Dynamic form configuration method and system based on user data

Abstract

The invention provides a dynamic form configuration method and system based on user data. The method comprises the steps of collecting a first behavior feature of a user based on historical interaction data of the user to construct a behavior distribution data set; extracting preference characteristics of the user based on the behavior distribution data set, and determining a classification label of the user based on the preference characteristics; according to a preset form rule base, the relevance between the classification labels and each form field is analyzed, and a mapping relation table is generated according to an analysis result; determining all fields to be displayed according to the mapping relation table, and determining the priority of each field to be displayed based on the behavior distribution data set; configuring a preliminary display position of each to-be-displayed field according to the priority, and performing matching analysis on each preliminary display position to adjust the priority; and configuring a target display position of each to-be-displayed field based on the adjusted priority, and generating a target form. According to the scheme, the problem that a traditional form is difficult to meet different user requirements is solved.

Description

Technical Field

[0001] The present application relates to the field of data processing, and in particular to a method and system for dynamic form configuration based on user data. Background Art

[0002] With the increasing importance of information technology and personalized services, leveraging big data analytics to uncover potential user needs and create customized experiences has become a key area of ​​competition across various industries. This not only impacts user satisfaction but also directly impacts the efficiency and accuracy of enterprise services. In particular, leveraging deep insights from big data mining to dynamically adjust form content based on user characteristics has become a core proposition for improving user experience.

[0003] However, many current solutions for personalized form configuration often rely on static rules or simple user categorization, failing to truly meet users' actual needs. These solutions only perform superficial processing of surface data, lacking in-depth big data mining, making it difficult to accurately capture the diversity of user behavior and the dynamic changes in preferences. This results in a mismatch between form content and user expectations, significantly compromising the user experience.

[0004] Looking deeper, the core issue lies in the inadequate ability to analyze and mine big data for user behavior characteristics and preference data. User behavior is complex and changeable, making it difficult to construct an accurate user profile based solely on basic data. Without a complete user profile formed through big data mining, precise form field design is impossible. Furthermore, due to the incompleteness of the user profile, the system is unable to effectively establish a mapping relationship between user characteristics and form configurations. The display priority of form fields is difficult to dynamically adjust based on real-time user needs, leaving users facing redundant or irrelevant content when filling out forms. This results in existing technologies being poorly adapted to the needs of diverse users.

[0005] Therefore, the present application provides a method and system for dynamic form configuration based on user data to solve one of the above technical problems. Summary of the Invention

[0006] The purpose of this application is to provide a method and system for dynamic form configuration based on user data, which can solve at least one of the technical problems mentioned above. The specific solution is as follows: According to a specific embodiment of the present application, in a first aspect, the present application provides a method for configuring a dynamic form based on user data, comprising: Based on the user's historical interaction data, the user's first behavioral characteristics are collected to construct a behavioral distribution data set; based on the behavioral distribution data set, the user's preference characteristics are extracted, and the user's classification label is determined based on the preference characteristics; according to the preset form rule library, the association between the classification label and each form field is analyzed, and a mapping relationship table is generated according to the analysis results; according to the mapping relationship table, all fields to be displayed are determined, and based on the behavioral distribution data set, the priority of each field to be displayed is determined; according to the priority, a preliminary display position of each field to be displayed is configured, and a matching analysis is performed on each preliminary display position to adjust the priority; based on the adjusted priority, a target display position of each field to be displayed is configured to generate a target form.

[0007] According to a specific embodiment of the present application, in a second aspect, the present application provides a dynamic form configuration system based on user data, comprising: A collection unit is used to collect the user's first behavioral characteristics based on the user's historical interaction data to construct a behavioral distribution data set; a processing unit is used to extract the user's preference characteristics based on the behavioral distribution data set, and determine the user's classification label based on the preference characteristics; according to a preset form rule library, the association between the classification label and each form field is analyzed, and a mapping relationship table is generated according to the analysis results; according to the mapping relationship table, all fields to be displayed are determined, and based on the behavioral distribution data set, the priority of each field to be displayed is determined; according to the priority, a preliminary display position of each field to be displayed is configured, and a matching analysis is performed on each preliminary display position to adjust the priority; based on the adjusted priority, a target display position of each field to be displayed is configured to generate a target form.

[0008] This application provides a method and system for dynamic form configuration based on user data, which has at least the following beneficial effects compared to the prior art: 1. This application constructs a behavioral distribution data set by collecting the first behavioral characteristics, which can systematically integrate multi-dimensional behavioral data such as user operation frequency, stay duration, page jump path, etc., providing a structured basis for subsequent analysis; by extracting preference characteristics and determining classification labels through the behavioral distribution data set, it can accurately identify users' personalized tendencies in field selection, content filling, etc., and realize refined segmentation of user groups.

[0009] 2. This application analyzes the correlation between classification labels and form fields and generates a mapping relationship table, which can establish a dynamic association model between user characteristics and form elements, making the form design more in line with the needs of target users; based on the mapping relationship table, the fields to be displayed are determined and their priority is calculated, which can quantify the importance of the fields in user interaction and avoid form information overload; the initial display position is matched and analyzed to adjust the priority, and the adaptability of user behavior and field layout is verified in real time to achieve dynamic calibration of priority, which can form a personalized form layout that conforms to user operating habits, reduce the time cost of users to find key fields, improve form filling efficiency and completion rate, and continuously adapt to changes in user preferences through dynamic optimization mechanism to enhance the interactive experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 A flow chart showing a method for dynamic form configuration based on user data is shown; Figure 2 A flow chart of a method for constructing a behavior distribution dataset using a first behavior feature is shown; Figure 3 A flow chart of a method for analyzing user preferences and generating classification labels is shown; Figure 4 A flow chart of a method for generating a mapping relationship table is shown; Figure 5 A flow chart of a method for determining fields to be displayed and their priorities is shown; Figure 6 A flow chart showing a method for configuring a preliminary display position of each field to be displayed is shown; Figure 7 A flow chart of a method for adjusting the priority of each field to be displayed is shown; Figure 8 A flow chart of a method for initial optimization of a target form is shown; Figure 9 A flow chart of a method for secondary optimization of a target form is shown; Figure 10 A unit block diagram of a dynamic form configuration system based on user data according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0011] To make the objectives, technical solutions, and advantages of this application more clear, this application will be further described in detail below with reference to the accompanying drawings. Obviously, the embodiments described are only some of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making any creative efforts are within the scope of protection of this application.

[0012] The terms used in the examples of this application are for the purpose of describing specific embodiments only and are not intended to limit this application. The singular forms "a," "the," and "the" used in the examples of this application and the appended claims are also intended to include plural forms, and unless the context clearly indicates otherwise, "a plurality" generally includes at least two.

[0013] It should be understood that the term "and / or" as used herein is merely a description of the relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " in this document generally indicates that the associated objects are in an "or" relationship.

[0014] It should be understood that although the terms first, second, third, etc. may be used to describe in the embodiments of the present application, these descriptions should not be limited to these terms. These terms are only used to distinguish the descriptions. For example, without departing from the scope of the embodiments of the present application, the first may also be referred to as the second, and similarly, the second may also be referred to as the first.

[0015] As used herein, the words "if" and "if" may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to the determination" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)," depending on the context.

[0016] It should also be noted that the terms "include," "comprises," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a product or system comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such product or system. In the absence of further limitations, an element defined by the phrase "comprises a..." does not exclude the presence of other identical elements in the product or system comprising the element.

[0017] It should be noted in particular that any symbols and / or numbers in the specification that are not marked in the accompanying drawings are not drawing marks.

[0018] The optional embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0019] The embodiment provided in this application is an embodiment of a dynamic form configuration method based on user data.

[0020] The following combination Figure 1 The embodiments of the present application are described in detail.

[0021] Figure 1 A flow chart of a method for configuring a dynamic form based on user data is shown. Figure 1 As shown, the following steps are included: Step S101: Based on the user's historical interaction data, the user's first behavior feature is collected to construct a behavior distribution data set.

[0022] Step S102: extracting the user's preference features based on the behavior distribution data set, and determining the user's classification label based on the preference features.

[0023] Step S103: Analyze the association between the classification label and each form field according to the preset form rule library, and generate a mapping relationship table according to the analysis result.

[0024] Step S104: determining all fields to be displayed according to the mapping relationship table, and determining the priority of each field to be displayed based on the behavior distribution data set.

[0025] Step S105 : configuring a preliminary display position of each to-be-displayed field according to the priority, and performing a matching analysis on each preliminary display position to adjust the priority.

[0026] Step S106: configuring a target display position for each field to be displayed based on the adjusted priority, and generating a target form.

[0027] First, a big data analysis is performed on a large number of historical user interaction records to mine behavioral data related to the current user's form interaction and use it as the first behavioral feature. Specifically, by extracting preset types of behavioral data from the user's historical interaction records, the preset types include operation frequency, dwell time, field input speed, and field operation sequence, which can be set according to actual business needs. In this way, multi-dimensional behavioral data of users in different form interaction scenarios is extracted, and the extracted results are used as the first behavioral feature corresponding to the user. Among them, form interaction scenarios include registration, ordering, or form filling. Subsequently, all first behavioral features are classified and organized to construct a behavioral distribution dataset. The behavioral distribution dataset can be used to obtain the distribution of users' behavioral patterns in form interactions. This behavioral distribution dataset integrates multi-dimensional data such as time distribution, page jump path, and operation characteristics to form a three-dimensional user behavior portrait, avoiding the one-sidedness of a single indicator and providing strong data support for subsequent user preference mining.

[0028] In some embodiments, a behavior distribution data set is constructed after all first behavior features are classified and sorted. Specifically, pre-established classification rules, such as time window division, page jump characteristics, etc., are used to classify and sort the first behavior features in different form interaction scenarios, so that the first behavior features are grouped according to time distribution and page jump characteristics. After grouping and sorting, multiple groups of behavior pattern data are obtained to form a preliminary behavior distribution data set. Taking the form filling scenario as an example, by grouping all collected user operation frequencies (such as the number of clicks per minute) and dwell time (such as the number of seconds spent on a single page) according to time distribution (such as 9:00-11:00 am on weekdays) and jump paths (such as home page-form page-confirmation page), the user's high-frequency operation periods and typical interaction paths are identified to form a preliminary behavior distribution data set. Based on the behavior distribution data set, a three-dimensional user behavior portrait can be formed. For example, a user's operation frequency between 9:00 and 11:00 a.m. on weekdays is 5 times per minute, each time they stay on the form page for about 30 seconds, and 80% of the interactions follow the jump path of "home page-form page-confirmation page". This type of data provides basic support for the time and path dimensions of subsequent preference analysis.

[0029] In the above embodiment, the user's first behavioral characteristics are collected from the user's historical interaction data to construct a behavioral distribution data set, which can truly and comprehensively reflect the user's individualized behavioral patterns in form operations, and provide an accurate data basis for subsequent feature extraction and personalized configuration. Based on this behavioral distribution data set, the user's preference characteristics in field selection and filling content are extracted, and the user's classification label is determined accordingly, thereby achieving structured classification of user attributes, which helps to improve the pertinence and accuracy of subsequent recommendation and display strategies. For example, adjusting the page layout based on user preferences can significantly improve the user experience, reduce operation time, and ultimately achieve a higher business conversion rate.

[0030] Figure 2 A flow chart of a method for constructing a behavior distribution data set through a first behavior feature is shown. Figure 2 As shown, the following steps are included: Step S201: extracting behavior data of a preset type from user historical interaction data as a first behavior feature.

[0031] Step S202: Based on a preset classification rule, all first behavior features are grouped according to interaction time and page jump path to obtain multiple groups of behavior pattern data.

[0032] Step S203 : performing consistency check on each set of behavior pattern data to find abnormal behavior data therein, and adjusting corresponding behavior pattern data according to the abnormal behavior data.

[0033] Step S204: constructing a behavior distribution data set based on each set of adjusted behavior pattern data.

[0034] In an embodiment of the present application, for each set of behavioral pattern data in the preliminary behavioral distribution dataset, the user's field filling habits and form operation habits are mined. Field filling habits include field priority, input speed, and number of modifications, while form operation habits include jump paths, time distribution, and page dwell time. When mining user field filling habits and form operation habits, multiple sets of behavioral pattern data can be compared across multiple dimensions, focusing on the consistency of behavioral data for the same form fields across different sets of behavioral pattern data. Taking field filling habit analysis as an example, the focus is on user input speed and operation sequence, and a time threshold is set. For example, field filling times greater than 15 seconds are considered abnormal and data filtering is performed. For example, if the average time a user takes to fill in the "name" field is 10 seconds, if a particular entry takes 20 seconds, exceeding the time threshold (15 seconds), it will be marked as an abnormal record and removed from the corresponding behavioral pattern data. By removing such atypical data, the interference of noise such as network latency and user distraction on the analysis results is reduced, and the representativeness of the data sample is improved. Through the above means, the behavioral pattern data is adjusted according to abnormal behavior data.

[0035] In the above embodiment, form operation habits are mined based on each adjusted set of behavioral pattern data. Correlation analysis of each set of behavioral pattern data is performed to extract potential connections between user preferences and page redirection, such as the probability of redirecting directly to the confirmation page after completing a form. Data comparison tools are then used to cross-validate the temporal distribution and operation frequency of each set of behavioral pattern data. If a user's operation frequency across multiple scenarios is stable at 4-6 times per minute, and the temporal distribution is concentrated within a fixed time period, their form operation habits are determined to be consistent. Ultimately, an interaction preference distribution encompassing preference type and behavior stability is constructed to generate a behavioral distribution dataset, providing a reliable basis for personalized design. Preference types include quick filling and cautious filling. For example, if a user consistently spends 40 seconds on a form page and consistently follows the sequence of "filling required fields first, then filling optional fields, then checking multiple times," their preference type is "cautious filling." Subsequent dynamic adjustments to the form design can be made accordingly, such as highlighting required fields and optimizing the entry point for the checklist function, shortening the user's operation path and improving interaction efficiency.

[0036] In the above embodiment, log parsing tools (such as Splunk) are used to extract detailed behavioral features, such as the total duration of stay on the form page, the priority of filling in required and optional items, etc., so as to construct a complete behavioral distribution data set.

[0037] In the above example, each link supports each other, forming a complete behavioral analysis chain, from preliminary data grouping to anomaly marking, and then to preference distribution and detailed feature extraction. This logical design ensures that the analysis results are both comprehensive and accurate, providing strong support for subsequent personalized recommendations or interface optimization. For example, adjusting the page layout based on user preferences can significantly improve the user experience, reduce operation time, and ultimately achieve higher business conversion rates.

[0038] Figure 3 A flow chart of a method for analyzing user preferences and generating classification labels is shown in FIG. Figure 3 As shown, the following steps are included: Step S301: extracting first indicator data of each form field according to the behavior distribution data set, and determining whether the first indicator data is higher than a first indicator threshold.

[0039] Step S302: If the first indicator data is higher than the first indicator threshold, obtain a preference feature based on the analysis of the first indicator data.

[0040] Step S303: Perform data mapping processing based on the preference characteristics to obtain classification labels that match the preference characteristics.

[0041] In this embodiment of the present application, clustering analysis algorithms, such as the K-means clustering algorithm, are used to group the first indicator data based on the behavioral distribution dataset. This process focuses on extracting key features from the user's field selection tendencies and content filling preferences, and based on these features, determines the final classification label of the first indicator data as the user's classification label.

[0042] In the above embodiment, the priority, input speed, input length, or click frequency of each form field in the behavior distribution data set is statistically quantified through a data grouping tool (such as an Excel pivot table, etc.), and the first indicator data under each group is obtained, which can be used to understand the user's preferences in form interaction. The priority of the field usually reflects the user's priority for certain information. In the form filling scenario, the user's priority on different form fields is obtained through the data grouping tool. It is found that when users fill in personal information, 80% of the time they prefer to choose the "name" field rather than the "contact information" field. This preliminary preference grouping data provides a basic direction for subsequent analysis.

[0043] In the above embodiment, for each first indicator data, an abnormality judgment can be made through a pre-established comparison rule. Assuming that the first indicator data is click frequency, the click frequency threshold in the corresponding comparison rule is 3 times per minute. If a user clicks only once per minute in a certain form filling, the click frequency is marked as abnormal. This abnormality may be caused by the user's unfamiliarity with the form design or temporary distraction. The data related to the click frequency will be removed from the behavioral distribution data set to ensure the reliability of subsequent analysis. It should be noted that this marking method is not simply to remove data, but to provide a reference for the subsequent analysis of preference characteristics to avoid interference with the overall tendency judgment due to outliers.

[0044] In the above example, the adjusted behavioral distribution dataset is deeply mined to extract page interaction details, such as the number of checks before clicking the "Next" button and the jump paths between fields. For example, the analysis found that a user checked their form an average of three times before clicking "Next," and each check took 25 seconds. This detailed feature indicates that the user may have high requirements for form accuracy. Extracting this key feature data can help determine user preferences, such as whether they prefer cautious operation or quick submission.

[0045] It's important to note that matching preference characteristics with classification labels can be achieved through common data mapping tools (such as Tableau association analysis and machine learning classification models). Assuming the classification labels are "fast users" and "cautious users," the mapping tool reveals that 90% of a user's actions meet the characteristics of a "cautious user." For example, a user with cautious preferences, such as repeated checking and prolonged page dwell time, would ultimately be classified as a "cautious user." This categorization can provide targeted guidance for subsequent form design, such as adding prompts for cautious users.

[0046] In one example, for the grouping of field priorities, assuming that a user completes the required items first 8 out of 10 times when filling out a form, this preference feature can further refine the user portrait. For abnormal marking, you can combine time period analysis. If the user's frequency is abnormally low during non-working hours, it may be related to personal habits rather than form design issues. For the extraction of operation detail features, you can pay attention to the user's jump path in the page, such as whether they frequently return to the previous page. This behavior may reflect confusion about the form logic. For classification matching, you can introduce a multi-label system, such as marking users as "cautious users" and "high-frequency users" at the same time to meet the needs of different scenarios.

[0047] In the above example, a complete analysis chain is formed, from initial grouping to anomaly adjustment, to detail extraction, and finally to classification labels. This approach ensures the comprehensiveness and accuracy of user preference classification data, providing a reliable basis for subsequent form optimization, such as adjusting field order or page layout based on user classification, thereby improving user operation efficiency and satisfaction.

[0048] Figure 4 A flow chart of a method for generating a mapping relationship table is shown. Figure 4 As shown, the following steps are included: Step S401: Obtain the logical condition of each form field from a preset form rule library.

[0049] Step S402: Determine the degree of association between each form field and the category label based on each logical condition.

[0050] Step S403: Generate a mapping relationship table based on the association degree.

[0051] In an embodiment of the present application, based on the determined classification labels and combined with the preset form rule library, the association between each classification label and the form field is analyzed through a semantic matching algorithm (such as cosine similarity calculation), and a mapping relationship table containing classification labels, form fields and association degrees is generated, providing a quantitative basis for subsequent field configuration.

[0052] In the above embodiment, on the basis of the classification label, when preliminary association processing can be performed on the characteristics of the field type, the user's preference data can be matched with the field type through common data comparison tools (such as cross-tab analysis, correlation coefficient calculation). Suppose in a form design scenario, a certain type of user is marked as preferring simple operations. Through the comparison tool, it is found that they are more inclined to select radio buttons rather than open text boxes. This association information can initially form a mapping relationship table to provide a basis for subsequent optimization of the form layout. It should be noted that the purpose of this preliminary association is to sort out the potential connection between user habits and field types to ensure that subsequent adjustments are supported by data.

[0053] In the above embodiment, when performing a deep comparison using a preset form rule library, attention can be paid to the impact of field characteristics on user interaction. The preset form rule library specifies the logical conditions for each form field. For example, if a text box requires deep input, and a category label is "Quick Fill," the association between the text box and the category label is adjusted to a low value. This adjustment method can more realistically reflect user usage habits and avoid interaction barriers caused by unreasonable field design.

[0054] In the above embodiment, the mapping relationship table can reduce the time users waste on infrequently used fields. By extracting behavioral details and building mapping relationships, we can provide form design solutions that better meet the needs of different user groups. These methods support each other and jointly improve the pertinence and practicality of form design.

[0055] Figure 5 A flow chart of a method for determining fields to be displayed and their priorities is shown. Figure 5 As shown, the following steps are included: Step S501: The form fields in the mapping relationship table whose association degrees meet a preset state are used as fields to be displayed.

[0056] Step S502: Obtain second indicator data for each field to be displayed based on the behavior distribution data set.

[0057] Step S503: Obtain a comprehensive weight of each field to be displayed according to the second indicator data, and determine a priority based on the comprehensive weight.

[0058] In an embodiment of the present application, the form fields whose association degree in the mapping relationship table meets the preset state are used as fields to be displayed. The preset state is a state where the association degree is set to high or medium, and the fields to be displayed are assigned priorities based on the user's behavior distribution data set.

[0059] In the above embodiment, assuming that the user click frequency for each form field is extracted as the second indicator data based on the behavioral distribution dataset, it is found that users click on radio button fields an average of 20 times per minute, while users click on text input fields an average of 5 times per minute. This difference indicates that radio button fields are more in line with their usage habits. Therefore, in the preliminary priority sorting, priority weights are calculated based on click frequency, and radio button fields are assigned a higher priority weight than text input fields. For example, using Min-Max normalization, click frequency is mapped to a weight interval of [0.4, 1.0] to calculate the corresponding priority weight. To avoid a weight of 0, the minimum value of the weight interval is set to 0.4. The priority weight is then calculated by first calculating the difference between the field's click rate and the minimum click rate, then calculating the difference between the maximum click rate and the minimum click rate, calculating the ratio of the two differences and multiplying it by 0.6, and finally adding the result to the minimum value of the weight interval, 0.4. The minimum click rate is determined based on the minimum click frequency among all form fields, for example, 2, and the maximum click rate is determined based on the maximum click frequency among all form fields, for example, 30. In this case, the radio button field has a priority weight of 0.79, and the text input field has a priority weight of 0.46. This method helps identify which field types are more suitable for specific user groups and provides a basis for subsequent optimization. Secondary indicator data can also include the length of time it takes to complete a field.

[0060] In the above embodiment, the preliminary priority ranking results are analyzed by combining historical interaction data with a preset form rule library. The threshold settings for field click frequency in the preset form rule library can be considered. For example, if the preset form rule library specifies a field click frequency threshold of 3 clicks per minute, and a field's click frequency in the historical interaction data is only 2 clicks per minute, then the field below the click frequency threshold will be downgraded. The priority weights in the preliminary priority ranking are then combined to form an adjusted field priority ranking. For example, for each field below the click frequency threshold, the priority weight corresponding to its preliminary priority ranking is downgraded by a preset downgrading factor (e.g., 0.5). The adjusted weight is then calculated by multiplying the priority weight by the downgrading factor. In this case, according to the aforementioned priority weight calculation method, a field with a click frequency of only 2 clicks per minute would have a priority weight of 0.4 in the preliminary priority ranking. Since its click frequency is below the click frequency threshold, its adjusted weight should be 0.2. This adjustment better meets user needs, avoiding placing infrequently used fields in prominent locations, thereby reducing distractions during user operations.

[0061] In the above example, prioritizing the displayed fields based on multiple dimensions ensures that the final display priority is more aligned with user habits, helping to improve the overall interaction efficiency of the form. Through this multifaceted analysis and adjustment, a complete optimization chain, from preliminary mapping to final weighted data, is formed, ensuring that form design is more tailored to user needs.

[0062] Figure 6 A flow chart of a method for configuring the initial display position of each field to be displayed is shown. Figure 6 As shown, the following steps are included: Step S601: sort all fields to be displayed in descending order according to their priorities.

[0063] Step S602: Divide the vertical space of the form into a high-frequency area, a medium-frequency area, and a low-frequency area.

[0064] Step S603: Determine whether the sequence of each field to be displayed after sorting is less than the first sequence number.

[0065] Step S604: If the order of the field to be displayed is less than the first order number, the high-frequency area is configured as a preliminary display position of the field to be displayed.

[0066] Step S605: If the order of the field to be displayed is greater than the first sequence number, it is determined whether the order of the field to be displayed is less than the second sequence number.

[0067] Step S606: If the order of the field to be displayed is less than the second order number, the intermediate frequency area is configured as the initial display position of the field to be displayed.

[0068] Step S607: If the order of the field to be displayed is greater than the second sequence number, the low-frequency area is configured as the initial display position of the field to be displayed.

[0069] In an embodiment of the present application, the vertical space of the form is divided into a high-frequency area, a medium-frequency area, and a low-frequency area, wherein the high-frequency area is generally the area near the top of the page, and the relatively low-frequency area is the area near the bottom of the page, and the rest of the page is the medium-frequency area. When analyzing the association between behavioral characteristics and the position of form fields, the user's field filling habits on different form fields are identified, such as click frequency or filling time. Through these field filling habits, the distribution of behavioral characteristics related to the field position is extracted, and a preliminary judgment is made on which fields are more suitable for being placed in a prominent position, that is, the high-frequency area. Suppose that in a form design scenario, the historical data of a user group shows that their click rate on the top field of the form is as high as 70%, while on the bottom field it is only 20%. This distribution feature suggests that the top position is more attractive to users, so the preliminary matching degree information will tend to arrange form fields with higher priority in the high-frequency area.

[0070] In the above embodiment, the first sequence number and the second sequence number are set according to application requirements. For example, the first sequence number can be set to the sequence number value corresponding to the top 30% percentile in the sorting, and the second sequence number can be the sequence number value corresponding to the top 70% percentile in the sorting.

[0071] Figure 7 A flow chart of a method for adjusting the priority of each field to be displayed is shown. Figure 7 As shown, the following steps are included: Step S701: extract third indicator data of each to-be-displayed field according to the behavior distribution data set, and determine the predicted position of each to-be-displayed field based on the third indicator data.

[0072] Step S702 : Compare the predicted position of each to-be-displayed field with the preliminary display position to obtain a matching score.

[0073] Step S703: determine whether the matching score corresponding to each to-be-displayed field is higher than a preset matching threshold.

[0074] In step S704, if the matching score corresponding to the field to be displayed is higher than the preset matching threshold, the weight value of the field to be displayed is increased by a preset increment to adjust the priority.

[0075] Step S705 : If the matching score corresponding to the field to be displayed is lower than the preset matching threshold, the weight value of the field to be displayed is reduced by a preset reduction rate to adjust the priority.

[0076] In an embodiment of the present application, the click-through rate of each field to be displayed is extracted as the third indicator data. All fields to be displayed are sorted in descending order based on click-through rate, and the predicted areas of each field to be displayed are assigned to high-frequency, medium-frequency, and low-frequency areas, respectively, according to the sorting. For example, the predicted positions of the fields to be displayed in the top 30% are in the high-frequency area, the predicted positions of the fields to be displayed in the top 30%-70% are in the medium-frequency area, and the predicted positions of the remaining fields to be displayed are in the low-frequency area. The predicted position of each form field is compared with the preliminary display position, for example, by comparing the coordinates of the interface. A matching score is calculated based on the comparison results. If there is a coordinate deviation between the predicted position and the preliminary display position, a matching score is calculated based on the coordinate deviation value. Regarding the processing of the preliminary matching score information, if the matching score of a field to be displayed is higher than a preset matching threshold, such as 60%, the field priority values ​​need to be rearranged, such as by increasing the weight value of the field to be displayed by a preset increment (e.g., 10%) to adjust its corresponding priority. If the match score for a field to be displayed falls below the preset match threshold, the weight of the field to be displayed is increased by a preset increment to adjust its corresponding priority. For example, if the match score for a field to be displayed is 75%, significantly above the match threshold, the priority of the field to be displayed is increased, and the initial display position of the field to be displayed is adjusted to the front of the form page, creating a new display position. This adjustment ensures that the fields users use most frequently are more accessible, reducing search time.

[0077] In the above embodiment, after obtaining the adjusted field position combination, behavioral features related to the form order can be further extracted. Suppose logs show that after the adjusted form order, users' completion rate for leading fields increased from 50% to 80%, while the rate of ignoring trailing fields was higher. This indicates that the leading position is indeed more in line with user habits. Ultimately, the dynamic adjustment solution will tend to fix high-frequency fields at the front and low-frequency fields at the back to optimize the overall interaction process.

[0078] In the above embodiment, combined with the real-time comparison requirements of user behavior, high-priority fields can be adjusted to the high-frequency area of ​​the form. Assuming that a certain field shows a continuous high level of user attention in real-time data and a click-through rate of 85%, it will be directly arranged at the top of the form to form the final form order result. This method can dynamically respond to user needs, ensure that the form design always fits the actual usage scenario, and at the same time improve the smoothness and efficiency of user operations. Through the above multi-angle analysis and adjustment, the optimization of the field position of the form can better meet user habits and reduce operational obstacles.

[0079] Figure 8 A flow chart of a method for initial optimization of a target form is shown, Figure 8 As shown, the following steps are included: Step S801: collecting the second behavior characteristics of the user in the target form to construct a first feedback data set.

[0080] Step S802: determining a first user rating corresponding to each to-be-displayed field based on the feedback data set, and monitoring whether each first user rating is lower than a preset rating threshold.

[0081] Step S803: If the first user score is lower than a preset score threshold, the to-be-displayed field corresponding to the first user score is used as the first optimized field.

[0082] Step S804: adjusting the priorities of all first optimized fields according to the first interaction data of each first optimized field, and updating the display positions of all first optimized fields according to the adjustment result to update the target form.

[0083] In an embodiment of the present application, based on the user's real-time feedback in the target form, behavioral pattern features related to the order of fields are extracted from the interaction data as second behavioral features, and all second behavioral features are preliminarily sorted to obtain a first feedback data set associated with the user experience. The satisfaction score of each field to be displayed is quantified based on the first feedback data set. If the score is lower than a preset score threshold, such as lower than 70 points, the field to be displayed is used as the first optimized field and a priority adjustment requirement for the first optimized field is triggered. All fields to be displayed that need to be optimized are obtained, their priorities are rearranged, and a dynamic display solution that matches the user feedback is determined based on the arrangement, and the target form is updated.

[0084] In the above embodiment, when analyzing the real-time feedback of users in form interactions, we can start with the essence of behavioral data and understand the user's operating habits when filling out forms. Record the user's dwell time, number of clicks, and jump order on each field to be displayed in the target form. Through this information, extract behavioral pattern features related to the order of fields, such as whether the user tends to complete the front fields first, or whether certain back fields are frequently skipped. Suppose in a certain form scenario, the extracted information shows that the average dwell time of users on the first three fields of the form is 30 seconds, while the last three fields are only 10 seconds, which indicates that users pay more attention to the front fields. After preliminary sorting, the first feedback data set associated with the user experience is obtained, which provides a basis for subsequent optimization.

[0085] In the above embodiment, the user satisfaction is quantitatively evaluated for the processing of the feedback data set to obtain the first user score corresponding to the field to be displayed. Assuming that the first user score is full of 100 points and the preset score threshold is 70 points, if the first user score of the field to be displayed in a certain form interaction is 65 points, which is lower than the preset score threshold, the field to be displayed will be used as the first optimized field, triggering the need to adjust the field order. The score calculation can be based on a combination of indicators such as the time required for the user to complete the form and the field completion rate. This method can intuitively reflect user experience problems, and then determine the field combination that needs to be optimized, providing a clear direction for subsequent adjustments.

[0086] In the above embodiment, after obtaining the field combination to be optimized, the field priority is rearranged in combination with the data distribution characteristics. Assuming that the first interactive data is click-through rate, the click-through rate of a first optimized field is as high as 80%, while the click-through rate of another first optimized field is only 30%. The priority of the first optimized field with a high click-through rate is increased, and the display position of the first optimized field with a high click-through rate is arranged to the front area of ​​the form. In this way, a dynamic display plan that matches user feedback is determined, ensuring that the adjusted order is more in line with user operating habits, and improving the usability of the form.

[0087] In the above embodiment, based on the dynamic display scheme and combined with the characteristics of behavioral patterns, feature information related to form adjustment is further extracted. Assuming that after the adjustment, the user completion rate of the front field increases from 60% to 85%, while the ignoring rate of the back field decreases, this indicates that the adjustment direction is correct. The final configuration optimization result will fix the high-attention fields in the front and the low-attention fields in the back, forming a form layout that better meets user needs. This optimization can effectively reduce invalid steps in user operations and improve the overall smoothness of interaction.

[0088] Figure 9 A flow chart of a method for secondary optimization of a target form is shown, Figure 9 As shown, the following steps are included: Step S901 : collecting the third behavior feature of the user in the updated target form to construct a second feedback data set.

[0089] Step S902: Determine the second user score corresponding to each first optimization field based on the second feedback data set, and monitor whether each second user score is lower than a preset score threshold.

[0090] Step S903: If the second user score is lower than a preset score threshold, the first optimized field corresponding to the second user score is used as the second optimized field.

[0091] Step S904: adjusting the priorities of all second optimized fields according to the second interaction data of the second optimized fields, and updating the display position of each second optimized field according to the adjustment result to update the target form again.

[0092] In an embodiment of the present application, based on the user's historical interaction records, the behavioral data before and after the adjustment of the first optimization field is obtained to obtain a third behavioral feature. A second feedback data set associated with the user experience is obtained to provide a basis for subsequent secondary optimization. Through the second feedback data set, the change range of the filling time and completion rate is quantified, and the satisfaction score of each first optimization field is comprehensively calculated, that is, the second user score. If the second user score is lower than the preset score threshold, such as lower than 70 points, the first optimization field is used as the second optimization field and the secondary adjustment demand for its priority is triggered. All second optimization fields that need secondary optimization are obtained, the priorities are rearranged, and the dynamic display scheme that matches the user feedback is determined based on the arrangement and the target form is updated for the second time.

[0093] In the above embodiment, when analyzing the user interaction history, behavioral data before and after the adjustment of the first optimized field is obtained, that is, the third behavioral feature. Assume that before the adjustment of a first optimized field, the average user filling time is 5 minutes and the completion rate is 70%, while after the adjustment, the time is shortened to 4 minutes and the completion rate is increased to 85%. After preliminary collation of these data, a second feedback data set is formed to provide a basis for subsequent analysis. The completion rate of the first optimized field can also be collected to facilitate multi-dimensional mining of user preference characteristics. Based on the processing of the second feedback data set, user satisfaction is quantitatively evaluated to obtain the second user score corresponding to the field to be displayed.

[0094] In the above example, regarding the change in the duration and completion rate of the second optimized field, assuming a preset threshold of 10% for the change, the actual duration was shortened by 20% and the completion rate increased by 15%, both exceeding the thresholds, indicating a significant adjustment effect on the second optimized field. However, if the change is lower than the threshold, for example, the duration is shortened by only 5% and the completion rate increased by 3%, further analysis of user behavior, such as whether certain content is frequently skipped, can be used to identify potential factors affecting efficiency.

[0095] In the above embodiment, after extracting the set of potential influencing factors, it is assumed that it is found that users pay more attention to the fields at the front after adjustment, while the ignoring rate of the fields at the back increases, which means that the layout order has a direct impact on user habits. Combined with the user's click rate and completion rate, that is, the second interaction data, the priority of the second optimized field is adjusted, such as increasing the priority of the second optimized field with a high click rate and arranging its display position to the front area of ​​the form. Through the above operation, it is possible to analyze which field positions are more in line with the operational logic, thereby providing improvement directions for subsequent form configurations. This method helps to ensure that the form design is close to the actual needs of users.

[0096] For example, suppose a second-best field in the original form was placed at the end and often overlooked by users. After adjusting its priority and moving it to the front, users' attention and completion rates increased significantly. By prioritizing frequently interacted fields based on user history, the optimized version aligns with user behavior. This adjustment can effectively reduce ineffective steps in user operations.

[0097] In the above example, optimizing the target form can also take into account user preferences. For example, if users tend to quickly fill out key fields in the morning on weekdays, but focus more on details in the afternoon, the order of fields can be fine-tuned based on the time of day. This refined design can further enhance the practicality of the form, allowing users to efficiently complete tasks in different scenarios.

[0098] Furthermore, the dynamic changes of user behavior data are monitored periodically, and relevant records of long-term trends are obtained from historical interaction data. The records are classified and processed to obtain a set of user behavior features that match the periodic monitoring, and the main direction of change in the behavior feature set is determined. The update features of the preference features are extracted based on the changes in the behavior feature set. If the change amplitude of the update features is low during extraction, the potential fluctuation factors of the user preferences are further analyzed to obtain the basis for preference updates related to long-term trends. Based on the basis for preference updates, an updated mapping relationship table is analyzed and the target form is updated according to the updated mapping relationship table using the same method as described above. The dynamic optimization mechanism is used to continuously adapt to changes in user preferences and enhance the interactive experience.

[0099] The present application also provides a system embodiment that is consistent with the above embodiment, which is used to implement the method steps of the above embodiment. The explanation based on the same name meaning is the same as the above embodiment, and has the same technical effect as the above embodiment, which will not be repeated here.

[0100] like Figure 10 As shown, the present application provides a dynamic form configuration system based on user data, including: The collecting unit 1001 is configured to collect the user's first behavior feature based on the user's historical interaction data to construct a behavior distribution dataset; Processing unit 1002 is used to extract user preference characteristics based on the behavior distribution data set, and determine the user's classification label based on the preference characteristics; analyze the association between the classification label and each form field according to the preset form rule library, and generate a mapping relationship table based on the analysis results; determine all fields to be displayed according to the mapping relationship table, and determine the priority of each field to be displayed based on the behavior distribution data set; configure a preliminary display position for each field to be displayed according to the priority, perform matching analysis on each preliminary display position to adjust the priority; configure a target display position for each field to be displayed based on the adjusted priority, and generate a target form.

[0101] Regarding the system in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0102] Although operations are described in a particular order in the drawings, this should not be understood as requiring that the operations be performed in the particular order shown or in serial order, or that all shown operations be performed to obtain the desired results. In certain circumstances, multitasking and parallel processing may be advantageous.

[0103] The methods and systems of the present application can be implemented using standard programming techniques, using rule-based logic or other logic to implement the various method steps. It should also be noted that the terms "system" and "module" as used herein and in the claims are intended to include implementations using one or more lines of software code and / or hardware implementations and / or devices for receiving input.

[0104] Any steps, operations or procedures described herein may be performed or implemented using one or more hardware or software modules, either alone or in combination with other devices. In one embodiment, the software modules are implemented using a computer program product comprising a computer-readable medium containing computer program code, which can be executed by a computer processor to perform any or all of the steps, operations or procedures described.

[0105] The foregoing description of the implementation of the present application has been provided for purposes of illustration and description. The foregoing description is not intended to be exhaustive or to limit the present application to the precise form disclosed, and various variations and modifications are possible in accordance with the above teachings or may result from the practice of the present application. These embodiments have been selected and described in order to illustrate the principles of the present application and its practical application, so as to enable those skilled in the art to utilize the present application in various embodiments and modifications as appropriate for the particular use contemplated.

[0106] Regarding the system in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0107] It is further understood that, unless otherwise specified, “connection” includes a direct connection where there are no other components between the two elements, and also includes an indirect connection where there are other elements between the two elements.

[0108] It should be further understood that although operations are described in a particular order in the drawings in the embodiments of the present application, this should not be construed as requiring that these operations be performed in the particular order shown or in a serial order, or that all of the illustrated operations be performed to obtain the desired results. In certain circumstances, multitasking and parallel processing may be advantageous.

[0109] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. This application is intended to encompass any variations, uses, or adaptations of the present application that follow the general principles of the present application and include common knowledge or customary techniques in the field of the present application that are not disclosed herein. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the scope of claims below.

[0110] It should be understood that the present application is not limited to the precise structures described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the scope of the appended claims.

[0111] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A dynamic form configuration method based on user data, characterized in that: include: Based on the user's historical interaction data, the user's first behavioral characteristics are collected to construct a behavioral distribution dataset; extracting user preference features based on the behavior distribution dataset, and determining a classification label for the user based on the preference features; Analyze the association between the classification label and each form field according to the preset form rule library, and generate a mapping relationship table based on the analysis results; Determine all fields to be displayed according to the mapping relationship table, and determine the priority of each field to be displayed based on the behavior distribution data set; configuring a preliminary display position of each of the to-be-displayed fields according to the priority, and performing a matching analysis on each of the preliminary display positions to adjust the priority; The target display position of each of the to-be-displayed fields is configured based on the adjusted priority, and a target form is generated.

2. The method according to claim 1, characterized in that The collecting of the user's first behavior feature based on the user's historical interaction data to construct a behavior distribution data set includes: Extracting a preset type of behavior data from the user historical interaction data as a first behavior feature; Based on preset classification rules, grouping all the first behavioral features according to interaction time and page jump path to obtain multiple groups of behavioral pattern data; Performing consistency check on each set of the behavior pattern data to find abnormal behavior data therein, and adjusting the corresponding behavior pattern data according to the abnormal behavior data; A behavior distribution data set is constructed based on each set of adjusted behavior pattern data.

3. The method according to claim 1, characterized in that The extracting the user's preference features based on the behavior distribution dataset, and determining the user's classification label based on the preference features, includes: extracting first indicator data of each form field according to the behavior distribution data set, and determining whether the first indicator data is higher than a first indicator threshold; If the first indicator data is higher than a first indicator threshold, obtaining the preference feature based on analysis of the first indicator data; Data mapping processing is performed based on the preference characteristics to obtain the classification label that matches the preference characteristics.

4. The method according to claim 1, wherein The analysis of the association between the classification label and each form field according to the preset form rule library and the generation of a mapping relationship table according to the analysis results include: Obtaining a logical condition for each form field from the preset form rule library; Determining the degree of association between each of the form fields and the category label based on each of the logical conditions; Based on the association degree, the mapping relationship table is generated.

5. The method according to claim 4, characterized in that The step of determining all fields to be displayed according to the mapping relationship table, and determining the priority of each field to be displayed based on the behavior distribution data set, includes: The form fields whose association degrees in the mapping relationship table meet a preset state are used as fields to be displayed; Obtaining second indicator data for each of the to-be-displayed fields according to the behavior distribution data set; A comprehensive weight of each of the to-be-displayed fields is obtained according to the second indicator data, and the priority is determined based on the comprehensive weight.

6. The method according to claim 5, characterized in that The configuring a preliminary display position of each of the to-be-displayed fields according to the priority level includes: Sort all the fields to be displayed in descending order according to the priority; Divide the vertical space of the form into high-frequency area, medium-frequency area and low-frequency area; Determine whether the order of each of the fields to be displayed after sorting is less than the first order number; If the order of the field to be displayed is less than the first order number, configuring the high-frequency area as a preliminary display position of the field to be displayed; If the order of the field to be displayed is greater than the first sequence number, determining whether the order of the field to be displayed is less than the second sequence number; If the order of the field to be displayed is less than the second order number, configuring the intermediate frequency region as a preliminary display position of the field to be displayed; If the sequence of the field to be displayed is greater than the second sequence number, the low-frequency area is configured as a preliminary display position of the field to be displayed.

7. The method according to claim 6, characterized in that The performing matching analysis on each of the preliminary placement positions to adjust the priority includes: extracting third indicator data of each of the to-be-displayed fields according to the behavior distribution data set, and determining a predicted position of each of the to-be-displayed fields based on the third indicator data; Comparing the predicted position of each to-be-displayed field with the preliminary display position to obtain a matching score; Determine whether the matching score corresponding to each of the to-be-displayed fields is higher than a preset matching threshold; If the matching score corresponding to the field to be displayed is higher than a preset matching threshold, the weight value of the field to be displayed is increased by a preset increment to adjust the priority; If the matching score corresponding to the field to be displayed is lower than a preset matching threshold, the weight value of the field to be displayed is reduced by a preset reduction rate to adjust the priority.

8. The method according to claim 1, characterized in that Also includes: collecting a second behavioral feature of the user in the target form to construct a first feedback data set; Determining a first user score corresponding to each of the to-be-displayed fields based on the feedback data set, and monitoring whether each of the first user scores is lower than a preset score threshold; If the first user score is lower than a preset score threshold, the to-be-displayed field corresponding to the first user score is used as a first optimized field; According to the first interaction data of each first optimized field, the priorities of all the first optimized fields are adjusted, and according to the adjustment result, the display positions of all the first optimized fields are updated to update the target form.

9. The method according to claim 8, characterized in that Also includes: collecting a third behavioral feature of the user on the updated target form to construct a second feedback data set; Determining a second user score corresponding to each of the first optimization fields based on the second feedback data set, and monitoring whether each of the second user scores is lower than the preset score threshold; If the second user score is lower than the preset score threshold, use the first optimized field corresponding to the second user score as the second optimized field; According to the second interaction data of the second optimized field, the priorities of all the second optimized fields are adjusted, and the display position of each second optimized field is updated according to the adjustment result to update the target form again.

10. A dynamic form configuration system based on user data, characterized in that: include: A collection unit, configured to collect the user's first behavior feature based on the user's historical interaction data to construct a behavior distribution data set; a processing unit, configured to extract preference features of the user based on the behavior distribution dataset, and determine a classification label of the user based on the preference features; Analyze the association between the classification label and each form field according to the preset form rule library, and generate a mapping relationship table based on the analysis results; Determine all fields to be displayed according to the mapping relationship table, and determine the priority of each field to be displayed based on the behavior distribution data set; configuring a preliminary display position of each of the to-be-displayed fields according to the priority, and performing a matching analysis on each of the preliminary display positions to adjust the priority; The target display position of each of the to-be-displayed fields is configured based on the adjusted priority, and a target form is generated.

Images