Automatic multi-channel deployment method and device for user interface

Abstract

The invention provides an automatic multi-channel deployment method and device for a user interface, relates to the field of artificial intelligence, can be used in the financial field, and comprises the following steps: when a user interface deployment request sent by a to-be-deployed device is received, determining a candidate user test interface according to a channel to which the to-be-deployed device belongs; performing edge calculation and depth analysis on functions in each candidate user test interface to determine interface candidate functions; generating a recommended user interface according to predetermined rendering elements and the interface candidate functions; and sending a development kit containing the recommended user interface to the to-be-deployed device, so that the to-be-deployed device completes user interface deployment by using the development kit. According to the method, the user interface can be automatically adjusted, the user interface scheme suitable for the channel application is determined through data analysis, and personalized user interface design is formed.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence and can be used in the financial field. Specifically, it is a method and device for automating multi-channel deployment of a user interface. Background Art

[0002] When promoting financial products, financial institutions may use APPs from multiple channels. For example, mobile banking APPs, lifestyle APPs, channel APPs, and counter APPs. When promoting financial products, due to the different user interface design styles of APPs in various channels, it is often necessary to deploy user interfaces for different channels separately, resulting in repeated deployment and difficulty in unified management and control.

[0003] Existing multi-channel deployment solutions often have defects such as the inability to obtain users' real usage experience, the inability to automatically optimize, and inflexible data analysis.

[0004] 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. Summary of the invention

[0005] In response to the problems in the prior art, the present application provides a method and device for automated multi-channel deployment of a user interface, which can automatically adjust the user interface, determine the user interface solution suitable for channel applications through data analysis, and form a personalized user interface design.

[0006] In order to solve the above technical problems, this application provides the following technical solutions:

[0007] In a first aspect, the present application provides a method for automating multi-channel deployment of a user interface, comprising:

[0008] When receiving a user interface deployment request sent by a device to be deployed, determining a candidate user test interface according to the channel to which the device to be deployed belongs;

[0009] Perform edge computing and in-depth analysis on the functions in each candidate user test interface to determine the candidate interface functions;

[0010] generating a recommended user interface according to the predetermined rendering elements and the candidate interface functions;

[0011] The development toolkit containing the recommended user interface is sent to the device to be deployed, so that the device to be deployed completes the user interface deployment by using the development toolkit.

[0012] Further, when receiving a user interface deployment request sent by a device to be deployed, determining a candidate user test interface according to a channel to which the device to be deployed belongs includes:

[0013] When receiving the user interface deployment request, generating multiple user test interfaces according to the channel to which the device to be deployed belongs;

[0014] Perform A / B testing on each user test interface and determine candidate user test interfaces based on the user conversion rate corresponding to each user test interface.

[0015] Furthermore, the edge computing and deep analysis of the functions in each candidate user test interface to determine the candidate interface functions include:

[0016] Adopting edge computing method, constructing a decision tree based on the functions in the candidate user test interface; wherein each function corresponds to each node in the decision tree;

[0017] A pessimistic pruning operation is performed on the decision tree according to preset pruning constraints to determine the candidate interface functions.

[0018] Furthermore, the edge computing and deep analysis of the functions in each candidate user test interface to determine the candidate interface functions include:

[0019] Using edge computing methods to collect click frequencies of various functions in the candidate user test interface;

[0020] The interface candidate functions are determined according to the click frequency.

[0021] Furthermore, the edge computing and deep analysis of the functions in each candidate user test interface to determine the candidate interface functions include:

[0022] Performing text analysis on user opinion information corresponding to the candidate functions of the interface;

[0023] The candidate interface functions are screened according to the text analysis results to obtain optimized candidate interface functions.

[0024] Furthermore, the rendering elements include channel rendering elements and scene rendering elements; and the generating of the recommended user interface according to the predetermined rendering elements and the interface candidate functions includes:

[0025] Determine the position of each interface candidate function in the page according to the channel rendering elements;

[0026] Determining a page appearance according to the scene rendering elements; wherein the page appearance includes page color and page style;

[0027] A recommended user interface is generated according to the position of each candidate interface function in the page and the appearance of the page, and loaded into the development toolkit.

[0028] In a second aspect, the present application provides a user interface automated multi-channel deployment device, comprising:

[0029] A test interface determination unit, configured to determine a candidate user test interface according to a channel to which the device to be deployed belongs when receiving a user interface deployment request sent by the device to be deployed;

[0030] A candidate function determination unit, used to perform edge computing and in-depth analysis on the functions in each candidate user test interface to determine the candidate functions of the interface;

[0031] A user interface recommendation unit, configured to generate a recommended user interface based on predetermined rendering elements and the candidate interface functions;

[0032] The interface deployment unit is used to send a development toolkit containing the recommended user interface to the device to be deployed, so that the device to be deployed completes the user interface deployment using the development toolkit.

[0033] Furthermore, the test interface determination unit includes:

[0034] A test interface generation module, configured to generate a plurality of user test interfaces according to the channel to which the device to be deployed belongs when receiving the user interface deployment request;

[0035] The test interface screening module is used to perform A / B testing on each user test interface and determine the candidate user test interface according to the user conversion rate corresponding to each user test interface.

[0036] Furthermore, the candidate function determination unit includes:

[0037] A decision tree construction module, used to construct a decision tree based on the functions in the candidate user test interface using an edge computing method; wherein each function corresponds to each node in the decision tree;

[0038] The pruning operation module is used to perform a pessimistic pruning operation on the decision tree according to preset pruning constraints to determine the candidate interface functions.

[0039] Furthermore, the candidate function determination unit includes:

[0040] A click frequency collection module, used to collect the click frequency of each function in the candidate user test interface by using an edge computing method;

[0041] A candidate function determination module is used to determine the candidate functions of the interface according to the click frequency.

[0042] Furthermore, the candidate function determination unit includes:

[0043] A text analysis module, used to perform text analysis on the user opinion information corresponding to the candidate functions of the interface;

[0044] The candidate function optimization module is used to screen the interface candidate functions according to the text analysis results to obtain optimized interface candidate functions.

[0045] Furthermore, the rendering elements include channel rendering elements and scene rendering elements; the user interface recommendation unit includes:

[0046] A function position determination module, used to determine the position of each interface candidate function in the page according to the channel rendering elements;

[0047] A page appearance determination module, used to determine the page appearance according to the scene rendering elements; wherein the page appearance includes page color and page style;

[0048] The user interface loading module is used to generate a recommended user interface according to the position of each candidate interface function in the page and the appearance of the page, and load it into the development toolkit.

[0049] In a third aspect, the present application provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method for automated multi-channel deployment of the user interface when executing the program.

[0050] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method for automated multi-channel deployment of a user interface.

[0051] In a fifth aspect, the present application provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the steps of the user interface automated multi-channel deployment method.

[0052] In response to the problems in the prior art, the user interface automated multi-channel deployment method and device provided in the present application can automatically adjust the user interface, determine the user interface solution suitable for channel applications through A / B testing, edge computing and other data analysis processes, and dynamically load the software tool development kit to deploy an adapted user interface on each channel, combining the software tool development kit with the application scenarios of each channel to form a personalized user interface design. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. 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 paying creative work.

[0054] Figure 1 This is a flowchart of the method for automating multi-channel deployment of a user interface in an embodiment of the present application;

[0055] Figure 2 A flowchart for determining a candidate user test interface in an embodiment of the present application;

[0056] Figure 3 This is one of the flow charts for determining candidate interface functions in an embodiment of the present application;

[0057] Figure 4 This is the second flowchart for determining candidate interface functions in an embodiment of the present application;

[0058] Figure 5 This is the third flowchart of determining the candidate interface functions in the embodiment of the present application;

[0059] Figure 6 A flowchart for generating a recommendation user interface in an embodiment of the present application;

[0060] Figure 7 This is a structural diagram of a user interface automation multi-channel deployment device in an embodiment of the present application;

[0061] Figure 8 This is a structural diagram of a test interface determination unit in an embodiment of the present application;

[0062] Fig. 9 This is one of the structural diagrams of the candidate function determination unit in the embodiment of the present application;

[0063] Fig.10 This is the second structural diagram of the candidate function determination unit in the embodiment of the present application;

[0064] Fig.11 This is the third structural diagram of the candidate function determination unit in the embodiment of the present application;

[0065] Fig.12 This is a structural diagram of a user interface recommendation unit in an embodiment of the present application;

[0066] Fig.13 A schematic diagram of the structure of an electronic device in an embodiment of the present application;

[0067] Fig.14 This is a schematic diagram of the overall control flow in the embodiment of the present application;

[0068] Fig.15 This is a schematic diagram of the display area in the embodiment of the present application;

[0069] Fig.16 Schematic diagram of the software development kit in the embodiment of the present application. DETAILED DESCRIPTION

[0070] 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.

[0071] The information collected in the technical solution of this application is 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.

[0072] 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.

[0073] 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.

[0074] In one embodiment, see Figure 1 In order to automatically adjust the user interface, determine the user interface solution suitable for channel applications through data analysis, and form a personalized user interface design, this application provides a user interface automatic multi-channel deployment method, including:

[0075] S101: When a user interface deployment request sent by a device to be deployed is received, a candidate user test interface is determined according to a channel to which the device to be deployed belongs.

[0076] S102: Perform edge computing and deep analysis on the functions in each candidate user test interface to determine the candidate interface functions.

[0077] S103: Generate a recommended user interface according to the predetermined rendering elements and the candidate interface functions.

[0078] S104: Sending the development toolkit containing the recommended user interface to the device to be deployed, so that the device to be deployed completes user interface deployment using the development toolkit.

[0079] Understandably, see Fig.14 , the execution subject of the embodiment of the present application can be a server system. When the server system receives a user interface (UI for short) deployment request sent by a device to be deployed (such as a PC device or a mobile device), it will determine the candidate user test interface according to the channel to which the device to be deployed belongs (PC channel or mobile channel, which can be further subdivided, such as a mobile banking channel). Different channels may correspond to different (candidate) user test interfaces. By performing edge computing and in-depth analysis on the functions in the candidate user test interface, the candidate functions of the interface can be determined, that is, some functions suitable for users under the channel. Then, a recommended user interface is generated based on the predetermined rendering elements and candidate functions of the interface, and the recommended user interface is loaded into a software development kit (SDK for short), and finally the SDK containing the recommended user interface is sent to the device to be deployed, so that the device to be deployed uses the SDK to complete the user interface deployment. When the device to be deployed belonging to a certain channel receives the SDK containing the UI, it updates the latest UI data in its application and renders the UI.

[0080] Among them, the device to be deployed can be a device equipped with a newly launched channel application (APP) or a device equipped with a channel application (APP) that has been running for a long time. For the latter, the method provided in this application can automatically update its user interface.

[0081] Then, in order to recommend a suitable user interface (also called a recommended user interface) to the device to be deployed, the server system needs to perform the following steps:

[0082] 1. Perform A / B testing on the user test interface to obtain the candidate user test interface.

[0083] 2. Use some edge computing strategies and methods to calculate the effects of functions in the candidate user test interface. For example, the candidate interface functions can be determined based on user click frequency, dwell time, number of comments, and other related data.

[0084] 3. Next, conduct in-depth analysis (deep processing) of the data to analyze whether a certain parameter reaches the set threshold. If it reaches the threshold, proceed to the next step; if it does not reach the set threshold for a long time, it can be transferred to the manual analysis platform for processing.

[0085] 4. For the devices to be deployed (or channels to be deployed), calculate the UI based on the number of user clicks, dwell time, and purchases, and generate the SDK.

[0086] 5. Send the recommended SDK (including UI data) to the device to be deployed (or the channel to be deployed).

[0087] In addition, the following concepts need to be explained:

[0088] (1) Management center for different channels: Receive SDKs recommended by system services, distribute SDKs to various channels, and record the design specifications of different channel UIs. For example, mobile banking channels have their own design specifications, and lifestyle apps have their own design specifications. Based on the design specifications, SDKs can better adapt to different channels.

[0089] (2) UI rendering: When the channel (corresponding to the device to be deployed) receives the latest SDK (including UI data), the SDK will update the UI rendering on the corresponding page. Taking mobile banking in the mobile channel as an example, the SDK can be updated dynamically. After the SDK file is downloaded, it is stored in the storage area of ​​the mobile phone. The program in the SDK can parse the UI data. For example, the layout of the placement, button position, background, text, etc. of a financial product function can be adjusted. Each channel can render different styles.

[0090] (3) SDK processing part see Fig.16 shown.

[0091] The system server can generate an SDK. The return message format of the SDK is unified, which facilitates unified processing by different channels, but the styles of different channels are different. The same SDK is processed differently by different channel ends and then sent to different channels. When the channel end receives the latest issued SDK, it can adjust the UI of the page according to the parameters therein. This step can be understood as, before generating a recommended user interface based on predetermined rendering elements and interface candidate functions, it also includes: sending the development toolkit containing the recommended user interface to a deployed device, so that the deployed device uses the development toolkit to complete the user interface update.

[0092] From the above description, it can be seen that the user interface automated multi-channel deployment method provided in this application can automatically adjust the user interface, determine the user interface solution suitable for channel applications through A / B testing, edge computing and other data analysis processes, and dynamically load the software tool development kit to deploy an adapted user interface on each channel, combining the software tool development kit with the application scenarios of each channel to form a personalized user interface design.

[0093] In one embodiment, see Figure 2, when receiving a user interface deployment request sent by a to-be-deployed device, determining a candidate user test interface according to a channel to which the to-be-deployed device belongs, includes:

[0094] S201: When the user interface deployment request is received, a plurality of user test interfaces are generated according to the channel to which the device to be deployed belongs.

[0095] S202: Performing A / B testing on each user testing interface, and determining a candidate user testing interface according to a user conversion rate corresponding to each user testing interface.

[0096] It is understandable that in order to conduct A / B testing, it is first necessary to establish some user testing interfaces (also called pages). These user testing interfaces may differ in terms of title font, background color, functions and text. For example, in an embodiment of the present application, two user testing interfaces can be established, and these two user testing interfaces can be pushed to all browsing users at the same time in a random manner. Next, the user conversion rates of the two user testing interfaces are counted respectively, and the advantages and disadvantages of the two designs can be clearly understood. Such comparisons can be carried out for multiple rounds. After determining the Top3 user testing interfaces, these Top3 user testing interfaces can also be randomly assigned to different users. By comparing parameters such as user retention rates, a better design is finally determined as a candidate user testing interface.

[0097] From the above description, it can be seen that the user interface automated multi-channel deployment method provided in the present application can determine a candidate user test interface according to the channel to which the device to be deployed belongs when receiving a user interface deployment request sent by the device to be deployed.

[0098] In one embodiment, see Figure 3 , the edge computing and deep analysis of the functions in each candidate user test interface to determine the candidate interface functions include:

[0099] S301: Using an edge computing method, a decision tree is constructed based on the functions in the candidate user test interface; wherein each function corresponds to a node in the decision tree.

[0100] S302: Performing a pessimistic pruning operation on the decision tree according to preset pruning constraints to determine the candidate interface functions.

[0101] It is understandable that after selecting the candidate user test interface, it is necessary to further screen the functions in the candidate user test interface. This step can be performed using an improved decision tree algorithm.

[0102] Among them, the decision tree algorithm is an algorithm in machine learning. The decision tree algorithm belongs to the supervised learning algorithm. The so-called supervised learning algorithm means that a certain sample data is given as the data for building a model. These data have their own attributes and categories. Through the established model, these data can be classified according to their respective attributes. When new data is available, the new data can also be classified using the same model. In the decision tree algorithm, the data is generally divided into a training set and a test set. The decision tree model is first built through the training set, and then the model is tested to see if it is accurate through the test set.

[0103] Specifically, the C4.5 algorithm uses the information gain rate to improve the decision tree algorithm.

[0104] The formula for information entropy is:

[0105]

[0106] Among them, p n is the proportion of samples of the nth class in the M sample set, |y| is the total number of sample classes, and the obtained Ent(M) can be used to calculate the information gain.

[0107] The comparison of information gain is used as the basis for node division. Information gain refers to the reduction of uncertainty in classification information after selecting a certain attribute. The greater the information gain, the smaller the uncertainty of separation. Selecting attributes with large information gain can make the classification ability stronger.

[0108] The formula for information gain is:

[0109]

[0110] The information gain rate is defined as:

[0111]

[0112] in,

[0113]

[0114] Among them, M is the training data set, |M| is the sample capacity, and the attribute x has v values, which are {x 1 ,x 2 ,...,x v}, the training data can be divided into v subsets of samples according to different attributes, and the information entropy of the vth (v=1,2,...,v)th attribute can be calculated using formula (1-1), M v is the sample divided according to the vth attribute, Ent(M v) is the information entropy of the sample divided by the vth attribute. v | / |M| represents the proportion of the vth attribute in the sample set in the total training data M.

[0115] is the “intrinsic value” of attribute x. It can be seen from the formula that the more values ​​a certain attribute x takes, the greater the value of IV(x) (called splitting information). If the corresponding information gain is also large, this preference can be corrected.

[0116] When using the decision tree algorithm, when the training data is overtrained, overfitting will occur. For the training data, the decision criteria obtained are accurate, but for new data, the decision results are biased. There are two ways to prune a decision tree: pre-pruning and post-pruning. Pre-pruning is to estimate each node before the entire decision tree is generated into a complete tree; if the division of the current node cannot improve the division ability of the decision tree, then stop the division and turn the current node into a leaf node.

[0117] The post-pruning method is to first build a complete decision tree, then overfit the training data, and then replace some subtrees with leaf nodes; if the replacement can improve the detection accuracy of the entire tree, then pruning is performed.

[0118] In order to prevent C4.5 from being over-split and causing overfitting, the embodiment of the present application adopts a pessimistic pruning method for pruning, which is a post-pruning algorithm.

[0119] Assume that a leaf node i has N samples, of which E samples are misclassified. When calculating the misclassification rate of this leaf node, a penalty factor of 0.5 needs to be added.

[0120] The formula for the misjudgment rate of a leaf node is:

[0121]

[0122] For a subtree replaced by a leaf node, if it has L leaf nodes, then its misjudgment rate before pruning is e tree :

[0123]

[0124] Among them, i represents the i-th leaf node.

[0125] E i Indicates the number of samples misclassified in the i-th leaf node of the subtree

[0126] N i Represents the total number of samples of the i-th leaf node of the subtree

[0127] In pessimistic pruning, the number of misjudgments of a subtree follows a binomial distribution. Therefore, the mean number of misjudgments before pruning can be calculated as E avg :

[0128]

[0129] The variance of the misjudgment of the subtree before pruning is σ:

[0130]

[0131] Thus, the maximum number of misjudgments before the subtree is pruned can be obtained as the sum of the mean value and the absolute value of the variance:

[0132] E error_before =E avg +σ (1-9)

[0133] The number of misjudgments after pruning is:

[0134] E error_after =E′+0.5 (1-10)

[0135] Among them, E′ is the mean number of misjudgments.

[0136] The condition for judging whether pruning is needed is: if the number of misjudgments after pruning is less than the number of misjudgments before pruning, then pruning is performed. That is, condition (1-11) is met.

[0137] E error_after <E error_before (1-11)

[0138] The above algorithm can be understood as follows:

[0139] The pessimistic pruning operation is performed on the decision tree according to the preset pruning constraint conditions, including: the first step, using the preset penalty factor to calculate the number of misjudgments of the leaf nodes in the decision tree before and after pruning; the second step, if the number of misjudgments after pruning is less than the number of misjudgments before pruning (pruning constraint conditions), a pruning operation is performed.

[0140] In specific implementation, edge computing methods can be used to execute the above improved decision tree algorithm, and through a series of decisions, the data (that is, the functions in the user test interface) can be screened. Only the functions screened by the decision tree can be processed in depth later.

[0141] The algorithm logic is as follows:

[0142] Input: Collect user data training set M = {(t1,k1),(t2,k2),…,(t n ,y n )};

[0143] Attribute set X = {x1, x2, …, x n};

[0144] Threshold ε;

[0145] Procedure: Function GenerateC4.5Tree(M,X)

[0146] Assume function GenerateC4.5Tree(M,X) {Set Tree to a single-node tree, set X k Mark the class of this node, return Tree;}

[0147] Step 1: If all instances in M ​​belong to the same class X k , then call the function GenerateC4.5Tree(M,X).

[0148] Step 2: If Then Tree (decision tree) calls the function GenerateC4.5Tree(M,X), otherwise execute step 3.

[0149] Step 3: According to the formula To calculate the information gain ratio of each attribute in X, select the attribute X with the largest information gain ratio v .

[0150] Step 4: If attribute X v If Gain_ratio(M,x)<ε, call the function GenerateC4.5Tree(M,X), otherwise execute step 5.

[0151] Step 5: X v Every x i (i=1,2,...,n), divide M into several non-empty subsets M i , M i The class with the largest number of instances is used as a marker, a child node is constructed, and the return value is Tree.

[0152] Step 6: For the i-th child node, use M i As a training set, remove X v The feature set X n-v As a new feature set, recursively repeat steps 1 to 5.

[0153] From the above description, it can be seen that the user interface automated multi-channel deployment method provided in this application can perform edge computing and in-depth analysis on the functions in each candidate user test interface to determine the candidate functions of the interface.

[0154] In one embodiment, see Figure 4, the edge computing and deep analysis of the functions in each candidate user test interface to determine the candidate interface functions include:

[0155] S401: Using edge computing methods, collect the click frequency of each function in the candidate user test interface.

[0156] S402: Determine the candidate interface functions according to the click frequency.

[0157] It is understandable that the determination of candidate interface functions may also be achieved by the following method.

[0158] For a certain function to be selected, such as financial information function, it is possible to determine whether to retain this function by collecting the user's click frequency.

[0159] Let the click frequency parameter be Di, assuming 10,000 clicks per day, and the dwell time parameter be Ti. Assume that the user stays in the function for a total of 1,800 seconds, the parameter for user participation in comments is Pi, and the total number of user comments is 2,000.

[0160] A simple preliminary calculation is performed on the user's data, and the parameters are weighted. The total weight is 1, the click frequency weight is d, the stay time weight is t, the number of comments is p, and the total weight is d+t+p=1.

[0161] Then assume d=0.2, t=0.3, p=0.5.

[0162] Then, 10000×0.2+1800×0.3+2000×0.5=3540.

[0163] The threshold is Y. If it is set greater than 2000 (threshold), it can participate in the subsequent in-depth analysis.

[0164] In other words, the constraint condition may be: Di×d+Ti×t+Pi×p>Y.

[0165] From the above description, it can be seen that the user interface automated multi-channel deployment method provided in this application can perform edge computing and in-depth analysis on the functions in each candidate user test interface to determine the candidate functions of the interface.

[0166] In one embodiment, see Figure 5 , the edge computing and deep analysis of the functions in each candidate user test interface to determine the candidate interface functions include:

[0167] S501: Performing text analysis on user opinion information corresponding to the candidate interface functions.

[0168] S502: Filter the candidate interface functions according to the text analysis result to obtain optimized candidate interface functions.

[0169] It is understandable that after completing the preliminary screening of the candidate interface functions by using steps S301 to S302 and / or steps S401 to S402, the data can be further analyzed in depth to obtain the optimized candidate interface functions. Among them, the "optimized candidate interface functions" are a subset of the "candidate interface functions", which can be understood as the candidate interface functions that better meet customer needs and are more suitable for application scenarios.

[0170] When conducting in-depth analysis, in addition to the data parameter information collected in the aforementioned steps, the number of users' favorable comments on the function and the user's feedback information can also be collected with the voluntary participation of the user. The embodiment of the present application will perform text processing on the above text information of the user, and the general steps include: performing keyword extraction, extracting and counting the opinions that are valuable to the function in the text. For example, if the customer mentioned that the investment advice in the financial information section is very effective, the design of the investment advice function will be increased next time.

[0171] For another example, let the number of good reviews for a function be Hp. Assume that the number of good reviews is 500, and the effective information extracted from the user's effective comments is Pl. Assume that for a function, the frequency of mentioning that the function is useful is 1000 times, and the threshold is set to Yu, for example, 1000. In other words, the constraint condition can be: Hp+Pl>Yu.

[0172] Then, if the number of positive reviews + the frequency of usefulness > the threshold, the function can be incorporated into the future recommendation user interface.

[0173] It should be noted that user text analysis can generally be divided into: user keyword extraction, user keyword quantity statistics, user sentiment analysis, etc. Its common steps include data collection, word segmentation, data cleaning, feature extraction and modeling, etc., which can be flexibly selected during specific implementation.

[0174] From the above description, it can be seen that the user interface automated multi-channel deployment method provided in this application can perform edge computing and in-depth analysis on the functions in each candidate user test interface to determine the candidate functions of the interface.

[0175] In one embodiment, see Figure 6 , the rendering elements include channel rendering elements and scene rendering elements; the generating of the recommended user interface according to the predetermined rendering elements and the interface candidate functions includes:

[0176] S601: Determine the position of each candidate interface function in the page according to the channel rendering element.

[0177] S602: Determine a page appearance according to the scene rendering elements; wherein the page appearance includes page color and page style.

[0178] S603: Generate a recommended user interface according to the position of each candidate interface function in the page and the appearance of the page, and load it into the development toolkit.

[0179] It is understandable that by generating an SDK based on business scenarios, function types, and channel characteristics, and generating corresponding function placement locations, user interface styles, colors, and fonts, it is possible to display different faces to different users, and to display the same user interface style to the same user on different channels.

[0180] After the previous steps, the functions that should be included in the new user interface have been determined. Next, the steps to recalculate (design) the user interface are as follows:

[0181] For the functions that need to be updated in the user interface in the previous step, the calculation method can introduce function weights. For example, if the function of designing the purchase of financial products is a key function of the bank, a high weight can be assigned. When there are two functions with similar other indicators, the function with a high weight should be designed first.

[0182] It is assumed that the positions of the user interface include: the top floor of the homepage (the part displayed with high frequency) and the bottom floor (the position displayed with relatively low frequency).

[0183] The page position of each function can be calculated (designed) based on the function weight. For example, Fig.15 For the user's mobile phone interface. Assuming that two functions enter the step of generating UI, one is the investment fund function and the other is the financial information function, then the weight of the investment fund is greater than the weight of the financial information. When generating UI, the investment fund function will be allocated to the page position of the high-frequency display area according to the weight.

[0184] These business-related considerations can be called channel rendering factors. Channel rendering factors can be used to determine the position of each interface candidate function on the page.

[0185] In addition to designing based on functional dimensions, the system also considers the UI styles commonly used by customers. For example, some people prefer UIs with more colorful colors and pay more attention to investment and financial information; some people prefer UIs with a more stable style. With the user's permission (authorization), the system can perform personalized design and calculation for different customer groups, and then design the same style of UI for users in different channels.

[0186] These considerations related to the page appearance can be called scene rendering factors. The page appearance can be determined by the scene rendering factors.

[0187] In the system, the designed UI can be stored according to the channel, and the corresponding SDK resource package can be generated at the same time. The SDK resource package contains the UI elements that should be displayed in the corresponding channel. These elements include common functions, layout styles and styles that should be displayed, etc. The SDK is distributed to each channel.

[0188] When sending SDK to various channels, different processing can be performed for different types of channels. For example, the channels of the entire banking system can be divided into two categories, namely PC and mobile. Different SDKs can be generated according to the different characteristics of these two ends. For different categories, the key designed UI can be placed in different sections.

[0189] Later, when a new application is launched for the first time, the bank may design the user interface based on similar channels, that is, use previous historical information to give priority to providing customers with similar UI styles. For example, when a bank deploys a new mobile application, it can deploy the user interface of the same channel that was previously stored for customers.

[0190] It can be seen from the above description that the user interface automated multi-channel deployment method provided in the present application can generate a recommended user interface based on predetermined rendering elements and the candidate interface functions.

[0191] It should be noted that the user interface automation multi-channel deployment method provided in the embodiment of the present invention can be used in the financial field, and can also be used in any technical field other than the financial field. The embodiment of the present invention does not limit the application field of the user interface automation multi-channel deployment method.

[0192] Based on the same inventive concept, the embodiments of the present application also provide a user interface automation multi-channel deployment device, which can be used to implement the method described in the above embodiments, as described in the following embodiments. Since the principle of solving the problem by the user interface automation multi-channel deployment device is similar to that of the user interface automation multi-channel deployment method, the implementation of the user interface automation multi-channel deployment device can refer to the implementation of the method based on software performance benchmark determination, and the repeated parts will not be repeated. As used below, the term "unit" or "module" can be a combination of software and / or hardware that implements predetermined functions. Although the system described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived.

[0193] In one embodiment, see Figure 7In order to automatically adjust the user interface, determine the user interface solution suitable for channel application through data analysis and form a personalized user interface design, the present application provides a user interface automatic multi-channel deployment device, including a test interface determination unit 701, a candidate function determination unit 702, a user interface recommendation unit 703 and an interface deployment unit 704.

[0194] The test interface determination unit 701 is used to determine a candidate user test interface according to the channel to which the device to be deployed belongs when receiving a user interface deployment request sent by the device to be deployed;

[0195] The candidate function determination unit 702 is used to perform edge computing and in-depth analysis on the functions in each candidate user test interface to determine the candidate interface functions;

[0196] The user interface recommendation unit 703 is used to generate a recommended user interface according to the predetermined rendering elements and the candidate interface functions;

[0197] The interface deployment unit 704 is used to send the development toolkit containing the recommended user interface to the device to be deployed, so that the device to be deployed completes the user interface deployment by using the development toolkit.

[0198] In one embodiment, see Figure 8 The test interface determination unit 701 includes a test interface generation module 801 and a test interface screening module 802.

[0199] The test interface generation module 801 is used to generate multiple user test interfaces according to the channel to which the device to be deployed belongs when receiving the user interface deployment request;

[0200] The test interface screening module 802 is used to perform A / B testing on each user test interface and determine candidate user test interfaces according to the user conversion rate corresponding to each user test interface.

[0201] In one embodiment, see Fig. 9 The candidate function determination unit 702 includes a decision tree construction module 901 and a pruning operation module 902.

[0202] The decision tree construction module 901 is used to construct a decision tree based on the functions in the candidate user test interface using an edge computing method; wherein each function corresponds to each node in the decision tree;

[0203] The pruning operation module 902 is used to perform a pessimistic pruning operation on the decision tree according to preset pruning constraints to determine the candidate interface functions.

[0204] In one embodiment, see Fig.10The candidate function determination unit 702 includes a click frequency acquisition module 1001 and a candidate function determination module 1002.

[0205] The click frequency collection module 1001 is used to collect the click frequency of each function in the candidate user test interface by using an edge computing method;

[0206] The candidate function determination module 1002 is used to determine the candidate functions of the interface according to the click frequency.

[0207] In one embodiment, see Fig.11 The candidate function determination unit 702 includes a text analysis module 1101 and a candidate function optimization module 1102.

[0208] The text analysis module 1101 is used to perform text analysis on the user opinion information corresponding to the candidate interface functions;

[0209] The candidate function optimization module 1102 is used to screen the interface candidate functions according to the text analysis results to obtain optimized interface candidate functions.

[0210] In one embodiment, see Fig.12 The rendering elements include channel rendering elements and scene rendering elements; the user interface recommendation unit 703 includes a function location determination module 1201, a page appearance determination module 1202 and a user interface loading module 1203.

[0211] A function position determination module 1201 is used to determine the position of each interface candidate function in the page according to the channel rendering element;

[0212] The page appearance determination module 1202 is used to determine the page appearance according to the scene rendering elements; wherein the page appearance includes page color and page style;

[0213] The user interface loading module 1203 is used to generate a recommended user interface according to the position of each candidate interface function in the page and the appearance of the page, and load it into the development toolkit.

[0214] From the hardware level, in order to automatically adjust the user interface, determine the user interface solution suitable for channel application through data analysis, and form a personalized user interface design, the present application provides an embodiment of an electronic device for implementing all or part of the contents of the user interface automatic multi-channel deployment method, and the electronic device specifically includes the following contents:

[0215] Processor, memory, communication interface and bus; wherein the processor, memory and communication interface communicate with each other through the bus; the communication interface is used to realize information transmission between the user interface automation multi-channel deployment device and related devices such as core business systems, user terminals and related databases; the logic controller can be a desktop computer, a tablet computer and a mobile terminal, etc., but the present embodiment is not limited thereto. In the present embodiment, the logic controller can be implemented with reference to the embodiment of the user interface automation multi-channel deployment method and the embodiment of the user interface automation multi-channel deployment device in the embodiment, and the contents thereof are incorporated herein, and the repeated parts are not repeated.

[0216] It is understandable that the user terminal may include a smart phone, a tablet electronic device, a network set-top box, a portable computer, a desktop computer, a personal digital assistant (PDA), a vehicle-mounted device, a smart wearable device, etc. Among them, the smart wearable device may include smart glasses, a smart watch, a smart bracelet, etc.

[0217] In practical applications, part of the user interface automation multi-channel deployment method can be executed on the electronic device side as described above, or all operations can be completed in the client device. The specific selection can be based on the processing capability of the client device and the limitations of the user's usage scenario. This application does not limit this. If all operations are completed in the client device, the client device may also include a processor.

[0218] The client device may have a communication module (i.e., a communication unit) that can communicate with a remote server to achieve data transmission with the server. The server may include a server on the task scheduling center side, and other implementation scenarios may also include a server on an intermediate platform, such as a server on a third-party server platform that has a communication link with the task scheduling center server. The server may include a single computer device, or a server cluster consisting of multiple servers, or a server structure of a distributed device.

[0219] Fig.13 FIG. 9 is a schematic block diagram of the system structure of the electronic device 9600 according to an embodiment of the present application. Fig.13 As shown, the electronic device 9600 may include a central processor 9100 and a memory 9140; the memory 9140 is coupled to the central processor 9100. It is worth noting that Fig.13 is exemplary; other types of structures may also be used to supplement or replace this structure to implement telecommunication functions or other functions.

[0220] In one embodiment, the user interface automation multi-channel deployment method function may be integrated into the central processing unit 9100. The central processing unit 9100 may be configured to perform the following control:

[0221] S101: When a user interface deployment request sent by a device to be deployed is received, a candidate user test interface is determined according to a channel to which the device to be deployed belongs.

[0222] S102: Perform edge computing and deep analysis on the functions in each candidate user test interface to determine the candidate interface functions.

[0223] S103: Generate a recommended user interface according to the predetermined rendering elements and the candidate interface functions.

[0224] S104: Sending the development toolkit containing the recommended user interface to the device to be deployed, so that the device to be deployed completes user interface deployment using the development toolkit.

[0225] From the above description, it can be seen that the user interface automated multi-channel deployment method provided in this application can automatically adjust the user interface, determine the user interface solution suitable for channel applications through A / B testing, edge computing and other data analysis processes, and dynamically load the software tool development kit to deploy an adapted user interface on each channel, combining the software tool development kit with the application scenarios of each channel to form a personalized user interface design.

[0226] In another embodiment, the user interface automation multi-channel deployment device can be configured separately from the central processing unit 9100. For example, the data composite transmission device user interface automation multi-channel deployment device can be configured as a chip connected to the central processing unit 9100, and the functions of the user interface automation multi-channel deployment method can be implemented through the control of the central processing unit.

[0227] like Fig.13 As shown, the electronic device 9600 may also include: a communication module, an input unit 9120, an audio processor 9130, a display 9160, and a power supply 9170. It is worth noting that the electronic device 9600 does not necessarily have to include Fig.13 In addition, the electronic device 9600 may also include Fig.13 For components not shown, reference may be made to the prior art.

[0228] like Fig.13 As shown, the central processing unit 9100 is sometimes also referred to as a controller or an operation control, and may include a microprocessor or other processor device and / or logic device, which receives input and controls the operation of various components of the electronic device 9600.

[0229] The memory 9140 may be, for example, one or more of a cache, a flash memory, a hard drive, a removable medium, a volatile memory, a non-volatile memory or other suitable devices. The above-mentioned information related to the failure may be stored, and a program for executing the relevant information may also be stored. The CPU 9100 may execute the program stored in the memory 9140 to implement information storage or processing, etc.

[0230] The input unit 9120 provides input to the central processing unit 9100. The input unit 9120 is, for example, a key or a touch input device. The power supply 9170 is used to provide power to the electronic device 9600. The display 9160 is used to display display objects such as images and texts. The display may be, for example, an LCD display, but is not limited thereto.

[0231] The memory 9140 may be a solid-state memory, such as a read-only memory (ROM), a random access memory (RAM), a SIM card, etc. It may also be a memory that saves information even when the power is off, can be selectively erased, and is provided with more data, examples of which are sometimes referred to as EPROMs, etc. The memory 9140 may also be some other type of device. The memory 9140 includes a buffer memory 9141 (sometimes referred to as a buffer). The memory 9140 may include an application / function storage unit 9142, which is used to store application programs and function programs or processes for executing the operation of the electronic device 9600 through the central processor 9100.

[0232] The memory 9140 may also include a data storage unit 9143 for storing data, such as contacts, digital data, pictures, sounds, and / or any other data used by the electronic device. The driver storage unit 9144 of the memory 9140 may include various drivers for communication functions of the electronic device and / or for executing other functions of the electronic device (such as messaging applications, address book applications, etc.).

[0233] The communication module is a transmitter / receiver that sends and receives signals via antenna 9111. The communication module (transmitter / receiver) 9110 is coupled to the central processor 9100 to provide input signals and receive output signals, which may be the same as the case of a conventional mobile communication terminal.

[0234] Based on different communication technologies, multiple communication modules may be provided in the same electronic device, such as a cellular network module, a Bluetooth module and / or a wireless LAN module, etc. The communication module (transmitter / receiver) 9110 is also coupled to a speaker 9131 and a microphone 9132 via an audio processor 9130 to provide an audio output via the speaker 9131 and receive an audio input from the microphone 9132, thereby realizing a common telecommunication function. The audio processor 9130 may include any suitable buffer, decoder, amplifier, etc. In addition, the audio processor 9130 is also coupled to the central processor 9100, so that recording can be performed on the local machine through the microphone 9132, and the sound stored on the local machine can be played through the speaker 9131.

[0235] The embodiments of the present application also provide a computer-readable storage medium capable of implementing all the steps of the user interface automation multi-channel deployment method in the above embodiment, where the execution subject is a server or a client. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, all the steps of the user interface automation multi-channel deployment method in the above embodiment are implemented. For example, when the processor executes the computer program, the following steps are implemented:

[0236] S101: When a user interface deployment request sent by a device to be deployed is received, a candidate user test interface is determined according to a channel to which the device to be deployed belongs.

[0237] S102: Perform edge computing and deep analysis on the functions in each candidate user test interface to determine the candidate interface functions.

[0238] S103: Generate a recommended user interface according to the predetermined rendering elements and the candidate interface functions.

[0239] S104: Sending the development toolkit containing the recommended user interface to the device to be deployed, so that the device to be deployed completes user interface deployment using the development toolkit.

[0240] From the above description, it can be seen that the user interface automated multi-channel deployment method provided in this application can automatically adjust the user interface, determine the user interface solution suitable for channel applications through A / B testing, edge computing and other data analysis processes, and dynamically load the software tool development kit to deploy an adapted user interface on each channel, combining the software tool development kit with the application scenarios of each channel to form a personalized user interface design.

[0241] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, devices, 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.

[0242] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (apparatus), 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 generate 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.

[0243] 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.

[0244] 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.

[0245] The present invention uses specific embodiments to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A user interface automated multi-channel deployment method, characterized in that: include: When receiving a user interface deployment request sent by a device to be deployed, determining a candidate user test interface according to the channel to which the device to be deployed belongs; Constructing a decision tree based on the functions in the candidate user test interface, and performing a pessimistic pruning operation on the decision tree according to preset pruning constraints to determine the interface candidate functions, wherein each function corresponds to each node in the decision tree; or collecting the click frequency of each function in the candidate user test interface, and determining the interface candidate functions according to the click frequency; generating a recommended user interface according to the predetermined rendering elements and the candidate interface functions; The development toolkit containing the recommended user interface is sent to the device to be deployed, so that the device to be deployed completes the user interface deployment by using the development toolkit.

2. The user interface automation multi-channel deployment method according to claim 1, characterized in that: When receiving a user interface deployment request sent by a to-be-deployed device, determining a candidate user test interface according to a channel to which the to-be-deployed device belongs includes: When receiving the user interface deployment request, generating multiple user test interfaces according to the channel to which the device to be deployed belongs; Perform A / B testing on each user test interface and determine candidate user test interfaces based on the user conversion rate corresponding to each user test interface.

3. The user interface automation multi-channel deployment method according to claim 1, characterized in that: The edge computing and deep analysis of the functions in each candidate user test interface to determine the candidate interface functions include: Performing text analysis on user opinion information corresponding to the candidate functions of the interface; The candidate interface functions are screened according to the text analysis results to obtain optimized candidate interface functions.

4. The user interface automation multi-channel deployment method according to claim 1, characterized in that: The rendering elements include channel rendering elements and scene rendering elements; the generating of the recommended user interface according to the predetermined rendering elements and the interface candidate functions includes: Determine the position of each interface candidate function in the page according to the channel rendering elements; Determining a page appearance according to the scene rendering elements; wherein the page appearance includes page color and page style; A recommended user interface is generated according to the position of each candidate interface function in the page and the appearance of the page, and loaded into the development toolkit.

5. The user interface automation multi-channel deployment method according to claim 1, characterized in that: The pessimistic pruning operation is performed on the decision tree according to the preset pruning constraint condition, including: Calculate the number of misjudgments of leaf nodes in the decision tree before and after pruning using a preset penalty factor; If the number of false positives after pruning is less than the number of false positives before pruning, pruning is performed.

6. The user interface automation multi-channel deployment method according to claim 1, characterized in that: Before generating a recommended user interface according to the predetermined rendering elements and the candidate interface functions, the method further includes: The development toolkit containing the recommended user interface is sent to the deployed device, so that the deployed device completes the user interface update by using the development toolkit.

7. A user interface automated multi-channel deployment device, characterized in that: include: A test interface determination unit, configured to determine a candidate user test interface according to a channel to which the device to be deployed belongs when receiving a user interface deployment request sent by the device to be deployed; A candidate function determination unit is used to construct a decision tree based on the functions in the candidate user test interface, and perform a pessimistic pruning operation on the decision tree according to preset pruning constraints to determine the interface candidate functions; wherein each function corresponds to each node in the decision tree; or collect the click frequency of each function in the candidate user test interface, and determine the interface candidate functions according to the click frequency; A user interface recommendation unit, configured to generate a recommended user interface based on predetermined rendering elements and the candidate interface functions; The interface deployment unit is used to send a development toolkit containing the recommended user interface to the device to be deployed, so that the device to be deployed completes the user interface deployment using the development toolkit.

8. An electronic 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 program, the steps of the user interface automated multi-channel deployment method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for automatic multi-channel deployment of a user interface as claimed in any one of claims 1 to 6 are implemented.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the steps of the method for automated multi-channel deployment of a user interface as claimed in any one of claims 1 to 6 are implemented.

Images