Information processing method, device, and program product

Abstract

Embodiments of the present disclosure relate to an information processing method, device and program product, wherein the method comprises: determining a target region in a first page, and obtaining document object model information corresponding to the target region; wherein the first page is a page for inputting form information; determining target input information corresponding to the target region based on the document object model information; obtaining target form text corresponding to the target region; comparing whether key information in the target input information and the target form text is consistent to obtain a comparison result; wherein the key information is information in the target form text corresponding to the target input information. Embodiments of the present disclosure can more efficiently and reliably obtain a comparison result, and effectively save labor costs.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of information processing, and in particular, to an information processing method, device and program product. BACKGROUND

[0002] A user can directly input personalized information related to a form, such as identity information, cooperation information, etc., on an electronic form, and then generate an actual form text on this basis, the form can be any page that needs to be filled in by the user, such as a contract, a work order, etc. However, there can be content difference between the information input by the user and the actual form text, such as the cooperation area input by the user online is a nationwide area, but the cooperation area displayed on the actual form text is a specific area, that is, the actual form text generated can not be accurate. In the related art, whether the actual generated form and the information input by the user are consistent is mainly compared in an artificial manner, which is time-consuming and laborious, and requires a high labor cost. SUMMARY

[0003] In order to solve the above technical problems or at least partially solve the above technical problems, the present disclosure provides an information processing method, device and program product.

[0004] The embodiment of the present disclosure provides an information processing method, which comprises: determining a target area in a first page, and acquiring document object model information corresponding to the target area; wherein the first page is a page for inputting form information; determining target input information corresponding to the target area based on the document object model information; acquiring target form text corresponding to the target area; comparing whether key information in the target input information and the target form text is consistent to obtain a comparison result; wherein the key information is information in the target form text corresponding to the target input information.

[0005] Optionally, the determining the target input information corresponding to the target area based on the document object model information comprises: inputting the document object model information into a preset first language model, and extracting the target input information corresponding to the target area from the document object model information through the first language model.

[0006] Optionally, the inputting the document object model information into a preset first language model comprises: in the case that the number of the target areas is multiple, splicing the document object model information corresponding to the multiple target areas to obtain an information splicing result; and inputting the information splicing result into a preset first language model.

[0007] Optionally, the acquiring the target form text corresponding to the target area comprises: generating the target form text corresponding to the target area based on the target input information and a preset form template.

[0008] Optionally, the determining whether the target input information is consistent with the key information in the target form text includes: inputting the target input information and the target form text into a preset second language model, determining, by the second language model, the key information in the target form text corresponding to the target input information, and determining whether the target input information is consistent with the key information to obtain the comparison result.

[0009] Optionally, the method further includes: displaying the target input information, the target form text, and the comparison result in a second page.

[0010] Optionally, the method further includes: in a case where the comparison result indicates that the target input information is inconsistent with the key information in the target form text, displaying a correction suggestion for the key information in the target form text in the second page.

[0011] Optionally, the determining the target region in the first page includes: in response to a region framing operation on the first page, determining a region corresponding to the region framing operation, and taking the region corresponding to the region framing operation as the target region in the first page.

[0012] Optionally, the obtaining the document object model information corresponding to the target region includes: obtaining the document object model information corresponding to the target region by a preset plug-in.

[0013] Optionally, the method further includes: in a case where the comparison result indicates that the target input information is inconsistent with the key information in the target form text, correcting the key information in the target form text based on the target input information; and in a case where the comparison result indicates that the target input information is consistent with the key information in the target form text, generating a final form text based on the target form text.

[0014] The embodiments of the present disclosure further provide an electronic device, including: a processor; a memory for storing executable instructions of the processor; and the processor is configured to read the executable instructions from the memory and execute the instructions to implement the information processing method provided by the embodiments of the present disclosure.

[0015] The embodiments of the present disclosure further provide a computer program product, including a computer program, which, when executed by a processor, implements the information processing method provided by the embodiments of the present disclosure.

[0016] The technical solution provided by the embodiments of the present disclosure can first determine a target region in a first page, and obtain document object model information corresponding to the target region, so that the target input information corresponding to the target region is quickly and accurately parsed based on the document object model information. On the basis of obtaining the target form text corresponding to the target region, the key information of the target input information and the target form text can be automatically compared. Compared with the manual comparison mode, the comparison result can be obtained more efficiently and reliably, and the labor cost can be effectively saved.

[0017] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it used to limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0018] The accompanying drawings, which are incorporated into and form part of the specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure or the prior art, the drawings needed to be used in the embodiments or the prior art description will be briefly introduced. Obviously, for those skilled in the art, other drawings can also be obtained from these drawings without creative labor.

[0020] Figure 1 A flowchart of an information processing method provided by the embodiments of the present disclosure;

[0021] Figure 2 A first page schematic diagram provided by the embodiments of the present disclosure;

[0022] Figure 3 A first page schematic diagram provided by the embodiments of the present disclosure;

[0023] Figure 4 A target form text schematic diagram provided by the embodiments of the present disclosure;

[0024] Figure 5 An information processing flow schematic diagram provided by the embodiments of the present disclosure;

[0025] Figure 6 A second page schematic diagram provided by the embodiments of the present disclosure;

[0026] Figure 7 An information processing flow schematic diagram provided by the embodiments of the present disclosure;

[0027] Figure 8A flowchart of an information processing method provided by an embodiment of the present disclosure is shown in the figure;

[0028] Figure 9 A structural diagram of an information processing device provided by an embodiment of the present disclosure is shown in the figure;

[0029] Figure 10 A structural diagram of an electronic device provided by an embodiment of the present disclosure is shown in the figure. DETAILED DESCRIPTION

[0030] In order to more clearly understand the above-mentioned purposes, features and advantages of the present disclosure, the solutions of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features in the embodiments can be combined with each other without conflict.

[0031] In the following description, many specific details are set forth in order to provide a thorough understanding of the present disclosure, but the present disclosure can also be implemented in other ways different from those described herein; obviously, the embodiments described in the specification are only a part of the embodiments of the present disclosure, not all the embodiments.

[0032] There may be content differences between the information input by the user in the online form such as electronic contract, electronic work order, etc. and the actual generated form text, and there are many possible reasons for the above content differences, such as form template errors will cause the generation of incorrect actual form text, and such as, the mapping error of the user selection item by the background system, so as to present the incorrectly mapped content in the actual form text, for example, the online presents the drop-down menu options corresponding to the cooperation area for the user, the user selects the option of the cooperation area as the national area on the page, but the background incorrectly calls the string of the cooperation area as the specific area in the form generation process, thereby causing the form content not to match the user input; and such as, the system program error causes the generated actual form text error. The above are brief examples, and will not be listed one by one. As described above, one or more problems may occur in the process of generating the actual form text, causing the actual form text to not match the user input information, and in the related art, the direct artificial one-by-one checking and comparison method not only consumes time and effort, but also may still miss. In order to improve the above problems, the present disclosure provides an information processing method, device and program product, which will be described in detail below.

[0033] Figure 1 A flowchart of an information processing method provided by an embodiment of the present disclosure is shown in the figure, which can be executed by an information processing device, wherein the device can be implemented by software and / or hardware, and can be integrated in an electronic device. As shown in the figure, the method mainly includes the following steps S102-S108: Figure 1

[0034] ​In step S102, a target region in the first page is determined, and document object model information corresponding to the target region is obtained; the first page is a page for inputting form information.

[0035] The first page is a form input page, and can also be referred to as an electronic form. The form type or form purpose is not limited in the embodiments of the present disclosure, and can be, for example, a contract, a work order, or the like. The first page can briefly present form item names and input controls corresponding to the form item names. A user can fill in information corresponding to the form item names through the input controls. The input controls can be used by the user to directly fill in information. The input controls can be text input controls or drop-down menu controls, which can be used by the user to select from a plurality of existing information. The form of the input controls is not limited in the embodiments of the present disclosure. Figure 2 The form items are names of categories to be filled in the form. Taking a contract form as an example, the form items are, for example, Party A, Party B, cooperation region, contact name, and the like. For ease of understanding, a first page diagram shown in FIG. 1 can be referred to. The first page diagram shows partial information of the first page. The first page can be divided into a plurality of regions (also referred to as units), such as a cooperation region, an after-sales contact method, and a settlement method. Each region contains corresponding form item names and input controls. Figure 2 The above is only an example for illustration and should not be regarded as a limitation.

[0036] A document object model (DOM) is a structured representation of web page content, which can represent an HTML (HyperText Markup Language) structure. Document object model information (also referred to as DOM information) can represent HTML web page content through a tree structure. In the embodiments of the present disclosure, the document object model information corresponding to the target region can be obtained, so that the page information of the target region in the first page can be efficiently and comprehensively obtained. For example, information input by a user to the first page through a plurality of forms such as a drop-down menu control, a check control, and a text input control can be presented through the document object model information.

[0037] In step S104, target input information corresponding to the target region is determined based on the document object model information. The document object model information can comprehensively present information of the target region, and the user input information (i.e., the target input information) in the target region can be obtained by analyzing the document object model information. In some embodiments, the target input information can be represented in a specified form, such as being associated with a form item name corresponding to the target input information, and being represented in the form of {form item name: user input value}. Taking the example of a user-selected cooperation region being the whole country, the target input information can be represented as {cooperation region: the whole country}. The present disclosure does not limit the manner of obtaining the target input information based on the document object model information, and for example, a pre-trained neural network model can be used to analyze the document object model information and output the target input information in a specified form, such as the aforementioned {form item name: user input value} form, which can be flexibly set and is not limited herein. In actual applications, to facilitate subsequent processing, the target input information can be presented in a specified format, such as being presented in a Json format.

[0038] In step S106, target form text corresponding to the target region is obtained.

[0039] In some embodiments, the target form text corresponding to the target region can be directly obtained, and the manner of generating the target form text is not limited herein, and any manner that can automatically generate the target form text based on the user input information can be used, such as directly obtaining a form text generated by a system in an original manner, and extracting the target form text corresponding to the target region from the form text. In other embodiments, to improve the reliability of the target form text as much as possible in the generation of the form text, based on the extracted target input information, the target form text corresponding to the target region can be directly generated based on the target input information and a preset form template. The form template includes a preset form text and a to-be-filled identifier, the preset form text can be a preset form clause or other text that does not need to be input by a user, and the to-be-filled identifier can be represented by an identifier such as a blank identifier, an underscore, a colon, or the like, and is used to indicate that a position corresponding to the to-be-filled identifier needs to be filled with user information. The present disclosure can automatically generate the target form text corresponding to the target region based on the aforementioned extracted target input information and the form template, and the target form text can be represented in the form of a string. In actual applications, a form generation rule can be preset, and the target input information and the preset form template can be processed based on the form generation rule to generate the target form text corresponding to the target region. For example, the form generation rule is used to indicate that the input information and the form template are spliced.

[0040] In step S108, the target input information is compared with the key information in the target form text to obtain a comparison result. The key information is information in the target form text corresponding to the target input information. It can be understood that the key information in the target form text corresponds to the form item name consistent with the form item name corresponding to the target input information. For example, for the form item name "cooperation area", the target input information is the whole country, and the key information in the target form text can be "the whole country" in "both parties confirm that the cooperation area under this form item is the whole country" in the target form text. The comparison result can be directly presented in the form of a similarity value, or can be presented in the form of a conclusion of "consistent" or "inconsistent", which is not limited here.

[0041] Compared with the manual comparison method, the above method provided by the embodiment of the disclosure can obtain the comparison result more efficiently and reliably, and effectively save the labor cost. Moreover, the comparison can be performed after the user input is completed, so as to ensure the accuracy of the final obtained form text in time, prevent the form flow from being blocked, and prevent the form text error from affecting the subsequent signing.

[0042] In some embodiments, in the step S102 of determining the target region in the first page, the region corresponding to the region framing operation can be determined in response to the region framing operation on the first page, and the region corresponding to the region framing operation can be taken as the target region in the first page. That is, in actual application, the user can frame the region of the first page to specify the target region information to be extracted. The first page can have one or more target regions, and the user can frame the required target region according to the demand. In addition, the user can frame multiple target regions at the same time, or frame the required target region one by one, which is not limited here. Through the above method, the target region of the user input information to be extracted can be specified efficiently and conveniently. Further, in the case that the confirmation instruction indicating that the form information input in the first page is completed is received, the region corresponding to the region framing operation can be determined in response to the region framing operation on the first page, and the region corresponding to the region framing operation can be taken as the target region in the first page. Through the above method, it can be ensured that the target region is determined after the user input is completed, that is, it can be ensured that the user input information exists in the target region, and it can be ensured that the subsequent operation can accurately extract the required target input information, so as to avoid the waste of processing resources caused by the execution of the subsequent operation when the target region is not filled with user information.

[0043] In some embodiments, the step of obtaining the document object model information corresponding to the target region in step S102 can be implemented by a preset plug-in. The preset plug-in can be a browser plug-in that can extract the document object model information. In this way, the document object model information can be extracted without code invasion, so that subsequent operations such as target input information extraction and comparison can be performed based on the document object model information. The plug-in-based document object model information extraction method is flexible and convenient, and can minimize the damage to the original code and reduce the impact on the original code, thereby helping to maintain the stability of the existing system.

[0044] In some embodiments, the step S104, i.e., the step of determining the target input information corresponding to the target region based on the document object model information, can be performed by referring to the following steps: inputting the document object model information into a preset first language model, and extracting the target input information corresponding to the target region from the document object model information by the first language model. For the convenience of understanding, the following will be described in detail:

[0045] The first language model can be a large language model, such as a GPT (Generative Pre-trained Transformer) model or its variants. The GPT model can be pre-trained based on a large amount of text data and other sample data. It can learn the structure and semantic relationship of language and has strong language processing capability, such as being able to understand complex text and generate coherent and context-related text.

[0046] In actual applications, the DOM information can be directly input into the first language model, or can be pre-processed such as formatting according to requirements, and then input into the first language model, which is not limited herein. In some specific implementation examples, when the number of target regions is multiple, the DOM information corresponding to the multiple target regions is spliced to obtain a spliced information; and the spliced information is input into the preset first language model. By the above manner, the DOM information of multiple target regions can be input into the first language model at one time, thereby improving the processing efficiency of the model. In addition, other information except the DOM information, such as the first prompt information, can also be input into the first language model, the first prompt information being used to indicate the processing information required by the first language model for the DOM information and / or being used to indicate the form of the DOM information processing result expected to be output by the first language model, so that the first language model can process the DOM information based on the first prompt information and output the expected result, such as the input information corresponding to the form item name in the target region extracted by the first language model from the DOM information. In some specific implementation examples, the first language model can associate and record the form item name in the target region and the input information corresponding to the form item name, such as outputting the information in the form of {form item name: user input value}. By the above manner, the target input information corresponding to the target region can be efficiently and accurately extracted from the DOM information by means of the powerful semantic understanding and processing capability of the language model.

[0047] In actual applications, the form template can be set in advance, and based on the target input information obtained by analysis and the preset form template, the target form text corresponding to the target region can be spliced and generated. For ease of understanding, first refer to Figure 3 a first page diagram as shown in FIG. 1, Figure 3 In Figure 2On the basis of the above, it is presented that the user has input corresponding information for the form item name of the target area 1 and the target area 2 respectively, in the target area 1, the form item name is "cooperation area", the user input value is "nationwide", in the target area 2, the form item name is "contact name", the user input value is "XX", the form item name is "contact phone", and the user input value is "XXXXXXXX". In fact, the aforementioned extracted target input information is the user input value, and the target input information can be associated with the corresponding cooperation item name and recorded in the form of {form item name: user input value}. As mentioned earlier, the preset form template includes preset form text and to-be-filled identifiers, and the to-be-filled identifiers corresponding to each target input information can be determined from the form template based on the form item name, so that the target input information is filled into the position indicated by the to-be-filled identifier corresponding thereto in the form template, and the target form text is spliced, for example, in the Figure 3 On the basis of the above, refer to a target form text schematic diagram shown in Figure 4 As an example, take the form as a contract form, such as "both parties confirm that the cooperation area under this contract is:", which can be regarded as the preset form text in the form template, and 【】 can be regarded as the to-be-filled identifier in the form template. By combining the form template with the target input information, the target form text corresponding to the cooperation area is "both parties confirm that the cooperation area under this contract is:

nationwide

[0048] In view of various reasons such as template problems, splicing problems, etc., the generated target form text may not match the actual target input information, and therefore it is necessary to check whether the user input information is consistent with the generated actual form text. Compared with the manner in which the related art needs to manually compare whether the user input information presented in the first page is consistent with the generated actual form text, the embodiments of the present disclosure can accurately determine the target input information by extracting and analyzing the document object model information in the first page, and automatically compare whether the target input information is consistent with the key information in the target form text, thereby guaranteeing the accuracy and reliability of the final obtained form text. In some embodiments, the step S108, i.e., the step of comparing whether the target input information is consistent with the key information in the target form text to obtain a comparison result, can be implemented by referring to the following steps: inputting the target input information and the target form text into a preset second language model, determining the key information in the target form text corresponding to the target input information through the second language model, and comparing whether the target input information is consistent with the key information to obtain a comparison result. The second language model can also be a large language model, such as the aforementioned GPT model. The second language model can be the same as or different from the first language model, which is not limited herein. In actual application, the second prompt information can also be inputted into the second language model together with the target input information and the target form text. The second prompt information is used to indicate the processing information required by the second language model for the target input information and the target form text, such as indicating that the second language model identifies the key information in the target form text corresponding to the target input information, and compares whether the target form text and the corresponding key information are consistent, and / or indicating the form of the comparison result expected to be outputted by the second language model, and further indicating that the second language model also outputs the correction suggestion for the target form text when the comparison result is inconsistent.

[0049] For ease of understanding, refer to the information processing flow diagram shown in FIG. 1. Figure 5 As shown in FIG. 1, the target area 1 and the target area 2 respectively acquire the document object model information through the plug-in. Figure 5corresponding to the target region 1 and the DOM information 2 corresponding to the target region 2, splicing the DOM information 1 and the DOM information 2 to obtain a DOM splicing result, and then inputting the DOM splicing result to the first language model for analysis to obtain target input information corresponding to the target region. Further, the target input information can be combined with the form template to generate target form text, and the target input information and the generated target form text are input to the second language model for comparison to obtain a comparison result. The first language model can extract the user input value corresponding to the form item name (i.e., the target input information) from the DOM splicing result, and record the association in the form of {form item name: user input value}. The second language model can further compare {form item name: user input value} and the target form text, thereby obtaining the comparison result. The above-mentioned manner can efficiently and conveniently extract the document object model information on the basis of non-invasive code with the aid of the plug-in. On the basis of the document object model information, the first language model and the second language model each have strong semantic understanding ability and text processing ability, so as to accurately extract the target input information and efficiently and accurately compare the target input information and the target form text, thereby obtaining the comparison result.

[0050] In order to facilitate the user to view, the embodiment of the disclosure can display the target input information, the target form text, and the comparison result in the second page. In actual application, the target input information, the target form text, and the comparison result can all be rendered and displayed in the second page. In some embodiments, in the case that the comparison result indicates that the target input information is inconsistent with the key information in the target form text, a correction suggestion for the key information in the target form text is displayed in the second page. The correction suggestion can be output together with the comparison result by the second language model, for example, referring to a second page schematic diagram as shown in Figure 6 The user input value corresponding to the form item "cooperation region" is "North China", the actual generated text (corresponding to the aforementioned target form text) is "both parties confirm that the cooperation region under the contract is: [nationwide]", and the comparison result and the modification opinion are further illustrated. Through the above-mentioned manner, the user can clearly know the current problem of the target form text and modify it, thereby obtaining the accurate target form text.

[0051] On the basis of the foregoing, the method provided by the embodiment of the disclosure further includes the following (1) and (2):

[0052] (1) In the case that the comparison result indicates that the target input information is inconsistent with the key information in the target form text, the key information in the target form text is corrected based on the target input information. For example, the key information is modified to be consistent with the target input information.

[0053] (2) If the comparison result indicates that the target input information matches the key information in the target form text, the final form text is generated based on the target form text. For example, if there are multiple target form texts, they can be concatenated to obtain the final form text. The concatenation order of the multiple target form texts can be determined based on the position of their respective target areas in the form template.

[0054] Using the above method, users can first fill in the required personalized information (also known as dynamic information) directly on a simplified electronic form, then generate the target form text based on this, and finally ensure the accuracy of the final form text by automatically comparing the differences between the target form text and the information entered by the user.

[0055] See Figure 7 The diagram illustrates an information processing flow, using a contract form as an example. It shows that a user can input relevant information into an electronic form (corresponding to the first page mentioned above). The DOM (Domain of Documentation) can then be extracted and parsed using the aforementioned method to obtain the user input information (corresponding to the target input information). This is further combined with a contract template (corresponding to the form template mentioned above) to obtain the actual contract text (corresponding to the target form text mentioned above). Consistency verification can be performed between the user input information and the actual contract text. If inconsistencies are found, the actual contract text can be corrected. Finally, a complete signed contract (i.e., the final form text mentioned above) is generated using the actual contract text consistent with the user input information. In practical applications, different areas of the electronic form can be used to obtain the corresponding actual contract text. By concatenating the actual contract texts corresponding to different areas, a complete signed contract can be obtained.

[0056] For easier understanding, please also refer to Figure 8 The flowchart shown here illustrates an information processing method, which mainly includes the following steps:

[0057] Step S802: In response to the area selection operation on the first page, determine the area corresponding to the area selection operation and use the area corresponding to the area selection operation as the target area on the first page.

[0058] Step S804: Obtain the document object model information corresponding to the target area through a preset plugin.

[0059] Step S806: Input the document object model information into the preset first language model, and determine the target input information corresponding to the target region through the first language model.

[0060] At step S808, the target form text corresponding to the target region is obtained. Illustratively, the target form text corresponding to the target region can be generated based on the target input information and the preset form template, or the corrected target form text can be directly obtained, or the target form text corresponding to the target region can be obtained in a manner in the related art, which is not limited herein.

[0061] At step S810, the target input information and the target form text are input into a preset second language model, the key information in the target form text corresponding to the target input information is determined through the second language model, and whether the target input information and the key information are consistent is compared to obtain a comparison result.

[0062] At step S812, whether the target input information and the key information are consistent is determined based on the comparison result. If not, step S814a is executed, and if yes, step S814b is executed.

[0063] At step S814a, the key information in the target form text is corrected based on the target input information. Then, the step S808 is returned to be executed.

[0064] At step S814b, the final form text is generated based on the target form text. Taking a contract as an example, the final form text can be referred to as a signed contract.

[0065] The above steps can refer to the related content described above, which is not repeated herein. It should be noted that, Figure 8 is only an implementation example, and can also be adjusted on the basis of Figure 8 such as, in actual application, the final form text can be directly generated based on the corrected target form text after the target form text is corrected based on the target input information, that is, step S814b can also be directly executed after step S814a is executed, which can be flexibly set, and is not limited herein.

[0066] It should be finally pointed out that the way of extracting user input information from the first page in the related art is different from the way of extracting and analyzing the document object model information provided by the embodiments of the present disclosure. For example, in the related art, a correspondence relationship (hereinafter referred to as correspondence relationship 1) between form items in an electronic form and the content in a form clause can be set in advance. For example, the relationship between the "cooperation area" and "nationwide", "North China", etc. is the aforementioned correspondence relationship 1. In the system, the content in the form clause is not directly stored, but the underlying interaction data is stored, such as the underlying interaction data corresponding to "nationwide" is a character in a specified format, and the mapping relationship between the form item and the underlying interaction data is the aforementioned correspondence relationship 2. After obtaining the electronic form recording the user input information, the related art cannot directly extract the user input information from the electronic form. Only the underlying interaction data corresponding to the user input information is extracted, so the user input information can be obtained based on the aforementioned correspondence relationship 1 and correspondence relationship 2. The above-mentioned method is not only complex and tedious, but also prone to problems when obtaining the user input information based on the aforementioned correspondence, resulting in that the obtained user input information does not match the actual one. Furthermore, the actual form text obtained based on the user input information does not match the user input information seen through the electronic form during manual checking. Moreover, the operation of manual consistency checking is time-consuming and laborious, and is prone to errors. However, the embodiments of the present disclosure can directly introduce the plug-in to extract the document object model information in the electronic form, and analyze and parse the document object model information by using the powerful processing capability of the language model. Without considering the aforementioned correspondence relationship 2, the user input information can be directly obtained, which is not only convenient and fast, but also can better ensure the accuracy of the extracted user input information. The embodiments of the present disclosure can further assist the language model to efficiently compare the user input information and the generated actual form text, so as to finally guarantee the reliability and accuracy of the form text, without manual comparison one by one, which greatly saves the labor cost and improves the user experience.

[0067] Corresponding to the aforementioned information processing method, the embodiments of the present disclosure further provide an information processing device, Figure 9 The structure diagram of an information processing device provided by the embodiments of the present disclosure is shown. The device can be realized by software and / or hardware, and can be integrated in an electronic device, such as a computer. Figure 9 As shown in the figure, the information processing device comprises:

[0068] The first acquisition module 902 is configured to determine a target area in a first page and acquire document object model information corresponding to the target area; wherein the first page is a page for inputting form information;

[0069] The information determination module 904 is configured to determine target input information corresponding to the target area based on the document object model information;

[0070] The second obtaining module 906 is configured to obtain target form text corresponding to the target region.

[0071] The information comparison module 908 is configured to compare the target input information with key information in the target form text to obtain a comparison result, wherein the key information is information in the target form text corresponding to the target input information.

[0072] The above device provided by the embodiments of the present disclosure can more efficiently and reliably obtain a comparison result, and effectively save labor costs.

[0073] In some embodiments, the information determination module 904 is specifically configured to: input the document object model information into a preset first language model, and extract the target input information corresponding to the target region from the document object model information through the first language model.

[0074] In some embodiments, the information determination module 904 is specifically configured to: in a case where the number of the target regions is multiple, splice the document object model information corresponding to the multiple target regions to obtain an information splicing result; and input the information splicing result into a preset first language model.

[0075] In some embodiments, the second obtaining module 906 is specifically configured to: generate the target form text corresponding to the target region based on the target input information and a preset form template.

[0076] In some embodiments, the information comparison module 908 is specifically configured to: input the target input information and the target form text into a preset second language model, determine key information in the target form text corresponding to the target input information through the second language model, and compare the target input information with the key information to obtain a comparison result.

[0077] In some embodiments, the device further includes a display module configured to display the target input information, the target form text, and the comparison result in a second page.

[0078] In some embodiments, the device further includes a suggestion module configured to, in a case where the comparison result indicates that the target input information is inconsistent with the key information in the target form text, display a correction suggestion for the key information in the target form text in the second page.

[0079] In some embodiments, the document object model obtaining module 902 is specifically configured to: in response to a region marquee operation on the first page, determine a region corresponding to the region marquee operation, and take the region corresponding to the region marquee operation as a target region in the first page.

[0080] In some embodiments, the document object model acquisition module 902 is specifically configured to acquire the document object model information corresponding to the target region through a preset plug-in.

[0081] In some embodiments, the device further includes a result processing module configured to, in a case where the comparison result indicates that the target input information is inconsistent with the key information in the target form text, correct the key information in the target form text based on the target input information; and in a case where the comparison result indicates that the target input information is consistent with the key information in the target form text, generate a final form text based on the target form text.

[0082] The information processing device provided in the embodiments of the present disclosure can perform the information processing method provided in any of the embodiments of the present disclosure, and has the corresponding function modules and beneficial effects of performing the method.

[0083] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the device embodiments described above can refer to the corresponding process in the method embodiments, which will not be repeated here.

[0084] The embodiments of the present disclosure provide an electronic device, which includes a storage device having a computer program stored thereon, and a processing device configured to execute the computer program in the storage device to implement the steps of any method in the present disclosure.

[0085] Reference is made below to Figure 10 which shows a structural schematic diagram of an electronic device 1000 suitable for implementing the embodiments of the present disclosure. The terminal device in the embodiments of the present disclosure can include, but is not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablets), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), and the like, and fixed terminals such as digital TVs, desktop computers, and the like. Figure 10 The electronic device shown is only an example, and should not bring any limitation to the functions and use range of the embodiments of the present disclosure.

[0086] As Figure 10As shown, the electronic device 1000 can include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 1001 that can perform various appropriate actions and processes according to programs stored in a read-only memory (ROM) 1002 or loaded into a random access memory (RAM) 1003 from a storage device 1008. Various programs and data required for the operation of the electronic device 1000 are also stored in the RAM 1003. The processing device 1001, the ROM 1002, and the RAM 1003 are connected to each other through a bus 1004. An input / output (I / O) interface 1005 is also connected to the bus 1004.

[0087] In general, the following devices can be connected to the I / O interface 1005: input devices 1006 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 1007 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 1008 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 1009. The communication devices 1009 can allow the electronic device 1000 to communicate wirelessly or wired with other devices to exchange data. Although Figure 10 The electronic device 1000 is shown with various devices, but it should be understood that not all of the shown devices are required to be implemented or present. More or fewer devices can alternatively be implemented or present.

[0088] In particular, the processes described above with reference to the flowcharts can be implemented as a computer software program according to embodiments of the present disclosure. For example, embodiments of the present disclosure include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods illustrated by the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network through the communication devices 1009, or installed from the storage devices 1008, or installed from the ROM 1002. When the computer program is executed by the processing device 1001, the above-described functions defined in the methods of embodiments of the present disclosure are performed.

[0089] In addition to the method and device described above, the embodiments of the present disclosure can also be a computer program product, which includes computer program instructions that make the processor execute the method provided by the embodiments of the present disclosure when the processor is running. The computer program product can be written in any combination of one or more programming languages to execute the program code of the embodiments of the present disclosure, including object-oriented programming languages such as Java, C++, and conventional procedural programming languages such as "C" language or similar programming languages. The program code can be executed entirely on a user computing device, partially on a user device, as an independent software package, partially on a user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0090] In addition, the embodiments of the present disclosure can also be a computer readable storage medium, which stores computer program instructions, and the computer program instructions make the processor execute the information processing method provided by the embodiments of the present disclosure when the processor is running.

[0091] The computer readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium may, for example, include but is not limited to an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or component, or any combination of the above. More specific examples (non-exhaustive list) of readable storage medium include: electrical connection with one or more conductive wires, portable disk, hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above.

[0092] The embodiments of the present disclosure also provide a computer program product, which includes computer programs / instructions that are executed by a processor to implement the information processing method in the embodiments of the present disclosure.

[0093] It can be understood that before using the technical solutions disclosed in the embodiments of the present disclosure, the type, use range, use scenario, etc. of the personal information involved in the present disclosure should be informed to the user and the authorization of the user should be obtained according to relevant laws and regulations.

[0094] For example, in response to receiving an active request of a user, a prompt information is sent to the user to explicitly prompt the user that the operation requested to be performed by the user will need to acquire and use personal information of the user. Thus, the user can autonomously select whether to provide the personal information to the software or hardware such as an electronic device, an application program, a server or a storage medium performing the operation of the technical solution of the present disclosure according to the prompt information.

[0095] As an optional but non-limiting implementation, in response to receiving an active request of a user, the manner of sending a prompt information to the user may, for example, be a pop-up window manner, and the prompt information may be presented in the pop-up window in the form of text. In addition, the pop-up window may also carry a selection control for the user to select “agree” or “disagree” to provide personal information to the electronic device.

[0096] It can be understood that the above notification and acquisition of user authorization process is only illustrative and does not limit the implementation of the present disclosure, and other manners meeting the relevant laws and regulations can also be applied to the implementation of the present disclosure.

[0097] It should be noted that in this document, relational terms such as “first” and “second”, and the like can be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms “comprises”, “comprising”, or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without more limitations, an element preceded by “comprises a...” does not, without more limitations, foreclose the existence of additional identical elements in the process, method, article, or apparatus that includes the recited element.

[0098] The above description is merely one specific implementation of the present disclosure, which enables those skilled in the art to understand or implement the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to these embodiments described herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An information processing method characterized by comprising: The method comprises: determining a target region in a first page, and obtaining document object model information corresponding to the target region; wherein the first page is a page for inputting form information; inputting the document object model information into a preset first language model, and extracting target input information corresponding to the target region from the document object model information through the first language model; generating target form text corresponding to the target region based on the target input information and a preset form template; inputting the target input information and the target form text into a preset second language model, determining key information corresponding to the target input information in the target form text through the second language model, and comparing the target input information and the key information to obtain a comparison result; wherein the key information is information in the target form text corresponding to the target input information.

2. The method of claim 1, wherein, The method further comprises: displaying the target input information, the target form text, and the comparison result in a second page. The method further comprises:

3. The method of claim 1, wherein, in a case where the comparison result indicates that the target input information is inconsistent with the key information in the target form text, displaying a correction suggestion for the key information in the target form text in the second page. The method further comprises:

4. The method of claim 3, wherein, in a case where the comparison result indicates that the target input information is inconsistent with the key information in the target form text, correcting the key information in the target form text based on the target input information; in a case where the comparison result indicates that the target input information is consistent with the key information in the target form text, generating a final form text based on the target form text.

5. The method of claim 1, wherein, The electronic device comprises: a storage device having a computer program stored thereon; 6. The method of claim 1, wherein, a processing device configured to execute the computer program in the storage device to implement the steps of the information processing method according to any one of claims 1-7. The computer program is configured to implement the information processing method according to any one of claims 1-7 when executed by a processor.

7. The method according to any one of claims 1 to 6, characterized in that, ​ ​ ​ 8. An electronic device, comprising: ​ ​ ​ 9. A computer program product, characterised in that, ​

Images