Qualification determination method and device, electronic equipment, medium and program product

Abstract

The invention provides a method for determining qualification of hand-filled receipts, which can be applied to the technical field of financial science and technology. The method comprises the steps of obtaining a receipt image of a hand-filled receipt, and displaying hand-filled content on the receipt image; according to the obtained contents to be filled in the receipts, constructing a font library of the contents to be filled in the receipts; matching the hand-filled content with a font library to obtain a matching result; according to the matching result, the qualification of the hand-filled receipts is determined, and the qualification is qualified or unqualified. The method is simple and easy to operate, the qualification of the hand-filled receipts can be automatically confirmed, the fonts of the content to be filled are added for decision making when the matching result is determined, so that the accuracy of the matching result can be improved, the matching result serves as a data basis for determining the qualification of the hand-filled receipts, and the accuracy of the matching result is improved due to the high accuracy of the matching result. According to the invention, the accuracy of determining the qualification of the hand-filled receipts is high. The invention further provides a device for determining the qualification of the hand-filled receipts, electronic equipment, a medium and a computer program product.

Description

Technical Field

[0001] The present disclosure relates to the field of financial technology, and more specifically, to a method, device, electronic device, medium and computer program product for determining the eligibility of a hand-filled return slip. Background Art

[0002] In real life, the service counters of bank service outlets have generally adopted information technology-based counter accounting systems, and provide customers with printed or electronic formatted receipts after the business is processed. The printed or electronic formatted receipts can ensure that the receipts provided to customers by the service counters of bank service outlets are consistent with the contents recorded in the counter accounting system. However, the service counters of bank service outlets cannot completely avoid business scenarios where tellers fill out receipts manually. For example, strong customer units (such as extremely important partners for banks, or judicial organs, etc.) require the bank to fill in the business receipt content on the paper voucher provided by the customer unit after the teller handles the business.

[0003] In this case, since there is no editable template for the voucher provided by the customer in the counter accounting system, the bank cannot format and print it. The bank can only rely on the teller to extract the part required by the customer from the receipt after the business is handled and copy it on the receipt provided by the customer. The receipt copied by the teller may be copied incorrectly. For example, the receipt should have written: 30 grams of gold and 1,000 grams of silver were handed over to a certain bank for safekeeping by a certain unit. It may be filled in by mistake as: 1,000 grams of gold and 30 grams of silver were handed over to a certain bank for safekeeping by a certain unit. This will cause adverse consequences and cause customer complaints.

[0004] Therefore, a method for automatically determining the eligibility of a hand-filled receipt is needed. Traditional optical character recognition technology can convert the content in an image into characters. Therefore, traditional optical character recognition technology can be applied to the service counters of bank service outlets. Specifically, the hand-filled receipt photographed by the high-speed scanner can be recognized to obtain the hand-filled characters of the hand-filled content, and the hand-filled characters can be compared with the acquired content to be filled, so as to determine whether the hand-filled receipt is qualified. However, there is a high probability of misjudgment when using traditional optical character recognition technology to determine whether a hand-filled receipt is qualified. For example, if some characters in the content to be filled have similar characters, and the teller's handwriting is sloppy and unclear, the comparison of the hand-filled content obtained by traditional optical character recognition with the content to be filled may cause misjudgment.

[0005] Therefore, how to improve the accuracy of the method for automatically determining the eligibility of hand-filled return forms has become a technical problem that technical personnel in this field urgently need to solve.

[0006] It should be noted that the above information disclosed in this section is only used to understand the background of the inventive concept of the present disclosure. Therefore, the above information may include information that does not constitute prior art, for example, technical content of applying traditional optical character recognition technology to service counters of bank service outlets. Summary of the invention

[0007] In view of this, the present disclosure provides a method, device, electronic device, computer-readable storage medium and computer program product for determining the eligibility of a hand-filled return form that is simple to operate and has a high accuracy rate.

[0008] One aspect of the present disclosure provides a method for determining the eligibility of a hand-filled receipt, comprising: obtaining a receipt image of the hand-filled receipt, the receipt image displaying the hand-filled content; constructing a font library of the content to be filled in the receipt based on the obtained content to be filled in the receipt; matching the hand-filled content with the font library to obtain a matching result; and determining the eligibility of the hand-filled receipt based on the matching result, wherein the eligibility is qualified or unqualified.

[0009] According to the method for determining the eligibility of a hand-filled receipt in an embodiment of the present disclosure, a receipt image of the hand-filled receipt is obtained, and the hand-filled content is displayed on the receipt image; a font library of the content to be filled in the receipt is constructed based on the obtained content to be filled in the receipt; thereby, the hand-filled content can be matched with the font library to obtain a matching result; thereby, the eligibility of the hand-filled receipt is determined based on the matching result, wherein the eligibility is qualified or unqualified. The method for determining the eligibility of a hand-filled receipt disclosed in the present disclosure is simple and easy to operate, and can automatically confirm the eligibility of a hand-filled receipt. Since the font of the content to be filled in is added to make a decision when determining the matching result, the accuracy of the matching result can be improved. The matching result serves as the data basis for determining the eligibility of the hand-filled receipt. Due to the high accuracy of the matching result, the accuracy of determining the eligibility of the hand-filled receipt can be higher.

[0010] In some embodiments, the step of constructing a font library of the content to be filled in on the receipt based on the acquired content to be filled in on the receipt includes: extracting m characters to be filled in on the receipt after the business is processed in the business system, wherein the m characters to be filled in represent the content to be filled in on the receipt, and m is an integer greater than or equal to 1; generating k fonts for each of the characters to be filled in based on a font library built into an electronic device that executes the method for determining the eligibility of the manually filled receipt, wherein k is an integer greater than or equal to 1; and storing the k fonts for each of the characters to be filled in in a database to form a font library for the content to be filled in on the receipt.

[0011] In some embodiments, the step of matching the hand-filled content with the font library to obtain a matching result includes: performing character segmentation on the hand-filled content of the receipt image according to a pre-set segmentation order using k fonts of the characters to be filled in with the same serial number as the segmentation order to obtain all actual segmented characters of the hand-filled content; and taking all actual segmented characters of the hand-filled content as the matching result.

[0012] In some embodiments, according to a preset segmentation sequence, the hand-filled content of the receipt image is segmented using k fonts of the characters to be filled in with the same sequence number as the segmentation sequence to obtain all the actual segmented characters of the hand-filled content, including: according to the preset segmentation sequence, the hand-filled content of the receipt image is segmented to obtain n characters of the same segmentation sequence. i pre-segmentation characters, where n i is an integer greater than or equal to 1, i is the sequence number of the segmentation order; when n i When n is equal to 1, the pre-segmentation character is used as the actual segmentation character; when n i When it is greater than or equal to 2, call the k fonts of the characters to be filled in with the same sequence number as the segmentation order, and calculate n respectively. i The similarity between each pre-segmented character in the pre-segmented characters and the k fonts is calculated to obtain k similarity values ​​for each pre-segmented character; the maximum value of the k similarity values ​​of each pre-segmented character is taken as the middle value; and n i The intermediate value is n i The pre-segmentation character corresponding to the maximum value among the intermediate values ​​is used as the actual segmentation character; the remaining characters of the hand-filled content excluding the actual segmentation character are further segmented to obtain n characters of the next segmentation order. i pre-split characters; repeat when n i When n is equal to 1, the pre-segmentation character is used as the actual segmentation character; when n i When it is greater than or equal to 2, call the k fonts of the characters to be filled in with the same sequence number as the segmentation order, and calculate n respectively. i The step of calculating the similarity between each pre-segmented character in the pre-segmented characters and the k fonts to obtain k similarity values ​​for each pre-segmented character, until all the hand-filled content is completely segmented, and all the actual segmented characters of the hand-filled content are obtained.

[0013] In some embodiments, the step of determining the eligibility of the hand-filled reply form based on the matching result includes: when the maximum value among the k similarity values ​​of all actual segmented characters of the hand-filled content is greater than or equal to a preset similarity threshold, determining that the hand-filled reply form is qualified; when any maximum value among the maximum values ​​of the k similarity values ​​of all actual segmented characters of the hand-filled content is less than a preset similarity threshold, determining that the hand-filled reply form is unqualified.

[0014] In some embodiments, the method for determining the eligibility of the hand-filled receipt further includes: using optical character recognition technology to convert the hand-filled content of the receipt image into g hand-filled characters, where g is an integer greater than or equal to 1; comparing the g hand-filled characters with the m characters to be filled in the acquired receipt to obtain a matching conclusion, where the matching conclusion is passed or failed. The step of determining the eligibility of the hand-filled receipt based on the matching result includes: determining the eligibility of the hand-filled receipt based on the matching result and the matching conclusion.

[0015] In some embodiments, the step of determining the eligibility of the hand-filled reply form based on the matching result and the matching conclusion includes: when the maximum value of the k similarity values ​​of all the actual segmented characters of the hand-filled content is greater than or equal to a preset similarity threshold, and the matching conclusion is passed, determining that the hand-filled reply form is qualified; when the maximum value of the k similarity values ​​of all the actual segmented characters of the hand-filled content is greater than or equal to the preset similarity threshold, and the matching conclusion is failed, determining that the hand-filled reply form is unqualified; when any maximum value of the maximum values ​​of the k similarity values ​​of all the actual segmented characters of the hand-filled content is less than a preset similarity threshold, determining that the hand-filled reply form is unqualified.

[0016] In some embodiments, the method for determining the eligibility of the hand-filled reply form further includes: returning processing measures based on the eligibility of the hand-filled reply form.

[0017] Another aspect of the present disclosure provides a device for determining the eligibility of a hand-filled receipt, comprising: an acquisition module, the acquisition module is used to acquire a receipt image of a hand-filled receipt, the hand-filled content being displayed on the receipt image; a construction module, the construction module is used to construct a font library of the content to be filled in the receipt based on the acquired content to be filled in the receipt; a matching module, the matching module is used to match the hand-filled content with the font library to obtain a matching result; and a determination module, the determination module is used to determine the eligibility of the hand-filled receipt based on the matching result, wherein the eligibility is qualified or unqualified.

[0018] Another aspect of the present disclosure provides an electronic device, comprising one or more processors and one or more memories, wherein the memories are used to store executable instructions, and when the executable instructions are executed by the processors, the above-mentioned method is implemented.

[0019] Another aspect of the present disclosure provides a computer-readable storage medium storing computer-executable instructions, which are used to implement the above method when executed.

[0020] Another aspect of the present disclosure provides a computer program product, comprising a computer program, wherein the computer program comprises computer executable instructions, and the instructions are used to implement the method as described above when executed. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The above and other objects, features and advantages of the present disclosure will become more apparent through the following description of the embodiments of the present disclosure with reference to the accompanying drawings, in which:

[0022] Figure 1 An exemplary system architecture to which the method and apparatus according to an embodiment of the present disclosure can be applied is schematically shown;

[0023] Figure 2 A flowchart of a method for determining the eligibility of a hand-filled return form according to an embodiment of the present disclosure is schematically shown;

[0024] Figure 3 A flowchart schematically shows the steps of constructing a font library of the content to be filled in the receipt according to the acquired content to be filled in the receipt according to an embodiment of the present disclosure;

[0025] Figure 4 A flowchart schematically shows the steps of matching the hand-filled content with the font library to obtain the matching result according to an embodiment of the present disclosure;

[0026] Figure 5 A flowchart schematically shows the steps of performing character segmentation on the hand-filled content of the receipt image according to a preset segmentation sequence using k fonts of characters to be filled in with the same sequence number as the segmentation sequence to obtain all actually segmented characters of the hand-filled content according to an embodiment of the present disclosure;

[0027] Figure 6 A schematic diagram of a hand-filled return form according to an embodiment of the present disclosure is shown;

[0028] Figure 7 A flowchart schematically illustrates the steps of determining the eligibility of a hand-filled return slip according to a matching result according to an embodiment of the present disclosure;

[0029] Figure 8 A flowchart of a method for determining the eligibility of a hand-filled return form according to an embodiment of the present disclosure is schematically shown;

[0030] Fig. 9 A flowchart schematically illustrates the steps of determining the eligibility of a hand-filled return slip according to a matching result and a matching conclusion according to an embodiment of the present disclosure;

[0031] Fig.10 The structure block diagram of the device for determining the eligibility of a hand-filled return form according to an embodiment of the present disclosure is schematically shown;

[0032] Fig.11 A block diagram of an electronic device according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0033] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present disclosure. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0034] In the technical solution of the present disclosure, the user information (including but not limited to user personal information, user image information, user device information, such as location information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved are all information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data comply with relevant laws, regulations and standards, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0035] In the scenario of using personal information for automated decision-making, the methods, devices, and systems provided by the embodiments of the present disclosure provide users with corresponding operation portals for users to choose to agree or reject the automated decision-making results; if the user chooses to reject, the expert decision-making process will be entered. The expression "automated decision-making" here refers to the activity of automatically analyzing and evaluating a person's behavioral habits, interests and hobbies, or economic, health, credit status, etc. through computer programs, and making decisions. The expression "expert decision-making" here refers to the activity of making decisions by people who specialize in a certain field, have specialized experience, knowledge and skills, and have reached a certain level of professionalism.

[0036] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "comprise", "include", etc. used herein indicate the existence of the features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0037] When using expressions such as "at least one of A, B or C, etc.", it should generally be interpreted in accordance with the meaning of the expression generally understood by those skilled in the art (for example, "a system having at least one of A, B or C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.). The terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, features defined as "first" and "second" may explicitly or implicitly include one or more of the said features.

[0038] In real life, the service counters of bank service outlets have generally adopted information technology-based counter accounting systems, and provide customers with printed or electronic formatted receipts after the business is processed. The printed or electronic formatted receipts can ensure that the receipts provided to customers by the service counters of bank service outlets are consistent with the contents recorded in the counter accounting system. However, the service counters of bank service outlets cannot completely avoid business scenarios where tellers fill out receipts manually. For example, strong customer units (such as extremely important partners for banks, or judicial organs, etc.) require the bank to fill in the business receipt content on the paper voucher provided by the customer unit after the teller handles the business.

[0039] In this case, since there is no editable template for the voucher provided by the customer in the counter accounting system, the bank cannot format and print it. The bank can only rely on the teller to extract the part required by the customer from the receipt after the business is handled and copy it on the receipt provided by the customer. The receipt copied by the teller may be copied incorrectly. For example, the receipt should have written: 30 grams of gold and 1,000 grams of silver were handed over to a certain bank for safekeeping by a certain unit. It may be filled in by mistake as: 1,000 grams of gold and 30 grams of silver were handed over to a certain bank for safekeeping by a certain unit. This will cause adverse consequences and cause customer complaints.

[0040] Therefore, a method for automatically determining the eligibility of a hand-filled receipt is needed. Traditional optical character recognition technology can convert the content in an image into characters. Therefore, traditional optical character recognition technology can be applied to the service counters of bank service outlets. Specifically, the hand-filled receipt photographed by the high-speed scanner can be recognized to obtain the hand-filled characters of the hand-filled content, and the hand-filled characters can be compared with the acquired content to be filled, so as to determine whether the hand-filled receipt is qualified. However, there is a high probability of misjudgment when using traditional optical character recognition technology to determine whether a hand-filled receipt is qualified. For example, if some characters in the content to be filled have similar characters, and the teller's handwriting is sloppy and unclear, the comparison of the hand-filled content obtained by traditional optical character recognition with the content to be filled may cause misjudgment.

[0041] Therefore, how to improve the accuracy of the method for automatically determining the eligibility of hand-filled return forms has become a technical problem that technical personnel in this field urgently need to solve.

[0042] It should be noted that the above information disclosed in this section is only used to understand the background of the inventive concept of the present disclosure. Therefore, the above information may include information that does not constitute prior art, for example, technical content of applying traditional optical character recognition technology to service counters of bank service outlets.

[0043] The embodiments of the present disclosure provide a method, device, electronic device, computer-readable storage medium and computer program product for determining the eligibility of a hand-filled receipt. The method for determining the eligibility of a hand-filled receipt includes: obtaining a receipt image of the hand-filled receipt, and displaying the hand-filled content on the receipt image; constructing a font library of the content to be filled in the receipt according to the obtained content to be filled in the receipt; matching the hand-filled content with the font library to obtain a matching result; and determining the eligibility of the hand-filled receipt according to the matching result, wherein the eligibility is qualified or unqualified.

[0044] It should be noted that the method, device, electronic device, computer-readable storage medium, and computer program product for determining the eligibility of a hand-filled receipt disclosed in the present invention can be used in the field of financial technology, and can be specifically used in bank counter receipt matters in the field of financial technology, and can be used to determine the eligibility of a hand-filled receipt. The method, device, electronic device, computer-readable storage medium, and computer program product for determining the eligibility of a hand-filled receipt disclosed in the present invention can also be used in any field other than the field of financial technology, and the field of the present invention is not limited here.

[0045] Figure 1 The exemplary system architecture 100 of the qualification determination method, apparatus, electronic device, computer-readable storage medium and computer program product that can be applied to the hand-filled return form according to the embodiment of the present disclosure is schematically shown. It should be noted that: Figure 1What is shown is merely an example of a system architecture to which the embodiments of the present disclosure can be applied, in order to help those skilled in the art understand the technical content of the present disclosure, but it does not mean that the embodiments of the present disclosure cannot be used in other devices, systems, environments or scenarios.

[0046] like Figure 1 As shown, the application scenario 100 according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, and a server 105. The network 104 is used to provide a medium for a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or optical fiber cables, etc.

[0047] The user can use the first terminal device 101, the second terminal device 102, and the third terminal device 103 to interact with the server 105 through the network 104 to receive or send messages, etc. Various communication client applications can be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only for example).

[0048] The first terminal device 101, the second terminal device 102, and the third terminal device 103 may be various electronic devices having display screens and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.

[0049] The server 105 may be a server that provides various services, such as a background management server (only as an example) that provides support for websites browsed by users using the first terminal device 101, the second terminal device 102, and the third terminal device 103. The background management server may analyze and process the received data such as user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal device.

[0050] It should be noted that the qualification determination method of the hand-filled reply form provided in the embodiment of the present disclosure can generally be executed by the server 105. Accordingly, the qualification determination device of the hand-filled reply form provided in the embodiment of the present disclosure can generally be set in the server 105. The qualification determination method of the hand-filled reply form provided in the embodiment of the present disclosure can also be executed by a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 105. Accordingly, the qualification determination device of the hand-filled reply form provided in the embodiment of the present disclosure can also be set in a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 105.

[0051] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to the implementation requirements.

[0052] The following will be based on Figure 1 The scene described by Figure 2~Figure 9 The method for determining the eligibility of a hand-filled reply form in an embodiment of the present disclosure is described in detail.

[0053] Figure 2 The flowchart of the method for determining the eligibility of a hand-filled reply form according to an embodiment of the present disclosure is schematically shown.

[0054] like Figure 2 As shown, the method for determining the eligibility of a hand-filled reply form in this embodiment includes operations S210 to S240.

[0055] In operation S210, a receipt image of the hand-filled receipt is obtained, and the hand-filled content is displayed on the receipt image. It is understandable that an image acquisition device (such as a high-speed scanner) can be placed on the bank counter, and the image acquisition device can acquire the receipt image of the hand-filled receipt.

[0056] In operation S220, a font library of the content to be filled in the receipt is constructed according to the acquired content to be filled in the receipt.

[0057] As a possible way to achieve this, Figure 3 As shown, operation S220 is a step of constructing a font library of the content to be filled in the receipt according to the acquired content to be filled in the receipt, including operation S221 to operation S223.

[0058] In operation S221, the m characters to be filled in the receipt after the business is processed in the business system are extracted, where the m characters to be filled in represent the content to be filled in the receipt, and m is an integer greater than or equal to 1. It can be understood that after the teller completes the business for the customer, the business system will provide a receipt to the customer. For customers without special requirements, the teller can directly print out the receipt and give it to the customer as a receipt voucher; but for customers with special requirements, the teller is required to copy the characters to be filled in on the receipt to the receipt provided by the customer to form a hand-filled receipt. The content copied by the teller can be understood as hand-filled content. In operation S221, the m characters to be filled in on the receipt after the business is processed can be extracted from the business system.

[0059] In operation S222, k fonts for each character to be filled in are generated according to a font library built into the electronic device that performs the method for determining the eligibility of a hand-filled return form, where k is an integer greater than or equal to 1. It is understandable that a font library may be built into the electronic device that performs the method for determining the eligibility of a hand-filled return form disclosed in the present invention, and the font library built into the electronic device may include, but is not limited to, fonts such as Songti, Heiti, Kaiti, Lishu, and Youyuan.

[0060] In operation S223, k fonts of each character to be filled in are stored in a database to form a font library of the content to be filled in the receipt.

[0061] Operations S221 to S223 can facilitate the step of constructing a font library of the content to be filled in the receipt according to the acquired content to be filled in the receipt.

[0062] In operation S230, the manually filled content is matched with the font library to obtain a matching result.

[0063] As an implementation method, Figure 4 As shown, operation S230 matches the hand-filled content with the font library to obtain a matching result, including operation S231 and operation S232.

[0064] In operation S231, the hand-filled content of the receipt image is segmented according to a preset segmentation sequence using k fonts of characters to be filled in with the same sequence number as the segmentation sequence to obtain all actual segmented characters of the hand-filled content.

[0065] In some specific embodiments, Figure 5 As shown, operation S231 performs character segmentation on the hand-filled content of the receipt image according to a pre-set segmentation order using k fonts with the same serial number as the segmentation order to obtain all the actual segmented characters of the hand-filled content, including operations S2311 to S2317.

[0066] In operation S2311, the hand-filled content of the receipt image is segmented into characters according to a preset segmentation sequence to obtain n i pre-segmentation characters, where n i is an integer greater than or equal to 1, and i is the sequence number of the segmentation order.

[0067] In operation S2312, when n i When equal to 1, the pre-segmentation character is used as the actual segmentation character.

[0068] In operation S2313, when n i When it is greater than or equal to 2, call k fonts with the same serial number as the segmentation order to fill in the characters, and calculate n respectively. i The similarity between each pre-segmented character in the pre-segmented characters and the k fonts is calculated to obtain k similarity values ​​for each pre-segmented character.

[0069] In operation S2314, the maximum value among the k similarity values ​​of each pre-segmented character is taken as the intermediate value.

[0070] In operation S2315, compare n i The intermediate value is n i The pre-segmentation character corresponding to the maximum value among the intermediate values ​​is used as the actual segmentation character.

[0071] In operation S2316, continue to perform character segmentation on the remaining characters of the hand-filled content except the actual segmentation characters to obtain n characters of the next segmentation order. i pre-splitting characters.

[0072] In operation S2317, the operation is repeated when n i When n is equal to 1, the pre-segmentation character is used as the actual segmentation character; when n i When it is greater than or equal to 2, call k fonts with the same serial number as the segmentation order to fill in the characters, and calculate n respectively. i The similarity between each pre-segmented character in the pre-segmented characters and k fonts is calculated to obtain k similarity values ​​of each pre-segmented character, until all the hand-filled content is segmented, and all the actual segmented characters of the hand-filled content are obtained.

[0073] It should be noted that the splitting order can be preset to split in order from front to back, or it can be preset to split in reverse order from back to front. Figure 6 The hand-filled return form is used to exemplify operations S2311 to S2317.

[0074] Specifically, Figure 6The handwritten characters on the hand-filled receipt are 6 in number, namely "亳", "州", "林", "昆", "公", and "司". Among them, the two "木" characters in the character "林" have a relatively large distance between them, but the distance is less than the threshold. The distance between the latter "木" character in the character "林" and the character "昆" is relatively close. During character recognition, if the distance exceeds the threshold, it will not be recognized as a single character, and if the distance is less than or equal to the threshold, it will be recognized as a single character. Suppose Figure 6 The hand-filled receipt is sequentially segmented from front to back. After the first segmentation sequence, 1 pre-segmented character is obtained, which is "亳", and "亳" is taken as the actual segmented character. After the second segmentation sequence, 1 pre-segmented character is obtained, which is "州", and "州" is taken as the actual segmented character. After the third segmentation sequence, 3 pre-segmented characters are obtained, namely "木", "林", and "林昆".

[0075] Next, call the k fonts of the third character to be filled in the content to be filled, calculate the similarity between "木" and each of the k fonts, obtain k similarity values of "木", and take the maximum value among the k similarity values of "木" as the intermediate value; calculate the similarity between "林" and each of the k fonts, obtain k similarity values of "林", and take the maximum value among the k similarity values of "林" as the intermediate value; calculate the similarity between "林昆" and each of the k fonts, obtain k similarity values of "林昆", and take the maximum value among the k similarity values of "林昆" as the intermediate value. Compare the intermediate values of "木", "林", and "林昆", and take the character corresponding to the largest intermediate value among the 3 intermediate values as the actual segmented character. Here, it is assumed that the intermediate value of "林" is the largest.

[0076] After the segmentation sequences 1 to 3, the remaining handwritten characters are "昆", "公", and "司". Continue to segment "昆", "公", and "司" in the same way as "亳", "州", and "林", which will not be elaborated here. After all the handwritten content is segmented into characters, the actual segmented characters "亳", "州", "林", "昆", "公", and "司" are obtained.

[0077] It can be understood that if traditional optical character recognition technology is used, only the character spacing is considered during character segmentation. For Figure 6The manually filled receipt may be recognized as "Haozhou Mugun Co., Ltd." or "Liangzhou Mugun Co., Ltd." Comparing "Haozhou Mugun Co., Ltd." or "Liangzhou Mugun Co., Ltd." with the content to be filled will lead to the conclusion that the manually filled content is incorrect, while the actual manually filled content is not incorrect. When the present disclosure performs character segmentation, it comprehensively considers the content to be filled and the character spacing. For each segmentation order, it takes into account various possible pre-segmented characters that may be segmented out, and corresponds to the characters to be filled in the content to be filled according to the segmentation order to determine the actual segmented characters. The actual segmented characters determined in this way are more consistent with the actual written characters, that is, the actual segmented characters determined in this way are more accurate. In addition, after determining the previous actual segmented character, the present disclosure eliminates the actual segmented character and continues to segment the remaining characters of the manually filled content, which can reduce the influence of the previous manually filled character on the subsequent manually filled character, avoid misleading recognition, and thus further improve the accuracy of determining the actual segmented characters.

[0078] Based on this, through operations S2311 to S2317, it is convenient to implement the step of performing character segmentation on the manually filled content of the receipt image by using k fonts of the characters to be filled with the same serial numbers as the segmentation order according to the pre-set segmentation order, and all the actual segmented characters of the manually filled content obtained are more accurate.

[0079] In operation S232, all the actual segmented characters of the manually filled content are used as the matching result.

[0080] Through operations S231 and S232, it is convenient to implement the step of matching the manually filled content with the font library to obtain the matching result.

[0081] In operation S240, according to the matching result, the qualification of the manually filled receipt is determined, where the qualification is qualified or unqualified.

[0082] As some possible implementation manners, such as Figure 7 shown, the step of operation S240 determining the qualification of the manually filled receipt according to the matching result includes operations S241 and S242.

[0083] In operation S241, when the maximum value among the k similarity values of all the actual segmented characters of the manually filled content is greater than or equal to the pre-set similarity threshold, it is determined that the manually filled receipt is qualified.

[0084] In operation S242, when any maximum value among the k similarity values of all the actual segmented characters of the manually filled content is less than the pre-set similarity threshold, it is determined that the manually filled receipt is unqualified.

[0085] Operations S241 and S242 can facilitate the step of determining the eligibility of the hand-filled return form based on the matching results.

[0086] According to the method for determining the eligibility of a hand-filled receipt in an embodiment of the present disclosure, a receipt image of the hand-filled receipt is obtained, and the hand-filled content is displayed on the receipt image; a font library of the content to be filled in the receipt is constructed based on the obtained content to be filled in the receipt; thereby, the hand-filled content can be matched with the font library to obtain a matching result; thereby, the eligibility of the hand-filled receipt is determined based on the matching result, wherein the eligibility is qualified or unqualified. The method for determining the eligibility of a hand-filled receipt disclosed in the present disclosure is simple and easy to operate, and can automatically confirm the eligibility of a hand-filled receipt. Since the font of the content to be filled in is added to make a decision when determining the matching result, the accuracy of the matching result can be improved. The matching result serves as the data basis for determining the eligibility of the hand-filled receipt. Due to the high accuracy of the matching result, the accuracy of determining the eligibility of the hand-filled receipt can be higher.

[0087] According to some embodiments of the present disclosure, Figure 8 As shown, the method for determining the eligibility of a manually filled-in receipt also includes operation S310 and operation S320.

[0088] In operation S310, the hand-filled content of the receipt image is converted into g hand-filled characters using optical character recognition technology, where g is an integer greater than or equal to 1. The optical character recognition technology can divide the hand-filled content into g hand-filled characters according to character spacing.

[0089] In operation S320, the g manually filled characters are compared with the m characters to be filled in the obtained receipt to obtain a matching conclusion, wherein the matching conclusion is passed or failed.

[0090] Operation S240 is a step of determining the eligibility of the hand-filled return slip according to the matching result, including operation S241.

[0091] In operation S241, the eligibility of the hand-filled return slip is determined based on the matching result and the matching conclusion.

[0092] By adding the traditional optical character recognition technology (ie, operation S310 and operation S320), a matching conclusion can be obtained. By combining the matching result and the matching conclusion as a basis for decision-making, the accuracy of determining the eligibility of the opponent's filled-in return form can be further improved.

[0093] According to some embodiments of the present disclosure, Fig. 9 As shown, operation S241 is a step for determining the eligibility of the hand-filled return form based on the matching results and matching conclusions, including operations S2411 to S2413.

[0094] In operation S2411, when the middle values ​​of all the actual segmented characters of the hand-filled content are greater than or equal to the preset similarity threshold, and the matching conclusion is passed, it is determined that the hand-filled receipt is qualified.

[0095] In operation S2412, when the middle values ​​of all the actual segmented characters of the hand-filled content are greater than or equal to the preset similarity threshold, and the matching conclusion is failed, it is determined that the hand-filled receipt is unqualified.

[0096] In operation S2413, when any intermediate value among the intermediate values ​​of all the actually segmented characters of the hand-filled content is smaller than a preset similarity threshold, it is determined that the hand-filled receipt is unqualified.

[0097] Operations S2411 to S2413 can facilitate the steps of determining the eligibility of the hand-filled return form based on the matching results and matching conclusions.

[0098] According to some embodiments of the present disclosure, the method for determining the eligibility of a manually filled-in reply form further includes operation S410.

[0099] In operation S410, processing measures are returned based on the eligibility of the hand-filled return form.

[0100] For example, when the median values ​​of all actual segmented characters of the hand-filled content are greater than or equal to the preset similarity threshold, and the matching conclusion is passed, it means that the hand-filled content is written correctly and in accordance with standards, and the hand-filled receipt can be prompted to provide qualified information, so that the next business process can be continued. When the median values ​​of all actual segmented characters of the hand-filled content are greater than or equal to the preset similarity threshold, and the matching conclusion is failed, it means that the hand-filled content is written correctly, but the handwriting may be sloppy and irregular, resulting in the failure of traditional optical character recognition to recognize it, and a prompt can be given to rewrite it and pay attention to the standard information. When any of the median values ​​of all actual segmented characters of the hand-filled content is less than the preset similarity threshold, it means that the hand-filled content is seriously inconsistent with the content that should be filled in, and a prompt can be given to rewrite the information after checking the content.

[0101] Operation S410 can be used to easily remind the teller to avoid erroneous receipts from entering the hands of customers and causing customer complaints.

[0102] Based on the above-mentioned method for determining the eligibility of a hand-filled return form, the present disclosure also provides a device for determining the eligibility of a hand-filled return form. Fig.10 The eligibility determination device for the hand-filled return form is described in detail.

[0103] Fig.10 The structural block diagram of the device for determining the eligibility of a hand-filled reply form according to an embodiment of the present disclosure is schematically shown.

[0104] The device 10 for determining the eligibility of a hand-filled reply form comprises an acquisition module 1 , a construction module 2 , a matching module 3 and a determination module 4 .

[0105] The acquisition module 1 is used to acquire a receipt image of a hand-filled receipt, and the hand-filled content is displayed on the receipt image.

[0106] The construction module 2 is used to construct a font library of the content to be filled in the receipt according to the acquired content to be filled in the receipt.

[0107] The matching module 3 is used to match the hand-filled content with the font library to obtain a matching result.

[0108] The determination module 4 is used to determine the eligibility of the hand-filled return form according to the matching results, wherein the eligibility is qualified or unqualified.

[0109] According to some embodiments of the present disclosure, the building module includes an extracting unit, a generating unit and a forming unit.

[0110] The extraction unit is used to extract m characters to be filled in the receipt after the business is processed in the business system, wherein the m characters to be filled in represent the content to be filled in the receipt, and m is an integer greater than or equal to 1.

[0111] The generating unit is used to execute a font library built into an electronic device for executing a method for determining the eligibility of a manually filled-in return form, and generate k fonts for each character to be filled in, wherein k is an integer greater than or equal to 1.

[0112] The forming unit is used to store k fonts of each character to be filled in into a database to form a font library of the content to be filled in the receipt.

[0113] According to some embodiments of the present disclosure, the matching module includes a first determination unit and a second determination unit.

[0114] The first determining unit is used to perform character segmentation on the hand-filled content of the receipt image according to a preset segmentation sequence using k fonts of characters to be filled in with the same sequence number as the segmentation sequence to obtain all actual segmented characters of the hand-filled content.

[0115] The second determining unit is used to take all actual segmented characters of the manually filled content as matching results.

[0116] According to some embodiments of the present disclosure, the first determining unit includes a first segmentation element, a first determination element, a calculation element, a second determination element, a third determination element, a second segmentation element, and a repeating element.

[0117] The first segmentation component is used to segment the hand-filled content of the receipt image according to a preset segmentation order, and obtain n i pre-segmentation characters, where n iis an integer greater than or equal to 1, and i is the sequence number of the segmentation order.

[0118] The first determining element is used when n i When equal to 1, the pre-segmentation character is used as the actual segmentation character.

[0119] The computing element is used when n i When it is greater than or equal to 2, call k fonts with the same serial number as the segmentation order to fill in the characters, and calculate n respectively. i The similarity between each pre-segmented character in the pre-segmented characters and the k fonts is calculated to obtain k similarity values ​​for each pre-segmented character.

[0120] The second determining element is used to take the maximum value among the k similarity values ​​of each pre-segmented character as the intermediate value.

[0121] The third determining element is used to compare n i The intermediate value is n i The pre-segmentation character corresponding to the maximum value among the intermediate values ​​is used as the actual segmentation character.

[0122] The second segmentation element is used to continue segmenting the remaining characters of the hand-filled content except the actual segmentation characters to obtain the next segmentation sequence n i pre-splitting characters.

[0123] Repeating element is used to repeat when n i When n is equal to 1, the pre-segmentation character is used as the actual segmentation character; when n i When it is greater than or equal to 2, call k fonts with the same serial number as the segmentation order to fill in the characters, and calculate n respectively. i The similarity between each pre-segmented character in the pre-segmented characters and k fonts is calculated to obtain k similarity values ​​of each pre-segmented character, until all the hand-filled content is segmented, and all the actual segmented characters of the hand-filled content are obtained.

[0124] According to some embodiments of the present disclosure, the determination module includes a third determination unit and a fourth determination unit.

[0125] The third determination unit is used to determine that the hand-filled receipt is qualified when the maximum value among the k similarity values ​​of all the actual segmented characters of the hand-filled content is greater than or equal to a preset similarity threshold.

[0126] The fourth determination unit is used to determine that the hand-filled receipt is unqualified when any maximum value among the k similarity values ​​of all actually segmented characters of the hand-filled content is less than a preset similarity threshold.

[0127] According to some embodiments of the present disclosure, the device for determining the eligibility of a hand-filled return form further includes a conversion module and an auxiliary determination module.

[0128] The conversion module is used to convert the hand-filled content of the receipt image into g hand-filled characters using optical character recognition technology, where g is an integer greater than or equal to 1.

[0129] The auxiliary determination module is used to compare the g manually filled characters with the m characters to be filled in the obtained receipt to obtain a matching conclusion, wherein the matching conclusion is passed or failed.

[0130] The determination includes a fifth determination unit, and the fifth determination unit is used to determine the eligibility of the hand-filled return form according to the matching result and the matching conclusion.

[0131] According to some embodiments of the present disclosure, the fifth determining unit includes a fourth determining element, a fifth determining element, and a sixth determining element.

[0132] The fourth determining element is used to determine that the hand-filled receipt is qualified when the maximum value of the k similarity values ​​of all the actual segmented characters of the hand-filled content is greater than or equal to the preset similarity threshold and the matching conclusion is passed.

[0133] The fifth determining element is used to determine that the hand-filled receipt is unqualified when the maximum value of the k similarity values ​​of all the actual segmented characters of the hand-filled content is greater than or equal to the preset similarity threshold and the matching conclusion is failure.

[0134] The sixth determining element is used to determine that the hand-filled receipt is unqualified when any maximum value among the k similarity values ​​of all actual segmented characters of the hand-filled content is less than a preset similarity threshold.

[0135] According to some embodiments of the present disclosure, the device for determining the eligibility of a hand-filled reply form further includes a return module, and the return module is used to return processing measures according to the eligibility of the hand-filled reply form.

[0136] According to the device 10 for determining the eligibility of a hand-filled receipt of the embodiment of the present disclosure, by acquiring a receipt image of the hand-filled receipt, the hand-filled content is displayed on the receipt image; by constructing a font library of the content to be filled in the receipt according to the acquired content to be filled in the receipt; thereby, the hand-filled content can be matched with the font library to obtain a matching result; thereby, the eligibility of the hand-filled receipt is determined according to the matching result, wherein the eligibility is qualified or unqualified. The method for determining the eligibility of a hand-filled receipt disclosed in the present disclosure is simple and easy to operate, and can automatically confirm the eligibility of a hand-filled receipt. Since the font of the content to be filled in is added to make a decision when determining the matching result, the accuracy of the matching result can be improved. The matching result serves as the data basis for determining the eligibility of the hand-filled receipt. Due to the high accuracy of the matching result, the accuracy of determining the eligibility of the hand-filled receipt can be higher.

[0137] In addition, according to an embodiment of the present disclosure, any multiple modules among the acquisition module 1, the construction module 2, the matching module 3 and the determination module 4 can be combined into one module for implementation, or any one of the modules can be split into multiple modules. Alternatively, at least part of the functions of one or more of these modules can be combined with at least part of the functions of other modules and implemented in one module.

[0138] According to an embodiment of the present disclosure, at least one of the acquisition module 1, the construction module 2, the matching module 3 and the determination module 4 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application-specific integrated circuit (ASIC), or can be implemented by hardware or firmware such as any other reasonable way of integrating or packaging the circuit, or can be implemented in any one of the three implementation methods of software, hardware and firmware, or in an appropriate combination of any of them.

[0139] Alternatively, at least one of the acquisition module 1, the construction module 2, the matching module 3 and the determination module 4 may be at least partially implemented as a computer program module, and when the computer program module is executed, the corresponding function may be executed.

[0140] The following describes in detail the method for determining the eligibility of a hand-filled return form according to an embodiment of the present disclosure. It is worth noting that the following description is only an exemplary description and is not a specific limitation of the present disclosure.

[0141] The method for determining the eligibility of a manually filled-in reply form may include steps 1 to 5, as follows.

[0142] Step 1: Obtain the real receipt content. It is relatively easy to obtain the real receipt content. You can directly extract the formatted receipt content from the bank's existing counter information technology (IT) system.

[0143] Step 2: Obtain the teller's hand-filled content, and transform the counter system. Before the teller applies for the seal (that is, stamping the business seal) of the manually filled voucher in the system, the teller is required to place the hand-filled voucher under the high-speed scanner for image collection. The high-speed scanner is a common device at bank counters, used in various scenarios in daily business that require the capture of business voucher images. Through a camera, the voucher placed on the bottom plate can be photographed and transmitted to the bank's IT system.

[0144] Step 3: Use traditional OCR recognition and compare with the electronic receipt. Use traditional optical character recognition technology (OCR) to convert the content filled in manually by the teller into text in the IT system and compare it with the receipt generated by the system to see if it is consistent. Traditional OCR recognition is relatively open in the industry and is generally considered to have the following parts.

[0145] 1. Character segmentation: Based on the spacing between the handwritten characters, determine which piece of the image corresponds to a character.

[0146] 2. Character recognition: Through the "pattern matching" technology, determine which character the image from the previous step is more similar to.

[0147] Step 4: Improved OCR recognition. Traditional OCR recognition also has the following defects.

[0148] 1. Defect in character segmentation: For example, in Figure 6 "林昆" is segmented into "木棍".

[0149] 2. Inaccurate character recognition: For example, in Figure 6 "亳州" is recognized as "亮州" or "毫州".

[0150] For example, a teller handwrites the text "亳州林昆公司". Due to non-standard handwriting, the writing style is as shown in Figure 6 If read through traditional OCR, there may be recognition ambiguities due to character spacing issues. There may also be problems due to handwriting, resulting in characters like "亳" (a rare character) being recognized as "亮" or "毫" when recognized in comparison with similar characters.

[0151] Therefore, for the scenario of bank counters, an improved OCR recognition method is proposed. This improved method matches the handwritten vouchers with the known real receipt content, and through single-character matching, realizes character segmentation to better check whether the handwritten content is consistent with the content expressed in the system.

[0152] The specific method is as follows: (1) Generate "亳" in multiple fonts according to the font library built into the IT system for the text in the IT system. (2) In the character recognition stage, compare the multiple-font texts generated above with the existing handwritten texts in the collected photos. When the similarity of any one of the fonts in the image pattern matching reaches a certain preset value, it can be considered that the handwritten text matches the text in the system. Here, since we directly compare "亳" with the handwritten style and only recognize whether the handwritten style is similar to "亳", it avoids the problem of ambiguity in matching recognition in traditional OCR recognition. (3) In the character segmentation stage, try multiple segmentation regions by traversing and adjusting the width of the segmentation region, select the segmentation method with the highest matching degree, and determine it as the character segmentation position. This avoids the problem of ambiguity caused by simply segmenting based on character spacing.

[0153] Step 5: Remind the teller of the problems with handwritten writing. By modifying the existing counter system, a prompt is given when the above OCR recognition fails. Here, different situations need to be treated differently.

[0154] (1) Improved OCR recognition fails: The teller's handwritten content is seriously inconsistent with the receipt content in the IT system. It is recommended to check the content and rewrite it.

[0155] (2) The improved OCR recognition passes, but the ordinary OCR recognition fails: This indicates that the teller's handwriting is correct, but the handwriting may be illegible or unclear. The teller is prompted to rewrite the message and pay attention to the standard when rewriting.

[0156] (3) Both the improved OCR recognition and the ordinary OCR recognition have been verified: Verification passed, and the next business process continues.

[0157] In the bank counter scenario, the OCR algorithm is improved to remind tellers of handwriting errors.

[0158] Fig.11 A block diagram of an electronic device suitable for implementing the above method according to an embodiment of the present disclosure is schematically shown.

[0159] like Fig.11 As shown, the electronic device 900 according to an embodiment of the present disclosure includes a processor 901, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 902 or a program loaded from a storage part 908 to a random access memory (RAM) 903. The processor 901 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or a related chipset and / or a dedicated microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 901 may also include an onboard memory for caching purposes. The processor 901 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0160] In RAM 903, various programs and data required for the operation of electronic device 900 are stored. Processor 901, ROM 902 and RAM 903 are connected to each other via bus 904. Processor 901 performs various operations of the method flow according to the embodiment of the present disclosure by executing the program in ROM 902 and / or RAM 903. It should be noted that the program can also be stored in one or more memories other than ROM 902 and RAM 903. Processor 901 can also perform various operations of the method flow according to the embodiment of the present disclosure by executing the program stored in the one or more memories.

[0161] According to an embodiment of the present disclosure, the electronic device 900 may further include an input / output (I / O) interface 905, which is also connected to the bus 904. The electronic device 900 may further include one or more of the following components connected to the input / output (I / O) interface 905: an input portion 906 including a keyboard, a mouse, etc.; an output portion 907 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage portion 908 including a hard disk, etc.; and a communication portion 909 including a network interface card such as a LAN card, a modem, etc. The communication portion 909 performs communication processing via a network such as the Internet. A drive 910 is also connected to the input / output (I / O) interface 905 as needed. A removable medium 911, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 910 as needed, so that a computer program read therefrom is installed into the storage portion 908 as needed.

[0162] The present disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or may exist independently without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method according to the embodiment of the present disclosure is implemented.

[0163] According to an embodiment of the present disclosure, a computer-readable storage medium may be a non-volatile computer-readable storage medium, for example, may include but is not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, an apparatus or a device. For example, according to an embodiment of the present disclosure, a computer-readable storage medium may include the ROM 902 and / or RAM 903 described above and / or one or more memories other than ROM 902 and RAM 903.

[0164] The embodiment of the present disclosure also includes a computer program product, which includes a computer program, and the computer program contains program code for executing the method shown in the flowchart. When the computer program product is run in a computer system, the program code is used to enable the computer system to implement the method provided by the embodiment of the present disclosure.

[0165] The above functions defined in the system / device of the embodiment of the present disclosure are performed when the computer program is executed by the processor 901. According to the embodiment of the present disclosure, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0166] In one embodiment, the computer program may be based on a tangible storage medium such as an optical storage device, a magnetic storage device, etc. In another embodiment, the computer program may also be transmitted and distributed in the form of a signal on a network medium, and downloaded and installed through the communication part 909, and / or installed from a removable medium 911. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0167] In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 909, and / or installed from the removable medium 911. When the computer program is executed by the processor 901, the above functions defined in the system of the embodiment of the present disclosure are performed. According to the embodiment of the present disclosure, the system, device, means, module, unit, etc. described above can be implemented by a computer program module.

[0168] According to an embodiment of the present disclosure, the program code for executing the computer program provided by the embodiment of the present disclosure can be written in any combination of one or more programming languages. Specifically, these computing programs can be implemented using high-level process and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, Java, C++, python, "C" language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on the remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect through the Internet).

[0169] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0170] It will be appreciated by those skilled in the art that the features described in the various embodiments of the present disclosure may be combined and / or combined in a variety of ways, even if such combinations or combinations are not explicitly described in the present disclosure. In particular, without departing from the spirit and teachings of the present disclosure, the features described in the various embodiments of the present disclosure may be combined and / or combined in a variety of ways. All of these combinations and / or combinations fall within the scope of the present disclosure.

[0171] The embodiments of the present disclosure are described above. However, these embodiments are only for the purpose of illustration, and are not intended to limit the scope of the present disclosure. Although the embodiments are described above, this does not mean that the measures in the various embodiments cannot be used in combination. Without departing from the scope of protection of the present disclosure, those skilled in the art can make a variety of alternatives and modifications, and these alternatives and modifications should all fall within the scope of protection of the present disclosure.

Claims

1. A method for determining the eligibility of a hand-filled receipt, characterized in that: include: Acquire a receipt image of a hand-filled receipt, where the hand-filled content is displayed on the receipt image; According to the acquired content to be filled in the receipt, a font library of the content to be filled in the receipt is constructed; Matching the hand-filled content with the font library to obtain a matching result; The eligibility of the hand-filled reply form is determined based on the matching result, wherein the eligibility is qualified or unqualified.

2. The method for determining the eligibility of a hand-filled receipt according to claim 1, characterized in that: The step of constructing a font library of the content to be filled in the receipt according to the acquired content to be filled in the receipt comprises: Extract m characters that should be filled in the receipt after the business is processed in the business system, wherein the m characters that should be filled in represent the contents that should be filled in the receipt, and m is an integer greater than or equal to 1; Generate k fonts for each of the characters to be filled in according to a font library built into the electronic device that executes the method for determining the eligibility of the hand-filled return form, where k is an integer greater than or equal to 1; The k fonts of each character to be filled in are stored in a database to form a font library for the content to be filled in the receipt.

3. The method for determining the eligibility of a hand-filled receipt according to claim 2, characterized in that: The step of matching the hand-filled content with the font library to obtain a matching result comprises: According to a preset segmentation sequence, the hand-filled content of the receipt image is segmented using k fonts of the characters to be filled in with the same sequence number as the segmentation sequence to obtain all actual segmentation characters of the hand-filled content; All actual segmentation characters of the hand-filled content are taken as matching results.

4. The method for determining the eligibility of a hand-filled receipt according to claim 3, characterized in that: The step of segmenting the hand-filled content of the receipt image using k fonts of the characters to be filled in with the same sequence number as the segmentation sequence according to a preset segmentation sequence to obtain all actual segmented characters of the hand-filled content includes: According to the pre-set segmentation order, the hand-filled content of the receipt image is segmented into characters to obtain n i pre-segmentation characters, where n i is an integer greater than or equal to 1, i is the sequence number of the segmentation order; When n i When it is equal to 1, the pre-segmentation character is used as the actual segmentation character; When n i When it is greater than or equal to 2, call the k fonts of the characters to be filled in with the same sequence number as the segmentation order, and calculate n respectively. i similarity between each pre-segmented character in the pre-segmented characters and the k fonts, to obtain k similarity values ​​for each pre-segmented character; Take the maximum value of the k similarity values ​​of each pre-segmented character as the middle value; Compare i The intermediate value is n i The pre-segmentation character corresponding to the maximum value among the intermediate values ​​is used as the actual segmentation character; Continue to perform character segmentation on the remaining characters of the hand-filled content except the actual segmentation characters to obtain n characters of the next segmentation order. i Pre-segmentation characters; Repeat when n i When n is equal to 1, the pre-segmentation character is used as the actual segmentation character; when n i When it is greater than or equal to 2, call the k fonts of the characters to be filled in with the same sequence number as the segmentation order, and calculate n respectively. i The step of calculating the similarity between each pre-segmented character in the pre-segmented characters and the k fonts to obtain k similarity values ​​for each pre-segmented character, until all the hand-filled content is completely segmented, and all the actual segmented characters of the hand-filled content are obtained.

5. The method for determining the eligibility of a hand-filled receipt according to claim 4, characterized in that: The step of determining the eligibility of the hand-filled receipt according to the matching result includes: When the maximum value among the k similarity values ​​of all the actually segmented characters of the hand-filled content is greater than or equal to a preset similarity threshold, the hand-filled receipt is determined to be qualified; When any maximum value among the k similarity values ​​of all actually segmented characters of the hand-filled content is smaller than a preset similarity threshold, it is determined that the hand-filled receipt is unqualified.

6. The method for determining the eligibility of a hand-filled receipt according to claim 5, characterized in that: The method for determining the eligibility of the hand-filled return form also includes: Using optical character recognition technology to convert the hand-filled content of the receipt image into g hand-filled characters, where g is an integer greater than or equal to 1; Compare the g manually filled characters with the m characters to be filled in the obtained receipt to obtain a matching conclusion, wherein the matching conclusion is passed or failed; The step of determining the eligibility of the hand-filled receipt according to the matching result includes: The eligibility of the hand-filled return slip is determined based on the matching result and the matching conclusion.

7. The method for determining the eligibility of a hand-filled receipt according to claim 6, characterized in that: The step of determining the eligibility of the hand-filled receipt according to the matching result and the matching conclusion includes: When the maximum value of the k similarity values ​​of all the actually segmented characters of the hand-filled content is greater than or equal to the preset similarity threshold, and the matching conclusion is passed, the hand-filled receipt is determined to be qualified; When the maximum value of the k similarity values ​​of all the actual segmented characters of the hand-filled content is greater than or equal to the preset similarity threshold, and the matching conclusion is failure, the hand-filled receipt is determined to be unqualified; When any maximum value among the k similarity values ​​of all actually segmented characters of the hand-filled content is smaller than a preset similarity threshold, it is determined that the hand-filled receipt is unqualified.

8. The method for determining the eligibility of a hand-filled receipt according to claim 7, characterized in that: Also includes: Return the processing measures based on the eligibility of the hand-filled return form.

9. A device for determining the eligibility of a hand-filled return form, characterized in that: include: An acquisition module, the acquisition module is used to execute acquisition of a receipt image of a hand-filled receipt, the hand-filled content being displayed on the receipt image; A construction module, the construction module is used to execute the construction of a font library of the content to be filled in the receipt according to the acquired content to be filled in the receipt; A matching module, the matching module is used to match the hand-filled content with the font library to obtain a matching result; A determination module is used to determine the eligibility of the hand-filled return form based on the matching result, wherein the eligibility is qualified or unqualified.

10. An electronic device comprising: one or more processors; a storage device for storing one or more computer programs, It is characterized in that the one or more processors execute the one or more computer programs to implement the steps of the method according to any one of claims 1 to 8.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

12. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images