CN117176775A - Bank data processing method and system based on remote service - Google Patents
Bank data processing method and system based on remote service Download PDFInfo
- Publication number
- CN117176775A CN117176775A CN202311444880.7A CN202311444880A CN117176775A CN 117176775 A CN117176775 A CN 117176775A CN 202311444880 A CN202311444880 A CN 202311444880A CN 117176775 A CN117176775 A CN 117176775A
- Authority
- CN
- China
- Prior art keywords
- data
- service
- banking
- sub
- scanning
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 10
- 238000012545 processing Methods 0.000 claims abstract description 84
- 238000000034 method Methods 0.000 claims abstract description 50
- 238000012512 characterization method Methods 0.000 claims abstract description 29
- 238000012795 verification Methods 0.000 claims description 27
- 230000008569 process Effects 0.000 claims description 15
- 238000007906 compression Methods 0.000 claims description 14
- 238000003860 storage Methods 0.000 claims description 14
- 230000006835 compression Effects 0.000 claims description 12
- 238000012937 correction Methods 0.000 claims description 9
- 230000002159 abnormal effect Effects 0.000 claims description 7
- 238000000354 decomposition reaction Methods 0.000 claims description 6
- 238000009499 grossing Methods 0.000 claims description 6
- 238000009826 distribution Methods 0.000 claims description 5
- 230000009467 reduction Effects 0.000 claims description 3
- 230000002452 interceptive effect Effects 0.000 abstract description 5
- 230000005540 biological transmission Effects 0.000 description 17
- 239000013598 vector Substances 0.000 description 10
- 238000004458 analytical method Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 9
- 230000003993 interaction Effects 0.000 description 8
- 230000007246 mechanism Effects 0.000 description 6
- 230000006837 decompression Effects 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 238000005457 optimization Methods 0.000 description 5
- 230000011218 segmentation Effects 0.000 description 5
- 230000009471 action Effects 0.000 description 4
- 238000013461 design Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000013507 mapping Methods 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000006798 recombination Effects 0.000 description 2
- 238000005215 recombination Methods 0.000 description 2
- 238000009877 rendering Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 238000005452 bending Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000013524 data verification Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000001815 facial effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000007654 immersion Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Processing Or Creating Images (AREA)
Abstract
The invention provides a bank data processing method and system based on remote service, and relates to the field of financial data processing, wherein the method comprises the following steps: acquiring service terminal information, and scanning a bank operator according to banking businesses to acquire banking service data of a corresponding service terminal of the banking businesses; decomposing the banking service data into a plurality of sub-service data according to banking businesses, and calculating characterization factors of the banking businesses corresponding to the sub-service data respectively; calculating target input processing parameters of the banking service data according to service terminal information, and calculating sub-input processing parameters of each sub-service data under the target input processing parameters according to the characterization factors; and processing each piece of sub-service data according to the sub-input processing parameters, and summarizing to generate banking service input data. The invention can intelligently determine the data processing scheme according to the information of the terminal network points, and effectively improves the safety and the processing efficiency of the interactive data in the remote service scene of the bank.
Description
Technical Field
The invention relates to the field of financial data processing, in particular to a bank data processing method and system based on remote service.
Background
Along with the development of mobile internet and big data technology, banking industry actively expands on-line business and provides remote services such as account opening, transfer remittance, loan approval and the like so as to realize digitization and intellectualization of the business.
Currently, these remote services involve the network transmission of a large amount of interactive data, including data such as the operational gestures, facial movements, etc. of the bank teller.
In the related art, the conventional unified data processing scheme is difficult to consider transmission efficiency and data security, lacks intelligent analysis processing aiming at the remote interaction data content characteristics of banks, cannot realize differentiated intelligent processing, and can reduce the interaction experience of users and virtual teller.
Disclosure of Invention
The technical problem to be solved by the invention is to provide the remote service-based bank data processing method and system, which can intelligently determine the data processing scheme according to the information of the terminal website, effectively improve the safety and processing efficiency of interactive data in a remote service scene of a bank, and optimize the reconstruction of a high-fidelity three-dimensional virtual image of a bank teller in the remote service of the bank.
In order to solve the technical problems, the technical scheme of the invention is as follows:
in a first aspect, a method for processing bank data based on remote service, the method comprising:
acquiring service terminal information, and scanning a bank operator according to banking businesses to acquire banking service data of a corresponding service terminal of the banking businesses;
decomposing the banking service data into a plurality of sub-service data according to banking businesses, and calculating characterization factors of the banking businesses corresponding to the sub-service data respectively;
calculating target input processing parameters of the banking service data according to service terminal information, and calculating sub-input processing parameters of each sub-service data under the target input processing parameters according to the characterization factors;
processing each piece of sub-service data according to the sub-input processing parameters, and summarizing to generate banking service input data;
outputting the banking service input data to a service terminal, and restoring the banking service input data to obtain banking service output data;
and generating a holographic image according to the output data of the banking service, and interacting with the user according to the holographic image.
Further, obtaining service terminal information, and scanning a bank operator according to banking business to obtain banking service data of a service terminal corresponding to the banking business, including:
Acquiring a service type and position coordinates of a service terminal, and scanning a bank operator corresponding to the service type to obtain three-dimensional model data of the bank operator;
verifying the three-dimensional model data to obtain a verification result;
setting a confidence threshold, calculating the confidence coefficient corresponding to the verification result, and storing the three-dimensional model data to generate banking service data if the confidence coefficient meets the confidence threshold; and if the confidence coefficient does not meet the confidence threshold value, scanning the bank operator again.
Further, scanning the bank operator corresponding to the service type to obtain three-dimensional model data of the bank operator, including:
checking the data of each scanning point, and if error points or missing point data exist, updating the data of the scanning points to generate a scanning data set corresponding to a bank operator;
and merging and denoising the elements in the scanning data set to obtain three-dimensional model data.
Further, the data of each scanning point is checked, if there is a wrong point or missing point data, the data of the scanning points is updated, and a scanning data set corresponding to a bank operator is generated, which includes:
Formatting the original three-dimensional scanning data to generate a data packet structure, wherein each data packet comprises a preset number of scanning data points;
calculating redundancy check codes for each data packet and adding the redundancy check codes into the data packets;
generating at least one data block according to the plurality of data packets, and calculating redundancy check codes corresponding to the data blocks, wherein the data blocks comprise a preset number of data packets;
setting a receiving verification end, and verifying the integrity according to the verification codes of the data packet and the data block, wherein if the data packet or the data block is incomplete, retransmission is requested;
generating a hash value of each scanning data point by using a hash algorithm, comparing the hash value with a preset correct hash value, and verifying whether the content of the scanning data point is correct;
correcting the scanned data points with verification errors by using an error correction coding algorithm until all the data points pass the verification;
a set of validated scan data points is generated.
Further, merging and denoising the elements in the scan dataset to obtain three-dimensional model data, including:
calculating the distance relation and the direction relation between each data point according to the three-dimensional coordinate values of the elements in the scanning data set;
Generating a three-dimensional grid model according to the distance relation and the direction relation between the data points;
smoothing the three-dimensional grid model, and adjusting coordinates of grid nodes to eliminate high-frequency noise;
judging whether abnormal noise points exist or not according to the distribution condition of data values on each grid in the three-dimensional grid model, and correcting the abnormal noise points;
and filling the cavities in the three-dimensional grid model to obtain three-dimensional model data.
Further, the method includes decomposing the banking service data into a plurality of sub-service data according to banking business, and calculating characterization factors of the respective sub-service data corresponding to the banking business, including:
calculating geometric factors of each point data in the bank service data, and extracting a three-dimensional contour of a physical part of a corresponding bank operator according to the geometric factors;
according to the topological structure of the banking service data, determining point data in the banking service data corresponding to each three-dimensional outline to obtain a plurality of sub-service data;
and calculating service descriptors of all the sub-service data, and calculating characterization factors of all the sub-service data according to the service descriptors.
Further, processing each piece of sub-service data according to the sub-input processing parameters, and summarizing to generate banking service input data, including:
Reading each piece of sub-service data and the corresponding compression rate and encryption strength parameters thereof, and compressing and encrypting each piece of sub-service data;
defining a unified data format, wherein the data format comprises a fixed-length header information field and a variable-length data field;
assembling all sub-service data according to the data format to generate summarized data;
the summary data is serialized in binary format to generate banking input data.
In a second aspect, a remote service based banking data processing system includes:
the acquisition module is used for acquiring the service terminal information, scanning a bank operator according to banking businesses, and acquiring banking service data of a service terminal corresponding to the banking businesses;
the decomposition module is used for decomposing the banking service data into a plurality of sub-service data according to banking businesses, and calculating characterization factors of the banking businesses corresponding to the sub-service data respectively;
the computing module is used for computing target input processing parameters of the banking service data according to the service terminal information and computing sub-input processing parameters of each sub-service data under the target input processing parameters according to the characterization factors;
The processing module is used for processing each piece of sub-service data according to the sub-input processing parameters and summarizing to generate banking service input data;
the output module is used for outputting the banking service input data to a service terminal, and carrying out reduction processing on the banking service input data to obtain banking service output data;
and the service module is used for generating a holographic image according to the bank service output data and carrying out interaction service with a user according to the holographic image.
In a third aspect, a computing device includes:
one or more processors;
and a storage device for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to implement the above-described methods.
In a fourth aspect, a computer readable storage medium stores a program that when executed by a processor implements the above method.
The scheme of the invention at least comprises the following beneficial effects:
according to the scheme, the data transmission scheme can be intelligently determined according to the information of the terminal website, the importance of the data area is judged based on the business content, differential processing is realized, the safety and the processing efficiency of interactive data in a remote service scene of a bank are effectively improved, and the reconstruction of a high-fidelity three-dimensional virtual image of a bank teller in the remote service of the bank is optimized.
Drawings
Fig. 1 is a schematic flow chart of a banking data processing method based on remote service according to an embodiment of the present invention.
FIG. 2 is a block diagram of a remote service based banking data processing system provided by an embodiment of the present invention.
Reference numerals:
10. an acquisition module; 20. a decomposition module; 30. a computing module; 40. a processing module; 50. an output module; 60. and a service module.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
As shown in fig. 1, an embodiment of the present invention proposes a banking data processing method based on remote service, the method including:
step 1, acquiring service terminal information, and scanning a bank operator according to banking businesses to obtain banking service data of a service terminal corresponding to the banking businesses;
Step 2, decomposing the banking service data into a plurality of sub-service data according to banking business, and calculating characterization factors of the banking business corresponding to each sub-service data respectively;
step 3, calculating target input processing parameters of the banking service data according to service terminal information, and calculating sub-input processing parameters of each sub-service data under the target input processing parameters according to the characterization factors;
step 4, processing each piece of sub-service data according to the sub-input processing parameters, and summarizing to generate banking service input data;
step 5, outputting the banking service input data to a service terminal, and restoring the banking service input data to obtain banking service output data;
and 6, generating a holographic image according to the output data of the banking service, and carrying out interactive service with the user according to the holographic image.
In a preferred embodiment of the present invention, the step 1 of obtaining service terminal information and scanning a banking operator according to banking business to obtain banking service data of a banking business corresponding service terminal includes:
step 11, acquiring the service type and the position coordinates of the service terminal, and scanning a bank operator corresponding to the service type to obtain three-dimensional model data of the bank operator;
Step 12, verifying the three-dimensional model data to obtain a verification result;
step 13, setting a confidence threshold value, calculating the confidence coefficient corresponding to the verification result, and storing the three-dimensional model data to generate banking service data if the confidence coefficient meets the confidence threshold value; and if the confidence coefficient does not meet the confidence threshold value, scanning the bank operator again.
In the above steps of the embodiment of the invention, step 11 obtains the position information of the service terminal, can calculate the transmission distance with the headquarter of the bank, and provides basis for the subsequent determination of the transmission scheme; step 12, ensuring the quality of the scanned three-dimensional data through a verification algorithm, avoiding data loss or error and ensuring the reliability of subsequent processing; step 13, setting a reasonable confidence threshold, wherein only three-dimensional data meeting the quality requirement can enter subsequent processing, and a re-scanning strategy also ensures that complete and available data is obtained; the obtained high-quality and complete three-dimensional data is the basis for realizing accurate digital banking service, and a verification algorithm can evaluate the scanning quality by calculating indexes such as the integrity, the precision, the authenticity and the like of the three-dimensional data; the confidence coefficient is integrated with a plurality of quality indexes, and whether the three-dimensional data reach the standard can be accurately judged by comparing the confidence coefficient with a threshold value, so that the limitation of a single index is avoided; the rescanning strategy can realize autonomous correction and optimization, three-dimensional data with reliable quality is finally obtained, and the reliability and the robustness of the bank service digitizing process are greatly improved through a quality verification mechanism.
In a preferred embodiment of the present invention, the step 11 of scanning the bank operator corresponding to the service type to obtain three-dimensional model data of the bank operator includes:
step 111, verifying the data of each scanning point, if there is a wrong point or missing point data, updating the data of the scanning points, and generating a scanning data set corresponding to a bank operator;
and step 112, merging and denoising the elements in the scanning data set to obtain three-dimensional model data.
In the above steps of the embodiment of the present invention, the scanning point data checking mechanism in step 111 may avoid various errors, such as coordinate errors, omission, etc., generated in the scanning process, so as to ensure the integrity and accuracy of the scanning point cloud data; updating the found error points and missing points, repairing data by using algorithms such as interpolation, fitting and the like, and avoiding negative influence of data defects on subsequent processing; the quality of the scanning point cloud data directly determines the effect of the three-dimensional model generated subsequently, and the step 111 ensures the data quality from the source through data verification and restoration; step 112, combining a large number of independent scan point data into a unified three-dimensional geometric model by using a three-dimensional reconstruction algorithm; noise in the model is removed by adopting algorithms such as smoothing and filtering, so that the geometric structure is finer and smoother; the scanning point cloud data often has the problems of scattering, redundancy and the like, and the step 112 is to obtain a compact and accurate three-dimensional digital model through data merging and denoising.
In a preferred embodiment of the present invention, the step 111 of verifying the data of each scan point, if there is an error point or missing point data, updating the data of the scan point to generate a scan data set corresponding to the bank operator includes:
step 1111, performing formatting processing on the original three-dimensional scan data to generate a data packet structure, wherein each data packet includes a preset number of scan data points;
step 1112, calculating redundancy check code for each data packet and adding the redundancy check code to the data packet;
step 1113, generating at least one data block according to the plurality of data packets, and calculating a redundancy check code corresponding to the data block, wherein the data block comprises a preset number of data packets;
step 1114, setting a receiving verification end, and verifying the integrity according to the verification codes of the data packet and the data block, wherein if the data packet or the data block is incomplete, retransmission is requested;
step 1115, generating a hash value of each scan data point by using a hash algorithm, comparing the hash value with a preset correct hash value, and verifying whether the contents of the scan data points are correct;
step 1116, correcting the scan data points with failed verification by using an error correction coding algorithm until all data points pass the verification;
Step 1117, a set of verified scan data points is generated, generating a scan data set.
In the above steps in the embodiment of the present invention, step 1111 encapsulates the original scan data into a structured data packet, which is convenient for verification and transmission, and improves the processing efficiency; step 1112 adds a redundancy check to each packet to detect the integrity of the packet during transmission; step 1113 further generates larger data blocks, each data block containing a plurality of data packets, and adds a check code, so that the integrity of the block-level data can be verified; step 1114 sets a receiving verification end, and can detect the correctness of the data packet and the data block in real time according to the check code, and request retransmission in time, so that data omission is avoided; step 1115 uses a hash algorithm to check the data content of each scanning point, so that errors introduced in the scanning process can be avoided; step 1116 carries out error correction coding correction on the detected error data points, thereby ensuring the accuracy of the data; step 1117, after layer-by-layer verification, outputting a reliable scanning data set; the multi-level redundancy check mechanism comprehensively verifies the integrity, correctness and consistency of the data, and greatly improves the robustness of the system; the error correction coding correction mechanism can be self-iterated and optimized, and accurate and reliable data can be output.
In a preferred embodiment of the present invention, the step 112 of merging and denoising the elements in the scan dataset to obtain three-dimensional model data includes:
step 1121, calculating the distance relation and the direction relation between each data point according to the three-dimensional coordinate values of the elements in the scanned data set;
step 1122, generating a three-dimensional grid model according to the distance relation and the direction relation between the data points;
step 1123, performing smoothing on the three-dimensional grid model, and adjusting coordinates of grid nodes to eliminate high-frequency noise;
step 1124, judging whether abnormal noise exists according to the distribution condition of the data values on each grid in the three-dimensional grid model, and correcting the abnormal noise;
and 1126, filling the holes in the three-dimensional grid model to obtain three-dimensional model data.
In the above steps of the embodiment of the present invention, step 1121 calculates the spatial relationship between data points, providing a foundation for constructing a topology structure, which is a precondition for realizing three-dimensional reconstruction; step 1122, generating a three-dimensional grid according to the data point spatial relationship, so as to realize the conversion from discrete points to a continuous surface and obtain an initial three-dimensional geometric model; step 1123 adjusts grid coordinates through smoothing, so that high-frequency errors caused by scanning noise can be eliminated, and the geometric accuracy of the model is improved; step 1124 detects and corrects the abnormal points of the data on the grid, avoids the pollution of errors to the reconstruction result, and ensures the correctness of the model; step 1126, filling the model cavity, so that the geometric structure is more rigorous and complete, and the usability of the model is improved; the model geometry is finer and smoother through smoothing and noise correction, so that the negative influence of scanning noise is avoided; the continuity and the tightness of the three-dimensional model are obviously improved through the cavity filling treatment.
In a preferred embodiment of the present invention, the step 2 of decomposing the banking data into a plurality of sub-service data according to banking, and calculating the characterization factor of each sub-service data corresponding to banking respectively includes:
step 21, calculating the geometric factors of each point data in the bank service data, and extracting the three-dimensional contour of the corresponding physical part of the bank operator according to the geometric factors;
step 22, determining point data in the banking data corresponding to each three-dimensional outline according to the topological structure of the banking data to obtain a plurality of sub-service data;
and step 23, calculating service descriptors of all the sub-service data, and calculating characterization factors of all the sub-service data according to the service descriptors.
In the above steps of the embodiment of the present invention, step 21 can accurately detect the three-dimensional contours of the face, limbs, etc. in the three-dimensional model of the bank teller by calculating geometric factors such as curvature, normal vector, etc.; the accurately extracted three-dimensional contour is the basis for body part segmentation; step 22, further determining three-dimensional point data corresponding to the outline according to topology information of the three-dimensional model, and realizing semantic segmentation of banking service data; the banking service data is decomposed into a plurality of sub-data areas such as a face area, a hand area and the like, and targeted business analysis can be performed; step 23, extracting and matching the feature descriptors of each piece of sub-service data, and counting the number of different service actions; the characterization factors directly reflect the importance of each body part area to the service scene reconstruction; the whole process realizes the upgrade of the banking service data from passive digitization to active analysis.
In a preferred embodiment of the present invention, the step 21 calculates a geometric factor of each point data in the banking data, and extracts a three-dimensional contour of a physical part of a corresponding banking operator according to the geometric factor, including:
step 211, traversing all of the banking dataAnd calculate eachA kind of electronic deviceAnd gradient direction ∇；
Step 212, according to eachA kind of electronic deviceAnd gradient direction ∇Calculate eachPrincipal curvature value in orthogonal directionAndwherein, the method comprises the steps of, wherein,，，as the second partial derivative of the normal vector n with respect to the x-coordinate,for a second order mixed bias of normal vector n with respect to the x and y coordinates,second partial derivative of normal vector n with respect to y coordinate;
step 213, according to eachPrincipal curvature value in orthogonal directionAndcalculate eachWherein,；
step 214, setting a contour curvature thresholdAnd compares the curvature K of each vertex withScreening to obtain contour points;
step 215, connecting the contour points according to the consistency of the normal vector directions, and outputting a three-dimensional space contour curve C corresponding to the physical part of the bank operator, wherein the connection condition of the two contour points is as follows: n 1· n 2 |＞cos(θ)，n 1 ，n 2 And the normal vectors of the two contour points are respectively, and theta is a preset normal vector angle threshold value.
In the above steps of the embodiment of the invention, the principal curvature reflects the bending degree of the curved surface at the point, and only further reflects the shape characteristics of the curved surface where the point is located, which is an important basis for extracting the contour; step 213 substitutes two principal curvature values into a formula, and can synthesize a gaussian curvature K of each point, where the gaussian curvature is a key geometric feature describing a curved surface; step 214 effectively screens out potential contour points from all points by setting a contour curvature threshold; step 215, further performing contour point connection according to the consistency of the normal vector, and extracting three-dimensional space contour curves of the parts such as the face; by means of the geometrical characteristics of curvature, accurate part segmentation of the three-dimensional model of the bank teller is realized; the smoothness and the correctness of the contour curve are ensured by the normal vector consistency constraint; the whole process realizes the intelligent analysis of the three-dimensional shape and achieves the effect of accurately detecting the outline of the part.
In a preferred embodiment of the present invention, the step 22 of determining, according to the topology structure of the banking data, point data in the banking data corresponding to each three-dimensional contour to obtain a plurality of sub-service data includes:
step 221, constructing a topological structure relation graph G (V, F) of the bank service data, wherein V is a top point set and F is a face set;
Step 222, finding all the faces F containing any vertex V on the contour curve C according to any vertex V through the topological structure relation graph G (V, F) v， ；
Step 223, to be processed by surface F v The data in the three-dimensional surface area is formed as sub-service data.
In a preferred embodiment of the present invention, the topology map G (V, F) of banking data satisfies the following condition: each surface F epsilon F is represented by a group of vertexes, and the vertex set of the surface F is set as V f The method comprises the steps of carrying out a first treatment on the surface of the If the vertex V is one of the vertices constituting the plane F, the edge (V, F) is added to the graph G (V, F).
In the above steps of the embodiment of the present invention, step 221 constructs a vertex-surface topology relationship diagram of banking data, and accurately describes topology information of a three-dimensional model; the topological relation graph associates basic unit faces of the model with vertexes constituting the faces, and establishes a corresponding relation between the faces and the vertexes; step 222, searching the surface of the vertex on the contour curve to determine the surface area of the face and other parts; step 223 finally extracts sub-service data corresponding to the three-dimensional surface, and completes semantic segmentation of bank service data; the topological relation diagram describes topological information of the three-dimensional model by a data structure of the diagram, so that the corresponding query between the surface and the vertex can be simple and efficient; the data area is extracted according to the topological structure, so that the process is automated, and the area does not need to be marked manually; the utilization of topology information improves the understandability of three-dimensional data and realizes the transition from passive digitization to active analysis; and finally, the accurate semantic segmentation of the banking service data is realized, and support is provided for differentiated service analysis of different parts.
In a preferred embodiment of the present invention, the step 23 calculates a service descriptor of each sub-service data, and calculates a characterization factor of each sub-service data according to the service descriptor, including:
step 231, detecting key points for each sub-service data, and extracting local service descriptors of the key points;
step 232, constructing a three-dimensional action key frame data set corresponding to the current banking business, and clustering the three-dimensional action key frame data set according to the local business descriptor;
step 233, counting the occurrence proportion of the business descriptors in each sub-service data in the clusters with the intra-class variance smaller than a preset threshold;
step 234, calculating a characterization factor for the sub-service data based on the scale.
Optionally, in the step 234, the formula is used:calculating a characterization factor F of sub-service data i Wherein, the method comprises the steps of, wherein,for the purpose of clustering the weight vectors,for the weight of class M clusters, f (·) is a softmax function, normalizing the characterization factor of each sub-service data to [0,1 ]]The range of the light-emitting diode is within the range,the occurrence ratio distribution of the business descriptors representing the sub-service data i in each cluster,the proportion of occurrence of the business descriptor for sub-service data i in class M clusters, The proportional distribution occurs for clusters of other sub-service data j.
In the above steps of the embodiment of the present invention, step 231 obtains a local service feature representation of each sub-service data area by detecting key points and extracting descriptors; step 232, constructing a service key frame data set, and analyzing different service actions by using a descriptor cluster to realize unsupervised service understanding; step 233, counting the proportion of descriptors in important service clusters, and reflecting the richness of the region containing the service information; the characterization factors directly reflect the importance of each sub-service data to the restored service scene; the softmax normalization makes the characterization factor range of each region uniform, so that the subsequent processing is convenient; the description sub-cluster avoids manual marking of service types and realizes intelligent service understanding; the intra-class variance judgment can effectively identify important business clusters with compact aggregation; finally, the extent of inclusion of different business information for each body part region can be assessed.
In a preferred embodiment of the present invention, the step 3 calculates a target input processing parameter of the banking data according to service terminal information, and calculates sub-input processing parameters of each sub-service data under the target input processing parameter according to the characterization factor, including:
Step 31, acquiring the transmission distance of the bank service data according to the position coordinates of the service terminal;
step 32, by the formula:constructing a transmission distance D and a compression rate C R A mapping relationship between the two, wherein,、andis an empirical parameter;
step 33, by the formula:constructing a mapping relation between the transmission distance D and the encryption intensity, wherein f (·) is a unit step function,is a preset threshold distance;is an encryption intensity coefficient;
step 34, by the formula:build compression complexityAnd encryption complexityWherein C is a processing resource capacity limit;
step 35, by the formula:constructing a business value model of sub-service dataWherein, the method comprises the steps of, wherein,characterization factor for sub-service data i，For the utility of the resource corresponding to the compression rate,security corresponding to encryption strength;
step 36, optimizing an objective function:the method comprises the steps of carrying out a first treatment on the surface of the Wherein N is the total number of sub-service data, and C is the processing resource capacity limit;
step 37, step by step determining each sub-service data using dynamic programmingAndwherein, the method comprises the steps of, wherein,；
step 38, dynamically adjusting the determined sub-service data during the optimization iterationAndand obtaining sub-input processing parameters of each sub-service data under the target input processing parameters.
In the above steps of the embodiment of the present invention, step 32 constructs a distance-compression ratio map, to realize a compression ratio that smoothly increases with distance, preventing loss caused by over-compression; step 33, constructing a distance ladder mapping relation, and grading and enhancing encryption strength along with the distance to realize the balance of safety and efficiency; step 34, establishing a constraint relation between compression and encryption, and ensuring that the total resource consumption does not exceed the device capacity limit; step 35, fully considering content importance, compression utility and encryption income, and establishing a complete business value model; step 36, constructing an optimization target with maximized service value, and searching an optimal parameter solution under constraint; step 37, adopting dynamic programming global searching to determine the optimal compression rate and encryption strength of each sub-service data; step 38, iterative optimization is carried out, and the scheme of the determined data is dynamically adjusted to achieve overall optimization.
In a preferred embodiment of the present invention, the step 4 processes each piece of sub-service data according to the sub-input processing parameter, and generates the banking service input data in a summarizing manner, including:
step 41, reading each piece of sub-service data and the corresponding compression rate and encryption strength parameters thereof, and compressing and encrypting each piece of sub-service data;
Step 42, defining a unified data format, wherein the data format comprises a header information field with fixed length and a data field with variable length;
step 43, all sub-service data are assembled according to the data format, and summary data are generated;
at step 44, the summary data is serialized in binary format to generate banking input data.
In the above steps of the embodiment of the present invention, the header information field includes control information such as a magic number, a data length, a check code, etc., for identifying and verifying data; the data field stores the compressed and encrypted different sub-service data, and a separator is added between each sub-service data for division.
In the above steps of the embodiment of the present invention, step 41 invokes the optimized compression and encryption parameters, and performs differential processing on each sub-service data, thereby improving efficiency; step 42 designs the unified data format, so that the receiving end can analyze and process conveniently, and the flexibility is improved; the head control information realizes the functions of data identification, verification and positioning; the data field organization mode gives consideration to the processing efficiency and the analysis simplicity; step 43, effectively combining the sub-data according to the format to generate summarized input data which can be directly transmitted; step 44 binary serialization realizes efficient and stable transmission and simplifies the processing of the receiving end; the user-defined format design realizes the effective fusion of the sub-service data; the formatting design improves the flexibility of data processing and transmission; finally, banking service input data capable of being directly transmitted is generated, and meanwhile, the position information of the sub data is reserved; an efficient application of the differentiated handling parameters is achieved.
In a preferred embodiment of the present invention, the step 5 of outputting the banking service input data to a service terminal, and performing a restoration process on the banking service input data to obtain banking service output data includes:
step 51, establishing an end-to-end encryption transmission channel, and outputting the banking service input data to the service terminal by using an encryption transmission protocol;
step 52, the terminal verifies the data signature by using a preset key, and calculates to verify the integrity of the data;
step 53, analyzing the self-defined data format, and using the control field to locate and separate each sub-service data area;
step 54, searching the encryption algorithm used in each area according to the encryption parameter table, calling the corresponding function to decrypt, and outputting compressed data;
step 55, constructing a decompression table to search the compression parameters of each sub-service data, and calling a corresponding function to acquire and decompress;
step 56, inquiring the decompression parameter table again, and calling a decompression function to gradually restore the original data;
and 57, searching the position information of each piece of sub-service data in the original data by using the registry, and re-assembling to generate the output data of the banking service.
In the above steps of the embodiment of the present invention, step 51 uses an encrypted transmission protocol, so as to ensure confidentiality and integrity of service data on the network; the step 52 terminal verification mechanism can prevent the data from being tampered in the transmission process, and ensures the reliability of the data; the data format customized in step 53 has flexibility, and can conveniently analyze and locate sub-service data; step 54 encrypts the parameter table so that a proper decryption algorithm can be selected for each sub-data, improving efficiency; step 55 builds a decompression parameter table, so that a proper decompression algorithm can be selected for each sub-service data, and efficiency is improved; step 56 decompresses and restores the original data step by step, which ensures the consistency from end to end; step 57 registry allows for simple sub-service data reassembly, guaranteeing semantic consistency of the data; the transmission verification mechanism ensures the safety and reliability of service data; the custom data format improves the flexibility of processing and analysis; the parameter table and the gradual decoding realize the effective recovery of the sub-service data; and finally, the end-to-end consistent input data conversion and analysis are realized.
In a preferred embodiment of the present invention, the step 6 of generating a hologram according to the banking output data and interacting with the user according to the hologram includes:
step 61, taking the output data of the banking service as the source information of the three-dimensional scene, and loading the source information into the holographic generating equipment;
step 62, generating hologram data according to the three-dimensional scene source information, and using laser to irradiate the hologram data to reconstruct the light wave advancing process of the three-dimensional scene;
and step 63, capturing the position of the user by using the sensing equipment, and rendering three-dimensional images under different visual angles in real time to interact with the user.
In the above steps in the embodiment of the present invention, step 61 takes the digitized data of banking as source information, which provides input support for holographic technology, and is the basis for realizing virtual interaction; step 62, calculating a holographic pattern and reconstructing a light wave propagation process according to an optical principle, so as to generate a three-dimensional holographic image of a bank teller; the holographic imaging technology restores the three-dimensional image of the bank teller with high fidelity, and realizes virtual simulation; step 63, capturing the position of a user in real time by using sensing equipment, and calculating three-dimensional images under different visual angles; according to the updated three-dimensional scene corresponding to the position change of the user, natural and smooth man-machine interaction is realized; the real-time rendering of the three-dimensional interaction scene greatly enhances the immersion and interaction experience of the user, and finally can realize virtual interaction of banking business, so that the user can enjoy service without going out.
As shown in fig. 2, an embodiment of the present invention further provides a banking data processing system based on remote service, including:
the acquiring module 10 is configured to acquire service terminal information, and scan a banking operator according to banking business to obtain banking service data of a service terminal corresponding to the banking business;
the decomposition module 20 is configured to decompose the banking service data into a plurality of sub-service data according to banking businesses, and calculate characterization factors of the banking businesses corresponding to the sub-service data respectively;
the calculating module 30 is configured to calculate a target input processing parameter of the banking service data according to the service terminal information, and calculate a sub-input processing parameter of each sub-service data under the target input processing parameter according to the characterization factor;
the processing module 40 is configured to process each piece of sub-service data according to the sub-input processing parameters, and aggregate the sub-service data to generate banking service input data;
the output module 50 is configured to output the banking service input data to a service terminal, and perform reduction processing on the banking service input data to obtain banking service output data;
the service module 60 is used for generating a hologram according to the output data of the banking service and interacting with the user according to the hologram.
It should be noted that, the system is a system corresponding to the above method, and all implementation manners in the above method embodiment are applicable to the embodiment, so that the same technical effects can be achieved.
Embodiments of the present invention also provide a computing device comprising: a processor, a memory storing a computer program which, when executed by the processor, performs the method as described above. All the implementation manners in the method embodiment are applicable to the embodiment, and the same technical effect can be achieved.
Embodiments of the present invention also provide a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform a method as described above. All the implementation manners in the method embodiment are applicable to the embodiment, and the same technical effect can be achieved.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk, etc.
Furthermore, it should be noted that in the apparatus and method of the present invention, it is apparent that the components or steps may be disassembled and/or assembled. Such decomposition and/or recombination should be considered as equivalent aspects of the present invention. Also, the steps of performing the series of processes described above may naturally be performed in chronological order in the order of description, but are not necessarily performed in chronological order, and some steps may be performed in parallel or independently of each other. It will be appreciated by those of ordinary skill in the art that all or any of the steps or components of the methods and apparatus of the present invention may be implemented in hardware, firmware, software, or a combination thereof in any computing device (including processors, storage media, etc.) or network of computing devices, as would be apparent to one of ordinary skill in the art after reading this description of the invention.
The object of the invention can thus also be achieved by running a program or a set of programs on any computing device. The computing device may be a well-known general purpose device. The object of the invention can thus also be achieved by merely providing a program product containing program code for implementing said method or apparatus. That is, such a program product also constitutes the present invention, and a storage medium storing such a program product also constitutes the present invention. It is apparent that the storage medium may be any known storage medium or any storage medium developed in the future. It should also be noted that in the apparatus and method of the present invention, it is apparent that the components or steps may be disassembled and/or assembled. Such decomposition and/or recombination should be considered as equivalent aspects of the present invention. The steps of executing the series of processes may naturally be executed in chronological order in the order described, but are not necessarily executed in chronological order. Some steps may be performed in parallel or independently of each other.
While the foregoing is directed to the preferred embodiments of the present invention, it will be appreciated by those skilled in the art that various modifications and adaptations can be made without departing from the principles of the present invention, and such modifications and adaptations are intended to be comprehended within the scope of the present invention.
Claims (10)
1. A method for processing bank data based on remote service, the method comprising:
acquiring service terminal information, and scanning a bank operator according to banking businesses to acquire banking service data of a corresponding service terminal of the banking businesses;
decomposing the banking service data into a plurality of sub-service data according to banking businesses, and calculating characterization factors of the banking businesses corresponding to the sub-service data respectively;
calculating target input processing parameters of the banking service data according to service terminal information, and calculating sub-input processing parameters of each sub-service data under the target input processing parameters according to the characterization factors;
processing each piece of sub-service data according to the sub-input processing parameters, and summarizing to generate banking service input data;
outputting the banking service input data to a service terminal, and restoring the banking service input data to obtain banking service output data;
and generating a holographic image according to the output data of the banking service, and interacting with the user according to the holographic image.
2. The remote service-based banking data processing method according to claim 1, wherein acquiring service terminal information and scanning a banking operator according to banking business to obtain banking service data of a banking business corresponding service terminal, includes:
Acquiring a service type and position coordinates of a service terminal, and scanning a bank operator corresponding to the service type to obtain three-dimensional model data of the bank operator;
verifying the three-dimensional model data to obtain a verification result;
setting a confidence threshold, calculating the confidence coefficient corresponding to the verification result, and storing the three-dimensional model data to generate banking service data if the confidence coefficient meets the confidence threshold; and if the confidence coefficient does not meet the confidence threshold value, scanning the bank operator again.
3. The remote service-based banking data processing method according to claim 2, wherein the scanning process is performed on a banking operator corresponding to a service type to obtain three-dimensional model data of the banking operator, comprising:
checking the data of each scanning point, and if error points or missing point data exist, updating the data of the scanning points to generate a scanning data set corresponding to a bank operator;
and merging and denoising the elements in the scanning data set to obtain three-dimensional model data.
4. A method for processing banking data based on remote service as claimed in claim 3, wherein verifying the data of each scanning point, if there is error point or missing point data, updating the data of the scanning point, generating a scanning data set corresponding to the banking operator, comprises:
Formatting the original three-dimensional scanning data to generate a data packet structure, wherein each data packet comprises a preset number of scanning data points;
calculating redundancy check codes for each data packet and adding the redundancy check codes into the data packets;
generating at least one data block according to the plurality of data packets, and calculating redundancy check codes corresponding to the data blocks, wherein the data blocks comprise a preset number of data packets;
setting a receiving verification end, and verifying the integrity according to the verification codes of the data packet and the data block, wherein if the data packet or the data block is incomplete, retransmission is requested;
generating a hash value of each scanning data point by using a hash algorithm, comparing the hash value with a preset correct hash value, and verifying whether the content of the scanning data point is correct;
correcting the scanned data points with verification errors by using an error correction coding algorithm until all the data points pass the verification;
a set of validated scan data points is generated.
5. The method for processing banking data based on remote service according to claim 4, wherein merging and denoising elements in the scan dataset to obtain three-dimensional model data, comprising:
Calculating the distance relation and the direction relation between each data point according to the three-dimensional coordinate values of the elements in the scanning data set;
generating a three-dimensional grid model according to the distance relation and the direction relation between the data points;
smoothing the three-dimensional grid model, and adjusting coordinates of grid nodes to eliminate high-frequency noise;
judging whether abnormal noise points exist or not according to the distribution condition of data values on each grid in the three-dimensional grid model, and correcting the abnormal noise points;
and filling the cavities in the three-dimensional grid model to obtain three-dimensional model data.
6. The remote service-based banking data processing method according to claim 5, wherein the banking data is decomposed into a plurality of sub-service data according to banking, and a characterization factor of each sub-service data corresponding to banking is calculated, respectively, including:
calculating geometric factors of each point data in the bank service data, and extracting a three-dimensional contour of a physical part of a corresponding bank operator according to the geometric factors;
according to the topological structure of the banking service data, determining point data in the banking service data corresponding to each three-dimensional outline to obtain a plurality of sub-service data;
And calculating service descriptors of all the sub-service data, and calculating characterization factors of all the sub-service data according to the service descriptors.
7. The method for processing banking data based on remote service according to claim 6, wherein each piece of sub-service data is processed according to the sub-input processing parameter and collectively generated into banking service input data, comprising:
reading each piece of sub-service data and the corresponding compression rate and encryption strength parameters thereof, and compressing and encrypting each piece of sub-service data;
defining a unified data format, wherein the data format comprises a fixed-length header information field and a variable-length data field;
assembling all sub-service data according to the data format to generate summarized data;
the summary data is serialized in binary format to generate banking input data.
8. A remote service-based banking data processing system, comprising:
the acquisition module (10) is used for acquiring service terminal information, scanning a bank operator according to banking businesses, and acquiring banking business data of a corresponding service terminal of the banking businesses;
the decomposition module (20) is used for decomposing the banking service data into a plurality of sub-service data according to banking businesses, and calculating characterization factors of the banking businesses corresponding to the sub-service data respectively;
The computing module (30) is used for computing target input processing parameters of the banking service data according to the service terminal information and computing sub-input processing parameters of each sub-service data under the target input processing parameters according to the characterization factors;
the processing module (40) is used for processing each piece of sub-service data according to the sub-input processing parameters and summarizing to generate banking service input data;
the output module (50) is used for outputting the banking service input data to a service terminal and carrying out reduction processing on the banking service input data to obtain banking service output data;
and the service module (60) is used for generating a holographic image according to the bank service output data and interacting with a user according to the holographic image.
9. A computing device, comprising: one or more processors; storage means for storing one or more programs which when executed by the one or more processors cause the one or more processors to implement the method of any of claims 1-7.
10. A computer readable storage medium, characterized in that the computer readable storage medium has stored therein a program which, when executed by a processor, implements the method according to any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311444880.7A CN117176775B (en) | 2023-11-02 | 2023-11-02 | Bank data processing method and system based on remote service |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311444880.7A CN117176775B (en) | 2023-11-02 | 2023-11-02 | Bank data processing method and system based on remote service |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117176775A true CN117176775A (en) | 2023-12-05 |
| CN117176775B CN117176775B (en) | 2023-12-29 |
Family
ID=88937894
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311444880.7A Active CN117176775B (en) | 2023-11-02 | 2023-11-02 | Bank data processing method and system based on remote service |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117176775B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110264527A1 (en) * | 2007-12-14 | 2011-10-27 | Dudley Fitzpatrick | Apparatuses, Methods and Systems for a Code-Mediated Content Delivery Platform |
| US9015065B2 (en) * | 2009-02-09 | 2015-04-21 | Huawei Device Co., Ltd. | Method, system, and device for implementing network banking service |
| US9098961B1 (en) * | 2011-04-26 | 2015-08-04 | Diebold Self-Service Systems Division Of Diebold, Incorporated | Automated banking machine that employs a virtual person for assisting customers |
| US20170308905A1 (en) * | 2014-03-28 | 2017-10-26 | Ratnakumar Navaratnam | Virtual Photorealistic Digital Actor System for Remote Service of Customers |
| CN111488433A (en) * | 2020-06-28 | 2020-08-04 | 南京银行股份有限公司 | Artificial intelligence interactive system suitable for bank and capable of improving field experience |
| CN112562433A (en) * | 2020-12-30 | 2021-03-26 | 华中师范大学 | 5G strong interaction remote delivery teaching system based on holographic terminal and working method thereof |
| CN113505199A (en) * | 2021-07-12 | 2021-10-15 | 北京顺天立安科技有限公司 | Business response information processing method and device based on bank number calling terminal and service end system |
| US20230099605A1 (en) * | 2021-09-28 | 2023-03-30 | Sony Group Corporation | Minimal volumetric 3d on demand for efficient 5g transmission |
| US20230205133A1 (en) * | 2020-04-21 | 2023-06-29 | Massachusetts Institute Of Technology | Real-time Photorealistic 3D Holography With Deep Neural Networks |
| CN116485960A (en) * | 2023-04-23 | 2023-07-25 | 中国建设银行股份有限公司 | Digital man driving method and device |
| CN116958420A (en) * | 2023-07-10 | 2023-10-27 | 华中师范大学 | A high-precision modeling method for the three-dimensional face of a digital human teacher |
-
2023
- 2023-11-02 CN CN202311444880.7A patent/CN117176775B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110264527A1 (en) * | 2007-12-14 | 2011-10-27 | Dudley Fitzpatrick | Apparatuses, Methods and Systems for a Code-Mediated Content Delivery Platform |
| US9015065B2 (en) * | 2009-02-09 | 2015-04-21 | Huawei Device Co., Ltd. | Method, system, and device for implementing network banking service |
| US9098961B1 (en) * | 2011-04-26 | 2015-08-04 | Diebold Self-Service Systems Division Of Diebold, Incorporated | Automated banking machine that employs a virtual person for assisting customers |
| US20170308905A1 (en) * | 2014-03-28 | 2017-10-26 | Ratnakumar Navaratnam | Virtual Photorealistic Digital Actor System for Remote Service of Customers |
| US20230205133A1 (en) * | 2020-04-21 | 2023-06-29 | Massachusetts Institute Of Technology | Real-time Photorealistic 3D Holography With Deep Neural Networks |
| CN111488433A (en) * | 2020-06-28 | 2020-08-04 | 南京银行股份有限公司 | Artificial intelligence interactive system suitable for bank and capable of improving field experience |
| CN112562433A (en) * | 2020-12-30 | 2021-03-26 | 华中师范大学 | 5G strong interaction remote delivery teaching system based on holographic terminal and working method thereof |
| CN113505199A (en) * | 2021-07-12 | 2021-10-15 | 北京顺天立安科技有限公司 | Business response information processing method and device based on bank number calling terminal and service end system |
| US20230099605A1 (en) * | 2021-09-28 | 2023-03-30 | Sony Group Corporation | Minimal volumetric 3d on demand for efficient 5g transmission |
| CN116485960A (en) * | 2023-04-23 | 2023-07-25 | 中国建设银行股份有限公司 | Digital man driving method and device |
| CN116958420A (en) * | 2023-07-10 | 2023-10-27 | 华中师范大学 | A high-precision modeling method for the three-dimensional face of a digital human teacher |
Non-Patent Citations (2)
| Title |
|---|
| 叶博宇;林懿楠;李瑾;赵天琪;: "兴业银行"智慧数字人――小兴"在实体网点成功探索应用", 中国金融电脑, no. 05 * |
| 裴亚民: "光大银行"数字人"建设实践", 中国金融电脑 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117176775B (en) | 2023-12-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10552730B2 (en) | Procedural modeling using autoencoder neural networks | |
| Olanrewaju et al. | Secure ear biometrics using circular kernel principal component analysis, Chebyshev transform hashing and Bose–Chaudhuri–Hocquenghem error-correcting codes | |
| Mirman et al. | Robustness certification with generative models | |
| CN106899567A (en) | User's core body method, apparatus and system | |
| JP2011521355A (en) | Fingerprint representation using gradient histogram | |
| CN115994849B (en) | Three-dimensional digital watermark embedding and extracting method based on point cloud up-sampling | |
| CN113191380A (en) | Image evidence obtaining method and system based on multi-view characteristics | |
| CN118690304A (en) | Anomaly detection method for high-dimensional time series data based on multimodal generative adversarial network | |
| Liu et al. | A hybrid with distributed pooling blockchain protocol for image storage | |
| CN117176775B (en) | Bank data processing method and system based on remote service | |
| CN118485841A (en) | Geometric shape feature extraction method for digital twin geometric model of manufacturing equipment | |
| CN112565254B (en) | Data transmission method, device, equipment and computer readable storage medium | |
| CN118247469A (en) | Three-dimensional model data merging method, device, computer equipment and storage medium | |
| CN118606920A (en) | Transaction processing method, device, storage medium and electronic device | |
| CN114693846B (en) | Face model generation method, device, storage medium and electronic device | |
| Zhang et al. | Earth Observation Data Provenance: A Blockchain-Based Solution | |
| Lin et al. | Cad-pu: A curvature-adaptive deep learning solution for point set upsampling | |
| Karathanasis et al. | A Comparative Analysis of Compression and Transfer Learning Techniques in DeepFake Detection Models. | |
| TWM592113U (en) | Anti-counterfeiting inspection equipment and anti-counterfeiting inspection machine thereof | |
| CN117273176A (en) | Federal learning modeling method based on stacking integrated learning algorithm | |
| Rosen et al. | G-invariant diffusion maps | |
| CN115801277A (en) | Multi-mode fusion identity authentication method and system for handheld operation and maintenance terminal considering multiple factors | |
| CN113572913B (en) | Image encryption method, device, medium and electronic equipment | |
| CN117292245B (en) | Quality assessment method and system for face images oriented to face semantic encoding and decoding | |
| CN116579956B (en) | Image restoration method based on gesture verification |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |