Information Generation Method, Device, Electronic Device and Storage Medium Combining RPA and AI

Abstract

The present disclosure provides an information generation method, apparatus, electronic device, and storage medium combining RPA and AI, which are applied to a robotic process automation (RPA) robot. The method includes: obtaining a standardized document, where the standardized document includes information on elements to be processed, determining the element type corresponding to the standardized document, and then determining a target recommended object matching the element type, where the target recommended object has corresponding object description information, and processing the information on the elements to be processed according to the object description information to obtain target element information. Thus, it is possible to effectively reduce the difficulty of analyzing and interpreting the standardized document, and thereby be able to intelligently generate target element information adapted to the target recommended object based on the standardized document, effectively improving the generation efficiency and generation accuracy of the element information, and further effectively improving the generation effect of the element information.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular, to a method, apparatus, electronic device, and storage medium for generating information of robotic process automation (RPA) and artificial intelligence (AI). Background Art

[0002] Robotic Process Automation (RPA) refers to using specific "robot software" to simulate human operations on a computer and automatically execute process tasks according to rules.

[0003] Artificial Intelligence (AI) is a technical science that studies, develops theories, methods, technologies, and application systems for simulating, extending, and expanding human intelligence.

[0004] Standardized documents, which can be, for example, preferential assistance development plan documents, reward and punishment plan documents, etc. When executing the element information in the standardized documents, different standardized documents can be respectively adapted to different recommended objects (recommended objects such as enterprises, users, etc.).

[0005] In the related art, in order to provide adapted standardized documents for different recommended objects, it is necessary to fully interpret the element information in the standardized documents so that the standardized documents provided for different recommended objects can effectively meet the personalized needs of different recommended objects.

[0006] In this way, due to the diverse forms of standardized documents and the large amount of information contained in the standardized documents, it is difficult to analyze and interpret the standardized documents. When generating element information recommended to the recommended object based on the standardized document, it is impossible to intelligently generate element information adapted to the recommended object, resulting in low generation efficiency and accuracy of the element information and poor generation effects. Summary of the Invention

[0007] Embodiments of the present disclosure provide a method and apparatus for generating information by combining RPA and AI to solve the problems existing in the related art. The technical solutions are as follows:

[0008] In a first aspect, an information generation method combining RPA and AI proposed by an embodiment of the present disclosure is applied to an RPA robot, and includes: obtaining a standardized document, where the standardized document includes: information on elements to be processed; determining an element type corresponding to the standardized document; determining a target recommended object matching the element type, where the target recommended object has corresponding object description information; and processing the information on elements to be processed according to the object description information to obtain target element information.

[0009] In a second aspect, an information generation device combining RPA and AI proposed by an embodiment of the present disclosure is applied to an RPA robot, and includes: an obtaining module for obtaining a standardized document, where the standardized document includes: information on elements to be processed; a first determination module for determining an element type corresponding to the standardized document; a second determination module for determining a target recommended object matching the element type, where the target recommended object has corresponding object description information; and a processing module for processing the information on elements to be processed according to the object description information to obtain target element information.

[0010] In a third aspect, an electronic device proposed by an embodiment of the present disclosure includes: a memory, a processor, and a computer program stored on the memory and executable on the processor, and is characterized in that when the processor executes the program, it implements an information generation method combining RPA and AI provided in the embodiment of the first aspect.

[0011] In a fourth aspect, the present disclosure provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, it implements an information generation method combining RPA and AI provided in the embodiment of the first aspect.

[0012] The advantages or beneficial effects in the above technical solutions at least include:

[0013] In the embodiment of the present disclosure, by obtaining a standardized document, where the standardized document includes: information on elements to be processed, determining an element type corresponding to the standardized document, then determining a target recommended object matching the element type, where the target recommended object has corresponding object description information, and processing the information on elements to be processed according to the object description information to obtain target element information, thus, it can effectively reduce the difficulty of analyzing and interpreting the standardized document, and thereby can intelligently generate target element information adapted to the target recommended object based on the standardized document, effectively improving the generation efficiency and generation accuracy of the element information, and further effectively improving the generation effect of the element information.

[0014] The above summary is for the purpose of the specification only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments, and features described above, further aspects, embodiments, and features of the present disclosure will be readily apparent by reference to the drawings and the following detailed description. Description of the Drawings

[0015] In the drawings, unless otherwise specified, the same reference numerals throughout the several views denote the same or similar components or elements. These drawings are not necessarily drawn to scale. It should be understood that these drawings depict only some embodiments proposed in accordance with the present disclosure and should not be regarded as limiting the scope of the present disclosure.

[0016] Figure 1 is a schematic flowchart of an information generation method combining RPA and AI proposed in an embodiment of the present disclosure;

[0017] Figure 2 is a schematic flowchart of an information generation method combining RPA and AI proposed in another embodiment of the present disclosure;

[0018] Figure 3 is a schematic flowchart of an information generation method combining RPA and AI proposed in another embodiment of the present disclosure;

[0019] Figure 4 is a schematic flowchart of the extraction process of information on elements to be processed proposed in an embodiment of the present disclosure;

[0020] Figure 5 is a schematic flowchart of an information generation method combining RPA and AI proposed in another embodiment of the present disclosure;

[0021] Figure 6 is a schematic structural diagram of an information generation device combining RPA and AI proposed in an embodiment of the present disclosure;

[0022] Figure 7 is a schematic structural diagram of an information generation device combining RPA and AI proposed in another embodiment of the present disclosure;

[0023] Figure 8 is a schematic hardware structure diagram of an electronic device provided in an embodiment of the present disclosure. Detailed Embodiments

[0024] Embodiments of the present disclosure are described in detail below. Examples of the embodiments are shown in the drawings, where the same or similar reference numerals throughout denote the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the drawings are exemplary only for explaining the present disclosure and should not be construed as limiting the present disclosure.

[0025] In the description of the embodiments of the present disclosure, the term "a plurality of" means two or more.

[0026] In the description of the embodiments of the present disclosure, the term "Robotic Process Automation (RPA)" means that it can provide another way to automate the manual operation process of end users by mimicking the manual operation mode of end users on a computer.

[0027] In the description of the embodiments of the present disclosure, the term "Natural Language Processing (NPL)" refers to the technology of using the natural language used by humans for communication to interact with machines. Through artificial processing of natural language, the computer can read and understand it. The related research on natural language processing began with the exploration of machine translation by humans.

[0028] In the description of the embodiments of the present disclosure, the term "Optical Character Recognition (OCR)" refers to the process in which an electronic device checks the characters printed on paper, determines their shapes by detecting dark and bright patterns, and then translates the shapes into computer text using character recognition methods; that is, for printed characters, the text in a paper document is converted into a black-and-white dot-matrix image file in an optical manner, and the text in the image is converted into a text format by an identification software for further editing and processing by a word processing software.

[0029] In the description of the embodiments of the present disclosure, the term "RPA robot" refers to a robot that can implement automated execution of corresponding business operations based on a pre-set automated operation process.

[0030] In the description of the embodiments of the present disclosure, the term "standardized document" refers to a document available for users to refer to on a multi-party platform, such as a reward and punishment plan document, a preferential assistance development plan document, etc.

[0031] In the description of the embodiments of the present disclosure, the term "element information to be processed" refers to multiple element information included in a standardized document, such as content element information, identification element information, and feature element information in a standardized document, and specifically can be, for example, reward standard content information, preferential index information, etc.

[0032] In the description of the embodiments of the present disclosure, the term "element type" refers to the category to which the elements to be processed in the standardized document belong, that is, the information of the elements to be processed in the standardized document is divided based on different classification dimensions to obtain elements to be processed of different element types. For example, the elements to be processed in the standardized document can be divided into reward types, penalty types, etc. based on the content classification dimension, or the elements to be processed can also be divided into picture types, text types, etc. based on the corresponding presentation forms of the elements to be processed in the standardized document.

[0033] In the description of the embodiments of the present disclosure, the term "target recommended object" refers to a recommended object that is adapted to the information of the elements to be processed in the standardized document when executing the element information in the standardized document. For example, an enterprise, a user, etc.

[0034] In the description of the embodiments of the present disclosure, the term "object description information" refers to the information used to describe the target recommended object. For example, the name information of the target recommended object, the identification information of the target recommended object, etc.

[0035] Referring to the following description and drawings, these and other aspects of the embodiments of the present disclosure will be clear. In these descriptions and drawings, some specific embodiments in the embodiments of the present disclosure are specifically disclosed to represent some ways of implementing the principles of the embodiments of the present disclosure. However, it should be understood that the scope of the embodiments of the present disclosure is not limited thereto. On the contrary, the embodiments of the present disclosure include all changes, modifications, and equivalents falling within the spirit and connotation of the appended claims.

[0036] Figure 1 It is a schematic flowchart of an information generation method combining RPA and AI proposed by an embodiment of the present disclosure.

[0037] In this embodiment, the information generation method combining RPA and AI is exemplified as being configured in an information generation device combining RPA and AI. In this embodiment, the information generation method combining RPA and AI can be configured in an information generation device combining RPA and AI. The information generation device combining RPA and AI can be set in a server, or can also be set in an electronic device. The embodiments of the present disclosure do not limit this.

[0038] See Figure 1 , the information generation method combining RPA and AI includes:

[0039] S101: Obtain a standardized document, where the standardized document includes: information of elements to be processed.

[0040] Among them, the standardized document can be a document published on a multi-party platform. This document can be specifically, for example, a reward and punishment plan document, a preferential assistance for development plan document, etc. There is no limitation on this.

[0041] Among them, the standardized document may include multiple element information, which can be referred to as the element information to be processed. The element information to be processed can be content element information, identification element information, characteristic element information, etc. in the standardized document. Specifically, for example, it can be reward standard content information, preferential index information, etc., and there is no limitation on this.

[0042] In the embodiments of the present disclosure, obtaining the standardized document may be that the RPA robot provides a corresponding file transfer interface, and a data transfer path is established between the RPA robot and the multi-party platform through this file transfer interface. Then, based on this data transfer path, the standardized document published by the multi-party platform is obtained. Or, obtaining the standardized document may also be to pre-configure a corresponding monitoring device for the RPA robot. Then, the RPA robot can monitor the multi-party platform based on this monitoring device, and when it monitors that the multi-party platform newly publishes a standardized document and / or updates the published standardized document, download the corresponding standardized document from the multi-party platform, and there is no limitation on this.

[0043] After obtaining the standardized document in the embodiments of the present disclosure, the standardized document can be parsed to identify multiple element information to be processed from the standardized document.

[0044] In some embodiments, the standardized document can be parsed by using the text parsing method, that is, multiple text information can be identified from the standardized document by using the text parsing method, and the multiple text information identified above is used as the element information to be processed. Or, other any possible methods can also be used to parse the standardized document to identify multiple element information to be processed from the standardized document. For example, the feature parsing method, the model parsing method, etc., and there is no limitation on this.

[0045] S102: Determine the element type corresponding to the standardized document.

[0046] Among them, the element type can be used to describe the category to which the element to be processed in the standardized document belongs. That is to say, the element information to be processed in the standardized document can be divided based on different classification dimensions to obtain elements to be processed of different element types. For example, the elements to be processed in the standardized document can be divided into reward types, punishment types, etc. based on the content classification dimension. Or, the elements to be processed can also be divided into picture types, text types, etc. based on the corresponding manifestation forms of the elements to be processed in the standardized document, and there is no limitation on this.

[0047] In some embodiments, it may be to determine the element type corresponding to the standardized document in combination with a pre-trained artificial intelligence model. That is, after parsing and identifying the information of the element to be processed from the standardized document, the RPA robot inputs the element to be processed into the pre-trained artificial intelligence model to obtain the element type corresponding to the standardized document output by the pre-trained artificial intelligence model. There is no limitation on this.

[0048] In other embodiments, to determine the element type corresponding to the standardized document, it may also be to perform semantic parsing on the information of the element to be processed after parsing and identifying the information of the element to be processed from the standardized document, so as to obtain the corresponding semantic parsing result, and determine the element type corresponding to the standardized document according to the semantic parsing result. There is no limitation on this.

[0049] For example, assuming that the information of the element to be processed parsed and identified from the standardized document is: "Reward 100,000 yuan", "Fine 100,000 yuan", then the semantic parsing can be performed on the above-mentioned parsed and identified information of the element to be processed to determine that the element type corresponding to the information of the element to be processed: "Reward 100,000 yuan" is the reward type, and the element type corresponding to the information of the element to be processed: "Fine 100,000 yuan" is the penalty type. There is no limitation on this.

[0050] S103: Determine the target recommended object that matches the element type, where the target recommended object has corresponding object description information.

[0051] In the embodiments of the present disclosure, when executing the element information in the standardized document, different standardized documents can be respectively adapted to different recommended objects (the recommended objects are, for example, enterprises, users, etc.). Correspondingly, the object obtained above that matches the element type corresponding to the standardized document can be called the target recommended object.

[0052] Among them, the information used to describe the target recommended object can be called object description information. The object description information can specifically be, for example, the name information of the target recommended object, the identification information of the target recommended object, or the object description information can also be other information of any possible dimension used to describe the target recommended object correspondingly. There is no limitation on this.

[0053] In the subsequent embodiments of the present disclosure, the target recommended object is taken as an enterprise for specific explanation. That is to say, a specific application scenario of the embodiments of the present disclosure can be specifically, for example: obtaining a standardized document, then determining the element type corresponding to the element information to be processed in the standardized document (for example, reward type, preferential subsidy type, etc.), and determining the enterprises that match the foregoing element type, and then determining the object description information of the enterprises (for example: turnover information, tax payment information, etc.). Then, the element information to be processed is processed according to the object description information of the enterprises to provide the target element information adapted to the enterprises, so that the enterprises can execute the solutions involved in the target element information according to the target element information (for example, the enterprises can apply for preferential subsidy plans and rewards according to the target element information adapted to them), thereby effectively helping the enterprises to fully interpret the information in the standardized document and make full use of the standardized document, and further effectively contributing to the development of the enterprises.

[0054] It should be noted that the embodiments of the present disclosure can also be applied to any other possible information generation scenarios, and no limitation is imposed thereon.

[0055] In the embodiments of the present disclosure, to determine the target recommended object that matches the element type, it can be that the RPA robot combines the existing large database system to parse the object description information of the target recommended object stored in the large database to determine the object description information that matches the element type, and use the recommended object corresponding to the object description information as the target recommended object, and no limitation is imposed thereon.

[0056] In some embodiments, the RPA robot can also directly obtain the target recommended object that matches the element type from the large database system according to the pre-established correspondence between the element type and the target recommended object, regularly monitor the relevant object description information of the target recommended object, collect and store the newly generated object description information in the database, and compare it with the existing object description information in the large database system. If the object description information has changed, the existing object description information is updated, and no limitation is imposed thereon.

[0057] S104: Process the element information to be processed according to the object description information to obtain the target element information.

[0058] After determining the target recommended object that matches the element type in the embodiments of the present disclosure, the element information to be processed can be processed according to the object description information corresponding to the target recommended object to obtain the target element information.

[0059] In some embodiments, processing the to-be-processed element information according to the object description information may be for an RPA robot to determine whether the object description information and the to-be-processed element information match, and when the object description information and the to-be-processed element information match, directly use the to-be-processed element information as the target element information.

[0060] For example, assume that the object description information is: "The monthly turnover increase rate of the enterprise is 30%", and the to-be-processed element information is: "If the monthly turnover increase rate is higher than 20%, a reward of 100,000 yuan will be given". Then, determining whether the object description information and the to-be-processed element information match may be to determine whether "The monthly turnover increase rate of the enterprise is 30%" meets the turnover increase rate condition described in the to-be-processed element information, and when "The monthly turnover increase rate of the enterprise is 30%" meets the increase rate condition described in "If the monthly turnover increase rate is higher than 20%, a reward of 100,000 yuan will be given", it is determined that the object description information and the to-be-processed element information match, and when the object description information and the to-be-processed element information match, use the to-be-processed element information "If the monthly turnover increase rate is higher than 20%, a reward of 100,000 yuan will be given" as the target element information, and there is no limitation on this.

[0061] Alternatively, determining whether the object description information and the to-be-processed element information match may also be to determine the similarity between the object description information and the to-be-processed element information, and when the similarity is greater than the similarity threshold, determine that the object description information and the to-be-processed element information match, and when the object description information and the to-be-processed element information match, directly use the to-be-processed element information as the target element information, and there is no limitation on this.

[0062] In this embodiment, by obtaining a standardized document, where the standardized document includes: the to-be-processed element information, determining the corresponding element type of the standardized document, and then determining the target recommended object that matches the element type, where the target recommended object has the corresponding object description information, and processing the to-be-processed element information according to the object description information to obtain the target element information. Thus, it is possible to effectively reduce the difficulty of analyzing and interpreting the standardized document, and thereby be able to intelligently generate the target element information adapted to the target recommended object based on the standardized document, effectively improving the generation efficiency and generation accuracy of the element information, and further effectively improving the generation effect of the element information.

[0063] Figure 2 It is a schematic flowchart of an information generation method combining RPA and AI proposed in another embodiment of the present disclosure.

[0064] See Figure 2 This information generation method combining RPA and AI includes:

[0065] S201: Determine the content of the to-be-processed file, where the content of the to-be-processed file has the corresponding file form.

[0066] Among them, in the initial stage of the information generation method combining RPA and AI, the file content obtained by the RPA robot from multiple platforms can be referred to as the file content to be processed. The file to be processed can have different forms, which can be referred to as file formats. The file format can be specifically, for example, a copyable format, a non-copyable format, etc., and no restrictions are imposed thereon.

[0067] That is to say, in the embodiments of the present disclosure, it is supported that the RPA robot obtains the file content to be processed from multiple platforms, and then the file content to be processed with different file formats can be correspondingly processed to obtain a standardized file. Then, based on the standardized file, the subsequent information generation method combining RPA and AI can be executed. For details, reference can be made to the subsequent embodiments.

[0068] In the embodiments of the present disclosure, obtaining the file content to be processed can be that the RPA robot automatically obtains the file content to be processed from the official websites of each province and city, or from the specified columns of the websites that need to be monitored and collected as agreed, according to a prefabricated process. Then, the file content to be processed can be processed in combination with the file format of the file content to be processed to obtain a standardized file. For details, reference can be made to the subsequent embodiments.

[0069] S202: Perform standardized processing on the corresponding file content to be processed according to the file format to obtain the corresponding standardized file.

[0070] In the embodiments of the present disclosure, after the RPA robot obtains the file content to be processed, the file content to be processed can be correspondingly processed (this processing method can be referred to as standardized processing) to obtain a standardized file that is more suitable for processing in the subsequent information generation method combining RPA and AI, thereby effectively improving the information generation efficiency.

[0071] In some embodiments, performing standardized processing on the corresponding file content to be processed according to the file format can determine the processing method corresponding to the file format after judging the file format corresponding to the file content to be processed, and process the file content to be processed based on this processing method to obtain a standardized file.

[0072] In the embodiments of the present disclosure, since the content of the file to be processed published on the multi-party platform may have different forms, different methods may be corresponding when interpreting the information of the file. For example, for the content of the file to be processed in a form that can be copied and / or downloaded on the platform, the processing methods of copying and / or downloading can be directly adopted to copy and / or download the corresponding content of the file to be processed from the platform. For the content of the file to be processed in a form that cannot be copied and / or downloaded on the platform, the corresponding content of the file to be processed cannot be directly obtained from the platform at this time. At this time, the screenshot processing method can be adopted to obtain the content of the file to be processed presented in the form of a picture from the platform. In the foregoing operation process, the content of the file to be processed directly copied and / or downloaded from the platform, or the content of the file to be processed obtained from the platform in the form of a picture can be referred to as a standardized file.

[0073] S203: Parse and identify the standardized file to obtain the information of the elements to be processed.

[0074] In the embodiments of the present disclosure, after the RPA robot obtains the standardized file, the standardized file can be parsed and identified to parse and obtain the information of the elements to be processed from the standardized file.

[0075] In some embodiments, the standardized file can be parsed and identified in combination with a pre-trained artificial intelligence model, that is, the standardized file can be input into the pre-trained artificial intelligence model to obtain the information of the elements to be processed output by the pre-trained artificial intelligence model. Or, any other possible method can also be adopted to parse and identify the standardized file to obtain the information of the elements to be processed, such as the method of feature parsing, semantic parsing, etc., which is not limited herein.

[0076] In the embodiments of the present disclosure, by determining the content of the file to be processed and performing corresponding processing on the content of the file to be processed according to the corresponding file form of the content of the file to be processed, processing operations adapted to the file form can be performed for the content of the file to be processed in different file forms, thereby effectively improving the processing efficiency and processing effect of the content of the file to be processed. In addition, in this way, the content of the file to be processed that is not easily obtained (cannot be copied, cannot be downloaded) on the platform can be converted into a picture for acquisition, thereby effectively improving the comprehensiveness of the obtained standardized file, and thus more accurate and comprehensive information of the elements to be processed can be identified based on the standardized file.

[0077] S204: Determine the element type corresponding to the standardized file.

[0078] S205: Determine the target recommended object that matches the element type, where the target recommended object has corresponding object description information.

[0079] S206: Process the to-be-processed element information according to the object description information to obtain the target element information.

[0080] For the descriptions of S204 - S206, please refer to the above embodiments for details and will not be elaborated here.

[0081] In this embodiment, by determining the content of the to-be-processed file and performing operations on the content of the to-be-processed file according to the corresponding file format of the to-be-processed file content, it is possible to perform processing operations adapted to the file format for the content of the to-be-processed file in different file formats, thereby effectively improving the processing efficiency and processing effect of the content of the to-be-processed file. In addition, in this way, the content of the to-be-processed file that is not easily obtained (non-copyable, non-downloadable) on the platform can be converted into a picture for acquisition, thereby effectively improving the comprehensiveness of the obtained standardized file. Based on the standardized file, more accurate and comprehensive to-be-processed element information can be identified from it. Then, determine the element type corresponding to the standardized file, and determine the target recommended object that matches the element type. The target recommended object has corresponding object description information. Then, process the to-be-processed element information according to the object description information to obtain the target element information, so as to be able to intelligently generate the target element information adapted to it for the target recommended object, effectively improving the generation effect of the element information.

[0082] Figure 3 It is a schematic flowchart of an information generation method combining RPA and AI proposed in another embodiment of the present disclosure.

[0083] See Figure 3 , the information generation method combining RPA and AI includes:

[0084] S301: Determine the content of the to-be-processed file, where the content of the to-be-processed file has a corresponding file format.

[0085] S302: Perform standardization processing on the corresponding content of the to-be-processed file according to the file format to obtain the corresponding standardized file.

[0086] For the descriptions of S301 - S302, please refer to the above embodiments for details and will not be elaborated here.

[0087] S303: Perform optical character recognition (OCR) processing on the standardized file based on artificial intelligence (AI) technology to obtain the standardized text.

[0088] After obtaining the corresponding standardized document in an embodiment of the present disclosure, an Optical Character Recognition (OCR) method can be used to process the standardized document to identify the corresponding text information from the standardized document form, and this text information can be referred to as standardized text.

[0089] For example, after obtaining the standardized document presented in the form of a picture from the platform by using the above screenshot processing method, the OCR method can be used to extract the corresponding standardized text from the standardized document presented in the form of a picture, and then the subsequent information generation method combining RPA and AI can be executed based on the standardized text. For details, refer to the subsequent embodiments.

[0090] S304: Identify the information of elements to be processed from the standardized text based on Natural Language Processing (NLP).

[0091] In an embodiment of the present disclosure, after identifying the standardized text from the standardized document, the information of elements to be processed can be identified from the standardized text based on Natural Language Processing (NLP) technology. Since the information of elements to be processed is identified from the standardized text by combining the OCR method and NLP technology, the accuracy and referenceability of the identified information of elements to be processed can be effectively improved.

[0092] In some embodiments, to identify the information of elements to be processed from the standardized text based on NLP, the NLP text understanding method can be used to identify the information of elements to be processed from the standardized text, or a pre-trained NLP model can also be used to identify the information of elements to be processed from the standardized text. There is no limitation in this regard.

[0093] Optionally, in some embodiments, to identify the information of elements to be processed from the standardized text based on Natural Language Processing (NLP), a target element information extraction model corresponding to the information type can be determined, and the standardized text can be input into the target element information extraction model to obtain the information of elements to be processed output by the element information extraction model. Since the information of elements to be processed is identified from the standardized text by combining the target element information extraction model, during the process of interpreting the standardized text, the interference caused by other subjective interpretation factors to the interpretation process of the standardized text can be avoided, thereby effectively reducing the interpretation difficulty of the standardized text, further effectively improving the recognition and acquisition efficiency of the information of elements to be processed, and effectively improving the accuracy of the information of elements to be processed.

[0094] Among them, the element information extraction model can be used to extract the element information to be processed from the standardized text. Standardized texts of different information types can respectively correspond to different element information extraction models. Correspondingly, the element information extraction model corresponding to the information type of the above-obtained standardized text can be called the target element information extraction model. The target recommended element information extraction model belongs to multiple trained element information extraction models, and multiple element information extraction models respectively correspond to multiple information types.

[0095] In the embodiments of the present disclosure, the RPA robot can automatically select the target element information extraction model corresponding to the information type from multiple element information extraction models according to the information type corresponding to the standardized text, and then the standardized text can be input into the target element information extraction model to obtain the element information to be processed output by the target element information extraction model.

[0096] S305: Determine the information type corresponding to the standardized text.

[0097] In the embodiments of the present disclosure, after determining the standardized text from the standardized document, the information type corresponding to the standardized text can be determined.

[0098] Among them, the information type can be used to describe the category to which the information of the standardized text belongs. That is to say, the information in the standardized text can be divided based on different classification dimensions to obtain different types of standardized texts. For example, the information of the standardized text can be divided into reward text types, penalty text types, etc. based on the content classification dimension, and no limitation is made thereto.

[0099] In some embodiments, determining the information type corresponding to the standardized text can be to parse the information content of the standardized text. For example, the standardized text can be parsed in a semantic parsing manner to determine the information type corresponding to the standardized text, or any other possible parsing manner can be used to parse the standardized text to determine the information type corresponding to the standardized text, such as feature parsing, text parsing, etc., and no limitation is made thereto.

[0100] Optionally, in some embodiments, determining the information type corresponding to the standardized text can be to input the standardized text into a pre-trained information classification model to obtain the information type corresponding to the standardized text output by the information classification model.

[0101] Among them, the information classification model can be used to classify the standardized text to obtain the information type corresponding to the standardized text. The information classification model can be an artificial intelligence model, specifically, for example, a neural network model or a machine learning model. Of course, other arbitrary artificial intelligence models that can perform information classification tasks can also be used, and no limitation is imposed thereon.

[0102] In summary, in the embodiments of the present disclosure, refer to Figure 4 , Figure 4 is a schematic diagram of the extraction process of the information of the element to be processed proposed in an embodiment of the present disclosure. That is, the content of the file to be processed can be obtained from the provincial government website platform, the third-party website platform, and other various website platforms, and it is determined whether the content of the file to be processed corresponds to a file form that can be copied and / or downloaded. When the content of the file to be processed is in a file form that can be copied and / or downloaded, the corresponding content of the file to be processed is directly copied and / or downloaded from the platform as the standardized file. When the content of the file to be processed is in a file form that cannot be copied and / or downloaded, the screenshot processing method is used to obtain the content of the file to be processed presented in the form of a picture from the platform as the standardized file. Then, the OCR recognition method can be used to recognize the standardized text from the standardized file presented in the form of a picture, and then the standardized text can be classified to determine the information type corresponding to the standardized text, and the element to be processed corresponding to the standardized file can be determined from the standardized text.

[0103] S306: Use the information type as the element type corresponding to the standardized file to which the standardized text belongs.

[0104] After determining the information type to which the standardized text in the standardized file belongs in the embodiments of the present disclosure, the information type to which the standardized text belongs can be used as the element type corresponding to the standardized file to which the standardized text belongs. Since the information type corresponding to the standardized text in the standardized file is used as the element type corresponding to the element to be processed, it is possible to accurately determine the information type corresponding to the standardized text based on the more comprehensive basis of the standardized text, and then effectively improve the accuracy of determining the element type when using the information type as the element type corresponding to the standardized file to which the standardized text belongs.

[0105] S307: Determine the target recommended object that matches the element type, where the target recommended object has corresponding object description information.

[0106] For the description of S307, reference can be specifically made to the above embodiments, and details are not described herein again.

[0107] S308: Determine whether the object description information and the information of the element to be processed meet the matching conditions.

[0108] In the embodiments of the present disclosure, after determining the object description information of the target recommended object and the information of the element to be processed in the standardized document, it can be determined whether the object description information and the information of the element to be processed meet the matching conditions.

[0109] Among them, in the process of matching the object description information and the information of the element to be processed, the conditions preset in the application scenario generated in combination with the actual information can be referred to as the matching conditions, and the matching conditions can be used to assist in judging whether the object description information and the information of the element to be processed match.

[0110] In some embodiments, to determine whether the object description information and the information of the element to be processed meet the matching conditions, corresponding feature information can be pre-extracted from the object description information and the information of the element to be processed respectively, and then a feature matching algorithm can be used to determine whether the corresponding feature information in the object description information and the information of the element to be processed meets the matching conditions. Alternatively, any other possible method can also be used to determine whether the object description information and the information of the element to be processed meet the matching conditions, such as the model matching method, and there is no limitation thereto.

[0111] Optionally, in some embodiments, to determine whether the object description information and the information of the element to be processed meet the matching conditions, a matching degree value of the object description information and the information of the element to be processed can be determined. When the matching degree value is greater than or equal to the matching degree threshold, it is determined that the object description information and the information of the element to be processed meet the matching conditions. When the matching degree value is less than the matching degree threshold, it is determined that the object description information and the information of the element to be processed do not meet the matching conditions. Since it is determined whether the object description information and the information of the element to be processed meet the matching conditions in combination with the matching degree threshold, it is possible to accurately determine whether the object description information and the information of the element to be processed meet the matching conditions based on the matching degree threshold.

[0112] Among them, the value used to quantitatively describe the matching degree between the object description information and the information of the element to be processed can be referred to as the matching degree value. The matching degree value can specifically be, for example, the similarity value between the object description information and the information of the element to be processed, the matching ratio between multiple object description information and multiple information of the element to be processed, etc., and there is no limitation thereto.

[0113] Among them, the threshold preset for the matching degree between the object description information and the information of the element to be processed can be referred to as the matching degree threshold.

[0114] In the embodiments of the present disclosure, determining whether the object description information and the element information to be processed meet the matching condition may be to determine the matching degree value (matching ratio) of the object description information and the element information to be processed, and compare the determined matching degree value (matching ratio) with a preset matching degree threshold (matching ratio threshold). When the matching degree value (matching ratio) is greater than or equal to the matching degree threshold (matching ratio threshold), it is determined that the object description information and the element information to be processed meet the matching condition. When the matching degree value (matching ratio) is less than the matching degree threshold (matching ratio threshold), it is determined that the object description information and the element information to be processed do not meet the matching condition.

[0115] For example, for 10 pieces of object description information and 10 pieces of element information to be processed, the number of matching items (for example, 7 items) between the 10 pieces of object description information and the 10 pieces of element information to be processed can be determined. At this time, it can be determined that the matching ratio between the 10 pieces of object description information and the 10 pieces of element information to be processed is 70%. At this time, the matching ratio of 70% can be compared with a preset matching ratio threshold of 60% to determine that the object description information and the element information to be processed meet the matching condition, and there is no limitation to this.

[0116] S309: If the object description information and the element information to be processed meet the matching condition, then the element information to be processed is used as the target element information.

[0117] In the embodiments of the present disclosure, when it is determined that the object description information and the element information to be processed meet the matching condition, the element information to be processed can be used as the target element information, and the target element information is pushed to the target recommended object corresponding to the object description information.

[0118] In some embodiments, when it is determined that the object description information and the element information to be processed do not meet the matching condition, the object description information and the element information to be processed can also be pushed to the relevant staff. The staff can also view the specific matching items and judge whether the target element information can be pushed to the target recommended object corresponding to the object description information.

[0119] Optionally, in some other embodiments, after it is determined that the object description information and the element information to be processed meet the matching condition, the standardized text to which the target element information belongs can be determined, and the belonging standardized text is provided to the target recommended object. Then, the target recommended object can perform subsequent operations in combination with the target element information and the standardized text.

[0120] S310: Parse and process the standardized text to obtain the declaration operation information.

[0121] Among them, the information for declaring the solution information involved in the standardized document, that is, the declaration operation information, can be specifically, for example, the declaration material information, the declaration method information, etc., and there is no limitation on this.

[0122] In the embodiments of the present disclosure, the RPA robot can parse and process the standardized text to obtain the declaration material information and the declaration operation method information required for declaring the corresponding solution from the standardized text, and then trigger subsequent steps in combination with the obtained declaration operation information, and there is no limitation on this.

[0123] For example, the standardized text can be parsed and processed to determine the declaration material information that an enterprise needs to provide if it needs to declare the corresponding solution information (for example, the reward plan) of the standardized text, and it can also be determined whether the existing declaration material information of the enterprise is perfect. When the declaration material information is not perfect, the corresponding declaration material supplement information is generated, and the foregoing declaration material information and the declaration material supplement information are provided to the corresponding enterprise, and there is no limitation on this.

[0124] S311: Generate a declaration operation link according to the standardized text.

[0125] After generating the corresponding declaration operation information according to the standardized text in the embodiments of the present disclosure, a corresponding declaration operation link can be generated according to the standardized text, where the declaration operation link can be used to execute the corresponding declaration operation.

[0126] That is to say, in the embodiments of the present disclosure, when it is determined that the object description information and the element information to be processed match, a declaration operation link can be generated according to the corresponding standardized text of the element information to be processed. Then, the target recommended object can realize the one-key declaration operation of the relevant solution based on the declaration operation link.

[0127] S312: Provide the declaration operation information and the declaration operation link to the target recommended object, where the target recommended object executes the declaration operation based on the declaration operation link and the declaration operation information.

[0128] After generating the declaration operation information and the declaration operation link according to the standardized text in the embodiments of the present disclosure, the RPA robot can provide the declaration operation information and the declaration operation link to the foregoing determined target recommended object, and the target recommended object can execute the corresponding declaration operation based on the declaration operation link and the declaration operation information.

[0129] For example, after the above-mentioned declaration material information and supplementary declaration material information are provided as declaration operation information to the corresponding target recommended object (enterprise), the RPA robot can provide the declaration operation link and the declaration material information to the enterprise. If the supplementary declaration material information indicates that the enterprise does not need to supplement the declaration material information, the enterprise can achieve one-click declaration according to the declaration operation link. If the supplementary declaration material information indicates that the enterprise needs to supplement the declaration material information, the enterprise can supplement the corresponding declaration material information through the supplementary entry generated by clicking the declaration operation link, and after the supplementary declaration material information is completed, complete the corresponding declaration operation, without any restrictions on this.

[0130] In the embodiments of the present disclosure, refer to Figure 5 , Figure 5 which is a schematic flowchart of an information generation method combining RPA and AI proposed in another embodiment of the present disclosure. At the beginning stage, it can be determined whether the standardized document contains the information of the to-be-processed element to be matched. When the standardized document contains the information of the to-be-processed element to be matched, according to the element type of the to-be-processed element information in the standardized document, the target recommended object matching the element type is determined, and the object description information of the target recommended object is determined. Then, it is judged whether the object description information and the to-be-processed element information meet the matching conditions. When the object description information and the to-be-processed element information meet the matching conditions, the to-be-processed element information is used as the target element information and provided to the corresponding target recommended object. Or, it can also be that when the object description information and the to-be-processed element information do not meet the matching conditions, it is manually judged whether the to-be-processed element information can be used as the target element information and provided to the corresponding target recommended object.

[0131] In this embodiment, by determining the content of the file to be processed, where the content of the file to be processed has a corresponding file format, and standardizing the corresponding content of the file to be processed according to the file format to obtain a corresponding standardized file, then performing optical character recognition (OCR) processing on the standardized file based on artificial intelligence (AI) technology to obtain a standardized text, and identifying the information of the element to be processed from the standardized text based on natural language processing (NLP), the accuracy and referenceability of the information of the element to be processed can be effectively improved. Then, determine the information type corresponding to the standardized text, and use the information type as the element type corresponding to the standardized file to which the standardized text belongs. Since the information type corresponding to the standardized text in the standardized file is used as the element type corresponding to the element to be processed, it is possible to accurately determine the information type corresponding to the standardized text based on the more comprehensive basis of the standardized text. Furthermore, when using the information type as the element type corresponding to the standardized file to which the standardized text belongs, the accuracy of determining the element type can be effectively improved. Then, determine the target recommended object that matches the element type, and determine whether the object description information and the information of the element to be processed meet the matching conditions. If the object description information and the information of the element to be processed meet the matching conditions, use the information of the element to be processed as the target element information. Then, perform parsing processing on the standardized text to obtain declaration operation information, generate a declaration operation link according to the standardized text, and provide the declaration operation information and the declaration operation link to the target recommended object. The target recommended object performs a declaration operation based on the declaration operation link and the declaration operation information. Thus, it can effectively facilitate the target recommended object to utilize the target element information and effectively facilitate the execution process of the declaration operation of the target recommended object.

[0132] Figure 6 It is a schematic structural diagram of an information generation device combining RPA and AI proposed in an embodiment of the present disclosure.

[0133] See Figure 6 , the information generation device 600 combining RPA and AI includes:

[0134] An acquisition module 601, configured to acquire a standardized file, where the standardized file includes: information of an element to be processed;

[0135] A first determination module 602, configured to determine an element type corresponding to the standardized file;

[0136] A second determination module 603, configured to determine a target recommended object that matches the element type, where the target recommended object has corresponding object description information; and

[0137] A processing module 604, configured to process the information of the element to be processed according to the object description information to obtain target element information.

[0138] Optionally, in some embodiments, referring to Figure 7 , Figure 7 FIG.

[0139] is a schematic structural diagram of an information generation device combining RPA and AI proposed in another embodiment of the present disclosure. Among them, the acquisition module 601 includes:

[0140] The first determination sub-module 6011 is used to determine the content of the file to be processed, where the content of the file to be processed has a corresponding file form;

[0141] The first processing sub-module 6012 is used to perform standardization processing on the corresponding content of the file to be processed according to the file form to obtain a corresponding standardized file; and

[0142] The parsing sub-module 6013 is used to parse and identify the standardized file to obtain the information of the elements to be processed.

[0143] Specifically, the parsing sub-module 6013 is used to:

[0144] Perform optical character recognition (OCR) processing on the standardized file based on artificial intelligence (AI) technology to obtain a standardized text;

[0145] Identify the information of the elements to be processed from the standardized text based on natural language processing (NLP).

[0146] Optionally, in some embodiments, the first determination module 602 includes:

[0147] The second determination sub-module 6021 is used to determine the information type corresponding to the standardized text;

[0148] The second processing sub-module 6022 is used to use the information type as the element type corresponding to the standardized file to which the standardized text belongs.

[0149] Optionally, in some embodiments, the second determination sub-module 6021 is further used to:

[0150] Input the standardized text into a pre-trained information classification model to obtain the information type corresponding to the standardized text output by the information classification model.

[0151] Optionally, in some embodiments, the parsing sub-module 6013 is further used to:

[0152] Determine the target element information extraction model corresponding to the information type;

[0153] Input the standardized text into the target element information extraction model to obtain the information of the elements to be processed output by the element information extraction model;Among them, the target recommendation element information extraction model belongs to multiple trained element information extraction models, and the multiple element information extraction models respectively correspond to multiple information types.

[0154] Optionally, in some embodiments, the processing module 604 includes:

[0155] A third determination sub-module 6041, configured to determine whether the object description information and the to-be-processed element information meet the matching condition;

[0156] A third processing sub-module 6042, configured to use the to-be-processed element information as the target element information when the object description information and the to-be-processed element information meet the matching condition.

[0157] Optionally, in some embodiments, the third determination sub-module 6041 is further configured to:

[0158] Determine the matching degree value of the object description information and the to-be-processed element information;

[0159] If the matching degree value is greater than or equal to the matching degree threshold, it is determined that the object description information and the to-be-processed element information meet the matching condition;

[0160] If the matching degree value is less than the matching degree threshold, it is determined that the object description information and the to-be-processed element information do not meet the matching condition.

[0161] Optionally, in some embodiments, the processing module 604 further includes:

[0162] A fourth determination sub-module 6043, configured to determine the standardized text to which the target element information belongs after using the to-be-processed element information as the target element information, and provide the belonging standardized text to the target recommendation object.

[0163] Optionally, in some embodiments, the processing module 604 further includes:

[0164] A fourth processing sub-module 6044, configured to perform parsing processing on the standardized text to obtain declaration operation information;

[0165] A generation sub-module 6045, configured to generate a declaration operation link according to the standardized text; and

[0166] A fifth processing sub-module 6046, configured to provide the declaration operation information and the declaration operation link to the target recommendation object, where the target recommendation object performs a declaration operation based on the declaration operation link and the declaration operation information.

[0167] It should be noted that for the functions and specific implementation principles of the above-mentioned modules in the embodiments of the present disclosure, reference may be made to the above-mentioned method embodiments, and details are not described herein again.

[0168] In this embodiment, by obtaining a standardized document, where the standardized document includes information on elements to be processed, determining the type of elements corresponding to the standardized document, and then determining a target recommended object that matches the element type, where the target recommended object has corresponding object description information, and processing the information on elements to be processed according to the object description information to obtain target element information. Thus, the difficulty of analyzing and interpreting the standardized document can be effectively reduced, and thus, based on the standardized document, it is possible to intelligently generate target element information that is adapted to the target recommended object, effectively improving the generation efficiency and generation accuracy of the element information, and further effectively improving the generation effect of the element information.

[0169] To implement the above embodiment, the present disclosure also provides an electronic device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, it implements the information generation method combining RPA and AI as proposed in the foregoing embodiments of the present disclosure.

[0170] Figure 8 It is a schematic diagram of the hardware structure of the electronic device provided in an embodiment of the present disclosure. As Figure 8 shown, the electronic device 800 includes: a memory 810 and a processor 820, and a computer program executable on the processor 820 is stored in the memory 810. When the processor 820 executes the computer program, it implements the information generation method combining RPA and AI in the above embodiment. The number of the memory 810 and the processor 820 can be one or more.

[0171] The electronic device further includes:

[0172] A communication interface 830, configured to communicate with external devices and perform data interaction and transmission.

[0173] If the memory 810, the processor 820, and the communication interface 830 are implemented independently, the memory 810, the processor 820, and the communication interface 830 can be interconnected through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of representation, Figure 8 only a thick line is used to represent it in the figure, but it does not mean that there is only one bus or one type of bus.

[0174] Optionally, in a specific implementation, if the memory 810, the processor 820, and the communication interface 830 are integrated on a single chip, the memory 810, the processor 820, and the communication interface 830 can communicate with each other through an internal interface.

[0175] The present disclosure also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the information generation method combining RPA and AI as proposed in the foregoing embodiments of the present disclosure.

[0176] The present disclosure also provides a computer program product, which, when the instruction processor in the computer program product executes, implements the information generation method combining RPA and AI as proposed in the foregoing embodiments of the present disclosure.

[0177] It should be understood that the above-mentioned processor may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. It is worth noting that the processor may be a processor supporting the advanced reduced instruction set machines (ARM) architecture.

[0178] Further, optionally, the above-mentioned memory may include a read-only memory and a random access memory, and may further include a non-volatile random access memory. The memory may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may include a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may include a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available. For example, static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchlink dynamic random access memory (SLDRAM), and direct access random access memory (DR RAM).

[0179] In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions according to the present disclosure are generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium.

[0180] In the description of this specification, the description with reference to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present disclosure. Moreover, the specific features, structures, materials, or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, without contradiction, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0181] In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one of such features. In the description of the present disclosure, "a plurality of" means two or more unless otherwise specifically defined.

[0182] Any process or method description represented in a flowchart or otherwise described herein may be understood to represent a module, segment, or portion of code including one or more executable instructions for implementing a specific logical function or process. And the scope of the preferred embodiments of the present disclosure includes additional implementations, where the functions may be performed in a substantially simultaneous manner or in a reverse order according to the functions involved, rather than in the order shown or discussed.

[0183] The logic and / or steps represented in a flowchart or otherwise described herein, for example, may be considered as a sequenced list of executable instructions for implementing a logical function and may be specifically implemented in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device.

[0184] It should be understood that the various parts of the present disclosure may be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods may be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. All or part of the steps of the above method embodiments may be completed by a program instructing relevant hardware, and the program may be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiments.

[0185] In addition, each functional unit in various embodiments of the present disclosure may be integrated into one processing module, or each unit may exist physically alone, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the above-mentioned integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium. The storage medium may be a read-only memory, a magnetic disk, an optical disc, or the like.

[0186] As described above, the foregoing are only specific embodiments of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present disclosure can easily think of various changes or substitutions thereof, and these should all be covered by the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure shall be subject to the protection scope of the claims.

Claims

1. An information generation method combining RPA and AI, characterized in that, Applied to an RPA robot, the method includes: Obtain a standardized document, where the standardized document includes: information on elements to be processed; Determine the element type corresponding to the standardized document, where the element type refers to the category to which the elements to be processed in the standardized document belong; Determine a target recommended object that matches the element type, where the target recommended object has corresponding object description information, and the target recommended object refers to a recommended object that is adapted to the information on the elements to be processed in the standardized document when executing the information on the elements in the standardized document; and Process the information on the elements to be processed according to the object description information to obtain target element information; The obtaining of the standardized document includes: performing optical character recognition (OCR) processing on the standardized document based on artificial intelligence (AI) technology to obtain a standardized text; Identifying the information on the elements to be processed from the standardized text based on natural language processing (NLP); The processing of the information on the elements to be processed according to the object description information to obtain target element information includes: Determining whether the object description information and the information on the elements to be processed meet the matching conditions; If the object description information and the information on the elements to be processed meet the matching conditions, then use the information on the elements to be processed as the target element information, determine the standardized text to which the target element information belongs, and provide the belonging standardized text to the target recommended object; Performing parsing processing on the standardized text to obtain declaration operation information; Generating a declaration operation link according to the standardized text; and Providing the declaration operation information and the declaration operation link to the target recommended object, where the target recommended object performs a declaration operation based on the declaration operation link and the declaration operation information.

2. The method according to claim 1, characterized in that The obtaining of the standardized document includes: Determining the content of the file to be processed, where the content of the file to be processed has a corresponding file format; Performing standardized processing on the corresponding content of the file to be processed according to the file format to obtain a corresponding standardized document.

3. The method according to claim 1, characterized in that The determining of the element type corresponding to the standardized document includes: Determining the information type corresponding to the standardized text; Using the information type as the element type corresponding to the standardized document to which the standardized text belongs.

4. The method according to claim 3, wherein The determining of the information type corresponding to the standardized text includes: Inputting the standardized text into a pre-trained information classification model to obtain the information type corresponding to the standardized text output by the information classification model.

5. The method according to claim 3, wherein The identifying of the information on the elements to be processed from the standardized text based on NLP includes: Determining a target element information extraction model corresponding to the information type; Inputting the standardized text into the target element information extraction model to obtain the information on the elements to be processed output by the element information extraction model; Where the target recommended element information extraction model belongs to multiple trained element information extraction models, and the multiple element information extraction models respectively correspond to multiple information types.

6. The method according to claim 1, characterized in that, Determining whether the object description information and the to-be-processed element information meet the matching condition includes: Determining a matching degree value of the object description information and the to-be-processed element information; If the matching degree value is greater than or equal to a matching degree threshold, determining that the object description information and the to-be-processed element information meet the matching condition; If the matching degree value is less than the matching degree threshold, determining that the object description information and the to-be-processed element information do not meet the matching condition.

7. The method according to claim 1, characterized in that, After using the to-be-processed element information as the target element information, it further includes: Determining the standardized text to which the target element information belongs and providing the belonging standardized text to the target recommended object.

8. An information generation device combining RPA and AI, characterized in that, Applied to an RPA robot, the device includes: An acquisition module, configured to acquire a standardized file, where the standardized file includes to-be-processed element information; A first determination module, configured to determine an element type corresponding to the standardized file, where the element type refers to the category to which the to-be-processed element in the standardized file belongs; A second determination module, configured to determine a target recommended object that matches the element type, where the target recommended object has corresponding object description information, and the target recommended object refers to a recommended object that is adapted to the to-be-processed element information in the standardized file when executing the element information in the standardized file; and A processing module, configured to process the to-be-processed element information according to the object description information to obtain target element information; The acquisition module includes: a parsing sub-module, configured to perform optical character recognition (OCR) processing on the standardized file based on artificial intelligence (AI) technology to obtain a standardized text; Identifying the to-be-processed element information from the standardized text based on natural language processing (NLP); The processing module is further configured to determine whether the object description information and the to-be-processed element information meet the matching condition; If the object description information and the to-be-processed element information meet the matching condition, using the to-be-processed element information as the target element information, determining the standardized text to which the target element information belongs, and providing the belonging standardized text to the target recommended object; Performing parsing processing on the standardized text to obtain declaration operation information; Generating a declaration operation link according to the standardized text; and Providing the declaration operation information and the declaration operation link to the target recommended object, where the target recommended object performs a declaration operation based on the declaration operation link and the declaration operation information.

9. The device according to claim 8, characterized in that, The acquisition module includes: A first determination sub-module, configured to determine the content of the to-be-processed file, where the content of the to-be-processed file has a corresponding file format; A first processing sub-module, configured to perform standardized processing on the corresponding content of the to-be-processed file according to the file format to obtain a corresponding standardized file.

10. An electronic device, characterized in that, It includes: A processor and a memory, where instructions are stored in the memory, and the instructions are loaded and executed by the processor to implement the information generation method combining RPA and AI according to any one of claims 1 to 7.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, it implements the information generation method combining RPA and AI as described in any one of claims 1-7.

Images