Resource object display method and apparatus, and device, storage medium and product

Abstract

The present application relates to a resource object display method and apparatus, and a computer device, a storage medium and a computer program product. The method comprises: in response to a trigger event of an account adjusting a display mode of resource objects in a financial client, acquiring account portrait information of the account (S101); inputting the account portrait information into a resource object recommendation model corresponding to an area where the account is located, and determining, by means of the resource object recommendation model, a target resource object recommended to the account in the financial client, wherein the resource object recommendation model is obtained by means of training on the basis of historical account portrait information of a historical account, and the historical account belongs to the area where the account is located (S102); and according to the target resource object, adjusting the display mode of the resource objects in the financial client of the account (S103). In the present application, required resource objects can be more accurately displayed for accounts in different areas, thereby avoiding frequent searching in a financial client, and effectively improving the efficiency of the acquisition of the resource objects.

Description

Resource object display method, device, equipment, storage medium and product

[0001] This application claims priority to the Chinese patent application filed with the China Patent Office on June 16, 2023, with application number 2023107180432, and application name “Resource Object Display Method, Device, Equipment, Storage Medium and Product”, all contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of financial software technology, and in particular to a resource object display method, apparatus, computer equipment, storage medium, and computer program product. Background Art

[0003] With the development of financial software technology, in order to make it easier for users in different regions to use financial clients, different application versions are often provided to users in different regions.

[0004] In related technologies, providing application versions for users in different regions mainly involves changes in regional languages. For example, a Chinese application version is provided for domestic users, while for overseas regions, targeted versions can be developed based on the language used in the corresponding region.

[0005] However, there are still many inconveniences in practice. Users in different regions still need to spend a lot of time to obtain the resource objects suitable for them in the application, and there is a problem of low efficiency in resource object acquisition.

[0006] Summary of the Invention

[0007] Based on this, it is necessary to provide a resource object display method, device, computer equipment, computer-readable storage medium and computer program product that can improve the efficiency of resource object acquisition in order to address the above technical problems.

[0008] In a first aspect, the present application provides a resource object display method. The method comprises:

[0009] In response to a triggering event in which an account adjusts the display manner of resource objects in a financial client, obtaining account profile information of the account;

[0010] Inputting the account profile information into a resource object recommendation model corresponding to the region where the account is located, and determining, by the resource object recommendation model, a target resource object recommended to the account in the financial client; wherein the resource object recommendation model is trained based on historical account profile information of historical accounts, and the historical accounts belong to the region where the account is located;

[0011] According to the target resource object, a display manner of the resource object in the financial client of the account is adjusted.

[0012] In one embodiment, before inputting the account profile information into a resource object recommendation model corresponding to the region where the account is located, the method further includes:

[0013] Determining a target client version corresponding to a target area from a plurality of pre-provided client versions; the plurality of client versions correspond to different areas respectively, and the target area is a selected area from the plurality of areas;

[0014] Historical account portrait information of historical accounts that have used the target client version is obtained, and based on the historical account portrait information, the initial model to be trained is trained to obtain a resource object recommendation model corresponding to the target area.

[0015] In one embodiment, before obtaining historical account portrait information of historical accounts that have used the target client version, the method further includes:

[0016] Identify candidate accounts that have used the target client version;

[0017] Based on the account location of each candidate account, a candidate account whose account location matches the target area is determined from the plurality of candidate accounts as a historical account corresponding to the target area.

[0018] In one embodiment, the historical account portrait information includes the operation data of the historical account on the resource object and the account characteristics of the historical account;

[0019] The training of the initial model to be trained based on the historical account portrait information to obtain a resource object recommendation model corresponding to the target area includes:

[0020] Based on the historical account operation data on the resource object and the account characteristics, the unsupervised model to be trained is trained to obtain a resource object recommendation model corresponding to the target area.

[0021] In one embodiment, there are multiple historical accounts;

[0022] The unsupervised model to be trained is trained based on the historical account operation data and account features of the resource object to obtain a resource object recommendation model corresponding to the target area, including:

[0023] determining a cluster center account serving as a cluster center from the plurality of historical accounts;

[0024] Clustering the plurality of historical accounts based on the cluster center account to obtain a plurality of account sets; the historical accounts belonging to the same account set have matching account characteristics and operation data;

[0025] Updating the cluster center account of each of the account sets, and returning to clustering the plurality of historical accounts based on the cluster center until a clustering end condition is met, and using the current cluster center of each account set as the target cluster center;

[0026] Based on each of the target cluster centers, a resource object recommendation model corresponding to the target area is determined; the resource object recommendation model is used to determine the account set to which the account belongs based on the similarity between the account and each of the target cluster centers, and to obtain the target resource object of the account based on the resource objects associated with the account set.

[0027] In one embodiment, determining the target resource object recommended to the account in the financial client by the resource object recommendation model includes:

[0028] Determining, by means of the resource object recommendation model, target resource objects recommended to the account in the financial client, and an attention priority of each target resource object in response to attention from the account;

[0029] The adjusting, according to the target resource object, the display manner of the resource object in the financial client of the account includes:

[0030] Based on the attention priority of each target resource object, a display priority of each target resource object is determined, and based on the display priority of each target resource object, a display mode of the resource object in the financial client of the account is adjusted.

[0031] In one embodiment, adjusting the display mode of the resource objects in the financial client of the account based on the display priority of each target resource object includes:

[0032] Determining a display priority of other resource objects among the resource objects, where the other resource objects are resource objects other than the target resource object, and the priority of the other resource objects is lower than the display priority of any of the target resource objects;

[0033] Determining a display format for each resource object based on the display priority of each target resource object and the display priority of each other resource object; the display format includes at least one of the following: a display position of the resource object in the functional interface of the financial client, and a sorting position of the resource object in a resource object list;

[0034] Each resource object is displayed in the financial client of the account according to its display form.

[0035] In a second aspect, the present application also provides a resource object display device. The device includes:

[0036] A portrait information acquisition module, configured to acquire account portrait information of an account in response to a triggering event in which an account adjusts the display manner of resource objects in a financial client;

[0037] a target resource object determination module, configured to input the account profile information into a resource object recommendation model corresponding to the region where the account is located, and determine, by the resource object recommendation model, a target resource object recommended to the account in the financial client; wherein the resource object recommendation model is trained based on historical account profile information of historical accounts belonging to the region;

[0038] A display module is used to adjust the display mode of the resource object in the financial client of the account according to the target resource object.

[0039] In a third aspect, the present application further provides a computer device. The computer device includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are performed:

[0040] In response to a triggering event in which an account adjusts the display manner of resource objects in a financial client, obtaining account profile information of the account;

[0041] Inputting the account profile information into a resource object recommendation model corresponding to the region where the account is located, and determining, by the resource object recommendation model, a target resource object recommended to the account in the financial client; wherein the resource object recommendation model is trained based on historical account profile information of historical accounts, and the historical accounts belong to the region;

[0042] According to the target resource object, a display manner of the resource object in the financial client of the account is adjusted.

[0043] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the following steps:

[0044] In response to a triggering event in which an account adjusts the display manner of resource objects in a financial client, obtaining account profile information of the account;

[0045] Inputting the account profile information into a resource object recommendation model corresponding to the region where the account is located, and determining, by the resource object recommendation model, a target resource object recommended to the account in the financial client; wherein the resource object recommendation model is trained based on historical account profile information of historical accounts, and the historical accounts belong to the region;

[0046] According to the target resource object, a display manner of the resource object in the financial client of the account is adjusted.

[0047] In a fifth aspect, the present application further provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the following steps:

[0048] In response to a triggering event in which an account adjusts the display manner of resource objects in a financial client, obtaining account profile information of the account;

[0049] Inputting the account profile information into a resource object recommendation model corresponding to the region where the account is located, and determining, by the resource object recommendation model, a target resource object recommended to the account in the financial client; wherein the resource object recommendation model is trained based on historical account profile information of historical accounts, and the historical accounts belong to the region;

[0050] According to the target resource object, a display manner of the resource object in the financial client of the account is adjusted.

[0051] The above-mentioned resource object display method, device, computer equipment, storage medium and computer program product can obtain the account portrait information of the account in response to a triggering event in which the account adjusts the display method of the resource objects in the financial client, and then the account portrait information can be input into the resource object recommendation model corresponding to the area where the account is located. The resource object recommendation model determines the target resource object recommended to the account in the financial client. The resource object recommendation model is trained based on the historical account portrait information of historical accounts, and the historical accounts belong to the area where the accounts are located. Then, the display method of the resource objects in the financial client of the account can be adjusted according to the target resource object. In the present application, by inputting the account portrait information of the account into the resource object recommendation model trained based on the historical account portrait information, it is possible to combine the usage of resource objects in the financial client by historical accounts in the same area to predict the target resource objects recommended to the account, so that the resource objects required by accounts in different areas can be displayed more accurately, avoiding frequent searches in the financial client, and effectively improving the efficiency of obtaining resource objects. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] FIG1 is a schematic diagram of a flow chart of a resource object display method according to an embodiment;

[0053] FIG2 is a flowchart illustrating steps for obtaining historical account profile information to train a resource object recommendation model in one embodiment;

[0054] FIG3 is a schematic flow chart of steps for training a clustering model according to an embodiment;

[0055] FIG4 is a flow chart showing steps for adjusting the display mode of resource objects in one embodiment;

[0056] FIG5 is a structural block diagram of a resource object display device according to an embodiment;

[0057] FIG6 is a diagram showing the internal structure of a computer device according to an embodiment;

[0058] FIG7 is a diagram showing the internal structure of another computer device according to an embodiment. DETAILED DESCRIPTION

[0059] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0060] In one embodiment, as shown in FIG1 , a resource object display method is provided. This embodiment uses the method applied to a financial client as an example for illustration, and the financial client can be deployed in a terminal. In this embodiment, the financial client can obtain the account portrait information of the account in response to the trigger time when the account adjusts the display mode of the resource objects in the financial client. The financial client can then input the account portrait information into the resource object recommendation model corresponding to the region where the account is located, and the resource object recommendation model determines the target resource object recommended to the account in the financial client; wherein, the resource object recommendation model is trained based on the historical account portrait information of historical accounts, and the historical accounts belong to the region where the accounts are located. Then, the financial client can adjust the display mode of the resource objects in the financial client of the account according to the target resource objects. Exemplarily, the terminal can be, but is not limited to, a personal computer, a laptop computer, a smart phone, a tablet computer, an Internet of Things device, and a portable wearable device.

[0061] It is understandable that the method can also be applied to a server, and can also be applied to a system including a terminal and a server, and implemented through the interaction between the terminal and the server. For example, after the financial client detects a trigger event in which the account adjusts the display mode of the resource objects in the financial client, the financial client can send a resource object recommendation request for the account to the server. After receiving the resource object recommendation request, the server can obtain the account portrait information of the account, input the account portrait information into the resource object recommendation model corresponding to the area where the account is located, and the resource object recommendation model determines the target resource object recommended to the account in the financial client, and returns the target resource object to the financial client. The financial client can adjust the display mode of the resource objects in the financial client of the account based on the target resource object.

[0062] In this embodiment, the method includes the following steps:

[0063] S101, in response to a triggering event in which an account adjusts the display manner of resource objects in a financial client, obtaining account portrait information of the account.

[0064] Among them, users can have corresponding accounts. In some optional embodiments, each user can obtain an account corresponding to each user based on the user's own identity identification, or can also obtain one or more accounts of each user based on one or more communication identifications (such as mobile phone numbers) of each user.

[0065] The account profile information of an account can be used to characterize the characteristics of the account, such as the characteristics of the inherent attributes of the account itself and the characteristics of the way the account uses the financial client. It should be emphasized that the account profile information in this application is information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data comply with the relevant laws, regulations and standards of the relevant countries and regions. The account profile information has been desensitized during use.

[0066] A financial client may be a client developed for financial services. A variety of resource objects may be provided within the financial client. In some optional embodiments, the resource objects may include at least one of the following: virtual resources (e.g., financial products, souvenirs, etc.), resource processing services (e.g., virtual resource balance inquiries, virtual resource transfers, etc.), and client function configuration settings specific to the financial client. Users may use one or more resource objects provided by the financial client to perform various transactions targeting virtual resources.

[0067] In a specific implementation, a user may log in to the financial client through his or her corresponding account, and the financial client may determine whether the current account has triggered a corresponding trigger event, which may indicate that the display method of the resource object in the financial client will be adjusted.

[0068] In some embodiments, the triggering event may include at least one of the following: launching a financial client, entering a designated function page in the financial client, and displaying multiple resource objects. The designated function in the financial client may be pre-configured by a developer or user. For example, if the financial client includes a first function page for credit cards and a second function page for lifestyle services, at least one of the first function page and the second function page may be designated as the designated function page.

[0069] When a financial client detects a trigger event, it can determine that multiple resource objects provided by the financial client will be displayed. In related art, the display of multiple resource objects in the financial client may be consistent for accounts in different regions, but the operation methods or usage habits of different accounts may vary. Therefore, in response to the detected trigger event, account profile information for the account can be obtained.

[0070] S102, input the account portrait information into the resource object recommendation model corresponding to the region where the account is located, and the resource object recommendation model determines the target resource object recommended to the account in the financial client; wherein the resource object recommendation model is trained based on the historical account portrait information of historical accounts, and the historical accounts belong to the region where the account is located.

[0071] [Corrected 15.12.2023 according to Rule 26] As an example, the region where the account is located can be a region divided according to customs or national borders, such as the countries in the European Union, the United Kingdom and Japan, or China; various financial institutions in the same region can provide resource objects that comply with financial regulatory rules to users in the region through financial clients based on the same financial regulatory rules.

[0072] In actual applications, there will be differences in the financial regulatory rules set by different regions or countries, which will result in different preferences for the same resource objects in the financial client among users in different regions. The present application can pre-train corresponding resource object recommendation models for different regions. The resource object recommendation model is based on the account portrait information of the historical account, that is, it is trained with the historical account portrait information. Since the historical account and the account belong to the same region, the historical account and the account select the resource objects provided by the financial institution in the financial client under the same financial regulatory rules. There is a correlation between the resource objects selected by the historical account and the resource objects that the account may select. The resource object recommendation model obtained by training with the historical account portrait information can more accurately predict the resource objects that the account may pay attention to.

[0073] Based on this, in this step, after obtaining the account portrait information of the account, the account portrait information can be input into the resource object recommendation model corresponding to the area where the account is located. The model determines the resource objects recommended to the account from the resource objects provided by the financial client as the target resource objects. The target resource objects can be one or more.

[0074] S103: Adjust the display mode of the resource object in the financial client of the account according to the target resource object.

[0075] Specifically, the target resource object can be a predicted commonly used resource object (that is, a resource object that the account may frequently use, and the frequency of use of the commonly used resource object is higher than a threshold). In order to facilitate the user to obtain the resource objects they need to use more conveniently and timely, the financial client can adjust the display method of the resource objects in the financial client of the account according to the target resource object.

[0076] In this embodiment, in response to a triggering event in which an account adjusts the display mode of resource objects in a financial client, the account portrait information of the account can be obtained, and then the account portrait information can be input into a resource object recommendation model corresponding to the region where the account is located. The resource object recommendation model determines the target resource object recommended to the account in the financial client. The resource object recommendation model is trained based on the historical account portrait information of historical accounts, and the historical accounts belong to the region where the accounts are located. Then, the display mode of resource objects in the financial client of the account can be adjusted according to the target resource object. In this application, by inputting the account portrait information of the account into the resource object recommendation model trained based on the historical account portrait information, it is possible to combine the usage of resource objects in the financial client by historical accounts in the same region to predict the target resource object recommended to the account, so that the resource objects required by accounts in different regions can be displayed more accurately, avoiding frequent searches in the financial client, and effectively improving the efficiency of obtaining resource objects.

[0077] In one embodiment, the resource object recommendation model can be constructed based on a convolutional neural network, wherein the architecture of the model can use a deep convolutional network structure, including convolutional layers, pooling layers, fully connected layers, etc.

[0078] In one embodiment, as shown in FIG2 , before inputting the account profile information into the resource object recommendation model corresponding to the region where the account is located, the present application may further include the following steps:

[0079] S201 , determining a target client version corresponding to a target area from a plurality of pre-provided client versions; the plurality of client versions correspond to different areas respectively, and the target area is a selected area from the plurality of areas.

[0080] In a specific implementation, when developing a financial client, developers can pre-configure different client versions for different regions, thereby obtaining multiple client versions of the financial client.

[0081] Then, the target area to be trained for the corresponding resource object recommendation model can be determined. The target area is a selected area among multiple areas. If there are multiple areas that need to train the corresponding resource object recommendation model, each area among the multiple areas can be used as an independent target area.

[0082] After the target region is determined, a client version corresponding to the target region may be obtained from multiple client versions as the target client version.

[0083] S202, obtaining historical account portrait information of historical accounts that have used the target client version, and training the initial model to be trained based on the historical account portrait information to obtain a resource object recommendation model corresponding to the target area.

[0084] In this step, the account profile information of historical accounts that have used the target client version can be obtained, and then the initial model is trained based on the historical account profile information. When the training end conditions are met, the current model is used as the resource object recommendation model corresponding to the target area. In some optional embodiments, the initial model to be trained may include an unsupervised model or a supervised model. In one embodiment, a supervised learning algorithm, such as a classification model (such as logistic regression, decision tree, random forest), can be used to construct a resource object recommendation model.

[0085] In this embodiment, by determining the target client version corresponding to the region, historical account portrait information of historical accounts associated with the region can be quickly and accurately obtained from the massive account information of the financial client, effectively improving the screening efficiency of the historical account portrait information.

[0086] In one embodiment, before S202, the present application may further include the following steps:

[0087] Determine candidate accounts that have used the target client version; and based on the account location of each candidate account, determine, from multiple candidate accounts, candidate accounts whose account location matches the target region as historical accounts corresponding to the target region.

[0088] As an example, the account location may be the account's permanent residence, which may be determined based on the account's pre-filled permanent address.

[0089] Specifically, each account that has used the target client version can be determined as multiple candidate accounts. In actual applications, there are cases where the account using the target client version is not in the target area, such as a domestic user using an overseas version of a financial client.

[0090] Based on this, after obtaining multiple candidate accounts, the account location of each candidate account can be determined, and the candidate accounts whose account location matches the target area (for example, the account location is within the range of the target area) are regarded as historical accounts.

[0091] In this embodiment, the candidate accounts that have used the target client version can be further screened by account location, thereby effectively improving the reliability and accuracy of the historical accounts ultimately obtained.

[0092] In some other embodiments, if the client version provided by the financial client is used by multiple different regions at the same time, for example, a financial client developed by a financial institution in China provides two client versions, a domestic version and an overseas version, then the overseas version will be used by users in multiple different regions; in response to this situation, the client version associated with the target region can be determined. In addition to being used by candidate accounts in the target region, this client version will also be used by candidate accounts in other regions. At this time, the account location of each candidate account can be used for screening to obtain historical accounts.

[0093] In one embodiment, historical account profile information may include historical account operation data on resource objects and account characteristics of the historical account. For example, historical account operation data on resource objects may include at least one of the following: number of clicks, click frequency, and number of uses; and account characteristics may include at least one of the following: desensitized identity identifier, desensitized user name, and desensitized contact information.

[0094] It can be understood that the account portrait information of the accounts involved in steps S101-S103 may include some or all types of historical account portrait information. The specific account portrait information can be referred to the above description and will not be repeated here.

[0095] Accordingly, S202 trains the initial model to be trained based on the historical account profile information to obtain a resource object recommendation model corresponding to the target area, which may include the following steps:

[0096] Based on the historical account operation data and account characteristics of resource objects, the unsupervised model to be trained is trained to obtain a resource object recommendation model corresponding to the target area.

[0097] In this step, the unsupervised model to be trained can be trained based on historical account operation data on resource objects and the account characteristics of the historical accounts. By using historical account operation data and account characteristics for unsupervised training, it can effectively save manual labeling time and facilitate the efficient and rapid training of corresponding resource object recommendation models for different regions.

[0098] In one embodiment, there are multiple historical accounts, and the unsupervised model may be a clustering model. As shown in FIG3 , based on the historical account operation data on resource objects and account features, the unsupervised model to be trained is trained to obtain a resource object recommendation model corresponding to the target area, which may include the following steps:

[0099] S301: Determine a cluster center account serving as a cluster center from multiple historical accounts.

[0100] Specifically, after obtaining multiple historical accounts, multiple historical accounts can be randomly determined from the historical accounts, and the randomly determined multiple historical accounts are used as cluster centers, thereby obtaining multiple cluster center accounts.

[0101] S302 , clustering multiple historical accounts based on a cluster center account to obtain multiple account sets; historical accounts belonging to the same account set have matching account features and operation data.

[0102] After determining multiple cluster center accounts, multiple historical accounts can be clustered. For example, the distance between each historical account and each cluster center account can be determined, and each historical account can be divided into the account set corresponding to the cluster center account with the smallest distance. In this way, multiple account sets can be obtained, each account set includes at least one historical account, and each historical account in each account set can have matching (identical or similar) account characteristics and operation data.

[0103] S303, updating the cluster center account of each account set, and returning to execute clustering of multiple historical accounts based on the cluster center until the clustering end condition is met, and using the current cluster center of each account set as the target cluster center.

[0104] Then, for each account set, the cluster center account for that account set can be re-determined based on the account characteristics and operation data of each historical account in the account set to obtain an updated cluster center account. The process then returns to step S302 until the clustering termination condition is met, such as when the cluster center account no longer changes or the number of iterations meets a preset condition. At this point, the cluster center for each account set can be used as the target cluster center.

[0105] S304, based on each target cluster center, determine the resource object recommendation model corresponding to the target area; the resource object recommendation model is used to determine the account set to which the account belongs based on the similarity between the account and each target cluster center, and obtain the target resource object of the account based on the resource objects associated with the account set.

[0106] In practical applications, after obtaining the target cluster center associated with each account, a resource object recommendation model can be derived based on each target cluster center. Specifically, for the multiple account sets clustered during the training process, a corresponding resource object can be associated with each account set. In an optional embodiment, the resource objects associated with the account set can be determined based on the historical operation data frequently performed on the resource objects by each account in the account set. In some embodiments, the attention priority of each resource object associated with the account set can also be determined based on the historical account operation data.

[0107] Furthermore, when the resource object recommendation model obtains the account portrait information of a new account, it can determine the similarity between the account and each target cluster center based on the operation data and account characteristics in the account portrait information, and determine the account set to which the account belongs based on each similarity. For example, the account set corresponding to the target cluster center with the highest similarity can be used as the account set to which the account belongs. Then, based on the resource objects associated with the account set, the target resource object of the account can be obtained and output as the prediction result of the resource object recommendation model.

[0108] In this embodiment, the historical account portrait information and account features of the historical accounts can be used to perform unsupervised training on the clustering model, so that the resource object recommendation model can be quickly obtained.

[0109] In one embodiment, determining the target resource object recommended to the account in the financial client by the resource object recommendation model may include the following steps:

[0110] The target resource objects recommended to the account in the financial client and the attention priority of each target resource object by the account are determined through the resource object recommendation model.

[0111] The attention priority may represent the possibility of using or acquiring the corresponding target resource object. The higher the attention priority, the greater the possibility that the account may use or acquire the corresponding target resource object.

[0112] In step S103, adjusting the display mode of the resource object in the financial client of the account according to the target resource object may include the following steps:

[0113] Based on the attention priority of each target resource object, the display priority of each target resource object is determined, and based on the display priority of each target resource object, the display method of the resource object in the financial client of the account is adjusted.

[0114] The display priority may represent the degree of prominence or emphasis when displaying the corresponding resource object. The higher the display priority, the more prominent the resource object.

[0115] In a specific implementation, the attention priority of each target resource object can be determined as the display priority of each target resource object. Since the multiple resource objects provided by the financial client include the target resource object, the display method of the multiple resource objects in the financial client can be adjusted according to the display priority of the target resource object.

[0116] In this embodiment, the display priority of each target resource object can be determined, and the display method of different resource objects in the financial client can be adjusted in combination with the display priority, so that when the user browses multiple resource objects displayed in the financial client, the user can locate the target resource object more quickly and efficiently among a large number of resource objects through the adjusted display method.

[0117] In one embodiment, as shown in FIG4 , adjusting the display mode of resource objects in the financial client of the account based on the display priority of each target resource object may include:

[0118] S401 : Determine the display priority of other resource objects in the resource objects. The other resource objects are resource objects other than the target resource object. The priority of the other resource objects is lower than the display priority of any target resource object.

[0119] Specifically, after obtaining the target resource object, the multiple resource objects provided by the financial client can be divided into the target resource object and other resource objects. After determining the display priority of each target resource object, the display priority of each other resource object can be configured based on the display priority of the other resource objects, so that the display priority of each other resource object is lower than the priority of each target resource object. The display priority among multiple other resource objects can be determined based on the number of times each other resource object is used in the financial client, or can also be determined based on business needs, or of course, can also be determined randomly.

[0120] S402: Determine the display format of each resource object based on the display priority of each target resource object and the display priority of each other resource object.

[0121] The display form includes at least one of the following: the display position of the resource object in the financial client function interface, and the sorting position of the resource object in the resource object list.

[0122] After obtaining the display priorities of the target resource object and other resource objects, the display form of each resource object can be determined according to the display priorities.

[0123] For example, if the display format includes display location, the attention level of each display location can be determined. The higher the display priority of a resource object, the higher the display position of the resource object. If the display format includes the sorting position of the resource object in the resource object list, the higher the display priority, the higher the sorting position of the resource object.

[0124] S403: Display each resource object in the financial client of the account according to its display format.

[0125] After determining the display format of each resource object, each resource object can be displayed in the financial client of the account according to the adjusted display format.

[0126] In this embodiment, the display form of resource objects in the financial client can be adaptively adjusted according to the display priority, so that users can more quickly browse resource objects that the users may use or pay attention to.

[0127] In order to enable those skilled in the art to better understand the above steps, the embodiment of the present application is illustrated below by using an example, but it should be understood that the embodiment of the present application is not limited to this.

[0128] In practical applications, a financial client developed by a financial institution can be used by accounts belonging to different regions. For example, accounts belonging to Regions A, B, and C, which are divided by customs territory, can all use the financial client. The financial client provides multiple resource objects. For example, the multiple resource objects may include resource objects for the following categories: credit cards, bank accounts, remittances, and personal settings.

[0129] For each region, a corresponding resource object recommendation model can be trained in advance for the region. When training the resource object recommendation model corresponding to the region, historical account portrait information of multiple historical accounts belonging to the region can be obtained, such as the click behavior data of historical accounts on different resource objects in the financial client, the usage data of resource objects, and the account attribute information of historical accounts; then, the clustering model can be trained using the historical account portrait information of the region, and the resource object recommendation model can be obtained after the training is completed.

[0130] Then, when account M logs in to its financial client, the financial client can identify account M as a user in region A. It can then obtain account M's account profile information and input it into the resource object recommendation model corresponding to region A. The model outputs the display priority of multiple resource objects. For example, the display priority from high to low can be: credit card, transfer and remittance, personal settings, and bank account. Of course, in other embodiments, the resource object recommendation model can also be embedded in the list query of resource objects, so that when the account queries resource objects, the resource objects that the account is interested in are displayed first, realizing personalized recommendations.

[0131] In this way, users can quickly obtain resource objects that they are interested in or may need to use in the financial client, thereby improving the efficiency of resource object acquisition and enhancing the stickiness between users and the financial client.

[0132] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0133] Based on the same inventive concept, embodiments of the present application also provide a resource object display device for implementing the resource object display method described above. The implementation solution provided by this device is similar to the implementation solution described in the above method. Therefore, the specific limitations of one or more resource object display device embodiments provided below can be found in the above-mentioned limitations of the resource object display method and will not be repeated here.

[0134] In one embodiment, as shown in FIG5 , a resource object display device is provided, including:

[0135] A portrait information acquisition module 501 is configured to acquire account portrait information of an account in response to a triggering event in which an account adjusts the display mode of resource objects in a financial client;

[0136] A target resource object determination module 502 is configured to input the account profile information into a resource object recommendation model corresponding to the region where the account is located, and determine, by the resource object recommendation model, a target resource object recommended to the account in the financial client; wherein the resource object recommendation model is trained based on historical account profile information of historical accounts belonging to the region where the account is located;

[0137] The display module 503 is configured to adjust the display mode of the resource object in the financial client of the account according to the target resource object.

[0138] In one embodiment, the apparatus further comprises:

[0139] a target version determination module, configured to determine a target client version corresponding to a target region from a plurality of pre-provided client versions; the plurality of client versions respectively correspond to different regions, the target region being a selected region from the plurality of the regions;

[0140] The model training module is used to obtain historical account portrait information of historical accounts that have used the target client version, and based on the historical account portrait information, train the initial model to be trained to obtain a resource object recommendation model corresponding to the target area.

[0141] In one embodiment, the apparatus further comprises:

[0142] a candidate account determination module, configured to determine candidate accounts that have used the target client version;

[0143] The historical account screening module is configured to determine, based on the account location of each candidate account, a candidate account whose account location matches the target area from among the plurality of candidate accounts as a historical account corresponding to the target area.

[0144] In one embodiment, the historical account portrait information includes the operation data of the historical account on the resource object and the account characteristics of the historical account;

[0145] The model training module is used to:

[0146] Based on the historical account operation data on the resource object and the account characteristics, the unsupervised model to be trained is trained to obtain a resource object recommendation model corresponding to the target area.

[0147] In one embodiment, there are multiple historical accounts;

[0148] The model training module is used to:

[0149] determining a cluster center account serving as a cluster center from the plurality of historical accounts;

[0150] Clustering the plurality of historical accounts based on the cluster center account to obtain a plurality of account sets; the historical accounts belonging to the same account set have matching account characteristics and operation data;

[0151] Updating the cluster center account of each of the account sets, and returning to clustering the plurality of historical accounts based on the cluster center until a clustering end condition is met, and using the current cluster center of each account set as the target cluster center;

[0152] Based on each of the target cluster centers, a resource object recommendation model corresponding to the target area is determined; the resource object recommendation model is used to determine the account set to which the account belongs based on the similarity between the account and each of the target cluster centers, and to obtain the target resource object of the account based on the resource objects associated with the account set.

[0153] In one embodiment, the target resource object determination module 502 is configured to:

[0154] Determining, by means of the resource object recommendation model, target resource objects recommended to the account in the financial client, and an attention priority of each target resource object in response to attention from the account;

[0155] The display module 503 is used to:

[0156] Based on the attention priority of each target resource object, a display priority of each target resource object is determined, and based on the display priority of each target resource object, a display mode of the resource object in the financial client of the account is adjusted.

[0157] In one embodiment, the display module 503 is used to:

[0158] Determining a display priority of other resource objects among the resource objects, where the other resource objects are resource objects other than the target resource object, and the priority of the other resource objects is lower than the display priority of any of the target resource objects;

[0159] Determining a display format for each resource object based on the display priority of each target resource object and the display priority of each other resource object; the display format includes at least one of the following: a display position of the resource object in the functional interface of the financial client, and a sorting position of the resource object in a resource object list;

[0160] Each resource object is displayed in the financial client of the account according to its display form.

[0161] Each module in the resource object display device can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in the computer device in the form of software, so that the processor can call and execute the corresponding operations of each module.

[0162] In one embodiment, a computer device is provided, which may be a terminal. Its internal structure diagram may be shown in FIG6 . The computer device includes a processor, memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are connected to the system bus via the input / output interface. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The input / output interface of the computer device is configured to exchange information between the processor and an external device. The communication interface of the computer device is configured to communicate with an external terminal via wired or wireless communication, where the wireless communication may be achieved via Wi-Fi, a mobile cellular network, NFC (near field communication), or other technologies. When executed by the processor, the computer program implements a method for displaying resource objects. The display unit of the computer device is configured to produce a visually visible image and may be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device casing, or an external keyboard, touchpad or mouse.

[0163] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be shown in Figure 7. The computer device includes a processor, a memory, an input / output interface (I / O), and a communication interface. The processor, memory, and I / O interface are connected via a system bus, and the communication interface is connected to the system bus via the I / O interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store account profile information. The I / O interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, it implements a resource object display method.

[0164] Those skilled in the art will understand that the structures shown in Figures 6 and 7 are merely block diagrams of partial structures related to the solution of the present application, and do not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figures, or combine certain components, or have a different component arrangement.

[0165] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0166] In response to a triggering event in which an account adjusts the display manner of resource objects in a financial client, obtaining account profile information of the account;

[0167] Inputting the account profile information into a resource object recommendation model corresponding to the region where the account is located, and determining, by the resource object recommendation model, a target resource object recommended to the account in the financial client; wherein the resource object recommendation model is trained based on historical account profile information of historical accounts, and the historical accounts belong to the region where the account is located;

[0168] According to the target resource object, a display manner of the resource object in the financial client of the account is adjusted.

[0169] In one embodiment, when the processor executes the computer program, the steps in the other embodiments described above are also implemented.

[0170] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0171] In response to a triggering event in which an account adjusts the display manner of resource objects in a financial client, obtaining account profile information of the account;

[0172] Inputting the account profile information into a resource object recommendation model corresponding to the region where the account is located, and determining, by the resource object recommendation model, a target resource object recommended to the account in the financial client; wherein the resource object recommendation model is trained based on historical account profile information of historical accounts, and the historical accounts belong to the region where the account is located;

[0173] According to the target resource object, a display manner of the resource object in the financial client of the account is adjusted.

[0174] In one embodiment, when the computer program is executed by a processor, the steps in the other embodiments described above are also implemented.

[0175] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0176] In response to a triggering event in which an account adjusts the display manner of resource objects in a financial client, obtaining account profile information of the account;

[0177] Inputting the account profile information into a resource object recommendation model corresponding to the region where the account is located, and determining, by the resource object recommendation model, a target resource object recommended to the account in the financial client; wherein the resource object recommendation model is trained based on historical account profile information of historical accounts, and the historical accounts belong to the region where the account is located;

[0178] According to the target resource object, a display manner of the resource object in the financial client of the account is adjusted.

[0179] In one embodiment, when the computer program is executed by a processor, the steps in the other embodiments described above are also implemented.

[0180] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions.

[0181] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processor involved in the various embodiments provided herein may be, but are not limited to, a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, and the like.

[0182] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0183] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A resource object display method, comprising: In response to a triggering event in which an account adjusts the display manner of resource objects in a financial client, obtaining account profile information of the account; Input the account portrait information into a resource object recommendation model corresponding to the region where the account is located, and determine the target resource object recommended to the account in the financial client by the resource object recommendation model; wherein the resource object recommendation model is trained based on historical account portrait information of historical accounts, and the historical accounts belong to the region where the account is located; According to the target resource object, the display mode of the resource object in the financial client of the account is adjusted.

2. The method according to claim 1, further comprising: Before inputting the account portrait information into the resource object recommendation model corresponding to the region where the account is located, Determining a target client version corresponding to a target area from a plurality of client versions provided in advance; the plurality of client versions correspond to different areas respectively, and the target area is a selected area among the plurality of areas; The historical account portrait information of the historical accounts that have used the target client version is obtained, and based on the historical account portrait information, the initial model to be trained is trained to obtain a resource object recommendation model corresponding to the target area.

3. The method according to claim 2, further comprising: Before obtaining the historical account portrait information of the historical accounts that have used the target client version, Determine candidate accounts that have used the target client version; Based on the account location of each of the candidate accounts, a candidate account whose account location matches the target area is determined from the plurality of candidate accounts as a historical account corresponding to the target area.

4. The method according to claim 2, wherein: The historical account portrait information includes the operation data of the historical account on the resource object and the account characteristics of the historical account; The training of the initial model to be trained based on the historical account portrait information to obtain a resource object recommendation model corresponding to the target area includes: Based on the operation data of the historical accounts on the resource objects and the account characteristics, the unsupervised model to be trained is trained to obtain a resource object recommendation model corresponding to the target area.

5. The method according to claim 4, wherein: There are multiple historical accounts; The step of training the unsupervised model to be trained based on the operation data of the historical account on the resource object and the account characteristics to obtain a resource object recommendation model corresponding to the target area includes: Determine a cluster center account as a cluster center from the plurality of historical accounts; Clustering the plurality of historical accounts based on the cluster center account to obtain a plurality of account sets; the historical accounts belonging to the same account set have matching account characteristics and operation data; Updating the cluster center account of each of the account sets, and returning to execute clustering the plurality of historical accounts based on the cluster center until a clustering end condition is met, and taking the current cluster center of each account set as the target cluster center; Based on each of the target cluster centers, a resource object recommendation model corresponding to the target area is determined; the resource object recommendation model is used to determine the account set to which the account belongs based on the similarity between the account and each of the target cluster centers, and to obtain the target resource object of the account based on the resource objects associated with the account set.

6. The method according to any one of claims 1 to 5, wherein: The determining, by the resource object recommendation model, a target resource object recommended to the account in the financial client includes: Determine, by means of the resource object recommendation model, the target resource object recommended to the account in the financial client, and the priority of attention of each target resource object by the account; adjusting the display of the resource object in the financial client of the account according to the target resource object Methods include: Based on the attention priority of each of the target resource objects, the display priority of each of the target resource objects is determined, and based on the display priority of each of the target resource objects, the display mode of the resource objects in the financial client of the account is adjusted.

7. The method according to claim 6, wherein: The adjusting the display mode of the resource object in the financial client of the account based on the display priority of each target resource object includes: Determine the display priority of other resource objects in the resource objects, the other resource objects are resource objects other than the target resource object, and the priority of the other resource objects is lower than the display priority of any of the target resource objects; Based on the display priority of each of the target resource objects and the display priority of each of the other resource objects, determining the display form of each of the resource objects; the display form includes at least one of the following: the display position of the resource object in the financial client function interface, the sorting position of the resource object in the resource object list; Each resource object is displayed in the financial client of the account according to its display form.

8. The method according to any one of claims 1 to 7, wherein: The financial client is deployed in a mobile terminal and / or a server.

9. The method according to any one of claims 1 to 7, wherein: The account is obtained based on the user's own identity identifier and / or one or more communication identifiers of the user.

10. The method according to any one of claims 1 to 7, wherein: The triggering event includes at least one of the following: starting a financial client, entering a designated function page in the financial client, and displaying a plurality of resource objects.

11. The method according to any one of claims 4, wherein: The operation data includes at least one of the following: number of clicks, click frequency, and number of uses; and the account characteristics include at least one of the following: desensitized identity identification, desensitized user name, and desensitized contact information.

12. A resource object display device, comprising: A portrait information acquisition module, configured to acquire account portrait information of the account in response to a triggering event in which the account adjusts the display mode of resource objects in the financial client; a target resource object determination module, configured to input the account portrait information into a resource object recommendation model corresponding to the region where the account is located, and determine the target resource object recommended to the account in the financial client by the resource object recommendation model; wherein the resource object recommendation model is trained based on the historical account portrait information of the historical account, and the historical account belongs to the region; A display module is used to adjust the display mode of the resource object in the financial client of the account according to the target resource object.

13. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

14. A computer-readable storage medium having a computer program stored thereon, wherein: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

15. A computer program product comprising a computer program, wherein: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images