Transfer transaction voucher processing method and device

Abstract

The invention discloses a transfer transaction voucher processing method and device, and relates to the technical field of mobile interconnection, and the method comprises the steps: obtaining user portrait information when a transfer transaction success message of a user is received; inputting the user portrait information into a marketing recommendation model, and outputting a bottoming picture and marketing information; generating a two-dimensional code by using the marketing information and the stored selection component information; the saving selection component information comprises selection information of the saving level of the transfer transaction voucher; inputting the transfer transaction information, the user portrait information, the bottoming picture and the two-dimensional code into a text graph model, and outputting a transfer transaction voucher picture; pushing the transfer transaction voucher picture to the client; receiving the storage level of the transfer transaction voucher selected by a user through scanning the two-dimensional code; and storing the transfer transaction voucher according to the storage level of the transfer transaction voucher selected by the user. According to the invention, transfer transaction information can be effectively utilized, and resource cost waste is reduced.

Description

Technical Field

[0001] The present invention relates to the field of mobile internet technology, and in particular to a method and device for pushing a transfer transaction voucher. Background Art

[0002] This section is intended to provide a background or context to the embodiments of the invention recited in the claims. No admission is made that the description herein is prior art by inclusion in this section.

[0003] A transfer transaction voucher is a data file that records information related to fund transfer transactions, and has multiple uses such as reconciliation, auditing, and credit assessment. In the prior art, after the user transfers money, the basic information of the transfer transaction is generally pushed to the customer via SMS or mini-programs, and the process ends. It is impossible to know whether the transfer transaction voucher is useful to the user, and the user's experience of banking services is also average, resulting in a waste of information resources. In addition, the transfer transaction information is generally kept for more than three years, and the transfer transaction information of a large number of users is also a burden for banking enterprises. In the long run, it will again cause a significant increase in hardware resource costs. Summary of the invention

[0004] An embodiment of the present invention provides a method for processing a transfer transaction voucher, which is used to effectively utilize transfer transaction information, improve user experience, and reduce resource cost waste. The method includes:

[0005] When receiving a successful transfer transaction message from the user, obtaining user portrait information; the successful transfer transaction message carries the transfer transaction information;

[0006] Input the user portrait information into the marketing recommendation model, and output the base image and marketing information; the marketing recommendation model pre-uses multiple historical information: user portrait information, base image and marketing information to train the machine learning model;

[0007] Generate a QR code using marketing information and save selection component information; the save selection component information includes selection information for the save level of the transfer transaction voucher; the save level includes different save durations and security levels;

[0008] Input the transfer transaction information, user portrait information, base image and QR code into the text-generated graph model, and output the transfer transaction voucher image; the text-generated graph model is used to generate an image based on the text description and the base image;

[0009] Push the transfer transaction voucher image to the client;

[0010] Receive the saving level of the transfer transaction voucher selected by the user by scanning the QR code;

[0011] The transfer transaction voucher is stored according to the preservation level of the transfer transaction voucher selected by the user.

[0012] In one embodiment, when a user's transfer transaction success message is received, user portrait information is obtained, including: when a user's transfer transaction success message is received, user portrait information is obtained based on a graph database using a user identifier; the graph database uses user identifiers, user preferences, and user behavior information as nodes, and uses user consumption types and user description information as user identifier node attributes.

[0013] In one embodiment, the user consumption type is obtained by performing a bubble sort process based on the probability of the user's historical consumption attributes.

[0014] In one embodiment, before inputting the user portrait information into the marketing recommendation model, the method also includes: inputting the user portrait information into the knowledge graph, performing logical judgment, deleting the user portrait information with logical errors, enhancing the weight of the user portrait information with correct logic, and obtaining the user portrait information after logical judgment; and updating the graph database using the user portrait information after logical judgment.

[0015] In one embodiment, the machine learning model includes a collaborative filtering model; the collaborative filtering model adopts one or any combination of the following similarity calculation methods:

[0016] Cosine similarity, Pearson correlation coefficient, Jaccard similarity.

[0017] In one embodiment, before pushing the transfer transaction voucher image to the client, the method further includes: performing a compliance check on the transfer transaction voucher image; when the compliance check fails, modifying the transfer transaction voucher image using a text graph model until the compliance check passes;

[0018] Pushing the transfer transaction voucher image to the client, including: when the compliance check passes, pushing the transfer transaction voucher image to the client.

[0019] In one embodiment, after receiving the storage level of the transfer transaction voucher selected by the user by scanning the QR code, the method further includes: sending a reward to the user.

[0020] The embodiment of the present invention further provides a transfer transaction voucher processing device, which is used to effectively utilize transfer transaction information, improve user experience, and reduce resource cost waste. The device includes:

[0021] A user portrait processing module, used to obtain user portrait information when receiving a user's transfer transaction success message; the transfer transaction success message carries the transfer transaction information;

[0022] The marketing recommendation processing module is used to input the user portrait information into the marketing recommendation model and output the base image and marketing information; the marketing recommendation model uses the historical multiple user portrait information, base image and marketing information in advance to train the machine learning model;

[0023] A transfer transaction voucher image generation module is used to generate a QR code using marketing information and save selection component information; the save selection component information includes selection information for the save level of the transfer transaction voucher; the save level includes different save durations and security levels; the transfer transaction information, user portrait information, base image and QR code are input into a text graph model, and the transfer transaction voucher image is output; the text graph model is used to generate an image based on the text description and the base image;

[0024] Push module, used to push the transfer transaction voucher image to the client;

[0025] The transfer transaction voucher storage level processing module is used to receive the storage level of the transfer transaction voucher selected by the user by scanning the QR code; and store the transfer transaction voucher according to the storage level of the transfer transaction voucher selected by the user.

[0026] An embodiment of the present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned transfer transaction voucher processing method when executing the computer program.

[0027] An embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned transfer transaction voucher processing method is implemented.

[0028] An embodiment of the present invention further provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the above-mentioned transfer transaction voucher processing method is implemented.

[0029] In the embodiment of the present invention, when generating a transfer transaction voucher, the transfer transaction voucher image is generated by utilizing the user portrait, the base image, the marketing information and the save selection component information. The transfer transaction voucher image includes both the transfer transaction information and the marketing information as well as the save selection component information. Moreover, the transfer transaction voucher image is generated in combination with the base image and the marketing information obtained by utilizing the user portrait information. The image effect meets the user's aesthetic requirements and can also be targeted at the user for marketing. In addition, the save level of the transfer transaction voucher can be directly determined to the user, so that the voucher is saved according to the save level. The embodiment of the present invention meets the user's requirements and improves the user experience. The use of the transfer transaction information for marketing can make full use of the transfer transaction message. Finally, the transfer transaction voucher can be saved according to the user's choice, thereby reducing the waste of resource costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0031] Figure 1 Schematic diagram of the process of the method for processing a transfer transaction voucher in an embodiment of the present invention;

[0032] Figure 2 A diagram showing a specific example of a method for processing a transfer transaction voucher in an embodiment of the present invention;

[0033] Figure 3 FIG. 2 is another specific example of the method for processing a transfer transaction voucher in an embodiment of the present invention;

[0034] Figure 4 Schematic diagram of a transfer transaction voucher processing device in an embodiment of the present invention;

[0035] Figure 5 Schematic diagram of a computer device in an embodiment of the present invention. DETAILED DESCRIPTION

[0036] To make the purpose, technical solution and advantages of the embodiments of the present invention more clear, the embodiments of the present invention are further described in detail below in conjunction with the accompanying drawings. Here, the exemplary embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0037] The acquisition, transmission, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of national laws and regulations.

[0038] It should be noted that in the embodiments of the present application, certain software, components, models and other existing solutions in the industry may be mentioned, and they should be regarded as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of the present application, but it does not mean that the applicant has or will necessarily use the solution.

[0039] Figure 1 FIG. 1 is a flow chart of a method for processing a transfer transaction voucher in an embodiment of the present invention. Figure 1 As shown, the method includes:

[0040] Step 101: upon receiving a successful transfer transaction message from a user, obtaining user portrait information; the successful transfer transaction message carries the transfer transaction information;

[0041] Step 102: Input the user portrait information into the marketing recommendation model, and output the base image and marketing information; the marketing recommendation model pre-uses the historical multiple user portrait information, base image and marketing information to train the machine learning model;

[0042] Step 103: Generate a QR code using the marketing information and the saving selection component information; the saving selection component information includes selection information for the saving level of the transfer transaction voucher; the saving level includes different saving durations and security levels;

[0043] Step 104: input the transfer transaction information, user portrait information, base image and QR code into the text-generated graph model, and output the transfer transaction voucher image; the text-generated graph model is used to generate an image based on the text description and the base image;

[0044] Step 105: Push the transfer transaction voucher image to the client;

[0045] Step 106: receiving the saving level of the transfer transaction voucher selected by the user by scanning the QR code;

[0046] Step 107: store the transfer transaction voucher according to the preservation level of the transfer transaction voucher selected by the user.

[0047] from Figure 1It can be seen from the shown process that in the embodiment of the present invention, when generating a transfer transaction voucher, the user portrait, the base picture, the marketing information and the save selection component information are used to generate the transfer transaction voucher picture. The transfer transaction voucher picture includes both the transfer transaction information and the marketing information, and the transfer transaction voucher picture is generated in combination with the base picture and the marketing information obtained by using the user portrait information. The picture effect meets the user's aesthetic requirements, and can also be targeted at the user for marketing. In addition, the preservation level of the transfer transaction voucher can be directly determined to the user, so that it can be saved according to the preservation level. The embodiment of the present invention meets user requirements and improves user experience. The use of transfer transaction information for marketing can make full use of transfer transaction messages. Finally, the transfer transaction voucher can be saved according to the user's choice, reducing the waste of resource costs.

[0048] The following is a detailed explanation of the method for processing a transfer transaction voucher in an embodiment of the present invention.

[0049] In the embodiment of the present invention, the transfer transaction voucher processing method is triggered and executed after the user's transfer transaction is successful. First, the user's transfer transaction success message is received. When the user's transfer transaction success message is received, the user portrait information is obtained, wherein the transfer transaction success message carries the user name, receiving account, amount and other transfer transaction information.

[0050] The user portrait information obtained includes user classification groups, user preference descriptions and other information.

[0051] Before this, it is necessary to collect basic information of all users in advance, profile the users, and determine different user attributes and weights. The collected information includes:

[0052] Attribute A (demographic): used to reach customers and understand their basic information, including basic attributes such as A1 (name), A2 (age), A3 (telephone number), and A4 (address).

[0053] Attribute B (credit): information on the user’s income potential, expenditure, and spending capacity, including credit information such as B1 (occupation), B2 (income), B3 (assets), B4 (liabilities), B5 (education), and B6 (credit score).

[0054] Attribute C (consumption): user consumption habits and preferences, identify high-frequency and high-value customers, and classify the population, including C1 (business travelers), C2 (overseas travelers), C3 (tourists), C4 (catering users), C5 (car users), C6 (mother and baby users), C7 (financial management users), etc.

[0055] Attribute D (hobbies): user’s hobbies and interests, and their willingness to spend on those hobbies. D1 (outdoor sports enthusiast), D2 (travel enthusiast), D3 (movie enthusiast), D4 (technology enthusiast), D5 (fitness enthusiast), D6 (luxury goods enthusiast), etc.

[0056] After that, feature transformation is performed to clarify the final key information and generate user portrait description information.

[0057] Rule changes: for example, age, 12-18 years old corresponds to teenagers; 18-30 years old, youth; 30-60 years old, middle-aged; over 60, elderly.

[0058] Generate user portrait description information based on key information such as users' purchasing behaviors and search records.

[0059] For example, the description information M is initially generated, such as a teenager, address XXX, student with no debt, and likes to travel. The description information A is input into the pre-trained large language model for language polishing to generate a universal language. For example, a teenager comes from XXX, is energetic, likes domestic travel, and is interested in the second dimension.

[0060] In one embodiment, when receiving a successful transfer transaction message from a user, obtaining user portrait information may include: when receiving a successful transfer transaction message from a user, obtaining user portrait information based on a graph database using a user identifier; the graph database uses user identifiers, user preferences, and user behavior information as nodes, and uses user consumption types and user description information as user identifier node attributes. User preferences may include user preferred pictures, and user behavior information may include information about products purchased by the user.

[0061] During implementation, the user portrait related information obtained above is stored in the graph database. Before forming the graph database, the obtained user related information is cleaned and preprocessed, and the user portrait information is classified and labeled according to business needs and data characteristics. For example, the user's interests and hobbies can be divided into categories such as "sports", "culture and art", "technology", etc., and the specific points of interest under each category are labeled, such as "sports-basketball" and "culture and art-classical music".

[0062] In a graph database, user identification nodes represent each individual user, and their attributes may include basic user information (age, gender, etc.), user consumption type, and user description information. For example, in a user portrait graph database, the attributes of the user node "User1" include "age: 30 years old, gender: male".

[0063] User preference nodes can include interest category nodes, behavior category nodes, etc. For example, if the user profile contains information related to interests and hobbies, an interest category node can be set up. For example, a "movie interest node" can have sub-nodes of different movie types, such as "science fiction movies" and "romance movies". For behavior category nodes, nodes are set up according to user behavior types, such as "purchase behavior" and "browsing behavior", etc., to better sort out the relationship between user behavior and other elements.

[0064] The relationship between nodes can exist in the form of user-ownership-interest relationship and user-execution-behavior relationship. For example, "user 1-ownership-interest in science fiction movies", "user 2-execution-purchase behavior", and attributes such as purchase amount, purchase time, etc. can be added to the corresponding nodes.

[0065] In a preferred embodiment, the user consumption type is obtained by performing a bubble sort process based on the probability of the user's historical consumption attributes.

[0066] For example, based on the crowd classification, determine the consumption type attribute of the person. Bubble sort the probabilities corresponding to the consumption type attribute, and obtain the highest-ranked type as the consumption type attribute. For example, if the person is a tourist, give the user a label of "loving to travel".

[0067] Figure 2 This is a specific example diagram of the method for processing a transfer transaction voucher in an embodiment of the present invention. Before inputting the user portrait information into the marketing recommendation model, the method may further include:

[0068] Step 201: Input the user portrait information into the knowledge graph, perform logical judgment, delete the user portrait information with logical errors, enhance the weight of the user portrait information with correct logic, and obtain the user portrait information after logical judgment;

[0069] Step 202: Update the graph database using the user portrait information after logical judgment.

[0070] In this example, the associated information is checked. For example, the node attribute information is input into the knowledge graph to perform logical judgment. Information with logical errors is filtered and deleted, and the weight of logically compliant information is increased. For example, it is obviously illogical for a group of teenagers to be mother and baby users, so this data cannot be reflected in the user description information.

[0071] Afterwards, in step 102, the user portrait information is input into the marketing recommendation model, and the base image and marketing information are output; the marketing recommendation model pre-uses multiple historical data: user portrait information, base image and marketing information to train the machine learning model.

[0072] In one embodiment, the marketing recommendation model is trained using a support vector machine model. During implementation, user portrait information is used to perform support vector machine classification and matched with images in a picture library to obtain a suitable base image.

[0073] For example, based on the age attribute of the money transfer scenario, a background photo with corporate characteristics is placed. For example, for teenagers, a youthful photo of CCB is placed; for middle-aged people, a mature corporate photo is placed.

[0074] In one embodiment, the machine learning model includes a collaborative filtering model; the collaborative filtering model adopts one or any combination of the following similarity calculation methods:

[0075] Cosine similarity, Pearson correlation coefficient, Jaccard similarity (Jaccard Similarity is a metric used to measure the similarity between two sets).

[0076] During implementation, multiple historical information such as user portrait information, base images, and marketing information are used to construct a training set, and the collaborative filtering model is trained using the training set. The trained model is used as a marketing recommendation model.

[0077] In the collaborative filtering model, based on the similarity calculation method, other users with similar behaviors to the target user are found and the items that these users like are recommended, or other items similar to the items that the target user has already liked are found and recommended.

[0078] In step 103, a QR code is generated using the marketing information and the saving selection component information; the saving selection component information includes selection information for the saving level of the transfer transaction voucher; the saving level includes different saving durations and security levels.

[0079] When implemented, the front end creates the web page containing the advertisement and the selection form, and the back end receives and processes the data selected by the user.

[0080] The preservation level includes different preservation durations and security levels, and the preservation levels are divided into very important and general. During implementation, the longest-duration and highest-level security backup is used for very important transfer transaction vouchers, and the short-duration and basic-level security backup is used for general transfer transaction vouchers.

[0081] In step 104, the transfer transaction information, user portrait information, base image and QR code are input into the text-generated graph model, and the transfer transaction voucher image is output; the text-generated graph model is used to generate an image based on the text description and the base image.

[0082] For example, based on the user preferences in the user portrait information, the transfer transaction information, the base image and the QR code are merged to generate a transfer transaction voucher image suitable for the scenario.

[0083] In one embodiment, the QR code in the transfer transaction voucher image is highlighted and includes prompt information that there is a surprise or reward for scanning the QR code.

[0084] After step 105 pushes the transfer transaction voucher image to the client, step 106 receives the saving level of the transfer transaction voucher selected by the user by scanning the QR code, and finally step 107 stores the transfer transaction voucher according to the saving level of the transfer transaction voucher selected by the user.

[0085] In one embodiment, before pushing the transfer transaction voucher image to the client, the method may further include:

[0086] Conduct compliance checks on images of transfer transaction vouchers;

[0087] If the compliance check fails, the Wensheng graph model is used to modify the transfer transaction voucher image until the compliance check passes;

[0088] Push the transfer transaction voucher image to the client, which may include:

[0089] When the compliance check passes, the transfer transaction voucher image will be pushed to the client.

[0090] During implementation, a security check is performed on the generated images, and the final generated images are input into the image non-compliance detection model. If the generated images are non-compliant, confirmation is carried out with the image generator, the prompt words are modified, and the image is adjusted until it meets the requirements.

[0091] In one embodiment, after storing the transfer transaction voucher, the method may further include:

[0092] Display a share button to users to share the transfer transaction voucher or the information in the QR code. When the user clicks the share button to perform the sharing operation, the user will be rewarded, including but not limited to point rewards, preferential rewards for marketing products, etc.

[0093] Figure 3 FIG. 2 is another specific example of the method for processing a transfer transaction voucher in an embodiment of the present invention. Figure 3 Said method further comprises:

[0094] Step 301: Send rewards to users.

[0095] For example, by sending users point rewards, coupon rewards, and cash rewards, users are encouraged to view the transfer transaction voucher again and scan the code to process it.

[0096] In summary, the embodiments of the present invention have the following advantages:

[0097] 1. Flexible image generation, allowing for different images for different groups of people and transfer transaction scenarios.

[0098] 2. Make full use of user portraits to generate pictures that users prefer, accelerate the subsequent promotion of financial products, and help reduce marketing costs.

[0099] 3. Based on the base maps of different scenes, use Wenshengtu technology to modify and adjust the pictures to synthesize pictures that meet the requirements of both financial institutions and users.

[0100] 4. Use the social attributes of sharing pictures to increase the click-through purchase rate of financial products.

[0101] The present invention also provides a transfer transaction voucher processing device, as described in the following embodiments. Since the principle of the device to solve the problem is similar to that of the transfer transaction voucher processing method, the implementation of the device can refer to the implementation of the transfer transaction voucher processing method, and the repeated parts will not be repeated.

[0102] Figure 4 FIG. 1 is a schematic diagram of a transfer transaction voucher processing device according to an embodiment of the present invention. Figure 4 As shown, the device 400 includes:

[0103] The user portrait processing module 401 is used to obtain user portrait information when receiving a successful transfer transaction message from the user; the successful transfer transaction message carries the transfer transaction information;

[0104] The marketing recommendation processing module 402 is used to input the user portrait information into the marketing recommendation model, and output the base image and marketing information; the marketing recommendation model uses the historical multiple user portrait information, base image and marketing information in advance to train the machine learning model;

[0105] The transfer transaction voucher image generation module 403 is used to generate a QR code using marketing information and save selection component information; the save selection component information includes selection information for the save level of the transfer transaction voucher; the save level includes different save durations and security levels; the transfer transaction information, user portrait information, the base image and the QR code are input into the text graph model, and the transfer transaction voucher image is output; the text graph model is used to generate an image according to the text description and the base image;

[0106] Push module 404, used to push the transfer transaction voucher image to the client;

[0107] The transfer transaction voucher storage level processing module 405 is used to receive the storage level of the transfer transaction voucher selected by the user by scanning the QR code; and store the transfer transaction voucher according to the storage level of the transfer transaction voucher selected by the user.

[0108] In one embodiment, the user portrait processing module 401 is specifically used for: upon receiving a successful transfer transaction message from a user, obtaining user portrait information based on a graph database using a user identifier; the graph database uses user identifiers, user preferences, and user behavior information as nodes, and uses user consumption types and user description information as user identifier node attributes.

[0109] In one embodiment, the user consumption type is obtained by performing a bubble sort process based on the probability of the user's historical consumption attributes.

[0110] In one embodiment, the device 400 may further include a knowledge graph logic judgment module;

[0111] The knowledge graph logic judgment module is used for the marketing recommendation processing module 402 to input the user portrait information into the knowledge graph before inputting the user portrait information into the marketing recommendation model, perform logic judgment, delete the user portrait information with logical errors, enhance the weight of the user portrait information with correct logic, and obtain the user portrait information after logic judgment; use the user portrait information after logic judgment to update the graph database.

[0112] In one embodiment, the machine learning model includes a collaborative filtering model; the collaborative filtering model adopts one or any combination of the following similarity calculation methods:

[0113] Cosine similarity, Pearson correlation coefficient, Jaccard similarity.

[0114] In one embodiment, before pushing the transfer transaction voucher image to the client, the device 400 may further include a compliance checking module:

[0115] The compliance check module is used to perform compliance check on the transfer transaction voucher image before the push module 404 pushes the transfer transaction voucher image to the client; when the compliance check fails, the transfer transaction voucher image is modified using the Wensheng graph model until the compliance check passes;

[0116] The push module 404 is specifically used for:

[0117] When the compliance check passes, the transfer transaction voucher image will be pushed to the client.

[0118] In one embodiment, the apparatus 400 may further include a reward processing module;

[0119] The reward processing module is used to send a reward to the user after the transfer transaction voucher storage level processing module 405 receives the storage level of the transfer transaction voucher selected by the user by scanning the QR code.

[0120] Figure 5 Schematic diagram of a computer device in an embodiment of the present invention. Figure 5 As shown, an embodiment of the present invention further provides a computer device 500, including a processor 501, a memory 502, and a computer program 503 stored in the memory 502 and executable on the processor 501, and the processor 501 implements the above-mentioned transfer transaction voucher processing method when executing the computer program 503.

[0121] An embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned transfer transaction voucher processing method is implemented.

[0122] An embodiment of the present invention further provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the above-mentioned transfer transaction voucher processing method is implemented.

[0123] In the embodiment of the present invention, when generating a transfer transaction voucher, the transfer transaction voucher image is generated by utilizing the user portrait, the base image, the marketing information and the save selection component information. The transfer transaction voucher image includes both the transfer transaction information and the marketing information as well as the save selection component information. Moreover, the transfer transaction voucher image is generated in combination with the base image and the marketing information obtained by utilizing the user portrait information. The image effect meets the user's aesthetic requirements and can also be targeted at the user for marketing. In addition, the save level of the transfer transaction voucher can be directly determined to the user, so that the voucher is saved according to the save level. The embodiment of the present invention meets the user's requirements and improves the user experience. The use of the transfer transaction information for marketing can make full use of the transfer transaction message. Finally, the transfer transaction voucher can be saved according to the user's choice, thereby reducing the waste of resource costs.

[0124] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0125] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0126] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0127] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0128] The specific embodiments described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for processing a transfer transaction voucher, characterized in that: include: When receiving a successful transfer transaction message from the user, obtaining user portrait information; the successful transfer transaction message carries the transfer transaction information; Input the user portrait information into the marketing recommendation model, and output the base image and marketing information; the marketing recommendation model pre-uses multiple historical information: user portrait information, base image and marketing information to train the machine learning model; Generate a QR code using marketing information and save selection component information; the save selection component information includes selection information for the save level of the transfer transaction voucher; the save level includes different save durations and security levels; Input the transfer transaction information, user portrait information, base image and QR code into the text-generated graph model, and output the transfer transaction voucher image; the text-generated graph model is used to generate an image based on the text description and the base image; Push the transfer transaction voucher image to the client; Receive the saving level of the transfer transaction voucher selected by the user by scanning the QR code; The transfer transaction voucher is stored according to the preservation level of the transfer transaction voucher selected by the user.

2. The method according to claim 1, characterized in that When receiving the user's transfer transaction success message, obtain the user profile information, including: When a successful transfer transaction message is received from the user, the user portrait information is obtained based on the graph database using the user identifier; the graph database uses the user identifier, user preference, and user behavior information as nodes, and the user consumption type and user description information as user identifier node attributes.

3. The method according to claim 2, characterized in that The user consumption type is obtained by performing bubble sorting based on the probability of the user's historical consumption attributes.

4. The method according to claim 2, characterized in that Before inputting user portrait information into the marketing recommendation model, it also includes: Input the user portrait information into the knowledge graph, perform logical judgment, delete the user portrait information with logical errors, enhance the weight of the user portrait information with logical correctness, and obtain the user portrait information after logical judgment; Update the graph database with user portrait information after logical judgment.

5. The method according to claim 1, characterized in that The machine learning model includes a collaborative filtering model; the collaborative filtering model adopts one or any combination of the following similarity calculation methods: Cosine similarity, Pearson correlation coefficient, Jaccard similarity.

6. The method according to claim 1, characterized in that Before pushing the transfer transaction voucher image to the client, it also includes: Conduct compliance checks on images of transfer transaction vouchers; If the compliance check fails, the Wensheng graph model is used to modify the transfer transaction voucher image until the compliance check passes; Push the transfer transaction voucher image to the client, including: When the compliance check passes, the transfer transaction voucher image will be pushed to the client.

7. The method according to claim 1, characterized in that After receiving the saving level of the transfer transaction voucher selected by the user by scanning the QR code, it also includes: Send rewards to users.

8. A transfer transaction voucher processing device, characterized in that: include: The user portrait processing module is used to obtain the user portrait information when receiving the user's transfer transaction success message; The transfer transaction success message carries the transfer transaction information; The marketing recommendation processing module is used to input the user portrait information into the marketing recommendation model and output the base image and marketing information; the marketing recommendation model uses the historical multiple user portrait information, base image and marketing information in advance to train the machine learning model; A transfer transaction voucher image generation module is used to generate a QR code using marketing information and save selection component information; the save selection component information includes selection information for the save level of the transfer transaction voucher; the save level includes different save durations and security levels; the transfer transaction information, user portrait information, base image and QR code are input into a text graph model, and the transfer transaction voucher image is output; the text graph model is used to generate an image based on the text description and the base image; Push module, used to push the transfer transaction voucher image to the client; The transfer transaction voucher storage level processing module is used to receive the storage level of the transfer transaction voucher selected by the user by scanning the QR code; and store the transfer transaction voucher according to the storage level of the transfer transaction voucher selected by the user.

9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

11. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images