Form parsing methods and related equipment

Abstract

This application discloses a form parsing method and related equipment, relating to the field of data processing technology. The form parsing method includes: acquiring multiple sets of valuation forms to be parsed and multiple target products; using current regular expression matching rules to match the multiple sets of valuation forms to be parsed with the multiple target products to obtain multiple sets of initial valuation forms with different form formats; acquiring semantic information corresponding to the form item information in the initial valuation forms; processing the initial valuation forms based on the semantic information using a preset form format processing model to obtain multiple sets of target valuation forms with the same form format; and parsing the target valuation forms to obtain the form parsing result. This application unifies the form format of the initial valuation forms based on the semantic information corresponding to the form item information. Only one valuation form parsing device is needed to complete the parsing of all valuation forms, effectively improving parsing efficiency.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to form parsing methods and related equipment. Background Technology

[0002] With the rapid development of technology, structured data storage in forms has become an important technological trend. In asset management scenarios, staff need to analyze product valuation data to more accurately assess and control product risks and returns. Valuation forms provide key indicators for product analysis, such as total assets, liabilities, net worth, and holdings. To facilitate online product management, staff use valuation form parsing devices to parse valuation forms, structure and store the data, and apply it to product analysis, thereby improving the efficiency of investment decision-making.

[0003] In existing form parsing technologies, a single valuation form parsing device can only parse some types of valuation forms. For different types of valuation forms, multiple valuation form parsing devices are required, resulting in very low parsing efficiency.

[0004] The above content is only used to help understand the technical solution of this application and does not represent an admission that the above content is prior art. Summary of the Invention

[0005] The main purpose of this application is to provide a form parsing method and related equipment, which aims to solve the technical problem that for different types of valuation forms, multiple valuation form parsing devices are required, resulting in very low parsing efficiency.

[0006] To achieve the above objectives, this application proposes a form parsing method, which includes:

[0007] Obtain multiple sets of valuation forms to be parsed, wherein the multiple sets of valuation forms to be parsed contain multiple sets of valuation forms with different form formats;

[0008] Obtain multiple target products, use the current regular expression matching rules to match the multiple sets of valuation forms to be parsed with the multiple target products, and if the match is successful, obtain multiple sets of initial valuation forms with different form formats;

[0009] Based on the form item information in the initial valuation form, semantic information corresponding to the form item information is obtained. Based on the semantic information, the initial valuation form is processed using a preset form format processing model to obtain multiple target valuation forms with the same form format. The preset form format processing model is a trained form format processing model.

[0010] The target valuation form is parsed to obtain the form parsing results.

[0011] In one embodiment, the step of obtaining multiple sets of valuation forms to be parsed further includes:

[0012] Based on the configured email address, receive multiple initial emails sent by the client, wherein the multiple initial emails contain a target email with an attachment of an valuation form;

[0013] Filter the initial emails to obtain multiple target emails;

[0014] Based on the multiple target emails, multiple sets of valuation forms to be parsed are obtained, wherein the multiple sets of valuation forms to be parsed contain multiple sets of valuation forms with different form formats.

[0015] In one embodiment, the step of using the current regular expression matching rule to match the multiple sets of valuation forms to be parsed with the multiple target products, and obtaining multiple sets of initial valuation forms with different form formats if the matching is successful, further includes:

[0016] Acquire multiple target products and determine the first name of the file corresponding to the valuation form and the second name of the target product;

[0017] Based on the first name, the second name, and the current orthogonal matching rule, multiple sets of valuation forms to be parsed are matched with multiple target products;

[0018] If the matching fails, modify the current orthogonal matching rule and return to the step of matching multiple sets of valuation forms to be parsed with multiple target products based on the first name, the second name and the current orthogonal matching rule, until multiple sets of valuation forms to be parsed are successfully matched with multiple target products. Set the successfully matched valuation form as the initial valuation form, wherein the initial valuation form includes multiple types of valuation forms.

[0019] If a match is successful, multiple initial valuation forms with different formats will be obtained.

[0020] In one embodiment, the step of parsing the target valuation form to obtain the form parsing result further includes:

[0021] Identify the header of the target valuation form;

[0022] Based on the header, determine the product information corresponding to the target valuation form, and determine the asset type to which the holding asset item in the target valuation form belongs;

[0023] Based on the asset type, the asset code in the target valuation form is verified to obtain a first verification result;

[0024] Based on the first verification result, the asset type, and the product information, the form parsing result is determined.

[0025] In one embodiment, the step of determining the form parsing result based on the first verification result, the asset type, and the product information further includes:

[0026] Obtain the disclosure frequency corresponding to the target valuation form;

[0027] Based on the disclosure frequency, product verification conditions are obtained, including but not limited to product disclosure density, delay days, holding ratio, and net asset value.

[0028] Based on the product inspection conditions and the disclosure frequency, the asset type and the product information are verified to obtain a second verification result.

[0029] Based on the first verification result, the second verification result, the asset type, and the product information, the form parsing result is determined.

[0030] In one embodiment, before the step of processing the initial valuation form using a preset form format processing model to obtain multiple sets of target valuation forms with the same form format, the method further includes:

[0031] Obtain the sample valuation form and the current form format processing model, wherein the target valuation form corresponding to the sample valuation form is the second valuation form;

[0032] Based on the current form format processing model, the sample valuation form is processed to obtain the first valuation form;

[0033] Determine whether the first valuation form and the second valuation form are the same;

[0034] If they are different, adjust the parameters of the current form format processing model;

[0035] Based on the current form format processing model after parameter adjustment, the process returns to the step of processing the sample valuation form based on the current form format processing model to obtain the first valuation form, until the first valuation form is the same as the second valuation form, and then the current form format processing model is set to the preset form format processing model.

[0036] Furthermore, to achieve the above objectives, this application also proposes a form parsing apparatus, which includes:

[0037] The acquisition module is used to acquire multiple sets of valuation forms to be parsed, wherein the multiple sets of valuation forms to be parsed include multiple sets of valuation forms with different form formats.

[0038] The matching module is used to obtain multiple target products, use the current regular expression matching rules to match the multiple sets of valuation forms to be parsed with the multiple target products, and if the matching is successful, obtain multiple sets of initial valuation forms with different form formats.

[0039] The form processing module is used to obtain semantic information corresponding to the form item information in the initial valuation form, and to process the initial valuation form using a preset form format processing model based on the semantic information to obtain multiple target valuation forms with the same form format. The preset form format processing model is a trained form format processing model.

[0040] The parsing module is used to parse the target valuation form and obtain the form parsing result.

[0041] In one embodiment, the acquisition module includes:

[0042] The receiving unit is configured to receive multiple initial emails sent by the client based on the configured email address, wherein the multiple initial emails include a target email with an attachment of an valuation form.

[0043] A filtering unit is used to filter the multiple initial emails to obtain multiple target emails;

[0044] The first acquisition unit is used to obtain multiple sets of valuation forms to be parsed based on the multiple target emails, wherein the multiple sets of valuation forms to be parsed include multiple sets of valuation forms with different form formats.

[0045] In one embodiment, the matching module includes:

[0046] The second acquisition unit is used to acquire multiple target products and determine the first name of the file corresponding to the valuation form and the second name of the target product.

[0047] The matching unit is used to match multiple sets of valuation forms to be parsed with multiple target products based on the first name, the second name and the current orthogonal matching rule;

[0048] If the matching fails, the setting unit modifies the current orthogonal matching rule and returns to the step of matching multiple sets of valuation forms to be parsed with multiple target products based on the first name, the second name and the current orthogonal matching rule, until multiple sets of valuation forms to be parsed are successfully matched with multiple target products. The successfully matched valuation forms are set as the initial valuation forms, wherein the initial valuation forms include multiple types of valuation forms.

[0049] The third acquisition module, if a match is successful, obtains multiple sets of initial valuation forms in different form formats.

[0050] In one embodiment, the parsing module includes:

[0051] An identification unit is used to identify the header of the target valuation form;

[0052] The first determining unit is used to determine the product information corresponding to the target valuation form based on the header, and to determine the asset type to which the holding asset item in the target valuation form belongs;

[0053] The first verification unit is used to verify the asset code in the target valuation form based on the asset type and obtain a first verification result;

[0054] The second determining unit is used to determine the form parsing result based on the first verification result, the asset type, and the product information.

[0055] In one embodiment, the parsing module further includes:

[0056] The fourth acquisition unit is used to acquire the disclosure frequency corresponding to the target valuation form;

[0057] The setting unit is used to obtain product verification conditions based on the disclosure frequency, wherein the product verification conditions include, but are not limited to, product disclosure density, delay days, holding ratio, and net value;

[0058] The second verification unit is used to verify the asset type and the product information based on the product inspection conditions and the disclosure frequency, and obtain a second verification result.

[0059] The third determining unit is used to determine the form parsing result based on the first verification result, the second verification result, the asset type, and the product information.

[0060] In one embodiment, the form processing module includes:

[0061] The fifth acquisition unit is used to acquire the sample valuation form and the current form format processing model, wherein the target valuation form corresponding to the sample valuation form is the second valuation form;

[0062] The form processing unit is used to process the sample valuation form based on the current form format processing model to obtain the first valuation form;

[0063] A judgment unit is used to determine whether the first valuation form and the second valuation form are the same;

[0064] If the adjustment units are different, then adjust the parameters of the current form format processing model;

[0065] The training unit is used to return a step of processing the sample valuation form based on the current form format processing model after adjusting the parameters, and obtaining a first valuation form, until the first valuation form is the same as the second valuation form, and then setting the current form format processing model to the preset form format processing model.

[0066] In addition, to achieve the above objectives, this application also proposes a form parsing device, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the form parsing method as described above.

[0067] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and which, when executed by a processor, implements the steps of the form parsing method described above.

[0068] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the form parsing method described above.

[0069] One or more technical solutions proposed in this application have at least the following technical effects:

[0070] This application proposes an inference calculation method and related equipment. In related technologies, a single valuation form parsing device can only parse some types of valuation forms. For different types of valuation forms, multiple valuation form parsing devices are required, resulting in low parsing efficiency. In this application, firstly, multiple sets of valuation forms to be parsed are obtained, wherein the multiple sets of valuation forms to be parsed contain multiple sets of valuation forms with different form formats. Then, multiple target products are obtained, and the multiple sets of valuation forms to be parsed are matched with the multiple target products using the current regular expression matching rules. If the matching is successful, multiple sets of initial valuation forms with different form formats are obtained. Further, based on the form item information in the initial valuation forms, the semantic information corresponding to the form item information is obtained. Based on the semantic information, a preset form format processing model is used to process the initial valuation forms to obtain multiple sets of target valuation forms with the same form format. The preset form format processing model is a trained form format processing model. Finally, the target valuation forms are parsed to obtain the form parsing result.

[0071] Understandably, in related technologies, form parsing devices need to use different types of form parsing apparatuses to parse forms with different formats, which consumes a lot of time and results in low parsing efficiency. However, in this application, based on the semantic information corresponding to the form item information, the form format of the initial valuation form is standardized to obtain multiple sets of target valuation forms with the same format. Therefore, the form parsing device only needs to use one valuation form parsing apparatus to parse all valuation forms, effectively improving parsing efficiency. Attached Figure Description

[0072] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0073] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0074] Figure 1 This is a flowchart illustrating an embodiment of the form parsing method in this application.

[0075] Figure 2 This is a schematic diagram of the form parsing process provided in Embodiment 1 of the form parsing method of this application;

[0076] Figure 3 This is a flowchart illustrating Embodiment 2 of the form parsing method in this application.

[0077] Figure 4 This is a schematic diagram of the module structure of the form parsing device according to an embodiment of this application;

[0078] Figure 5 This is a schematic diagram of the device structure of the hardware operating environment involved in the form parsing method in this application embodiment.

[0079] The purpose, features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0080] It should be understood that the specific embodiments described herein are merely used to explain the technical solutions of the present application and are not intended to limit the present application.

[0081] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0082] The main solution in this application's embodiments is:

[0083] In this embodiment, for ease of description, the form parsing device will be used as the execution subject in the following description.

[0084] Because existing technologies require multiple valuation form parsing devices to address different types of valuation forms, the parsing efficiency is very low.

[0085] This application provides a solution in which: first, multiple sets of valuation forms to be parsed are obtained, wherein the multiple sets of valuation forms to be parsed contain multiple sets of valuation forms with different form formats; then, multiple target products are obtained, and the multiple sets of valuation forms to be parsed are matched with the multiple target products using the current regular expression matching rules; if the match is successful, multiple sets of initial valuation forms with different form formats are obtained; further, based on the form item information in the initial valuation forms, semantic information corresponding to the form item information is obtained; based on the semantic information, a preset form format processing model is used to process the initial valuation forms to obtain multiple sets of target valuation forms with the same form format, wherein the preset form format processing model is a trained form format processing model; finally, the target valuation forms are parsed to obtain the form parsing results.

[0086] Understandably, in related technologies, form parsing devices need to use different types of form parsing apparatuses to parse forms with different formats, which consumes a lot of time and results in low parsing efficiency. However, in this application, based on the semantic information corresponding to the form item information, the form format of the initial valuation form is standardized to obtain multiple sets of target valuation forms with the same format. Therefore, the form parsing device only needs to use one valuation form parsing apparatus to parse all valuation forms, effectively improving parsing efficiency.

[0087] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or an electronic device or form parsing device capable of performing the above functions. The following description uses a form parsing device as an example to illustrate this embodiment and the subsequent embodiments.

[0088] Based on this, this application provides a form parsing method, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the form parsing method of this application.

[0089] In this embodiment, the form parsing method includes steps S100 to S400:

[0090] Step S100: Obtain multiple sets of valuation forms to be parsed, wherein the multiple sets of valuation forms to be parsed include multiple sets of valuation forms with different form formats;

[0091] In this embodiment, the execution entity is a form parsing device, which can be a computing service device with data processing, network communication and program execution functions, such as a tablet computer, personal computer, mobile phone, etc., or an electronic device capable of performing the above functions.

[0092] In this embodiment, reference can be made to Figure 2 , Figure 2 This is a diagram illustrating the form parsing process. Specific application scenarios could include:

[0093] Given a valuation form to be parsed, the staff needs to parse the form by clicking the "parse" button. After detecting this, the form parsing device reads the valuation form from memory.

[0094] Specifically, the step of obtaining multiple sets of valuation forms to be parsed further includes steps S110 to S130:

[0095] Step S110: Based on the configured email address, receive multiple initial emails sent by the client, wherein the multiple initial emails include a target email with an attachment of an valuation form.

[0096] Understandably, the valuation form is transmitted as an email attachment. That is, the form parsing device receives emails with the valuation form as an attachment sent by the client, based on the configured email address.

[0097] The configured email address refers to the email address and user information that have been set up. Furthermore, for different types of products, dedicated email addresses can be set up to manage emails related to those products.

[0098] Step S120: Filter the multiple initial emails to obtain multiple target emails;

[0099] Understandably, the form parsing device is based on a configured email address and receives emails of various types. Among the received emails, only some may have valuation forms attached.

[0100] In this embodiment, the filtering of the multiple initial emails is based on a blacklist word library, an ignore word library, and other similar word libraries. These word libraries are pre-set by staff. The form parsing device uses these word libraries to identify invalid emails (emails that do not contain valuation forms) among the multiple initial emails. Therefore, the form parsing device obtains multiple target emails containing valuation forms.

[0101] Step S130: Based on the multiple target emails, obtain multiple sets of valuation forms to be parsed, wherein the multiple sets of valuation forms to be parsed include multiple sets of valuation forms with different form formats.

[0102] In this embodiment, after the form parsing device obtains multiple target emails, the form parsing device retrieves multiple sets of valuation forms to be parsed from the multiple target emails and stores the multiple sets of valuation forms to be parsed in memory.

[0103] Step S200: Obtain multiple target products, use the current regular expression matching rules to match the multiple sets of valuation forms to be parsed with the multiple target products, and if the matching is successful, obtain multiple sets of initial valuation forms with different form formats.

[0104] It should be noted that the valuation form is related to the target product. The valuation form provides key indicators such as the target product's total assets, liabilities, net worth, and holdings. These key indicators are used to analyze the target product.

[0105] Additionally, it's important to note that regular expression matching rules refer to the process of using regular expressions to determine whether a string conforms to a certain pattern. A regular expression is a text pattern that includes ordinary characters (such as letters from a to z) and special characters (called "metacharacters"). It is typically used to search for and replace text that matches a certain pattern. Regular expressions use a single string to describe a series of strings that conform to a certain syntax rule. When performing regular expression matching, the `match` function is usually used to determine whether a string matches a specific pattern. For example, in Python, the `re.match` function can be used to determine if a string begins with a specific pattern. If a match is successful, the `match` function returns a match object.

[0106] Understandably, based on the current regular expression matching rules, the table parsing device reads the form names of multiple sets of valuation forms to be parsed from memory, matches the form names with the names of the target products, and determines the target product corresponding to the parsed valuation form. If a match is successful, the successfully matched form is set as the initial valuation form.

[0107] Specifically, the step of using the current regular expression matching rules to match the multiple sets of valuation forms to be parsed with the multiple target products, and obtaining multiple sets of initial valuation forms with different form formats if the matching is successful, further includes steps S210 to S240:

[0108] Step S210: Obtain multiple target products and determine the first name of the file corresponding to the valuation form and the second name of the target product;

[0109] It should be noted that the first name is the name of the valuation form to be parsed.

[0110] Step S220: Based on the first name, the second name and the current orthogonal matching rule, match multiple sets of valuation forms to be parsed with multiple target products;

[0111] Step S230: If the matching fails, modify the current orthogonal matching rule and return to the step of matching multiple sets of valuation forms to be parsed with multiple target products based on the first name, the second name and the current orthogonal matching rule, until multiple sets of valuation forms to be parsed are successfully matched with multiple target products. Set the successfully matched valuation forms as the initial valuation forms, wherein the initial valuation forms include multiple types of valuation forms.

[0112] It should be noted that in this application, the orthogonal matching rule is constantly changing. The multiple sets of valuation forms to be parsed are matched with the multiple target products. If there are valuation forms to be parsed that are not matched successfully, the current orthogonal matching rule is adjusted. Based on the adjusted current orthogonal matching rule, the valuation forms to be parsed that are not matched successfully are rematched until all valuation forms to be parsed are matched successfully.

[0113] It is understood that, in this embodiment, when adjusting the current orthogonal matching rules, only the matching rules associated with the valuation forms to be parsed that failed to match need to be adjusted. The current orthogonal matching rules include various types of matching rules.

[0114] Step S240: If the matching is successful, obtain multiple sets of initial valuation forms with different form formats.

[0115] In this embodiment, the form that is successfully matched is set as the initial valuation form.

[0116] Understandably, since the target emails come from different clients, the form formats of the valuation forms to be parsed are different, and consequently, the form formats of multiple initial valuation forms are also different.

[0117] Step S300: Based on the form item information in the initial valuation form, obtain the semantic information corresponding to the form item information; based on the semantic information, use a preset form format processing model to process the initial valuation form to obtain multiple sets of target valuation forms with the same form format, wherein the preset form format processing model is a trained form format processing model.

[0118] It should be noted that the preset form format processing model is a pre-trained form format processing model. This model is used to modify the format of the input form and output a form with the target format.

[0119] It should also be noted that before modifying the format of the initial valuation form, it is necessary to obtain the form item information corresponding to each piece of data in the form, and then determine the semantic information corresponding to each piece of data in the form. Based on the semantic information, a preset form format processing model is used to modify the format of the initial valuation form to obtain the target valuation form. Specifically, the form parsing device stores the data from the initial valuation form into form items in the target valuation form whose semantic information is similar to that of the data pieces.

[0120] Step S400: Parse the target valuation form to obtain the form parsing result.

[0121] Finally, the form parsing device parses multiple sets of target valuation forms with a uniform form format to obtain the form parsing results. These results include the asset type of the target product, the product information of the target product, and the verification results of the product information.

[0122] Specifically, the step of parsing the target valuation form to obtain the form parsing result further includes steps S410 to S440:

[0123] Step S410: Identify the header of the target valuation form;

[0124] It should be noted that the header refers to the form item information in the target valuation form.

[0125] Step S420: Based on the header, determine the product information corresponding to the target valuation form, and determine the asset type to which the holding asset item in the target valuation form belongs;

[0126] In this embodiment, after the form parsing device identifies the header of the target valuation form, based on the header, the form parsing device determines the product information corresponding to the target valuation form and determines the asset type to which the holding asset item in the target valuation form belongs;

[0127] Step S430: Based on the asset type, verify the asset code in the target valuation form to obtain a first verification result;

[0128] In this embodiment, after the form parsing device determines the asset type and product information, the form parsing device verifies the asset code in the target valuation form and obtains a first verification result.

[0129] For example, if the asset "603197" is identified as a Shanghai Stock Exchange A-share based on the asset holdings account, then the holdings of this code are verified in the public stock market data to obtain the first verification result.

[0130] Step S440: Based on the first verification result, the asset type, and the product information, determine the form parsing result.

[0131] Specifically, the step of determining the form parsing result based on the first verification result, the asset type, and the product information further includes steps S441 to S444:

[0132] Step S441: Obtain the disclosure frequency corresponding to the target valuation form;

[0133] It should be noted that disclosure frequency refers to the frequency at which the initial valuation form for the same target product is provided.

[0134] Step S442: Based on the disclosure frequency, obtain product verification conditions, wherein the product verification conditions include, but are not limited to, product disclosure density, delay days, holding ratio, and net asset value.

[0135] It should be noted that the product inspection conditions are set in advance by the staff. Taking the holding ratio as an example, if the holding ratio information obtained from the target valuation form is within the preset ratio threshold range, the inspection result is that the data is normal, and this verification result is the second verification result.

[0136] Step S443: Based on the product inspection conditions and the disclosure frequency, verify the asset type and the product information to obtain a second verification result;

[0137] For example, if the disclosure frequency is 1 hour, and the holding ratio is verified, it is determined whether the change in the holding ratio within one hour is within the preset ratio threshold range, and a second verification result is obtained.

[0138] Step S444: Based on the first verification result, the second verification result, the asset type, and the product information, determine the form parsing result.

[0139] One or more technical solutions proposed in this application have at least the following technical effects:

[0140] This application proposes an inference calculation method and related equipment. In related technologies, a single valuation form parsing device can only parse some types of valuation forms. For different types of valuation forms, multiple valuation form parsing devices are required, resulting in low parsing efficiency. In this application, firstly, multiple sets of valuation forms to be parsed are obtained, wherein the multiple sets of valuation forms to be parsed contain multiple sets of valuation forms with different form formats. Then, multiple target products are obtained, and the multiple sets of valuation forms to be parsed are matched with the multiple target products using the current regular expression matching rules. If the matching is successful, multiple sets of initial valuation forms with different form formats are obtained. Further, based on the form item information in the initial valuation forms, the semantic information corresponding to the form item information is obtained. Based on the semantic information, a preset form format processing model is used to process the initial valuation forms to obtain multiple sets of target valuation forms with the same form format. The preset form format processing model is a trained form format processing model. Finally, the target valuation forms are parsed to obtain the form parsing result.

[0141] Understandably, in related technologies, form parsing devices need to use different types of form parsing apparatuses to parse forms with different formats, which consumes a lot of time and results in low parsing efficiency. However, in this application, based on the semantic information corresponding to the form item information, the form format of the initial valuation form is standardized to obtain multiple sets of target valuation forms with the same format. Therefore, the form parsing device only needs to use one valuation form parsing apparatus to parse all valuation forms, effectively improving parsing efficiency.

[0142] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in the first embodiment described above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 2 Before step S300, the form parsing method further includes steps S310 to S350:

[0143] Step S310: Obtain the sample valuation form and the current form format processing model, wherein the target valuation form corresponding to the sample valuation form is the second valuation form;

[0144] It should be noted that the sample valuation form is used to train the current form format processing model.

[0145] Step S320: Based on the current form format processing model, process the sample valuation form to obtain the first valuation form;

[0146] Understandably, the first valuation form is the result obtained by the current form format processing model after processing the sample valuation form, while the second valuation form is the actual target valuation form. There may be differences between the first and second valuation forms. Therefore, if there are differences, the current form format processing model will be trained.

[0147] Step S330: Determine whether the first valuation form and the second valuation form are the same;

[0148] Step S340: If they are not the same, adjust the parameters of the current form format processing model;

[0149] Step S350: Based on the current form format processing model after parameter adjustment, return to the step of processing the sample valuation form based on the current form format processing model to obtain the first valuation form, until the first valuation form is the same as the second valuation form, and set the current form format processing model to the preset form format processing model.

[0150] In this embodiment, the form format processing model is trained based on the sample valuation form, which effectively improves the reliability of the target valuation form.

[0151] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the form parsing method of this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0152] This application also provides a form parsing device; please refer to [reference needed]. Figure 4 The form parsing device includes:

[0153] The acquisition module 10 is used to acquire multiple sets of valuation forms to be parsed, wherein the multiple sets of valuation forms to be parsed include multiple sets of valuation forms with different form formats.

[0154] Matching module 20 is used to obtain multiple target products, use the current regular expression matching rules to match the multiple sets of valuation forms to be parsed with the multiple target products, and if the matching is successful, obtain multiple sets of initial valuation forms with different form formats.

[0155] The form processing module 30 is used to obtain semantic information corresponding to the form item information in the initial valuation form based on the form item information in the initial valuation form, and to process the initial valuation form using a preset form format processing model based on the semantic information to obtain multiple sets of target valuation forms with the same form format. The preset form format processing model is a trained form format processing model.

[0156] Parsing module 40, the form parsing module is used to parse the target valuation form and obtain the form parsing result.

[0157] In one embodiment, the acquisition module includes:

[0158] The receiving unit is configured to receive multiple initial emails sent by the client based on the configured email address, wherein the multiple initial emails include a target email with an attachment of an valuation form.

[0159] A filtering unit is used to filter the multiple initial emails to obtain multiple target emails;

[0160] The first acquisition unit is used to obtain multiple sets of valuation forms to be parsed based on the multiple target emails, wherein the multiple sets of valuation forms to be parsed include multiple sets of valuation forms with different form formats.

[0161] In one embodiment, the matching module includes:

[0162] The second acquisition unit is used to acquire multiple target products and determine the first name of the file corresponding to the valuation form and the second name of the target product.

[0163] The matching unit is used to match multiple sets of valuation forms to be parsed with multiple target products based on the first name, the second name and the current orthogonal matching rule;

[0164] If the matching fails, the setting unit modifies the current orthogonal matching rule and returns to the step of matching multiple sets of valuation forms to be parsed with multiple target products based on the first name, the second name and the current orthogonal matching rule, until multiple sets of valuation forms to be parsed are successfully matched with multiple target products. The successfully matched valuation forms are set as the initial valuation forms, wherein the initial valuation forms include multiple types of valuation forms.

[0165] The third acquisition module, if a match is successful, obtains multiple sets of initial valuation forms in different form formats.

[0166] In one embodiment, the parsing module includes:

[0167] An identification unit is used to identify the header of the target valuation form;

[0168] The first determining unit is used to determine the product information corresponding to the target valuation form based on the header, and to determine the asset type to which the holding asset item in the target valuation form belongs;

[0169] The first verification unit is used to verify the asset code in the target valuation form based on the asset type and obtain a first verification result;

[0170] The second determining unit is used to determine the form parsing result based on the first verification result, the asset type, and the product information.

[0171] In one embodiment, the parsing module further includes:

[0172] The fourth acquisition unit is used to acquire the disclosure frequency corresponding to the target valuation form;

[0173] The setting unit is used to obtain product verification conditions based on the disclosure frequency, wherein the product verification conditions include, but are not limited to, product disclosure density, delay days, holding ratio, and net value;

[0174] The second verification unit is used to verify the asset type and the product information based on the product inspection conditions and the disclosure frequency, and obtain a second verification result.

[0175] The third determining unit is used to determine the form parsing result based on the first verification result, the second verification result, the asset type, and the product information.

[0176] In one embodiment, the form processing module includes:

[0177] The fifth acquisition unit is used to acquire the sample valuation form and the current form format processing model, wherein the target valuation form corresponding to the sample valuation form is the second valuation form;

[0178] The form processing unit is used to process the sample valuation form based on the current form format processing model to obtain the first valuation form;

[0179] A judgment unit is used to determine whether the first valuation form and the second valuation form are the same;

[0180] If the adjustment units are different, then adjust the parameters of the current form format processing model;

[0181] The training unit is used to return a step of processing the sample valuation form based on the current form format processing model after adjusting the parameters, and obtaining a first valuation form, until the first valuation form is the same as the second valuation form, and then setting the current form format processing model to the preset form format processing model.

[0182] The form parsing apparatus provided in this application, employing the form parsing method described in the above embodiments, can solve the technical problem of form parsing. Compared with the prior art, the beneficial effects of the form parsing apparatus provided in this application are the same as those of the form parsing method provided in the above embodiments, and other technical features in the form parsing apparatus are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0183] This application provides a form parsing device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, which are executed by the at least one processor to enable the at least one processor to perform the form parsing method in Embodiment 1 above.

[0184] The following is for reference. Figure 5 The diagram illustrates a structural schematic of a form parsing device suitable for implementing embodiments of this application. The form parsing device in these embodiments may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 5 The form parsing device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0185] like Figure 5As shown, the form parsing device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.) that can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the form parsing device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, magnetic tape, hard disk, etc.; and communication devices 1009. Communication device 1009 allows the form parsing device to communicate wirelessly or wiredly with other devices to exchange data. While the figures show form parsing devices with various systems, it should be understood that implementation or possession of all the systems shown is not required. More or fewer systems may be implemented alternatively.

[0186] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0187] The form parsing device provided in this application, employing the form parsing method described in the above embodiments, can solve the technical problem of form parsing. Compared with the prior art, the beneficial effects of the form parsing device provided in this application are the same as those of the form parsing method provided in the above embodiments, and other technical features of this form parsing device are the same as those disclosed in the method of the previous embodiment, and will not be repeated here.

[0188] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0189] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0190] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the form parsing method in the above embodiments.

[0191] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0192] The aforementioned computer-readable storage medium may be included in the form parsing device; or it may exist independently and not be assembled into the form parsing device.

[0193] The aforementioned computer-readable storage medium carries one or more programs that, when executed by the form parsing device, cause the form parsing device to:

[0194] Obtain multiple sets of valuation forms to be parsed, wherein the multiple sets of valuation forms to be parsed contain multiple sets of valuation forms with different form formats;

[0195] Obtain multiple target products, use the current regular expression matching rules to match the multiple sets of valuation forms to be parsed with the multiple target products, and if the match is successful, obtain multiple sets of initial valuation forms with different form formats;

[0196] Based on the form item information in the initial valuation form, semantic information corresponding to the form item information is obtained. Based on the semantic information, the initial valuation form is processed using a preset form format processing model to obtain multiple target valuation forms with the same form format. The preset form format processing model is a trained form format processing model.

[0197] The target valuation form is parsed to obtain the form parsing results.

[0198] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0199] 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 application. In this regard, each box in the flow chart or block diagram can represent a module, program segment or a part of code, and the module, program segment or a part of 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 than that 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 and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a combination of dedicated hardware and computer instructions.

[0200] The modules described in the embodiments of the present application may be implemented in software or hardware, wherein the name of a module does not necessarily limit the unit itself.

[0201] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described form parsing method, thereby solving the technical problem of form parsing. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the form parsing method provided in the above embodiments, and will not be repeated here.

[0202] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the form parsing method described above.

[0203] The computer program product provided in this application can solve the technical problem of form parsing. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as the beneficial effects of the form parsing method provided in the above embodiments, and will not be repeated here.

[0204] The above description is only part of the embodiments of the present application and does not limit the patent scope of the present application. All equivalent structural transformations made by using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect application in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A form parsing method, characterized in that, The form parsing method includes: Obtain multiple sets of valuation forms to be parsed, wherein the multiple sets of valuation forms to be parsed contain multiple sets of valuation forms with different form formats; Obtain multiple target products, use the current regular expression matching rules to match the multiple sets of valuation forms to be parsed with the multiple target products, and if the match is successful, obtain multiple sets of initial valuation forms with different form formats; Based on the form item information in the initial valuation form, semantic information corresponding to the form item information is obtained. Based on the semantic information, the initial valuation form is processed using a preset form format processing model to obtain multiple target valuation forms with the same form format. The preset form format processing model is a trained form format processing model. The target valuation form is parsed to obtain the form parsing results; The step of parsing the target valuation form to obtain the form parsing result further includes: Identify the header of the target valuation form; Based on the header, determine the product information corresponding to the target valuation form, and determine the asset type to which the holding asset item in the target valuation form belongs; Based on the asset type, the asset code in the target valuation form is verified to obtain a first verification result; Based on the first verification result, the asset type, and the product information, the form parsing result is determined; The step of determining the form parsing result based on the first verification result, the asset type, and the product information further includes: Obtain the disclosure frequency corresponding to the target valuation form; Based on the disclosure frequency, product verification conditions are obtained, wherein the product verification conditions include product disclosure density, delay days, holding ratio, and net asset value. Based on the product verification conditions and the disclosure frequency, the asset type and the product information are verified to obtain a second verification result. Based on the first verification result, the second verification result, the asset type, and the product information, the form parsing result is determined.

2. The form parsing method as described in claim 1, characterized in that, The step of obtaining multiple sets of valuation forms to be parsed also includes: Based on the configured email address, receive multiple initial emails sent by the client, wherein the multiple initial emails contain a target email with an attachment of an valuation form; Filter the initial emails to obtain multiple target emails; Based on the multiple target emails, multiple sets of valuation forms to be parsed are obtained, wherein the multiple sets of valuation forms to be parsed contain multiple sets of valuation forms with different form formats.

3. The form parsing method as described in claim 1, characterized in that, The step of using the current regular expression matching rules to match the multiple sets of valuation forms to be parsed with the multiple target products, and obtaining multiple sets of initial valuation forms with different form formats if the match is successful, further includes: Acquire multiple target products and determine the first name of the file corresponding to the valuation form and the second name of the target product; Based on the first name, the second name, and the current orthogonal matching rule, multiple sets of valuation forms to be parsed are matched with multiple target products; If the matching fails, modify the current orthogonal matching rule and return to the step of matching multiple sets of valuation forms to be parsed with multiple target products based on the first name, the second name and the current orthogonal matching rule, until multiple sets of valuation forms to be parsed are successfully matched with multiple target products. Set the successfully matched valuation form as the initial valuation form, wherein the initial valuation form includes multiple types of valuation forms. If a match is successful, multiple initial valuation forms with different formats will be obtained.

4. The form parsing method as described in claim 1, characterized in that, Before the step of processing the initial valuation form using a preset form format processing model to obtain multiple sets of target valuation forms with the same form format, the method further includes: Obtain the sample valuation form and the current form format processing model, wherein the target valuation form corresponding to the sample valuation form is the second valuation form; Based on the current form format processing model, the sample valuation form is processed to obtain the first valuation form; Determine whether the first valuation form and the second valuation form are the same; If they are different, adjust the parameters of the current form format processing model; Based on the current form format processing model after parameter adjustment, the process returns to the step of processing the sample valuation form based on the current form format processing model to obtain the first valuation form, until the first valuation form is the same as the second valuation form, and then the current form format processing model is set to the preset form format processing model.

5. A form parsing device, characterized in that, The form parsing device includes: The acquisition module is used to acquire multiple sets of valuation forms to be parsed, wherein the multiple sets of valuation forms to be parsed include multiple sets of valuation forms with different form formats. The matching module is used to obtain multiple target products, use the current regular expression matching rules to match the multiple sets of valuation forms to be parsed with the multiple target products, and if the matching is successful, obtain multiple sets of initial valuation forms with different form formats. The form processing module is used to obtain semantic information corresponding to the form item information in the initial valuation form, and to process the initial valuation form using a preset form format processing model based on the semantic information to obtain multiple target valuation forms with the same form format. The preset form format processing model is a trained form format processing model. The parsing module, specifically the form parsing module, is used to parse the target valuation form and obtain the form parsing result. The parsing module is also used to implement: Identify the header of the target valuation form; Based on the header, determine the product information corresponding to the target valuation form, and determine the asset type to which the holding asset item in the target valuation form belongs; Based on the asset type, the asset code in the target valuation form is verified to obtain a first verification result; Based on the first verification result, the asset type, and the product information, the form parsing result is determined; The parsing module is also used to implement: Obtain the disclosure frequency corresponding to the target valuation form; Based on the disclosure frequency, product verification conditions are obtained, wherein the product verification conditions include product disclosure density, delay days, holding ratio, and net asset value. Based on the product verification conditions and the disclosure frequency, the asset type and the product information are verified to obtain a second verification result. Based on the first verification result, the second verification result, the asset type, and the product information, the form parsing result is determined.

6. A form parsing device, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the form parsing method as described in any one of claims 1 to 4.

7. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the form parsing method as described in any one of claims 1 to 4.

8. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the steps of the form parsing method as described in any one of claims 1 to 4.

Images