Visual interface processing method and device, equipment and medium

Abstract

The invention provides a visual interface processing method, and relates to the field of artificial intelligence. The method comprises the steps that N object labels of a first object and S object attributes of M second objects are obtained, the M second objects comprise candidate objects recommended to the first object, and N, M and S are integers larger than or equal to 1; determining a target object from the M second objects; obtaining prompt content based on the N object tags and the S object attributes of the target object, wherein the prompt content comprises content used for guiding a generative artificial intelligence model to generate a visual interface; and inputting the prompt content into the generative artificial intelligence model to generate the visual interface. The invention further provides a visual interface processing device and equipment, a storage medium and a program product.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence, and more specifically, to a visualization interface processing method, device, equipment, medium and program product. Background Art

[0002] The front end usually displays a unified interface to all service objects, and displays various information in response to the operations of each service object on the front end interface. In this case, the style, content, components, and content structure of the front end are consistent. For example, a unified interface is generally displayed in the form of text and pictures in an application or H5.

[0003] In the process of realizing the inventive concept of the present disclosure, the inventors discovered that different service objects or the same service object at different times see the same front-end interface, and the information transmission channels and forms are relatively single. It is impossible to form a visual interface that is different for each user based on their actual situation, which may cause users to perform unnecessary operations and increase the consumption of computer resources. Summary of the invention

[0004] In view of the above problems, the present disclosure provides a visualization interface processing method, apparatus, device, medium and program product.

[0005] One aspect of an embodiment of the present disclosure provides a method for processing a visualization interface, including: obtaining N object labels of a first object, and S object attributes of each of M second objects, the M second objects including candidate objects recommended to the first object, and N, M and S are all integers greater than or equal to 1; determining a target object from the M second objects; obtaining prompt content based on the N object labels and the S object attributes of the target object, the prompt content including content for guiding a generative artificial intelligence model to generate a visualization interface; and inputting the prompt content into the generative artificial intelligence model to generate the visualization interface.

[0006] According to an embodiment of the present disclosure, the first object includes a target user, the second object includes a credit card, the N object tags include a consumption preference tag, and the S object attributes include credit card benefits; obtaining prompt content based on the N object tags and the S object attributes of the target object includes: obtaining consumption preference data based on each consumption record corresponding to the consumption preference tag of the target user within the first time period; obtaining the prompt content based on the consumption preference data and at least one credit card benefit.

[0007] According to an embodiment of the present disclosure, obtaining the prompt content based on the consumption preference data and at least one credit card benefit includes: extracting Q consumption fields from the consumption records under the consumption preference label based on Q pre-set prompt content dimensions, where Q is an integer greater than or equal to 1; determining Q consumption field values ​​from the Q consumption fields based on prompt content generation rules, wherein the prompt content generation rules include at least one generation rule for time, place, person, gender, consumption behavior, environment or decoration; obtaining the prompt content based on the Q consumption field values ​​and the at least one credit card benefit.

[0008] According to an embodiment of the present disclosure, before obtaining N object tags of a first object and S object attributes of each of M second objects, the method further includes: matching the N object tags with the S object attributes of each of K second objects, where K is an integer greater than or equal to M; and determining the M second objects that match the N object tags from the K second objects for recommendation.

[0009] According to an embodiment of the present disclosure, obtaining N object tags of the first object includes: obtaining the personal information and consumption records of the target user with the authorization of the target user; and constructing a target user portrait based on the personal information and consumption records of the target user, wherein the target user portrait includes the consumption preference tags.

[0010] According to an embodiment of the present disclosure, constructing a target user portrait based on the target user's personal information and consumption record includes: obtaining the first consumption frequency and the first consumption total amount of the target user in a second time period, and obtaining target preference data based on the first consumption frequency and the first consumption total amount; obtaining the second consumption frequency and the second consumption total amount of all users in the second time period, and obtaining overall preference data based on the second consumption frequency and the second consumption total amount; and constructing the target user portrait based on the target preference data and the overall preference data.

[0011] According to an embodiment of the present disclosure, constructing the target user portrait based on the target preference data and the overall preference data includes: determining X consumption categories involved based on the consumption record of the target user, where X is an integer greater than or equal to 1; dividing the target preference data into X sub-target preference data and the overall preference data into X sub-overall preference data according to the X consumption categories; under each consumption category, determining the proportion of the sub-target preference data to the sub-overall preference data; constructing the target user portrait according to the proportions corresponding to each of the X consumption categories, wherein the consumption category whose corresponding proportion is greater than a preset threshold is used as the consumption preference label.

[0012] According to an embodiment of the present disclosure, the S object attributes also include a card type attribute, and matching the N object tags with the S object attributes of each of the K second objects includes: obtaining card type category information applicable to the target user based on the consumption preference tag of the target user; and matching the card type attributes of each of the K second objects based on the card type category information.

[0013] According to an embodiment of the present disclosure, determining the target object from the M second objects includes: displaying M credit cards that meet the card category information and at least one credit card benefit of each to the target user; and determining the target credit card and at least one target credit card benefit based on the target user's selection.

[0014] Another aspect of the present disclosure provides a visual interface processing device, including:

[0015] a data acquisition module, configured to acquire N object tags of a first object and S object attributes of each of M second objects, wherein the M second objects include candidate objects recommended to the first object, and N, M and S are all integers greater than or equal to 1;

[0016] A target object module, used to determine a target object from the M second objects;

[0017] A prompt content module, used to obtain prompt content based on the N object tags and the S object attributes of the target object, wherein the prompt content includes content for guiding the generative artificial intelligence model to generate a visual interface;

[0018] The interface generation module is used to input the prompt content into the generative artificial intelligence model to generate the visual interface.

[0019] 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.

[0020] 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.

[0021] 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.

[0022] One or more of the above-mentioned embodiments have the following beneficial effects: it is possible to obtain prompt content by combining the N object tags of the first object and the S object attributes of the target object, which can take into account the characteristics and needs of the first object as a service object, and can integrate the object attributes of the recommended target object into the prompt content, thereby generating a visual interface adapted to the first object, which can effectively convey information to the first object, form a visual interface display effect that is different for each person, reduce unnecessary operations on the first object, and reduce the consumption of computer resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] 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:

[0024] Figure 1 A diagram schematically shows an application scenario of the visual interface processing method according to an embodiment of the present disclosure;

[0025] Figure 2 A flowchart of a visual interface processing method according to an embodiment of the present disclosure is schematically shown;

[0026] Figure 3 A flowchart of constructing a target user portrait according to an embodiment of the present disclosure is schematically shown;

[0027] Figure 4 A flowchart of constructing a target user portrait according to another embodiment of the present disclosure is schematically shown;

[0028] Figure 5 A flowchart of constructing a target user portrait according to another embodiment of the present disclosure is schematically shown;

[0029] Figure 6 A recommended flow chart according to an embodiment of the present disclosure is schematically shown;

[0030] Figure 7 A matching flow chart according to an embodiment of the present disclosure is schematically shown;

[0031] Figure 8 A flowchart for determining a target object according to an embodiment of the present disclosure is schematically shown;

[0032] Fig. 9 A flowchart of obtaining prompt content according to an embodiment of the present disclosure is schematically shown;

[0033] Fig.10 A flowchart of obtaining prompt content according to another embodiment of the present disclosure is schematically shown;

[0034] Fig.11 Schematically shows a flow chart of generating a visualization interface according to an embodiment of the present disclosure;

[0035] Fig.12 Schematically shows a flow chart of generating a visualization interface according to another embodiment of the present disclosure;

[0036] Fig.13 A structural block diagram schematically shows a visual interface processing device according to an embodiment of the present disclosure; and

[0037] Fig.14 A block diagram of an electronic device suitable for implementing a visual interface processing method according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0038] 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.

[0039] 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.

[0040] In the related art, a unified interface is displayed to all service objects, but the needs of different service objects or the same service object at different times are inconsistent, and redundant operations will be performed on the unified interface to find the target service step by step, which increases the consumption of computer resources and wastes user time.

[0041] In some embodiments of the present disclosure, a visualization interface processing method is provided, which can combine N object tags of the first object and S object attributes of the target object to obtain prompt content, can take into account the characteristics and needs of the first object as a service object, and can integrate the object attributes of the recommended target object into the prompt content, thereby generating a visualization interface adapted to the first object, can effectively convey information to the first object, form a visualization interface display effect that is different for each person, reduce unnecessary operations on the first object, and reduce the consumption of computer resources.

[0042] Figure 1 The following schematically shows an application scenario diagram of the visual interface processing 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.

[0043] 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.

[0044] 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 examples).

[0045] 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.

[0046] 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.

[0047] 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.

[0048] In applications such as client applications and web applications (abbreviated as APP in English), the client (i.e., front end) and the server (i.e., back end) can communicate data through network messages. For example, in the APP client, the parameters that the server needs to obtain from the client are assembled, and the network request method is called to send them to the server.

[0049] In some embodiments, the service object may include a user, which is used to access various services through an application in the terminal device 101, 102, 103, and one or more interfaces in the application are generated and displayed using the visual interface processing method provided by the present disclosure. It should be noted that the visual interface processing 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 visual interface processing device provided in the embodiment of the present invention can generally be set in the terminal device 101, 102, 103 or the server 105.

[0050] 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 the implementation requirements.

[0051] The following will be based on Figure 1 The scene described by Figure 2 to Figure 12 The visual interface processing method of the embodiment of the present disclosure is described in detail.

[0052] Figure 2 The flowchart of the visual interface processing method according to the embodiment of the present disclosure is schematically shown.

[0053] like Figure 2 As shown, the visual interface processing method of this embodiment includes:

[0054] In operation S210 , N object tags of a first object and S object attributes of each of M second objects are obtained, where the M second objects include candidate objects recommended to the first object, and N, M, and S are all integers greater than or equal to 1.

[0055] The first object may include a person, such as a user of an e-commerce shopping platform, a bank product recommendation platform, a social platform, a news website, a music platform, or a video website, and the second object may include a commodity, a bank product, social information, news, music, or a product, etc. For example, in response to a user logging in, the object tag of the user is read and the second object is recommended accordingly. The object attributes of the second object are stored in the background.

[0056] The first object may include items, such as cars, mobile phones, computers, VR devices, smart watches, etc. The visual interface generated for these first objects is provided to the user holding it and operated by the user. For example, when entering a mobile phone accessories sales outlet, the model of the mobile phone can be read as an object tag, and a variety of accessories such as selfie sticks, power banks, and mobile phone cases can be recommended. If each mobile phone case is used as a second object, the object attributes may include color, thickness, and pattern, etc.

[0057] Exemplarily, an object attribute is an attribute carried by or derived from the object itself, and an object label is a label assigned based on the object attribute, behavior, or external data.

[0058] In operation S220, a target object is determined from among the M second objects.

[0059] The target object with the highest matching degree with the first object may be automatically determined from the M second objects, or the target object may be selected by the user and determined in response to the selection of the user.

[0060] The target object can be one or more.

[0061] In operation S230, prompt content is obtained based on the N object tags and the S object attributes of the target object, and the prompt content includes content for guiding the generative artificial intelligence model to generate a visualization interface.

[0062] Generative artificial intelligence (AIGC) refers to a technology that generates relevant content through learning and identifying existing data based on artificial intelligence technical methods such as generative adversarial networks and large pre-trained models. For example, by inputting keywords, descriptions, and samples, matching articles, images, and audio can be generated. The prompt content of the embodiment of the present disclosure may include any one or more of prompt words, images, and audio.

[0063] In operation S240, the prompt content is input into a generative artificial intelligence model to generate a visual interface.

[0064] Generative AI models may include ChatGPT, Claude, Llama, MidJourney AI visualization software, image generation models, etc. The visualization interface is allowed to be displayed on the front end in the form of at least one image, and audio, video, etc. may also be generated for display.

[0065] According to the embodiments of the present disclosure, the prompt content can be obtained by combining the N object tags of the first object and the S object attributes of the target object, which can take into account the characteristics and needs of the first object as a service object, and can integrate the object attributes of the recommended target object into the prompt content, thereby generating a visual interface adapted to the first object, which can effectively convey information to the first object, form a visual interface display effect that is different for each person, reduce unnecessary operations on the first object, and reduce the consumption of computer resources.

[0066] The following uses the first object as a bank user and the second object as a credit card to illustrate some embodiments of the visual interface processing method by recommending a scenario in which a bank user applies for a credit card. However, it is understood that the present disclosure is not limited to bank users and credit cards.

[0067] Figure 3A flowchart of constructing a target user portrait according to an embodiment of the present disclosure is schematically shown.

[0068] like Figure 3 As shown, this embodiment is one of the embodiments of operation S210, including:

[0069] In operation S310, with authorization by the target user, personal information and consumption records of the target user are obtained.

[0070] For example, for a banking platform, the first object may be a registered user. The target user's personal information (such as name, gender, age, etc.) and consumption records (such as the types of goods purchased, purchase frequency, etc.) can be obtained through authorization by the target user. This information can be used to build a profile of the target user.

[0071] In operation S320, a target user portrait is constructed based on the target user's personal information and consumption record, and the target user portrait includes a consumption preference tag. The object tag includes a consumption preference tag.

[0072] By analyzing the target user’s personal information and consumption records, we can learn about the user’s shopping preferences, the types of goods in their preferred data, purchase frequency, etc. Based on this information, we can build a profile of the target user, which includes the user’s consumption preference labels, such as “young people who love sports”, “middle-aged people who like to travel”, etc.

[0073] According to the embodiments of the present disclosure, by obtaining the personal information and consumption records of the target user and building a portrait of the target user based on this information, personalized services for the first object can be achieved, and an adaptive and personalized visual interface can be displayed to the user according to the user's characteristics and needs.

[0074] Figure 4 A flowchart for constructing a target user portrait according to another embodiment of the present disclosure is schematically shown.

[0075] like Figure 4 As shown, this embodiment is one of the embodiments of operation S320, including:

[0076] In operation S410, a first consumption frequency and a first consumption total amount of a target user in a second time period are acquired, and target preference data is obtained based on the first consumption frequency and the first consumption total amount.

[0077] For example, if the second time period refers to the most recent month, the number of shopping times and the total amount of spending by the target user in this month can be counted.

[0078] In operation S420, the second consumption frequency and the second consumption amount of all users in the second time period are obtained, and the overall preference data is obtained based on the second consumption frequency and the second consumption amount. The shopping times and the total consumption amount of all users in the last month can be counted.

[0079] In operation S430, a target user portrait is constructed based on the target preference data and the overall preference data.

[0080] For example, by comparing and analyzing the target user's preference data and overall preference data, the target user's special preferences and personalized needs relative to the overall user can be determined. Based on these data, a profile of the target user can be constructed, for example, the user prefers to buy high-end brand electronic products and has a high shopping frequency in the past month. By constructing a profile of the target user based on the target user's preference data and overall preference data, a visual interface adapted to the target user can be generated, effectively delivering information to the target user.

[0081] Figure 5 A flowchart for constructing a target user portrait according to another embodiment of the present disclosure is schematically shown.

[0082] like Figure 5 As shown, this embodiment is one of the embodiments of operation S210, including:

[0083] In operation S510, X consumption categories involved are determined based on the consumption record of the target user, where X is an integer greater than or equal to 1.

[0084] Assuming that the target user’s consumption records include the purchase of electronic products, clothing, and food, then X is equal to 3.

[0085] In operation S520, the target preference data is divided into X sub-target preference data according to the X consumption categories, and the overall preference data is divided into X sub-overall preference data.

[0086] According to X consumption categories, the target user's preference data and overall preference data are divided into X sub-datasets. For example, according to the three consumption categories in the above example, the target user's preference data can be divided into electronic product preference data, clothing preference data, and food preference data, and the overall preference data can be divided into electronic product overall preference data, clothing overall preference data, and food overall preference data. The preference data under each consumption category is obtained by the consumption frequency and total consumption under that category.

[0087] In operation S530, under each consumption category, a ratio of the sub-target preference data to the sub-population preference data is determined.

[0088] For example, in the electronic products category, the ratio of electronic product preference data to the total electronic product preference data is calculated. In the clothing category, the ratio of clothing preference data to the total clothing preference data is calculated. In the food category, the ratio of food preference data to the total food preference data is calculated.

[0089] In operation S540, a target user portrait is constructed according to the proportions corresponding to the X consumption categories, wherein the consumption categories with a corresponding proportion greater than a preset threshold are used as consumption preference labels.

[0090] Assuming that the preset threshold is 90%, under the electronic product category, if the proportion of electronic product preference data to the overall electronic product preference data is greater than 90%, then electronic products become the consumer preference label of the target user.

[0091] According to the embodiments of the present disclosure, by dividing the data set according to consumption categories and calculating the proportion of each category, the preference of the target user under different consumption categories can be more accurately understood. When constructing a user portrait, the consumption categories with a proportion greater than a preset threshold are used as consumption preference labels, which can more specifically describe the consumption preferences of the target user.

[0092] Reference Figure 3 to Figure 5 , giving an example to illustrate the process of building a target user portrait. The construction of a user consumption portrait is mainly through the use of a normal distribution model to compare the current user's consumption information with the consumption information of all users in the bank system to discover the user's consumption preferences. The specific process is as follows:

[0093] 1.1 Obtain the current logged-in user's clothing, food, housing, transportation, entertainment, and shopping consumption information in the bank system. Including: monthly consumption frequency (f) and monthly consumption total (t).

[0094] 1.2 Calculate the current user's: monthly consumption preference data (p) = monthly consumption frequency (f) * monthly consumption total (t).

[0095] Take the current user consumption preference data in the field of "travel" as an example: 行 =f 行 *t 行 .

[0096] 1.3 Obtain all users' consumption information on clothing, food, housing, transportation, entertainment, and shopping in the banking system, including: monthly consumption frequency (F) and monthly consumption total (T).

[0097] 1.4 Calculate user n’s: monthly total consumption preference data (Pn) = monthly consumption frequency (Fn) * monthly total consumption (Tn).

[0098] 1.5 Fit the consumption preference data of user n into a normal distribution curve. According to the normal distribution, it is concluded that the current user's consumption preference data ranks in the top x% of the total users.

[0099] 1.6 pairs x 衣 、x 食 、x 住 、x 行 、x 文娱 、x 购 To sort:

[0100] Assume that the user's travel consumption is at the 95% percentile of the normal distribution (x 行 =95), which means it exceeds 95% of ordinary users.

[0101] For example: (x 行 =95)>(x 食 =92)>(x 文娱 =60)>(x 购 =45)>(x 衣 =20)=(x 住 =20), then travel-related credit cards will be recommended to them first.

[0102] The target user profile can take "travel" and "food" as the consumption preference labels of the user. The ranking, priority or weight of the "travel" label is greater than that of the "food" label.

[0103] Figure 6 The recommended flow chart according to the embodiment of the present disclosure is schematically shown.

[0104] Before obtaining N object tags of the first object and S object attributes of each of the M second objects, such as Figure 6 As shown, this embodiment includes:

[0105] In operation S610 , N object tags are matched with S object attributes of each of K second objects, where K is an integer greater than or equal to M.

[0106] Assume that the first object is a user who applies for a credit card, and the N object tags include age, income, occupation, etc. The second object is a credit card product, and the K credit card products each have S object attributes, such as card type, credit limit, interest rate, promotional activities, etc. In this step, the user's object tag can be matched with the attributes of each credit card product. For example, matching is achieved based on at least one of similarity calculation, machine learning model classification, or keyword matching.

[0107] In operation S620 , M second objects matching the N object tags are determined from the K second objects for recommendation.

[0108] Assume that through matching, it is found that there are 3 credit cards that match the user's object label and can be recommended to the user.

[0109] According to the embodiments of the present disclosure, by matching the object tag with the object attribute of the second object and selecting the matching second object for recommendation, the accuracy and personalization of the recommendation can be improved. Users can get more suitable recommendation results according to their own characteristics and needs.

[0110] Figure 7 The matching flow chart according to the embodiment of the present disclosure is schematically shown.

[0111] like Figure 7 As shown, the S object attributes also include a card type attribute. In this embodiment, matching the N object tags with the S object attributes of the K second objects includes:

[0112] In operation S710, based on the consumption preference tag of the target user, the card type information applicable to the target user is obtained.

[0113] Assuming that the target user's consumption preference tags include high-end electronic products, fashionable clothing and gourmet food, it can be judged based on these tags that the target user is suitable for applying for a high-end credit card, a fashionable credit card or a gourmet credit card, etc.

[0114] In operation S720, matching is performed with the card type attributes of the K second objects based on the card type category information.

[0115] Assuming that the card type information is a high-end credit card, it can be matched with the card type attributes of K credit card products to filter out credit card products that match high-end credit cards, such as platinum-level credit cards. Among them, they can be divided into silver cards, gold cards, and platinum cards, with gradually increasing levels.

[0116] According to an embodiment of the present disclosure, by obtaining applicable card category information based on the target user's consumption preference tag and matching it with the card type attribute of the second object, credit card products suitable for the target user can be screened out more accurately, thereby improving the accuracy and personalization of credit card recommendations.

[0117] Figure 8 The flowchart of determining the target object according to an embodiment of the present disclosure is schematically shown.

[0118] like Figure 8 As shown, this embodiment is one of the embodiments of operation S220, including:

[0119] In operation S810, M credit cards that match the card type information and at least one credit card benefit of each are displayed to a target user.

[0120] In operation S820, a target credit card and at least one target credit card benefit thereof are determined based on the selection of the target user.

[0121] Assuming that the card type information is high-end credit card, select the credit card products that meet the high-end credit card category from the previously matched M credit card products, and display them and at least one credit card benefit to the target user. Among the credit card products and credit card benefits displayed to the target user, the target user can select the credit card product of interest and determine the target credit card and at least one target credit card benefit from them.

[0122] According to an embodiment of the present disclosure, by displaying credit card products and credit card benefits that meet the card category information to target users, and determining the target credit card and its target credit card benefits based on the target user's selection, personalized credit card recommendations and benefits displays can be provided to meet the needs and preferences of the target users.

[0123] Fig. 9 The flowchart of obtaining prompt content according to an embodiment of the present disclosure is schematically shown.

[0124] The first object includes the target user, the second object includes the credit card, the N object tags include the consumption preference tag, and the S object attributes include the credit card benefits. Fig. 9 As shown, this embodiment is one of the embodiments of operation S230, including:

[0125] In operation S910, consumption preference data is obtained based on consumption records corresponding to consumption preference tags of a target user within a first time period.

[0126] In operation S920, prompt content is obtained based on the consumption preference data and at least one credit card benefit.

[0127] Assuming that the target user's consumption preference tags include electronic product tags, clothing tags and food tags, the consumption preference data includes electronic products, fashion clothing and food purchased in the recent period, such as one month (i.e., the first time period), and prompt words such as "electronic product model", "clothing style", "food category" and so on can be obtained.

[0128] Next, select at least one credit card benefit and combine it with the consumer preference data. Assume that the selected credit card benefits include electronic product discounts and exclusive fashion brand activities. Combine the consumer preference data and the selected credit card benefits to generate prompt content. The generated prompt content is used as input to the generative artificial intelligence model, and the corresponding image output is obtained through model training and learning. The generative artificial intelligence model can be a deep learning model for image generation.

[0129] According to the embodiments of the present disclosure, consumption preference data can be obtained based on the actual consumption records of target users, and combined with credit card benefits to generate prompt content, so that the visual interface is adapted to the target users.

[0130] Fig.10 A flowchart for obtaining prompt content according to another embodiment of the present disclosure is schematically shown.

[0131] like Fig.10 As shown, this embodiment is one of the embodiments of operation S320, including:

[0132] In operation S1010, based on the preset Q prompt content dimensions, Q consumption fields are extracted from the consumption records under the consumption preference tag, where Q is an integer greater than or equal to 1.

[0133] Q consumption fields related to the prompt content are extracted from the consumption records under the consumption preference label, and these fields can be used to generate the prompt content. The preset prompt content dimensions are time, place and consumption amount, and the three consumption fields of time, place and consumption amount are extracted from the consumption records with the consumption preference label of "high-end".

[0134] In operation S1020, Q consumption field values ​​(ie, consumption preference data) are determined from the Q consumption fields based on prompt content generation rules, wherein the prompt content generation rules include generating rules for at least one of time, place, person, gender, consumption behavior, environment, or decoration.

[0135] Assume that the generation rule is that the time field is determined by the season, the location field is determined by the city where the target user is located, and the consumption amount field is averaged based on the consumption records. If the time field is spring, the location field is Beijing, and the average value of the consumption amount field is 1,000 yuan, then the generated consumption field values ​​are "spring", "Beijing", and "1,000 yuan".

[0136] In operation S1030, prompt content is obtained based on the Q consumption field values ​​and at least one credit card benefit.

[0137] Assuming that the credit card benefit is a discount on high-end electronic products, the consumption field values ​​"Spring", "Beijing" and "1,000 yuan" are combined with the high-end electronic product discount to generate the final prompt content "Spend 1,000 yuan in Beijing in spring to enjoy a discount on high-end electronic products."

[0138] According to the embodiments of the present disclosure, by extracting the consumption field from the consumption record under the consumption preference tag, determining the consumption field value according to the generation rule, and combining the credit card benefits, personalized prompt content can be generated. In this way, prompt information related to the consumption behavior and credit card benefits of the target user can be provided, enhancing the user's attractiveness and user experience.

[0139] Fig.11 The flowchart of generating a visualization interface according to an embodiment of the present disclosure is schematically shown.

[0140] The entire process involves users, clients, and backend servers. The backend needs to: 1) obtain the user's consumption records of clothing, food, housing, transportation, culture, entertainment, and shopping in the banking system in advance, so as to form a user consumption portrait, quickly visualize the user's scene image, and make personalized card recommendations. 2) Establish a credit card database, which must include card types, rights and interests information, and real-life rights and interests consumption scene pictures in order to quickly recommend card types and generate scene pictures in combination with user consumption portraits. Among them, the material database needs to record: card type name, rights and interests information text corresponding to each card type, real-life pictures of each right, and user consumption records of clothing, food, housing, transportation, culture, entertainment, and shopping in the banking system.

[0141] Reference Fig.11 , combined with the user's consumption preferences and credit card benefits information, AIGC technology is used to present personalized scene images. The core lies in the positioning of user preferences, label matching with credit card benefits, and extraction of AIGC technology keyword segments, and then combined with the midjourney artificial intelligence visualization software API interface to generate scene images. The details are as follows.

[0142] In operation S1110, it is detected that the user enters the card digital space. The user consumption preference portrait is obtained, such as Figure 3 to Figure 5 The user portrait constructed. The background pre-loads the credit card benefit information fields in the credit card benefit information database.

[0143] In operation S1120, 3. the user's consumption preference profile tag (such as the consumption preference tag) is matched with the credit card type field (characterizing the card type attribute), and the corresponding recommended card types are displayed in sequence on the front end according to the degree of matching. The user selects the card type, and according to the degree of matching between the user's consumption preference profile tag and the different benefits of the card, the benefits that best match the user's consumption preference profile tag are displayed on the front end first. The user selects the benefits that he is interested in.

[0144] In operation S1130, 1) retrieve the user's personal consumables consumption record fields in the past six months from the user consumption database (e.g., the user bought a red dress and jasmine tea in the past six months), 2) retrieve the user's travel record fields in the past six months from the user's frequently used map coordinate database (e.g., the user has lived in Beijing for the past six months and often travels to various places from Beijing Capital Airport), and 3) extract the rights and interests scenario information fields from the credit card rights and interests information database (e.g., beverage shops, high-speed rail VIP lounges).

[0145] In operation S1140, keyword combinations are generated according to the format of "someone + in a certain place + what they are doing" (eg, person wearing red pants + high-speed rail VIP lounge in Beijing + drinking jasmine tea).

[0146] In some embodiments, more information can be provided, and keyword combinations can be generated according to the format of "gender + age + what kind of clothes are worn + in a certain city + a certain public space + doing a certain consumption behavior" for each prompt content dimension (such as: female + 37 years old + wearing a red dress + in Beijing + Capital Airport VIP lounge + drinking jasmine tea). Among them, gender, age, and city information are extracted from the customer information database, clothing information extracts the user's most recent clothing consumption record, and public space information is displayed in combination with the card type selected by the user (for example, the user selects a global travel credit card. According to the airport VIP lounge rights of this credit card, the public space information can be extracted as the airport VIP lounge), and consumption behavior information is extracted by extracting the user's most recent consumption information of consumables at the bank (such as: purchasing jasmine tea).

[0147] In operation S1150, the AIGC-Midjourney api technical interface is called to generate a customized rights and interests scenario diagram, which is displayed to the user on the front end.

[0148] The prompt content may contain one or more rights. In some embodiments, for example, if prompt content A contains A rights and prompt content B contains B rights, the visualization interfaces corresponding to the two prompt contents may be used as new prompt contents to generate a new visualization interface. In some embodiments, the prompt content may allow the user to enter or more words to generate a visualization interface.

[0149] Fig.12 A flowchart for generating a visualization interface according to another embodiment of the present disclosure is schematically shown.

[0150] Step 1: The user enters the credit card marketing display space and clicks the scenario-based marketing display button.

[0151] Step 2: Recommend card types based on the user’s past spending records in the bank system. The user selects the card type of interest.

[0152] Take the "Global Travel Plus Credit Card" as an example: according to the user's bank card consumption records, this user has visited more than 80 countries around the world. For ordinary users who travel abroad more than 80%, the "Global Travel Plus Credit Card" will be recommended first.

[0153] Step 3: Display the rights and interests information of the relevant card types according to the card type selected by the user. The priority of the rights and interests information display is determined by the user's past consumption. The user selects the rights and interests that interest him or her.

[0154] Take the "Global Travel Plus Credit Card" as an example: background data statistics show that this user likes to travel by plane, and his annual flight frequency is greater than 70%. Users with the same label (ordinary users with a frequency of traveling abroad greater than 80%) will be given priority in displaying the "Global Airport VIP Lounge" benefits of the "Global Travel Plus Credit Card".

[0155] Step 4: Combine the airports that users frequently visit with the user’s image information to visualize the benefits scenarios, allowing users to intuitively experience the benefits that can be obtained by applying for this credit card, thereby promoting business conversion.

[0156] Take the "Global Travel Plus Credit Card" as an example: This user always flies to various places from Beijing Capital Airport. In addition, his consumption information at the bank shows that he is a coffee lover and has recently bought red glasses, a yellow hat, and brown shorts. He is an adventurous person in his 30s. The AIGC technology will combine the existing rights and interests of the airport VIP lounge and the available user information to display a real-life picture of this user sitting on a chair drinking coffee in the VIP lounge of Beijing Capital Airport.

[0157] Reasonable use of the full-scenario consumption information of users held by the bank, combined with the cutting-edge AIGC visualization image generation technology, to generate traditional textual information in a scenario-based manner, greatly giving play to AIGC's advantages in image generation, flexible content creation, and strong immediacy. At the same time, as the most trendy and highly participatory marketing space method for young people, the digital space gamification experience, combined with personalized scenario-based rights and interests display, can better enhance the fun of marketing information transmission and help credit card rights and interests information to be disseminated on a larger scale. While visualizing credit card rights and interests for individual users, it also aims to attract new users and promote activation through this interesting new technology, making the product more vibrant, meeting product data goals, and promoting marketing activities to improve the conversion of credit card opening business.

[0158] Based on the above visual interface processing method, the present disclosure also provides a visual interface processing device. Fig.13 The device is described in detail.

[0159] Fig.13 The structural block diagram of the visual interface processing device according to an embodiment of the present disclosure is schematically shown.

[0160] like Fig.13 As shown, the visual interface processing device 1300 of this embodiment includes a data acquisition module 1310 , a target object module 1320 , a prompt content module 1330 and an interface generation module 1340 .

[0161] The data acquisition module 1310 may perform operation S210 to acquire N object tags of the first object and S object attributes of M second objects respectively, where the M second objects include candidate objects recommended to the first object, and N, M and S are all integers greater than or equal to 1.

[0162] In some embodiments, the data acquisition module 1310 may further perform operations S310 to S320, operations S410 to S430, and operations S510 to S540, which will not be described in detail herein.

[0163] The target object module 1320 may perform operation S220 for determining a target object from the M second objects.

[0164] In some embodiments, the target object module 1320 may further perform operations S810 to S820, which will not be described in detail herein.

[0165] The prompt content module 1330 can perform operation S230 to obtain prompt content based on N object tags and S object attributes of the target object, where the prompt content includes content for guiding the generative artificial intelligence model to generate a visual interface.

[0166] In some embodiments, the prompt content module 1330 may also perform operations S910 to S920 and operations S1010 to S1030, which are not described in detail herein.

[0167] The interface generation module 1340 may perform operation S240 to input the prompt content into a generative artificial intelligence model to generate a visual interface.

[0168] In some embodiments, the visual interface processing device 1300 may include a recommendation module for performing operations S610 to S620 and operations S710 to S720, which will not be described in detail herein.

[0169] The visual interface processing device 1300 includes two components for executing the above Figure 2 to Figure 12 A module for each step of any one of the described embodiments.

[0170] Based on AIGC technology, combined with the bank user's past consumption records in the ICBC system, the consumption preference profile label is constructed and matched with the credit card rights information field to make targeted recommendations for credit card types, and a personalized AIGC visualization scene diagram is generated based on the user's recent consumption data field, map coordinate information field and credit card rights field, so that users can truly and intuitively feel the rights and interests that can be enjoyed by opening a card for precise promotion. This patent reduces the browsing cost of the existing credit card promotion process, and aims to better enable the credit card opening business through innovations in interactive forms and information transmission methods.

[0171] 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.

[0172] According to an embodiment of the present disclosure, any multiple modules among the data acquisition module 1310, the target object module 1320, the prompt content module 1330 and the interface generation module 1340 can be combined into one module for implementation, or any one of the modules can be split into multiple modules. Alternatively, at least part of the functions of one or more of these modules can be combined with at least part of the functions of other modules and implemented in one module.

[0173] According to an embodiment of the present disclosure, at least one of the data acquisition module 1310, the target object module 1320, the prompt content module 1330, and the interface generation module 1340 can 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 can 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 1310, the target object module 1320, the prompt content module 1330, and the interface generation module 1340 can be at least partially implemented as a computer program module, and when the computer program module is run, the corresponding function can be executed.

[0174] Fig.14 A block diagram of an electronic device suitable for implementing a visual interface processing method according to an embodiment of the present disclosure is schematically shown.

[0175] like Fig.14 As shown, the electronic device 1400 according to an embodiment of the present disclosure includes a processor 1401, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1402 or a program loaded from a storage part 1408 into a random access memory (RAM) 1403. The processor 1401 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 1401 may also include an onboard memory for caching purposes. The processor 1401 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.

[0176] In RAM 1403, various programs and data required for the operation of electronic device 1400 are stored. Processor 1401, ROM 1402 and RAM 1403 are connected to each other via bus 1404. Processor 1401 performs various operations of the method flow according to the embodiment of the present disclosure by executing the program in ROM 1402 and / or RAM 1403. It should be noted that the program can also be stored in one or more memories other than ROM 1402 and RAM 1403. Processor 1401 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.

[0177] According to an embodiment of the present disclosure, the electronic device 1400 may further include an input / output (I / O) interface 1405, which is also connected to the bus 1404. The electronic device 1400 may further include one or more of the following components connected to the I / O interface 1405: an input portion 1406 including a keyboard, a mouse, etc. An output portion 1407 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc. A storage portion 1408 including a hard disk, etc. And a communication portion 1409 including a network interface card such as a LAN card, a modem, etc. The communication portion 1409 performs communication processing via a network such as the Internet. A drive 1410 is also connected to the I / O interface 1405 as needed. A removable medium 1411, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 1410 as needed, so that the computer program read therefrom is installed into the storage portion 1408 as needed.

[0178] 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.

[0179] 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 1402 and / or RAM 1403 described above and / or one or more memories other than ROM 1402 and RAM 1403.

[0180] 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.

[0181] 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 1401. According to the embodiment of the present disclosure, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0182] 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 1409, and / or installed from the removable medium 1411. 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.

[0183] In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 1409, and / or installed from the removable medium 1411. When the computer program is executed by the processor 1401, 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.

[0184] 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).

[0185] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0186] 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.

[0187] 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. A visual interface processing method, comprising: Obtaining N object tags of a first object and S object attributes of each of M second objects, wherein the M second objects include candidate objects recommended to the first object, where N, M, and S are all integers greater than or equal to 1; Determine a target object from the M second objects; Obtaining prompt content based on the N object labels and the S object attributes of the target object, wherein the prompt content includes content for guiding the generative artificial intelligence model to generate a visualization interface; The prompt content is input into the generative artificial intelligence model to generate the visualization interface.

2. The method according to claim 1, wherein: The first object includes a target user, the second object includes a credit card, the N object tags include a consumption preference tag, and the S object attributes include credit card benefits; The prompt content obtained based on the N object tags and the S object attributes of the target object includes: Obtaining consumption preference data based on consumption records corresponding to the consumption preference tag of the target user within the first time period; The prompt content is obtained based on the consumption preference data and at least one credit card benefit.

3. The method according to claim 2, wherein: Based on the consumption preference data and at least one credit card benefit, obtaining the prompt content includes: Based on the preset Q prompt content dimensions, Q consumption fields are extracted from the consumption records under the consumption preference tag, where Q is an integer greater than or equal to 1; Determine Q consumption field values ​​from the Q consumption fields based on a prompt content generation rule, wherein the prompt content generation rule includes a generation rule for at least one of time, place, person, gender, consumption behavior, environment, or decoration; The prompt content is obtained based on the Q consumption field values ​​and the at least one credit card benefit.

4. The method according to any one of claims 1 to 3, wherein: Before acquiring the N object tags of the first object and the S object attributes of each of the M second objects, the method further includes: Matching the N object tags with S object attributes of each of the K second objects, where K is an integer greater than or equal to M; The M second objects matching the N object tags are determined from the K second objects for recommendation.

5. The method according to claim 2, wherein: Obtaining N object tags of the first object includes: With the authorization of the target user, obtaining the personal information and consumption records of the target user; A target user portrait is constructed based on the target user's personal information and consumption record, and the target user portrait includes the consumption preference label.

6. The method according to claim 5, wherein: Building a target user profile based on the target user's personal information and consumption records includes: Acquire a first consumption frequency and a first consumption total amount of the target user in a second time period, and obtain target preference data based on the first consumption frequency and the first consumption total amount; Acquire the second consumption frequency and the second consumption total amount of all users in the second time period, and obtain overall preference data based on the second consumption frequency and the second consumption total amount; The target user portrait is constructed based on the target preference data and the overall preference data.

7. The method according to claim 6, wherein: Constructing the target user portrait based on the target preference data and the overall preference data includes: Determine X consumption categories involved based on the consumption record of the target user, where X is an integer greater than or equal to 1; According to the X consumption categories, the target preference data is divided into X sub-target preference data, and the overall preference data is divided into X sub-overall preference data; Under each consumption category, determine the proportion of the sub-target preference data to the sub-total preference data; The target user portrait is constructed according to the proportions corresponding to each of the X consumption categories, wherein the consumption category with a corresponding proportion greater than a preset threshold is used as the consumption preference label.

8. The method according to claim 4, wherein: The S object attributes further include a card type attribute, and matching the N object tags with the S object attributes of each of the K second objects includes: Based on the consumption preference tag of the target user, obtain the card type category information applicable to the target user; Matching is performed based on the card type category information and the card type attributes of each of the K second objects.

9. The method according to claim 8, wherein: Determining the target object from the M second objects includes: Displaying M credit cards that match the card type information and at least one credit card benefit of each to the target user; A target credit card and at least one target credit card benefit thereof are determined based on the selection of the target user.

10. A visual interface processing device, comprising: a data acquisition module, configured to acquire N object tags of a first object and S object attributes of each of M second objects, wherein the M second objects include candidate objects recommended to the first object, and N, M and S are all integers greater than or equal to 1; A target object module, used to determine a target object from the M second objects; A prompt content module, used to obtain prompt content based on the N object tags and the S object attributes of the target object, wherein the prompt content includes content for guiding the generative artificial intelligence model to generate a visual interface; The interface generation module is used to input the prompt content into the generative artificial intelligence model to generate the visual interface.

11. 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 9.

12. 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 9.

Images