Commodity recommendation method and device, computer equipment, readable storage medium and program product

Abstract

The invention relates to a commodity recommendation method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: in response to a transaction recommendation request triggered in a chat interface, displaying a first reply message in the chat interface; inputting a transaction feature based on the first reply message; in response to completion of input of the transaction characteristics, displaying a second reply message in the chat interface, the second reply message comprising a target commodity list; the target commodity list is determined based on the transaction characteristics; and carrying out combined transaction on the commodities in the target commodity list based on a triggering operation on the second reply message. By adopting the method, the matching degree between the target commodity list and the user demand can be improved, and the commodity recommendation accuracy and the commodity recommendation efficiency are improved.

Description

Technical Field

[0001] The present application relates to the field of Internet technology, and in particular to a commodity recommendation method, apparatus, computer equipment, computer-readable storage medium, and computer program product. Background Art

[0002] The product information service system (also commonly known as the e-commerce platform) serves as a centralized traffic scenario and provides shopping guide services to users.

[0003] In the traditional method, users need to have clear purchasing category requirements and budgets, and then manually integrate information such as product usage scenarios, product requirements, brand preferences, and budget ranges, and then search and query the massive amount of product information in the product information service system to manually configure a product recommendation list.

[0004] However, traditional methods require users to manually configure and search for multi-dimensional information, which makes interactive operations complex and the convenience of product recommendations poor. Summary of the invention

[0005] Based on this, it is necessary to provide a product recommendation method, device, computer equipment, computer-readable storage medium and computer program product to address the above technical problems.

[0006] In a first aspect, the present application provides a product recommendation method, comprising:

[0007] In response to a transaction recommendation request triggered in the chat interface, displaying a first reply message in the chat interface;

[0008] inputting transaction characteristics based on the first reply message;

[0009] In response to completion of input of the transaction feature, displaying a second reply message in the chat interface, the second reply message including a target commodity list; the target commodity list is determined based on the transaction feature;

[0010] Based on the triggering operation on the second reply message, a combined transaction is performed on the commodities in the target commodity list.

[0011] In one embodiment, in response to a transaction recommendation request triggered in a chat interface, before displaying a first reply message in the chat interface, the method further comprises:

[0012] In response to a triggering operation on a first target control in a shopping page, displaying a chat interface; or,

[0013] In response to a triggering operation on a recommendation entry in a content details page of published content, displaying the chat interface; or,

[0014] In response to a triggering operation on a second target control in the video display page, the chat interface is displayed.

[0015] In one embodiment, the first reply message includes a guide recommendation option and a transaction parameter control, and in response to the transaction recommendation request triggered in the chat interface, displaying the first reply message in the chat interface includes:

[0016] In response to a transaction recommendation request triggered in the chat interface, displaying a shopping demand card in the chat interface; the shopping demand card includes a guide recommendation option, and the guide recommendation option is used to guide the user to input the transaction demand; and / or,

[0017] In response to a transaction recommendation request triggered in the chat interface, the transaction parameter control is displayed, and the transaction parameter control is used to instruct the user to enter a transaction amount parameter.

[0018] In one embodiment, inputting transaction characteristics based on the first reply message includes:

[0019] In response to a triggering operation on a first guidance recommendation option in the shopping demand card, a first transaction demand is input; the first transaction demand is used to reflect a commodity category; and / or,

[0020] In response to a triggering operation on a second guidance recommendation option in the shopping requirement card, a second transaction requirement is input, where the second transaction requirement is used to reflect a product brand; and / or,

[0021] In response to the triggering operation on the transaction parameter control, a transaction amount parameter is input.

[0022] In one embodiment, in response to the triggering operation on the transaction parameter control, inputting the transaction amount parameter includes:

[0023] In response to a trigger operation on a transaction input box, input a transaction amount parameter; or,

[0024] In response to a trigger operation on a target transaction value option in a transaction parameter value option, input a transaction amount parameter; or,

[0025] In response to a triggering operation on a target transaction amount interval in the candidate transaction amount interval, a transaction amount parameter is input.

[0026] In one embodiment, in response to the completion of the input of the transaction feature, after displaying the second reply message in the chat interface, the method further includes:

[0027] Display the target product list page;

[0028] In response to a replacement operation of a target product in the target product list page, a product selection floating layer is displayed; the product selection floating layer includes one or more of a shopping page entrance, a transaction list page entrance, a chat interface entrance, and other target product list page entrances;

[0029] In response to a triggering operation of selecting any one of the entrances in the floating layer for the commodity, a display interface corresponding to the entrance is displayed, and a replacement commodity is determined, wherein the replacement commodity is used to replace the target commodity.

[0030] In one embodiment, after displaying the target product list page, the method further includes:

[0031] In response to a sliding operation on the target product list page, a next target product list of a different dimension from the current target product list is displayed on the target product list page.

[0032] In one embodiment, the performing of a combined transaction on the commodities in the target commodity list based on the triggering operation on the second reply message includes:

[0033] In response to the first operation on the target commodity list in the second reply message, trading the target commodity list; or,

[0034] In response to a second operation on the target commodities included in each target commodity list in the second reply message, a combined transaction is performed based on the target commodities.

[0035] In a second aspect, the present application also provides a product recommendation device, comprising:

[0036] A display module, configured to display a first reply message in the chat interface in response to a transaction recommendation request triggered in the chat interface;

[0037] An input module, used for inputting transaction characteristics based on the first reply message;

[0038] A display module, configured to display a second reply message in the chat interface in response to completion of input of the transaction feature, wherein the second reply message includes a target commodity list; the target commodity list is determined based on the transaction feature;

[0039] A transaction module is used to perform a combined transaction on the commodities in the target commodity list based on a triggering operation on the second reply message.

[0040] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0041] In response to a transaction recommendation request triggered in the chat interface, displaying a first reply message in the chat interface;

[0042] inputting transaction characteristics based on the first reply message;

[0043] In response to completion of input of the transaction feature, displaying a second reply message in the chat interface, the second reply message including a target commodity list; the target commodity list is determined based on the transaction feature;

[0044] Based on the triggering operation on the second reply message, a combined transaction is performed on the commodities in the target commodity list.

[0045] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0046] In response to a transaction recommendation request triggered in the chat interface, displaying a first reply message in the chat interface;

[0047] inputting transaction characteristics based on the first reply message;

[0048] In response to completion of input of the transaction feature, displaying a second reply message in the chat interface, the second reply message including a target commodity list; the target commodity list is determined based on the transaction feature;

[0049] Based on the triggering operation on the second reply message, a combined transaction is performed on the commodities in the target commodity list.

[0050] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0051] In response to a transaction recommendation request triggered in the chat interface, displaying a first reply message in the chat interface;

[0052] inputting transaction characteristics based on the first reply message;

[0053] In response to completion of input of the transaction feature, displaying a second reply message in the chat interface, the second reply message including a target commodity list; the target commodity list is determined based on the transaction feature;

[0054] Based on the triggering operation on the second reply message, a combined transaction is performed on the commodities in the target commodity list.

[0055] The above-mentioned commodity recommendation method, device, computer equipment, computer-readable storage medium and computer program product, in response to a shopping recommendation request triggered in a chat interface, display a shopping guidance message in the chat interface; in response to an operation on the shopping guidance message, determine the user's shopping needs; display a budget range card, and in response to the target budget range entered in the budget range card, generate a shopping list in combination with the user's shopping needs. By adopting this method, with the help of an AI system, when the user does not have clear commodity recommendation needs such as shopping categories and transaction parameter amounts, the user is guided to enter transaction features through the first reply message to clarify the commodity recommendation needs, and then, based on the transaction features, a multi-dimensional and multi-type target commodity list is generated, which reduces user configuration operations and information query and search operations, simplifies the commodity recommendation process, and then improves the commodity recommendation efficiency of the target commodity list. In addition, the user can make combined transactions among the commodities in the target commodity list recommended by the AI ​​system, which improves the transaction flexibility of the recommended commodities in the target commodity list and the convenience of commodity recommendation. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0057] FIG1 is a diagram of an application environment of a commodity recommendation method in one embodiment;

[0058] Figure 2 A schematic diagram of a signaling interaction flow of human-computer interaction and interaction between a terminal and a server during a product recommendation process in one embodiment;

[0059] Figure 3 A schematic diagram of a flow chart of a commodity recommendation method in one embodiment;

[0060] Figure 4 A schematic diagram of a process for displaying a first reply message on a chat interface in one embodiment;

[0061] Figure 5 This is a schematic diagram of a chat interface including a commodity category card in one embodiment;

[0062] Figure 6 This is a schematic diagram of a chat interface including a product brand card in one embodiment;

[0063] Figure 7 This is a schematic diagram of a chat interface including a transaction parameter control in one embodiment;

[0064] Figure 8 A schematic diagram of a flow chart of steps for inputting transaction amount parameters in various different ways in one embodiment;

[0065] Fig. 9 It is a flowchart of the steps of combining transactions for commodities in a target commodity list in one embodiment;

[0066] Fig.10 This is a schematic diagram of the interface of a target product list page in one embodiment;

[0067] Fig.11 This is a schematic diagram of a commodity transaction interface in one embodiment;

[0068] Fig.12 A flowchart of steps for displaying a chat interface in multiple ways in one embodiment;

[0069] Fig.13 This is a schematic diagram of a shopping interface in one embodiment;

[0070] Fig.14 A schematic diagram of a process for determining a target product step by displaying various editing entrances for a user to edit a target product list in a floating form in an embodiment;

[0071] Fig.15 A schematic diagram of an interface for horizontally displaying a second reply message including a plurality of candidate commodity recommendation lists in the form of information cards in a chat interface in one embodiment;

[0072] Fig.16 A schematic diagram of an interface for vertically displaying a second reply message containing a plurality of candidate commodity recommendation lists in the form of information cards in a chat interface in one embodiment;

[0073] Fig.17 This is a schematic diagram of an interface of a display page of a target product list in an embodiment;

[0074] Fig.18 A schematic diagram of an interface for displaying a product selection floating page in an embodiment;

[0075] Fig.19 This is a schematic diagram of a shopping interface including a query entry for replacing goods in one embodiment;

[0076] Fig. 20 A schematic diagram of an interface in which a product detail page includes a target button for adding a target product to a target product list in an embodiment;

[0077] Fig.21 A schematic diagram of an interface in which a query entry for replacing goods is a transaction list page in an embodiment;

[0078] Fig. 22 A schematic diagram of a flow chart of steps for switching to display different target product lists in one embodiment;

[0079] Fig.23 A schematic diagram of a flow chart of a step of updating a transaction amount parameter in an embodiment;

[0080] Fig.24 A flowchart showing steps of creating a page for displaying a target product list in one embodiment;

[0081] Fig.25 This is a schematic diagram of an interface showing a chat interface including a second reply message in one embodiment;

[0082] Fig.26 is a structural block diagram of a commodity recommendation device in one embodiment;

[0083] Fig. 27 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0084] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0085] The commodity recommendation method provided in the embodiment of the present application can be applied in the application environment as shown in Figure 1. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. In response to the transaction recommendation request triggered in the chat interface, the terminal 102 displays a first reply message in the chat interface. Based on the first reply message, the terminal 102 inputs the transaction features. Then, in response to the completion of the input of the transaction features, the terminal 102 displays a second reply message in the chat interface. Among them, the second reply message includes a target commodity list. The target commodity list is determined based on the transaction features. Then, the terminal 102 performs a combined transaction on the commodities in the target commodity list based on the triggering operation of the second reply message.

[0086] The terminal 102 may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, IoT devices, and portable wearable devices. The IoT devices may be smart speakers, smart TVs, smart air conditioners, smart car devices, projection devices, etc. Portable wearable devices may be smart watches, smart bracelets, head-mounted devices, etc. Head-mounted devices may be virtual reality (VR) devices, augmented reality (AR) devices, smart glasses, etc. The server 104 may be an independent physical server, a server cluster or distributed system consisting of multiple physical servers, or a cloud server that provides cloud computing services.

[0087] In an exemplary embodiment, Figure 2 As shown, Figure 2 The signaling interaction diagram of a product recommendation method shows the interaction process between the user and the terminal, and between the terminal and the server. Specifically, the interaction process corresponding to the product recommendation method includes:

[0088] Step 201: The terminal displays a chat interface, which is a chat interface of an AI (Artificial Intelligence) assistant.

[0089] Step 202: The user inputs a transaction recommendation request in the chat interface.

[0090] Step 203: The terminal responds to the transaction recommendation request triggered in the chat interface by forwarding the transaction recommendation request to the server.

[0091] Step 204: In response to the transaction recommendation request, the server obtains original material information related to the recommendation requirement in the transaction recommendation request, and feeds the original material information back to the terminal. The original material information includes content information from multiple sources such as web pages, platforms, and various applications. The content included in the original material information is related to the transaction recommendation requirement involved in the transaction recommendation request, and can be obtained by performing a similarity search on the information in the transaction recommendation requirement.

[0092] In step 205, the terminal analyzes and processes the original material information based on the pre-integrated product recommendation model (an AI model), obtains a first reply message, and displays the first reply message in the chat interface. The first reply message includes the product category, product brand, transaction amount control related to the transaction recommendation demand, and guidance information for guiding the user to input transaction features.

[0093] Step 206: The user enters transaction features in the chat interface based on the prompt of the first reply message.

[0094] Step 207: The terminal inputs the transaction features based on the user's input operation, and displays a second reply message in the chat interface in response to the completion of the input of the transaction features. The second reply message includes a target product list. The target product list is obtained by the terminal processing the input transaction features and original material information based on the AI ​​model, and the target product list includes recommended products.

[0095] Step 208: The user performs a triggering operation on the second reply message.

[0096] Step 209: The terminal performs a combined transaction on the commodities in the target commodity list included in the second reply message based on the triggering operation on the second reply message.

[0097] In an exemplary embodiment, Figure 3 As shown, a commodity recommendation method is provided, and the method is applied to the terminal in FIG1 as an example for description, including the following steps 302 to 308. Among them:

[0098] Step 302, in response to the transaction recommendation request triggered in the chat interface, display a first reply message in the chat interface.

[0099] In implementation, an AI system (also referred to as an AI assistant) is pre-integrated in the terminal, and the user can conduct a conversation with the AI ​​system by asking questions in the AI ​​system, thereby obtaining the information the user wants. For example, if the AI ​​system is used for product recommendation, the user can ask questions in the AI ​​system to obtain the recommended product information, that is, initiate a transaction recommendation request, thereby conducting an interactive dialogue for product recommendation. Specifically, the user can enter the chat interface of the AI ​​system through multiple entrances. After the user enters the chat interface, the user can enter the target question or enter keywords in the input box provided in the chat interface to inform the application purpose or usage scenario of the product recommendation, thereby triggering the transaction recommendation request. In this way, the terminal responds to the transaction recommendation request triggered in the chat interface, processes the transaction recommendation request, analyzes the user's intention for the transaction recommendation request, and displays the first reply message in the chat interface. The first reply message may include relevant recommendation content information for the transaction recommendation request, and may also include guidance information for guiding the user to clarify the recommendation needs, for example, options such as product categories and product brands are involved as guidance options to guide the user to clarify the product recommendation needs. The embodiment of the present disclosure does not limit the specific content information contained in the first reply message.

[0100] Optionally, the AI ​​system can also be integrated on the server side, and the chat interface of the AI ​​system is displayed on the terminal side, so that the user can realize the application of the AI ​​system through the interaction between the terminal and the server. Specifically, when the user triggers a transaction recommendation request in the chat interface of the AI ​​system provided by the terminal, the terminal will send the transaction recommendation request triggered by the user to the server, and the server will run the AI ​​system, respond to the transaction recommendation request, and obtain the original material information related to the transaction recommendation request. The original material information can be information content related to the commodity recommendation demand obtained from various applications, information platforms, website pages, etc., and then, the server generates AI reply content based on the original material information and the pre-integrated commodity recommendation model. The AI ​​reply content will be fed back to the terminal as a reply message, for example, a first reply message, a second reply message, etc. After the terminal receives the reply message, the reply message is displayed in the chat interface of the AI ​​system on the terminal side, so that based on the development of a new dialogue, each dialogue is completed by the interaction between the user, the terminal and the server until the current round of commodity recommendation is completed, and the reply message displayed in the chat interface of the AI ​​system contains a list of recommended target commodities. Therefore, the embodiments of the present disclosure do not limit whether the AI ​​system is integrated into a terminal or a server, and can be pre-configured based on actual business needs.

[0101] During the product recommendation process, the AI ​​system will display a first reply message in the chat interface, which is used to guide the user to enter transaction features to clarify the user's product recommendation needs. The first reply message may include guidance recommendation options and / or transaction parameter controls, etc. Specifically, in an exemplary embodiment, Figure 4 As shown, during the interaction between the user and the AI ​​system, the first reply message output by the AI ​​system may include a guidance recommendation option or a transaction parameter control for guiding the user to clarify the commodity recommendation requirements. The specific processing process of step 302 includes:

[0102] Step 401, in response to a transaction recommendation request triggered in the chat interface, display a shopping demand card in the chat interface.

[0103] The shopping demand card includes a guidance recommendation option, which is used to guide the user to input transaction needs.

[0104] In implementation, after the user inputs a transaction recommendation request in the chat interface, the terminal responds to the transaction recommendation request by displaying a shopping demand card in the chat interface. The shopping demand card contains various guidance recommendation options to guide the user to clarify the product recommendation needs. For example, the shopping demand card may include a product category card, a product brand card, etc. Figure 5As shown, the transaction recommendation request triggered by the user is a recommendation request for "hiking, want to buy some outdoor supplies." Based on the recommendation request, the AI ​​system first displays the product category card, which contains various product category options related to the transaction recommendation request. For example, backpacks, sleeping bags, tents, jackets, sunglasses, camping chairs, thermos cups, lamps... Through product category options, users are guided to clarify the specific product categories they want to buy. Each product category option is used to guide users to clarify the target product category that needs to be recommended. After the user triggers the target product category option, only the product category option selected by the user is displayed in the product category card, and the product category option is highlighted, hiding the unselected product category options. Furthermore, shopping demand cards with other guiding content can be displayed in the chat interface. For example, product brand cards, such as Figure 6 As shown, the product brand card contains multiple product brands, and the user can specify the target product brand among the product brands.

[0105] Optionally, if the product category that the user wants to purchase is not included in the product category options or product brands given in the shopping demand card, the shopping demand card also includes an "other" option. The user can click on the "other" option and enter text to supplement the product category or product brand that he wants to be recommended.

[0106] Step 402, in response to a transaction recommendation request triggered in the chat interface, display a transaction parameter control.

[0107] The transaction parameter control is used to instruct the user to enter the transaction amount parameter.

[0108] In implementation, after the user enters a transaction recommendation request in the chat interface, the terminal can also prompt the user to further clarify the recommendation requirements in the form of a display control. Specifically, the terminal displays a transaction parameter control in response to the transaction recommendation request triggered in the chat interface. Figure 7 As shown, the transaction parameter control is displayed in the chat interface in the form of a parameter input box, and the parameter input box may also include prompt information to prompt the user to input relevant parameters. For example, "I want to ask what your budget range is?" This guides the user to enter the upper and lower limits of the transaction amount parameter in the transaction parameter control, so that the upper and lower limits of the transaction amount parameter given by the user are used as the recommended constraint conditions, and more accurate product recommendations are made to the user.

[0109] In this embodiment, during the interaction between the user and the AI ​​system, the first reply message displayed by the AI ​​system guides the user to input information and clarifies the user's product recommendation needs. Thus, based on the transaction features input in the first reply message, relevant products are recommended to the user, thereby improving the accuracy of product recommendations.

[0110] Optionally, the disclosed embodiments do not limit the display order of the transaction parameter controls and shopping demand cards, as well as the specific prompt contents corresponding to the transaction parameter controls and shopping demand cards. When a user triggers a transaction recommendation request, the AI ​​system can first display the shopping demand card in the chat interface to clarify the user's needs for purchasing commodity categories, and then further display the transaction parameter controls to clarify the user's overall budget. Alternatively, the transaction parameter controls can be displayed first to clarify the user's overall budget, and then, within the scope of the overall budget, the shopping demand card can be displayed to clarify the commodity category needs that the user wants to purchase.

[0111] Optionally, the transaction parameter control is configured with an intelligent budget adjustment function. When the user enters the transaction amount parameter and clicks Confirm, the AI ​​system analyzes and processes the input transaction amount parameter and determines that the input transaction amount parameter does not meet the preset transaction amount constraint condition, that is, when the input transaction amount parameter is unreasonable or abnormal, the corresponding recommended product will not be displayed in the chat interface, but the indication adjustment information of the transaction amount parameter will be intelligently displayed. Specifically, when the transaction amount parameter entered by the user is an abnormal transaction amount range, for example, the upper limit value of the transaction amount parameter is greater than the lower limit value, or the transaction amount parameter has a negative value, a prompt message indicating that the transaction amount parameter is abnormal is displayed. When the transaction amount parameter entered by the user is an unreasonable transaction amount range, for example, the commodity category and commodity type selected by the user are too different from the transaction amount parameter range (budget range) entered by the user, and the transaction amount parameter range given by the user is obviously too small (insufficient budget) or obviously too large, a prompt message for adjusting the transaction amount parameter is displayed. For example, "Based on the type of commodity you selected, the current budget is a bit low, and it may be difficult to buy high-quality commodities. It is recommended to increase the budget appropriately if the economy allows." This can guide the user to further adjust the transaction amount parameter range given in the transaction parameter control, and the transaction parameter control also includes a modification control. The user clicks the modification control to restore the state of the transaction amount upper limit and transaction amount lower limit in the transaction parameter control, that is, to restore the modification. In this way, the user can appropriately adjust the transaction amount parameter range to ensure that the AI ​​system makes more reasonable product recommendations.

[0112] Step 304: input transaction characteristics based on the first reply message.

[0113] In implementation, the user inputs transaction features that reflect the recommended needs of this transaction based on the first reply message displayed in the chat interface, such as transaction amount parameters, transaction commodity categories, transaction commodity brands, etc. Then, the terminal obtains the transaction features based on the user's input operation, and the transaction features are used to reflect the user's purchasing tendency and purchasing needs. Among them, the terminal can have multiple specific implementation methods for inputting transaction features based on the first reply message: for example, the user long presses the first reply message, and the terminal responds to the long press trigger operation of the first reply message, and displays the information input box and the software keyboard in the form of a floating layer. The transaction features are entered in the information input box through the software keyboard, and the input transaction features are used as the reply content of the first reply message, and the transaction features are displayed in the chat interface. For another example, the first reply message contains multiple guide options. The terminal obtains the transaction features corresponding to the target guide option based on the selection operation of the target guide option among the multiple guide options, thereby completing the input of the transaction features. Specifically, the terminal can understand the order based on preset transaction characteristics and first display the guidance options of the first dimension. For example, if the first dimension is product category, then multiple guidance options of the product category dimension will be first displayed in the chat interface: product category one, product category two, product category three, product category four and others. Among them, the product categories displayed in the chat interface are all product categories related to the transaction recommendation request input by the user. For example, if the transaction recommendation request wants to buy some outdoor products, the recommended product categories are all products related to outdoor products, such as tents, lamps, thermos cups, camping chairs, backpacks, etc. Among them, it also includes the "other" option. Other options can support users to enter the commodity categories they want to buy. That is, when the current displayed first dimension guidance options do not have the commodity categories that users want, or when the commodity categories that users want are missing, users can trigger other options, and the chat interface will automatically trigger the AI ​​system to further supplement the query "What are the other specific ones?" Such a first reply message, at this time, the user can enter the commodity categories they want, for example, "sleeping bags" and other commodity categories that are not in the guidance options, thereby completing the supplementary needs of the commodity category dimension. In this way, after the user performs the selection operation of the first dimension guidance options and enters the target commodity category they want, the user can trigger the confirmation operation to complete the input of the transaction features of the first dimension. After clarifying the transaction features of the first dimension, the guidance options of the transaction features of the second dimension are further displayed in the chat interface. For example, if the second dimension is the commodity brand, multiple guidance options of the commodity brand dimension are displayed in the chat interface: brand A, brand B, brand C, brand D and others, among which other options also support users to directly enter the target commodity brand. In this way, through an operation method similar to the product category guidance options, users can select the target guidance options in the guidance options of each product brand or directly enter their favorite target product brand in the chat interface to complete the input of the transaction characteristics of the second dimension.Similarly, after clarifying the transaction characteristics of the second dimension, the chat interface can further output a transaction parameter control, which contains prompt information to guide the user to enter the transaction amount parameter, as well as an input box or a guide option for the transaction amount parameter, and the user can enter the transaction amount parameter in the transaction parameter control or select the target guide option corresponding to the target transaction amount parameter in the guide option to clarify the transaction characteristics of the third dimension. In addition, after clarifying the basic commodity attribute information, the user can also output other guide options related to commodity attribute characteristics in the chat interface. For example, for the target commodity "windbreaker" clearly identified by the user, the chat interface displays the guide options of the style type related to the target commodity: "Style Type One", "Style Type Two", "Style Type Three" and other options, through which the user can further limit the style attribute characteristics of the target commodity. For another example, for the user's identified target product "windbreaker", guidance options for the material type of the target product are displayed in the chat interface: "Material One", "Material Two", "Material Three" and other options. The guidance options are used to guide the user to further limit the material attribute characteristics of the target product. In this way, the disclosed embodiment only provides a method of using guidance options of different dimensions to guide users to clarify their product recommendation needs, without limiting the dimensions and specific content of the guidance options.

[0114] For another example, the first reply message is an input box or information card for information to be input. The user can directly trigger the input box in the first reply message, or directly trigger the information card, so that the terminal responds to the triggering operation of the first reply message and displays an input mark in the first reply message, such as a mouse cursor mark. In this way, the user directly fills in the transaction feature in the input box or information card through the input mark to complete the input of the transaction feature. For example, the user directly fills in the category of the desired product in the blank position given in the first reply message, "I want to buy some XXX", where XXX represents the blank position. After the user fills in the target product in the blank position, the first reply message is displayed as "I want to buy some hiking outdoor users". After the transaction feature is filled in, the terminal can further give a reply message based on the filled-in transaction feature, and output further inquiry content to carry out a product recommendation dialogue. In the subsequent product recommendation dialogue, the information filling position can be further reserved to guide the user to enter other transaction features, or the user can be directly asked whether there are other requirements. The embodiment of the present disclosure does not limit the input of transaction features for the first reply message to be filled in.

[0115] Optionally, if the user wants to re-determine the transaction recommendation requirements during the product recommendation process with the AI ​​system, a reset button will be included in the first reply message or in the chat interface. The user can trigger the reset button to clear the originally input transaction features and re-enter new transaction features.

[0116] In the specific implementation process of step 304, if Figure 8 As shown, the transaction characteristics may include information such as transaction amount parameters, product category, and product brand. The following takes the transaction amount parameter as an example to further introduce three implementation methods of inputting transaction characteristics based on the first reply message:

[0117] Step 801: In response to a trigger operation on a transaction input box, a transaction amount parameter is input.

[0118] In implementation, the first reply message includes a transaction parameter control, which is displayed in the form of a transaction input box. Prompt information guiding the input is also displayed in the transaction input box. Based on the prompt information, the user performs a trigger operation on the transaction input box, so that the terminal enters the transaction amount parameter in response to the trigger operation on the transaction input box.

[0119] Optionally, in addition to the transaction input box, the transaction parameter control may also include a confirmation option, a modification option, and a reset option. The reset option and the confirmation option are displayed by default in the transaction parameter control, which are used to reset or confirm the upper and lower limit parameter range values ​​contained in the transaction parameter control that have been entered. When the user completes the input of the transaction amount parameter, the confirmation option is replaced by the modification option to adjust the transaction amount parameter based on the modification option, for example, modifying the upper limit parameter value of the transaction amount parameter, or modifying the lower limit parameter value of the transaction amount parameter.

[0120] Step 802: In response to a trigger operation on a target transaction value option in a transaction parameter value option, a transaction amount parameter is input.

[0121] In implementation, the transaction parameter control is displayed in the form of transaction parameter value options, that is, the transaction parameter control contains multiple candidate transaction parameter value options. In this way, the user can determine the transaction amount parameter by triggering the corresponding transaction parameter value option in the candidate transaction parameter control. The terminal enters the transaction amount parameter in response to the user's triggering operation on the target transaction value option in the candidate transaction parameter value option.

[0122] Step 803: In response to a triggering operation on a target transaction amount interval in a candidate transaction amount interval, a transaction amount parameter is input.

[0123] In implementation, the transaction parameter control is displayed in the form of a transaction amount interval, and a plurality of candidate transaction amount interval options are included in the transaction parameter control. Thus, for the plurality of candidate transaction amount interval options, the user determines the transaction amount parameter by triggering a target transaction amount interval option among the candidate transaction amount intervals. The terminal inputs the transaction amount parameter in response to the user's triggering operation for the target transaction amount interval in the candidate transaction amount interval.

[0124] In this embodiment, the input of transaction amount parameters is implemented in the form of various transaction parameter controls. Various different implementation methods improve the flexibility of information input, and different transaction amount parameter input methods are adapted to different application scenarios to meet the business needs of different application scenarios.

[0125] Step 306, in response to completion of input of the transaction feature, displaying a second reply message in the chat interface.

[0126] The second reply message includes a target commodity list, which is determined based on the transaction characteristics.

[0127] In practice, when the user inputs a conversation in the chat interface that contains an ending identifier (e.g., "No more", "Not needed", "No need", "Not available for the time being", "None"), etc., it is assumed that the user's transaction feature input is complete. For example, when the AI ​​system interacts with the user, when the current first reply message output by the AI ​​system is "Do you have any other product recommendations?", the user's reply is "No more". This indicates that the current transaction feature input is complete.

[0128] Alternatively, when the user interacts with the AI ​​system, the first reply message contains a confirmation option, the user clicks on the first reply message, and enters the transaction features in the input box contained in the first reply message. When all the information to be filled in the input box is completed and the confirmation option contained in the first reply message is triggered, it indicates that the current transaction feature input is completed. In this way, after the transaction feature input is completed, the terminal responds to the transaction feature input completion operation, inputs the transaction feature into the product recommendation model, recommends products to the user through the product recommendation model and the transaction feature, and includes the product recommendation result in the second reply message, and displays the second reply message in the chat interface.

[0129] Optionally, the second reply message includes the result of the product recommendation, and the result of the product recommendation can be displayed in the form of a target product list. Specifically, the target product list includes various products that meet the transaction characteristics. For example, the transaction characteristics include product categories, product brands, and transaction amount parameters. For example, the product categories in the transaction characteristics are tents, thermos cups, and outdoor chairs. The product brands require brand A and brand B. The transaction amount is in the range of 500-2000 (yuan). Then the target product list (one) recommended by the AI ​​system may include: tents of brand A, thermos cups of brand B, and outdoor chairs of brand B, and the total price of all products is 1500 yuan. The target product list (two) may include: tents of brand B, thermos cups of brand A, and outdoor chairs of brand B, and the total price of all products is 1000 yuan, etc. The disclosed embodiment does not limit the target product list that specifically meets the transaction characteristics.

[0130] Optionally, the transaction features may include, but are not limited to, transaction attribute indicators such as transaction amount range, transaction commodity category, and transaction commodity brand. The user's recommendation needs can be clarified through the various transaction attribute indicators contained in the transaction features. Then, the terminal recommends commodities to the user based on the transaction features and obtains a target commodity list. Specifically, the target commodity list can be obtained in at least two ways. In one way, the terminal queries a commodity list that meets the same type of needs of the transaction features based on the transaction features determined during the chat session with the user, as the target commodity list. Specifically, the knowledge base of the commodity recommendation model uses the account as the dimension to classify and store a variety of constructed commodity lists. The commodity list includes the commodity list name, the total transaction amount parameter corresponding to the commodity list, and each candidate commodity. The commodity list name can reflect the application scenario and purpose of the commodity list. Therefore, when the terminal inputs the transaction features of this product recommendation into the product recommendation model, the product recommendation model analyzes and processes each transaction feature to determine the user's product recommendation needs. Then, the AI ​​system matches and identifies the product recommendation needs in the knowledge base of the AI ​​system, and finds a list of products with the same or similar application scenarios and purpose needs as the product recommendation needs of this round. Then, based on the transaction amount parameter range, further screening is performed in the screened product list to obtain a list of products whose total transaction amount parameters are within the transaction amount parameter range. This product list is used as the target product list for this product recommendation to display to the user. In this way, the product list can be reused, the efficiency of generating the product list can be improved, and data processing resources can be saved.

[0131] Method 2: When there is no product list with the same type of demand, when the terminal recommends products to the user, it can first search for products that meet the transaction characteristics on the entire network and the entire platform, and then generate a target product list based on the determined products. Specifically, the terminal inputs the transaction characteristics (including product attribute characteristics and transaction amount parameters) into the product recommendation model of the AI ​​system. The product recommendation model uses natural language processing to screen candidate products that meet the product attribute characteristics in the knowledge base or database based on the input product category information, product brand information and other product attribute characteristics. In this process, the same product category is supported to correspond to multiple candidate products. For example, in the same product category of tents, there can be tents of brand A, tents of brand B, tents worth 500, and tents worth 800. Then, the AI ​​system combines the requirements of each candidate product according to the product category requirements required to be included in the target product list, and obtains multiple candidate product lists. Then, the AI ​​system uses the transaction amount parameter (i.e., the transaction amount range) as a constraint condition to further screen the multiple candidate product lists and determine the candidate product list that meets the transaction amount parameter as the final target product list.

[0132] Step 308: Based on the triggering operation of the second reply message, a combined transaction is performed on the commodities in the target commodity list.

[0133] In implementation, in each target commodity list included in the second reply message, the user can browse and view each target commodity list, and can combine and trade the commodities in the target commodity list to complete a commodity recommendation. Specifically, for each recommended target commodity list included in the second reply message, the user performs a trigger operation, and the terminal trades the commodities based on the user's trigger operation on the second reply message. Optionally, the user can perform a trigger operation on a target commodity list among multiple target commodity lists, and then, in response to the trigger operation, the terminal can trade all the commodities in the list for the selected target commodity list. For another example, the user can also perform a trigger operation on each commodity in multiple target commodity lists, so that the terminal trades the combined commodities in each target commodity list in response to the trigger operation.

[0134] In an exemplary embodiment, for a determined target commodity list, a user can directly trade and settle all commodities included in the target commodity list, or select any commodity in the target commodity list for trade and settlement, or combine and settle some commodities included in multiple target commodity lists. The disclosed embodiment provides users with multiple combined transaction modes, so that users can flexibly trade commodities in the target commodity list. Fig. 9 As shown, the specific processing process of step 308 includes:

[0135] Step 901: In response to a first operation on a target commodity list in a second reply message, a transaction is performed on the target commodity list.

[0136] In implementation, the second reply message includes multiple target product lists, each of which displays products under the product category required by the user's product recommendation needs. The user triggers one of the target product lists to display the target product list page corresponding to the target product list in full-screen display. Fig.10 As shown, Fig.10 In the target product list page, there is a check-all control before the list name, which is used to select all products in the target product list. The target product list page also includes a transaction option, that is, Fig.10 In this way, the user triggers the full check control for the entire target product list, checks all the products in the target product list, and then triggers the transaction option displayed at the bottom of the target product list page, completing the first operation on the target product list in the second reply message. In response to a series of operations on the target product list (i.e., the first operation), the terminal can directly perform a combined transaction on all the products checked in the current target product list. Specifically, Fig.11 As shown, Fig.11 This is a transaction page for the target product list. The transaction page includes all the products in the target product list, as well as the total transaction amount, payment method, delivery address and other information of all the products. The transaction page of the target product list also includes payment options, and the combined transaction of all the products is completed by triggering the payment options.

[0137] Step 902: In response to a second operation on the target commodities included in each target commodity list in the second reply message, a combined transaction is performed based on the target commodities.

[0138] In implementation, the second reply message contains multiple target product lists, each of which displays products under the product category required by the user's product recommendation needs. The user triggers one of the target product lists and displays the target product list page corresponding to the target product list in full-screen display. Each product included in the target product list page corresponds to a check control. And the target product list page also contains a transaction option, so that the user can choose to trigger the check control of the target product in the target product list and check the target product. Similarly, it also supports users to select products across target product lists, that is, different target product lists correspond to multiple different brands and different price products under the same product type. The user can slide the target product list page and switch to display other target product lists of different dimensions for horizontal product comparison. Then, the user can also check other target products in other target product lists. After completing the selection, fill in the final target product list. Finally, for the target product list that is refilled with products in the final multiple target product lists, the user triggers the transaction option displayed at the bottom of the target product list page, and the terminal responds to the second operation of the target products contained in each target product list in the second reply message, and performs a combined transaction based on each target product checked by the user.

[0139] In an optional embodiment, in addition to performing a combined transaction based on the target product lists given by the terminal to complete the product recommendation, the user can also select any one or several products in any target product list after the recommended target product lists are displayed on the chat page, without filling them into any target product list (i.e., not generating a new target product list, not updating a target product list), and directly perform a product purchase operation only for the selected recommended product. In this way, the target product list page jumps to the transaction page of the selected target product, which contains the target product, as well as the transaction amount, payment method, user's delivery address and other information of the product. The target product transaction page also contains a payment option, and the user can initiate a payment request by triggering the payment option, and the terminal and the server interact to complete the transaction of the product.

[0140] Optionally, the total amount of the final transaction is displayed in the transaction interface of the target product list. If the transaction amount of the target product list finally generated is greater than the transaction amount parameter value preset by the user, a pop-up window will be displayed to prompt the user that the current total transaction amount exceeds the transaction amount parameter value originally entered, and a modification entry will be provided, through which the user can modify the transaction amount parameter value again.

[0141] In this embodiment, the commodity recommendation task is completed by combining and trading the target commodity list or the target commodities in the target commodity list, thereby improving the transaction flexibility of the recommended commodities in the target commodity list.

[0142] In the above-mentioned commodity recommendation method, in response to a transaction recommendation request triggered in a chat interface, a first reply message is displayed in the chat interface; based on the first reply message, transaction features are input; in response to the completion of the input of the transaction features, a second reply message is displayed in the chat interface, the second reply message including a target commodity list; the target commodity list is determined based on the transaction features; based on the triggering operation of the second reply message, a combined transaction is performed on the commodities in the target commodity list. By adopting this method, with the help of an AI system, when the user does not have clear commodity recommendation requirements such as shopping categories, transaction parameter amounts, etc., the user is guided to input transaction features and clarify commodity recommendation requirements through a first reply message, and then, based on the transaction features, a multi-dimensional and multi-type target commodity list is generated, thereby improving the recommendation accuracy of the commodities included in the target commodity list, and then, the user can perform a combined transaction among the commodities in the target commodity list recommended by the AI ​​system, thereby improving the transaction flexibility of the recommended commodities in the target commodity list.

[0143] In an exemplary embodiment, the AI ​​system is integrated into the application of the terminal to realize the main function of the AI ​​system: providing product recommendations to users. Therefore, multiple entrances to the AI ​​chat interface are provided to users in the application. Users can enter the chat interface of the AI ​​system through different entrances and then apply the product recommendation function of the AI ​​system, such as Fig.12 As shown, before step 302, the method further includes steps 1202 to 1206. Among them:

[0144] Entry one: Step 1202, in response to a triggering operation on a first target control in a shopping page, displaying a chat interface.

[0145] In implementation, the shopping page of the application includes a product display area and a toolbar area, such as Fig.13 As shown, Fig.13 This is a schematic diagram of the shopping page interface. Fig.13In the product display area of ​​the shopping page, the product information is displayed in a double-column arrangement. Various types of information cards can also be displayed above the product display area, for example, live recommendation cards, product recommendation cards and other shopping recommendation information. At the top of each type of information card is the toolbar area. The toolbar area contains various tool controls. Among these tool controls is the first target control that can trigger the opening of the AI ​​chat interface. The user can trigger the first target control, and the terminal responds to the triggering operation of the first target control, turns on the AI ​​function, and displays the chat interface.

[0146] Entry 2: Step 1204, in response to a triggering operation on a recommended entry in a content details page of a target published content, a chat interface is displayed.

[0147] In implementation, the application includes a variety of content display pages, and the recommended content display page of the application displays a variety of types of published content, which can be graphic notes, video notes, short videos, etc., which include target published content for triggering AI system product recommendations. The content details page of the target published content includes the media content of the target product, the transaction control of the target product, and the recommendation entrance for triggering the AI ​​function. The recommendation entrance can be an activity control, an AI assistant or a search control, that is, it is used to search or recommend products similar to the target product. The user can trigger the recommendation entrance on the content details page to turn on the AI ​​function and display the chat interface. In the chat interface, the AI ​​system actively displays content related to the target product and guidance prompt information for the user. The user can directly perform further information queries and request product recommendations based on the target product in the chat interface. Optionally, the user can also open a new transaction recommendation request after ending the recommendation for the target product, and continue to inquire about transaction recommendation requests for other products, etc.

[0148] In an optional embodiment, the disclosed embodiment provides a specific example process of triggering a target note to start a product recommendation method, and the example process includes:

[0149] Step 12041, display the content details page of the target published content.

[0150] Among them, the content details page includes a recommended entrance.

[0151] In implementation, when the target published content containing the AI ​​system product recommendation is a target note, the user can trigger the target note during the browsing process to display the content details page of the target note in the terminal display interface. Among them, the content form of the target note can be a graphic note, a video note, etc. The details page in the target note contains the media content of the target product, the transaction control of the target product, and the recommendation entrance for triggering the AI ​​function. Among them, the content details page of the target note contains a variety of recommendation entrances for triggering the AI ​​function of the target note. The user can trigger the product recommendation function through any of the recommendation entrances of the AI ​​function. For example, the user clicks to enlarge the product picture in the target note, and the target display area corresponding to the product picture can display the search control corresponding to the AI ​​system entrance. The search control is used to enter the chat interface of the AI ​​system and start the chat dialogue of product recommendation. For example, the target area in the target note is directly equipped with a trigger button of the target activity control corresponding to the AI ​​system. The user can directly trigger the trigger button of the target activity control and directly enter the chat interface of the AI ​​system to start the chat dialogue of product recommendation. For another example, an AI assistant is pre-embedded in the note text or picture contained in the target note. When the user triggers the text field in the target note or the target position in the picture, the terminal responds to the trigger operation and displays a pop-up window introducing the content information corresponding to the text field and the target picture content. The pop-up window introducing the content information includes a target activity control, which is used to enter the chat interface of the AI ​​system and start a chat dialogue for product recommendations.

[0152] Step 12042, in response to the triggering operation on the recommendation entry, display the chat interface.

[0153] The recommendation entry may be an activity control, an AI assistant, or a search control. The chat interface includes a guide window, which includes guide information for guiding the user to send the product included in the target note.

[0154] In implementation, after displaying the recommendation entry, the terminal jumps from the display page of the target note to the chat interface of the AI ​​system in response to the triggering operation of the recommendation entry. The chat interface includes a guide window, which includes guide information. Among them, the guide information is used to guide the user to send the goods contained in the target note. For example, the target note is a recommendation note for an outdoor tent. Therefore, the guide information of "Do you want to get the same outdoor tent in the target note?" can be displayed in the guide window of the chat interface. Optionally, the user can directly enter a transaction recommendation request to search for the same outdoor tent in the chat interface based on the guide information, and then the user can make a product recommendation based on the transaction recommendation demand entered by the user. Among them, the AI ​​system can query the pictures and text content in the target note, directly obtain the same goods in the target note for product recommendation, and similarly, it can also find the same type of goods based on the target goods in the target note and display them together with the same goods in the target note in the chat interface to achieve horizontal comparison of the same type of goods. For example, the recommended goods in the target note browsed by the user involve an outdoor tent of brand A worth 1,000 yuan. When triggered by a transaction recommendation request input by the user, the AI ​​system can search for the same product in the target note and recommend it to the user. It can also search for similar products of the same type for recommendation. The AI ​​system can filter similar products based on the similarity between each product and the product in the target note and the preset similarity threshold. Optionally, for a product of brand A's outdoor tent worth 1,000 yuan, brand A's outdoor tent worth 700 yuan, brand B's outdoor tent worth 1,000 yuan, or brand B's outdoor tent worth 700 yuan, etc. can all be counted as similar products.

[0155] Optionally, in addition to displaying the guidance information "Do you want to get the same outdoor tent in the target note?" in the guide window, a link to the same product involved in the target note can also be displayed at the bottom of the chat interface. The link to the same product contains recommended details of the same product involved in the target note. In this way, the user clicks on the link without entering a query in the form of a question to trigger the AI ​​system to recommend products. The recommended details of the same product are directly input into the AI ​​system in the form of an information card and displayed in the chat interface. The AI ​​system can quickly query the same product based on the recommended details entered by the user, and display the purchase link of the same product in the chat interface to achieve product recommendation. In addition, users can also directly purchase the same product through the purchase link in the chat interface.

[0156] Entry three: Step 1206, in response to the triggering operation of the second target control in the video display page, display the chat interface.

[0157] In implementation, the application includes a variety of content display pages, and the video display page of the application displays videos, pictures and other content in a double-column arrangement or a single-column arrangement. The video display page of the application includes an upper toolbar, and the toolbar may also include a second target control. The second target control is also used to trigger the chat interface of the AI ​​system. Therefore, the user can trigger the second target control, and the terminal responds to the triggering operation of the second target control, turns on the AI ​​function, and displays the chat interface.

[0158] In this embodiment, by adding multiple different entrances to the application, users can turn on the AI ​​function through different entrances, display the chat interface of the AI ​​system, and then implement intelligent recommendations of products based on the AI ​​system, thereby improving the accuracy and efficiency of product recommendations.

[0159] In an exemplary embodiment, Fig.14 As shown, after step 306, the method further includes:

[0160] Step 1401, display the target product list page.

[0161] In implementation, after the second reply message is displayed in the conversation page, the second reply message includes a product recommendation list. Specifically, the product recommendation list is displayed in the second reply message in the form of an information card or thumbnail. Fig.15 As shown, in the second reply message, multiple candidate product recommendation lists are displayed in the form of information cards, and the recommended products included in each candidate product recommendation list are arranged and displayed in a horizontal arrangement. Fig.16 As shown, in the second reply message, the candidate product recommendation list is displayed in the form of an information card, and the recommended products included in the product recommendation list are arranged and displayed in a vertical arrangement. In this way, for the product recommendation list included in the second reply message, the user can trigger the target product list in the second reply message to display the details of the target product list. Thus, in response to the trigger operation on the target product list, the terminal takes the target product list as the current display page and displays the target product list page in full screen. In the target product list page, the recommended products included in the target product list are arranged vertically, and the name or type of the target product list and the select all control of the target product list are displayed above the target product list. The select all control is used to select all recommended products in the target product list. In front of each recommended product included in the target product list, there is also a corresponding checkable control for selecting each recommended product.

[0162] Step 1402: In response to a replacement operation on a target product in a target product list page, a product selection pop-up layer is displayed.

[0163] The product selection floating layer includes one or more of a shopping page entrance, a transaction list page entrance, a chat interface entrance, and other target product list page entrances.

[0164] In implementation, after the user obtains the target product list, the user can also flexibly replace each product in the target product list. Specifically, for each recommended product included in the target product list, the user can select any one of the products as the target product and perform a replacement operation on the target product, such as Fig.17 As shown, in the target product list displayed on the currently displayed target product list page, each target product corresponds to a replacement control, and the replacement control is displayed through a trigger button of "Change to a new product". When the user wants to replace any of the target products, the user triggers the replacement control of the target product to perform the replacement operation on the target product. In response to the replacement operation on the target product, the terminal displays a product selection floating layer on the target product list page displayed in full screen, such as Fig.18 As shown, the product selection floating layer includes entrances for various replacement paths for replacing the target product. Different entrances correspond to different product search paths, that is, the user can obtain replaceable products (i.e., replacement products) through different entrances and different product search paths to replace the target product in the product list page.

[0165] Step 1403, in response to a triggering operation on any entry in the product selection floating layer, display a display interface corresponding to the entry, and determine to replace the product.

[0166] The replacement product is used to replace the target product.

[0167] In implementation, among the multiple entrances displayed in the product selection floating layer, the user can select any one of the entrances to perform a trigger operation. In this way, the terminal responds to the trigger operation of any one of the entrances in the product selection floating layer, displays the display interface corresponding to the entrance, and searches and determines the replacement product in the display interface through the corresponding product search method.

[0168] The following is a detailed description of the target product replacement process achieved by different links corresponding to different entrances. In the actual target product replacement process, the user can only execute one of the links to achieve the target product replacement, or can achieve the target product replacement by combining multiple links. The embodiment of the present disclosure does not limit this. Specifically, the process is divided into the following links:

[0169] Entrance 1, such as Fig.19As shown, the entry for replacing the target product selected by the user is the entry of the shopping page, and the terminal jumps to the shopping page from the product selection floating layer in response to the user's triggering operation on the shopping page entry. The product display area of ​​the shopping page contains recommended products for the user, and the recommended products are searched based on user portrait features such as user search records, purchase records, and user preferences. In addition, a search input box and a product search control are also displayed at the top of the shopping page. The user can trigger the search input box, pull up the soft keyboard, and then enter the corresponding search keyword (the search keyword is determined based on the replacement product), and click the product search control. The terminal responds to the triggering operation of the product search control, searches for related products based on the search keyword, and displays the searched related products in the product display area of ​​the shopping page. For example, if the user wants to replace the thermos cup in the target product list, the user can search for products of the same category as the replacement product based on the search input box and the product search control in the shopping page. For example, the relevant products are searched for with keywords such as "thermos cup" and "water cup". In response to the keyword search, the terminal displays various commodities related to the keyword on the shopping page, such as various thermos cups, etc. Then, the user can filter out the target commodity from the various thermos cups provided on the shopping page, add the target commodity to the target commodity list, and replace the commodity to be replaced in the current target commodity list. For example, the thermos cup B selected by the user on the shopping page is added to the target commodity list, replacing the original thermos cup A.

[0170] In an optional embodiment, the user does not search for keywords on the shopping page, but browses products in the product display area of ​​the recommended products on the shopping page. If the user sees a desired product (referred to as a target product) and wants to add it to the target product list, the user can also click on the target product card on the shopping page to enter the product details page, such as Fig.19 As shown, the upper left corner of the product details page contains a return control, which is used to return to the shopping page. The upper right corner of the store details page contains multiple function buttons, including a target button for adding the target product included in the product details page to the target product list (i.e. Fig. 20The second from the right to the left among the function buttons in the upper right corner of the page), therefore, when the user clicks the target button in the upper right corner (also called the [Add to Target Product List button]), the terminal responds to the user's click operation on the target button and adds the target product to the target product list currently displayed on the target product list page. At this time, a pop-up window will be displayed at the bottom of the product details page to inform the user that other target product lists can be modified, and a modification entry will be provided in the pop-up window, which is displayed in the form of a modification option. If the user clicks the modification option in the pop-up window, a list page of each target product list in a semi-floating form will appear at the bottom of the product details page. In the list page, each target product list has a check option corresponding to it. The user can check the target product list and select the modified target product list by triggering the check option. Thus, after the user selects the modified target product list, the target product selected by the user can be added to the selected target product list to complete the modification of the target product list.

[0171] Entrance 2, such as Fig.21 As shown, the entry selected by the user is the transaction list page entry, and the terminal displays the transaction list page in response to the user's trigger operation on the transaction list entry. The transaction list page contains a variety of candidate commodities to be traded that are pre-selected by the user, and supports multiple commodities under the same commodity type. Then, the user can select commodities on the transaction list page, and the terminal determines the replacement commodity to replace the target commodity in response to the user's selection operation on the commodity. Specifically, when the user browses commodities on the shopping page, the user can add all the candidate commodities he likes to the transaction list page, and the transaction list page classifies and stores the commodities pre-purchased by the user according to different commodity categories, different stores and other dimensions. For example, Fig.21In the transaction list page, among the tent category products displayed on the transaction list page, the user has pre-purchased multiple tents. For example, in the transaction list page, two tents of the same brand but different prices corresponding to store A are pre-purchased, and two tents of different prices corresponding to store B are also pre-purchased. In this case, with the store as the dimension, the products of store A and store B are stored separately in the form of product sublists, and the corresponding store name corresponds to the top of the product sublist corresponding to each store. And there is a check option corresponding to the front end of each product included in the transaction list page. In addition, when the store is used as the storage dimension, there is also a full check option in front of each store name. In this way, when the user performs a product replacement, the user can replace the target product in the transaction list page with multiple target products pre-purchased. Among them, the user can select a target product from multiple candidate products corresponding to a certain store as the target product to replace the products in the target product list, or directly check the products in the entire store as the target product to replace the products in the target product list. Alternatively, the user can freely combine the products corresponding to multiple stores, check the corresponding target product, and replace the products in the target product list. For example, Fig.21 In the transaction list page, there are multiple tents from different stores, different models or different prices in the same store that have been pre-purchased. Thus, when the user enters the transaction list page through the transaction list page entrance corresponding to the product selection floating layer, the user can select one of the tents to replace the tent in the original target product list. The target product list is modified.

[0172] Optionally, different product categories are displayed in different transaction list pages. Fig.21 In the upper part of the transaction list, options of different product categories are displayed. Users can trigger the options of different product categories to display the transaction list page of the product category. For product categories that are not in the target product list, users can also pre-purchase to the transaction list to increase the types of product categories in the transaction list. When the user performs the target product replacement process, the product of the product category can be selected in the transaction list page and added to the original target product list to supplement the target product list.

[0173] Entrance three: If the entrance selected by the user in the product selection floating layer is the chat interface entrance, the terminal displays the chat interface of the AI ​​system in response to the user's triggering operation on the chat interface entrance. Returning to the chat interface again, the user can initiate a supplementary request based on the product category, product brand, transaction amount parameters and other information of the product to be replaced, that is, on the basis of the context dialogue of the user's product recommendation request in this round that has been saved in the chat interface, the user can additionally supplement the product attribute restriction requirements for the product to be replaced, and the AI ​​system will conduct targeted supplementary retrieval and recommend feedback to the user. For example, for each product included in the target product list that the current AI system has fed back, where the user wants to replace the tent (the product to be replaced) of brand B with a price of 500 yuan included in the current target product list, the user executes the target product replacement process, and after returning to the chat interface of the AI ​​system again, a supplementary question can be asked in the chat interface: "Please recommend a tent of brand A with a price of about 1,000 yuan", and then, through the analysis and processing of the AI ​​system, the tent that meets the constraints in the user's supplementary question is displayed in the chat interface. The terminal uses the tent as a target commodity to replace the commodity to be replaced in the current target commodity list, thereby completing the modification of the target commodity list.

[0174] Entrance 4: If the entrance selected by the user in the product selection floating layer is the entrance to the page of other target product lists, it indicates that the user can select the desired product in the other target product lists to replace the products in the current target product list, and realize the free combination of products in different target product lists. Specifically, in response to the triggering operation of the entrance (i.e., entrance 4) of the other target product list page in the product selection floating layer, the terminal jumps from the product selection floating layer to the other target product list page to display the other target product list. In the other target product list, the user can horizontally compare products of different brands, different prices, and different performances of the same category. For example, the AI ​​system feeds back multiple target product lists to the user, and the tent in the target product list displayed on the current target product list page, the product attribute characteristics of this product fail to meet the user's expectations, then the user executes the target product replacement process, jumps to the other target product list page through the entrance 4, displays the other target product list by horizontal sliding, selects a desired one from the multiple tents of different prices and brands contained in the other target product list as the target product, and replaces it in the target product list displayed on the current target product list page, and completes the modification of the target product list.

[0175] In this embodiment, the AI ​​system also provides users with a variety of different display entrances for replacing target products for the target product list recommended by the AI ​​system. By querying replaceable products through different display entrances, flexible configuration of each recommended product included in the target product list is achieved, thereby improving the flexibility and accuracy of target product recommendation.

[0176] In an exemplary embodiment, Fig. 22 As shown, after step 1401, the method further includes:

[0177] Step 2201: In response to a sliding operation on the target product list page, a next target product list of a different dimension from the current target product list is displayed on the target product list page.

[0178] In implementation, in the multiple target product lists included in the second reply message, the terminal pre-sorts the multiple target product lists and determines the sorting results of the multiple target product lists. The sorting result is the display order of each target product list when it is displayed in full screen, and can be displayed in sequence on the target product list page. When the user performs a trigger operation on the second reply message, the terminal will display the target product list when the target product list currently triggered by the user is displayed as a full-screen page based on the trigger operation. For target product lists of other types and other recommended dimensions that are not displayed, candidates are displayed according to the sorting results of each target product list. In this way, when the user wants to view target product lists of other types and other recommended dimensions, the user can view target product lists of other types and other recommended dimensions by sliding horizontally, such as Fig.10 As shown, the terminal responds to the horizontal sliding operation on the target product list page and displays the next target product list adjacent to the current target product list according to the sorting results of each target product list. For example, if the user performs a left sliding operation on the target product list page, the terminal responds to the left sliding operation and displays the next target product list adjacent to the target product list. If the user performs a right sliding operation on the target product list page, the terminal responds to the right sliding operation and displays the previous target product list adjacent to the target product list.

[0179] In this embodiment, the current target product list is displayed through the target product list page, and in response to the user's sliding operation, the target product lists of different types can be switched, displayed and queried.

[0180] In an optional embodiment, if Fig.23 As shown, a process for editing and modifying a transaction amount parameter in a target commodity list is provided. Specifically, the method further includes:

[0181] Step 2301, in response to a triggering operation on a transaction parameter control, updating a transaction amount parameter.

[0182] In implementation, after obtaining the target commodity list, the transaction amount control corresponding to the target commodity list can be displayed in the top area of ​​the display page of the target commodity list, and the transaction amount parameter range (including the upper limit and lower limit of the transaction amount) of the current target commodity list is displayed in the transaction amount control. The transaction amount control supports user modification. When the user triggers the transaction parameter control, the user responds to the trigger operation and displays a configurable transaction amount input mark. The user re-modifies the upper limit and / or lower limit of the transaction amount based on the transaction amount input mark, thereby obtaining a new transaction amount parameter range. In this way, the terminal can adaptively adjust the commodities in the target commodity list based on the user's modification operation of the transaction amount parameter, that is, realize the linkage between the transaction amount parameter and each commodity in the target commodity list.

[0183] Similarly, when the user deletes a product in the target product list, the transaction amount parameter range corresponding to the transaction parameter control is automatically adjusted to the adapted transaction amount parameter range based on the target product list after the product is deleted. Specifically, in the target product list, the user performs a right swipe operation on a certain product to remove or delete the product from the target product list. In response to the right swipe operation performed by the user, the terminal deletes the display mark of the product in the target product list and adaptively adjusts the transaction amount parameter range corresponding to the target product list, that is, the transaction amount upper limit value and the transaction amount lower limit value of the original transaction amount parameter range are respectively subtracted from the amount of the product to obtain the updated transaction amount parameter range, and the updated transaction amount parameter range is displayed, so as to realize the updated target product list and the adapted transaction amount parameter range.

[0184] In an optional embodiment, for the target product list obtained in the product recommendation process, the user can choose to store the target product list to facilitate subsequent reuse of the target product list, or publish the target product list to the entire network and AI system, and recommend it as a candidate target product list when recommending products for other users who have the same type of product recommendation needs.

[0185] In an optional embodiment, the second reply message further includes a button for directly creating a target product list. The second reply message is displayed in the chat interface. After the second reply message includes the target product list, Fig.24 As shown, the method also includes:

[0186] Step 2401: In response to a trigger operation on a second reply message, a target product list creation page is displayed.

[0187] The target product list creation page includes a transaction feature control for creating a target product list, and the transaction feature control is used to input transaction features.

[0188] In practice, after the second reply message containing the target product list is displayed in the chat interface, the second reply message also contains a direct create button for directly creating the target product list and a view details button. The view details button is used to view the target product list recommended by the AI ​​system, while the direct create button can be triggered to directly create the target product list when the user is not satisfied with the target product list recommended by the AI ​​system or the user does not want to view the target product list recommended by the AI ​​system. Fig.25 As shown, in Fig.25 The second reply message not only displays the recommended target product list, but also contains a direct creation button at the bottom of the target product list thumbnail. If the user triggers the direct creation button, the chat page of the AI ​​system jumps to the target product list creation page, such as Fig. 27 As shown, the target product list creation page includes a transaction parameter control for filling in the transaction amount parameter range of the target product list. In the transaction parameter control, the user can fill in the upper and lower limits of the transaction amount parameter. Below the transaction parameter control, a product selection control for the desired product is displayed, and the product selection control includes a product add button, which is displayed as a button logo with a plus sign. The user adds products of different product categories by triggering the product add button. After determining the target product category, there is a select product button corresponding to each target product category item, and the select product button is used to select the target product under the product category. Specifically, if the user triggers the select product button, the terminal responds to the triggering operation of the select product button and displays a product selection floating layer, and the product selection floating layer includes one or more of a shopping page entrance, a transaction list page entrance, a chat interface entrance, and other target product list page entrances. Furthermore, the user can enter different display interfaces through different entrances in the product selection floating layer to search and select the target product. The process of the user triggering any entrance in the product selection floating layer, displaying the corresponding display interface and determining to replace the product is consistent with the link process involved in the above step 1403. If it has been described in the above step 1403, it will not be repeated here.

[0189] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0190] Based on the same inventive concept, the embodiment of the present application also provides a product recommendation device for implementing the product recommendation method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more product recommendation device embodiments provided below can refer to the limitations on the product recommendation method above, and will not be repeated here.

[0191] In an exemplary embodiment, Fig.26 As shown, a commodity recommendation device 2600 is provided, comprising: a first display module 2601, an input module 2602, a second display module 2603 and a transaction module 2604, wherein:

[0192] The first display module 2601 is used to display a first reply message in the chat interface in response to a transaction recommendation request triggered in the chat interface.

[0193] The input module 2602 is used to input transaction characteristics based on the first reply message.

[0194] The second display module 2603 is used to display a second reply message in the chat interface in response to completion of the input of the transaction characteristics, and the second reply message includes a target product list; the target product list is determined based on the transaction characteristics.

[0195] The transaction module 2604 is used to perform a combined transaction on the commodities in the target commodity list based on the triggering operation of the second reply message.

[0196] In one embodiment, the product recommendation device 2600 further includes:

[0197] A third display module is used to display a chat interface in response to a triggering operation on the first target control in the shopping page; or,

[0198] A fourth display module is used to display a chat interface in response to a triggering operation on a recommendation entry in a content details page of a target published content; or,

[0199] The fifth display module is used to display a chat interface in response to a triggering operation on a second target control in the video display page.

[0200] In one embodiment, the first reply message includes a guidance recommendation option and a transaction parameter control, and the first display module 2601 is specifically used to display a shopping demand card in the chat interface in response to a transaction recommendation request triggered in the chat interface; the shopping demand card includes a guidance recommendation option, and the guidance recommendation option is used to guide the user to enter the transaction demand; and / or,

[0201] In response to a transaction recommendation request triggered in the chat interface, a transaction parameter control is displayed, and the transaction parameter control is used to instruct the user to enter a transaction amount parameter.

[0202] In one embodiment, the first display module 2601 is specifically used to input a first transaction requirement in response to a trigger operation on a first guidance recommendation option in a shopping requirement card; the first transaction requirement is used to reflect a commodity category; and / or,

[0203] In response to a triggering operation on a second guidance recommendation option in a shopping requirement card, a second transaction requirement is input, where the second transaction requirement is used to reflect a product brand; and / or,

[0204] In response to the triggering operation on the transaction parameter control, the transaction amount parameter is input.

[0205] In one embodiment, the first display module 2601 is specifically configured to input a transaction amount parameter in response to a trigger operation on the transaction input box; or

[0206] In response to a trigger operation on a target transaction value option in a transaction parameter value option, input a transaction amount parameter; or,

[0207] In response to a triggering operation on a target transaction amount interval in the candidate transaction amount interval, a transaction amount parameter is input.

[0208] In one embodiment, the product recommendation device 2600 further includes:

[0209] The sixth display module is used to display the target product list page;

[0210] A seventh display module is used to display a product selection floating layer in response to a replacement operation of a target product in a target product list page; the product selection floating layer includes one or more of a shopping page entrance, a transaction list page entrance, a chat interface entrance, and other target product list page entrances;

[0211] The eighth display module is used to respond to the triggering operation of any entrance in the product selection floating layer, display the display interface corresponding to the entrance, and determine the replacement product, which is used to replace the target product.

[0212] In one embodiment, the product recommendation device 2600 further includes:

[0213] The ninth display module is used to display a next target product list of a different dimension from the current target product list in the target product list page in response to a sliding operation on the target product list page.

[0214] In one embodiment, the transaction module 2604 is specifically configured to perform a transaction on the target commodity list in response to the first operation on the target commodity list in the second reply message; or

[0215] In response to a second operation on the target commodities included in each target commodity list in the second reply message, a combined transaction is performed based on the target commodities.

[0216] Each module in the above-mentioned commodity recommendation device can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the corresponding operations of each module.

[0217] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Fig. 27As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, near field communication (NFC) or other technologies. When the computer program is executed by the processor, a commodity recommendation method is implemented. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0218] Those skilled in the art will understand that Fig. 27 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0219] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0220] In response to a transaction recommendation request triggered in the chat interface, displaying a first reply message in the chat interface;

[0221] Based on the first reply message, input transaction characteristics;

[0222] In response to the completion of the input of the transaction characteristics, a second reply message is displayed in the chat interface, the second reply message including a target commodity list; the target commodity list is determined based on the transaction characteristics;

[0223] Based on the triggering operation on the second reply message, a combined transaction is performed on the commodities in the target commodity list.

[0224] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0225] In response to a triggering operation on a first target control in a shopping page, displaying a chat interface; or,

[0226] In response to a triggering operation on a recommendation entry in a content details page of a target published content, displaying a chat interface; or,

[0227] In response to a triggering operation on a second target control in the video display page, a chat interface is displayed.

[0228] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0229] In response to a transaction recommendation request triggered in the chat interface, displaying a shopping demand card in the chat interface; the shopping demand card includes a guide recommendation option, and the guide recommendation option is used to guide the user to input the transaction demand; and / or,

[0230] In response to a transaction recommendation request triggered in the chat interface, a transaction parameter control is displayed, and the transaction parameter control is used to instruct the user to enter a transaction amount parameter.

[0231] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0232] In response to a triggering operation on a first guidance recommendation option in a shopping requirement card, a first transaction requirement is input; the first transaction requirement is used to reflect a commodity category; and / or,

[0233] In response to a triggering operation on a second guidance recommendation option in a shopping requirement card, a second transaction requirement is input, where the second transaction requirement is used to reflect a product brand; and / or,

[0234] In response to the triggering operation on the transaction parameter control, the transaction amount parameter is input.

[0235] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0236] In response to a trigger operation on a transaction input box, input a transaction amount parameter; or,

[0237] In response to a trigger operation on a target transaction value option in a transaction parameter value option, input a transaction amount parameter; or,

[0238] In response to a triggering operation on a target transaction amount interval in the candidate transaction amount interval, a transaction amount parameter is input.

[0239] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0240] Display the target product list page;

[0241] In response to a replacement operation of a target product in a target product list page, a product selection pop-up layer is displayed; the product selection pop-up layer includes one or more of a shopping page entrance, a transaction list page entrance, a chat interface entrance, and other target product list page entrances;

[0242] In response to a triggering operation on any one of the entrances in the product selection floating layer, a display interface corresponding to the entrance is displayed, and a replacement product is determined, and the replacement product is used to replace the target product.

[0243] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0244] In response to a sliding operation on the target product list page, a next target product list of a different dimension from the current target product list is displayed on the target product list page.

[0245] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0246] In response to the first operation on the target product list in the second reply message, trading is performed on the target product list; or,

[0247] In response to a second operation on the target commodities included in each target commodity list in the second reply message, a combined transaction is performed based on the target commodities.

[0248] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0249] In response to a transaction recommendation request triggered in the chat interface, displaying a first reply message in the chat interface;

[0250] Based on the first reply message, input transaction characteristics;

[0251] In response to the completion of the input of the transaction characteristics, a second reply message is displayed in the chat interface, the second reply message including a target commodity list; the target commodity list is determined based on the transaction characteristics;

[0252] Based on the triggering operation on the second reply message, a combined transaction is performed on the commodities in the target commodity list.

[0253] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0254] In response to a triggering operation on a first target control in a shopping page, displaying a chat interface; or,

[0255] In response to a triggering operation on a recommendation entry in a content details page of a target published content, displaying a chat interface; or,

[0256] In response to a triggering operation on a second target control in the video display page, a chat interface is displayed.

[0257] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0258] In response to a transaction recommendation request triggered in the chat interface, displaying a shopping demand card in the chat interface; the shopping demand card includes a guide recommendation option, and the guide recommendation option is used to guide the user to input the transaction demand; and / or,

[0259] In response to a transaction recommendation request triggered in the chat interface, a transaction parameter control is displayed, and the transaction parameter control is used to instruct the user to enter a transaction amount parameter.

[0260] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0261] In response to a triggering operation on a first guidance recommendation option in a shopping requirement card, a first transaction requirement is input; the first transaction requirement is used to reflect a commodity category; and / or,

[0262] In response to a triggering operation on a second guidance recommendation option in a shopping requirement card, a second transaction requirement is input, where the second transaction requirement is used to reflect a product brand; and / or,

[0263] In response to the triggering operation on the transaction parameter control, the transaction amount parameter is input.

[0264] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0265] In response to a trigger operation on a transaction input box, input a transaction amount parameter; or,

[0266] In response to a trigger operation on a target transaction value option in a transaction parameter value option, input a transaction amount parameter; or,

[0267] In response to a triggering operation on a target transaction amount interval in the candidate transaction amount interval, a transaction amount parameter is input.

[0268] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0269] Display the target product list page;

[0270] In response to a replacement operation of a target product in a target product list page, a product selection pop-up layer is displayed; the product selection pop-up layer includes one or more of a shopping page entrance, a transaction list page entrance, a chat interface entrance, and other target product list page entrances;

[0271] In response to a triggering operation on any one of the entrances in the product selection floating layer, a display interface corresponding to the entrance is displayed, and a replacement product is determined, and the replacement product is used to replace the target product.

[0272] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0273] In response to a sliding operation on the target product list page, a next target product list of a different dimension from the current target product list is displayed on the target product list page.

[0274] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0275] In response to the first operation on the target product list in the second reply message, trading is performed on the target product list; or,

[0276] In response to a second operation on the target commodities included in each target commodity list in the second reply message, a combined transaction is performed based on the target commodities.

[0277] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0278] 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, and the collection, use and processing of relevant data must comply with relevant regulations.

[0279] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory 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. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0280] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, 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 application.

[0281] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A product recommendation method, characterized in that: The method comprises: In response to a transaction recommendation request triggered in the chat interface, displaying a first reply message in the chat interface; inputting transaction characteristics based on the first reply message; In response to completion of input of the transaction feature, displaying a second reply message in the chat interface, the second reply message including a target commodity list; the target commodity list is determined based on the transaction feature; Based on the triggering operation on the second reply message, a combined transaction is performed on the commodities in the target commodity list.

2. The method according to claim 1, characterized in that In response to the transaction recommendation request triggered in the chat interface, before displaying the first reply message in the chat interface, the method further includes: In response to a triggering operation on a first target control in a shopping page, displaying a chat interface; or, In response to a triggering operation on a recommendation entry in a content details page of a target published content, displaying the chat interface; or, In response to a triggering operation on a second target control in the video display page, the chat interface is displayed.

3. The method according to claim 1, characterized in that The first reply message includes a guide recommendation option and a transaction parameter control, and the displaying of the first reply message in the chat interface in response to the transaction recommendation request triggered in the chat interface includes: In response to a transaction recommendation request triggered in the chat interface, displaying a shopping demand card in the chat interface; the shopping demand card includes a guide recommendation option, and the guide recommendation option is used to guide the user to input the transaction demand; and / or, In response to a transaction recommendation request triggered in the chat interface, the transaction parameter control is displayed, and the transaction parameter control is used to instruct the user to enter a transaction amount parameter.

4. The method according to claim 3, characterized in that The inputting transaction characteristics based on the first reply message includes: In response to a triggering operation on a first guidance recommendation option in the shopping demand card, a first transaction demand is input; the first transaction demand is used to reflect a commodity category; and / or, In response to a triggering operation on a second guidance recommendation option in the shopping requirement card, a second transaction requirement is input, where the second transaction requirement is used to reflect a product brand; and / or, In response to the triggering operation on the transaction parameter control, a transaction amount parameter is input.

5. The method according to claim 4, characterized in that The step of inputting a transaction amount parameter in response to a triggering operation on the transaction parameter control includes: In response to a trigger operation on a transaction input box, input a transaction amount parameter; or, In response to a trigger operation on a target transaction value option in a transaction parameter value option, input a transaction amount parameter; or, In response to a triggering operation on a target transaction amount interval in the candidate transaction amount interval, a transaction amount parameter is input.

6. The method according to claim 1, characterized in that In response to the completion of the input of the transaction feature, after displaying the second reply message in the chat interface, the method further includes: Display the target product list page; In response to a replacement operation of a target product in the target product list page, a product selection floating layer is displayed; the product selection floating layer includes one or more of a shopping page entrance, a transaction list page entrance, a chat interface entrance, and other target product list page entrances; In response to a triggering operation of selecting any one of the entrances in the floating layer for the commodity, a display interface corresponding to the entrance is displayed, and a replacement commodity is determined, wherein the replacement commodity is used to replace the target commodity.

7. The method according to claim 6, characterized in that After displaying the target product list page, the method further includes: In response to a sliding operation on the target product list page, a next target product list of a different dimension from the current target product list is displayed on the target product list page.

8. The method according to claim 1, characterized in that The performing a combined transaction on the commodities in the target commodity list based on the triggering operation on the second reply message includes: In response to the first operation on the target commodity list in the second reply message, trading the target commodity list; or, In response to a second operation on the target commodities included in each target commodity list in the second reply message, a combined transaction is performed based on the target commodities.

9. A commodity recommendation device, characterized in that: The device comprises: A first display module, configured to display a first reply message in the chat interface in response to a transaction recommendation request triggered in the chat interface; An input module, used for inputting transaction characteristics based on the first reply message; a second display module, configured to display a second reply message in the chat interface in response to completion of input of the transaction feature, wherein the second reply message includes a target commodity list; the target commodity list is determined based on the transaction feature; A transaction module is used to perform a combined transaction on the commodities in the target commodity list based on a triggering operation on the second reply message.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

Images