

[0155] In the above embodiments, refer to Figure 3 and Figure 4As shown, in addition to displaying product packages, the client can also display historical order records of users such as "3 times of Taiwanese Braised Pork with Rice and 2 times of Fish and Pork Meatballs", as well as product keywords such as "meat dishes" and "single-person meals" used to reveal users' ordering characteristics. By displaying historical order records and / or product keywords, it is convenient for users to quickly understand their own dietary preferences, thereby improving the interpretability and趣味性 of product package combinations, and improving users' ordering efficiency and experience.

[0156] In an optional implementation, the client can display historical order records and / or product keywords in a structured manner. Optionally, the client can also display the products in the historical order records and the number of times the products are ordered. Further optionally, the client can also display product keywords through a keyword control, where the keyword control can be used to update the display of product packages in response to a keyword selection operation.

[0157] In the above implementation, the client can display historical order records and / or product keywords in a structured manner such as by serial numbers, segmentation, and equidistant intervals, thereby improving the neatness of historical order records and / or product keywords and enhancing the user experience. In addition, the client can display more detailed historical order records, such as the names of ordered products and the number of times ordered, etc., to facilitate users to quickly understand and recall their own product preferences and enhance the readability and趣味性 of information. In addition, the client can also display product keywords through a keyword control to make the product keywords in an interactive state. Users can select product keywords through the keyword control and update the display result of the product package, improving the accuracy of product package recommendations.

[0158] In an optional implementation, the client can sort at least one product package based on the selected product keywords to obtain an updated display of the product package, and / or receive and display at least one regenerated product package, where the product package can be generated by a large model based on user information, merchant information, and the selected product keywords.

[0159] In the above implementation, when the user selects a product keyword through the keyword control, the client can update the display result of the product package. Among them, updating the display of the product package can be achieved by sorting the product package, or by regenerating the product package, or by a combination of the two methods. For example, the client can send the product keywords selected by the user to the server so that the server generates some new product packages and sends them to the client. The client re-sorts the product packages by the product keywords and displays the sorted product packages to the user. Through the above method, dynamic adjustment of the product package can be achieved, thereby meeting more personalized needs of users and enhancing the user experience.

[0160] In one optional implementation, the client may send the product demand information to the server in response to receiving the product demand information input by the user. In response to receiving the product demand information, the server may regenerate at least one product package based on the user information, merchant information, and product demand information, and send the package information of the regenerated product package to the client. The client may receive and display the regenerated product package.

[0161] In the above implementation, the client can receive the user's product demand information through the information input box displayed on the client, and send the product demand information to the server. This allows the service to regenerate a batch of product packages based on the product demand information and send them to the client. This method further enhances the adjustability of product packages, enabling the generated packages to meet diverse personalized needs of users. Furthermore, the above interaction method greatly improves the user experience.

[0162] Step 209: The client responds to the edit request for any product in the product package and performs product editing operations on the product.

[0163] Specifically, the client can respond to an edit request for any item in the product package and perform product editing operations on the requesting item. In this embodiment, each item in the product package supports editing, and the editing methods can include at least one of the following: deletion, replacement, modification of specifications, etc. (Refer to...) Figure 4 As shown in the diagram, users can initiate an editing request for any product by clicking the product editing control. The client responds to the editing request by displaying the product editing interface, allowing users to select the appropriate editing method to perform the product editing operation. This embodiment, by supporting users to edit any product within a product package, enhances the flexibility of product package settings and the efficiency of personalized configuration, thereby increasing the probability of ordering product packages and improving the user experience.

[0164] Step 210: The client responds to the order request for the product package by displaying the order submission page, which shows the package information of the product package and the product information of at least one item in the product package.

[0165] Specifically, in response to a user's order request for a product package, the client can redirect to an order submission page. This page displays the package information and the details of at least one item within the package, allowing the user to confirm the information of each item and place the order. In this embodiment, each product package supports one-click ordering. (Refer to...) Figure 4As shown in the diagram, users can initiate an order request for a product package by clicking the "One-Click Purchase" control. In response, the client will redirect to the order submission page, which displays the package information and the individual product information within the package, facilitating the user's order placement. This embodiment effectively improves the efficiency of product package ordering by supporting one-click ordering.

[0166] In an optional implementation, the client can display order remarks in the remarks input box on the order submission page. These remarks can be generated based on order remarks from the user's historical orders. In this implementation, when a user initiates a one-click order, previously entered order remarks from the user's historical orders, such as "no spice," "place a set of tableware," or "place on the table near the entrance," can be automatically filled into the remarks input box on the order submission page. This automatic filling of order remarks further improves the user's ordering efficiency and experience.

[0167] In one optional implementation, the client can prompt the user via a pop-up window or similar means before automatically filling in the order remarks information. If the user selects "yes," the information is automatically filled in; if the user selects "no," the information is not automatically filled in. And / or, the client can also prompt the user that the order remarks information has been filled in after it has been automatically filled in, asking the user to check if the information is correct. This implementation, by soliciting the user's opinion before and / or after filling in the order remarks information, can avoid the risk of incorrect remarks, thereby improving the accuracy of order placement.

[0168] Step 211: The server summarizes the order data for the product packages and sends the summarized order data to the merchant.

[0169] Step 212: The merchant displays the order summary data for the product packages.

[0170] Specifically, the server can aggregate order data for various product packages according to preset cycles, such as daily, weekly, or monthly, and send the aggregated order data to the merchant for display. Compared to existing technologies that only provide merchants with order data for packages and individual items, this embodiment provides merchants with more accurate data support by aggregating order data for various product packages. This helps merchants better understand user needs and product popularity, thereby helping them adjust their product packages and optimize and manage their inventory.

[0171] In one optional implementation, the server can generate first order summary data for the product packages and second order summary data for the individual products within the product packages based on order data for the product packages within a preset time period, and then send the first and second order summary data to the merchant. Upon receiving the first and second order summary data, the merchant can display the first order summary data for the product packages and the second order summary data for the individual products within the product packages.

[0172] In the above implementation, by aggregating order data based on a preset time period, the accuracy and real-time nature of the data can be ensured, enabling merchants to monitor product sales in real time and avoid situations such as inventory backlog or stockouts. Furthermore, through the first set of order summary data, merchants can clearly understand the overall situation of the product package, while through the second set of order summary data, merchants can understand the individual details of each product within the product package. Therefore, by displaying the first set of order summary data for the product package and the second set of order summary data for each product within the package on the merchant's end, merchants can fully understand user needs and product popularity, thereby enabling them to adjust product inventory and procurement plans in advance and reduce operating costs.

[0173] By applying the technical solution of this embodiment, various types of product packages can be generated by combining a large model with multiple product package combination strategies. These product packages can be displayed and operated in various ways, which can effectively improve the matching degree between product packages and users. At the same time, it can also enhance the diversity and richness of product packages, thereby meeting users' personalized needs and improving users' ordering efficiency and experience.

[0174] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the labels corresponding to each step in the above embodiments are only for identification purposes and are not intended to limit the order of execution of the steps. The order of execution of the steps in each embodiment can be set according to the actual situation.

[0175] Furthermore, as Figure 1 To specifically implement the method, this application provides a product package generation device, such as... Figure 5 As shown, the device includes:

[0176] User request response module 51 can be used to respond to product package generation request and send the product package generation request;

[0177] The product package display module 52 can be used to receive and display at least one product package, wherein the product package is composed of at least one product from the product list of the merchant information corresponding to the product package generation request, based on the user information corresponding to the product package generation request and a preset product package combination strategy, through a large model.

[0178] It should be noted that other corresponding descriptions of the functional units involved in the product package generation device provided in this application embodiment can be found by referring to... Figures 1 to 4 The corresponding descriptions in the method will not be repeated here.

[0179] Furthermore, as Figures 1 to 4 To specifically implement the method, this application provides a product package generation device, such as... Figure 6 As shown, the device includes:

[0180] The product package generation module 61 is used to respond to receiving a product package generation request, obtain the user information and merchant information corresponding to the product package generation request, and select at least one product from the product list corresponding to the merchant information through a large model based on the user information and a preset product package combination strategy, and generate at least one product package based on the selected product.

[0181] The product package sending module 62 is used to send the package information of the product package to the client so that the client can receive and display the product package.

[0182] It should be noted that other corresponding descriptions of the functional units involved in the product package generation device provided in this application embodiment can be found by referring to... Figures 1 to 4 The corresponding descriptions in the method will not be repeated here.

[0183] This application also provides a computer device, specifically a personal computer, server, network device, etc. The computer device includes a bus, processor, memory, and communication interface, and may also include input / output interfaces and a display device. The processor of the computer device provides computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database of the computer device stores location information. The network interface of the computer device is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements the steps in the various method embodiments.

[0184] Those skilled in the art will understand that the structure of the computer device described above is only a partial structure related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. A specific computer device may include more or fewer components, or combine certain components, or have different component arrangements.

[0185] In one embodiment, a computer-readable storage medium is provided, which may be non-volatile or volatile, having stored thereon a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0186] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0187] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, graphics processors, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0188] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0189] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for generating a product package, characterized in that, The method includes: The client responds to the product package generation request by sending the product package generation request to the server; In response to receiving the product package generation request, the server obtains the user information and merchant information corresponding to the product package generation request, and based on the user information and a preset product package combination strategy, selects at least one product from the product list corresponding to the merchant information through a large model, and generates at least one product package based on the selected product. The server sends the package information of the product package to the client; The client receives and displays the product package.

2. The method according to claim 1, characterized in that, The client displays the product package, including: The client displays package information for at least one of the product packages and product information for at least one product within the product package. The package information includes at least one of the following: package label, package prompt, package price, and package order control. The product information includes at least one of the following: product image, product name, product specifications, product price, and product editing control.

3. The method according to claim 1 or 2, characterized in that, The method further includes: The client responds to an edit request for any product within the product package by performing a product editing operation on that product, wherein the product editing operation includes at least one of deletion, replacement, and specification modification operations; and / or, In response to the order request for the product package, the client displays an order submission page, which shows the package information of the product package and the product information of at least one item in the product package.

4. The method according to claim 3, characterized in that, The method further includes: The client displays order remarks in the remarks input box on the order submission page, wherein the order remarks are generated based on the order remarks in the user's historical orders.

5. A method for generating a product package, characterized in that, The method includes: In response to the request to generate a product package, the request to generate the product package is sent; Receive and display at least one product package, wherein the product package is composed of at least one product from the product list of the merchant information corresponding to the product package generation request, based on the user information corresponding to the product package generation request and a preset product package combination strategy, through a large model.

6. A method for generating a product package, characterized in that, The method includes: In response to receiving a product package generation request, the system obtains the user information and merchant information corresponding to the product package generation request, and based on the user information and a preset product package combination strategy, selects at least one product from the product list corresponding to the merchant information through a large model, and generates at least one product package based on the selected product. The package information of the product package is sent to the client so that the client can receive and display the product package.

7. A product package generation device, characterized in that, The device includes: The user request response module is used to respond to the product package generation request and send the product package generation request; The product package display module is used to receive and display at least one product package, wherein the product package is composed of at least one product from the product list of the merchant information corresponding to the product package generation request, based on the user information corresponding to the product package generation request and a preset product package combination strategy, through a large model.

8. A product package generation device, characterized in that, The device includes: The product package generation module is used to respond to a received product package generation request, obtain the user information and merchant information corresponding to the product package generation request, and select at least one product from the product list corresponding to the merchant information through a large model based on the user information and a preset product package combination strategy, and generate at least one product package based on the selected product. The product package sending module is used to send the package information of the product package to the client so that the client can receive and display the product package.

9. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 6.

10. A computer device, comprising a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method of any one of claims 1 to 6.

Images