Control method, display method and electronic device

Abstract

This application provides a control method, a display method, and an electronic device. The method includes: detecting an address retrieval command; determining the matching degree between multiple addresses in an address list and current user behavior data; reordering the multiple addresses according to the matching degree; and responding to the address retrieval command based on the sorting result. The technical solution provided by this application achieves fast and accurate address retrieval.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a control method, a display method, and an electronic device. Background Technology

[0002] The development of internet and e-commerce technologies has made online purchasing a common part of daily life. Online purchases often require logistics and delivery, so users need to provide a delivery address. Furthermore, some online products are also address-dependent, requiring users to provide their delivery address so that the system can recommend products relevant to that address.

[0003] In practical applications, users may have different desired delivery addresses each time they purchase a product, and they may also need to view products related to different addresses. Therefore, to meet user needs, users can provide multiple addresses and save them to an address list. When an address is needed, it can be selected from the address list first. However, when there are many addresses in the address list, it is often impossible to quickly and accurately locate the target address, which undoubtedly increases the selection time. Summary of the Invention

[0004] This application provides a control method, a display method, and an electronic device to solve the technical problem of being unable to quickly and accurately implement address calls.

[0005] Firstly, this application provides a control method, including:

[0006] Detect address call instructions;

[0007] Determine the degree of match between each address in the address list and the current user behavior data;

[0008] The multiple addresses are reordered according to the matching degree.

[0009] The address call instruction is responded to based on the sorting result.

[0010] Optionally, the matching degree between the multiple addresses in the address list and the current user behavior data includes:

[0011] By combining the historical user behavior data corresponding to the historical usage records of the multiple addresses, the matching degree between the multiple addresses and the current user behavior data is determined.

[0012] Optionally, determining the matching degree between the multiple addresses and the current user behavior data by combining the historical user behavior data from the historical usage records of the multiple addresses includes:

[0013] Using a matching model trained on historical user behavior data corresponding to the historical usage records of the multiple addresses, the matching degree between the multiple addresses in the address list and the current user behavior data is determined.

[0014] Optionally, the matching model is trained in the following manner:

[0015] Retrieve historical order data;

[0016] Determine the historical user behavior data corresponding to the historical order data and the order address used;

[0017] A matching model is trained based on the historical behavior data and the order address.

[0018] Optionally, training the matching model based on the historical behavior data and the order address includes:

[0019] The historical behavior data and the corresponding order addresses are used as positive samples;

[0020] Replace the order address corresponding to the historical behavior data with an arbitrary address, and use the historical behavior data and the corresponding replacement address as negative samples;

[0021] A matching model is trained using the positive and negative samples.

[0022] The matching model, trained using historical user behavior data corresponding to the historical usage records of the multiple addresses, determines the matching degree between the multiple addresses in the address list and the current user behavior data, including:

[0023] For each address in the address list, the address and the current user behavior data are input into the matching model to calculate the matching degree between the address and the current user behavior data.

[0024] Optionally, the historical user behavior data includes one or more of the following parameters: order generation time, product characteristics of the product corresponding to the order, user characteristics, and order placement location;

[0025] The current user behavior data includes one or more of the following parameters: current time, user characteristics, current user location, and product characteristics of the currently operated product.

[0026] Optionally, it also includes:

[0027] Upon detecting a user's operation to retrieve the address list, the address retrieval instruction is generated;

[0028] The response to the address call instruction based on the sorting result includes:

[0029] The multiple addresses in the address list are displayed according to the sorting result.

[0030] Optionally, it also includes:

[0031] Upon receiving an order request for at least one product, the address invocation instruction is generated;

[0032] The response to the address call instruction based on the sorting result includes:

[0033] Select the address that best matches the current user behavior data based on the sorting results, and generate order confirmation information;

[0034] The order confirmation information is displayed.

[0035] Secondly, this application provides a display method, including:

[0036] Provide a display interface;

[0037] In the display interface, multiple addresses in the address list are displayed according to the sorting result; wherein, the sorting result is determined based on the matching degree between the multiple addresses and the current user behavior data.

[0038] Thirdly, this application provides an electronic device including a storage component and a processing component. The storage component stores one or more computer instructions. The one or more computer instructions are invoked and executed by the processing component to implement the control method as described in the first or second aspect above.

[0039] In this embodiment of the application, when an address call instruction is detected, the matching degree between the addresses in the address list and the current user behavior data is calculated. This allows multiple addresses in the address list to be reordered according to the matching degree. Then, the address call instruction is responded to according to the sorting result. Since the matching degree between multiple addresses and the current user behavior data can be determined according to the sorting result, calling the address accordingly is more in line with the user's current intent, thus enabling fast and accurate address calling.

[0040] These or other aspects of this application will become more apparent from the description of the following embodiments. Attached Figure Description

[0041] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0042] Figure 1 A flowchart of one embodiment of the control method provided in this application is shown;

[0043] Figure 2 A flowchart of an embodiment of a model training method provided in this application is shown;

[0044] Figure 3 A flowchart of one embodiment of a display method provided in this application is shown;

[0045] Figure 4a This illustration shows a scenario interaction diagram of an embodiment of this application in a practical application;

[0046] Figures 4b-4c The following are schematic diagrams illustrating the address list sorting process in a practical application according to embodiments of this application;

[0047] Figure 5 A schematic diagram of one embodiment of the control device provided in this application is shown;

[0048] Figure 6 This application provides a schematic diagram illustrating the structure of an embodiment of an electronic device.

[0049] Figure 7 A schematic diagram of another embodiment of an electronic device provided in this application is shown. Detailed Implementation

[0050] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.

[0051] In some of the processes described in the specification, claims, and accompanying drawings of this application, multiple operations appearing in a specific order are included. However, it should be clearly understood that these operations may not be executed in the order they appear herein, or may be executed in parallel. The operation numbers, such as 101, 102, etc., are merely used to distinguish different operations and do not themselves represent any execution order. Furthermore, these processes may include more or fewer operations, and these operations may be executed sequentially or in parallel. It should be noted that the descriptions such as "first," "second," etc., in this document are used to distinguish different messages, devices, modules, etc., and do not represent a chronological order, nor do they limit "first" and "second" to different types.

[0052] The technical solutions of this application embodiment can be applied to any scenario where an address is called based on an address list, such as displaying addresses in the address list or selecting an address from the address list. The technical solutions of this application embodiment can be applied to various e-commerce scenarios involving product delivery, such as O2O (Online To Offline), B2B (Business-to-Business), B2C (Business-to-Customer), C2B (Customer-to-Business), or C2C (Customer-to-Customer) e-commerce scenarios. For example, O2O e-commerce scenarios can include food delivery scenarios, where products are purchased online and delivered to the user's designated delivery address; or scenarios where products are purchased online and picked up offline, such as online group buying scenarios based on communities or other resident groups, where users purchase products online, the products are delivered to a system-designated pickup address, and the user picks them up offline at a designated pickup address.

[0053] Taking an O2O-based online food delivery scenario as an example, since users may place orders from different locations, such as home, office, hotel, and shopping mall, the address list becomes extremely long. During the development of this application, the inventors discovered that addresses in the address list are often sorted by their editing time, meaning the address the user actually wants might be listed later. This leads to users spending considerable time selecting a target address, increasing the time cost of selection. Furthermore, currently, when a user places an order for a product, an order confirmation is generated for confirmation. This confirmation, or on some product display pages, often automatically selects an address from the address list. This address is often the first address in the list, which is not necessarily the address the user wants. The user then needs to retrieve the address list and select again, making the automatic selection inaccurate and increasing the time spent on address selection. In conclusion, the inventors attribute the inability to quickly and accurately retrieve addresses to the address sorting method in the address list. Therefore, accurately sorting addresses in the address list is a key technical problem that needs to be solved to achieve fast and accurate address retrieval.

[0054] Accordingly, in order to achieve fast and accurate address retrieval, the inventors have proposed the technical solution of this application after a series of studies. In the embodiments of this application, when an address retrieval instruction is detected, the matching degree between the addresses in the address list and the current user behavior data is calculated. Thus, multiple addresses in the address list can be reordered according to the matching degree. Afterwards, the address retrieval instruction is responded to according to the sorting result. Since the matching degree between multiple addresses and the current user behavior data can be determined according to the sorting result, the address retrieval is more in line with the user's current intent. Therefore, fast and accurate address retrieval can be achieved, the user experience is improved, and the product conversion rate of the online platform is improved.

[0055] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0056] Figure 1 The flowchart illustrates an embodiment of a detection method provided in this application. The technical solution of this embodiment can be executed by a user terminal or by a server that has established a network connection with the user terminal. This application does not impose specific limitations on this. The method may include the following steps:

[0057] 101: Detect address call instruction.

[0058] As an optional approach, the address retrieval command can be generated upon detecting a user's action to retrieve the address list. In other words, when a user wants to search for the address list, triggering a corresponding action generates this address retrieval command. In a practical application, this address list retrieval action could occur after order confirmation information is output; if the address in the order confirmation information does not meet the user's needs, the user triggers an address modification action based on the order confirmation information. Alternatively, it could occur when a user browses a product's detailed product page. Since product detail pages often display address information and delivery times determined based on that address, if the address on the product detail page does not meet the user's needs, the user triggers an address modification action based on the product detail page.

[0059] As an alternative approach, the address retrieval instruction can be generated upon receiving an order request for at least one product. Upon receiving such a request, the system generates order confirmation information, which requires addresses from the address list. Therefore, an address retrieval instruction can be generated accordingly. The order confirmation information is used for user modification or confirmation. Currently, the address in the order confirmation information is usually the first address selected from the address list or a default address set by the user. However, these addresses may not necessarily meet the user's current order requirements. The technical solution of this application embodiment can solve this problem.

[0060] As another alternative, the address call instruction can be generated when a target page display request is received. The target page can be a product details page that contains address information. When a user wants to view the product details page of a product in actual application, the corresponding page display request can be triggered, thereby generating the address call instruction accordingly.

[0061] When the technical solution of this embodiment is executed by the server, the address call instruction can be generated by the user and sent to the server.

[0062] 102: Determine the degree of matching between multiple addresses in the address list and the current user behavior data.

[0063] Optionally, the current user behavior data may include one or more parameters such as current time, user characteristics, current user location, and product characteristics of the currently operated product.

[0064] The current time can refer to the time when the instruction to call this address was triggered; user characteristics can include user attributes and user profiles, such as gender and age, and user profiles can include product characteristics of user preferences, which can be obtained through big data statistical analysis; the current user location can refer to the current location of the user's device, which can be obtained through location services; the currently operated product can refer to the product that the user is currently browsing or the product that the user is currently requesting to order, and product characteristics can refer to the product category, such as clothing, shoes, cosmetics, etc.

[0065] Current user behavior data can reflect the current user's intent, so we can determine the current user behavior data first.

[0066] It is understood that the products referred to in the embodiments of this application exist online in the form of virtual objects, which correspond to physical entities offline. After a user purchases a product online, delivery is based on the physical entity. This will not be explained further below, and the products will be referred to as such.

[0067] If an address call instruction is detected, step 102 can be executed.

[0068] In addition, in practical applications, the addresses in the address list can be the delivery addresses provided by the user in advance. Of course, in some scenarios, such as online purchase of products and offline pickup, it can also refer to the pickup address selected by the user from the pickup addresses provided by the system. In the community group buying scenario, the pickup address can refer to the address of the group leader provided by the system. Users may conduct online group buying in different locations, thereby generating multiple pickup addresses and saving them in the address list.

[0069] 103: Reorder multiple addresses according to their matching degree.

[0070] 104: Response address call instruction based on sorting result.

[0071] Since current user behavior data reflects the current user's intent, the matching degree between addresses in the address list and the current user behavior data can be calculated to determine the degree to which the addresses match the current user's intent. Then, multiple addresses can be reordered according to the matching degree; optionally, they can be reordered in descending order of matching degree. A higher matching degree indicates that the address better matches the user's current intent, and the more likely the address is to be used. In the address list, addresses with higher matching degrees are placed before those with lower matching degrees, so that users can see addresses with higher matching degrees first when searching the address list. Finally, the address call command is responded to according to the sorting result.

[0072] As can be seen from the preceding text, as an optional method, when a user's operation to obtain the address list is detected and an address call instruction is generated, the response address call instruction packet based on the sorting result can be: displaying multiple addresses in the address list according to the sorting result.

[0073] For example, multiple addresses in the address list are displayed in descending order of their match with the current user behavior data. This allows users to see addresses with a higher match with their current behavior data first, meaning that addresses that match the user's current intent will be listed first. This makes it easier for users to quickly and accurately locate the target address and reduces the time spent selecting an address.

[0074] Currently, multiple addresses in the address list can also be displayed in ascending order of matching degree. If the user knows the sorting rules, the target address can still be determined quickly and accurately.

[0075] Optionally, multiple addresses in the address list can be displayed in the user's terminal display interface according to the sorting result.

[0076] As an alternative approach, when receiving an order request for at least one product and generating an address call instruction, the response to the address call instruction based on the sorting result can be: selecting the address with the highest matching degree to the current user behavior data according to the sorting result, generating order confirmation information, and displaying the order confirmation information.

[0077] The address that best matches the current user behavior data is the address that best reflects the user's current usage intent. Order confirmation information generated based on this address is more accurate, which can reduce the user's address modification operations, save address selection time, and achieve fast and accurate address retrieval.

[0078] Optionally, the order confirmation information can be displayed on the user's terminal display interface.

[0079] In addition, after displaying the order confirmation information, if an address modification operation is detected for that order confirmation information, multiple addresses in the address list can be displayed according to the sorting results.

[0080] As another optional approach, when a target page display request is received and an address call instruction is generated, the response to the address call instruction based on the sorting result can be: update the target page according to the address in the sorting result that has the highest matching degree with the current user behavior data; or display the target page.

[0081] The address that best matches the current user behavior data is the address that best reflects the user's current intent. Updating the target page based on this address can reduce the number of user address modification operations, save address selection time, and achieve fast and accurate address retrieval.

[0082] Alternatively, the target page can be displayed on the user's terminal display interface.

[0083] In addition, after displaying the target page, if an address modification operation targeting the target page is detected, multiple addresses in the address list can be displayed according to the sorting results.

[0084] In this embodiment, the addresses in the address list are reordered according to their matching degree with the current user behavior data. Based on the sorting result, the matching degree of multiple addresses with the current user behavior data can be determined. Calling the address accordingly is more in line with the user's current intent, thus enabling fast and accurate address calling, improving user experience, and helping to increase the product conversion rate of the online platform.

[0085] Furthermore, to meet the actual needs of different users, the method can support users in choosing whether to reorder the address list, allowing them to switch between a personalized address list and the original address list; therefore, in some embodiments, the method may further include:

[0086] Provide address sorting suggestions;

[0087] A user sorting request was detected; the address list is now set with sorting flags.

[0088] If a user cancels a request, the sorting flag in the address list can be removed.

[0089] Therefore, upon detecting an address call instruction, the data used to determine the current user behavior may include:

[0090] If an address call command is detected, check if there is a sorting mark in the address list. If so, determine the current user behavior data; otherwise, respond to the address call command directly in the original sorting order of the address list.

[0091] In some embodiments, determining the matching degree between multiple addresses in the address list and the current user behavior data may include:

[0092] By combining historical user behavior data corresponding to the historical usage records of multiple addresses, the matching degree between each address and the current user behavior data is determined.

[0093] By combining historical user behavior data corresponding to the historical usage records of multiple addresses, it can be determined that under the same or similar user behavior data, the address used in the past is most likely to be the address that is currently wanted to be used. Therefore, the matching degree between this address and the current user behavior data will be relatively high.

[0094] Historical usage records can refer to usage records within historical orders. Therefore, historical user behavior data can be the user behavior data corresponding to historical order data. This historical user behavior data may include, for example, the order generation time, product characteristics of the product corresponding to the order, user characteristics, and the order placement location; the order placement location refers to the user's location when the historical order was generated, i.e., the user's device location.

[0095] By combining historical user behavior data from multiple addresses, statistical analysis can be used to identify addresses with similar historical user behavior data that have a high degree of matching with the current user behavior data (e.g., a match score of 1), while other addresses have a match score of 0. For example, in an order placement scenario, user behavior data can include order time, product characteristics of the purchased product, and the current user's location. By analyzing historical user behavior data, addresses used by the user in the past when purchasing the same or similar products at the same or similar times and locations can be identified. These addresses have a high degree of matching with the current user behavior data and can be prioritized in the address list to save users time in selecting addresses, ultimately achieving fast and accurate address retrieval.

[0096] Furthermore, as another optional approach, to improve the accuracy of matching degree calculation and further ensure the accuracy of sorting results, thereby further improving the accuracy of address invocation, a matching model trained based on historical user behavior data corresponding to the historical usage records of multiple addresses can be used. This matching model can be used to calculate the matching degree between different addresses and the current user behavior data. Therefore, determining the matching degree between multiple addresses and the current user behavior data by combining the historical user behavior data in the historical usage records of multiple addresses includes:

[0097] A matching model trained using historical user behavior data corresponding to historical usage records of multiple addresses is used to determine the matching degree between multiple addresses in the address list and the current user behavior data.

[0098] like Figure 2 The diagram shows a flowchart of an embodiment of the model training method for this matching model, which may include the following steps:

[0099] 201: Retrieve historical order data.

[0100] 202: Determine the historical user behavior data corresponding to the historical order data and the order address used.

[0101] Historical user behavior data includes one or more of the following parameters: order generation time, product characteristics of the product corresponding to the order, user characteristics, and order placement location.

[0102] 203: Train a matching model based on historical behavior data and order addresses.

[0103] Optionally, the matching model can be implemented using a binary classification model, such as a traditional machine learning model or a deep learning model, such as logistic regression, support vector machine, feedforward neural network, etc.

[0104] The matching model, trained based on historical behavioral data and order addresses, can include:

[0105] Historical behavior data and corresponding order addresses are used as positive samples;

[0106] Replace the order address corresponding to the historical behavior data with an arbitrary address, and use the historical behavior data and the corresponding replacement address as negative samples;

[0107] The matching model is trained using both positive and negative samples.

[0108] Optionally, a matching model can be trained by using positive samples as model inputs and matching degree 1 as model labels, and negative samples as model inputs and matching degree 0 as model labels. This matching model can then be used to calculate the matching degree between addresses and user behavior data, with the value ranging from 0 to 1.

[0109] Therefore, by using a matching model trained on historical user behavior data corresponding to historical usage records of multiple addresses, the matching degree between multiple addresses in the address list and the current user behavior data can be determined as follows:

[0110] For each address in the address list, input the address and the current user behavior data into the matching model, and calculate the matching degree between the address and the current user behavior data.

[0111] This means that the matching model can be used to calculate the matching score between each address and the current user behavior data. When the model label is 1 or 0, the matching score is between 0 and 1. The higher the score, the greater the matching degree.

[0112] To further improve model training accuracy, historical user behavior data and addresses can be standardized. For example, the parameters in historical user behavior data can be converted into discrete features to facilitate data processing. For instance, order time can be represented as a date type and a time period type. The date type can include weekdays and holidays, while the time period type can include morning, noon, afternoon, evening, and late night. Address data can be converted into a string using the Geohash algorithm (a geocoding algorithm that encodes two-dimensional spatial latitude and longitude data into a string).

[0113] In addition, the parameters in the address and historical behavior data can be reduced in dimensionality first. For example, the discretized features obtained above can be mapped to a low-dimensional vector space using embedding technology to obtain the model input data, and then the model can be trained based on the obtained model input data.

[0114] In a practical application scenario, an address list can be used by a user to select a target address when placing an order for at least one product. Therefore, an address retrieval command can be used to trigger the display of the address list. For example... Figure 3 As shown in the illustration, this application embodiment also provides a display method, which can be executed by a user terminal. The method may include the following steps:

[0115] 301: Provides a display interface.

[0116] 302: In the display interface, multiple addresses in the address list are displayed according to the sorting results.

[0117] The sorting results are determined based on the matching degree between multiple addresses and the current user behavior data. The specific method for determining the matching degree can be found in the previous embodiments and will not be repeated here.

[0118] Optionally, the display interface can directly target the address list retrieval operation. Upon detecting the address list retrieval operation, an address retrieval instruction is generated. This instruction triggers the reordering of multiple addresses based on their matching degree with the current user behavior data, thereby obtaining a sorting result. The display interface can then show multiple addresses from the address list according to the sorting result.

[0119] Furthermore, in some embodiments, before displaying multiple addresses in the address list according to the sorting result in the display interface, the method may further include:

[0120] The order confirmation information is displayed on the screen.

[0121] In response to the address modification operation for the order confirmation information, an address retrieval instruction is generated; this address retrieval instruction is used to reorder multiple addresses based on their matching degree with the current user behavior data to obtain a sorting result.

[0122] Optionally, the address in the order confirmation information can be the address that best matches the current user behavior data, selected according to the sorting results.

[0123] Furthermore, in some embodiments, before displaying multiple addresses in the address list according to the sorting result in the display interface, the method may further include:

[0124] Display the target page in the display interface;

[0125] In response to an address modification operation targeting the page, an address invocation instruction is generated. This address invocation instruction is used to reorder multiple addresses based on their matching degree with the current user behavior data to obtain a sorting result.

[0126] Optionally, the address in the target page can be the address that best matches the current user behavior data, selected according to the sorting results.

[0127] In practical applications, the target page can refer to the product details page.

[0128] To facilitate a deeper understanding of the technical solution of this application, the following example illustrates a practical application scenario where a user selects and places an order, and requests an address list from the order confirmation information. The example also demonstrates how the user and server interact to sort the addresses. It should be noted that address sorting can also be performed by the user to reduce the amount of data on the server side. As shown in Figure 4, after receiving the order request from the user 402, the server 401 sends order confirmation information to the user 402.

[0129] The client detected a 402 error indicating a user's attempt to retrieve an address list, generated an address retrieval command, and sent it to the server. In practical applications, the user refers to the consumer.

[0130] After receiving the address adjustment instruction, the server 401 can determine the current user behavior data, determine the matching degree of multiple addresses in the address list with the current user behavior data, and reorder the multiple addresses according to the matching degree; then, it can send the reordered address list to the client 402.

[0131] The client-side 402 can display multiple addresses in the address list in the display interface according to the sorting result.

[0132] Afterwards, users can quickly and accurately locate the target address from the address list and send a confirmation request to the server based on that target address. The server can then generate an order based on that target address. The specific implementation of order generation is the same as the traditional method, and will not be elaborated further here.

[0133] like Figure 4b as well as Figure 4c The diagram illustrates the sorting process of the address list. The original sorting of multiple addresses in address list 41 is based on their editing time, from most recent to oldest. Addresses listed earlier are prioritized for exposure and viewing by the user. Using the technical solution of this application, based on the address call command, historical user behavior data from multiple dimensions, including time (i.e., order generation time), space (i.e., order location), product category (i.e., product characteristics), and user characteristics, combined with current user behavior data, can be used to determine the matching degree between each address and the current user behavior data. This matching degree is then used to re-sort the address list, resulting in the desired sorting. Figure 4cThe reordered address list 42 is determined using a matching method described above, which will not be repeated here. By calculating the matching degree, we can statistically identify addresses that have a high match degree with the user when purchasing similar products at similar times and locations in the past. For example, suppose the user most frequently uses Xixi Beiyuan when shopping on weekends; this address has the highest match degree with the current user behavior data and will be prioritized at the top. This address list 42 can then be displayed on the interface for the user to select from.

[0134] Figure 5 This is a schematic diagram of one embodiment of a control device provided in this application. The device may include:

[0135] Detection module 501 is used to detect address call instructions;

[0136] The determination module 502 is used to determine the matching degree between multiple addresses in the address list and the current user behavior data;

[0137] The sorting module 503 is used to reorder multiple addresses according to their matching degree;

[0138] Processing module 504 is used to respond to address call instructions based on sorting results.

[0139] In some embodiments, the determining module may be specifically used to combine the historical user behavior data corresponding to the historical usage records of the multiple addresses to determine the matching degree between the multiple addresses and the current user behavior data.

[0140] In some embodiments, the determining module may be specifically used to determine the matching degree between multiple addresses in the address list and the current user behavior data by using a matching model trained based on historical user behavior data corresponding to the historical usage records of the multiple addresses.

[0141] In some embodiments, the device may further include:

[0142] The model training module is used to acquire historical order data; determine the historical user behavior data corresponding to the historical order data and the order address used; and train a matching model based on the historical behavior data and the order address.

[0143] In some embodiments, the model training module trains the matching model based on the historical behavior data and the order address by: using the historical behavior data and the corresponding order address as positive samples; replacing the order address corresponding to the historical behavior data with an arbitrary address, and using the historical behavior data and the corresponding replacement address as negative samples; and training the matching model using the positive samples and the negative samples.

[0144] In some embodiments, the determining module may specifically target each address in the address list, input the address and the current user behavior data into the matching model, and calculate the matching degree between the address and the current user behavior data.

[0145] The historical user behavior data may include one or more of the following parameters: order generation time, product characteristics of the product corresponding to the order, user characteristics, and order placement location;

[0146] The current user behavior data may include one or more of the following parameters: current time, user characteristics, current user location, and product characteristics of the currently operated product.

[0147] In some embodiments, the device may further include:

[0148] The first generation module is used to detect the user's operation to obtain the address list and generate the address call instruction;

[0149] The processing module is specifically used to display the multiple addresses in the address list according to the sorting result.

[0150] In the model embodiment, the device may further include:

[0151] When the second generation module receives an order request for at least one product, it generates the address call instruction.

[0152] The processing module can be specifically used to select the address with the highest matching degree with the current user behavior data according to the sorting result, generate order confirmation information, and display the order confirmation information.

[0153] Figure 5 The control device can perform Figure 1 The implementation principle and technical effects of the control method described in the illustrated embodiments will not be repeated here. The specific methods by which each module and unit of the control device in the above embodiments performs its operations have been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0154] In one possible design, Figure 5 The control device shown in the embodiment can be implemented as an electronic device, such as... Figure 6 As shown, the electronic device may include a storage component 601 and a processing component 602;

[0155] Storage component 601 stores one or more computer instructions, wherein the one or more computer instructions are invoked and executed by processing component 602 to implement, for example... Figure 1 The control method shown.

[0156] Of course, electronic devices may also include other components, such as input / output interfaces and communication components.

[0157] Input / output interfaces provide interfaces between processing components and peripheral interface modules, which can be output devices, input devices, etc.

[0158] The communication components are configured to facilitate wired or wireless communication between computing devices and other devices.

[0159] The electronic device can be a physical device or an elastic computing host provided by a cloud computing platform. In this case, the computing device can refer to a cloud server, and the aforementioned processing components, storage components, etc., can be basic server resources rented or purchased from the cloud computing platform.

[0160] Of course, the electronic device can also refer to user terminal devices, such as mobile phones, tablets and other portable terminals.

[0161] Furthermore, embodiments of this application also provide a computer-readable storage medium storing a computer program, which, when executed by a computer, can perform the above-described functions. Figure 1 The control method of the embodiment shown.

[0162] In addition, this application embodiment also provides an information display device with a display interface that can display multiple addresses in an address list according to a sorting result; wherein the sorting result is determined based on the matching degree between the multiple addresses and the current user behavior data.

[0163] In one possible design, such as Figure 7 As shown in the figure, this application also provides an electronic device, which may include a storage component 701, a display component 702, and a processing component 703; the storage component 701 stores one or more computer program instructions; the one or more computer program instructions are to be called and executed by the processing component 703;

[0164] Processing component 703 provides a display interface via display component 702. The display interface shows multiple addresses from the address list according to a sorting result; wherein the sorting result is determined based on the matching degree between each address and the current user behavior data.

[0165] Of course, electronic devices may also include other components, such as input / output interfaces and communication components.

[0166] Input / output interfaces provide interfaces between processing components and peripheral interface modules, which can be output devices, input devices, etc.

[0167] The communication components are configured to facilitate wired or wireless communication between computing devices and other devices.

[0168] The electronic device can refer to a user terminal device, such as a mobile phone, tablet computer, or other portable terminal.

[0169] Furthermore, embodiments of this application also provide a computer-readable storage medium storing a computer program, which, when executed by a computer, can perform the above-described functions. Figure 3 The display method of the illustrated embodiment.

[0170] In the corresponding embodiments described above, the processing component may include one or more processors to execute computer instructions to complete all or part of the steps in the above-described method. Alternatively, the processing component may be implemented as one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above-described method.

[0171] Storage components are configured to store various types of data to support operations on the terminal. Storage components can be implemented from any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0172] The display component can be an electroluminescent (EL) element, a liquid crystal display or a microdisplay with a similar structure, or a retina-direct display or a similar laser scanning display.

[0173] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0174] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0175] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0176] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A control method, characterized in that, include: Detect address call instructions; The matching model is used to determine the degree of matching between multiple addresses in the address list and the current user behavior data. The multiple addresses are reordered according to the matching degree. The address call instruction is responded to based on the sorting result; The matching model is specifically trained as follows: acquire historical order data; determine the historical user behavior data corresponding to the historical order data and the order address used; use the historical user behavior data and the corresponding order address as positive samples; Replace the order address corresponding to the historical user behavior data with an arbitrary address, and use the historical user behavior data and the corresponding replacement address as negative samples; use the positive samples and the negative samples to train a matching model.

2. The method according to claim 1, characterized in that, The step of using a matching model to determine the matching degree between multiple addresses in the address list and the current user behavior data includes: For each address in the address list, the address and the current user behavior data are input into the matching model to calculate the matching degree between the address and the current user behavior data.

3. The method according to claim 1, characterized in that, The historical user behavior data includes one or more of the following parameters: order generation time, product characteristics of the product corresponding to the order, user characteristics, and order placement location; The current user behavior data includes one or more of the following parameters: current time, user characteristics, current user location, and product characteristics of the currently operated product.

4. The method according to claim 1, characterized in that, Also includes: Upon detecting a user's operation to retrieve the address list, the address retrieval instruction is generated; The response to the address call instruction based on the sorting result includes: The multiple addresses in the address list are displayed according to the sorting result.

5. The method according to claim 1, characterized in that, Also includes: Upon receiving an order request for at least one product, the address invocation instruction is generated; The response to the address call instruction based on the sorting result includes: Select the address that best matches the current user behavior data based on the sorting results, and generate order confirmation information; The order confirmation information is displayed.

6. A display method, characterized in that, include: Provide a display interface; In the display interface, multiple addresses in the address list are displayed according to the sorting result; wherein, the sorting result is determined by using a matching model to determine the matching degree between each of the multiple addresses in the address list and the current user behavior data, and then re-sorting the multiple addresses according to the matching degree; The matching model is specifically trained as follows: acquiring historical order data; determining the historical user behavior data and the order address used corresponding to the historical order data; using the historical user behavior data and the corresponding order address as positive samples; replacing the order address corresponding to the historical user behavior data with an arbitrary address, and using the historical user behavior data and the corresponding replacement address as negative samples; and training the matching model using the positive samples and the negative samples.

7. An electronic device, characterized in that, It includes a storage component and a processing component, wherein the storage component stores one or more computer instructions; the one or more computer instructions are invoked and executed by the processing component to implement the control method as described in any one of claims 1 to 5.

Images