Voucher uploading method and device and computer equipment
Through the user-side electronic signature recognition and verification, automatic uploading and watermark generation method, the problem of single credential upload channels and low manual review efficiency in the existing technology is solved, and more efficient and accurate credential upload and privacy protection is achieved.
Patent Information
- Application Number
- CN202411416626.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-11
- Publication Date
- 2025-01-03
AI Technical Summary
In the prior art, the voucher upload channel is single and relies on manual review, resulting in low efficiency and accuracy of business processing or business investigation, and if vouchers are not received in a timely manner, it will affect the operation efficiency.
Electronic signature recognition and verification are carried out through the user side, and edge detection algorithm and contour extraction algorithm are used to identify stroke endpoints and intersections, calculate signature similarity, and generate declaration tables and watermarks, automatically verify and upload credentials, enrich upload channels, and improve timely and efficiency, reduce the burden of manual inspection and enhance privacy protection.
It improves the timeliness and efficiency of voucher uploads, reduces the error and workload of manual inspection, enhances privacy protection, and improves the accuracy and efficiency of electronic signature verification.
Smart Images

Figure CN119250535A_ABST
Abstract
Description
Technical Field
[0001] The embodiments of this specification relate to the field of automatic programming technology, and in particular to a credential uploading method, apparatus, and computer device. Background Art
[0002] Due to the need for business processing or business investigation, customers are often required to provide relevant vouchers, such as negotiated repayment, cashback not received, and agreed repayment account not deducted. However, the existing voucher upload channels are relatively single, and voucher interaction with customers can only be completed through email or fax, and then the vouchers uploaded by users are manually reviewed. At present, there are about 7,000 work orders per year for manual seats to fill out email receipt vouchers and send them to centralized operations for processing. After receiving the customer's voucher within five working days and confirming that the materials are clear, the centralized operation will attach the materials to the email receipt voucher form for settlement. Due to the manual method, there are problems with low audit efficiency and high error rate, which is not conducive to shortening the processing or investigation cycle of related businesses. In addition, if the customer's voucher is not received within five working days, the order must be returned to the agent, and the agent will contact the customer again, which greatly affects the work efficiency.
[0003] In view of this, the embodiments of this specification are intended to provide a credential uploading method, apparatus and computer device. Summary of the invention
[0004] In view of the above-mentioned problems in the prior art, the purpose of the embodiments of this specification is to provide a credential uploading method, device and computer equipment to solve the problem of low efficiency and accuracy in business processing or business investigation due to the use of credential uploading channels such as email or fax and manual review in the prior art.
[0005] In order to solve the above technical problems, the specific technical solutions of the embodiments of this specification are as follows:
[0006] In a first aspect, an embodiment of the present specification provides a method for uploading a credential, including:
[0007] In response to a risk event, display the declaration information to the user to obtain the user's electronic signature;
[0008] Identify each stroke of the electronic signature when it is written, and determine the endpoints of each stroke and the intersection between any two strokes;
[0009] Calculating a first similarity between the electronic signature and a pre-stored user signature based on the endpoint and the intersection point;
[0010] verifying the electronic signature according to the first similarity;
[0011] Generate a declaration form according to the declaration information and the verified electronic signature and send a notification of uploading risk credentials to the user terminal;
[0012] Receive risk credentials uploaded by the user and verify them;
[0013] adding watermarks to the risk certificate and the declaration form that have passed the verification respectively;
[0014] Associating the risk credential and the declaration form with the watermarked risk event and generating a reminder of successful upload of the risk credential;
[0015] A reminder of successful upload of the risk credential is sent to an investigator to conduct a manual investigation of the risk event.
[0016] Furthermore, identifying each stroke of the electronic signature when it is written, and determining the endpoints of each stroke and the intersection between any two strokes further includes:
[0017] Preprocessing the electronic signature;
[0018] Using an edge detection algorithm and a contour extraction algorithm, the contours of each stroke of the pre-processed electronic signature are identified;
[0019] Calculating the curvature of each pixel in the contour;
[0020] The pixel point in the contour whose curvature change meets a preset condition is determined as the endpoint or the intersection point.
[0021] Furthermore, the calculating, based on the endpoints and the intersection points, a first similarity between the electronic signature and a pre-stored user signature includes:
[0022] Determine the coordinates of the endpoint and the intersection point on a two-dimensional plane coordinate system;
[0023] Calculate the distance between any point in the set consisting of the endpoints and the intersection points and the remaining points in the set according to the coordinates;
[0024] constructing an electronic signature distance matrix based on the distances;
[0025] Construct a user signature distance matrix corresponding to the pre-stored user signatures;
[0026] The similarity between the electronic signature distance matrix and the user signature distance matrix is calculated to obtain the first similarity.
[0027] Preferably, before identifying each stroke when writing the electronic signature and determining the endpoints of each stroke and the intersection between any two strokes, the method further includes:
[0028] Using an optical character recognition method, recognizing characters in the electronic signature;
[0029] Determining whether the character is consistent with the user name corresponding to the risk event;
[0030] If they are consistent, each stroke in the electronic signature is identified.
[0031] Specifically, the method further includes:
[0032] Obtaining the process information of the electronic signature fed back by the user;
[0033] Determining the occurrence time of each endpoint and each intersection in the electronic signature according to the process information;
[0034] Determining the writing order of the strokes and the writing speed of the strokes according to the occurrence times;
[0035] Calculating a second similarity between the electronic signature and a pre-stored user signature according to the writing order and the writing speed;
[0036] Determining whether the second similarity is greater than or equal to a preset second similarity threshold;
[0037] If yes, it is determined that the electronic signature passes the verification;
[0038] If not, it is determined that the electronic signature has failed the verification.
[0039] Further, generating a declaration form according to the declaration information and the verified electronic signature includes:
[0040] Obtaining a declaration form template corresponding to the risk event, wherein the declaration form template includes a plurality of fields to be filled in;
[0041] According to the attributes of each field to be filled in, extract the relevant information of the risk event and the electronic signature and fill them into the corresponding fields to be filled in respectively;
[0042] Determine whether there are unfilled fields to be filled;
[0043] If not, display the input box to obtain relevant information input by the user until there are no unfilled fields to be filled in;
[0044] If so, the declaration table is generated.
[0045] Furthermore, watermarks are added to the risk certificate and the declaration form that have passed the verification, respectively, including:
[0046] Obtaining relevant information of the risk event, the relevant information at least including one or a combination of the columns of user name, date of birth, ID number, transaction number, transaction time and transaction location;
[0047] generating a watermark element based on at least part of the relevant information;
[0048] The risk certificate and the declaration form that have passed verification are watermarked according to the watermark element.
[0049] Furthermore, the risk credentials uploaded by the user are verified, including:
[0050] Determine whether the number of risk credentials uploaded by the user is consistent with the number of risk credential upload entries;
[0051] If they are consistent, identifying the text characters of the risk certificate uploaded through each of the upload entrances;
[0052] According to the text characters, determining whether the risk certificate is consistent with the corresponding upload entry;
[0053] If they are consistent, it is determined that the risk certificate has passed the verification;
[0054] Otherwise, it is determined that the risk certificate has failed the verification.
[0055] Further, receiving the risk certificate uploaded by the user is:
[0056] Determining whether the risk credential is less than or equal to a preset size threshold;
[0057] If not, the risk credential is compressed.
[0058] Specifically, the method further includes:
[0059] In response to a transaction event, sending a transaction voucher upload notification to the user terminal;
[0060] Receive transaction vouchers fed back by the user and verify them;
[0061] Associating the verified transaction voucher with the transaction event;
[0062] Generate a successful transaction voucher upload reminder and send it to the investigator to manually investigate the transaction event.
[0063] Preferably, the method further comprises:
[0064] Determining whether the transaction voucher is smaller than or equal to a preset transaction voucher size threshold;
[0065] If not, the transaction voucher is compressed.
[0066] In a second aspect, an embodiment of the present specification provides a credential uploading device, including:
[0067] An acquisition module, used to respond to a risk event and display the declaration information to the user to obtain the user's electronic signature;
[0068] An acquisition module, used to respond to a risk event and display the declaration information to the user to obtain the user's electronic signature;
[0069] A recognition module, used to recognize each stroke when the electronic signature is written, and determine the endpoints of each stroke and the intersection between any two strokes;
[0070] A first calculation module, configured to calculate a first similarity between the electronic signature and a pre-stored user signature based on the endpoints and the intersection;
[0071] A first verification module, configured to verify the electronic signature according to the first similarity;
[0072] A generating module, used to generate a declaration form according to the declaration information and the verified electronic signature and send a notification of uploading risk credentials to the user terminal;
[0073] The second verification module is used to receive and verify the risk certificate uploaded by the user;
[0074] A watermark adding module, used to add watermarks to the risk certificate and the declaration form that have passed the verification;
[0075] A first association module, used to associate the risk credential and the declaration form with the risk event after adding the watermark and generate a reminder of successful upload of the risk credential;
[0076] The first reminder module is used to send a reminder of successful upload of the risk credential to an investigator so as to conduct a manual investigation on the risk event.
[0077] Furthermore, the device also includes:
[0078] A notification module, used for sending a transaction voucher upload notification to the user terminal in response to a transaction event;
[0079] The third verification module is used to receive and verify the transaction voucher fed back by the user end;
[0080] A second associating module, configured to associate the verified transaction voucher with the transaction event;
[0081] The second reminder module is used to generate a reminder of successful upload of the transaction voucher and send it to the investigator to manually investigate the transaction event.
[0082] In a third aspect, an embodiment of the present specification provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method provided by the above technical solution when executing the computer program.
[0083] In a fourth aspect, an embodiment of the present specification provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method provided by the above technical solution is implemented.
[0084] In a fifth aspect, an embodiment of the present specification provides a computer program product, comprising at least one instruction or at least one program, wherein the at least one instruction or the at least one program is loaded and executed by a processor to implement the method provided by the above technical solution.
[0085] By adopting the above-mentioned technical scheme, a credential uploading method, device and computer equipment provided in the embodiments of this specification upload credentials through the user terminal on the user side, enriching the credential uploading channels and being beneficial to improving the timeliness and efficiency of credential uploading; and automatically verifying the electronic signature submitted by the user and the uploaded risk credentials, thereby improving the verification efficiency, being beneficial to reducing the workload of manual inspection and reducing the error of manual inspection; and being able to add watermarks to the risk credentials and declaration forms uploaded by the user to avoid the risk credentials and declaration forms being used for other purposes, thereby improving the privacy protection.
[0086] In order to make the above and other purposes, features and advantages of the embodiments of this specification more obvious and easy to understand, the following specifically cites preferred embodiments and describes them in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS
[0087] In order to more clearly illustrate the embodiments of this specification or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0088] Figure 1 A schematic diagram showing the steps of a method for uploading a credential provided in an embodiment of this specification is shown;
[0089] Figure 2 A schematic diagram showing the steps of determining the endpoints of each stroke and the intersection between any two strokes in the embodiment of this specification;
[0090] Figure 3A schematic diagram showing the steps of calculating the first similarity between the electronic signature and the pre-stored user signature according to the endpoints and the intersection point in an embodiment of this specification;
[0091] Figure 4 A schematic diagram showing another step of verifying an electronic signature in an embodiment of this specification;
[0092] Figure 5 A schematic diagram of the steps of generating a declaration form according to the declaration information and the verified electronic signature in the embodiment of this specification is shown;
[0093] Figure 6 A schematic diagram of the steps of adding watermarks to the risk certificate and the declaration form that have passed the verification in the embodiment of this specification is shown;
[0094] Figure 7 A schematic diagram showing the steps of verifying the risk credentials uploaded by the user end in the embodiment of this specification is shown;
[0095] Figure 8 A schematic diagram showing another step of a method for uploading a credential provided in an embodiment of this specification is shown;
[0096] Fig. 9 A schematic diagram of the structure of a credential uploading device provided in an embodiment of this specification is shown;
[0097] Fig.10 A schematic diagram of the structure of a computer device provided in an embodiment of this specification is shown.
[0098] Description of the accompanying symbols:
[0099] 91. Get module;
[0100] 92. Identification module;
[0101] 93. A first computing module;
[0102] 94. A first verification module;
[0103] 95. Generate module;
[0104] 96. A second verification module;
[0105] 97. Watermark adding module;
[0106] 98. First association module;
[0107] 99. The first reminder module;
[0108] 1002. Computer equipment;
[0109] 1004. Processor;
[0110] 1006. Memory;
[0111] 1008. Driving mechanism;
[0112] 1010, input / output module;
[0113] 1012. Input device;
[0114] 1014. Output device;
[0115] 1016. Presentation equipment;
[0116] 1018. Graphical user interface;
[0117] 1020. Network interface;
[0118] 1022. Communication link;
[0119] 1024. Communication bus. DETAILED DESCRIPTION
[0120] The following will be combined with the drawings in the embodiments of this specification to clearly and completely describe the technical solutions in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this specification.
[0121] It should be noted that the terms "first", "second", etc. in this specification and claims and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of this specification described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, device, product or equipment that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or equipment.
[0122] In order to solve the above problems, the embodiments of this specification provide a credential uploading method, device and computer equipment, which can solve the problem of low efficiency and accuracy in business processing or business investigation due to the use of email or fax credential uploading channels and manual review methods in the prior art. Figure 1This is a schematic diagram of the steps of a credential upload method provided in an embodiment of this specification. This specification provides method operation steps as described in the embodiment or flowchart, but may include more or fewer operation steps based on conventional or non-creative labor. The order of steps listed in the embodiment is only one way of executing the order of many steps and does not represent the only execution order. When the actual system or device product is executed, it can be executed in the order of the method shown in the embodiment or the accompanying drawings or in parallel.
[0123] It should be noted that the credential uploading method and device provided in the embodiments of this specification can be used in the financial field, and can also be used in any field other than the financial field. The embodiments of this specification do not limit the application field of the credential uploading method and device. The acquisition, storage, use, and processing of information such as user electronic signatures in the technical scheme of the embodiments of this specification comply with the relevant provisions of national laws and regulations. In addition, in the embodiments of this specification, some existing solutions in the industry such as certain software, components, and models may be mentioned, and they should be considered as exemplary. Their purpose is only to illustrate the feasibility of the implementation of the technical solution of this application, but it does not mean that the applicant has or will necessarily use the solution.
[0124] Specific as Figure 1 As shown, the method may include:
[0125] S110: In response to the risk event, display the declaration information to the user to obtain the user's electronic signature.
[0126] In the embodiments of this specification, the risk event may be obtained based on the risk assessment results of the pre-connected risk warning system, for example, the risk warning system assesses that a certain credit card transaction of a certain user has the risk of reverse brushing, etc. Then, based on this assessment result, the risk event is checked. Among them, the declaration information includes a description of the risk event, for example, including the user's name, birth date, number of the risk transaction, time and place of the risk transaction, etc.
[0127] S120: Identify each stroke of the electronic signature when it is written, and determine the endpoints of each stroke and the intersection between any two strokes.
[0128] S130: Calculate a first similarity between the electronic signature and a pre-stored user signature based on the endpoints and the intersection.
[0129] S140: Verify the electronic signature according to the first similarity.
[0130] That is, it is determined whether the first similarity is greater than or equal to a preset first similarity threshold; if so, it is determined that the electronic signature has passed the verification; otherwise, it is determined that the electronic signature has failed the verification.
[0131] It should be noted that there may be one or more pre-stored user signatures. When there are multiple pre-stored user signatures, the first similarity between the current electronic signature and each user signature may be calculated respectively, and then the multiple first similarities may be combined to improve the accuracy of the judgment of whether the current electronic signature is signed by the user himself.
[0132] S150: Generate a declaration form according to the declaration information and the verified electronic signature and send a risk credential upload notification to the user end.
[0133] S160: Receive the risk certificate uploaded by the user and verify it.
[0134] Risk credentials may include certificate materials, report receipts and other supporting materials. The certificate materials are photos of the user's ID card; the report receipt may be the receipt received by the user after reporting a transaction, for example, the user realizes that a transaction is not completed by him / her and there is a risk, and reports the case, and the report receipt is obtained after the report; the other supporting materials are materials other than certificate materials and report receipts; other supporting materials may be present or absent according to the actual application situation.
[0135] In the embodiment of this specification, the verification of the risk certificate may include integrity verification and consistency verification. Figure 7 and the related description below.
[0136] S170: Adding watermarks to the risk certificate and the declaration form that have passed verification respectively.
[0137] By adding watermarks, the certificate materials, report receipts, other proof documents and declaration forms uploaded by users can only be used to verify the risk event, preventing the materials from being used for other purposes, thereby achieving privacy protection for the materials uploaded by users.
[0138] S180: Associating the watermarked risk credential and the declaration form with the risk event and generating a risk credential upload success reminder.
[0139] For example, the risk certificate and the declaration form may be uploaded as attachments to the attachment column of the risk event.
[0140] S190: Sending a reminder of successful upload of the risk credential to an investigator so as to conduct a manual investigation on the risk event.
[0141] That is, for risk events, in the embodiments of this specification, not only are credentials uploaded and verified by computer methods, but they are also verified by manual investigation methods. The double verification ensures the accuracy of the uploaded credentials, which is beneficial to the verification and handling of risk events.
[0142] Furthermore, the credential uploading method provided in the embodiment of this specification also includes:
[0143] When the certificate materials, report receipt and other proof documents fail to pass the verification, a prompt to re-upload is sent to the user end; and
[0144] When the electronic signature fails verification, a re-signing prompt is sent to the user.
[0145] The embodiment of this specification provides a method for uploading credentials, which can upload credentials through the user end of the user side, enrich the credential upload channel, and is conducive to improving the timeliness and efficiency of credential upload; and automatically verify the electronic signature submitted by the user and the uploaded risk credentials, which improves the verification efficiency, helps to reduce the workload of manual verification, and reduces the error of manual verification; it can also add watermarks to the risk credentials and declaration forms uploaded by the user to avoid risk credentials and declaration forms being used for other purposes, and improve privacy protection. And it can judge whether the electronic signature is signed by the user himself through the layout information of the endpoints and intersections of the strokes, which is conducive to improving the accuracy and efficiency of electronic signature verification; and compared with the algorithm using spatial feature extraction, it is conducive to reducing the complexity of the algorithm and easy to implement.
[0146] Furthermore, if Figure 2 As shown, step S120: identifying each stroke when writing the electronic signature, determining the endpoints of each stroke and the intersection between any two strokes, may include the following steps:
[0147] S210: Preprocess the electronic signature.
[0148] The pre-processing may include gray-scaling, binarization or a combination of gray-scaling and binarization.
[0149] After grayscale and binarization processing, the strokes of the characters in the electronic signature will be black, while the background will be white, which will help to more accurately define the boundaries of the strokes.
[0150] S220: Using an edge detection algorithm and a contour extraction algorithm, the contours of each stroke of the pre-processed electronic signature are identified.
[0151] The edge detection algorithm can analyze the changes in the intensity of each pixel in the electronic signature, thereby identifying which pixels are located on the boundary of the stroke; the contour extraction algorithm can connect the pixel points located at the boundary to form a complete stroke path, that is, the contour of the stroke.
[0152] S230: Calculate the curvature of each pixel point in the contour.
[0153] S240: Determine the pixel point in the contour whose curvature change meets a preset condition as the endpoint or the intersection.
[0154] In this way, the endpoints of each stroke in the electronic signature and the intersections between any two strokes can be simply and quickly identified, so that the layout information of the strokes contained in the electronic signature can be analyzed based on the endpoints and the intersections, and then the electronic signature can be verified.
[0155] Furthermore, if Figure 3 As shown, in some feasible embodiments, step S130: calculating the first similarity between the electronic signature and the pre-stored user signature according to the endpoint and the intersection point may include:
[0156] S310: Determine the coordinates of the endpoint and the intersection point in a two-dimensional plane coordinate system.
[0157] S320: Calculate the distance between any point in the set consisting of the endpoints and the intersection points and the remaining points in the set according to the coordinates.
[0158] S330: Constructing an electronic signature distance matrix according to the distance.
[0159] Specifically, the coordinates of each point in the set may be sorted in the order of the horizontal coordinate from small to large and the vertical coordinate from small to large, and then a matrix may be established based on the sorting and the distance.
[0160] For example, the points in the sorted set are P1, P2, ..., P n , then the resulting matrix (n×n dimensions) is as follows:
[0161]
[0162]
[0163] And there are:
[0164]
[0165] Among them, L ij is the distance between the i-th point and the j-th point in the set. i and i are the horizontal and vertical coordinates of the i-th point respectively; x j and j are the horizontal and vertical coordinates of the jth point respectively.
[0166] S340: Construct a user signature distance matrix corresponding to the pre-stored user signature.
[0167] The method for constructing the user signature distance matrix is the same or similar to the method for constructing the electronic signature distance matrix corresponding to the above-mentioned electronic signature, and will not be repeated here.
[0168] S350: Calculate the similarity between the electronic signature distance matrix and the user signature distance matrix to obtain the first similarity.
[0169] Since the number of each endpoint and each intersection in the electronic signature is large, the dimension of the constructed electronic signature distance matrix is often high, which is not conducive to the subsequent similarity calculation. In addition, there may be inconsistencies between the total number of each endpoint and each intersection in the electronic signature and the total number of each endpoint and each intersection in the pre-stored user signature, which makes the dimensions of the electronic signature distance matrix and the user signature distance matrix constructed separately inconsistent, which will also be not conducive to the similarity calculation between the two matrices. Therefore, before step S350, the electronic signature distance matrix and the user signature distance matrix can also be decomposed and / or dimensionally reduced. Then, the similarity between the two matrices after decomposition and / or dimension reduction is used as the first similarity between the electronic signature and the pre-stored user signature.
[0170] In the embodiments of the present specification, the user's writing habits of broken and connected strokes during the signing of the electronic signature can be analyzed based on the endpoints and intersections in the electronic signature uploaded by the user, and then used to verify whether the electronic signature is signed by the user himself, which is beneficial to improving the accuracy of electronic signature verification.
[0171] In another feasible embodiment, step S240: calculating the first similarity between the electronic signature and the pre-stored user signature according to the endpoint and the intersection point may also be:
[0172] The coordinates of the endpoints and the intersection of the electronic signature and the endpoints and the intersection of the pre-stored user signature are respectively input into a pre-trained signature verification model, thereby outputting a first similarity between the electronic signature and the pre-stored user signature.
[0173] The signature verification model may be an RNN model.
[0174] In some preferred embodiments, before step S120: identifying each stroke of the electronic signature and determining the endpoints of each stroke and the intersection between any two strokes, the method may further include:
[0175] The characters in the electronic signature are recognized using an optical character recognition method.
[0176] That is, the content of the electronic signature is recognized using the OCR (Optical Character Recognition) method. Further, in the embodiments of this specification, the electronic signature can be Chinese characters or English characters or characters in other languages.
[0177] Determine whether the character is consistent with the user name corresponding to the risk event.
[0178] For example, if the electronic signature of the user is "Zhang San", then it is verified whether the characters of the electronic signature are consistent with the user's name.
[0179] If they are consistent, the endpoints of each stroke and the intersections between the strokes in the electronic signature are identified.
[0180] The method provided in the embodiment of this specification first verifies whether the characters corresponding to the electronic signature are consistent with the user's name. When the characters are inconsistent with the user's signature, there is no need to perform the first similarity calculation, thereby simplifying the algorithm and reducing the complexity of the algorithm.
[0181] like Figure 4 As shown, in some preferred embodiments, at S140: after verifying the electronic signature according to the first similarity, the method may further include:
[0182] S410: Acquire the process information of the electronic signature fed back by the user.
[0183] The process information refers to the process of the user signing the electronic signature on the user terminal, including the position coordinates of the pixel points corresponding to the electronic signature at each sampling time point when sampling at smaller time intervals from the moment the user starts signing to the moment the signature is completed and the user clicks confirmation in the signature area displayed on the user terminal.
[0184] S420: Determine the occurrence time of each endpoint and each intersection in the electronic signature according to the process information.
[0185] That is, the coordinates of each endpoint and each intersection are compared with the position coordinates of the pixel points corresponding to each sampling time point to determine the occurrence time of each endpoint and each intersection.
[0186] S430: Determine the writing order of the strokes and the writing speed of the strokes according to the occurrence times.
[0187] Specifically, the writing order of each point in the set composed of each endpoint and each intersection is determined according to the order of occurrence time; and then the writing order of each stroke is determined according to the correspondence between each stroke and each endpoint and each intersection. And according to the occurrence time of the endpoint and intersection corresponding to each stroke, the writing speed of the stroke is calculated.
[0188] S440: Calculating a second similarity between the electronic signature and a pre-stored user signature according to the writing order and the writing speed.
[0189] Specifically, the writing speeds of the strokes are sorted according to the writing order of the strokes to obtain an electronic signature vector. The writing order and writing speed of the strokes of the pre-stored user signature are obtained to obtain the user signature vector. The similarity between the electronic signature vector and the user signature vector is calculated, which is the second similarity between the electronic signature and the pre-stored user signature.
[0190] S450: Determine whether the second similarity is greater than or equal to a preset second similarity threshold.
[0191] S460: If yes, determine that the electronic signature passes the verification.
[0192] S470: If not, it is determined that the electronic signature has not passed the verification.
[0193] That is, the certificate uploading method provided in the embodiment of this specification can not only verify whether the electronic signature is signed by the user himself according to the final result of the electronic signature uploaded by the user, but also can further improve the accuracy of the electronic signature verification according to the user's writing habits such as stroke order and stroke speed in combination with the process of the user signing the electronic signature.
[0194] Furthermore, if Figure 5 As shown, in the embodiment of this specification, step S130: generating a declaration form according to the declaration information and the verified electronic signature may include:
[0195] S510: Obtain a declaration form template corresponding to the risk event, wherein the declaration form template includes a plurality of fields to be filled in.
[0196] In an embodiment of the present specification, the attributes of each field to be filled in the declaration form template are different, for example, including at least a combination of one or more of the name field, birth date field, ID number field, transaction number field, transaction time field and transaction location field.
[0197] S520: According to the attributes of each field to be filled in, extract the relevant information of the risk event and the electronic signature and fill them into the corresponding fields to be filled in respectively.
[0198] For example, extract the relevant information of the risk event to obtain the user's name as "Zhang San", and the date of birth as a certain year, month, and day, etc., then fill the name "Zhang San" into the corresponding column of the attribute of name, fill the certain year, month, and day into the column corresponding to the attribute of date of birth, etc. And import the electronic signature input by the user end into the corresponding signature area in the declaration template.
[0199] S530: Determine whether there is an unfilled field to be filled.
[0200] S540: If yes, display the input box to obtain relevant information input by the user until there are no unfilled fields to be filled in;
[0201] S550: If not, generate the declaration table.
[0202] In the embodiments of this specification, the declaration form adopts a universal declaration template, which is conducive to the reuse of the verification process of risk events, thereby simplifying the process; and by automatically extracting relevant information of risk events and filling it into the corresponding fields of the declaration template, it can reduce the amount of information input by the user-end user, which is conducive to improving the credential upload experience of the user-end user. In the embodiments of this specification, the user's electronic signature, user name, ID number and other information are all information that has been authorized and agreed by the user in the past. The acquisition, storage, use, and processing of the above information in the technical solution described in the embodiments of this specification are in compliance with the relevant provisions of national laws and regulations.
[0203] In some feasible embodiments, step S150: adding watermarks to the risk certificate and the declaration form that have passed the verification respectively may be:
[0204] A universal watermark is added to the risk certificate and the declaration form that have passed verification. For example, the name of the branch to which the risk event belongs is used as a watermark element, and the watermark element is then added to the risk certificate and the declaration form.
[0205] like Figure 6 As shown, in some other feasible embodiments, step S150: adding watermarks to the risk certificate and the declaration form that have passed the verification respectively, may further include:
[0206] S610: Obtain relevant information of the risk event, wherein the relevant information includes at least one or a combination of the columns of user name, date of birth, ID number, transaction number, transaction time and transaction location.
[0207] S620: Generate a watermark element according to at least part of the relevant information.
[0208] It should be noted that in the embodiments of this specification, at least part of the relevant information may be one or more of the relevant information, or part of a certain information or parts of each of the several information. For example, a watermark element may be obtained by combining a few digits in a transaction number and a few digits in a user ID number.
[0209] S630: Perform watermark processing on the risk certificate and the declaration form that have passed the verification according to the watermark element.
[0210] In the embodiments of this specification, the method of adding watermark elements to the risk certificate and the declaration form can adopt the existing watermark adding method, which is not specifically limited here. In the embodiments of this specification, the generated watermark element can uniquely identify a risk event, which is conducive to preventing the material from being used for other purposes and realizing the privacy protection of user information.
[0211] Furthermore, if Figure 7 As shown, in the embodiment of this specification, in step S140, verifying the risk certificate uploaded by the user terminal may include:
[0212] S710: Determine whether the number of risk credentials uploaded by the user is consistent with the number of risk credential upload entries.
[0213] That is, to verify the integrity of the materials of the risk certificate.
[0214] S720: If they are consistent, identify the text characters of the risk certificate uploaded through each of the upload entrances.
[0215] S730: Determine whether the risk certificate is consistent with the corresponding upload entry based on the text characters.
[0216] That is, the consistency of the risk certificate is verified. For example, an optical character recognition method can be used to recognize the text characters of the certificate materials, report receipts and other certification materials uploaded by the user.
[0217] S740: If they are consistent, it is determined that the risk certificate has passed the verification.
[0218] In some preferred embodiments, only the first line or the first few lines of characters in the risk certificate can be identified to simplify the algorithm. If the text characters corresponding to the certificate material are names, resident ID cards, etc., the text characters corresponding to the report receipt are certain receipts, and the text characters corresponding to other certification materials are certain certificates, etc., then it is determined that the risk certificate has passed the verification.
[0219] S750: Otherwise, it is determined that the risk certificate has failed the verification.
[0220] In the embodiments of the present specification, the integrity and consistency of risk credentials uploaded by users can be automatically checked, which can reduce the workload of subsequent manual verification and review.
[0221] Furthermore, in step S140, receiving the risk credential uploaded by the user terminal further includes:
[0222] Determining whether the risk credential is less than or equal to a preset size threshold;
[0223] If not, the risk credential is compressed.
[0224] Specifically, size thresholds can be set for certificate materials, report receipts and other supporting materials respectively, and then a judgment can be made as to whether the certificate materials, report receipts and other supporting materials are less than or equal to their respective size thresholds; when any one of the certificate materials, report receipts and other supporting materials is not less than or equal to its corresponding size threshold, the risk credential will be compressed.
[0225] In some specific embodiments, the user terminal may also determine the size and compress the credential material uploaded by the user.
[0226] like Figure 8 As shown, the method provided in the embodiment of this specification also includes:
[0227] S810: In response to the transaction event, sending a transaction voucher upload notification to the user terminal.
[0228] When processing transactions such as negotiated repayment, cashback not received, and agreed repayment account not deducted, users are required to upload the corresponding transaction voucher. Here, a transaction voucher upload notification is sent to the user end.
[0229] It should be noted that in the embodiments of this specification, transaction events and risk events do not interfere with each other. A transaction voucher upload notification or a risk voucher upload notification is sent to the user according to actual application needs, and the transaction voucher upload interface and the risk voucher upload interface are displayed to the user respectively.
[0230] S820: Receive the transaction voucher fed back by the user and verify it.
[0231] The verification of the transaction voucher is specifically a consistency check, which can be performed by identifying whether the characters of the transaction voucher uploaded through the transaction voucher upload entry are consistent with the attributes of the corresponding transaction voucher entry.
[0232] S830: Associating the verified transaction voucher with the transaction event.
[0233] Upload the transaction voucher as an attachment to the attachment column of the transaction event.
[0234] S840: Generate a successful transaction voucher upload reminder and send it to the investigator to manually investigate the transaction event.
[0235] A voucher uploading method provided in the embodiment of this specification can upload transaction vouchers through the user terminal on the user side, enriching the transaction voucher uploading channels, and is conducive to improving the timeliness and efficiency of transaction voucher uploading, which is conducive to the handling of user business.
[0236] Similar to the uploading of risk credentials, the method further includes:
[0237] Determining whether the transaction voucher is smaller than or equal to a preset transaction voucher size threshold;
[0238] If not, the transaction voucher is compressed.
[0239] Based on the above-mentioned method for uploading a credential, an embodiment of this specification also provides a corresponding credential uploading device. The device may include a system (including a distributed system), software (application), module, component, server, client, etc. using the method described in the embodiment of this specification and a device combined with necessary implementation hardware. Based on the same innovative concept, the device in one or more embodiments provided in the embodiment of this specification is as described in the following embodiments. Since the implementation scheme and method for solving the problem of the device are similar, the implementation of the specific device in the embodiment of this specification can refer to the implementation of the aforementioned method, and the repetitions will not be repeated. As used below, the term "unit" or "module" can implement a combination of software and / or hardware for predetermined functions. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived.
[0240] like Fig. 9 As shown in FIG. 1 , it is a schematic diagram of the structure of a credential uploading device provided in an embodiment of this specification, such as Fig. 9 As shown, the device comprises:
[0241] An acquisition module 91 is used to display the declaration information to the user terminal in response to the risk event to obtain the user's electronic signature;
[0242] The recognition module 92 is used to recognize each stroke when the electronic signature is written, and determine the endpoints of each stroke and the intersection between any two strokes;
[0243] A first calculation module 93, configured to calculate a first similarity between the electronic signature and a pre-stored user signature according to the endpoints and the intersection;
[0244] A first verification module 94, configured to verify the electronic signature according to the first similarity;
[0245] A generating module 95, configured to generate a declaration form according to the declaration information and the verified electronic signature and send a notification of uploading risk credentials to the user terminal;
[0246] The second verification module 96 is used to receive and verify the risk certificate uploaded by the user;
[0247] A watermark adding module 97, used to add watermarks to the risk certificate and the declaration form that have passed the verification;
[0248] A first associating module 98, configured to associate the risk credential and the declaration form with the risk event after adding the watermark and generate a reminder of successful upload of the risk credential;
[0249] The first reminder module 99 is used to send a reminder of successful upload of the risk credential to the investigator so as to conduct a manual investigation on the risk event.
[0250] Furthermore, the credential uploading device provided in the embodiment of this specification also includes:
[0251] A notification module, used for sending a transaction voucher upload notification to the user terminal in response to a transaction event;
[0252] The third verification module is used to receive and verify the transaction voucher fed back by the user end;
[0253] A second associating module, configured to associate the verified transaction voucher with the transaction event;
[0254] The second reminder module is used to generate a reminder of successful upload of the transaction voucher and send it to the investigator to manually investigate the transaction event.
[0255] The beneficial effects obtained by the device provided in the embodiments of this specification are consistent with the beneficial effects obtained by the above method and will not be repeated here.
[0256] like Fig.10As shown, a computer device provided in an embodiment of this specification is provided. The credential uploading device in this specification can be a computer device in this embodiment, and the above method of this specification is executed. The computer device 1002 may include one or more processors 1004, such as one or more central processing units (CPUs), and each processing unit may implement one or more hardware threads. The computer device 1002 may also include any memory 1006, which is used to store any kind of information such as code, settings, data, etc. Non-limiting, for example, the memory 1006 may include any one or more combinations of the following: any type of RAM, any type of ROM, flash memory device, hard disk, optical disk, etc. More generally, any memory can use any technology to store information. Further, any memory can provide volatile or non-volatile retention of information. Further, any memory can represent a fixed or removable component of the computer device 1002. In one case, when the processor 1004 executes an associated instruction stored in any memory or a combination of memories, the computer device 1002 can perform any operation of the associated instruction. The computer device 1002 also includes one or more drive mechanisms 1008 for interacting with any storage, such as a hard disk drive mechanism, an optical disk drive mechanism, etc.
[0257] The computer device 1002 may also include an input / output module 1010 (I / O) for receiving various inputs (via input devices 1012) and for providing various outputs (via output devices 1014). A specific output mechanism may include a presentation device 1016 and an associated graphical user interface (GUI) 1018. In other embodiments, the input / output module 1010 (I / O), the input device 1012, and the output device 1014 may not be included, and the computer device 1002 may be used as a computer device in a network. The computer device 1002 may also include one or more network interfaces 1020 for exchanging data with other devices via one or more communication links 1022. One or more communication buses 1024 couple the components described above together.
[0258] The communication link 1022 may be implemented in any manner, for example, through a local area network, a wide area network (e.g., the Internet), a point-to-point connection, etc., or any combination thereof. The communication link 1022 may include any combination of hardwired links, wireless links, routers, gateway functions, name servers, etc. governed by any protocol or combination of protocols.
[0259] Corresponding to Figures 1 to 8 In addition to the method shown, an embodiment of the specification also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above method are executed.
[0260] The embodiment of the present specification also provides a computer-readable instruction, wherein when the processor executes the instruction, the program therein causes the processor to execute the following Figures 1 to 8 The method shown.
[0261] The embodiments of the present specification also provide a computer program product, including at least one instruction or at least one program, wherein the at least one instruction or the at least one program is loaded and executed by a processor to implement the following Figures 1 to 8 The method shown.
[0262] It should be understood that in the various embodiments of this specification, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this specification.
[0263] It should also be understood that in the embodiments of this specification, the term "and / or" is only a description of the association relationship of the associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this specification generally indicates that the associated objects before and after are in an "or" relationship.
[0264] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in this specification can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this specification.
[0265] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.
[0266] In the several embodiments provided in this specification, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, or it can be an electrical, mechanical or other form of connection.
[0267] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of this specification.
[0268] In addition, each functional unit in each embodiment of this specification may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0269] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this specification is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of this specification. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.
[0270] Specific embodiments are used in this specification to illustrate the principles and implementation methods of this specification. The description of the above embodiments is only used to help understand the methods and core ideas of this specification. At the same time, for those skilled in the art, according to the ideas of this specification, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on this specification.
Claims
1. A method for uploading a certificate, characterized in that: include: In response to a risk event, display the declaration information to the user to obtain the user's electronic signature; Identify each stroke of the electronic signature when it is written, and determine the endpoints of each stroke and the intersection between any two strokes; Calculating a first similarity between the electronic signature and a pre-stored user signature based on the endpoint and the intersection point; verifying the electronic signature according to the first similarity; Generate a declaration form according to the declaration information and the verified electronic signature and send a notification of uploading risk credentials to the user terminal; Receive risk credentials uploaded by the user and verify them; adding watermarks to the risk certificate and the declaration form that have passed the verification respectively; Associating the risk credential and the declaration form with the watermarked risk event and generating a reminder of successful upload of the risk credential; A reminder of successful upload of the risk credential is sent to an investigator to conduct a manual investigation of the risk event.
2. The method according to claim 1, characterized in that Recognizing each stroke of the electronic signature when it is written, and determining the endpoints of each stroke and the intersection between any two strokes, further includes: Preprocessing the electronic signature; Using an edge detection algorithm and a contour extraction algorithm, the contours of each stroke of the pre-processed electronic signature are identified; Calculating the curvature of each pixel in the contour; The pixel point in the contour whose curvature change meets a preset condition is determined as the endpoint or the intersection point.
3. The method according to claim 2, characterized in that The calculating, based on the endpoints and the intersection, a first similarity between the electronic signature and a pre-stored user signature further comprises: Determine the coordinates of the endpoint and the intersection point on a two-dimensional plane coordinate system; Calculate the distance between any point in the set consisting of the endpoints and the intersection points and the remaining points in the set according to the coordinates; constructing an electronic signature distance matrix based on the distances; Constructing a user signature distance matrix corresponding to the pre-stored user signature; The similarity between the electronic signature distance matrix and the user signature distance matrix is calculated to obtain the first similarity.
4. The method according to claim 1, characterized in that Before identifying each stroke of the electronic signature and determining the endpoints of each stroke and the intersection between any two strokes, the method further includes: Using an optical character recognition method, recognizing characters in the electronic signature; Determining whether the character is consistent with the user name corresponding to the risk event; If they are consistent, each stroke in the electronic signature is identified.
5. The method according to claim 1, characterized in that After verifying the electronic signature according to the first similarity, the method further includes: Obtaining the process information of the electronic signature fed back by the user; Determining the occurrence time of each endpoint and each intersection in the electronic signature according to the process information; Determining the writing order of the strokes and the writing speed of the strokes according to the occurrence times; Calculating a second similarity between the electronic signature and a pre-stored user signature according to the writing order and the writing speed; Determining whether the second similarity is greater than or equal to a preset second similarity threshold; If yes, it is determined that the electronic signature passes the verification; If not, it is determined that the electronic signature has failed the verification.
6. The method according to claim 1, characterized in that Generating a declaration form according to the declaration information and the verified electronic signature further includes: Obtaining a declaration form template corresponding to the risk event, wherein the declaration form template includes a plurality of fields to be filled in; According to the attributes of each field to be filled in, extract the relevant information of the risk event and the electronic signature and fill them into the corresponding fields to be filled in respectively; Determine whether there are unfilled fields to be filled; If not, display the input box to obtain relevant information input by the user until there are no unfilled fields to be filled in; If so, the declaration table is generated.
7. The method according to claim 1, characterized in that Adding watermarks to the risk certificate and the declaration form that have passed the verification, further comprising: Obtaining relevant information of the risk event, the relevant information at least including one or a combination of the columns of user name, date of birth, ID number, transaction number, transaction time and transaction location; generating a watermark element based on at least part of the relevant information; The risk certificate and the declaration form that have passed verification are watermarked according to the watermark element.
8. The method according to claim 1, characterized in that Verifying the risk credentials uploaded by the user further includes: Determine whether the number of risk credentials uploaded by the user is consistent with the number of risk credential upload entries; If they are consistent, identifying the text characters of the risk certificate uploaded through each of the upload entrances; According to the text characters, determining whether the risk certificate is consistent with the corresponding upload entry; If they are consistent, it is determined that the risk certificate has passed the verification; Otherwise, it is determined that the risk certificate has failed the verification.
9. The method according to claim 1, characterized in that: Receive risk credentials uploaded by the user, and further: Determining whether the risk credential is less than or equal to a preset size threshold; If not, the risk credential is compressed.
10. The method according to claim 1, characterized in that The method further comprises: In response to a transaction event, sending a transaction voucher upload notification to the user terminal; Receive transaction vouchers fed back by the user and verify them; Associating the verified transaction voucher with the transaction event; Generate a successful transaction voucher upload reminder and send it to the investigator to manually investigate the transaction event.
11. The method according to claim 10, characterized in that The method further comprises: Determining whether the transaction voucher is smaller than or equal to a preset transaction voucher size threshold; If not, the transaction voucher is compressed.
12. A credential uploading device, characterized in that: include: An acquisition module, used to respond to a risk event and display the declaration information to the user to obtain the user's electronic signature; A recognition module, used to recognize each stroke when the electronic signature is written, and determine the endpoints of each stroke and the intersection between any two strokes; A first calculation module, configured to calculate a first similarity between the electronic signature and a pre-stored user signature based on the endpoints and the intersection; A first verification module, configured to verify the electronic signature according to the first similarity; A generating module, used to generate a declaration form according to the declaration information and the verified electronic signature and send a notification of uploading risk credentials to the user terminal; The second verification module is used to receive and verify the risk certificate uploaded by the user; A watermark adding module, used to add watermarks to the risk certificate and the declaration form that have passed the verification; A first association module, used to associate the risk credential and the declaration form with the risk event after adding the watermark and generate a reminder of successful upload of the risk credential; The first reminder module is used to send a reminder of successful upload of the risk credential to an investigator so as to conduct a manual investigation on the risk event.
13. The device according to claim 12, characterized in that Also includes: A notification module, used for sending a transaction voucher upload notification to the user terminal in response to a transaction event; The third verification module is used to receive and verify the transaction voucher fed back by the user end; A second associating module, configured to associate the verified transaction voucher with the transaction event; The second reminder module is used to generate a reminder of successful upload of the transaction voucher and send it to the investigator to manually investigate the transaction event.
14. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 11 is implemented.
15. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 11 is implemented.
16. A computer program product, characterized in that The method comprises at least one instruction or at least one program, wherein the at least one instruction or the at least one program is loaded and executed by a processor to implement the method according to any one of claims 1 to 11.
