Icon arrangement method and device, electronic equipment and storage medium

Abstract

The invention provides an icon arrangement method, and relates to the field of artificial intelligence, the field of finance or other fields. The method comprises the steps that in response to an icon arrangement request on a preset interface, historical behavior data of a user and reference data associated with the user are acquired under the condition of user authorization; obtaining a user feature vector based on the historical behavior data and the reference data; n combination feature vectors corresponding to the N icon combinations in a one-to-one mode are obtained, each icon combination comprises M icons, the icon combinations have different icon content or different icon sorting relations under the same image content, and both N and M are integers larger than or equal to 1; and recommending at least one candidate icon combination to the user based on the matching degree between the user feature vector and the N combined feature vectors. The invention further provides an icon arrangement device and equipment, a storage medium and a program product.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence, finance or other fields, and more specifically, to an icon organization method, device, equipment, medium and program product. Background Art

[0002] Intelligent interaction of desktop or software interface has become an important means to improve user experience and increase user stickiness, which can improve user experience and stickiness while meeting user needs. Intelligent interaction includes intelligent arrangement of icons.

[0003] In the related art, the user manually adjusts the position of at least one icon on the desktop or software interface to meet his / her usage needs. Alternatively, the icons are automatically sorted by the number of times the user clicks on each icon and the usage time of the corresponding service of each icon to replace the manual sorting by the user.

[0004] In the process of realizing the inventive concept of the present disclosure, the inventors found that the method of manually adjusting icons does not meet the requirements of intelligent interaction, while the method of automatically organizing icons only by historical usage times or duration is relatively lagging, unable to meet the users' current new needs, and unable to tap into and meet the users' potential needs. Summary of the invention

[0005] In view of the above problems, the present disclosure provides an icon organization method, apparatus, device, medium and program product.

[0006] One aspect of an embodiment of the present disclosure provides an icon organization method, comprising: in response to an icon organization request in a preset interface, obtaining a user's historical behavior data and reference data associated with the user with the user's authorization; obtaining a user feature vector based on the historical behavior data and the reference data; obtaining N combination feature vectors corresponding to N icon combinations, wherein each icon combination includes M icons, and each icon combination has a different icon content or a different icon sorting relationship under the same image content, and N and M are both integers greater than or equal to 1; and recommending at least one candidate icon combination to the user based on the degree of match between the user feature vector and the N combination feature vectors.

[0007] According to an embodiment of the present disclosure, before responding to an icon arrangement request in a preset interface, the method further includes: monitoring the user's first drag operation on any icon displayed in the preset interface; and confirming receipt of the icon arrangement request when the user's first drag distance of the dragged icon is greater than or equal to a first preset distance.

[0008] According to an embodiment of the present disclosure, if the user does not select any candidate icon combination, the method further includes: monitoring the user's second drag operation on any icon displayed in the preset interface; when the user's second drag distance of the dragged icon is greater than or equal to a second preset distance, confirming that the icon sorting request is received again, and re-recommending at least one candidate icon combination.

[0009] According to an embodiment of the present disclosure, the icon arrangement operation includes the first drag operation and / or the second drag operation, and the reference data includes the current icon sorting result of the preset interface in response to the icon arrangement operation; obtaining the user feature vector based on the historical behavior data and the reference data includes: obtaining the user feature vector based on the historical behavior data and the current icon sorting result.

[0010] According to an embodiment of the present disclosure, recommending at least one candidate icon combination to the user includes: inputting the user feature vector and N combination feature vectors into a pre-trained recommendation model to obtain N matching degrees; and recommending the at least one candidate icon combination based on the sizes of the N matching degrees.

[0011] According to an embodiment of the present disclosure, obtaining the user's historical behavior data includes: obtaining the user's historical usage data for each icon of the preset interface; and / or obtaining at least one icon searched in the user's historical search operations.

[0012] According to an embodiment of the present disclosure, obtaining reference data associated with the user includes: obtaining the current real-time location of the user; and determining at least one of other user information, merchant information, and recommended business information within a predetermined area around the real-time location.

[0013] According to an embodiment of the present disclosure, obtaining a user feature vector based on the historical behavior data and the reference data includes: determining a first weight coefficient based on the historical usage data and / or the at least one searched icon; determining a second weight coefficient based on at least one of the other user information, merchant information and recommended business information; and processing the historical behavior data and the reference data based on the first weight coefficient and the second weight coefficient, respectively, to obtain the user feature vector.

[0014] According to an embodiment of the present disclosure, before obtaining N combination feature vectors corresponding to N icon combinations, the method further includes: determining S first candidate icons based on the historical usage data and / or the at least one icon searched; determining K second candidate icons based on at least one of the other user information, business information, and recommended business information, where S and K are both integers greater than or equal to 1; and obtaining the N icon combinations based on the S first candidate icons and the K second candidate icons.

[0015] According to an embodiment of the present disclosure, each icon in any one of the N icon combinations serves as a corresponding business entrance, and the K second candidate icons are determined based on at least one of the following operations: determining at least one second candidate icon based on historical business transactions between the user and any other user in the predetermined area; determining at least one second candidate icon based on historical business transactions between the user and any merchant in the predetermined area; determining at least one second candidate icon based on historical business transactions between all users and any merchant in the predetermined area; determining at least one second candidate icon based on an association between any merchant in the predetermined area and a corresponding business of any icon in the N icon combinations; determining at least one second candidate icon based on an association between the user and a recommended business in the predetermined area.

[0016] Another aspect of an embodiment of the present disclosure provides an icon organization device, including: a data acquisition module, used to respond to an icon organization request in a preset interface, and obtain a user's historical behavior data and reference data associated with the user with the user's authorization; a user vector module, used to obtain a user feature vector based on the historical behavior data and the reference data; an icon vector module, used to obtain N combination feature vectors corresponding to N icon combinations, wherein each icon combination includes M icons, and each icon combination has a different icon content or a different icon sorting relationship under the same image content, and N and M are both integers greater than or equal to 1; a recommendation module, used to recommend at least one candidate icon combination to the user based on the matching degree between the user feature vector and the N combination feature vectors.

[0017] Another aspect of an embodiment of the present disclosure provides an electronic device, comprising: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors execute the method as described above.

[0018] Another aspect of the embodiments of the present disclosure further provides a computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, causes the processor to execute the method as described above.

[0019] Another aspect of the embodiments of the present disclosure further provides a computer program product, including a computer program, which implements the above method when executed by a processor.

[0020] One or more of the above embodiments have the following beneficial effects: based on the introduction of the user's historical behavior data, the reference data associated with it is further considered, and the user feature vector is matched with each combination feature vector at the granularity of the icon combination, and at least one candidate icon combination is recommended to the user for selection from the perspective of intelligent interaction and user needs. It is possible to automatically recommend products and services customized for each user through icon content and sorting based on the user's historical behavior data and reference data, dynamically and in real time meet the user's changing needs, and can also explore and meet the user's potential needs to improve the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The above contents and other objects, features and advantages of the present disclosure will become more apparent through the following description of the embodiments of the present disclosure with reference to the accompanying drawings, in which:

[0022] Figure 1 A diagram schematically shows an application scenario of the icon arrangement method according to an embodiment of the present disclosure;

[0023] Figure 2 A flowchart of an icon arrangement method according to an embodiment of the present disclosure is schematically shown;

[0024] Figure 3 Schematically shows a flow chart of confirming receipt of an icon arrangement request according to an embodiment of the present disclosure;

[0025] Figure 4 A flowchart of re-recommendation according to an embodiment of the present disclosure is schematically shown;

[0026] Figure 5 A flowchart of obtaining a user feature vector according to an embodiment of the present disclosure is schematically shown;

[0027] Figure 6 Schematically shows a flow chart of obtaining an icon combination according to an embodiment of the present disclosure;

[0028] Figure 7 A recommended flow chart according to an embodiment of the present disclosure is schematically shown;

[0029] Figure 8 A flowchart of an icon arrangement method according to another embodiment of the present disclosure is schematically shown;

[0030] Fig. 9 A schematic diagram of a structural block diagram of an icon arrangement device according to an embodiment of the present disclosure is shown; and

[0031] Fig.10 A block diagram of an electronic device suitable for implementing an icon organization method according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0032] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present disclosure. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0033] In the technical solution of the present invention, the user information (including but not limited to user personal information, user image information, user device information, such as location information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved are all information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data comply with the relevant laws, regulations and standards of relevant countries and regions, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0034] Figure 1 The following schematically shows an application scenario diagram of the icon arrangement method according to an embodiment of the present disclosure. It should be noted that: Figure 1 What is shown are merely examples to which the embodiments of the present disclosure can be applied, so as to help those skilled in the art understand the technical content of the present disclosure, but it does not mean that the embodiments of the present disclosure cannot be used in other devices, systems, environments or scenarios.

[0035] like Figure 1 As shown, the application scenario 100 according to this embodiment may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for a communication link between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0036] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only for example).

[0037] The terminal devices 101 , 102 , and 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, and desktop computers.

[0038] The server 105 may be a server that provides various services, such as a background management server (only an example) that provides support for websites browsed by users using the terminal devices 101, 102, and 103. The background management server may analyze and process the received data such as user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal device.

[0039] Server 105 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud computing, network services, and middleware services.

[0040] For example, an icon refers to an image used to represent an application or application service on the desktop or in a specific application interface. On the desktop of the terminal devices 101, 102, and 103, icons of applications such as user-side applications and web applications (abbreviated as APP in English) are displayed. For another example, in applications such as user-side applications and web applications, each interface is provided to display one or more icons. Whether it is an icon on the desktop or on the interface within the APP, it can respond to a user's click to enter a specific service, which can provide corresponding products and services. The preset interfaces involved in the present disclosure include the desktop and the interface within the APP.

[0041] It should be noted that the icon arrangement method provided in the embodiment of the present invention can be executed by the terminal device 101, 102, 103 or the server 105. Accordingly, the icon arrangement device provided in the embodiment of the present invention can generally be set in the terminal device 101, 102, 103 or the server 105.

[0042] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0043] The following will be based on Figure 1 The scene described by Figure 2 to Figure 8 The icon organization method of the embodiment of the present disclosure is described in detail.

[0044] Figure 2 The flowchart of the icon arrangement method according to the embodiment of the present disclosure is schematically shown.

[0045] like Figure 2 As shown, the icon arrangement method of this embodiment includes:

[0046] In operation S210, in response to an icon arrangement request in a preset interface, historical behavior data of the user and reference data associated with the user are obtained with the authorization of the user.

[0047] For example, in a terminal device, the preset interface can be the main interface (desktop) displayed after the terminal is turned on. The main interface can be a single screen that does not support left and right sliding, or it can be a multi-screen that supports left and right sliding. In an application, the preset interface can be the main interface of the APP, which provides icons corresponding to multiple services. The main interface can also support left and right sliding. Of course, when an icon sorting request is received, the preset interface can be a blank area or an icon can be displayed.

[0048] For example, the icon arrangement request can be triggered according to the user's instructions, such as long pressing a certain area in the preset interface, swiping a preset track in the preset interface, sliding with multiple fingers, or voice commands, etc. The icon arrangement request can also be automatically triggered, such as every time the terminal is turned on, the user sets a scheduled arrangement task, detects that the user moves to a predetermined location, or receives a push from the operator of the application.

[0049] In some embodiments, obtaining the user's historical behavior data includes: obtaining the user's historical usage data of each icon in the preset interface, and / or obtaining at least one icon searched in the user's historical search operation.

[0050] Historical behavior data may include a series of continuous operations within a predetermined time period in the past from the current moment, such as within a period of time (such as 5 minutes) when a user accesses an APP, he may click the balance query icon to enter the balance page, then exit the balance page and click the transfer icon, then enter the transfer page to transfer money, then exit the transfer page and click the fund icon, enter the fund page to buy funds, etc. Historical behavior data may also include discrete operations, such as the number of times a certain icon is clicked each month, or the situation of clicking various icons at a certain position.

[0051] In some embodiments, obtaining reference data associated with the user includes: obtaining the user's current real-time location and determining at least one of other user information, merchant information, and recommended business information within a predetermined area around the real-time location.

[0052] Reference data includes real-time data obtained after receiving an icon sorting request, which is used to analyze and determine the user's current needs and potential needs. The reference data associated with the user can be determined through the user's personal information, historical behavior data, current behavior time, and external environment information. The role of reference data is to provide real-time information input, so as to dynamically meet the user's real-time needs and tap into potential needs. The degree of association can be flexibly determined by manually or automatically setting rules in advance.

[0053] The real-time location can be, for example, the latitude and longitude of the user, which can be obtained through technical means such as GPS and Wi-Fi positioning. The predetermined area refers to a geographical range specified by the user, which can be a circular area, a rectangular area or an area of ​​a custom shape, such as setting a circular area with a radius of 500 meters. Other user information refers to the information of other users related to the user's current location, such as the user name, avatar, gender, historical behavior information and predicted real-time needs of other users with the authorization of other users. Merchant information refers to the information of merchants related to the user's current location, such as the merchant name, address, evaluation, services provided, etc. Recommended business information refers to business information recommended based on the user's current location and personal preferences.

[0054] Taking into account that users’ needs may change in different locations, the attributes of location information are added based on the user’s historical behavior information. This makes it possible to dynamically track the transfer and changes of the user’s geographic location during behavior, so that the user’s needs can be better mined and predicted based on the location information, providing accurate candidate icon combinations.

[0055] According to the embodiments of the present disclosure, information related to the user can be screened out through user location information, which is then combined with icon arrangement to affect the icon content and icon order recommended to the user, and provide icon combinations that meet the user's needs. Determining a predetermined area can limit the query range to the geographical area of ​​interest to the user according to the user's settings, thereby improving the relevance of information and user experience.

[0056] In operation S220, a user feature vector is obtained based on the historical behavior data and the reference data.

[0057] For example, historical behavior data and reference data are vectorized using word2vev algorithm, hot vector encoding and neural network extraction.

[0058] In operation S230, N combination feature vectors corresponding to N icon combinations are obtained, wherein each icon combination includes M icons, and the icon combinations have different icon contents or different icon sorting relationships under the same image content, and N and M are both integers greater than or equal to 1.

[0059] Each icon in the N icon combinations includes icons that have been displayed in the preset interface and / or icons that are not displayed in the preset interface. The N icon combinations can be obtained by exhaustively permuting and combining some icons, or by first obtaining icons with high similarity based on user feature vectors and then combining them. Each icon is a corresponding business entrance, and the combined feature vector can be obtained based on the introduction of the corresponding business of each icon. For example, in an icon combination, any icon obtains an icon vector based on the corresponding business introduction, and then all icon vectors are spliced ​​or input into a neural network model to obtain a combined feature vector.

[0060] In operation S240, at least one candidate icon combination is recommended to the user based on the matching degree between the user feature vector and the N combination feature vectors.

[0061] A candidate icon combination refers to a combination of several icons ranked high according to the matching degree, so as to recommend a group of candidate icon combinations matching the characteristics of the user according to the user's personality and preference, and provide a more personalized icon selection service.

[0062] Since the icons are automatically sorted and recommended to the user after receiving the icon arrangement request, the user can choose whether to accept a certain icon combination. If accepted, the icons are displayed on the preset interface after selection, which improves the convenience and efficiency of icon sorting compared to the prior art.

[0063] According to the embodiments of the present disclosure, based on the introduction of the user's historical behavior data, the reference data associated with it is further considered, and the user feature vector is matched with each combination feature vector at the granularity of the icon combination, and at least one candidate icon combination is recommended to the user for selection from the perspective of intelligent interaction and user needs. It is possible to automatically recommend products and services customized for each user through icon content and sorting based on the user's historical behavior data and reference data, dynamically and in real time meet the user's changing needs, and can also explore and meet the user's potential needs to improve the user experience.

[0064] Figure 3 The flowchart of confirming the receipt of an icon arrangement request according to an embodiment of the present disclosure is schematically shown.

[0065] Before responding to the icon arrangement request in the preset interface, Figure 3 As shown, this embodiment includes:

[0066] In operation S310, a first drag operation of a user on any icon displayed in a preset interface is monitored.

[0067] In operation S320, when a first dragging distance of the dragged icon by the user is greater than or equal to a first preset distance, it is confirmed that the icon arrangement request has been received.

[0068] The drag distance refers to the distance from the original position of the icon to the target position when the user long presses the icon and moves it. For example, if a user long presses an icon and moves it to another position, the distance of the movement is the drag distance. The first preset distance is a pre-set distance threshold used to determine whether the user really intends to sort the icons. When the distance the user drags the icon reaches or exceeds the first preset distance, the relevant operations of icon sorting will be performed.

[0069] For example, if the drag distance exceeds four icons, the smart sorting is activated, and if the drag distance is less than four icons (not including four), the smart sorting is not activated.

[0070] According to an embodiment of the present disclosure, by monitoring the user's dragging operation on the icon and judging based on the dragging distance, an icon arrangement request can be accurately triggered and confirmed.

[0071] Figure 4 The flowchart of re-recommendation according to an embodiment of the present disclosure is schematically shown.

[0072] If the user does not select any candidate icon combination, such as Figure 4 As shown, this embodiment includes:

[0073] In operation S410, a second drag operation of a user on any icon displayed in a preset interface is monitored.

[0074] The user can perform a drag operation by touching the screen and sliding a finger to drag the icon from one position to another. The second drag operation can be a second drag operation performed by the user on the same icon or another icon relative to the first drag operation.

[0075] In operation S420, when the second dragging distance of the dragged icon by the user is greater than or equal to the second preset distance, it is confirmed that the icon arrangement request is received again, and at least one candidate icon combination is re-recommended.

[0076] The second preset distance is a preset distance threshold, which is used to determine whether the user intends to reorganize the icons again, so as to realize the re-triggering and confirmation of the icon arrangement operation.

[0077] After activating smart sorting, if the user does not select any of the recommended candidate icon combinations and continues to drag the icons, the recommended results will continue to be recalculated and displayed based on the user's movement results until the user completes the icon movement operation.

[0078] By monitoring the user's second drag operation on the icon and judging the second drag distance, the icon sorting request can be triggered and confirmed again, and candidate icon combinations can be re-recommended to provide a more accurate icon sorting service.

[0079] It is understood that the first drag operation and / or the second drag operation include operations in which the user moves or rearranges icons by clicking, long pressing, and dragging them. For example, a user drags an application icon to another location on the screen. It may also include more complex operations such as creating folders, merging icons, etc. by clicking, long pressing, and dragging icons. For example, a user drags multiple application icons together to create a folder. The present disclosure is not limited to drag operations, and the position of icons may also be moved by voice commands, eye tracking, and the like.

[0080] In some embodiments, the icon arrangement operation includes a first drag operation and / or a second drag operation, and the reference data includes a current icon sorting result of a preset interface in response to the icon arrangement operation. Obtaining a user feature vector based on historical behavior data and reference data includes: obtaining a user feature vector based on historical behavior data and a current icon sorting result.

[0081] The current icon sorting result is used as reference data to reflect the real-time sorting operation results of the user on the icons. This result can reflect the user's current layout preferences and goals. By using the user feature vector as input, various optimization algorithms can be applied to further optimize the icon sorting results. For example, a machine learning algorithm can be used to predict user preferences and behaviors to better meet user needs.

[0082] According to the embodiments of the present disclosure, the order and layout of icons can be made more in line with the current expectations and habits of users, so that users can find the required services more quickly, thereby improving operation efficiency and convenience of use.

[0083] Figure 5 The flowchart of obtaining a user feature vector according to an embodiment of the present disclosure is schematically shown.

[0084] like Figure 5 As shown, this embodiment is one of the embodiments of operation S220, including:

[0085] In operation S510, a first weight coefficient is determined based on historical usage data and / or at least one searched icon.

[0086] Historical usage data refers to the user's past usage records and behavior data, including information such as which applications are used, how often they are used, and how long they are used. Searched icons refer to business icons that can be found through the search function. Users can find the business icons they need by entering keywords or performing voice searches.

[0087] Exemplarily, for each icon, a weight coefficient of a single icon is obtained according to the proportion of the historical usage or search frequency to the sum of the total historical usage frequency and the total search frequency, and then normalized and added to obtain a first weight coefficient.

[0088] In operation S520, a second weight coefficient is determined based on at least one of other user information, merchant information, and recommended service information.

[0089] Exemplarily, for each sample, including at least one of other users, merchants or recommended services, a corresponding weight coefficient is assigned according to the historical interaction data between each sample and the user, and then normalized and added to obtain a second weight coefficient. The historical interaction data may include data such as the number of transfers and the amount of transfers, and the weight coefficient may be assigned manually or automatically by pre-setting the allocation rules.

[0090] In operation S530, the historical behavior data and the reference data are processed based on the first weight coefficient and the second weight coefficient respectively to obtain a user feature vector.

[0091] For example, first, extract the historical behavior data and reference data respectively to obtain the historical feature vector and the reference feature vector. Then, multiply the historical feature vector by the first weight coefficient and multiply the reference feature vector by the second weight coefficient. Finally, concatenate the two multiplication results to obtain the user feature vector.

[0092] According to the setting of the first weight coefficient, the importance of the historical behavior data is emphasized or weakened to better reflect the user's behavior preference. By multiplying the second weight coefficient with the reference data, the weight of the reference data in the user feature vector can be adjusted to emphasize or weaken the importance of the reference data.

[0093] By using the first weight coefficient and the second weight coefficient to process the historical behavior data and the reference data, the user's historical behavior preferences and current behavior characteristics can be comprehensively considered. By flexibly adjusting the weights of the historical behavior data and the reference data in the user feature vector, the accuracy and effectiveness of personalized recommendations and services can be improved.

[0094] Figure 6 The flowchart of obtaining icon combination according to an embodiment of the present disclosure is schematically shown.

[0095] Before obtaining N combination feature vectors corresponding to N icon combinations one by one, such as Figure 6 As shown, this embodiment includes:

[0096] In operation S610, S first candidate icons are determined based on historical usage data and / or at least one searched icon.

[0097] In combination with the user's search behavior, the user's keywords, search result clicks, etc. during the search process can be analyzed to determine the icons related to the user's search intent. Based on the analysis of historical usage data and searched icons, icons related to the user's usage preferences and search intent are selected as the first candidate icons, for example, icons with higher usage frequency or search frequency are selected as the first candidate icons.

[0098] In operation S620 , K second candidate icons are determined based on at least one of other user information, merchant information, and recommended service information, where S and K are both integers greater than or equal to 1.

[0099] Collect other user information based on the use of the same application in a predetermined area. Collect information related to merchants in a predetermined area, including merchant type, merchant evaluation, and services provided by merchants. Collect popular recommendations, personalized recommendations, and services with high user evaluations.

[0100] Based on other collected user information, merchant information, and recommended business information, an algorithm or model is used for comprehensive analysis to determine an icon that matches the user's personal characteristics and recommendation preferences as the second candidate icon. For example, if the service provided by the merchant information is highly rated and the service is related to a certain business, then that business will be selected as the second candidate icon.

[0101] In operation S630, N icon combinations are obtained based on the S first candidate icons and the K second candidate icons.

[0102] Arrange and combine multiple first candidate targets and multiple second candidate targets. Consider the user's usage frequency, other users and merchant information and assign different weights to obtain different combinations. For example, in one combination, the merchant is given a heavy weight, and the related business is determined based on the services provided by the merchant, and its icon is placed in an important position. In another combination, the recommended business is given a heavy weight, and the icon of the recommended business is placed in an important position. The important position is not the first icon position, but is placed in a preset area based on the user's usage habits, such as an area that is easy for the user to click.

[0103] By considering the user's usage frequency and preferences, as well as the current information of other users and merchants, a more comprehensive and more matching candidate icon can be provided to each user to achieve personalized recommendations. Based on personalized recommendations and the determination of important locations, users can be guided to participate more in the use of the application, thereby improving user participation and stickiness.

[0104] In some embodiments, any icon in the N icon combinations is used as a corresponding service entry, and the K second candidate icons are determined based on at least one of the following operations:

[0105] At least one second candidate icon is determined based on historical business transactions between the user and any other user in the predetermined area. For example, if a user often transfers money with other users, an icon for the money transfer business can be used as the second candidate icon.

[0106] At least one second candidate icon is determined based on the historical business transactions between the user and any merchant in the predetermined area. For example, if a user often shops at a certain store or uses its services, the preferential services available at the merchant can be used as the second candidate icon.

[0107] At least one second candidate icon is determined based on the historical business transactions between all users and any merchant in the predetermined area. For example, if a merchant is often selected or visited by most users, the preferential business available in the merchant can also be used as the second candidate icon.

[0108] At least one second candidate icon is determined based on the correlation between any merchant in the predetermined area and the service corresponding to any icon in the N icon combinations. For example, if the service of a merchant is highly related to the preferential service corresponding to a certain icon, the icon can be used as the second candidate icon.

[0109] At least one second candidate icon is determined based on the association between the user and the recommended business in the predetermined area. For example, if the financial status and consumption habits of a user are highly matched with the loan business promoted by the bank branch in the predetermined area, the system can recommend the loan business to the user as the second candidate icon.

[0110] By considering the user's historical business dealings, the merchant's business dealings, the relevance of the business, and the relevance of the recommended business, a second candidate icon related to the icon combination is determined. From multiple dimensions, a more personalized and user-friendly second candidate icon can be provided, and a more personalized and user-friendly icon combination solution can be provided.

[0111] Figure 7 The recommended flow chart according to the embodiment of the present disclosure is schematically shown.

[0112] like Figure 7 As shown, this embodiment is one of the embodiments of operation S210, including:

[0113] In operation S710, the user feature vector and N combined feature vectors are input into a pre-trained recommendation model to obtain N matching degrees.

[0114] In operation S720, at least one candidate icon combination is recommended based on the magnitudes of the N matching degrees.

[0115] In some embodiments, for example, a single icon feature is extracted from the business content corresponding to each icon, and then spliced ​​into a combined feature vector. The recommendation model can be used to determine the sub-matching degree between the user feature vector and the single icon feature. The matching degree between each icon combination is obtained based on the sum of multiple sub-matching degrees.

[0116] In other embodiments, based on the following steps of data preprocessing, establishing and training a recommendation model, and deploying the recommendation model, the recommendation model is enabled to obtain N matching degrees.

[0117] Data preprocessing: Convert user historical behavior data and historical reference data into interaction matrix. Interaction matrix M∈R N×M Indicates the degree of interaction between user i and button combination j, where 0 indicates no interaction and 1 indicates interaction. For example, this process includes high-frequency services used by users in this APP, services that users search for multiple times inside and outside the APP, and main services promoted by the regional branch. By assigning adaptive weights to these three behaviors, the interaction behaviors and interaction degrees between users and button combinations can be summarized from a global perspective to obtain the interaction matrix.

[0118] Build and train recommendation models: You can build recommendation models based on content, collaborative filtering, and matrix decomposition. For example, solve the interaction matrix M into two low-rank matrices U∈R N×K and V∈R M×K The product of: M≈UV T . Among them, U represents the user feature vector matrix, V represents the combined feature vector matrix, and K represents the vector dimension, also known as the "latent feature". Since most matrices are sparse, regularization methods can be used to avoid overfitting, such as L1 regularization and L2 regularization. The model can be optimized using Mean Squared Error (MSE) as the loss function. On this basis, the Stochastic Gradient Descent (SGD) method is introduced for optimization during the training process.

[0119] Deploy the recommendation model: After the model training is completed, the user's historical behavior and current reference data can be used to predict the user's next action. Specifically, the user's historical behavior and current reference data are used to obtain the user's feature vector as input, and the recommendation model is used to calculate the matching value with each icon combination. The matching value is sorted according to the score size, and the first α icon combination solutions are recommended to the user. The above recommendation is based on the highest score. The first α (α≥1) icon combination solutions are recommended to the user.

[0120] According to an embodiment of the present disclosure, a recommendation algorithm is applied to an icon arrangement scenario, and a layout of icon rearrangement is automatically recommended from multiple dimensions to provide a more targeted service.

[0121] Figure 8 A flowchart of an icon organization method according to another embodiment of the present disclosure is schematically shown.

[0122] like Figure 8 As shown, the icon arrangement method of this embodiment includes:

[0123] In operation S801 , it is detected that a user long presses an icon.

[0124] In operation S802, the user completes the target icon movement.

[0125] In operation S803, it is determined whether the moving position is greater than four icon positions.

[0126] In operation S804, if yes, the smart sorting algorithm is activated.

[0127] In operation S805 , the background retrieves the input amount and executes the recommendation algorithm.

[0128] In some embodiments, for the input amount, when the user long presses the screen, the system is constructed from three perspectives: interface aesthetics, user experience, and banking services, and automatically recommends a layout for rearranging icons.

[0129] For example, the aesthetics of the interface is the overall aesthetic principle of designing the software interface. Icon styles and interactive interfaces are designed for different software arrangements. Based on these arrangements, the aesthetics of the icon arrangement can be ensured. Collect and analyze various types of user data. These data may include search keywords, browsing content, usage frequency, dwell time and other information. At the same time, retrieve the user's usage records and search records on the bank's online webpage, user terminal, mini-programs and offline outlets, retrieve the user's used services and potential services. Based on these data, from the user's perspective, user preferences and interests can be mined, so as to better make personalized recommendations. Based on the business needs of the time period, the main business position needs to be moved forward to promote the actual conversion of banking business.

[0130] For example, the high-frequency services used by users in the APP, the services that users searched for multiple times in and outside the APP (predicted services), and the main services recommended by the regional branch can be selected as input quantities. The frequency of occurrence of the three behaviors as input quantities usually has significant differences in the total number of times used. After regularizing the corresponding frequencies of these behaviors, they are normalized to weight coefficients under the same unit, and finally a differentiated weight branch is constructed.

[0131] For the recommendation system, matrix decomposition is selected as the system application algorithm. Matrix decomposition is an algorithm widely used in recommendation systems. It can decompose the user-button combination interaction matrix into the product of two low-rank matrices, thereby realizing the vector representation learning of the user and button combination. Based on this vector representation, the user's historical behavior and reference data can be used to predict the user's next action, which is represented by the icon combination that the user may use. The so-called next action is to place the icon that the user clicks next in the preset position.

[0132] In operation S806, the icon combination with the highest score is recommended.

[0133] The icon combination includes each icon, the icon sorting relationship and the coordinate information of each icon located in the preset interface.

[0134] In operation S807, the recommended sorting icons are displayed, that is, the result of operation S806. For example, a list is popped up on the preset interface, and the list provides several icon combination options for the user to select.

[0135] In operation S808, if the user does not select the recommended icon combination, it is detected whether the user continues to move the icons. If yes, the process jumps to operation S804, otherwise, the process ends.

[0136] In operation S809, if the user has not moved the icon more than 4 positions, it is detected whether the user continues to move the icon. If so, the process jumps to operation S802, otherwise, the intelligent recommendation is not displayed.

[0137] Taking the application of the icon organization method of any of the above embodiments on the main interface or other interfaces of the bank user terminal as an example, more intelligent and personalized services can be provided to users, thereby enhancing user stickiness and improving user satisfaction and loyalty.

[0138] First, products and services can be customized for the user's end page based on the user's historical data and preferences. Taking the smart investment advisor as an example, the recommendation system can recommend suitable investment portfolios and products to users based on factors such as the user's risk preference and investment goals. In this way, banks can provide more targeted services based on user needs, enabling users to obtain better investment returns, thereby increasing user loyalty and satisfaction.

[0139] Secondly, it can help banks increase cross-sales of users. By analyzing the user's purchase history, browsing history and other data, the recommendation system can recommend relevant products to users. For example, when a user transfers money on online banking or mobile banking, the recommendation system can automatically recommend icons corresponding to financial products or insurance products to the user. This can not only increase the bank's sales, but also provide users with more comprehensive and personalized financial services.

[0140] Finally, it can help banks optimize user experience. By analyzing user behavior data, the recommendation system can automatically identify user preferences and adjust the display method and content of the user-side page in a targeted manner. For example, when users often conduct transactions on mobile banking, the recommendation system can place transaction-related functions at the core of the page to facilitate user operations. This allows users to feel the bank's attention and caring service, thereby enhancing user stickiness.

[0141] In summary, application to bank user-end pages can bring multiple expected effects, including improving user experience, increasing user stickiness, and promoting sales.

[0142] Based on the above icon arrangement method, the present disclosure also provides an icon arrangement device. Fig. 9 The device is described in detail.

[0143] Fig. 9 The structural block diagram of the icon organization device according to an embodiment of the present disclosure is schematically shown.

[0144] like Fig. 9 As shown, the icon organizing device 900 of this embodiment includes a data acquisition module 910 , a user vector module 920 , an icon vector module 930 , and a recommendation module 940 .

[0145] The data acquisition module 910 may perform operation S210 for acquiring the user's historical behavior data and reference data associated with the user in response to an icon arrangement request in a preset interface and with the user's authorization.

[0146] The user vector module 920 may perform operation S220 for obtaining a user feature vector based on the historical behavior data and the reference data.

[0147] In some embodiments, the user vector module 920 may further perform operations S510 to S530, which will not be described in detail herein.

[0148] The icon vector module 930 can perform operation S230 to obtain N combination feature vectors corresponding to N icon combinations, where each icon combination includes M icons, and the icon combinations have different icon contents or different icon sorting relationships under the same image content, and N and M are both integers greater than or equal to 1.

[0149] In some embodiments, the icon vector module 930 may further perform operations S610 to S630, which will not be described in detail herein.

[0150] The recommendation module 940 may perform operation S240 for recommending at least one candidate icon combination to the user based on the matching degree between the user feature vector and the N combination feature vectors.

[0151] In some embodiments, the recommendation module 940 may further perform operations S710 to S740, which will not be described in detail herein.

[0152] In some embodiments, the icon arrangement device 900 may further include an icon arrangement request detection module, which may execute operations S310 to S320 and operations S410 to S420, which will not be described in detail herein.

[0153] The icon arrangement device 900 includes two parts for performing the above Figure 2 to Figure 8 A module for each step of any one of the described embodiments.

[0154] It should be noted that the implementation methods, technical problems solved, functions realized, and technical effects achieved of each module / unit / sub-unit in the device part embodiment are the same or similar to the implementation methods, technical problems solved, functions realized, and technical effects achieved of each corresponding step in the method part embodiment, and will not be repeated here.

[0155] According to an embodiment of the present disclosure, any multiple modules among the data acquisition module 910, the user vector module 920, the icon vector module 930, and the recommendation module 940 may be combined into one module for implementation, or any one of the modules may be split into multiple modules. Alternatively, at least part of the functions of one or more of these modules may be combined with at least part of the functions of other modules and implemented in one module.

[0156] According to an embodiment of the present disclosure, at least one of the data acquisition module 910, the user vector module 920, the icon vector module 930, and the recommendation module 940 may be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application-specific integrated circuit (ASIC), or may be implemented by hardware or firmware such as any other reasonable way of integrating or packaging the circuit, or implemented in any one of the three implementation methods of software, hardware, and firmware, or in an appropriate combination of any of them. Alternatively, at least one of the data acquisition module 910, the user vector module 920, the icon vector module 930, and the recommendation module 940 may be at least partially implemented as a computer program module, and when the computer program module is run, the corresponding function may be executed.

[0157] Fig.10 A block diagram of an electronic device suitable for implementing an icon organization method according to an embodiment of the present disclosure is schematically shown.

[0158] like Fig.10As shown, the electronic device 1000 according to an embodiment of the present disclosure includes a processor 1001, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage part 1008 into a random access memory (RAM) 1003. The processor 1001 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or a related chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 1001 may also include an onboard memory for caching purposes. The processor 1001 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0159] In RAM 1003, various programs and data required for the operation of electronic device 1000 are stored. Processor 1001, ROM 1002 and RAM 1003 are connected to each other via bus 1004. Processor 1001 performs various operations of the method flow according to the embodiment of the present disclosure by executing the program in ROM 1002 and / or RAM 1003. It should be noted that the program can also be stored in one or more memories other than ROM 1002 and RAM 1003. Processor 1001 can also perform various operations of the method flow according to the embodiment of the present disclosure by executing the program stored in one or more memories.

[0160] According to an embodiment of the present disclosure, the electronic device 1000 may further include an input / output (I / O) interface 1005, which is also connected to the bus 1004. The electronic device 1000 may further include one or more of the following components connected to the I / O interface 1005: an input portion 1006 including a keyboard, a mouse, etc. An output portion 1007 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc. A storage portion 1008 including a hard disk, etc. And a communication portion 1009 including a network interface card such as a LAN card, a modem, etc. The communication portion 1009 performs communication processing via a network such as the Internet. A drive 1010 is also connected to the I / O interface 1005 as needed. A removable medium 1011, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 1010 as needed, so that the computer program read therefrom is installed into the storage portion 1008 as needed.

[0161] The present disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments. It may also exist independently without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method according to the embodiment of the present disclosure is implemented.

[0162] According to an embodiment of the present disclosure, a computer-readable storage medium may be a non-volatile computer-readable storage medium, for example, may include but is not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, an apparatus or a device. For example, according to an embodiment of the present disclosure, a computer-readable storage medium may include the ROM 1002 and / or RAM 1003 described above and / or one or more memories other than ROM 1002 and RAM 1003.

[0163] The embodiment of the present disclosure also includes a computer program product, which includes a computer program, and the computer program contains program code for executing the method shown in the flowchart. When the computer program product is run in a computer system, the program code is used to enable the computer system to implement the method provided by the embodiment of the present disclosure.

[0164] The above functions defined in the system / device of the embodiment of the present disclosure are performed when the computer program is executed by the processor 1001. According to the embodiment of the present disclosure, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0165] In one embodiment, the computer program may rely on tangible storage media such as optical storage devices, magnetic storage devices, etc. In another embodiment, the computer program may also be transmitted and distributed in the form of signals on a network medium, and downloaded and installed through the communication part 1009, and / or installed from the removable medium 1011. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0166] In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 1009, and / or installed from the removable medium 1011. When the computer program is executed by the processor 1001, the above functions defined in the system of the embodiment of the present disclosure are performed. According to the embodiment of the present disclosure, the system, device, means, module, unit, etc. described above can be implemented by a computer program module.

[0167] According to an embodiment of the present disclosure, the program code for executing the computer program provided by the embodiment of the present disclosure can be written in any combination of one or more programming languages. Specifically, these computing programs can be implemented using high-level process and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, Java, C++, python, "C" language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on the remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect through the Internet).

[0168] It will be appreciated by those skilled in the art that the features described in the various embodiments and / or claims of the present disclosure may be combined and / or combined in a variety of ways, even if such combinations and / or combinations are not explicitly described in the present disclosure. In particular, the features described in the various embodiments and / or claims of the present disclosure may be combined and / or combined in a variety of ways without departing from the spirit and teachings of the present disclosure. All of these combinations and / or combinations fall within the scope of the present disclosure.

[0169] The embodiments of the present disclosure are described above. However, these embodiments are only for illustrative purposes and are not intended to limit the scope of the present disclosure. Although the embodiments are described above separately, this does not mean that the measures in the various embodiments cannot be used in combination to advantage. The scope of the present disclosure is defined by the attached claims and their equivalents. Without departing from the scope of the present disclosure, those skilled in the art may make a variety of substitutions and modifications, which should all fall within the scope of the present disclosure.

Claims

1. An icon arrangement method, comprising: In response to an icon arrangement request in a preset interface, obtaining historical behavior data of the user and reference data associated with the user with the authorization of the user; Obtaining a user feature vector based on the historical behavior data and the reference data; Obtain N combination feature vectors corresponding to N icon combinations, wherein each icon combination includes M icons, and each icon combination has different icon contents or different icon ordering relationships under the same image content, and N and M are both integers greater than or equal to 1; At least one candidate icon combination is recommended to the user based on the matching degree between the user feature vector and the N combination feature vectors.

2. The method according to claim 1, wherein: Before responding to the icon arrangement request on the preset interface, the method further includes: monitoring a first drag operation performed by the user on any icon displayed in the preset interface; When a first dragging distance of the dragged icon by the user is greater than or equal to a first preset distance, it is confirmed that the icon arrangement request has been received.

3. The method according to claim 2, wherein: If the user does not select any candidate icon combination, the method further includes: monitoring a second drag operation performed by the user on any icon displayed in the preset interface; When the second dragging distance of the dragged icon by the user is greater than or equal to the second preset distance, it is confirmed that the icon arrangement request is received again, and at least one candidate icon combination is re-recommended.

4. The method according to claim 2 or 3, wherein: The icon arrangement operation includes the first drag operation and / or the second drag operation, and the reference data includes a current icon sorting result of the preset interface in response to the icon arrangement operation; Obtaining a user feature vector based on the historical behavior data and the reference data includes: The user feature vector is obtained based on the historical behavior data and the current icon sorting result.

5. The method according to claim 1, wherein: Recommending at least one candidate icon combination to the user includes: Inputting the user feature vector and the N combined feature vectors into a pre-trained recommendation model to obtain N matching degrees; The at least one candidate icon combination is recommended based on the magnitudes of the N matching degrees.

6. The method according to claim 1, wherein: Obtaining historical user behavior data includes: Obtaining historical usage data of each icon of the preset interface by the user; and / or At least one icon searched in the historical search operation of the user is obtained.

7. The method according to claim 6, wherein: Acquiring reference data associated with the user includes: Obtaining the current real-time location of the user; At least one of other user information, business information, and recommended business information within a predetermined area around the real-time location is determined.

8. The method according to claim 7, wherein: Obtaining a user feature vector based on the historical behavior data and the reference data includes: determining a first weight coefficient based on the historical usage data and / or the searched at least one icon; Determine a second weight coefficient based on at least one of the other user information, the merchant information, and the recommended service information; The historical behavior data and the reference data are processed respectively based on the first weight coefficient and the second weight coefficient to obtain the user feature vector.

9. The method according to claim 8, wherein: Before obtaining N combination feature vectors corresponding to the N icon combinations one by one, the method further includes: Determine S first candidate icons based on the historical usage data and / or the at least one icon searched; Determine K second candidate icons based on at least one of the other user information, the merchant information, and the recommended business information, where S and K are both integers greater than or equal to 1; The N icon combinations are obtained based on the S first candidate icons and the K second candidate icons.

10. The method according to claim 9, wherein: Each icon in the N icon combinations is used as a corresponding service entrance, and the K second candidate icons are determined based on at least one of the following operations: Determine at least one second candidate icon based on historical business transactions between the user and any other user in the predetermined area; Determine at least one second candidate icon based on historical business transactions between the user and any merchant in the predetermined area; Determine at least one second candidate icon based on historical business transactions between all users and any merchant in the predetermined area; Determine at least one second candidate icon based on the association between any merchant in the predetermined area and the business corresponding to any icon in the N icon combinations; At least one second candidate icon is determined based on the association between the user and the recommended service in the predetermined area.

11. An icon arrangement device, comprising: A data acquisition module, for obtaining the user's historical behavior data and reference data associated with the user in response to an icon arrangement request in a preset interface and with the user's authorization; A user vector module, used to obtain a user feature vector based on the historical behavior data and the reference data; An icon vector module, used to obtain N combination feature vectors corresponding to N icon combinations, wherein each icon combination includes M icons, and each icon combination has different icon contents or different icon ordering relationships under the same image content, and N and M are both integers greater than or equal to 1; The recommendation module is used to recommend at least one candidate icon combination to the user based on the matching degree between the user feature vector and the N combination feature vectors.

12. An electronic device comprising: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors are enabled to execute the method according to any one of claims 1 to 10.

13. A computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, causes the processor to execute the method according to any one of claims 1 to 10.

Images