A visual service terminal control system and method for banks

Abstract

The present invention provides a visual service terminal control system and method for a bank, wherein the system comprises: a face recognition module, which performs face recognition on a user based on a bank visual service terminal and outputs face recognition information of the user; an interaction module, which reads interaction information of the user based on an interactive desktop of the bank visual service terminal; an information analysis module, which analyzes interaction information to obtain execution requirements corresponding to the interaction information, and analyzes face recognition information of the user to obtain facial features of the user; a visual recommendation module, which matches a plurality of bank service items in the bank visual service terminal based on execution requirements, and optimizes and recommends the user in a plurality of bank service items based on facial features, and visually displays the recommended bank service items in the bank visual service terminal; the convenience and intelligence of recommending and applying bank service items are improved, thereby improving user satisfaction.

Description

Technical Field

[0001] The present invention relates to the technical field of bank visualization service control, and in particular to a visual service terminal control system and method for banks. Background Art

[0002] Currently, banking service terminals are used to help customers better understand and use their financial assets. This technology can effectively avoid the need to hire a large number of employees to provide services to customers in traditional banking business, thus wasting a lot of bank costs;

[0003] However, in the prior art, the service items are recommended to users through the bank service terminal, but the face recognition and interaction operations are not integrated to recommend products and services that are more suitable for customers. Therefore, the accuracy and intelligence of the recommendation of bank service items cannot be guaranteed, thereby reducing user satisfaction.

[0004] Therefore, in order to overcome the above technical problems, the present invention provides a visual service terminal control system and method for banks. Summary of the invention

[0005] The present invention provides a visual service terminal control system and method for banks, which are used to collect facial recognition information and interaction information of users, thereby effectively realizing the accurate acquisition of execution requirements of users and facial features of users, and realizing optimized recommendation of bank service items and visual display thereof by combining execution requirements and facial features of users. Based on the interactive process and combined with facial recognition, the accuracy of recommendation of bank service items can be effectively guaranteed, thereby saving the time of users in selecting bank service items, and through visual display, the convenience and intelligence of recommendation and application of bank service items are improved, thereby improving user satisfaction.

[0006] A visual service terminal control system for a bank, comprising:

[0007] A face recognition module is used to perform face recognition on users based on a bank visual service terminal and output the face recognition information of users;

[0008] An interactive module, used to read user interaction information based on the interactive desktop of the bank's visual service terminal;

[0009] The information analysis module is used to analyze the interaction information to obtain the execution requirements corresponding to the interaction information, and at the same time, analyze the user's face recognition information to obtain the user's facial features;

[0010] The visualization recommendation module is used to match multiple banking service items in the bank visualization service terminal based on execution needs, and optimize the recommendations for users in multiple banking service items based on facial features. At the same time, the recommended banking service items are visualized and displayed in the bank visualization service terminal.

[0011] Preferably, a visual service terminal control system for a bank, a face recognition module, comprises:

[0012] The facial capture unit is used to capture the user's face based on the bank visual service terminal, and when the target face is captured, the user's stay time in front of the bank visual service terminal is timed to obtain the target time;

[0013] The face recognition unit is used to perform face recognition on the user and obtain face recognition information of the user when the target moment reaches a preset standard.

[0014] Preferably, a visual service terminal control system for a bank, a facial capture unit, comprises:

[0015] The picture acquisition subunit is used to acquire pictures of the external area in real time based on the bank visualization service terminal, and read the picture acquisition frames of the external area in real time;

[0016] The initial picture information acquisition subunit is used to acquire the initial picture information of the external area and set the picture acquisition frame corresponding to the initial picture information as the current picture acquisition frame;

[0017] Dynamic tracking subunit for:

[0018] Dynamically tracking the picture information of the next picture acquisition frame based on the current picture acquisition frame;

[0019] When the picture information of the next picture acquisition frame is consistent with the initial picture information of the current picture acquisition frame, the next picture acquisition frame is updated to the current picture acquisition frame, until the picture information of the next picture acquisition frame is inconsistent with the initial picture information, the external area image corresponding to the next picture acquisition frame is captured;

[0020] The image analysis subunit is used to analyze the external area image, obtain the foreground image of the external area image, and at the same time, obtain the outer contour points and inner contour points of the foreground image, and determine the image features of the foreground image according to the outer contour points and inner contour points of the foreground image;

[0021] A capture subunit is used to match the image features of the exterior image with the sample features, and when the image features of the exterior image match the sample features, the target face is captured;

[0022] The dynamic tracking subunit is also used to update the next picture acquisition frame to the current picture acquisition frame when the image features of the exterior scene image do not match the sample features, and continue to dynamically track the picture information of the next picture acquisition frame based on the current picture acquisition frame.

[0023] Preferably, a visual service terminal control system for a bank, a face recognition module, comprises:

[0024] A scanning node creation unit, used to create a scanning node based on a bank visual service terminal and build a scanning mechanism in the scanning node;

[0025] A sub-recognition model building unit, used for obtaining multiple face recognition dimensions, mapping the multiple face recognition dimensions in a scanning node, and building multiple sub-recognition mechanisms in the scanning node based on the mapping results;

[0026] The scanning interval determination unit is used for:

[0027] Get the location node of the bank's visual service terminal;

[0028] Obtain the user's location node relative to the bank's visualization service terminal;

[0029] A scanning interval for scanning the user based on the bank visualization service terminal is constructed based on the location node of the bank visualization service terminal and the location node of the user relative to the bank visualization service terminal;

[0030] A parameter configuration unit, used to determine a vertical scanning parameter and a horizontal scanning parameter based on a scanning interval, and configure the vertical scanning parameter and the horizontal scanning parameter in a scanning mechanism;

[0031] Scanning unit for:

[0032] Scan the user's face vertically and horizontally based on the configured scanning mechanism;

[0033] Draw a target scan image of the user's face based on vertical scanning and horizontal scanning;

[0034] The face recognition information acquisition unit is used to:

[0035] The target scanned image of the user's face is input into each sub-recognition mechanism in the scanning node respectively, and the corresponding sub-face recognition information is output based on the sub-recognition mechanism to obtain the user's face recognition information.

[0036] Preferably, a visual service terminal control system for a bank, an interactive module, comprises:

[0037] The interactive desktop monitoring unit is used to monitor the interactive desktop in real time when the user performs interactive operations on the interactive desktop, determine the execution dynamics of the interactive desktop,

[0038] An information reading mode determining unit, used to determine the user's interaction mode based on the execution dynamics, and at the same time, determine the information reading mode according to the user's interaction mode;

[0039] The interactive information reading unit is used to read the execution dynamics of the interactive desktop based on the information reading method to determine the user's interactive information.

[0040] Preferably, a visual service terminal control system for a bank, an information analysis module, comprises:

[0041] A first information analysis unit, used to analyze the interaction information and determine the user's execution requirements;

[0042] The second information analysis unit is used to analyze the user's face recognition information to obtain the user's facial features.

[0043] Preferably, a visual service terminal control system for a bank, the first information analysis unit, comprises:

[0044] The information processing subunit is used to obtain the interaction frequency between the user and the interactive desktop of the bank visual service terminal, and to segment the interaction information according to the interaction frequency to obtain multiple interaction information sequences;

[0045] An information sequence reading subunit, used to read each interactive information sequence respectively, and determine a plurality of first-level interactive nodes corresponding to each interactive information sequence;

[0046] The core field acquisition subunit is used to:

[0047] Obtaining repetition frequencies of multiple first-level interaction nodes in a corresponding interaction information sequence, and extracting second-level interaction nodes whose repetition frequencies are within a preset frequency range;

[0048] Matching the plurality of first-level interaction nodes with the bank vocabulary library, and determining the third-level interaction nodes among the plurality of first-level interaction nodes that match the third-level interaction nodes in the bank vocabulary library;

[0049] A core execution node determination subunit, used for generating a core execution node corresponding to an interactive information sequence based on the secondary interactive node and the tertiary interactive node;

[0050] The execution requirement determination subunit is used to calculate the distance between each core execution node and the remaining core execution nodes respectively, and determine the core execution community according to the distance between each core execution node and the remaining core execution nodes, and splice the target core execution nodes in the core execution community, and output the user's execution requirements based on the splicing results.

[0051] Preferably, a visual service terminal control system for a bank, the second information analysis unit, comprises:

[0052] The reading subunit is used to read the user's face recognition information and determine the morphological distribution characteristics of the user's facial features;

[0053] The facial feature determination subunit is used to determine the facial features of the user based on the facial features of the user.

[0054] Preferably, a visual service terminal control system for a bank, a visual recommendation module, comprises:

[0055] The project matching unit is used to read the execution requirements, determine the execution targets, and match m banking service projects in the bank visual service terminal according to the execution targets;

[0056] A facial feature reading unit is used to read the facial features of the user, determine the age range of the user, and simultaneously obtain the applicable age range corresponding to each banking service item;

[0057] A service item extraction unit, used to match the user's age range with the adapted age range corresponding to each bank service item, and extract i bank service items corresponding to the user's age range based on the matching result, where i≤m;

[0058] The facial feature reading unit is further used to read the facial features of the user, determine the gender of the user, and at the same time, extract j banking service items from i banking service items according to the gender of the user, wherein j≤i;

[0059] Visual display unit for:

[0060] Perform preliminary visualization of j banking service items on the bank visualization service terminal, and output satisfaction scores of j banking service items based on the emotional changes in the user's facial features;

[0061] The j banking service items are sorted in descending order according to the satisfaction scores, and the final visualization is performed on the bank visualization service terminal based on the sorting results.

[0062] A visual service terminal control method for a bank, comprising:

[0063] Step 1: Perform facial recognition on the user based on the bank's visual service terminal and output the user's facial recognition information;

[0064] Step 2: Read the user's interactive information based on the interactive desktop of the bank's visual service terminal;

[0065] Step 3: Analyze the interaction information to obtain the execution requirements corresponding to the interaction information. At the same time, analyze the user's face recognition information to obtain the user's facial features.

[0066] Step 4: Match multiple banking service items on the bank visualization service terminal based on execution requirements, and optimize and recommend multiple banking service items to users based on facial features. At the same time, visualize the recommended banking service items on the bank visualization service terminal.

[0067] Compared with the prior art, the present invention has the following beneficial effects:

[0068] 1. By collecting the user's facial recognition information and the user's interactive information, the user's execution needs and the user's facial features can be effectively and accurately obtained. By combining the execution needs and the user's facial features, the optimized recommendation of banking service items can be realized and visualized. Based on the interactive process and combined with facial recognition, the accuracy of banking service item recommendations can be effectively guaranteed, thereby saving users' time in selecting banking service items. Through visual display, the convenience and intelligence of banking service item recommendations and applications are improved, thereby improving user satisfaction.

[0069] 2. By determining the initial screen information of the external area, and then taking the screen acquisition frame corresponding to the initial screen information as the initial screen acquisition frame, the initial screen acquisition frame is used to dynamically track the screen information of the next frame of the screen acquisition frame, which can effectively realize the screen capture of the external area based on the visualization service terminal, and then timely realize the user's face capture. Through the frame-by-frame recognition method, the effectiveness of face capture is guaranteed. At the same time, real-time updating of the initial screen acquisition frame can reduce the storage and analysis of image data, thereby improving the efficiency of face capture.

[0070] 3. The interactive information is segmented according to the interaction frequency to obtain multiple interactive information sequences, multiple first-level interactive nodes in the multiple interactive information sequences are identified, and the second-level interactive nodes in the first-level interactive nodes are extracted based on the repetition frequency. The first-level interactive nodes are matched with the bank vocabulary library to extract the third-level interactive nodes in the first-level interactive nodes, and then the core execution nodes of the interactive information sequence are obtained through the second-level interactive nodes and the third-level interactive nodes. The core execution nodes are screened again by determining the core execution community to obtain the target core execution nodes. The user's execution needs are effectively obtained by splicing the target core execution nodes, thereby improving the accuracy of obtaining the execution needs.

[0071] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures specifically pointed out in this application document.

[0072] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0074] Figure 1 This is a structural diagram of a visual service terminal control system for a bank in an embodiment of the present invention;

[0075] Figure 2 This is a structural diagram of a face recognition module in a structural diagram of a visual service terminal control system for a bank in an embodiment of the present invention;

[0076] Figure 3 The present invention is a flowchart of a visual service terminal control method for a bank in an embodiment of the present invention. DETAILED DESCRIPTION

[0077] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0078] Embodiment 1:

[0079] This embodiment provides a visual service terminal control system for a bank, such as Figure 1 As shown, including:

[0080] A face recognition module is used to perform face recognition on users based on a bank visual service terminal and output the face recognition information of users;

[0081] An interactive module, used to read user interaction information based on the interactive desktop of the bank's visual service terminal;

[0082] The information analysis module is used to analyze the interaction information to obtain the execution requirements corresponding to the interaction information, and at the same time, analyze the user's face recognition information to obtain the user's facial features;

[0083] The visualization recommendation module is used to match multiple banking service items in the bank visualization service terminal based on execution needs, and optimize the recommendations for users in multiple banking service items based on facial features. At the same time, the recommended banking service items are visualized and displayed in the bank visualization service terminal.

[0084] In this embodiment, the face recognition information may be the distribution status of facial features and the like.

[0085] In this embodiment, the interactive information may be based on a banking service request input by a user in an interactive desktop of a bank visual service terminal, wherein the interactive mode may include but is not limited to language interaction, text interaction, and other interactive modes.

[0086] In this embodiment, the interaction information is analyzed to determine the banking services required by the user, and the facial recognition information is analyzed to determine the user's gender and the user's satisfaction with the currently displayed information through the user's facial features, and to evaluate the user's age range (based on wrinkles, etc.).

[0087] In this embodiment, banking service items may include: intelligent push of bank advertisements, intelligent financial management for each individual (such as VIP access control, payment by face recognition: intelligent recommendation of financial products), appearance loan, and may support call number reminder.

[0088] In this embodiment, the visual display may include a large screen and an interactive desktop.

[0089] In this embodiment, the execution requirements may be submitted by different users to the bank visualization service terminal, and are used to represent the bank interaction items that need to be performed.

[0090] The working principle and beneficial effects of the above technical solution are: by collecting the user's facial recognition information and the user's interaction information, the user's execution needs and the user's facial features can be effectively and accurately acquired, and by combining the execution needs and the user's facial features, the optimized recommendation of banking service items can be realized and visualized. Based on the interaction process and combined with facial recognition, the accuracy of the recommendation of banking service items can be effectively guaranteed, thereby saving the user's time in selecting banking service items, and through visual display, the convenience and intelligence of the recommendation and application of banking service items are improved, thereby improving user satisfaction.

[0091] Embodiment 2:

[0092] Based on Example 1, this example provides a visual service terminal control system for a bank, such as Figure 2 As shown, the face recognition module includes:

[0093] The facial capture unit is used to capture the user's face based on the bank visual service terminal, and when the target face is captured, the user's stay time in front of the bank visual service terminal is timed to obtain the target time;

[0094] The face recognition unit is used to perform face recognition on the user and obtain face recognition information of the user when the target moment reaches a preset standard.

[0095] In this embodiment, the target time may be the total length of time the user stays in front of the bank visualization service terminal.

[0096] In this embodiment, the preset standard may be that when the target time reaches a set time length (for example, the target time reaches more than 5 seconds), the preset standard is met.

[0097] The working principle and beneficial effects of the above technical solution are: by capturing the user's face, timing the stay time, and performing face recognition when the preset standard is reached, the false recognition rate of face recognition can be avoided (that is, when there is no face recognition demand, and the user just passes by the bank's visual service terminal, face recognition is not performed), which can save the amount of data analysis of the bank's visual service terminal.

[0098] Embodiment 3:

[0099] Based on Example 2, this embodiment provides a visual service terminal control system for a bank, a facial capture unit, including:

[0100] The picture acquisition subunit is used to acquire pictures of the external area in real time based on the bank visualization service terminal, and read the picture acquisition frames of the external area in real time;

[0101] The initial picture information acquisition subunit is used to acquire the initial picture information of the external area and set the picture acquisition frame corresponding to the initial picture information as the current picture acquisition frame;

[0102] Dynamic tracking subunit for:

[0103] Dynamically tracking the picture information of the next picture acquisition frame based on the current picture acquisition frame;

[0104] When the picture information of the next picture acquisition frame is consistent with the initial picture information of the current picture acquisition frame, the next picture acquisition frame is updated to the current picture acquisition frame, until the picture information of the next picture acquisition frame is inconsistent with the initial picture information, the external area image corresponding to the next picture acquisition frame is captured;

[0105] The image analysis subunit is used to analyze the external area image, obtain the foreground image of the external area image, and at the same time, obtain the outer contour points and inner contour points of the foreground image, and determine the image features of the foreground image according to the outer contour points and inner contour points of the foreground image;

[0106] A capture subunit is used to match the image features of the exterior image with the sample features, and when the image features of the exterior image match the sample features, the target face is captured;

[0107] The dynamic tracking subunit is also used to update the next picture acquisition frame to the current picture acquisition frame when the image features of the exterior scene image do not match the sample features, and continue to dynamically track the picture information of the next picture acquisition frame based on the current picture acquisition frame.

[0108] In this embodiment, the external area can be the external range that can be monitored by the bank visualization service terminal as the external area.

[0109] In this embodiment, the picture acquisition frame may be a time point corresponding to when the picture information of the external area is acquired according to a preset time interval (such as every 3 seconds) as the picture acquisition frame.

[0110] In this embodiment, the initial screen information may be screen information of the external area corresponding to when there is no shielding in front of the bank visualization service terminal (ie, there is no person or obstacle in front of the bank visualization service terminal).

[0111] In this embodiment, the external area image is analyzed, and the foreground image of the external area image is obtained by overlapping the external area image with the initial screen information, extracting the overlapping part of the external area image and the initial screen information as the background image of the external area image, and then removing the background image of the external area image from the external area image, and obtaining the foreground image of the external area image based on the removal result.

[0112] In this embodiment, the outer contour feature of the foreground image may be the outermost boundary point distribution feature, and the inner contour feature of the foreground image may be the boundary point distribution feature of each area in the foreground image determined according to the pixel distribution state inside the foreground image (for example, when the foreground image is a human being, the outer contour feature is the distribution state of the pixel points corresponding to the outermost periphery of the face, and the inner contour feature is the distribution state of the pixel points corresponding to the edges of the person's eyes, nose, mouth, etc.

[0113] In this embodiment, the image feature is the image feature of the foreground image obtained by combining the outer contour feature and the inner contour feature.

[0114] In this embodiment, the sample feature may be a distribution feature of image pixels obtained after recognizing a human face.

[0115] The working principle and beneficial effects of the above technical solution are: by determining the initial picture information of the external area, and then taking the picture acquisition frame corresponding to the initial picture information as the initial picture acquisition frame, the picture information of the next picture acquisition frame is dynamically tracked through the initial picture acquisition frame, which can effectively realize the picture capture of the external area based on the visualization service terminal, and then timely realize the face capture of the user, and through the frame-by-frame recognition method, the effectiveness of face capture is guaranteed. At the same time, real-time updating of the initial picture acquisition frame can reduce the storage and analysis of image data, thereby improving the efficiency of face capture.

[0116] Embodiment 4:

[0117] Based on Example 1, this embodiment provides a visual service terminal control system for a bank, a face recognition module, including:

[0118] A scanning node creation unit, used to create a scanning node based on a bank visual service terminal and build a scanning mechanism in the scanning node;

[0119] A sub-recognition model building unit, used for obtaining multiple face recognition dimensions, mapping the multiple face recognition dimensions in a scanning node, and building multiple sub-recognition mechanisms in the scanning node based on the mapping results;

[0120] The scanning interval determination unit is used for:

[0121] Get the location node of the bank's visual service terminal;

[0122] Obtain the user's location node relative to the bank's visualization service terminal;

[0123] A scanning interval for scanning the user based on the bank visualization service terminal is constructed based on the location node of the bank visualization service terminal and the location node of the user relative to the bank visualization service terminal;

[0124] A parameter configuration unit, used to determine a vertical scanning parameter and a horizontal scanning parameter based on a scanning interval, and configure the vertical scanning parameter and the horizontal scanning parameter in a scanning mechanism;

[0125] Scanning unit for:

[0126] Scan the user's face vertically and horizontally based on the configured scanning mechanism;

[0127] Draw a target scan image of the user's face based on vertical scanning and horizontal scanning;

[0128] The face recognition information acquisition unit is used to:

[0129] The target scanned image of the user's face is input into each sub-recognition mechanism in the scanning node respectively, and the corresponding sub-face recognition information is output based on the sub-recognition mechanism to obtain the user's face recognition information.

[0130] In this embodiment, the scanning node includes: a scanning mechanism (used to implement a model for scanning a face, which can effectively scan a face), and multiple sub-recognition mechanisms (used to implement the corresponding face recognition model under the face recognition dimension based on the face recognition dimension).

[0131] In this embodiment, the face recognition dimensions may include: age recognition, gender recognition, and emotion recognition, and therefore, the sub-recognition mechanisms include three.

[0132] In this embodiment, a scanning interval for scanning the user based on the bank visualization service terminal is constructed based on the location node of the bank visualization service terminal and the location node of the user relative to the bank visualization service terminal, that is, the vertical distance between the visualization service terminal and the user is determined by the location node of the bank visualization service terminal and the location node of the user relative to the bank visualization service terminal. The scanning interval determined by the visible range of the location node of the visualization service terminal and the vertical distance can ensure the accuracy of the face scanning of the user, and can effectively ensure that the face image is fully collected.

[0133] In this embodiment, the scanning interval is the interval for scanning the user's face.

[0134] The working principle and beneficial effects of the above technical solution are: by constructing a scanning node and a scanning mechanism in the scanning node, and configuring the horizontal scanning parameters and the vertical scanning parameters in the scanning mechanism based on the scanning interval, face scanning of different users is realized, thereby improving the fault tolerance and accuracy of face scanning of users, ensuring the integrity of the target scanning image of the user's face that is fully collected, and realizing recognition of different face recognition dimensions by transmitting the target scanning image to different sub-recognition mechanisms respectively, achieving the accuracy and precision of the target scanning image recognition, thereby effectively ensuring the accuracy of the acquired face recognition information, and laying a good foundation for the effectiveness and accuracy of the recommendation of banking service items.

[0135] Embodiment 5:

[0136] Based on Example 1, this embodiment provides a visual service terminal control system for a bank, an interactive module, including:

[0137] The interactive desktop monitoring unit is used to monitor the interactive desktop in real time when the user performs interactive operations on the interactive desktop, determine the execution dynamics of the interactive desktop,

[0138] An information reading mode determining unit, used to determine the user's interaction mode based on the execution dynamics, and at the same time, determine the information reading mode according to the user's interaction mode;

[0139] The interactive information reading unit is used to read the execution dynamics of the interactive desktop based on the information reading method to determine the user's interactive information.

[0140] In this embodiment, the execution dynamics are the operation dynamics of the user on the interactive desktop.

[0141] In this embodiment, the information reading mode is determined according to the user's interaction mode, and one interaction mode may correspond to one information reading mode, for example, if the language interaction mode is used, the corresponding information reading mode is language recognition.

[0142] The working principle and beneficial effects of the above technical solution are: by matching the corresponding information reading method based on the user's own selection of the interaction mode, the user's experience of the bank's visual service terminal can be improved. At the same time, through the information reading method, the information collection of user interactions can be realized in a timely manner, thereby improving service efficiency.

[0143] Embodiment 6:

[0144] Based on Example 1, this embodiment provides a visual service terminal control system for a bank, an information analysis module, including:

[0145] A first information analysis unit, used to analyze the interaction information and determine the user's execution requirements;

[0146] The second information analysis unit is used to analyze the user's face recognition information to obtain the user's facial features.

[0147] In this embodiment, the second information analysis unit includes:

[0148] The reading subunit is used to read the user's facial recognition information and determine the morphological distribution characteristics of the user's facial features (i.e. eyebrows, eyes, mouth, nose, and wrinkles on the facial features to determine the user's facial expression, gender and age range).

[0149] The facial feature determination subunit is used to determine the facial features of the user based on the facial features of the user.

[0150] The beneficial effects of the above technical solution are: effectively realizing the execution needs of users and obtaining the facial features of users, recommending banking service items, and providing intelligent guarantee.

[0151] Embodiment 7:

[0152] Based on Example 6, this embodiment provides a visual service terminal control system for a bank, wherein the first information analysis unit includes:

[0153] The information processing subunit is used to obtain the interaction frequency between the user and the interactive desktop of the bank visual service terminal, and to segment the interaction information according to the interaction frequency to obtain multiple interaction information sequences;

[0154] An information sequence reading subunit, used to read each interactive information sequence respectively, and determine a plurality of first-level interactive nodes corresponding to each interactive information sequence;

[0155] The core field acquisition subunit is used to:

[0156] Obtaining repetition frequencies of multiple first-level interaction nodes in a corresponding interaction information sequence, and extracting second-level interaction nodes whose repetition frequencies are within a preset frequency range;

[0157] Matching the plurality of first-level interaction nodes with the bank vocabulary library, and determining the third-level interaction nodes among the plurality of first-level interaction nodes that match the third-level interaction nodes in the bank vocabulary library;

[0158] A core execution node determination subunit, used for generating a core execution node corresponding to an interactive information sequence based on the secondary interactive node and the tertiary interactive node;

[0159] The execution requirement determination subunit is used to calculate the distance between each core execution node and the remaining core execution nodes respectively, and determine the core execution community according to the distance between each core execution node and the remaining core execution nodes, and splice the target core execution nodes in the core execution community, and output the user's execution requirements based on the splicing results.

[0160] In this embodiment, the interaction frequency is the number of operations performed by the user when performing interactive operations on the interactive desktop.

[0161] In this embodiment, the first-level interaction node may be a data set having connections in the interaction information sequence, and is not unique.

[0162] In this embodiment, the preset frequency interval can be set in advance to achieve the purpose of screening multiple first-level interaction nodes. For example, if the preset frequency interval is greater than or equal to 3, then if the frequency of the first-level interaction node appearing in the interaction information sequence is less than 3, the corresponding first-level interaction node will be eliminated; otherwise, the corresponding first-level interaction node will be extracted, wherein the extracted first-level interaction node is used as the second-level interaction node.

[0163] In this embodiment, the bank vocabulary library can be used to store key words used by the bank, such as "appearance loan" and other words. When there is an interaction node matching the bank vocabulary library in the first-level interaction node, the corresponding interaction node will be used as a third-level interaction node.

[0164] In this embodiment, the core execution node is a node obtained by integrating the second-level interaction node and the third-level interaction node in the interactive information sequence.

[0165] In this embodiment, the distances between the core execution nodes in the plurality of interaction information sequences may be calculated as the association distances between the core execution nodes, that is, the distances between the core execution nodes are calculated by using a semantic matrix or the like.

[0166] In this embodiment, determining the core execution community according to the distance between each core execution node and the remaining core execution nodes can be based on a preset distance threshold, dividing the core execution nodes corresponding to the distance between the current core execution node and the remaining core execution nodes that is less than the preset distance threshold into a community, obtaining the size of the community corresponding to each core execution node, and taking the largest community as the core execution community.

[0167] The working principle and beneficial effects of the above technical solution are: by segmenting the interactive information according to the interaction frequency, a plurality of interactive information sequences are obtained, by identifying a plurality of first-level interactive nodes in the plurality of interactive information sequences, the second-level interactive nodes in the first-level interactive nodes are extracted based on the repetition frequency, by matching the first-level interactive nodes with the bank vocabulary library, the third-level interactive nodes in the first-level interactive nodes are extracted, and then the core execution nodes of the interactive information sequence are obtained through the second-level interactive nodes and the third-level interactive nodes, the core execution nodes are screened again by determining the core execution community, and the target core execution nodes are obtained, and by splicing the target core execution nodes, the user's execution needs are effectively obtained, thereby improving the accuracy of obtaining the execution needs.

[0168] Embodiment 8:

[0169] Based on Example 1, this embodiment provides a visual service terminal control system for a bank, a visual recommendation module, including:

[0170] The project matching unit is used to read the execution requirements, determine the execution targets, and match m banking service projects in the bank visual service terminal according to the execution targets;

[0171] A facial feature reading unit is used to read the facial features of the user, determine the age range of the user, and simultaneously obtain the applicable age range corresponding to each banking service item;

[0172] A service item extraction unit, used to match the user's age range with the adapted age range corresponding to each bank service item, and extract i bank service items corresponding to the user's age range based on the matching result, where i≤m;

[0173] The facial feature reading unit is further used to read the facial features of the user, determine the gender of the user, and at the same time, extract j banking service items from i banking service items according to the gender of the user, wherein j≤i;

[0174] Visual display unit for:

[0175] Perform preliminary visualization of j banking service items on the bank visualization service terminal, and output satisfaction scores of j banking service items based on the emotional changes in the user's facial features;

[0176] The j banking service items are sorted in descending order according to the satisfaction scores, and the final visualization is performed on the bank visualization service terminal based on the sorting results.

[0177] In this embodiment, the execution target may be a type of project that needs to be carried out through the bank visualization service terminal, for example, a financial management project.

[0178] In this embodiment, the execution requirements may be submitted by different users to the bank visualization service terminal, and are used to represent the bank interaction items that need to be performed.

[0179] In this embodiment, the adaptive age range may be a reference age range set by the bank for different banking service items, for example, the age range targeted by high-risk financial products may be between 30 and 40 years old.

[0180] In this embodiment, extracting i banking service items corresponding to the user's age range based on the matching result may be extracting the corresponding banking service items when the user's age range is in the adaptation age range corresponding to the banking service items.

[0181] In this embodiment, selecting j banking service items from i banking service items according to the gender of the user may be determined according to the male-female ratio of the target audiences of different banking service items, that is, which ones are relatively more suitable for men or women.

[0182] In this embodiment, the preliminary visualization display may be to display the obtained j banking service items on the banking visualization service terminal without considering the user's satisfaction with the banking service items, that is, the banking service items are displayed irregularly.

[0183] In this embodiment, the emotion change state may be the emotion change state of the user at different times, for example, it may be a change from anger to peace.

[0184] In this embodiment, the satisfaction score may be a representation of the user's satisfaction with different banking service items determined through emotion change characteristics, and the larger the value, the more satisfied the user is.

[0185] The beneficial effects of the above technical solution are: by analyzing the execution requirements, the bank service items can be effectively determined, and the acquired facial features of the users can be analyzed to accurately analyze the age ranges of different users. Secondly, by matching the age ranges of different users with the adaptive age ranges of the bank service items, the determined bank service items can be preliminarily screened. Finally, the user's satisfaction with the preliminarily screened bank service items is evaluated by facial features, and the preliminarily screened bank service items are screened again according to the satisfaction evaluation results, and the screened bank service items are sorted and displayed in descending order according to the satisfaction scores, thereby improving the service effect of the bank's visual service terminal, and facilitating different users to quickly select bank service items suitable for themselves according to the displayed results, thereby improving work efficiency.

[0186] Embodiment 9:

[0187] This embodiment provides a visual service terminal control method for a bank. Figure 3 As shown, including:

[0188] Step 1: Perform facial recognition on the user based on the bank's visual service terminal and output the user's facial recognition information;

[0189] Step 2: Read the user's interactive information based on the interactive desktop of the bank's visual service terminal;

[0190] Step 3: Analyze the interaction information to obtain the execution requirements corresponding to the interaction information. At the same time, analyze the user's face recognition information to obtain the user's facial features.

[0191] Step 4: Match multiple banking service items on the bank visualization service terminal based on execution requirements, and optimize and recommend multiple banking service items to users based on facial features. At the same time, visualize the recommended banking service items on the bank visualization service terminal.

[0192] The working principle and beneficial effects of the above technical solution are: by collecting the user's facial recognition information and the user's interaction information, the user's execution needs and the user's facial features can be effectively and accurately acquired, and by combining the execution needs and the user's facial features, the optimized recommendation of banking service items can be realized and visualized. Based on the interaction process and combined with facial recognition, the accuracy of the recommendation of banking service items can be effectively guaranteed, thereby saving the user's time in selecting banking service items, and through visual display, the convenience and intelligence of the recommendation and application of banking service items are improved, thereby improving user satisfaction.

[0193] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A visual service terminal control system for a bank, characterized in that: include: A face recognition module is used to perform face recognition on users based on a bank visual service terminal and output the face recognition information of users; An interactive module, used to read user interaction information based on the interactive desktop of the bank's visual service terminal; The information analysis module is used to analyze the interaction information to obtain the execution requirements corresponding to the interaction information, and at the same time, analyze the user's face recognition information to obtain the user's facial features; A visualization recommendation module is used to match multiple banking service items on a bank visualization service terminal based on execution requirements, and to optimize and recommend multiple banking service items to users based on facial features. At the same time, the recommended banking service items are visualized and displayed on the bank visualization service terminal; Face recognition module, including: A scanning node creation unit, used to create a scanning node based on a bank visual service terminal and build a scanning mechanism in the scanning node; A sub-recognition model building unit, used for obtaining multiple face recognition dimensions, mapping the multiple face recognition dimensions in a scanning node, and building multiple sub-recognition mechanisms in the scanning node based on the mapping results; The scanning interval determination unit is used for: Get the location node of the bank's visual service terminal; Obtain the user's location node relative to the bank's visualization service terminal; A scanning interval for scanning the user based on the bank visualization service terminal is constructed based on the location node of the bank visualization service terminal and the location node of the user relative to the bank visualization service terminal; A parameter configuration unit, used to determine a vertical scanning parameter and a horizontal scanning parameter based on a scanning interval, and configure the vertical scanning parameter and the horizontal scanning parameter in a scanning mechanism; Scanning unit for: Scan the user's face vertically and horizontally based on the configured scanning mechanism; Draw a target scan image of the user's face based on vertical scanning and horizontal scanning; The face recognition information acquisition unit is used to: The target scanned image of the user's face is input into each sub-recognition mechanism in the scanning node respectively, and the corresponding sub-face recognition information is output based on the sub-recognition mechanism to obtain the user's face recognition information.

2. A visual service terminal control system for a bank, characterized in that: include: A face recognition module is used to perform face recognition on users based on a bank visual service terminal and output the face recognition information of users; An interactive module, used to read user interaction information based on the interactive desktop of the bank's visual service terminal; The information analysis module is used to analyze the interaction information to obtain the execution requirements corresponding to the interaction information, and at the same time, analyze the user's face recognition information to obtain the user's facial features; A visualization recommendation module is used to match multiple banking service items on a bank visualization service terminal based on execution requirements, and to optimize and recommend multiple banking service items to users based on facial features. At the same time, the recommended banking service items are visualized and displayed on the bank visualization service terminal; The face recognition module comprises: The facial capture unit is used to capture the user's face based on the bank visual service terminal, and when the target face is captured, the user's stay time in front of the bank visual service terminal is timed to obtain the target time; A face recognition unit, used to perform face recognition on a user and obtain face recognition information of the user when the target moment reaches a preset standard; Facial capture unit, comprising: The picture acquisition subunit is used to acquire pictures of the external area in real time based on the bank visualization service terminal, and read the picture acquisition frames of the external area in real time; The initial picture information acquisition subunit is used to acquire the initial picture information of the external area and set the picture acquisition frame corresponding to the initial picture information as the current picture acquisition frame; Dynamic tracking subunit for: Dynamically tracking the picture information of the next picture acquisition frame based on the current picture acquisition frame; When the picture information of the next picture acquisition frame is consistent with the initial picture information of the current picture acquisition frame, the next picture acquisition frame is updated to the current picture acquisition frame, until the picture information of the next picture acquisition frame is inconsistent with the initial picture information, the external area image corresponding to the next picture acquisition frame is captured; The image analysis subunit is used to analyze the external area image, obtain the foreground image of the external area image, and at the same time, obtain the outer contour points and inner contour points of the foreground image, and determine the image features of the foreground image according to the outer contour points and inner contour points of the foreground image; A capture subunit is used to match the image features of the scene image with the sample features. When the image features of the scene image match the sample features, the target face is captured; The dynamic tracking subunit is also used to update the next picture acquisition frame to the current picture acquisition frame when the image features of the exterior scene image do not match the sample features, and continue to dynamically track the picture information of the next picture acquisition frame based on the current picture acquisition frame.

3. A visual service terminal control system for a bank according to claim 1, characterized in that: Interaction modules include: The interactive desktop monitoring unit is used to monitor the interactive desktop in real time when the user performs interactive operations on the interactive desktop, determine the execution dynamics of the interactive desktop, An information reading mode determining unit, used to determine the user's interaction mode based on the execution dynamics, and at the same time, determine the information reading mode according to the user's interaction mode; The interactive information reading unit is used to read the execution dynamics of the interactive desktop based on the information reading method to determine the user's interactive information.

4. A visual service terminal control system for a bank according to claim 1, characterized in that: Information analysis module, including: A first information analysis unit, used to analyze the interaction information and determine the user's execution requirements; and a second information analysis unit, for analyzing the user's face recognition information to obtain the user's facial features.

5. A visual service terminal control system for a bank according to claim 4, characterized in that: The first information analysis unit comprises: The information processing subunit is used to obtain the interaction frequency between the user and the interactive desktop of the bank visual service terminal, and to segment the interaction information according to the interaction frequency to obtain multiple interaction information sequences; An information sequence reading subunit, used to read each interactive information sequence respectively, and determine a plurality of first-level interactive nodes corresponding to each interactive information sequence; The core field acquisition subunit is used to: Obtaining repetition frequencies of multiple first-level interaction nodes in a corresponding interaction information sequence, and extracting second-level interaction nodes whose repetition frequencies are within a preset frequency range; Matching the plurality of first-level interaction nodes with the bank vocabulary library, and determining the third-level interaction nodes among the plurality of first-level interaction nodes that match the third-level interaction nodes in the bank vocabulary library; A core execution node determination subunit, used for generating a core execution node corresponding to an interactive information sequence based on the secondary interactive node and the tertiary interactive node; The execution requirement determination subunit is used to calculate the distance between each core execution node and the remaining core execution nodes respectively, and determine the core execution community according to the distance between each core execution node and the remaining core execution nodes, and splice the target core execution nodes in the core execution community, and output the user's execution requirements based on the splicing results.

6. A visual service terminal control system for a bank according to claim 4, characterized in that: The second information analysis unit comprises: The reading subunit is used to read the user's face recognition information and determine the morphological distribution characteristics of the user's facial features; The facial feature determination subunit is used to determine the facial features of the user based on the facial features of the user.

7. A visual service terminal control system for a bank according to claim 1, characterized in that: Visual recommendation module, including: The project matching unit is used to read the execution requirements, determine the execution targets, and match m banking service projects in the bank visual service terminal according to the execution targets; A facial feature reading unit is used to read the facial features of the user, determine the age range of the user, and simultaneously obtain the applicable age range corresponding to each banking service item; The service item extraction unit is used to match the user's age range with the adapted age range corresponding to each bank service item, and extract i bank service items corresponding to the user's age range based on the matching result, wherein: ; The facial feature reading unit is also used to read the facial features of the user, determine the gender of the user, and extract j banking service items from i banking service items according to the gender of the user, wherein: ; and visual display unit for: Perform preliminary visualization of j banking service items on the bank visualization service terminal, and output satisfaction scores of j banking service items based on the emotional changes in the user's facial features; The j banking service items are sorted in descending order according to the satisfaction scores, and the final visualization is performed on the bank visualization service terminal based on the sorting results.

8. A visual service terminal control method for a bank, characterized in that: include: Step 1: Perform facial recognition on the user based on the bank's visual service terminal and output the user's facial recognition information; Step 2: Read the user's interactive information based on the interactive desktop of the bank's visual service terminal; Step 3: Analyze the interaction information to obtain the execution requirements corresponding to the interaction information. At the same time, analyze the user's face recognition information to obtain the user's facial features. Step 4: Match multiple banking service items on the bank visualization service terminal based on the execution requirements, and optimize and recommend the user from the multiple banking service items based on the facial features. At the same time, visualize the recommended banking service items on the bank visualization service terminal; Step 1 includes: Based on the bank visual service terminal, a scanning node is created using a scanning node creation unit, and a scanning mechanism is built in the scanning node; Acquire multiple face recognition dimensions using a sub-recognition model construction unit, map the multiple face recognition dimensions in a scanning node, and construct multiple sub-recognition mechanisms in the scanning node based on the mapping results; Using a scanning interval determination unit to obtain a location node of the bank visualization service terminal and a location node of the user relative to the bank visualization service terminal, and constructing a scanning interval for scanning the user based on the bank visualization service terminal based on the location node of the bank visualization service terminal and the location node of the user relative to the bank visualization service terminal; Determine the vertical scanning parameters and the horizontal scanning parameters based on the scanning interval using a parameter configuration unit, and configure the vertical scanning parameters and the horizontal scanning parameters in the scanning mechanism; Scanning the user's face vertically and horizontally using a scanning unit based on a configured scanning mechanism; drawing a target scan image of the user's face based on the vertical scanning and the horizontal scanning; The face recognition information acquisition unit is used to input the target scan image of the user's face into each sub-recognition mechanism in the scanning node respectively, and the corresponding sub-face recognition information is output based on the sub-recognition mechanism to obtain the user's face recognition information.

Images