Information processing method, device and program product

Abstract

The embodiment of the invention relates to an information processing method and device and a program product, and the method comprises the steps: 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 used for inputting form information; determining target input information corresponding to the target area based on the document object model information; obtaining a target form text corresponding to the target area; comparing whether the target input information is consistent with key information in the target form text to obtain a comparison result; wherein the key information is information corresponding to the target input information in the target form text. According to the embodiment of the invention, the comparison result can be more efficiently and reliably obtained, and the labor cost is effectively saved.

Description

Technical Field

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

[0002] Users can directly enter personalized information related to the form, such as identity information, cooperation information, etc. on the electronic form, and then generate the actual form text based on this. The form can be any page that requires users to fill in information, such as contracts and work orders. However, there may be content differences between the user-entered information and the actual form text. For example, the cooperation area entered by the user online is the national area, but the cooperation area displayed on the actual form text is a specific area, that is, the actual form text generated may not be accurate. The relevant technology mainly uses manual methods to compare whether the actual generated form is consistent with the user-entered information, which is time-consuming and labor-intensive, and requires high labor costs. Summary of the invention

[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] An embodiment of the present disclosure provides an information processing method, which includes: determining a target area in a first page, and obtaining 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; obtaining a target form text corresponding to the target area; comparing the target input information with key information in the target form text to determine whether they are consistent, and obtaining a comparison result; wherein the key information is information in the target form text that corresponds to the target input information.

[0005] Optionally, determining the target input information corresponding to the target area based on the document object model information includes: 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, inputting the document object model information into a preset first language model includes: when there are multiple target areas, 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 the preset first language model.

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

[0008] Optionally, comparing the target input information with key information in the target form text to see if they are consistent and obtaining a comparison result includes: inputting the target input information and the target form text into a preset second language model, determining key information in the target form text corresponding to the target input information through the second language model, and comparing the target input information with the key information to see if they are consistent and obtaining a comparison result.

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

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

[0011] Optionally, determining the target area in the first page includes: in response to an area selection operation on the first page, determining an area corresponding to the area selection operation, and using the area corresponding to the area selection operation as the target area in the first page.

[0012] Optionally, the acquiring document object model information corresponding to the target area includes: acquiring the document object model information corresponding to the target area through a preset plug-in.

[0013] Optionally, the method also includes: when the comparison result indicates that the target input information is inconsistent with key information in the target form text, correcting the key information in the target form text based on the target input information; when 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] An embodiment of the present disclosure also provides an electronic device, which includes: a processor; a memory for storing executable instructions of the processor; the processor is used to read the executable instructions from the memory and execute the instructions to implement the information processing method provided by the embodiment of the present disclosure.

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

[0016] The above technical solution provided by the embodiment of the present disclosure can first determine the target area in the first page and obtain the document object model information corresponding to the target area, so as to quickly and accurately parse the target input information corresponding to the target area based on the document object model information. On the basis of obtaining the target form text corresponding to the target area, the key information of the target input information and the target form text can be automatically compared for consistency. Compared with the manual comparison method, the embodiment of the present disclosure can obtain the comparison result more efficiently and reliably, and effectively save labor costs.

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

[0018] The accompanying drawings, which are incorporated in and constitute a part of this 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 embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

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

[0021] Figure 2 A schematic diagram of a first page provided in an embodiment of the present disclosure;

[0022] Figure 3 A schematic diagram of a first page provided in an embodiment of the present disclosure;

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

[0024] Figure 5 A schematic diagram of an information processing flow provided by an embodiment of the present disclosure;

[0025] Figure 6 A schematic diagram of a second page provided in an embodiment of the present disclosure;

[0026] Figure 7 A schematic diagram of an information processing flow provided by an embodiment of the present disclosure;

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

[0028] Fig. 9 A schematic diagram of the structure of an information processing device provided by an embodiment of the present disclosure;

[0029] Fig.10 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0030] In order to more clearly understand the above-mentioned objectives, features and advantages of the present disclosure, the scheme 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 to facilitate a full understanding of the present disclosure, but the present disclosure may also be implemented in other ways different from those described herein; it is obvious that the embodiments in the specification are only part of the embodiments of the present disclosure, rather than all of the embodiments.

[0032] There may be content differences between the information entered by the user in online forms such as electronic contracts and electronic work orders and the actual generated form text. There are many possible reasons for the above content differences, such as form template errors will lead to the generation of incorrect actual form texts, and for example, the background system has a mapping error for the user's selection items, so that the incorrectly mapped content is presented in the actual form text. For example, the online drop-down menu options corresponding to the cooperation area are presented to the user. Although the user selects the option of the cooperation area as the national area on the page, the background mistakenly calls the string of the cooperation area as a specific area during the form generation process, resulting in the form content not matching the user input; another example is that the system program has an error that causes the generated actual form text to be wrong. The above are all brief examples, and the reasons are not listed one by one. As mentioned above, there may be one or more problems in the process of generating the actual form text that cause the actual form text to be inconsistent with the user input information. In the related art, the method of directly checking and comparing one by one manually is not only time-consuming and laborious, but also may still result in omissions. In order to improve the above problems, the embodiments of the present disclosure provide an information processing method, device and program product, which are described in detail below.

[0033] Figure 1 The present invention provides a flowchart of an information processing method provided by an embodiment of the present invention. The method can be executed by an information processing device, wherein the device can be implemented by software and / or hardware and can generally be integrated in an electronic device. Figure 1 As shown, the method mainly includes the following steps S102 to S108:

[0034] Step S102, determining a target area in a first page, and obtaining document object model information corresponding to the target area; wherein the first page is a page for inputting form information.

[0035] The first page is the form input page, which may also be specifically referred to as an electronic form. The embodiments of the present disclosure do not limit the form format or purpose of the form, such as contracts, work orders, etc. The first page may briefly present the form item name and the input control corresponding to the form item name. The user may fill in the information corresponding to the form item name through the input control. The input control allows the user to fill in the information directly. The input control may be a text fill-in control or a drop-down menu control for the user to select from a variety of existing information. The embodiments of the present disclosure do not limit the form of the input control. The form item is the name of the form category to be filled in. Taking the contract form as an example, the form items include Party A, Party B, Cooperation Area, Contact Name, etc. For ease of understanding, please refer to Figure 2 A schematic diagram of a first page is shown, illustrating partial information of the first page. The first page can be divided into multiple areas (also called units), such as cooperation area, after-sales contact information, settlement method, etc. Each area contains corresponding form item names and input controls. Figure 2 This is merely an illustration and should not be considered limiting.

[0036] Document Object Model (DOM) is a structured representation of web page content, which can represent 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. The embodiment of the present disclosure can efficiently and comprehensively obtain page information of the target area in the first page by obtaining the document object model information corresponding to the target area. For example, information input into the first page by the user through various forms such as drop-down menu controls, check controls, and text input controls can be presented through the document object model information.

[0037] Step S104, determine the target input information corresponding to the target area based on the document object model information. The document object model information can present the information of the target area more comprehensively. By parsing the document object model information, the user input information in the target area (i.e., the target input information) can be obtained. In some implementation examples, the target input information can be represented by a specified form, such as by associating with the form item name corresponding to the target input information, and represented in the form of {form item name: user input value}. Taking the user selecting the cooperation area as the whole country as an example, it can be represented as {cooperation area: whole country}. The embodiment of the present disclosure does not limit the method of obtaining the target input information corresponding to the target area by parsing the document object model information. Exemplarily, the document object model information can be parsed by a pre-trained neural network model, and the target input information can be output in a specified form. The specified form is such as the aforementioned {form item name: user input value} form, which can be flexibly set and is not limited here. In actual applications, in order to facilitate subsequent processing, the target input information can be presented in a specified format of data, such as data in Json format.

[0038] Step S106, obtaining the target form text corresponding to the target area.

[0039] In some embodiments, the target form text corresponding to the generated target area can be directly obtained. The generation method of the target form text is not limited here. Any method that can automatically generate the target form text based on the user input information can be used, such as directly obtaining the form text generated by the original method of the system, and extracting the target form text corresponding to the target area from the form text. In other embodiments, in order to improve the reliability of the target form text as much as possible in the generation link of the form text, on the basis of extracting more accurate target input information, the target form text corresponding to the target area can be directly generated based on the target input information and the preset form template. The form template includes a preset form text and a to-be-filled mark. The preset form text can be a text that does not require user input, such as a preset form clause, and the to-be-filled mark can be represented by marks such as fill-in marks, underscores, colons, etc., which are used to indicate that the position corresponding to the to-be-filled mark needs to be filled in with user information. The disclosed embodiment can automatically generate the target form text corresponding to the target area based on the aforementioned extracted target input information and form template, wherein the target form text can be represented in the form of a string. In actual applications, a form generation rule can be set in advance, and the target input information and the preset form template are processed based on the form generation rule to generate the target form text corresponding to the target area. Exemplarily, the above form generation rule is used to instruct to splice the input information and the form template.

[0040] Step S108, compare the target input information with the key information in the target form text to see if they are consistent, and obtain the comparison result; wherein the key information is the information in the target form text that corresponds to the target input information. It can be understood that the form item name corresponding to the key information in the target form text is consistent with the form item name corresponding to the target input information. For example, for a form item named "cooperation area", the target input information is nationwide, and the key information in the target form text can be "nationwide" in the target form text "Both parties confirm that the cooperation area under this form item is: nationwide". The comparison result can be presented directly in the form of a similarity value, or in the form of a "consistent" or "inconsistent" conclusion, which is not limited here.

[0041] Compared with manual comparison, the above method provided by the embodiment of the present disclosure can obtain comparison results more efficiently and reliably, and effectively save labor costs. Moreover, the comparison can be performed after the user completes the input, and the accuracy of the final form text can be ensured in time to prevent the form process from being blocked, that is, to prevent the form text errors from affecting the subsequent signing.

[0042] In some embodiments, the step of determining the target area in the first page in the above step S102 can be implemented in a specific manner, in response to the area selection operation for 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 in the first page. That is, in actual applications, the user can specify the information of the target area to be extracted by performing area selection on the first page. The first page may have one or more target areas, and the user can select the required target area from them according to needs. In addition, the user can select multiple target areas at the same time, or select the required target areas one by one, which is not limited here. In the above manner, the target area of ​​the user input information to be extracted can be specified efficiently and conveniently. Furthermore, in the case of receiving a confirmation instruction for indicating that the input of the form information in the first page is completed, in response to the area selection operation for the first page, the area corresponding to the area selection operation is determined, and the area corresponding to the area selection operation is used as the target area in the first page. Through the above method, it can be fully guaranteed that the target area is determined after the user input is completed, which can effectively ensure that the user input information already exists in the target area, and ensure that subsequent operations can accurately extract the required target input information, avoiding the subsequent operations when the user information is not filled in the target area, resulting in a waste of processing resources.

[0043] In some embodiments, the step of obtaining the document object model information corresponding to the target area in the above step S102 can obtain the document object model information corresponding to the target area through a preset plug-in during specific implementation. The preset plug-in is, for example, 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 intrusion, so that subsequent operations such as target input information extraction and comparison can be performed based on the document object model information. The method of using the plug-in to extract the document object model information is not only flexible and convenient, but also can avoid damaging the original code as much as possible, reduce the impact on the original code, and help maintain the stability of the existing system.

[0044] In some implementations, the above step S104, i.e., the step of determining the target input information corresponding to the target area based on the document object model information, can be performed with reference 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 area from the document object model information through the first language model. For ease of understanding, the following is a detailed description:

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

[0046] In practical applications, the document object model information can be directly input into the first language model, or the document object model information can be pre-processed such as formatting based on demand and then input into the first language model, which is not limited here. In some specific implementation examples, when there are multiple target areas, the document object model information corresponding to the multiple target areas is spliced ​​to obtain an information splicing result; the information splicing result is input into the preset first language model. In the above manner, the document object model information of multiple target areas can be input into the first language model at one time, thereby improving the model processing efficiency. In addition, other information other than the document object model information, such as the first prompt information, can also be input into the first language model. The first prompt information is used to indicate the processing information that the first language model needs to perform on the document object model information and / or to indicate the form of the document object model information processing result that the first language model expects to be output, so that the first language model can process the document object model information based on the first prompt information and output the expected result, such as the first language model extracting the input information corresponding to the form item name in the target area by parsing the document object model information, and then the input information extracted by the first language model can be used as the target input information corresponding to the target area. In some specific implementation examples, the first language model can record the form item name in the target area in association with the input information corresponding to the form item name, such as outputting information in the form of {form item name: user input value}. In the above manner, with the help of the powerful semantic understanding and processing capabilities of the language model, the target input information corresponding to the target area can be efficiently and accurately extracted from the document object model information.

[0047] In actual applications, the form template can be pre-set. Based on the parsed target input information and the preset form template, the target form text corresponding to the target area can be spliced ​​and generated. Figure 3 A schematic diagram of a first page is shown, Figure 3 exist Figure 2On the basis of this, it is shown that the user has entered the corresponding information for the form item names of target area 1 and target area 2 respectively. In target area 1, the form item name is "Cooperation Area" and the user input value is "Nationwide". In target area 2, the form item name is "Contact Name" and the user input value is "XX". The form item name is "Contact Phone Number" and the user input value is "XXXXXXXX". In fact, the target input information extracted above is the user input value. 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 above, the preset form template includes preset form text and to-be-filled markers. Based on the form item name, the to-be-filled marker corresponding to each target input information can be determined from the form template, so that the target input information can be filled in the corresponding position indicated by the corresponding to-be-filled marker in the form template, and the target form text can be obtained by splicing. For example, in Figure 3 Based on Figure 4 A schematic diagram of a target form text is shown, taking a contract form as an example. For example, "The parties confirm that the cooperation area under this contract is: " can be regarded as the preset form text in the form template, and [ ] can be regarded as the to-be-filled mark in the form template. By combining the form template with the target input information, the target form text corresponding to the cooperation area can be obtained as "The parties confirm that the cooperation area under this contract is: [nationwide]".

[0048] Considering various reasons such as template problems and splicing problems, the generated target form text may not match the actual target input information. Therefore, it is necessary to check whether the user input information is consistent with the generated actual form text. Compared with the method of manually comparing the user input information presented in the first page with the generated actual form text in the related art, the embodiment of the present disclosure can accurately determine the target input information by extracting and parsing the document object model information in the first page, and automatically compare the target input information with the key information in the target form text to ensure the accuracy and reliability of the final form text. In some embodiments, the above step S108, that is, comparing the key information in the target input information and the target form text to obtain the comparison result, can be implemented by referring to the following steps: input the target input information and the target form text into a preset second language model, determine the key information corresponding to the target input information in the target form text through the second language model, and compare the target input information with the key information to obtain the comparison result. The second language model can also be a large language model, such as the aforementioned GPT model, and the second language model can be the same as or different from the first language model, which is not limited here. In actual applications, the second prompt information can also be input 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 that the second language model needs to perform on the target input information and the target form text, such as instructing the second language model to identify key information corresponding to the target input information from the target form text, and compare whether the target form text and its corresponding key information are consistent, and / or, used to indicate the form of the comparison result expected to be output by the second language model, and can further indicate that the second language model is expected to output correction suggestions for the target form text when an inconsistent comparison result is obtained.

[0049] For easier understanding, please refer to Figure 5 The schematic diagram of an information processing flow shown in FIG. 1 shows that target area 1 and target area 1 obtain document object model information ( Figure 5DOM information is referred to as DOM information in the text), DOM information 1 corresponding to target area 1 and DOM information 2 corresponding to target area 2 are obtained, DOM information 1 and DOM information 2 are spliced ​​to obtain a DOM splicing result, and then the DOM information 1 and DOM information 2 are input into the first language model for parsing to obtain the target input information corresponding to the target area. Further, the target input information can be combined with the form template to generate a target form text, and the target input information and the generated target form text are input into the second language model for comparison to obtain a comparison result. The first language model can extract the user input value (that is, the target input information) corresponding to the form item name from the DOM splicing result, and associate the record 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 to obtain a comparison result. The above method can extract document object model information efficiently and conveniently without code intrusion with the help of the plug-in. On the basis of the document object model information, the first language model and the second language model can use their respective powerful semantic understanding capabilities and text processing capabilities to achieve accurate extraction of target input information and efficient and accurate comparison between target input information and target form text to obtain a comparison result.

[0050] In order to facilitate user viewing, the embodiment of the present disclosure can display the target input information, the target form text and the comparison result in the second page. In actual applications, the target input information, the target form text and the comparison result can all be rendered and displayed on the second page. In some embodiments, when the comparison result indicates that the target input information is inconsistent with the key information in the target form text, the second page displays correction suggestions for the key information in the target form text. The correction suggestions can be output together with the comparison result through the second language model. For example, see Figure 6 The second page schematic diagram shown in the figure takes the comparison of only the cooperation area as an example, indicating that the user input value corresponding to the form item "cooperation area" is "North China", and the actual generated text (corresponding to the aforementioned target form text) is "Both parties confirm that the cooperation area under this contract is: [National]", and further indicates the comparison results and modification opinions. Through the above method, users can clearly know the current problems of the target form text and correct them, so as to obtain accurate target form text.

[0051] Based on the above, the method provided in the embodiment of the present disclosure also includes the following (1) and (2):

[0052] (1) When 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, such as modifying the key information to be consistent with the target input information.

[0053] (2) When the comparison result indicates that the target input information is consistent with the key information in the target form text, a final form text is generated based on the target form text. For example, if there are multiple target form texts, the multiple target form texts can be spliced ​​to obtain the final form text. The splicing order of the multiple target form texts can be determined based on the positions of the corresponding target areas in the form template.

[0054] Through the above method, users can first fill in the personalized information (also called dynamic information) required for the form directly on a simple electronic form, and then generate the target form text based on this, and then automatically compare the differences between the target form text and the information entered by the user to ensure the accuracy of the final form text.

[0055] See also Figure 7 The schematic diagram of an information processing flow shown in the figure takes the form of a contract as an example, indicating that the user can enter relevant information into the electronic form (corresponding to the aforementioned first page), and then the DOM can be extracted and parsed using the aforementioned method to obtain the user input information (corresponding to the aforementioned target input information), and further combined with the contract template (corresponding to the aforementioned form template) to obtain the actual contract text (corresponding to the aforementioned target form text), and the consistency verification process can be performed on the user input information and the actual contract text. If there is inconsistency, the actual contract text can be corrected, and finally the actual contract text consistent with the user input information is used to generate a complete signed contract (that is, the aforementioned final form text). In actual applications, the corresponding actual contract texts can be obtained for different areas in the electronic form, and the actual contract texts corresponding to different areas are spliced ​​to obtain a complete signed contract.

[0056] For easier understanding, see also Figure 8 The flowchart of an information processing method shown in FIG. 1 mainly includes the following steps:

[0057] Step S802 , in response to the area selection operation on the first page, determining the area corresponding to the area selection operation, and using the area corresponding to the area selection operation as the target area in the first page.

[0058] Step S804: obtaining document object model information corresponding to the target area through a preset plug-in.

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

[0060] Step S808, obtaining the target form text corresponding to the target area. Exemplarily, the target form text corresponding to the target area 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 area can be obtained by using the method in the related art, which is not limited here.

[0061] Step S810, input the target input information and the target form text into a preset second language model, determine the key information in the target form text corresponding to the target input information through the second language model, and compare whether the target input information is consistent with the key information to obtain a comparison result.

[0062] Step S812: Determine whether the target input information is consistent with the key information based on the comparison result. If not, execute step S814a; if yes, execute step S814b.

[0063] Step S814a, modify the key information in the target form text based on the target input information, and then return to step S808.

[0064] Step S814b, generating a final form text based on the target form text. Taking the form as a contract as an example, the final form text may be called a signed contract.

[0065] The above steps can refer to the above related content, and will not be repeated here. It should be noted that: Figure 8 This is just an implementation example. Figure 8 For example, in actual applications, after the target form text is corrected based on the target input information, the final form text can be generated directly based on the corrected target form text, that is, step S814b can be directly executed after step S814a is executed. The specific settings can be flexibly made and are not limited here.

[0066] Finally, it should be noted that the method of extracting user input information from the first page in the related art is different from the method of extracting and parsing document object model information provided by the embodiment of the present disclosure. For example, in the related art, the correspondence between the form items in the electronic form and the content in the form clauses (hereinafter referred to as correspondence 1) can be pre-set. For example, the relationship between "cooperation area" and "national" and "North China" is the aforementioned correspondence 1, and in the system, it is not directly stored as the content in the form clauses, but stored as the underlying interactive data, such as the underlying interactive data corresponding to "national" is a character in a specified format, and the mapping relationship between the form items and the underlying interactive data is the aforementioned correspondence 2. After obtaining the electronic form that records the user input information, the related technology cannot directly extract the user input information from the electronic form. What is extracted is only the underlying interactive data corresponding to the user input information. Therefore, the user input information can only be obtained based on the above correspondence 1 and correspondence 2. The above method is not only complicated and cumbersome, but also prone to problems when obtaining the user input information based on the above correspondence, resulting in the obtained user input information not being consistent with the actual situation, and further resulting in the actual form text obtained based on the user input information being inconsistent with the user input information seen through the electronic form during manual verification. In addition, the operation of manually performing consistency verification is also relatively time-consuming and labor-intensive, and is also prone to errors. However, the embodiment of the present disclosure can directly introduce a plug-in to extract the document object model information in the electronic form, and use the powerful processing power of the language model to analyze and parse the document object model information. Without considering the above correspondence 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 disclosed embodiment can further use the language model to efficiently compare the user input information with the actual generated form text, so as to ultimately ensure the reliability and accuracy of the form text. There is no need for manual one-to-one comparison, which greatly saves labor costs and improves user experience.

[0067] Corresponding to the aforementioned information processing method, the present disclosure further provides an information processing device, Fig. 9 This is a schematic diagram of the structure of an information processing device provided by an embodiment of the present disclosure. The device can be implemented by software and / or hardware and can generally be integrated into an electronic device, such as Fig. 9 As shown, the information processing device includes:

[0068] A first acquisition module 902 is used 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] An information determination module 904, configured to determine target input information corresponding to a target area based on document object model information;

[0070] The second acquisition module 906 is used to acquire the target form text corresponding to the target area;

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

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

[0073] In some implementations, 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 area from the document object model information through the first language model.

[0074] In some implementations, the information determination module 904 is specifically used to: when there are multiple target areas, splice the document object model information corresponding to the multiple target areas to obtain an information splicing result; and input the information splicing result into a preset first language model.

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

[0076] In some embodiments, the information comparison module 908 is specifically used to: input the target input information and the target form text into a preset second language model, determine the 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 see if they are consistent, to obtain a comparison result.

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

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

[0079] In some implementations, the document object model acquisition module 902 is specifically used to: in response to a region selection operation on the first page, determine the region corresponding to the region selection operation, and use the region corresponding to the region selection operation as the target region in the first page.

[0080] In some implementations, the document object model acquisition module 902 is specifically used to: acquire the document object model information corresponding to the target area through a preset plug-in.

[0081] In some embodiments, the device also includes a result processing module for correcting the key information in the target form text based on the target input information when the comparison result indicates that the target input information is inconsistent with the key information in the target form text; and generating a final form text based on the target form text when the comparison result indicates that the target input information is consistent with the key information in the target form text.

[0082] The information processing device provided by the embodiments of the present disclosure can execute the information processing method provided by any embodiment of the present disclosure, and has the corresponding functional modules and beneficial effects of the execution method.

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

[0084] An embodiment of the present disclosure provides an electronic device, which includes: a storage device on which a computer program is stored; and a processing device for executing the computer program in the storage device to implement the steps of any method in the present disclosure.

[0085] Reference below Fig.10 , which shows a schematic diagram of the structure of an electronic device 1000 suitable for implementing the embodiment of the present disclosure. The terminal device in the embodiment of the present disclosure may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle terminals (such as vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Fig.10 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0086] like Fig.10As shown, the electronic device 1000 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 1001, which 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 1008 into a random access memory (RAM) 1003. In the RAM 1003, various programs and data required for the operation of the electronic device 1000 are also stored. The processing device 1001, the ROM 1002, and the RAM 1003 are connected to each other via a bus 1004. An input / output (I / O) interface 1005 is also connected to the bus 1004.

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

[0088] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains 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 through a communication device 1009, or installed from a storage device 1008, 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 of the present disclosure are executed.

[0089] In addition to the above-mentioned methods and devices, the embodiments of the present disclosure may also be a computer program product, which includes computer program instructions, which, when executed by a processor, cause the processor to perform the method provided by the embodiments of the present disclosure. The computer program product may be written in any combination of one or more programming languages ​​to write program codes for performing the operations of the embodiments of the present disclosure, the programming languages ​​including object-oriented programming languages ​​such as Java, C++, etc., and also conventional procedural programming languages ​​such as "C" language or similar programming languages. The program code may 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 may also be a computer-readable storage medium on which computer program instructions are stored. When the computer program instructions are executed by a processor, the processor executes the information processing method provided by the embodiments of the present disclosure.

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

[0092] The embodiments of the present disclosure also provide a computer program product, including a computer program / instruction, which implements the information processing method in the embodiments of the present disclosure when executed by a processor.

[0093] It is understandable that before using the technical solutions disclosed in the various embodiments of the present disclosure, the types, scope of use, usage scenarios, etc. of the personal information involved in the present disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0094] For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly prompt the user that the operation requested to be performed will require obtaining and using the user's personal information. Thus, the user can autonomously choose whether to provide personal information to software or hardware such as an electronic device, application, server, or storage medium that performs the operation of the technical solution of the present disclosure according to the prompt message.

[0095] As an optional but non-limiting implementation, in response to receiving an active request from the user, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0096] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0097] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0098] The above description is only a specific embodiment of the present disclosure, so that those skilled in the art can 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 may 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 the 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 in that: include: Determine a target area in a first page, and obtain document object model information corresponding to the target area; wherein the first page is a page for inputting form information; Determine the target input information corresponding to the target area based on the document object model information; Obtain the target form text corresponding to the target area; The target input information is compared with key information in the target form text to determine whether they are consistent, and a comparison result is obtained; wherein the key information is information in the target form text corresponding to the target input information.

2. The method according to claim 1, characterized in that The determining the target input information corresponding to the target area based on the document object model information includes: The document object model information is input into a preset first language model, and the target input information corresponding to the target area is extracted from the document object model information by using the first language model.

3. The method according to claim 2, characterized in that The step of inputting the document object model information into a preset first language model includes: In the case that there are multiple target areas, the document object model information corresponding to the multiple target areas is spliced ​​to obtain an information splicing result; The information concatenation result is input into a preset first language model.

4. The method according to claim 1, characterized in that: The step of obtaining the target form text corresponding to the target area includes: Based on the target input information and a preset form template, a target form text corresponding to the target area is generated.

5. The method according to claim 1, characterized in that The comparing the target input information with the key information in the target form text to determine whether they are consistent, and obtaining a comparison result, includes: The target input information and the target form text are input into a preset second language model, key information corresponding to the target input information in the target form text is determined by the second language model, and the target input information is compared with the key information to obtain a comparison result.

6. The method according to claim 1, characterized in that The method further comprises: The target input information, the target form text and the comparison result are displayed on the second page.

7. The method according to claim 6, characterized in that The method further comprises: When the comparison result indicates that the target input information is inconsistent with the key information in the target form text, correction suggestions for the key information in the target form text are displayed in the second page.

8. The method according to claim 1, characterized in that: The determining of the target area in the first page includes: In response to a region selection operation on the first page, a region corresponding to the region selection operation is determined, and the region corresponding to the region selection operation is used as a target region in the first page.

9. The method according to claim 1, characterized in that: The obtaining document object model information corresponding to the target area includes: The document object model information corresponding to the target area is obtained through a preset plug-in.

10. The method according to any one of claims 1 to 9, characterized in that: The method further comprises: If 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; When the comparison result indicates that the target input information is consistent with key information in the target form text, a final form text is generated based on the target form text.

11. An electronic device, characterized in that: The electronic device comprises: a storage device having a computer program stored thereon; A processing device, used 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 to 10.

12. A computer program product, characterized in that The invention comprises a computer program, which implements the information processing method according to any one of claims 1 to 10 when being executed by a processor.

Images