Form processing method, device, computer equipment and storage medium

Abstract

The present application relates to a form processing method, apparatus, computer equipment, and storage medium. The method comprises: in response to a form editing instruction, calling a robotic process automation model to extract a form to be processed; performing content recognition processing on the form to be processed through the robotic process automation model to obtain keyword information of the form to be processed; determining the category of the form to be processed based on the keyword information; determining an automated executable identification result of the form to be processed based on the category of the form to be processed and the keyword information; and automatically editing the form to be processed if the automated executable identification result indicates that the form to be processed is automated. The use of this method can improve the circulation efficiency of forms.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a form processing method, apparatus, computer equipment, storage medium, and computer program product. Background Art

[0002] Collection and editing refers to the collection and editing of information. In the field of business processing, it is often necessary to collect and edit knowledge of forms based on business needs.

[0003] In related technologies, knowledge base editing systems rely on editors to edit, upload, and submit forms for review based on business needs. For example, after receiving a request for n games to be added to the platform, an editor would manually search the tree nodes in the knowledge tree, then edit and publish the latest information for each game's request form. This approach, where editors manually extract information, edit, and circulate each form individually, results in low form circulation efficiency. Summary of the Invention

[0004] Based on this, it is necessary to provide a form processing method, apparatus, computer equipment, computer-readable storage medium and computer program product to address the technical problem of low form circulation efficiency.

[0005] In a first aspect, the present application provides a form processing method. The method comprises:

[0006] In response to the form collection and editing instruction, the robotic process automation model is called to extract the form to be processed;

[0007] Performing content recognition processing on the form to be processed by the robotic process automation model to obtain keyword information of the form to be processed;

[0008] Determining the category of the form to be processed based on the keyword information;

[0009] Determining an automatically executable recognition result of the form to be processed according to the category of the form to be processed and the keyword information;

[0010] When the result of the automated execution identification is that the form to be processed can be automatically executed, the form to be processed is automatically edited and processed.

[0011] In one embodiment, determining the category of the to-be-processed form based on the keyword information includes:

[0012] Obtaining a preset form feature library, wherein the form feature library is used to store mapping relationships between form features and categories of multiple forms;

[0013] According to the keyword information of the form to be processed, the form feature library is searched to obtain the category of the form to be processed.

[0014] In one embodiment, determining the automatically executable recognition result of the form to be processed based on the category of the form to be processed and the keyword information includes:

[0015] Obtaining a preset knowledge model library; the knowledge model library includes automated execution conditions for different types of forms;

[0016] According to the category of the form to be processed, determining the target automation execution condition corresponding to the form to be processed from the knowledge model library;

[0017] If the keyword information of the form to be processed meets the target automatic execution condition, it is determined that the form to be processed can be automatically executed.

[0018] In one embodiment, the knowledge model library also includes several typical form cases;

[0019] When the form to be processed can be automatically executed, automatically compiling and processing the form to be processed includes:

[0020] In the case where the form to be processed can be automatically executed, the form to be processed is compared with each typical form case in the knowledge model library to obtain the similarity between the form to be processed and each typical form case;

[0021] If the similarity between the form to be processed and any typical form case is greater than a threshold, the form to be processed is edited and processed according to the editing and processing flow corresponding to the typical form case.

[0022] In one embodiment, after determining the automatically executable recognition result of the form to be processed based on the category of the form to be processed and the keyword information, the method further includes:

[0023] If the result of the automated execution identification indicates that the pending form cannot be automatically executed, or if the similarity between the pending form and each typical form case is not greater than a threshold, determining the corresponding order recording conditions for the pending form based on the category; the order recording conditions include the business fields required for order recording and the field information requirements of the required business fields;

[0024] If the current form content of the to-be-processed form meets the order recording condition, the to-be-processed form is automatically recorded.

[0025] In one embodiment, the method further comprises:

[0026] If the current form content of the pending form does not meet the corresponding order recording conditions, the pending form is automatically completed;

[0027] Automatically record the completed pending forms.

[0028] In one embodiment, the automatic information completion process for the pending form includes:

[0029] Based on the current form content of the form to be processed and the order recording conditions corresponding to the form to be processed, the business resource information required by the form to be processed is obtained;

[0030] According to the business resource information, automatic information completion processing is performed on the to-be-processed form.

[0031] In a second aspect, the present application further provides a form processing device. The device comprises:

[0032] A model calling module is used to call the robotic process automation model to extract the form to be processed in response to the form collection and editing instruction;

[0033] A form recognition module is used to perform content recognition processing on the form to be processed through the robotic process automation model to obtain keyword information of the form to be processed;

[0034] A category determination module, configured to determine the category of the form to be processed based on the keyword information;

[0035] A result determination module, configured to determine an automatically executable recognition result of the form to be processed based on the category of the form to be processed and the keyword information;

[0036] The automatic collection and editing module is used to automatically collect and edit the form to be processed when the result of the automatic execution identification is that the form to be processed can be automatically executed.

[0037] In a third aspect, the present application further provides a computer device. The computer device includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are performed:

[0038] In response to the form collection and editing instruction, the robotic process automation model is called to extract the form to be processed;

[0039] Performing content recognition processing on the form to be processed by the robotic process automation model to obtain keyword information of the form to be processed;

[0040] Determining the category of the form to be processed based on the keyword information;

[0041] Determining an automatically executable recognition result of the form to be processed according to the category of the form to be processed and the keyword information;

[0042] When the result of the automated execution identification is that the form to be processed can be automatically executed, the form to be processed is automatically edited and processed.

[0043] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the following steps:

[0044] In response to the form collection and editing instruction, the robotic process automation model is called to extract the form to be processed;

[0045] Performing content recognition processing on the form to be processed by the robotic process automation model to obtain keyword information of the form to be processed;

[0046] Determining the category of the form to be processed based on the keyword information;

[0047] Determining an automatically executable recognition result of the form to be processed according to the category of the form to be processed and the keyword information;

[0048] When the result of the automated execution identification is that the form to be processed can be automatically executed, the form to be processed is automatically edited and processed.

[0049] In a fifth aspect, the present application further provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the following steps:

[0050] In response to the form collection and editing instruction, the robotic process automation model is called to extract the form to be processed;

[0051] Performing content recognition processing on the form to be processed by the robotic process automation model to obtain keyword information of the form to be processed;

[0052] Determining the category of the form to be processed based on the keyword information;

[0053] Determining an automatically executable recognition result of the form to be processed according to the category of the form to be processed and the keyword information;

[0054] When the result of the automated execution identification is that the form to be processed can be automatically executed, the form to be processed is automatically edited and processed.

[0055] The above-mentioned form processing method, apparatus, computer equipment, storage medium, and computer program product, in response to a form collection and editing instruction, calls a robotic process automation model to extract a form to be processed; uses the robotic process automation model to perform content recognition processing on the form to be processed to obtain keyword information of the form to be processed; determines the category of the form to be processed based on the keyword information; determines an automated executable identification result for the form to be processed based on the category and keyword information of the form to be processed; and automatically collects and edits the form to be processed if the automated executable identification result indicates that the form to be processed is automated. By introducing a robotic process automation model to perform intelligent identification and classification of forms, this method can realize the automated execution of the collection and editing process, thereby freeing up human resources and improving the circulation efficiency of forms. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 A flowchart of a form processing method in the prior art;

[0057] Figure 2 1 is a flow chart of a form processing method in one embodiment;

[0058] Figure 3 A flowchart of the steps for determining the recognition results of a form that can be automatically executed in one embodiment;

[0059] Figure 4 A flowchart of a form processing method according to another embodiment;

[0060] Figure 5 This is a schematic diagram of the structure of an RPA-based knowledge base automated editing system for implementing the form processing method of the present application in one embodiment;

[0061] Figure 6 This is a schematic diagram of the execution process of an RPA-based knowledge base automated collection and editing system in one embodiment;

[0062] Figure 7 A schematic diagram of a process for performing keyword sorting, clustering, and tagging on a form in one embodiment;

[0063] Figure 8 A schematic diagram of a process for automatically collecting and editing forms in one embodiment;

[0064] Figure 9 A schematic diagram of a process for automatically recording a form in one embodiment;

[0065] Figure 10 is a structural block diagram of a form processing device in one embodiment;

[0066] Figure 11 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0067] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0068] refer to Figure 1 , is a schematic diagram of the processing flow of processing a form in the prior art, such as Figure 1 As shown, editors can create editing forms through self-service touchpoints to enter forms. For newly added or modified knowledge points, editors need to manually sort keywords according to the business requirements and order content issued by the business manager; the keywords after sorting will be pushed to the corresponding knowledge tree nodes simultaneously; and for knowledge points that need to be taken off the shelves or deleted, editors need to manually perform the expiration operation according to the requirements issued by the business manager; when the form completion information or existing information entered by the editor is ambiguous, the editor needs to manually correct it. Only after the correction is completed can the latest news be released for the changed knowledge points.

[0069] This processing method needs to rely on editors, but due to the different knowledge backgrounds of editors, it is easy to cause non-standard operations, resulting in many form mapping errors; at the same time, when products involving certain nodes under a certain branch of the knowledge tree are offline, personnel are required to manually sort the forms and perform corresponding operations, which is inefficient.

[0070] Based on the above problems, this application proposes the introduction of Robotic Process Automation (RPA) technology, which uses RPA anthropomorphism to sort keywords and automatically connect standard cases to knowledge tree diagrams for the entire network's knowledge base editing forms; for forms that cannot be executed automatically, standardized information and business resource verification results are supplemented to the greatest extent possible to improve form processing efficiency, reduce manual intervention links, and realize batch processing of forms.

[0071] In one embodiment, Figure 2As shown, a form processing method is provided. This embodiment uses the method applied to a terminal as an example for illustration. It is understandable that the method can also be applied to a server, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. Among them, the terminal can be, but is not limited to, various personal computers, laptops, smart phones, tablets, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car-mounted devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The server can be implemented as an independent server or a server cluster consisting of multiple servers. In this embodiment, the method includes the following steps:

[0072] Step S210: In response to the form editing instruction, the robotic process automation model is called to extract the form to be processed.

[0073] The robotic process automation model in this application adopts robotic process automation technology (RPA technology). RPA is a business process automation technology that uses virtual software robots, also known as digital robots or robots, to perform time-consuming manual work or tasks, mainly used to handle repetitive and modular work.

[0074] In specific implementations, after receiving a request for editing, the editor triggers the self-service order recording channel, which aggregates and stores all pending forms in a form cache. When the terminal receives the form editing instruction, it activates the Robotic Process Automation model to extract the pending forms from the form cache and automatically processes them. The number of pending forms can be one or more.

[0075] Step S220 : performing content recognition processing on the form to be processed through the robotic process automation model to obtain keyword information of the form to be processed.

[0076] The keyword information may be understood as words that can represent the information content of the form to be processed.

[0077] In specific implementation, the robotic process automation model can be combined with artificial intelligence technology to identify the content in the form to be processed and extract keyword information from each field in the form.

[0078] In this step, keyword information of the form to be processed is extracted so as to facilitate subsequent classification of the form to be processed based on the keyword information.

[0079] Step S230: Determine the category of the form to be processed based on the keyword information.

[0080] Among them, the categories of forms to be processed can be divided into product categories, fault categories, complaint categories, etc. according to the scenarios, and can also be divided into addition, deletion, modification and other types according to business needs. They can also be classified according to other dimensions. This application does not make specific restrictions on this.

[0081] In a specific implementation, a form feature library can be pre-set to store form features of different categories. After obtaining keyword information of the form to be processed, the form feature library can be queried through the keyword information to obtain the category of the form to be processed.

[0082] Furthermore, in one embodiment, when there are multiple pending forms, after determining the categories of each pending form, the pending forms can be clustered according to their categories. Specifically, pending forms with the same category are grouped as a cluster to form a data warehouse. The pending forms in each cluster are then assigned to different processing terminals based on their categories. Each processing terminal then independently compiles and processes the received pending forms, thereby improving the processing efficiency of the pending forms.

[0083] Step S240 : determining an automatically executable recognition result of the form to be processed based on the category and keyword information of the form to be processed.

[0084] It is understandable that since the form may contain incorrect information, conflict with historical form content, or be ambiguous, in this case, the form content needs to be further verified. Therefore, not all forms can be automatically edited. Therefore, before performing automated editing on the form to be processed, it is also necessary to determine whether the form to be processed can be automatically executed. Specifically, the identification result of the form to be processed that can be automatically executed is determined based on the category and keyword information of the form to be processed.

[0085] In a specific implementation, different types of forms may correspond to different automation execution conditions. Therefore, the target automation execution conditions corresponding to the to-be-processed form may be determined first according to the type of the to-be-processed form. Furthermore, based on the keyword information of the to-be-processed form, it may be determined whether the to-be-processed form meets the target automation execution conditions, thereby obtaining the automation execution identification result of the to-be-processed form.

[0086] Step S250: If the result of the automated execution identification indicates that the form to be processed is automated, the form to be processed is automatically edited and processed.

[0087] In a specific implementation, if the pending form meets the corresponding target automation execution conditions, it can be determined that the pending form can be automatically executed. In this case, the pending form can be automatically collected and processed.

[0088] In the above-mentioned form processing method, in response to a form collection and editing instruction, a robotic process automation model is called to extract a form to be processed; the robotic process automation model is used to perform content recognition processing on the form to be processed to obtain keyword information of the form to be processed; the category of the form to be processed is determined based on the keyword information; based on the category and keyword information of the form to be processed, an automated execution identification result of the form to be processed is determined; if the automated execution identification result indicates that the form to be processed is automated, the form to be processed is automatically collected and edited. By introducing a robotic process automation model to perform intelligent identification and classification of forms, this method can realize the automated execution of the collection and editing process, thereby freeing up human resources and improving the circulation efficiency of forms.

[0089] In an exemplary embodiment, in step S230, the category of the form to be processed is determined based on the keyword information, including: obtaining a preset form feature library, which is used to store the mapping relationship between form features and categories of multiple forms; and querying the form feature library based on the keyword information of the form to be processed to obtain the category of the form to be processed.

[0090] In a specific implementation, for each form category, several sample forms belonging to that category that have been processed historically are obtained. Feature extraction is performed on these sample forms to obtain multiple form features for the forms within that category. A mapping relationship is then established between each form feature and the form category. The multiple form features for each form and the corresponding category are stored in a form feature library, thereby obtaining the form feature library. Furthermore, after obtaining keyword information for the form to be processed, the keyword information can characterize the features of the form to be processed. Therefore, based on the keyword information, a preset form feature library can be queried, and the category of the form to be processed can be obtained based on the mapping relationship in the form feature library.

[0091] More specifically, the form to be processed may be matched with each form feature of each category respectively, and the target category having the largest number of form features matched with the form to be processed is determined based on the matching results, and the target category is used as the category of the form to be processed.

[0092] In this embodiment, a form feature library is pre-set to store form features of different categories of forms, so that after determining the keyword information of the form to be processed, the form feature library can be directly queried to determine the category of the form to be processed, thereby improving the efficiency of determining the category of the form to be processed.

[0093] In an exemplary embodiment, Figure 3 As shown, in step S240, based on the category and keyword information of the form to be processed, the automatically executable recognition result of the form to be processed is determined, including:

[0094] Step S241: Obtain a preset knowledge model library; the knowledge model library includes automation execution conditions for different types of forms;

[0095] Step S242: Determine the target automation execution condition corresponding to the form to be processed from the knowledge model library according to the category of the form to be processed;

[0096] Step S243: If the keyword information of the form to be processed meets the target automation execution condition, it is determined that the form to be processed can be automatically executed.

[0097] In a specific implementation, the automated execution conditions may include whether the execution logic is available, whether it is a typical case, whether the automated execution requirements are met, etc. Since the execution logic and execution requirements of different categories of forms may be different, it is necessary to set corresponding automated execution conditions for different categories of forms, and to establish a mapping relationship between different categories and corresponding automated execution conditions, and to store this mapping relationship in the knowledge model library. After further determining the category of the form to be processed, the knowledge model can be searched and the automated execution conditions corresponding to the form to be processed can be determined from the knowledge model library as the target automated execution conditions. Then, based on the keyword information of the form to be processed, it is determined whether the form to be processed meets the target automated execution conditions. If so, it is determined that the form to be processed can be automatically executed. Otherwise, it is determined that the form to be processed cannot be automatically executed. After obtaining the automated execution identification result of the form to be processed, the form to be processed can be labeled according to the automated execution identification result, and the labeled form to be processed can be stored in the form cache medium.

[0098] In this embodiment, a knowledge model library is pre-set to store the automated execution conditions of different types of forms, so that after determining the category and keyword information of the form to be processed, the knowledge model library can be directly queried to determine the automated execution identification results of the form to be processed, thereby improving the recognition efficiency of the automated execution identification results of the form to be processed, and facilitating further execution of different processing strategies based on the automated execution identification results.

[0099] In an exemplary embodiment, the knowledge model library also includes several typical form cases;

[0100] In the above-mentioned step S250, when the form to be processed can be automatically executed, the step of automatically compiling and processing the form to be processed specifically includes: when the form to be processed can be automatically executed, comparing the form to be processed with each typical form case in the knowledge model library to obtain the similarity between the form to be processed and each typical form case; if the similarity between the form to be processed and any typical form case is greater than a threshold, compiling and processing the form to be processed according to the compilation and processing flow corresponding to any typical form case.

[0101] In a specific implementation, the preset knowledge model library includes not only the automated execution conditions for different types of forms, but also several typical form cases. When it is determined that the form to be processed can be automatically executed, the robotic process automation model can be used to compare the form to be processed with each typical form case in the knowledge model library to obtain the similarity between the form to be processed and each typical form case. When there is a typical form case in each typical form case whose similarity with the form to be processed is greater than a threshold, the form to be processed can be edited and processed according to the editing and processing flow corresponding to the typical form case. Conversely, if the similarity between the form to be processed and each typical form case is not greater than the threshold, the form to be processed is automatically recorded and processed.

[0102] In one embodiment, if there are multiple typical form cases in each typical form case whose similarity with the form to be processed is greater than a threshold, these typical form cases with corresponding similarities greater than the threshold can be sorted according to the numerical value of the similarity, and the form to be processed can be edited and processed according to the editing and processing flow corresponding to the typical form case with the greatest similarity.

[0103] In this embodiment, when the pending form can be automatically executed, the pending form is compared with each typical form case in the knowledge model library. Based on the comparison results, the pending form is edited and processed according to the editing and processing flow corresponding to the typical form case whose similarity with the pending form is greater than the threshold. This allows the pending form to be quickly completed, improving the processing efficiency of the pending form. If the similarity between the pending form and each typical form case is not greater than the threshold, the robotic process automation model is used to automatically complete the information and then automatically record the form. This allows most of the processing flow to be automatically handled by the robotic process automation model, reducing manual intervention and improving the efficiency of form circulation.

[0104] In an exemplary embodiment, after determining the automated execution identification result of the form to be processed based on the category and keyword information of the form to be processed in the above step S240, it also includes: when the automated execution identification result is that the form to be processed cannot be automatically executed, or the similarity between the form to be processed and each typical form case is not greater than a threshold, determining the recording conditions corresponding to the form to be processed according to the category; the recording conditions include the business fields required for recording and the field information requirements of the required business fields; if the current form content of the form to be processed meets the recording conditions, the form to be processed is automatically recorded.

[0105] In a specific implementation, if the automated execution identification result of the pending form is determined to be non-automatic based on the category and keyword information of the pending form, or if the similarity between the pending form and each typical form case is not greater than the threshold, it indicates that there is a problem with the pending form. In order to improve the efficiency of form processing, the pending form can be automatically recorded. However, automatic recording also has some restrictive recording conditions, and not every form can be automatically recorded. Therefore, after determining that the pending form cannot be automatically executed, the recording conditions corresponding to the pending form can be further determined to determine whether the pending form meets the corresponding recording conditions. If so, the pending form can be automatically recorded.

[0106] More specifically, different categories of forms correspond to different order recording conditions. Therefore, the order recording conditions corresponding to the form to be processed can be determined based on the category of the form to be processed obtained in advance. The order recording conditions may include the business fields required for order recording and the field information requirements of the required business fields. The current form content of the form to be processed is then matched with the business fields required for the form of the category to be processed and the field information requirements of the required business fields to determine whether the current form content of the form to be processed meets the order recording conditions. If the current form content of the form to be processed lacks field information of certain business fields, or the field information of certain business fields does not meet the corresponding field information requirements, it can be determined that the current form content of the form to be processed does not meet the order recording conditions. Conversely, if the current form content of the form to be processed includes the business fields required for the form of the category to which it belongs, and the field information also meets the corresponding field information requirements, it can be determined that the current form content of the form to be processed meets the order recording conditions, and the form to be processed can be automatically recorded and processed through the robotic process automation model.

[0107] Furthermore, in an exemplary embodiment, the form processing method further includes: if the current form content of the form to be processed does not meet the corresponding order recording conditions, automatically completing the information of the form to be processed; and automatically recording the completed form to be processed.

[0108] Among them, information completion may include information modification and information filling.

[0109] In the specific implementation, if the current form content of the pending form does not meet the corresponding order recording conditions, it indicates that the current form content of the pending form lacks field information of certain business fields, or the field information of certain business fields does not meet the corresponding field information requirements. Then, the robotic process automation model can be used to automatically complete the information of the pending form to obtain the completed pending form that meets the order recording conditions, and then the completed pending form is automatically recorded.

[0110] In this embodiment, for pending forms that cannot be automatically executed, it is first determined whether they meet the order recording conditions. If they do, the pending forms are automated through the robotic process automation model. If they do not, the robotic process automation model is used to automatically complete the information so that the pending forms meet the order recording conditions, and then automatically record the forms. In this way, most of the processing processes can be automatically handled by the robotic process automation model, reducing manual intervention and improving the efficiency of form circulation.

[0111] In an exemplary embodiment, automatic information completion processing is performed on the form to be processed, including: obtaining business resource information required for the form to be processed based on the current form content of the form to be processed and the order recording conditions corresponding to the form to be processed; and automatically completing the information of the form to be processed according to the business resource information.

[0112] In the specific implementation, in order to complete the information of the form to be processed, it is necessary to determine the current form content and the completion benchmark or basis of the form to be processed. In this embodiment, the recording conditions corresponding to the form to be processed are used as the completion benchmark. Based on the current form content of the form to be processed and the recording conditions corresponding to the form to be processed, the fields that are inconsistent with the current form content and the recording conditions can be determined, and then the required business resource information is obtained from the resource provision system, which can be specifically the field information of the inconsistent fields. The obtained field information of the inconsistent fields is then supplemented to the form to be processed to obtain the completed form to be processed.

[0113] In this embodiment, based on the current form content of the form to be processed and the order recording conditions corresponding to the form to be processed, the business resource information required for the form to be processed is obtained from the resource provision system, and the information completion processing of the form to be processed is performed automatically according to the business resource information. This process is implemented by the robotic process automation model, which can reduce manual intervention and improve form processing efficiency.

[0114] refer to Figure 4 , is a flow chart of a form processing method provided by another exemplary embodiment of the present application. In this embodiment, the following steps are included:

[0115] Step S401, in response to the form collection and editing instruction, calling the robotic process automation model to extract the form to be processed;

[0116] Step S402: Using the Robotic Process Automation model, content recognition is performed on the form to be processed to obtain keyword information of the form to be processed;

[0117] Step S403: querying a preset form feature library based on the keyword information of the form to be processed to obtain the category of the form to be processed;

[0118] Step S404: Determine the target automation execution condition corresponding to the form to be processed from a preset knowledge model library according to the category of the form to be processed;

[0119] Step S405: determining whether the form to be processed is an automated execution result based on the keyword information of the form to be processed;

[0120] Step S406: If the form to be processed can be automatically executed, the form to be processed is compared with each typical form case in the knowledge model library to obtain the similarity between the form to be processed and each typical form case;

[0121] Step S407: determining whether there is a target typical form case among the typical form cases whose similarity to the form to be processed is greater than a threshold;

[0122] Step S408: If yes, then the form to be processed is processed according to the collection and editing process corresponding to the target typical form case; if not, then the form to be processed is automatically recorded;

[0123] Step S409: If the pending form cannot be automatically executed, the corresponding record conditions of the pending form are determined according to the category;

[0124] Step S410: determine whether the current form content of the form to be processed meets the order recording conditions;

[0125] Step S411: If yes, the form to be processed is automatically recorded.

[0126] Step S412: If not, the form to be processed is automatically completed, and the completed form to be processed is automatically recorded.

[0127] The form processing method provided in this embodiment can realize the automated execution of the editing process by introducing a robotic process automation model to perform intelligent identification and classification of forms, thereby freeing up human resources and improving the circulation efficiency of forms.

[0128] In one embodiment, in order to facilitate those skilled in the art to understand the embodiments of the present application, specific examples will be described below with reference to the accompanying drawings.

[0129] refer to Figure 5 , provides a structural diagram of an RPA-based knowledge base automated editing system for implementing the form processing method of this application, including: RPA computer equipment, configuration module, feature library, knowledge template library, policy center and automated execution module. This application adds PRA computer equipment to the existing editing and processing flow to implement anthropomorphic sorting and standardized processing of all the editing form keywords on the entire network. Among them:

[0130] RPA computer equipment is the core module of anthropomorphic operations. It can automatically sort the keywords of the editing forms through instance feature information such as the form feature library and the knowledge model library, and combine the knowledge model library and product deadline recognition results to mark whether the forms to be processed can be automatically executed.

[0131] For the forms that can be automatically executed in the editing and compiling forms to be processed, the RPA computer equipment uses the automation execution module. Based on the knowledge model library and strategy center, it quickly processes the pending forms that have a similarity of more than 90% with the typical form cases in the knowledge model library and outputs the latest message column; for the pending forms with a similarity of less than 90%, it performs automated recording processing based on the editing and compiling processing strategy, and records the processing results and publishes them in the latest message column on the knowledge base homepage.

[0132] For forms that cannot be automatically executed in the editing and processing forms, RPA computer equipment uses the automated execution module. Based on the policy center, it matches the business field information, business verification information and other recording conditions required by the corresponding form system, and automatically records the form to generate the corresponding form to be processed, returning to the original manual processing process.

[0133] Automated execution module: This module is primarily used by RPA to perform functions such as collecting and editing knowledge points, sorting keywords, automating form processing, and intelligently recording orders.

[0134] Form feature library: used to store editing form features, knowledge type features, scenario phenomenon features, etc., and provide keyword sorting and scenario type support.

[0135] Knowledge model library: used to store the automated execution conditions and typical form case information of different types of forms, supporting automated scenario services and editing form processing.

[0136] Strategy Center: Used to store editing form processing strategies, customer automated return visit strategies, and information completion strategies to support automated processing capabilities.

[0137] refer to Figure 6 The following figure shows the execution process of the RPA-based knowledge base automated collection and editing system, which includes the following steps:

[0138] ① After receiving the editing requirements, the editor will trigger the automated editing operation independently, and the RPA robot will take over, extract the keywords of the form, and classify the form in combination with the form feature library, and store it in clusters.

[0139] ②The PRA robot identifies whether the form can be automatically executed based on the form's category, keywords, and knowledge model library, and caches the preliminary judgment results to the form cache medium.

[0140] ③For forms that cannot be executed automatically, the RPA robot will perform automatic order recording operations.

[0141] ④ For forms that can be executed automatically, the RPA robot further compares the form with various typical form cases in the knowledge model to determine whether there is a target typical form case whose similarity with the form is greater than the threshold.

[0142] ⑤ If it does, the RPA robot will automatically compile the form according to the compilation and editing process of the target typical form case. Specifically, this can be combined with the strategy center to perform operations such as business information verification and resource information verification, and perform automated business online and offline processing.

[0143] ⑥After the form processing is completed, it will be published to the latest news column.

[0144] ⑦If it does not exist, the RPA robot will perform the automatic order recording operation as in step ③.

[0145] Specifically, the steps for the RPA robot to perform automatic order recording operations include:

[0146] ⑧Compare the order recording conditions corresponding to the current content of the form.

[0147] ⑨If the current content does not meet the order recording conditions, the RPA robot can obtain business resource information through the corresponding support system based on the strategy center and automatically complete the form information.

[0148] ⑩The RPA robot completes the relevant field information and performs automated order recording, notifying the corresponding form processing personnel to handle it, and the form returns to the existing manual processing process.

[0149] refer to Figure 7 , is a flow chart of performing keyword sorting and clustering on a form provided by an embodiment, including the following steps:

[0150] ① The editor triggers the self-service order recording channel, and all pending requests are aggregated in the full form cache medium (readable storage medium);

[0151] ②The RPA robot module begins to intervene and perform keyword sorting and form clustering tasks.

[0152] ③The RPA robot uses the automated execution module and AI-based capabilities to extract form content and keywords from each form field.

[0153] ④The RPA robot uses the automated execution module to classify forms based on the feature information recorded in the form feature library.

[0154] ⑤The RPA robot clusters the sorted work orders based on the classification results to form a data warehouse.

[0155] ⑥The RPA robot uses the automatic execution module to match the classification results and keywords with the knowledge model library to determine whether the form has the characteristics that can be automatically executed, including: whether it has execution logic, whether it is a typical case, and whether it meets the requirements for automated execution.

[0156] ⑦ Based on the result of determining whether the form has the characteristics that can be automatically executed, an automated execution label is generated and each form is marked.

[0157] ⑧Store the form with the label in the form cache medium.

[0158] refer to Figure 8 , which is a flow chart of an embodiment of the automatic editing of forms, including the following steps:

[0159] ①The RPA robot extracts the form to be processed from the form cache medium.

[0160] ② According to the form category and keywords, match the form processing flow, processing logic and processing method of the corresponding characteristics of the strategy center.

[0161] ③ The forms that can be executed automatically start the automatic execution process; the forms that cannot be executed automatically are transferred to the automatic order recording process (see Figure 9 ); the automated execution process includes the following steps:

[0162] ④The RPA robot compares the form to be processed with the knowledge model library. If it can match a typical form case with a similarity greater than the threshold, it quickly generates a result and executes ⑦ and ⑧. After the form is posted, it is broadcast to the latest news column.

[0163] ⑤ If a typical form case with a similarity greater than the threshold cannot be matched, the RPA robot obtains resource information, business information and information required for business acceptance through the relevant support system according to the form processing logic and processing method, and executes Figure 9 The form recording processing flow is shown.

[0164] ⑥After the form is completed, the interface capability is called to inform the business manager of the processing results.

[0165] ⑦RPA will attach the completed form to the corresponding node of the knowledge tree and archive it, while deleting the relevant information of the form cache medium.

[0166] refer to Figure 9 , is a flowchart of an embodiment of an automatic recording operation for a form that cannot be automatically executed, including the following steps:

[0167] ① The RPA robot obtains the tasks of the forms to be processed from the form cache medium and executes this process for the forms that cannot be automated.

[0168] ② Sort the results based on the form keywords and obtain the business fields required for recording the corresponding form from the production and sales system / form system / installation and maintenance system.

[0169] ③RPA robots perform intelligent order recording, including filling in basic form information, form content, and preliminary resource audits, business audits, and other information.

[0170] ④ The strategy center provides support for algorithms, resource addresses, network resource pools and other related information based on the needs of automated order recording.

[0171] ⑤The RPA robot performs resource audits or business situation audits based on the required business fields and resource addresses, and records the audit content.

[0172] ⑥ When the business support system is unable to supplement relevant resource information, third-party network resources are obtained through the Internet, such as information on various IPTV games, etc., to complete and standardize the information.

[0173] ⑦ When information cannot be completed through the business system and web crawlers, the necessary business information can be obtained by interacting with the business manager through calling AI capabilities.

[0174] ⑧The RPA robot automatically records the form in the corresponding form system and deletes the form cache information.

[0175] The form processing method proposed in this application has the following advantages: (1) By introducing RPA computer equipment, the work of business editors can be effectively analyzed, and most processes can be automated by machines. (2) By supplementing intelligent technology and standardized cases, keyword mapping relationships can be automatically extracted. (3) By standardizing the form processing process, batch operations of businesses under leaf nodes can be realized.

[0176] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0177] Based on the same inventive concept, embodiments of the present application also provide a form processing device for implementing the aforementioned form processing method. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations of one or more form processing device embodiments provided below can be found in the above-described limitations of the form processing method and will not be further elaborated here.

[0178] In one embodiment, Figure 10 As shown, a form processing device is provided, comprising: a model calling module 1001, a form recognition module 1002, a category determination module 1003, a result determination module 1004 and an automatic collection and editing module 1005, wherein:

[0179] The model calling module 1001 is used to call the robotic process automation model to extract the form to be processed in response to the form collection and editing instruction;

[0180] The form recognition module 1002 is used to perform content recognition processing on the form to be processed through the robotic process automation model to obtain keyword information of the form to be processed;

[0181] Category determination module 1003, used to determine the category of the form to be processed based on the keyword information;

[0182] Result determination module 1004, for determining the automatically executable recognition result of the form to be processed based on the category and keyword information of the form to be processed;

[0183] The automatic collection and editing module 1005 is used to automatically collect and edit the form to be processed when the result of the automatic execution recognition is that the form to be processed can be automatically executed.

[0184] In one embodiment, the category determination module 1003 is further used to obtain a preset form feature library, which is used to store the mapping relationship between form features and categories of multiple forms; based on the keyword information of the form to be processed, the form feature library is queried to obtain the category of the form to be processed.

[0185] In one embodiment, the result determination module 1004 is further used to obtain a preset knowledge model library; the knowledge model library includes automation execution conditions for forms of different categories; according to the category of the form to be processed, the target automation execution condition corresponding to the form to be processed is determined from the knowledge model library; if the keyword information of the form to be processed meets the target automation execution condition, it is determined that the form to be processed can be automatically executed.

[0186] In one embodiment, the knowledge model library also includes several typical form cases; the automatic editing module 1005 is also used to compare the form to be processed with each typical form case in the knowledge model library when the form to be processed can be automatically executed, and obtain the similarity between the form to be processed and each typical form case; if the similarity between the form to be processed and any typical form case is greater than a threshold, the form to be processed is edited and processed according to the editing and processing flow corresponding to any typical form case.

[0187] In one embodiment, the form processing device also includes an automatic recording module, which is used to determine the recording conditions corresponding to the form to be processed according to the category when the automated execution recognition result is that the form to be processed cannot be automatically executed, or the similarity between the form to be processed and each typical form case is not greater than a threshold; the recording conditions include the business fields required for recording and the field information requirements of the required business fields; if the current form content of the form to be processed meets the recording conditions, the form to be processed is automatically recorded.

[0188] In one embodiment, the automatic order recording module is also used to automatically complete the information of the form to be processed if the current form content of the form to be processed does not meet the corresponding order recording conditions; and automatically record the completed form to be processed.

[0189] In one embodiment, the automatic order recording module is also used to obtain the business resource information required for the form to be processed based on the current form content of the form to be processed and the order recording conditions corresponding to the form to be processed; and automatically complete the information of the form to be processed based on the business resource information.

[0190] Each module in the above-mentioned form processing device can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in the computer device in the form of software, so that the processor can call and execute the corresponding operations of each module.

[0191] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 11As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a form processing method is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad provided on the computer device housing, or an external keyboard, touchpad or mouse.

[0192] Those skilled in the art will understand that Figure 11 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0193] In one embodiment, a computer device is further provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0194] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0195] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0196] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions.

[0197] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processor involved in the various embodiments provided herein may be, but are not limited to, a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, and the like.

[0198] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0199] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A form processing method, characterized in that: The method comprises: In response to the form collection and editing instruction, the robotic process automation model is called to extract the form to be processed; Performing content recognition processing on the form to be processed by the robotic process automation model to obtain keyword information of the form to be processed; Determining the category of the form to be processed based on the keyword information; Determining an automated execution identification result of the pending form based on the category of the pending form and the keyword information; specifically, determining a target automated execution condition corresponding to the pending form from a preset knowledge model library based on the category of the pending form; and determining that the pending form is automated execution capable if the keyword information of the pending form meets the target automated execution condition; the knowledge model library includes automated execution conditions for forms of different categories; When the result of the automated execution identification is that the form to be processed can be automatically executed, the form to be processed is automatically edited and processed.

2. The method according to claim 1, characterized in that Determining the category of the to-be-processed form based on the keyword information includes: Obtaining a preset form feature library, wherein the form feature library is used to store mapping relationships between form features and categories of multiple forms; According to the keyword information of the form to be processed, the form feature library is searched to obtain the category of the form to be processed.

3. The method according to claim 1, characterized in that The knowledge model library also includes several typical form cases; When the form to be processed can be automatically executed, automatically compiling and processing the form to be processed includes: In the case where the form to be processed can be automatically executed, the form to be processed is compared with each typical form case in the knowledge model library to obtain the similarity between the form to be processed and each typical form case; If the similarity between the form to be processed and any typical form case is greater than a threshold, the form to be processed is edited and processed according to the editing and processing flow corresponding to the typical form case.

4. The method according to claim 1 or 3, characterized in that After determining the automatically executable recognition result of the form to be processed according to the category of the form to be processed and the keyword information, the method further includes: If the result of the automated execution identification indicates that the pending form cannot be automatically executed, or if the similarity between the pending form and each typical form case is not greater than a threshold, determining the corresponding order recording conditions for the pending form based on the category; the order recording conditions include the business fields required for order recording and the field information requirements of the required business fields; If the current form content of the to-be-processed form meets the order recording condition, the to-be-processed form is automatically recorded.

5. The method according to claim 4, characterized in that The method further comprises: If the current form content of the pending form does not meet the corresponding order recording conditions, the pending form is automatically completed; Automatically record the completed pending forms.

6. The method according to claim 5, characterized in that The automatic information completion process for the to-be-processed form includes: Based on the current form content of the form to be processed and the order recording conditions corresponding to the form to be processed, the business resource information required by the form to be processed is obtained; According to the business resource information, automatic information completion processing is performed on the to-be-processed form.

7. A form processing device, characterized in that: The device comprises: A model calling module is used to call the robotic process automation model to extract the form to be processed in response to the form collection and editing instruction; A form recognition module is used to perform content recognition processing on the form to be processed through the robotic process automation model to obtain keyword information of the form to be processed; A category determination module, configured to determine the category of the form to be processed based on the keyword information; A result determination module is configured to determine, based on the category of the pending form and the keyword information, an identification result of whether the pending form is capable of automated execution. Specifically, based on the category of the pending form, the module determines, from a preset knowledge model library, a target automated execution condition corresponding to the pending form. If the keyword information of the pending form meets the target automated execution condition, the module determines that the pending form is capable of automated execution. The knowledge model library includes automated execution conditions for forms of different categories. The automatic collection and editing module is used to automatically collect and edit the form to be processed when the result of the automatic execution identification is that the form to be processed can be automatically executed.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the form processing method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the form processing method according to any one of claims 1 to 6 are implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the form processing method according to any one of claims 1 to 6 are implemented.

Images