Financial transaction system user interface development and design system and method

Abstract

The invention discloses a system and a method for developing and designing a user interface of a financial transaction system, relates to the field of financial transactions, and solves the problem of insufficient safety of the existing system for developing and designing the user interface of the financial transaction system. The analysis module is used for analyzing the occurrence probability of a click event in each interface design sub-period according to historical login records and acquiring historical operation acquisition data of a user according to an analysis result, and the event prediction module is used for performing real-time operation prediction on a target user, acquiring a predicted click event according to a prediction result and outputting the predicted click event to the user. The page layout module is used for acquiring a plurality of interface sub-regions, performing position distance analysis on each interface sub-region and a user sight focus point, and marking a predicted click region according to an analysis result, and the operation control module is used for performing operation control on the user. The safety and the intelligence of the user interface of the financial transaction system can be improved.

Description

Technical Field

[0001] The present invention belongs to the field of financial transactions, relates to system development technology, and specifically is a system and method for developing and designing a user interface of a financial transaction system. Background Art

[0002] When developing a user interface with the existing system for developing and designing a user interface of a financial transaction system, the following specific defects exist: 1. The user interface developed by the existing system for developing and designing a user interface of a financial transaction system cannot predict the real-time operation behavior of a user based on the user's historical login data, and no separate operation window is developed for the prediction result, thus unable to effectively improve the operation efficiency of the user; 2. The user interface developed by the existing system for developing and designing a user interface of a financial transaction system cannot perform a commonality analysis on the operation data of the user in the current login state and the historical operation data, and cannot evaluate the operation security of the user according to the analysis result, thus resulting in certain potential safety hazards in financial transactions.

[0003] Therefore, we propose a system and method for developing and designing a user interface of a financial transaction system. Summary of the Invention

[0004] Aiming at the deficiencies of the existing technology, the purpose of the present invention is to provide a system and method for developing and designing a user interface of a financial transaction system, and the present invention aims to improve the security and operation efficiency of the financial transaction system.

[0005] To achieve the above purpose, the present invention adopts the following technical solutions: A system for developing and designing a user interface of a financial transaction system, comprising: A behavior collection module: used for collecting multiple historical login records of a target user on the user interface, dividing the time period covered by the historical login records into multiple interface design sub-time periods, obtaining each click event involved in the historical login records, analyzing the occurrence probability of the click events in each interface design sub-time period, obtaining multiple event transition probability matrices according to the analysis results, and obtaining user historical operation collection data; An event prediction module: used for performing real-time operation prediction on the target user according to the user historical operation collection data, and obtaining a predicted click event according to the prediction result; A page layout module: used for dividing the user interface into several interface sub-regions, obtaining the user's line-of-sight focus points, performing relative position analysis and relative distance analysis on each interface sub-region and the user's line-of-sight focus points, and marking the predicted click regions according to the analysis results; An operation control module: used for performing periodic click count analysis on the predicted click regions, and performing operation control on the user according to the analysis result.

[0006] Further, data collection of user historical operations is obtained as follows: Arbitrarily select one user from multiple logged-in users served by the user interface of the financial trading system as the target user; Obtain multiple historical login records of the target user in the user interface of the financial trading system, respectively obtain the user click events in each historical login record, obtain multiple user click events, and respectively mark the multiple obtained user click events as click event 1 to click event p; Divide the period during which the user interface of the financial trading system is open into several interface design sub-periods, and arbitrarily select one sample design sub-period from the obtained several interface design sub-periods; Conduct common operation analysis on the click events during the sample design sub-period according to the historical login records to obtain the event transition probability matrix corresponding to the sample design sub-period; Respectively obtain the event transition probability matrix corresponding to each interface design sub-period to obtain the data collection of user historical operations.

[0007] Further, obtaining the event transition probability matrix corresponding to the sample design sub-period is as follows: Obtain multiple historical login records during the sample design sub-period, and respectively obtain the click event sequences of click event 1 to click event p in each historical login record according to the historical login records to obtain multiple click event sequences; Traverse each click event sequence, count the number of times that each click event i directly transfers to click event j to obtain the click calculation matrix C; In multiple click event sequences, if there is a situation where click event i directly transfers to click event j, calculate the event transition probability matrix P corresponding to the sample design sub-period through the click calculation matrix C; Calculate the event transition probability matrix P, and the specific formula is as follows: ; Where P is the click calculation matrix, P(i,j) represents the probability value that click event i directly transfers to click event j, C is the click calculation matrix, C(i,j) represents the number of times that click event i directly transfers to click event j appears, and C(i,k) represents the number of times that click event i directly transfers to click event k appears; In multiple click event sequences, if there is no situation where click event i directly transfers to click event j, calculate the event transition probability matrix P corresponding to the sample design sub-period through the click calculation matrix C; Calculate the event transition probability matrix P, and the specific formula is as follows: ; Among them, P is the click calculation matrix, P(i,j) represents the probability value that click event i directly transfers to click event j, C is the click calculation matrix, C(i,j) represents the number of times that click event i directly transfers to click event j occurs, C(i,k) represents the number of times that click event i directly transfers to click event k occurs, and p is the numerical value corresponding to the user click event.

[0008] Further, obtain the predicted click event as follows: Obtain the user historical operation collection data, and obtain the event transfer probability matrix corresponding to each interface design sub-period according to the user historical operation collection data; Mark the user click event closest to the current moment as the real-time click event, obtain the event transfer probability matrix corresponding to the current moment, and obtain the real-time event probability matrix; Substitute the real-time click event and click event 1 into the real-time event probability matrix to obtain the real-time transfer occurrence probability corresponding to click event 1. Substitute the real-time click event and click event 2 into the real-time event probability matrix to obtain the real-time transfer occurrence probability corresponding to click event 2, and so on. Substitute the real-time click event and click event p into the real-time event probability matrix to obtain the real-time transfer occurrence probability corresponding to click event p; Obtain the predicted click event by analyzing the real-time transfer occurrence probability corresponding to each click event.

[0009] Further, obtain the real-time transfer occurrence probability corresponding to each click event as follows: Obtain the real-time transfer occurrence probabilities corresponding to click events 1 to p, compare the numerical values of the obtained multiple real-time transfer occurrence probabilities, and mark the click event corresponding to the real-time transfer occurrence probability with the largest numerical value as the click event with the maximum probability; If there are multiple click events with the maximum probability, obtain the time values corresponding to the previous operations of each click event with the maximum probability to obtain multiple event operation time values, calculate the difference between the event operation time value and the current moment time value, and mark the click event with the maximum probability with the smallest obtained time difference as the predicted click event; If there is only one click event with the maximum probability, mark the click event with the maximum probability as the predicted click event.

[0010] Further, obtain the predicted click area as follows: Divide the user interface into several interface sub-areas, and arbitrarily select a sample interface sub-area from the several divided interface sub-areas; Use a 3D structured light device to perform 3D scanning on the user interface and the space area where the user is located, and create a 3D model of the user interface according to the scanning results; Create a three-dimensional coordinate system for the user interface, analyze the position of the target user according to the three-dimensional coordinate system of the user interface, and obtain the first line-of-sight feature point and the second line-of-sight feature point according to the analysis results; Use the ELG algorithm to obtain the gaze ray starting from the first line-of-sight feature point to get the first gaze line of sight, and use the ELG algorithm to obtain the gaze ray starting from the second line-of-sight feature point to get the second gaze line of sight; Obtain the intersection point of the first target line of sight and the first coordinate plane to get the first line-of-sight intersection point, obtain the intersection point of the second target line of sight and the first coordinate plane to get the second line-of-sight intersection point. In the first coordinate plane, connect the first line-of-sight intersection point and the second line-of-sight intersection point, and mark the midpoint of the connection as the user's line-of-sight focus point; If the user's line-of-sight focus point is within the user interface, mark the interface sub-region where the user's line-of-sight focus point is located as the line-of-sight aggregation region; If the user's line-of-sight focus point is not within the user interface, analyze the boundary distance values between each interface sub-region and the user's line-of-sight focus point, and mark the line-of-sight aggregation region according to the analysis results; Obtain the predicted click event, automatically set the line-of-sight aggregation region as the operation region of the predicted click event, and name it the predicted click region.

[0011] Furthermore, obtain the first line-of-sight feature point and the second line-of-sight feature point as follows: In the three-dimensional model of the user interface, obtain the geometric center of the user interface and mark it as the coordinate origin. Mark the coordinate plane where the user interface is located as the first coordinate plane. Pass a plane perpendicular to the first coordinate plane through the coordinate origin to get the second coordinate plane. Mark the straight line where the intersection line of the first coordinate plane and the second coordinate plane is located as the coordinate x-axis. In the second coordinate plane, pass a straight line perpendicular to the coordinate x-axis through the coordinate origin to get the coordinate y-axis. Pass a straight line perpendicular to the second coordinate plane through the coordinate origin to get the coordinate z-axis. Mark the plane rectangular coordinate system composed of the coordinate origin, the coordinate x-axis, and the coordinate y-axis as the three-dimensional coordinate system of the user interface; In the three-dimensional coordinate system of the user interface, mark the center point of the left eye pupil of the target user as the first line-of-sight feature point, and mark the center point of the right eye pupil of the target user as the second line-of-sight feature point.

[0012] Furthermore, obtain the line-of-sight aggregation region as follows: Obtain multiple boundary pixel points corresponding to the sample interface sub-region, and name the multiple obtained pixel points as the first boundary pixel point to the jth boundary pixel point respectively; Obtain the three-dimensional coordinates of the first boundary pixel point in the three-dimensional coordinate system of the user interface to get the first three-dimensional coordinates, and obtain the three-dimensional coordinates of the user's line-of-sight focus point in the user's three-dimensional coordinate system to get the second three-dimensional coordinates; Calculate the distance value between the user's line-of-sight focus point and the first boundary pixel point from the first three-dimensional coordinates and the second three-dimensional coordinates, and name it the first line-of-sight movement distance value; Calculate the first line-of-sight movement distance value, and the specific formula is as follows: ; Where, Yj1 is the first line-of-sight movement distance value, (x1, y1, z1) is the first three-dimensional coordinate, and (x2, y2, z2) is the second three-dimensional coordinate; Respectively obtain the distance values from the user's line-of-sight focus point to the second boundary pixel point to the jth boundary pixel point, and get the second line-of-sight movement distance value to the jth line-of-sight movement distance value; Calculate the average value of the first line-of-sight movement distance value to the jth line-of-sight movement distance value to obtain the average line-of-sight movement distance corresponding to the sample interface sub-region; Respectively obtain the average line-of-sight movement distance corresponding to each interface sub-region to get multiple average line-of-sight movement distances; Compare the numerical sizes of the obtained multiple average line-of-sight movement distances, and mark the interface sub-region corresponding to the minimum average line-of-sight movement distance as the line-of-sight aggregation region.

[0013] Furthermore, perform operation control on the user, specifically as follows: Obtain the predicted click area, and mark an operation control monitoring period during the process of the target user performing financial transaction operations through the user interface; During the operation control monitoring period, obtain the time values of each click of the target user on the predicted click area to get multiple click time values, and mark the obtained multiple click time events as D1 click time value to Dz click time value in sequence according to the time sequence; Calculate the periodic predicted click interval duration from the D1 click time value to the Dz click time value; Calculate the periodic predicted click interval duration, and the specific formula is as follows: ; Where, Zyj is the periodic predicted click interval duration, Dj i is the D i click time value, Dj i-1 is the D i-1 click time value, and z is the quantity value corresponding to the click time value; Obtain the preset click interval duration range. If the periodic predicted click interval duration is within the preset click interval duration range, it is determined that the user's financial transaction is in a normal state. If the periodic predicted click interval duration is not within the preset click interval duration range, it is determined that the user's financial transaction is in an abnormal state. At this time, the user interface returns to the login interface, and the target user is re-authenticated.

[0014] A method for developing and designing a user interface of a financial transaction system, including the following specific steps: Step S1: Collect multiple historical login records of the target user on the user interface. Divide the time period covered by the historical login records into multiple interface design sub-periods. Obtain each click event involved in the historical login records, analyze the occurrence probability of the click events in each interface design sub-period, and obtain multiple event transition probability matrices according to the analysis results to obtain the user's historical operation collection data. Step S2: Perform real-time operation prediction on the target user according to the user's historical operation collection data, and obtain the predicted click event according to the prediction result. Step S3: Divide the user interface into several interface sub-regions, obtain the user's line-of-sight focus point, perform relative position analysis and relative distance analysis on each interface sub-region and the user's line-of-sight focus point, and mark the predicted click area according to the analysis results. Step S4: Analyze the periodic click times of the predicted click area, and perform operation control on the user according to the analysis results.

[0015] In summary, due to the adoption of the above technical solutions, the beneficial effects of the present invention are: 1. The present invention predicts the user's real-time operation behavior according to the user's historical login data, and develops a separate operation window for the prediction result, enabling the user to perform one-key operations on the predicted event, thereby effectively improving the user's operation efficiency.

[0016] 2. The present invention performs commonality analysis on the operation data of the user in the current login state and the historical operation data, evaluates the operation security of the user according to the analysis results, and controls abnormal operations, which can effectively reduce the potential safety hazards existing in financial transactions. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] For the convenience of those skilled in the art to understand, the present invention will be further described below with reference to the accompanying drawings.

[0018] Figure 1 It is the overall system block diagram of the present invention; Figure 2 It is the implementation step diagram of the present invention; Figure 3 It is the three-dimensional coordinate system schematic diagram of the user interface in the present invention; Figure 4 Schematic diagram of the sample interface sub-region in the present invention Specific embodiments

[0019] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention. Embodiment 1

[0020] Please refer to Figure 1 , the present invention provides a technical solution: a financial trading system user interface development and design system, including a behavior collection module, an event prediction module, a page layout module, an operation control module and a server. The behavior collection module, the event prediction module, the page layout module and the operation control module are respectively connected to the server, and the server controls the behavior collection module, the event prediction module, the page layout module and the operation control module respectively; The behavior collection module collects multiple historical login records of the target user on the user interface, divides the time period covered by the historical login records into multiple interface design sub-periods, obtains each click event involved in the historical login records, analyzes the occurrence probability of the click events in each interface design sub-period, and obtains multiple event transition probability matrices according to the analysis results to obtain user historical operation collection data; Specifically as follows: Arbitrarily select one user from multiple logged-in users served by the financial trading system user interface as the target user; Obtain multiple historical login records of the target user on the financial trading system user interface, respectively obtain the user click events in each historical login record, obtain multiple user click events, and respectively label the multiple obtained user click events as click event 1 to click event p; It should be noted here that: In this application, any interface operation of the user in the financial trading system is a user click event in sequence, and the interface operations involved here include but are not limited to login, deposit, transfer and loan; In this application, p involved here is the numerical value corresponding to the user click event; Each user click event involved here corresponds to a function partition of the financial trading system user interface.

[0021] Divide the open time period of the financial trading system user interface into several interface design sub-periods, and arbitrarily select a sample design sub-period from the obtained several interface design sub-periods; Perform a common operation analysis on click events in the sample design sub-period based on historical login records to obtain the event transition probability matrix corresponding to the sample design sub-period; Specifically as follows: Obtain multiple historical login records in the sample design sub-period, and respectively obtain the click event sequences of click event 1 to click event p in each historical login record according to the historical login records to obtain multiple click event sequences; It should be noted here that: In this application, each historical registration record corresponds to a click event sequence; In specific implementation, there is a historical login record, and there are 5 click events in this historical login record. The corresponding click event sequence is as follows: Click event 1 → Click event 2 → Click event 5 → Click event 7 → Click event 3; "→" indicates a direct transition, that is, directly transfer to the next click event after a click event is completed. For example, "Click event 1 → Click event 2" means that the next click event completed by the user after completing click event 1 is click event 2; Traverse each click event sequence, count the number of times that each click event i directly transfers to click event j, and obtain the click calculation matrix C; It should be noted here that: In this application, since there are at most p click events in the click event sequence, the size of the click calculation matrix is p×p; In this application, the click event i involved here can be any one of click event 1 to click event p, the click event j involved here can be any one of click event 1 to click event p, and both i and j are integers greater than 1; In specific implementation, in multiple click event sequences, if the number of times that click event 3 appears immediately after click event 1 is 50 times, then C(1,3)=50.

[0022] In multiple click event sequences, if there is a direct transfer from click event i to click event j, calculate the event transition probability matrix P corresponding to the sample design sub-period through the click calculation matrix C; Calculate the event transition probability matrix P, and the specific formula is as follows: ; Among them, P is the click calculation matrix, P(i,j) represents the probability value that click event i directly transfers to click event j, C is the click calculation matrix, C(i,j) represents the number of times that click event i directly transfers to click event j appears, and C(i,k) represents the number of times that click event i directly transfers to click event k appears; It should be noted here that: In this application, k involved here can be any one of click events from click event 1 to click event p.

[0023] In specific implementation, there are the following experimental data: If the click event sequence is as follows: Click event 1 → Click event 2 → Click event 5 → Click event 7 → Click event 3 → Click event 2 → Click event 3 → Click event 2 → Click event 3 → Click event 5 → Click event 7 → Click event 3 → Click event 2; The above click event sequence has a total of 13 click events, the user clicks 12 times in total, and C(3,2)=3, so P(i,j)=0.25.

[0024] In multiple click event sequences, if there is no click event i directly transferring to click event j, the event transfer probability matrix P corresponding to the sample design sub-period is calculated through the click calculation matrix C; Calculate the event transfer probability matrix P, and the specific formula is as follows: ; Among them, P is the click calculation matrix, P(i,j) represents the probability value that click event i directly transfers to click event j, C is the click calculation matrix, C(i,j) represents the number of times that click event i directly transfers to click event j appears, C(i,k) represents the number of times that click event i directly transfers to click event k appears, and p is the quantity value corresponding to the user click event.

[0025] Repeat the process of obtaining the event transfer probability matrix corresponding to the sample design sub-period, and obtain the event transfer probability matrix corresponding to each interface design sub-period respectively to obtain the user historical operation collection data; The event prediction module performs real-time operation prediction on the target user according to the user historical operation collection data, and obtains the predicted click event according to the prediction result; Specifically as follows: Obtain the user historical operation collection data, and obtain the event transfer probability matrix corresponding to each interface design sub-period according to the user historical operation collection data; Mark the user click event closest to the current moment as the real-time click event, and obtain the real-time event probability matrix by obtaining the event transfer probability matrix corresponding to the current moment; Substitute the real-time click event and click event 1 into the real-time event probability matrix to obtain the real-time transfer occurrence probability corresponding to click event 1. Substitute the real-time click event and click event 2 into the real-time event probability matrix to obtain the real-time transfer occurrence probability corresponding to click event 2, and so on. Substitute the real-time click event and click event p into the real-time event probability matrix to obtain the real-time transfer occurrence probability corresponding to click event p; Obtain the predicted click event by analyzing the real-time transfer occurrence probability corresponding to each click event; Specifically as follows: Obtain the real-time transfer occurrence probabilities corresponding to click events 1 to click event p, and perform numerical comparison on the obtained multiple real-time transfer occurrence probabilities. Mark the click event corresponding to the real-time transfer occurrence probability with the largest value as the click event with the maximum probability; If there are multiple click events with the maximum probability, obtain the time values corresponding to the previous operations of each click event with the maximum probability to obtain multiple event operation time values. Calculate the difference between the event operation time value and the current moment time value, and mark the click event with the maximum probability with the smallest obtained time difference as the predicted click event; If there is only one click event with the maximum probability, mark the click event with the maximum probability as the predicted click event; The page layout module divides the user interface into several interface sub-regions, obtains the user's line of sight focus point, analyzes the relative position and relative distance between each interface sub-region and the user's line of sight focus point, and marks the predicted click area according to the analysis results; Specifically as follows: Divide the user interface into several interface sub-regions, and arbitrarily select a sample interface sub-region from the divided several interface sub-regions; Use a 3D structured light device to perform 3D scanning on the user interface and the space area where the user is located, and create a 3D model of the user interface according to the scanning results; Please refer to Figure 3 , in the 3D model of the user interface, obtain the geometric center of the user interface and mark it as the coordinate origin. Mark the coordinate plane where the user interface is located as the first coordinate plane. Draw a plane perpendicular to the first coordinate plane through the coordinate origin to obtain the second coordinate plane. Mark the straight line where the intersection line of the first coordinate plane and the second coordinate plane is located as the coordinate x-axis. In the second coordinate plane, draw a straight line perpendicular to the coordinate x-axis through the coordinate origin to obtain the coordinate y-axis. Draw a straight line perpendicular to the second coordinate plane through the coordinate origin to obtain the coordinate z-axis. Mark the plane rectangular coordinate system composed of the coordinate origin, the coordinate x-axis, and the coordinate y-axis as the 3D coordinate system of the user interface; It should be noted here that: In this application, the first coordinate plane involved here is the extended plane of the user interface, that is, the user interface only occupies a partial area of the first coordinate plane.

[0026] In the three-dimensional coordinate system of the user interface, mark the center point of the left eye pupil of the target user as the first line-of-sight feature point, and mark the center point of the right eye pupil of the target user as the second line-of-sight feature point; Use the ELG algorithm to obtain the gaze ray starting from the first line-of-sight feature point to get the first gaze line of sight, and use the ELG algorithm to obtain the gaze ray starting from the second line-of-sight feature point to get the second gaze line of sight; It should be noted here that: In this application, the ELG algorithm: a line-of-sight estimation method based on eye region landmark points, can obtain the line of sight of the target user; In this application, both the first gaze line of sight and the second gaze line of sight involved here require the target user to face the user interface, and it is necessary to ensure that the first gaze line of sight and the second gaze line of sight have intersections with the first coordinate plane.

[0027] Obtain the intersection point of the first target line of sight and the first coordinate plane to get the first line-of-sight intersection point, obtain the intersection point of the second target line of sight and the first coordinate plane to get the second line-of-sight intersection point, in the first coordinate plane, connect the first line-of-sight intersection point and the second line-of-sight intersection point, and mark the midpoint of the connection as the user's line-of-sight focus point; If the user's line-of-sight focus point is within the user interface, mark the interface sub-region where the user's line-of-sight focus point is located as the line-of-sight aggregation region; If the user's line-of-sight focus point is not within the user interface, analyze the boundary distance values between each interface sub-region and the user's line-of-sight focus point, and mark the line-of-sight aggregation region according to the analysis results; Specifically as follows: Please refer to Figure 4 , obtain multiple boundary pixel points corresponding to the sample interface sub-region, and name the multiple obtained pixel points as the first boundary pixel point to the j-th boundary pixel point; It should be noted here that: In this application, j involved here is the numerical value corresponding to the number of boundary pixel points, and j is an integer greater than 0.

[0028] Obtain the three-dimensional coordinates of the first boundary pixel point in the three-dimensional coordinate system of the user interface to get the first three-dimensional coordinates, and obtain the three-dimensional coordinates of the user's line-of-sight focus point in the user's three-dimensional coordinate system to get the second three-dimensional coordinates; Calculate the distance value between the user's line-of-sight focus point and the first boundary pixel point through the first three-dimensional coordinates and the second three-dimensional coordinates, and name it the first line-of-sight movement distance value; Calculate the first line-of-sight movement distance value. The specific formula is as follows: ; Where, Yj1 is the first line-of-sight movement distance value, (x1, y1, z1) is the first three-dimensional coordinate, and (x2, y2, z2) is the second three-dimensional coordinate; It should be noted here that: In a specific implementation, if the first three-dimensional coordinate is (3, 7, 9) and the first three-dimensional coordinate is (3, 10, 15), the first line-of-sight movement distance value can be calculated as 6.71.

[0029] Repeat the process of obtaining the first line-of-sight movement distance value, and respectively obtain the distance values from the user's line-of-sight focus point to the second boundary pixel point to the j-th boundary pixel point, to obtain the second line-of-sight movement distance value to the j-th line-of-sight movement distance value; Calculate the average value of the first line-of-sight movement distance value to the j-th line-of-sight movement distance value to obtain the average line-of-sight movement distance corresponding to the sub-region of the sample interface; Repeat the average line-of-sight movement distance corresponding to the sub-region of the sample interface, and respectively obtain the average line-of-sight movement distance corresponding to each interface sub-region to obtain multiple average line-of-sight movement distances; Compare the magnitudes of the obtained multiple average line-of-sight movement distances, and mark the interface sub-region corresponding to the minimum average line-of-sight movement distance as the line-of-sight aggregation region; It should be noted here that: In this application, if there is a situation where the minimum average line-of-sight movement distances are tied, then compare the minimum line-of-sight movement distance values of the tied interface sub-regions, that is, the minimum values among the first line-of-sight movement distance value to the j-th line-of-sight movement distance value.

[0030] Obtain the predicted click event, and automatically set the line-of-sight aggregation region as the operation region of the predicted click event, and name it the predicted click region; It should be noted here that: To avoid affecting the user's operation of non-predicted click events, the appearance duration of the predicted click region involved here on the user interface is specifically 5s, and the start appearance time point is the time point when the user's line-of-sight focus point is on the user interface.

[0031] The page layout module obtains the predicted click region and conveys it to the operation control module; The operation control module analyzes the periodic click times of the predicted click region and controls the user according to the analysis result; Specifically as follows: Obtain the predicted click area. During the process of a target user performing financial transaction operations through the user interface, mark an operation control monitoring period. Within the operation control monitoring period, obtain the time values of each click on the predicted click area by the target user, obtaining multiple click time values, and sequentially mark the multiple obtained click time events as the D1 click time value to the Dz click time value in chronological order. It should be noted here that: In this application, D involved here is the identifier corresponding to the click time value, and z involved here is the quantity value corresponding to the click time value, and z is an integer greater than 0. Calculate the periodic predicted click interval duration from the D1 click time value to the Dz click time value. Calculate the periodic predicted click interval duration. The specific formula is as follows: ; Among them, Zyj is the periodic predicted click interval duration, Dj i is the D i click time value, Dj i-1 is the D i-1 click time value, and z is the quantity value corresponding to the click time value. It should be noted here that: In specific implementation, there are the following experimental data: It is known that the D1 click time value is 7:54:31, the D2 click time value is 7:54:38, the D2 click time value is 7:54:44, the D3 click time value is 7:54:59, the D4 click time value is 7:55:08, and z is 5. The periodic predicted click interval duration can be calculated to be 9.25 seconds.

[0032] Obtain the preset click interval duration range. If the periodic predicted click interval duration is within the preset click interval duration range, it is determined that the user's financial transaction is in a normal state. If the periodic predicted click interval duration is not within the preset click interval duration range, it is determined that the user's financial transaction is in an abnormal state. At this time, the user interface returns to the login interface to re-authenticate the target user.

[0033] It should be noted here that: The normal state involved here includes the situation where the periodic predicted click interval duration is at the boundary of the preset click interval duration range.

[0034] If the periodic predicted click interval duration is not within the preset click interval duration range, the user's multiple click operations lack operational commonality with historical operations. At this time, the login interface determines that the user's operation is abnormal. The process of obtaining the preset click interval duration range involved here is as follows: Collect the periodic predicted click intervals corresponding to multiple platform users known to be in a normal state, calculate the average value and standard deviation of the obtained multiple periodic predicted click intervals, calculate the sum of the obtained average value and the standard, obtain the upper limit of the preset click interval duration range, calculate the difference between the obtained average value and the standard, obtain the lower limit of the preset click interval duration range, and mark the values between the lower limit and the upper limit of the preset click interval duration range as the preset click interval duration range.

[0035] In this application, if there are corresponding calculation formulas, the above calculation formulas are all dimensionless and take their numerical values for calculation. The weight coefficients, proportionality coefficients, and other coefficients in the formulas are set to obtain a result value by quantifying each parameter. Regarding the magnitudes of the weight coefficients and proportionality coefficients, as long as the proportional relationship between the parameters and the result value is not affected.

[0036] Embodiment 2 Please refer to Figure 2 , based on another concept of the same invention, a method for developing and designing a user interface of a financial trading system is proposed, including the following steps: Step S1: Collect multiple historical login records of the target user on the user interface, divide the time period covered by the historical login records into multiple interface design sub-periods, obtain each click event involved in the historical login records, analyze the occurrence probability of the click events in each interface design sub-period, and obtain multiple event transition probability matrices according to the analysis results to obtain the user historical operation collection data; In the step S1, the following specific steps are further included: Step S11: Arbitrarily select one user from multiple logged-in users served by the user interface of the financial trading system as the target user; Step S12: Obtain multiple historical login records of the target user on the user interface of the financial trading system, respectively obtain the user click events in each historical login record, obtain multiple user click events, and respectively mark the obtained multiple user click events as click event 1 to click event p; Step S13: Divide the open time period of the user interface of the financial trading system into several interface design sub-periods, and arbitrarily select a sample design sub-period from the obtained several interface design sub-periods; Step S14: Analyze the operation commonalities of the click events in the sample design sub-period according to the historical login records to obtain the event transition probability matrix corresponding to the sample design sub-period; In the step S14, the following specific steps are further included: Obtain multiple historical login records during the sample design sub-period, and respectively obtain the click event sequences of click event 1 to click event p in each historical login record according to the historical login records, so as to obtain multiple click event sequences; Traverse each click event sequence, count the number of times that each click event i directly transfers to click event j, and obtain the click calculation matrix C; In multiple click event sequences, if there is a situation where click event i directly transfers to click event j, calculate the event transfer probability matrix P corresponding to the sample design sub-period through the click calculation matrix C; Calculate the event transfer probability matrix P, and the specific formula is as follows: ; Where P is the click calculation matrix, P(i,j) represents the probability value that click event i directly transfers to click event j, C is the click calculation matrix, C(i,j) represents the number of times that click event i directly transfers to click event j appears, and C(i,k) represents the number of times that click event i directly transfers to click event k appears; In multiple click event sequences, if there is no situation where click event i directly transfers to click event j, calculate the event transfer probability matrix P corresponding to the sample design sub-period through the click calculation matrix C; Calculate the event transfer probability matrix P, and the specific formula is as follows: ; Where P is the click calculation matrix, P(i,j) represents the probability value that click event i directly transfers to click event j, C is the click calculation matrix, C(i,j) represents the number of times that click event i directly transfers to click event j appears, C(i,k) represents the number of times that click event i directly transfers to click event k appears, and p is the numerical value corresponding to the user click event.

[0037] Step S15: Respectively obtain the event transfer probability matrices corresponding to each interface design sub-period to obtain the user historical operation collection data; Step S2: Perform real-time operation prediction on the target user according to the user historical operation collection data, and obtain the predicted click event according to the prediction result; In the said step S2, it further includes the following specific steps: Step S21: Obtain the user historical operation collection data, and obtain the event transfer probability matrix corresponding to each interface design sub-period according to the user historical operation collection data; Step S22: Mark the user click event closest to the current moment as the real-time click event, obtain the event transfer probability matrix corresponding to the current moment, and obtain the real-time event probability matrix; Step S23: Substitute the real-time click event and click event 1 into the real-time event probability matrix to obtain the real-time transition occurrence probability corresponding to click event 1. Substitute the real-time click event and click event 2 into the real-time event probability matrix to obtain the real-time transition occurrence probability corresponding to click event 2, and so on. Substitute the real-time click event and click event p into the real-time event probability matrix to obtain the real-time transition occurrence probability corresponding to click event p; Step S24: Obtain the predicted click event by analyzing the real-time transition occurrence probability corresponding to each click event; In step S24, the following specific steps are further included: Obtain the real-time transition occurrence probabilities corresponding to click events 1 to click event p, and perform a numerical comparison on the obtained multiple real-time transition occurrence probabilities. Mark the click event corresponding to the real-time transition occurrence probability with the largest value as the click event with the maximum probability; If there are multiple click events with the maximum probability, obtain the time values corresponding to the previous operations of each click event with the maximum probability to obtain multiple event operation time values. Calculate the difference between the event operation time value and the current time value, and mark the click event with the maximum probability with the smallest obtained time difference as the predicted click event; If there is only one click event with the maximum probability, mark the click event with the maximum probability as the predicted click event; Step S3: Divide the user interface into several interface sub-regions, obtain the user's line-of-sight focus point, perform relative position analysis and relative distance analysis on each interface sub-region and the user's line-of-sight focus point, and mark the predicted click region according to the analysis results; In step S3, the following specific steps are further included: Step S31: Divide the user interface into several interface sub-regions, and arbitrarily select a sample interface sub-region from the divided several interface sub-regions; Step S32: Use a 3D structured light device to perform 3D scanning on the user interface and the space region where the user is located, and create a three-dimensional model of the user interface according to the scanning results; Step S33: Create a three-dimensional coordinate system for the user interface, perform position analysis on the target user according to the three-dimensional coordinate system of the user interface, and obtain the first line-of-sight feature point and the second line-of-sight feature point according to the analysis results; In step S33, the following specific steps are further included: In the three-dimensional model of the user interface, obtain the geometric center of the user interface and mark it as the coordinate origin. Mark the coordinate plane where the user interface is located as the first coordinate plane. Pass a plane perpendicular to the first coordinate plane through the coordinate origin to obtain the second coordinate plane. Mark the straight line where the intersection line of the first coordinate plane and the second coordinate plane is located as the coordinate x-axis. In the second coordinate plane, pass a straight line perpendicular to the coordinate x-axis through the coordinate origin to obtain the coordinate y-axis. Pass a straight line perpendicular to the second coordinate plane through the coordinate origin to obtain the coordinate z-axis. Mark the plane rectangular coordinate system composed of the coordinate origin, the coordinate x-axis, and the coordinate y-axis as the three-dimensional coordinate system of the user interface; In the three-dimensional coordinate system of the user interface, mark the center point of the target user's left eye pupil as the first line-of-sight feature point, and mark the center point of the target user's right eye pupil as the second line-of-sight feature point; Step S34: Use the ELG algorithm to obtain the gaze ray starting from the first line-of-sight feature point to get the first gaze line of sight, and use the ELG algorithm to obtain the gaze ray starting from the second line-of-sight feature point to get the second gaze line of sight; Step S35: Obtain the intersection point of the first target line of sight and the first coordinate plane to get the first line-of-sight intersection point, obtain the intersection point of the second target line of sight and the first coordinate plane to get the second line-of-sight intersection point. In the first coordinate plane, connect the first line-of-sight intersection point and the second line-of-sight intersection point, and mark the midpoint of the connection as the user's line-of-sight focus point; Step S36: If the user's line-of-sight focus point is within the user interface, mark the interface sub-region where the user's line-of-sight focus point is located as the line-of-sight aggregation region; Step S37: If the user's line-of-sight focus point is not within the user interface, analyze the boundary distance values between each interface sub-region and the user's line-of-sight focus point, and mark the line-of-sight aggregation region according to the analysis results; In the said step S37, it further includes the following specific steps: Obtain multiple boundary pixel points corresponding to the sample interface sub-region, and name the multiple obtained pixel points as the first boundary pixel point to the j-th boundary pixel point respectively; Obtain the three-dimensional coordinates of the first boundary pixel point in the three-dimensional coordinate system of the user interface to get the first three-dimensional coordinates, and obtain the three-dimensional coordinates of the user's line-of-sight focus point in the three-dimensional coordinate system of the user to get the second three-dimensional coordinates; Calculate the distance value between the user's line-of-sight focus point and the first boundary pixel point through the first three-dimensional coordinates and the second three-dimensional coordinates, and name it the first line-of-sight movement distance value; Calculate the first line-of-sight movement distance value, and the specific formula is as follows: ; Wherein, Yj1 is the numerical value of the first line-of-sight movement distance, (x1, y1, z1) is the first three-dimensional coordinate, and (x2, y2, z2) is the second three-dimensional coordinate; Repeat the process of obtaining the numerical value of the first line-of-sight movement distance, and respectively obtain the distance values from the user's line-of-sight focus point and the second boundary pixel point to the jth boundary pixel point, to obtain the second line-of-sight movement distance value to the jth line-of-sight movement distance value; Calculate the average value of the first line-of-sight movement distance value to the jth line-of-sight movement distance value, to obtain the average line-of-sight movement distance corresponding to the sub-region of the sample interface; Repeat the average line-of-sight movement distance corresponding to the sub-region of the sample interface, and respectively obtain the average line-of-sight movement distance corresponding to each interface sub-region, to obtain multiple average line-of-sight movement distances; Compare the numerical magnitudes of the obtained multiple average line-of-sight movement distances, and mark the interface sub-region corresponding to the minimum average line-of-sight movement distance as the line-of-sight aggregation region; Step S38: Obtain the predicted click event, automatically set the line-of-sight aggregation region as the operation region of the predicted click event, and name it the predicted click region; Step S4: Analyze the periodic click times of the predicted click region, and perform operation control on the user according to the analysis result; In the said step S4, it further includes the following specific steps: Step S41: Obtain the predicted click region, and mark an operation control monitoring period during the process of the target user performing financial transaction operations through the user interface; Step S42: During the operation control monitoring period, obtain the time numerical values of each click of the target user on the predicted click region, to obtain multiple click time numerical values, and sequentially mark the obtained multiple click time events as the D1 click time numerical value to the Dz click time numerical value in chronological order; Step S43: Calculate the periodic predicted click interval duration from the D1 click time numerical value to the Dz click time numerical value; Calculate the periodic predicted click interval duration, and the specific formula is as follows: ; Wherein, Zyj is the periodic predicted click interval duration, Dj i is the D i click time numerical value, Dj i-1 is the D i-1 click time numerical value, and z is the numerical value corresponding to the click time numerical value; Step S44: Obtain a preset click interval duration range. If the periodic predicted click interval duration is within the preset click interval duration range, it is determined that the user's financial transaction is in a normal state. If the periodic predicted click interval duration is not within the preset click interval duration range, it is determined that the user's financial transaction is in an abnormal state. At this time, the user interface returns to the login interface, and re-authentication is performed on the target user.

[0038] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the present invention to only the specific implementation manners. Obviously, many modifications and changes can be made according to the content of this specification. These embodiments are selected and specifically described in this specification to better explain the principle and practical application of the present invention, so that those skilled in the relevant art can understand and utilize the present invention well. The present invention is only limited by the claims and their full scope and equivalents.

Claims

1. A financial trading system user interface development and design system, characterized in that, Including: Behavior collection module: used to collect multiple historical login records, divide the time period covered by the historical login records into multiple interface design sub-periods, obtain each click event involved in the historical login records, analyze the occurrence probability of the click events in each interface design sub-period, obtain multiple event transition probability matrices according to the analysis results, and obtain user historical operation collection data; Event prediction module: used to perform real-time operation prediction on the target user according to the user historical operation collection data, and obtain predicted click events according to the prediction results; Page layout module: used to divide the user interface into several interface sub-areas, obtain the user's line-of-sight focus point, perform relative position analysis and relative distance analysis on each interface sub-area and the user's line-of-sight focus point, and mark the predicted click area according to the analysis results; Operation control module: used to monitor the periodic click times of the predicted click area, and perform operation control on the user according to the monitoring results.

2. The user interface development and design system for a financial trading system according to claim 1, characterized in that, Obtain the user historical operation collection data as follows: Arbitrarily select one user from multiple logged-in users served by the financial trading system user interface as the target user; Obtain multiple historical login records of the target user in the financial trading system user interface, respectively obtain the user click events in each historical login record, obtain multiple user click events, and mark the obtained multiple user click events as click event 1 to click event p; Divide the time period when the financial trading system user interface is open into several interface design sub-periods, and arbitrarily select one sample design sub-period from the obtained several interface design sub-periods; Perform operation commonality analysis on the click events of the interface design sub-period according to the historical login records, obtain the event transition probability matrix corresponding to each interface design sub-period according to the analysis results, and obtain user historical operation collection data.

3. A user interface development and design system for a financial trading system according to claim 2, characterized in that, Obtain the event transition probability matrix as follows: Obtain multiple historical login records in the sample design sub-period, and respectively obtain the click event sequences of click event 1 to click event p in each historical login record according to the historical login records, and obtain multiple click event sequences; Traverse each click event sequence, count the number of times click event i transfers to click event j, and obtain the click calculation matrix C; If C(i,j) is not 0, calculate the event transition probability matrix P corresponding to the sample design sub-period through the click calculation matrix C; Calculate the event transition probability matrix P, and the specific formula is as follows: ； Where P is the click calculation matrix, P(i,j) represents the probability value that click event i directly transfers to click event j, C is the click calculation matrix, C(i,j) represents the number of times that click event i directly transfers to click event j appears, and C(i,k) represents the number of times that click event i directly transfers to click event k appears; If C(i,j) is 0, calculate the event transition probability matrix P corresponding to the sample design sub-period through the click calculation matrix C; Calculate the event transition probability matrix P, and the specific formula is as follows: ； Where p is the numerical value corresponding to the user click event.

4. A user interface development and design system for a financial trading system according to claim 1, characterized in that, Obtain the predicted click event as follows: Obtain the collected data of the user's historical operations, and obtain the event transition probability matrix corresponding to each sub-period of the interface design according to the collected data of the user's historical operations; Mark the user click event closest to the current moment as the real-time click event, obtain the event transition probability matrix corresponding to the current moment, and obtain the real-time event probability matrix; Substitute the real-time click event and click event 1 into the real-time event probability matrix to obtain the real-time transition occurrence probability corresponding to click event 1, and so on, to obtain the real-time transition occurrence probability corresponding to click event p; Obtain the predicted click event by analyzing the real-time transition occurrence probability corresponding to each click event.

5. A user interface development and design system for a financial trading system according to claim 4, characterized in that, Obtain the real-time transition occurrence probability corresponding to each click event as follows: Obtain the real-time transition occurrence probabilities corresponding to click events 1 to p, compare the numerical values of the obtained multiple real-time transition occurrence probabilities, and mark the click event corresponding to the real-time transition occurrence probability with the largest numerical value as the click event with the highest probability; If there are multiple click events with the highest probability, obtain the time values corresponding to the previous operations of each click event with the highest probability to obtain multiple event operation time values, calculate the difference between the event operation time value and the current moment time value, and mark the click event with the highest probability with the smallest obtained time difference as the predicted click event; If there is only one click event with the highest probability, mark the click event with the highest probability as the predicted click event.

6. A user interface development and design system for a financial trading system according to claim 1, characterized in that, Obtain the predicted click area as follows: Divide the user interface into several interface sub-areas, and arbitrarily select a sample interface sub-area from the divided several interface sub-areas; Perform 3D scanning on the user interface and the space area where the user is located, and create a three-dimensional model of the user interface according to the scanning results; Create a three-dimensional coordinate system for the user interface, analyze the position of the target user according to the three-dimensional coordinate system of the user interface, and obtain the first line-of-sight feature point and the second line-of-sight feature point according to the analysis results; Mark the gaze ray with the first line-of-sight feature point as the starting point as the first gaze line of sight, and mark the gaze ray with the second line-of-sight feature point as the starting point as the second gaze line of sight; Obtain the intersection point of the first target line of sight and the first coordinate plane to obtain the first line-of-sight intersection point, obtain the intersection point of the second target line of sight and the first coordinate plane to obtain the second line-of-sight intersection point, connect the first line-of-sight intersection point and the second line-of-sight intersection point in the first coordinate plane, and mark the midpoint of the connection as the user's line-of-sight focus point; If the user's line-of-sight focus point is within the user interface, mark the interface sub-area where the user's line-of-sight focus point is located as the line-of-sight aggregation area; If the user's line-of-sight focus point is not within the user interface, analyze the boundary distance values between each interface sub-area and the user's line-of-sight focus point, and mark the line-of-sight aggregation area according to the analysis results; Obtain the predicted click event, automatically set the line-of-sight aggregation area as the operation area of the predicted click event, and name it the predicted click area.

7. A user interface development and design system for a financial trading system according to claim 6, characterized in that, Obtain the first line-of-sight feature point and the second line-of-sight feature point as follows: In the three-dimensional model of the user interface, obtain the geometric center of the user interface and mark it as the coordinate origin. Mark the coordinate plane where the user interface is located as the first coordinate plane. Pass a plane perpendicular to the first coordinate plane through the coordinate origin to obtain the second coordinate plane. Mark the line where the intersection of the first coordinate plane and the second coordinate plane is located as the coordinate x-axis. In the second coordinate plane, pass a line perpendicular to the coordinate x-axis through the coordinate origin to obtain the coordinate y-axis. Pass a line perpendicular to the second coordinate plane through the coordinate origin to obtain the coordinate z-axis. Mark the plane rectangular coordinate system composed of the coordinate origin, the coordinate x-axis, and the coordinate y-axis as the three-dimensional coordinate system of the user interface; In the three-dimensional coordinate system of the user interface, mark the center point of the left eye pupil of the target user as the first line-of-sight feature point, and mark the center point of the right eye pupil of the target user as the second line-of-sight feature point.

8. A user interface development and design system for a financial trading system according to claim 6, characterized in that, Obtain the line-of-sight aggregation area as follows: Obtain a plurality of boundary pixel points corresponding to the sample interface sub-region, and name the obtained pixel points as the first boundary pixel point to the j-th boundary pixel point respectively; Obtain the three-dimensional coordinates of the first boundary pixel point in the three-dimensional coordinate system of the user interface to obtain the first three-dimensional coordinates, and obtain the three-dimensional coordinates of the user's line-of-sight focus point in the three-dimensional coordinate system of the user to obtain the second three-dimensional coordinates; Calculate the first line-of-sight movement distance value Yj1 by calculating the first three-dimensional coordinates (x1, y1, z1) and the second three-dimensional coordinates (x2, y2, z2); Obtain the distance values between the user's line-of-sight focus point and the second boundary pixel point to the j-th boundary pixel point respectively, to obtain the second line-of-sight movement distance value to the j-th line-of-sight movement distance value; Calculate the average value of the first line-of-sight movement distance value to the j-th line-of-sight movement distance value to obtain the average line-of-sight movement distance corresponding to the sample interface sub-region; Obtain the average line-of-sight movement distances corresponding to each interface sub-region respectively to obtain a plurality of average line-of-sight movement distances; Compare the numerical sizes of the obtained plurality of average line-of-sight movement distances, and mark the interface sub-region corresponding to the minimum average line-of-sight movement distance as the line-of-sight aggregation area.

9. A user interface development and design system for a financial trading system according to claim 1, characterized in that, Perform operation control on the user as follows: Obtain the predicted click area, and mark an operation control monitoring period during the process of the target user performing financial transaction operations through the user interface; During the operation control monitoring period, obtain the time values of each click of the target user on the predicted click area to obtain a plurality of click time values, and mark the obtained plurality of click time events as the D1 click time value to the Dz click time value in chronological order; Calculate the periodic predicted click interval duration by calculating the D1 click time value to the Dz click time value; Calculate the periodic predicted click interval duration, and the specific formula is as follows: ； Among them, Zyj is the cycle prediction click interval duration, Dj i is the D i click time value, Dj i-1 is the D i-1 click time value, z is the quantity value corresponding to the click time value; Obtain a preset click interval duration range. If the periodic predicted click interval duration is within the preset click interval duration range, it is determined that the user's financial transaction is in a normal state. If the periodic predicted click interval duration is not within the preset click interval duration range, it is determined that the user's financial transaction is in an abnormal state, and the user interface re-authenticates the target user.

10. A method for developing and designing a user interface of a financial trading system, characterized in that, Applicable to a user interface development and design system for a financial transaction system according to any one of claims 1-9, including the following steps: Step S1: Collect multiple historical login records, divide the time period covered by the historical login records into multiple interface design sub-time periods, obtain each click event involved in the historical login records, analyze the occurrence probability of the click events in each interface design sub-time period, and obtain multiple event transition probability matrices according to the analysis results to obtain user historical operation collection data; Step S2: Perform real-time operation prediction on the target user according to the user historical operation collection data, and obtain a predicted click event according to the prediction result; Step S3: Divide the user interface into several interface sub-regions, obtain the user's line-of-sight focus point, perform relative position analysis and relative distance analysis on each interface sub-region and the user's line-of-sight focus point, and mark the predicted click area according to the analysis results; Step S4: Monitor the periodic click times of the predicted click area, and control the user's operation according to the monitoring results.

Images