CN114580346A

CN114580346A - Information generation method and device combining RPA and AI, electronic equipment and storage medium

Info

Publication number: CN114580346A
Application number: CN202210153071.XA
Authority: CN
Inventors: 程飞
Original assignee: Laiye Technology Beijing Co Ltd
Current assignee: Laiye Technology Beijing Co Ltd
Priority date: 2022-02-18
Filing date: 2022-02-18
Publication date: 2022-06-03

Abstract

The present disclosure provides an information generating method, apparatus, electronic device, and storage medium combining RPA and AI, applied to a Robot Process Automation (RPA) robot, the method including: obtaining a standardized file, wherein the standardized file comprises: the method comprises the steps of processing element information to be processed, determining element types corresponding to standardized files, and determining target recommendation objects matched with the element types, wherein the target recommendation objects have corresponding object description information, and processing the element information to be processed according to the object description information to obtain the target element information.

Description

Information generation method and device combining RPA and AI, electronic equipment and storage medium

Technical Field

The present disclosure relates to the field of computer technologies, and in particular, to a method and an apparatus for generating information of Robot Process Automation (RPA) and Artificial Intelligence (AI), an electronic device, and a storage medium.

Background

Robot Process Automation (RPA) means that a specific "robot software" simulates a human operation on a computer and automatically executes a Process task according to a rule.

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

The standardized files may be, for example, a preferential power development scheme file, a reward and punishment scheme file, and when the element information in the standardized files is executed, different standardized files may be respectively adapted to different recommendation objects (recommendation objects, such as enterprises and users).

In the related art, in order to provide adaptive standardized files for different recommended objects, element information in the standardized files needs to be fully interpreted, so that the standardized files provided for different recommended objects can effectively meet personalized requirements of different recommended objects.

In this system, since the standardized document has various formats and the amount of information included in the standardized document is large, it is difficult to analyze and interpret the standardized document, and when generating the element information recommended to the recommendation target based on the standardized document, the element information cannot be generated intelligently in accordance with the recommendation target, and the generation efficiency and the generation accuracy of the element information are poor, and the generation effect is not good.

Disclosure of Invention

The embodiment of the disclosure provides an information generation method and device combining RPA and AI, in order to solve the problems in the related art, the technical scheme is as follows:

in a first aspect, an information generating method combining an RPA and an AI, provided by an embodiment of the present disclosure, is applied to an RPA robot, and includes: obtaining a standardized file, wherein the standardized file comprises: element information to be processed; determining element types corresponding to the standardized files; determining a target recommendation object matched with the element type, wherein the target recommendation object has corresponding object description information; and processing the element information to be processed according to the object description information to obtain target element information.

In a second aspect, an information generating apparatus combining an RPA and an AI according to an embodiment of the present disclosure is applied to an RPA robot, and includes: an obtaining module, configured to obtain a standardized file, where the standardized file includes: element information to be processed; the first determining module is used for determining the element type corresponding to the standardized file; the second determination module is used for determining a target recommendation object matched with the element type, wherein the target recommendation object has corresponding object description information; and the processing module is used for processing the element information to be processed according to the object description information to obtain the target element information.

In a third aspect, an electronic device provided in an embodiment of the present disclosure includes: the information generating method is characterized in that when the processor executes the program, the information generating method combining the RPA and the AI is realized.

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

The advantages or beneficial effects in the above technical solution at least include:

in the embodiment of the present disclosure, a standardized file is obtained, where the standardized file includes: the method comprises the steps of processing element information to be processed, determining element types corresponding to standardized files, and determining target recommendation objects matched with the element types, wherein the target recommendation objects have corresponding object description information, and processing the element information to be processed according to the object description information to obtain the target element information.

The foregoing summary is provided for the purpose of description 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 following detailed description.

Drawings

In the drawings, like reference numerals refer to the same or similar parts or elements throughout the several views unless otherwise specified. The figures are not necessarily to scale. It is appreciated that these drawings depict only some embodiments that have been presented in accordance with the disclosure and are not to be considered limiting of its scope.

Fig. 1 is a schematic flowchart of an information generating method combining RPA and AI according to an embodiment of the disclosure;

fig. 2 is a schematic flow chart of an information generating method combining RPA and AI according to another embodiment of the present disclosure;

fig. 3 is a schematic flow chart of an information generating method combining RPA and AI according to another embodiment of the present disclosure;

fig. 4 is a schematic diagram of a flow of extracting element information to be processed according to an embodiment of the disclosure;

fig. 5 is a schematic flowchart of an information generating method combining RPA and AI according to another embodiment of the present disclosure;

fig. 6 is a schematic structural diagram of an information generating apparatus that combines RPA and AI according to an embodiment of the present disclosure;

fig. 7 is a schematic structural diagram of an information generating apparatus that combines RPA and AI according to another embodiment of the present disclosure;

fig. 8 is a schematic hardware structure diagram of an electronic device according to an embodiment of the present disclosure.

Detailed Description

Reference will now be made in detail to the embodiments of the present disclosure, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the drawings are exemplary only for the purpose of illustrating the present disclosure and should not be construed as limiting the same.

In the description of the embodiments of the present disclosure, the term "plurality" refers to two or more.

In the description of the embodiments of the present disclosure, the term "Robot Process Automation (RPA)" refers to a method that may provide another way to automate the end user's manual operation Process by simulating the manual operation of the end user in a computer.

In the description of the embodiments of the present disclosure, the term "Natural Language Processing (NPL)" refers to a technology for performing interactive communication with a machine using a Natural Language used for human communication. The natural language is processed by human, so that the computer can read and understand the natural language. Relevant research in natural language processing begins with human exploration of machine translation.

In the description of the embodiments of the present disclosure, the term "Optical Character Recognition (OCR)" refers to a process in which an electronic device checks a Character printed on paper, determines its shape by detecting dark and light patterns, and then translates the shape into a computer text by a Character Recognition method; the method is characterized in that characters in a paper document are converted into an image file with a black-and-white dot matrix in an optical mode aiming at printed characters, and the characters in the image are converted into a text format through recognition software for further editing and processing by word processing software.

In the description of the embodiments of the present disclosure, the term "RPA robot" refers to a robot that can automatically execute corresponding business operations based on a preset automatic operation flow.

In the description of the embodiment of the present disclosure, the term "standardized file" refers to a file issued on a multi-party platform and available for a user to refer to, for example, a reward and punishment scheme file, a preferential power-assisted development scheme file, and the like.

In the description of the embodiment of the present disclosure, the term "element information to be processed" refers to a plurality of element information included in the standardized document, for example, content element information, identification element information, feature element information, and the like in the standardized document, and specifically, for example, bonus standard content information, preferential indicator information, and the like may be used.

In the description of the embodiment of the present disclosure, the term "element type" refers to a category to which an element to be processed in a standardized document belongs, that is, the element 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 element to be processed of the standardized document may be divided into a bonus type, a penalty type, and the like based on content classification dimensions, or the element to be processed may be divided into a picture type, a text type, and the like based on a corresponding expression form of the element to be processed of the standardized document.

In the description of the embodiments of the present disclosure, the term "target recommendation object" refers to a recommendation object that is adapted to element information to be processed in a standardized document when the element information in the standardized document is executed, for example, an enterprise, a user, and the like.

In the description of the embodiments of the present disclosure, the term "object description information" refers to information for describing a target recommendation object, for example, name information of the target recommendation object, identification information of the target recommendation object, and the like.

These and other aspects of embodiments of the disclosure will be apparent with reference to the following description and attached drawings. In the description and drawings, particular embodiments of the disclosure have been disclosed in detail as being indicative of some of the ways in which the principles of the embodiments of the disclosure may be practiced, but it is understood that the scope of the embodiments of the disclosure is not limited thereby. On the contrary, the embodiments of the disclosure include all changes, modifications and equivalents coming within the spirit and terms of the claims appended hereto.

Fig. 1 is a schematic flowchart of an information generating method combining an RPA and an AI according to an embodiment of the present disclosure.

The embodiment is exemplified in that the information generation method combining the RPA and the AI is configured as the information generation apparatus combining the RPA and the AI, the information generation method combining the RPA and the AI in the embodiment may be configured in the information generation apparatus combining the RPA and the AI, and the information generation apparatus combining the RPA and the AI may be disposed in the server or may also be disposed in the electronic device, which is not limited in this disclosure.

Referring to fig. 1, the information generating method combining RPA and AI includes:

s101: obtaining a standardized file, wherein the standardized file comprises: and element information to be processed.

The standardized file may be a file published on a multi-party platform, and the file may be specifically, for example, a reward and punishment scheme file, a preferential power-assisted development scheme file, or the like, which is not limited thereto.

The standardized document may include a plurality of element information, which may be referred to as element information to be processed, and the element information to be processed may be content element information, identification element information, feature element information, and the like in the standardized document, and may specifically be, for example, reward standard content information, benefit indicator information, and the like, without limitation.

In this embodiment of the present disclosure, the obtaining of the standardized file may be that an RPA robot provides a corresponding file transmission interface, a data transmission path between the RPA robot and a multi-party platform is established through the file transmission interface, and then the standardized file already published by the multi-party platform is obtained based on the data transmission path, or the obtaining of the standardized file may also be that a corresponding monitoring device is configured in advance for the RPA robot, and then the RPA robot may monitor the multi-party platform based on the monitoring device, and download the corresponding standardized file from the multi-party platform when the newly published standardized file is monitored, and/or update the published standardized file, which is not limited in this respect.

After the standardized file is obtained, the standardized file can be analyzed, so that a plurality of pieces of element information to be processed can be identified from the standardized file.

In some embodiments, the standardized file may be parsed by text parsing, that is, a plurality of pieces of text information may be identified from the standardized file by text parsing, and the identified text information is used as the element information to be processed, or any other possible manner may be used to parse the standardized file to identify a plurality of pieces of element information to be processed from the standardized file, for example, a manner of feature parsing, a manner of model parsing, and the like, which is not limited thereto.

S102: the element type corresponding to the standardized document is determined.

The element types may be used to describe categories to which the to-be-processed elements in the standardized file belong, that is, the to-be-processed element information in the standardized file may be divided based on different classification dimensions to obtain the to-be-processed elements of different element types, for example, the to-be-processed elements of the standardized file may be divided into bonus types, penalty types, and the like based on content classification dimensions, or the to-be-processed elements may be divided into picture types, text types, and the like based on corresponding expression forms of the to-be-processed elements of the standardized file, which is not limited in this respect.

In some embodiments, the element type corresponding to the standardized document may be determined by combining the pre-trained artificial intelligence model, that is, after the information of the element to be processed is obtained by parsing and identifying 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, which is not limited to this.

In other embodiments, the element type corresponding to the standardized file is determined, or after the element information to be processed is obtained by parsing and identifying from the standardized file, semantic parsing may be performed on the element information to be processed to obtain a corresponding semantic parsing result, and the element type corresponding to the standardized file is determined according to the semantic parsing result, which is not limited.

For example, it is assumed that the information of the element to be processed obtained by parsing and identifying from the standardized document is: and if the reward is 10 ten thousand yuan and the penalty is 10 ten thousand yuan, semantic analysis can be performed on the element information to be processed obtained through analysis and recognition, so as to determine the element information to be processed: the element type corresponding to the reward 10 ten thousand yuan is a reward type, and the element type is related to the information of the element to be processed: the element type corresponding to the "penalty of 10 ten thousand yuan" is a penalty type, and is not limited thereto.

S103: and determining a target recommendation object matched with the element type, wherein the target recommendation object has corresponding object description information.

In the embodiment of the present disclosure, when the element information in the standardized file is executed, different standardized files may be respectively adapted to different recommendation objects (recommendation objects, such as enterprises, users, and the like), and accordingly, the obtained object matching the element type corresponding to the standardized file may be referred to as a target recommendation object.

The information for describing the target recommended object may be referred to as object description information, and the object description information may specifically be, for example, name information of the target recommended object, identification information of the target recommended object, or the object description information may also be information of any other possible dimensions for correspondingly describing the target recommended object, which is not limited to this.

In the subsequent embodiments of the present disclosure, the target recommendation object may be an enterprise as an example for specific explanation, that is, a specific application scenario of the embodiments of the present disclosure may specifically be, for example: acquiring a standardized file, determining element types (such as reward types, preferential subsidy types and the like) corresponding to element information to be processed in the standardized file, determining enterprises matched with the element types, determining object description information (such as business amount information, tax intake information and the like) of the enterprises, processing the element information to be processed according to the object description information of the enterprises to provide matched target element information for the enterprises, so that the enterprises can execute schemes related to the target element information according to the target element information (for example, the enterprises can declare preferential subsidy schemes, rewards and the like according to the matched target element information), thereby effectively helping the enterprises to fully decode information in the standardized file and fully utilize the standardized file, thereby effectively helping the development of enterprises.

It should be noted that the embodiment of the present disclosure may also be applied to any other possible information generation scenarios, and is not limited thereto.

In the embodiment of the present disclosure, the target recommendation object matching the element type may be determined by combining an RPA robot with an existing big database system, and analyzing object description information of the target recommendation object stored in the big database to determine object description information matching the element type, and taking a recommendation object corresponding to the object description information as the target recommendation object, which is not limited in this regard.

In some embodiments, the RPA robot may further directly obtain a target recommended object matched with the element type from the large database system according to a pre-established correspondence between the element type and the target recommended object, periodically monitor related object description information of the target recommended object, collect and store newly generated object description information, compare the newly generated object description information with existing object description information in the large database system, and update the existing object description information if the object description information is changed, without limitation.

S104: and processing the element information to be processed according to the object description information to obtain target element information.

After the target recommendation object matched with the element type is determined, the element information to be processed can be processed according to the object description information corresponding to the target recommendation object, so as to obtain the target element information.

In some embodiments, the element information to be processed is processed according to the object description information, and the RPA robot may determine whether the object description information and the element information to be processed match, and when the object description information and the element information to be processed match, the element information to be processed is directly used as the target element information.

For example, assume that the object description information is: "the monthly turnover expansion of the enterprise is 30%", and the information of the key elements to be processed is as follows: if the monthly expansion of the turnover is higher than 20% and 10 ten thousand yuan is rewarded, whether the object description information is matched with the element information to be processed is judged, whether the monthly expansion of the enterprise is 30% or not is judged, whether the condition of the monthly expansion of the enterprise is met or not is judged, when the monthly expansion of the enterprise is 30% or not is met and the condition of the monthly expansion of the turnover is higher than 20% and 10 ten thousand yuan is rewarded, the object description information is determined to be matched with the element information to be processed, and when the object description information is matched with the element information to be processed, the monthly expansion of the turnover is higher than 20% and 10 ten thousand yuan is rewarded as the object element information, so that the object description information is not limited.

Or, whether the object description information and the element information to be processed are matched is judged, or the similarity between the object description information and the element information to be processed is determined, when the similarity is greater than a similarity threshold, the object description information and the element information to be processed are determined to be matched, and when the object description information and the element information to be processed are matched, the element information to be processed is directly used as the target element information, which is not limited.

In this embodiment, a standardized file is obtained, where the standardized file includes: the method comprises the steps of processing element information to be processed, determining element types corresponding to standardized files, and determining target recommendation objects matched with the element types, wherein the target recommendation objects have corresponding object description information, and processing the element information to be processed according to the object description information to obtain the target element information.

Fig. 2 is a schematic flowchart of an information generating method combining RPA and AI according to another embodiment of the disclosure.

Referring to fig. 2, the information generating method combining RPA and AI includes:

s201: and determining the content of the file to be processed, wherein the content of the file to be processed has a corresponding file form.

In an initial stage of the information generation method combining the RPA and the AI, the RPA robot acquires file content from a multi-party platform, which may be referred to as file content to be processed, the file to be processed may have different presentation forms, which may be referred to as file forms, and the file forms may be, for example, a reproducible form, a non-reproducible form, and the like, which is not limited to this.

That is to say, in the embodiment of the present disclosure, it is supported that the RPA robot acquires the content of the file to be processed from the multiple platforms, then the content of the file to be processed having different file forms may be correspondingly processed to obtain the standardized file, and then a subsequent information generation method combining the RPA and the AI may be performed based on the standardized file, which may be specifically referred to in the subsequent embodiments.

In the embodiment of the present disclosure, the content of the file to be processed may be obtained by the RPA robot from an official website of each province and city or from a designated column of a website to be monitored and collected, and the content of the file to be processed is automatically obtained according to a preset flow, and then the content of the file to be processed may be processed in combination with the file form of the obtained content of the file to be processed, so as to obtain a standardized file, which may be referred to in the following embodiments.

S202: and standardizing the content of the corresponding file to be processed according to the file form to obtain a corresponding standardized file.

After the content of the file to be processed is obtained by the RPA robot, the content of the file to be processed can be correspondingly processed (the processing mode can be called as standardized processing) to obtain a standardized file which is more suitable for being processed in a subsequent information generation method combining RPA and AI, so that the information generation efficiency is effectively improved.

In some embodiments, the corresponding to-be-processed file content is standardized according to the file format, and after the file format corresponding to the to-be-processed file content is determined, a processing mode corresponding to the file format is determined, and the to-be-processed file content is processed based on the processing mode, so as to obtain a standardized file.

In the embodiment of the present disclosure, because the contents of the file to be processed issued on the multi-party platform are different in file form, when the information of the file is interpreted, the file may correspond to different manners, for example, for the contents of the file to be processed issued on the platform in a reproducible and/or downloadable file form, a processing manner of copying and/or downloading may be directly adopted to copy and/or download the corresponding contents of the file to be processed from the platform, for the contents of the file to be processed issued on the platform in an unreproducible and/or non-downloadable file form, at this time, the corresponding contents of the file to be processed cannot be directly obtained from the platform, at this time, a processing manner of screenshot may be adopted to obtain the contents of the file to be processed presented in a picture form from the platform, and in the foregoing operation process, the file content to be processed obtained by directly copying and/or downloading from the platform, or the file content to be processed obtained in the form of pictures from the platform may be called a standardized file.

S203: and analyzing and identifying the standardized file to obtain element information to be processed.

According to the embodiment of the disclosure, after the RPA robot acquires the standardized file, the standardized file can be analyzed and identified, so that the element information to be processed can be analyzed and acquired from the standardized file.

In some embodiments, the standardized file may be analyzed and identified by combining with the pre-trained artificial intelligence model, that is, the standardized file may be input into the pre-trained artificial intelligence model to obtain the element information to be processed output by the pre-trained artificial intelligence model, or the standardized file may be analyzed and identified by any other possible method to obtain the element information to be processed, for example, a feature analysis method, a semantic analysis method, and the like, which is not limited thereto.

In the embodiment of the disclosure, the content of the file to be processed is determined, and the content of the file to be processed is processed according to the file form corresponding to the content of the file to be processed, so that the processing operation adaptive to the file form can be performed on the content of the file to be processed in different file forms, and the processing efficiency and the processing effect of the content of the file to be processed can be effectively improved.

S204: the element type corresponding to the standardized document is determined.

S205: and determining a target recommendation object matched with the element type, wherein the target recommendation object has corresponding object description information.

S206: and processing the element information to be processed according to the object description information to obtain target element information.

For the description of S204-S206, reference may be made to the above embodiments, which are not described herein again.

In the embodiment, the content of the file to be processed is determined, and the content of the file to be processed is processed according to the file form corresponding to the content of the file to be processed, so that the processing operation adaptive to the file form can be performed on the content of the file to be processed in different file forms, and the processing efficiency and the processing effect of the content of the file to be processed can be effectively improved, in addition, the content of the file to be processed, which is difficult to obtain (cannot be copied and downloaded) on a platform, can be converted into the picture to be obtained, so that the comprehensiveness of the obtained standardized file is effectively improved, more accurate and comprehensive element information to be processed can be obtained by identifying the standard file, then the element type corresponding to the standardized file is determined, and the target recommended object matched with the element type is determined, wherein, the target recommendation object has corresponding object description information, and the element information to be processed is processed according to the object description information to obtain the target element information, so that the target element information matched with the target recommendation object can be intelligently generated for the target recommendation object, and the generation effect of the element information is effectively improved.

Fig. 3 is a schematic flowchart of an information generating method combining RPA and AI according to another embodiment of the present disclosure.

Referring to fig. 3, the information generating method combining RPA and AI includes:

s301: and determining the content of the file to be processed, wherein the content of the file to be processed has a corresponding file form.

S302: and standardizing the content of the corresponding file to be processed according to the file form to obtain a corresponding standardized file.

For the description of S301 to S302, reference may be made to the above embodiments, which are not described herein again.

S303: and carrying out Optical Character Recognition (OCR) processing on the standardized file based on an Artificial Intelligence (AI) technology to obtain a standardized text.

After the corresponding standardized file is obtained, the standardized file may be processed by an Optical Character Recognition (OCR) method, so as to identify and obtain corresponding text information from the standardized file form, where the text information may be referred to as a standardized text.

For example, after the standardized document presented in the form of a picture is obtained from the platform by using the screenshot processing method, an OCR method may be used to extract a corresponding standardized text from the standardized document presented in the form of a picture, and then a subsequent information generation method combining an RPA and an AI may be performed based on the standardized text, which may be specifically referred to in the subsequent embodiments.

S304: and identifying element information to be processed from the standardized text based on Natural Language Processing (NLP).

After the standardized text is identified and obtained from the standardized file, the element information to be processed can be identified and obtained from the standardized text based on Natural Language Processing (NLP) technology.

In some embodiments, the element information to be processed is identified and obtained from the standardized text based on the NLP, and the element information to be processed may be identified and obtained from the standardized text by using an NLP text understanding method, or alternatively, the element information to be processed may be identified and obtained from the standardized text by using a pre-trained NLP model, which is not limited to this.

Optionally, in some embodiments, the element information to be processed is identified and obtained from the standardized text based on natural language processing NLP, which may be determining a target element information extraction model corresponding to an information type, and inputting the standardized text into the target element information extraction model to obtain the element information to be processed output by the element information extraction model, because the element information to be processed is identified and obtained from the standardized text in combination with the target element information extraction model, interference of other subjective interpretation factors on the interpretation process of the standardized text can be avoided in the interpretation process of the standardized text, so that the interpretation difficulty of the standardized text is effectively reduced, the identification and acquisition efficiency of the element information to be processed is effectively improved, and the accuracy of the element information to be processed is effectively improved.

The element information extraction model can be used for extracting element information to be processed from a standardized text, standardized texts of different information types can respectively correspond to different element information extraction models, and correspondingly, the element information extraction model corresponding to the information type of the obtained standardized text can be called a target element information extraction model, the target recommended element information extraction model belongs to a plurality of trained element information extraction models, and the plurality of element information extraction models respectively correspond to a plurality of information types.

In the embodiment of the disclosure, the RPA robot may automatically select a target element information extraction model corresponding to the information type from among the plurality of element information extraction models according to the information type corresponding to the standardized text, and then may input the standardized text into the target element information extraction model to obtain the to-be-processed element information output by the target element information extraction model.

S305: a type of information corresponding to the standardized text is determined.

After determining the standardized text from the standardized file, the disclosed embodiments may determine the type of information corresponding to the standardized text.

The information type may be used to describe a category to which information of the standardized text belongs, that is, the information in the standardized text may be divided based on different classification dimensions to obtain different types of standardized texts, for example, the information of the standardized text may be divided into a bonus text type and a penalty text type based on content classification dimensions, which is not limited to this.

In some embodiments, the determining of the information type corresponding to the standardized text may be analyzing the information content of the standardized text, for example, the standardized text may be analyzed in a semantic analysis manner to determine the information type corresponding to the standardized text, or any other possible analysis manner may also be analyzed to determine the information type corresponding to the standardized text, for example, a feature analysis manner, a text analysis manner, and the like, which is not limited thereto.

Optionally, in some embodiments, determining the information type corresponding to the normalized text may be inputting the normalized text into a pre-trained information classification model to obtain the information type corresponding to the normalized text output by the information classification model.

The information classification model may be an artificial intelligence model, specifically, for example, a neural network model or a machine learning model, or may be any other possible artificial intelligence model capable of performing an information classification task, which is not limited herein.

To sum up, in the embodiment of the present disclosure, referring to fig. 4, fig. 4 is a schematic diagram of an extraction process of element information to be processed provided in an embodiment of the present disclosure, that is, a content of a file to be processed may be obtained from a provincial government website platform, a third-party website platform, and other various website platforms, and whether the content of the file to be processed corresponds to a file format that can be copied and/or downloaded is determined, when the content of the file to be processed is the file format that can be copied and/or downloaded, a processing method of copying and/or downloading is directly adopted, the corresponding content of the file to be processed is obtained from the platform as a standardized file, when the content of the file to be processed is the file format that cannot be copied and/or downloaded, a processing method of screenshot is adopted, the content of the file to be processed presented in a picture form is obtained from the platform, as the standardized file, a standardized text can be recognized from the standardized file presented in the form of a picture by means of OCR recognition, 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.

S306: and taking the information type as an element type corresponding to the standardized file to which the standardized text belongs.

According to the information type determining method and device, after the information type to which the standardized text in the standardized file belongs is determined, 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, and 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, so that the information type corresponding to the standardized text can be accurately determined based on a more comprehensive basis of the standardized text, and the accuracy of determining the element type can be effectively improved when the information type is used as the element type corresponding to the standardized file to which the standardized text belongs.

S307: and determining a target recommendation object matched with the element type, wherein the target recommendation object has corresponding object description information.

For the description of S307, reference may be made to the foregoing embodiments, which are not described herein again.

S308: and determining whether the object description information and the element information to be processed meet the matching condition.

After determining the object description information of the target recommendation object and the element information to be processed of the standardized file, the disclosed embodiment may determine whether the object description information and the element information to be processed satisfy a matching condition.

In the matching process of the object description information and the element information to be processed, a condition preset in an application scene generated by combining actual information may be referred to as a matching condition, and the matching condition may be used to assist in determining whether the object description information and the element information to be processed are matched.

In some embodiments, determining whether the object description information and the element information to be processed satisfy the matching condition may be to pre-extract corresponding feature information from the object description information and the element information to be processed, and then determine whether the corresponding feature information in the object description information and the element information to be processed satisfies the matching condition by using a feature matching algorithm, or may also determine whether the object description information and the element information to be processed satisfy the matching condition by using any other possible method, for example, a model matching method, which is not limited thereto.

Optionally, in some embodiments, determining whether the object description information and the to-be-processed element information satisfy the matching condition may be determining a matching degree value of the object description information and the to-be-processed element information, and determining that the object description information and the to-be-processed element information satisfy the matching condition when the matching degree value is greater than or equal to a matching degree threshold, and determining that the object description information and the to-be-processed element information do not satisfy the matching condition when the matching degree value is less than the matching degree threshold.

The value used for quantitatively describing the matching degree between the object description information and the element information to be processed may be referred to as a matching degree value, and the matching degree value may specifically be, for example, a similarity value between the object description information and the element information to be processed, a matching ratio between a plurality of object description information and a plurality of element information to be processed, and the like, which is not limited herein.

The threshold value preset for the matching degree between the object description information and the element information to be processed may be referred to as a matching degree threshold value.

In the embodiment of the present disclosure, determining whether the object description information and the to-be-processed element information satisfy the matching condition may be determining a matching degree value (matching ratio) of the object description information and the to-be-processed element information, comparing the determined matching degree value (matching ratio) with a preset matching degree threshold (matching ratio threshold), determining that the object description information and the to-be-processed element information satisfy the matching condition when the matching degree value (matching ratio) is greater than or equal to the matching degree threshold (matching ratio threshold), and determining that the object description information and the to-be-processed element information do not satisfy the matching condition when the matching degree value (matching ratio) is less than the matching degree threshold (matching ratio threshold).

For example, for 10 items of object description information and 10 items of element information to be processed, the number of matching items (for example, 7 items) between 10 items of object description information and 10 items of element information to be processed may be determined, at this time, it may be determined that the matching ratio between 10 items of object description information and 10 items of element information to be processed is 70%, at this time, the matching ratio of 70% may be compared with a preset matching ratio threshold value of 60% to determine that the object description information and the element information to be processed satisfy the matching condition, which is not limited.

S309: and if the object description information and the element information to be processed meet the matching condition, taking the element information to be processed as target element information.

When it is determined that the object description information and the element information to be processed satisfy the matching condition, the embodiment of the present disclosure may use the element information to be processed as the target element information, and push the target element information to a target recommendation object corresponding to the object description information.

In some embodiments, when it is determined that the object description information and the to-be-processed element information do not satisfy the matching condition, the object description information and the to-be-processed element information may also be pushed to a relevant worker, and the worker may also view a specific matching item, and determine whether the target element information can be pushed to a target recommendation object corresponding to the object description information.

Optionally, in other embodiments, after it is determined that the object description information and the element information to be processed satisfy the matching condition, a standardized text to which the target element information belongs may be determined, and the standardized text to which the target element information belongs may be provided to the target recommendation object, and then the target recommendation object may perform a subsequent operation in combination with the target element information and the standardized text.

S310: and analyzing the standardized text to obtain declaration operation information.

The information for performing the declaration operation on the scenario information in the standardized file may be referred to as declaration operation information, and the declaration operation information may be, for example, declaration material information, declaration form information, or the like, but is not limited thereto.

In the embodiment of the disclosure, the RPA robot may analyze the standardized text to obtain the declaration material information and declaration operation mode information required for declaring the scheme corresponding to the standardized text from the standardized text, and then trigger the subsequent steps in combination with the declaration operation information obtained through the analysis, which is not limited in this regard.

For example, the standardized text may be analyzed to determine the declared material information that needs to be provided if an enterprise needs to declare the scheme information (e.g., the reward scheme) corresponding to the standardized text, and may also determine whether the existing declared material information of the enterprise is complete at present, generate corresponding declared material supplementary information when the declared material information is incomplete, and provide the declared material information and the declared material supplementary information to the corresponding enterprise, which is not limited herein.

S311: and generating a declaration operation link according to the standardized text.

After generating the corresponding declaration operation information according to the standardized text, the embodiment of the disclosure can generate the corresponding declaration operation link according to the standardized text, wherein the declaration operation link can be used for executing the corresponding declaration operation.

That is to say, in the embodiment of the present disclosure, when it is determined that the object description information matches the to-be-processed element information, the declaration operation link may be generated according to the standardized text corresponding to the to-be-processed element information, and then, the target recommendation object may implement the one-key declaration operation of the relevant scheme based on the declaration operation link.

S312: and providing the declaration operation information and the declaration operation link to a target recommendation object, wherein the target recommendation object executes declaration operation based on the declaration operation link and the declaration operation information.

According to the embodiment of the disclosure, after generating the declaration operation information and the declaration operation link according to the standardized text, the RPA robot may provide the declaration operation information and the declaration operation link to the determined target recommendation object, and the target recommendation object may perform corresponding declaration operation based on the declaration operation link and the declaration operation information.

For example, after the declaration material information and the declaration material supplemental information are provided as declaration operation information to the corresponding target recommendation object (enterprise), the RPA robot may provide the declaration operation link and the declaration material information to the enterprise together, if the declaration material supplemental information indicates that the enterprise does not need to supplement the declaration material information, the enterprise may implement one-key declaration according to the declaration operation link, and if the declaration material supplemental information indicates that the enterprise needs to supplement the declaration material information, the enterprise may supplement the corresponding declaration material information according to a declaration material information supplement entry generated by clicking the declaration operation link, and complete the corresponding declaration operation after the declaration material information is supplemented, which is not limited.

In the embodiment of the present disclosure, referring to fig. 5, fig. 5 is a schematic flowchart of an information generating method combining RPA and AI according to another embodiment of the present disclosure, in a starting stage, it may be determined whether a normalized document includes element information to be processed to be matched, and when the normalized document includes the element information to be matched, according to an element type corresponding to the element information to be processed in the normalized document, a target recommendation object matching the element type is determined, and object description information of the target recommendation object is determined, and then it is determined whether the object description information and the element information to be processed satisfy a matching condition, and when the object description information and the element information to be processed satisfy the matching condition, the element information to be processed is provided as the target element information to the corresponding target recommendation object, or when the object description information and the element information to be processed do not satisfy the matching condition, and judging whether the element information to be processed can be provided to a corresponding target recommendation object as target element information or not manually.

In the embodiment, the content of the file to be processed is determined, wherein the content of the file to be processed has a corresponding file form, the corresponding content of the file to be processed is standardized according to the file form to obtain a corresponding standardized file, the standardized file is subjected to Optical Character Recognition (OCR) processing based on an Artificial Intelligence (AI) technology to obtain a standardized text, and element information to be processed is identified and obtained from the standardized text based on Natural Language Processing (NLP), so that the accuracy and the referential property of the element information to be processed can be effectively improved, the information type corresponding to the standardized text is determined, the information type is taken as the element type corresponding to the standardized file to which the standardized text belongs, and the information type corresponding to the standardized text in the standardized file is taken as the element type corresponding to the element to be processed, so that the method can be based on a more comprehensive basis based on the standardized text, the method comprises the steps of accurately determining the information type corresponding to the standardized text, effectively improving the accuracy of determining the element type when the information type is used as the element type corresponding to the standardized file to which the standardized text belongs, determining a target recommendation object matched with the element type, determining whether object description information and element information to be processed meet matching conditions, taking the element information to be processed as target element information when the object description information and the element information to be processed meet the matching conditions, analyzing 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 recommendation object, wherein the target recommendation object executes declaration operation based on the declaration operation link and the declaration operation information, so that, the target element information can be effectively and conveniently utilized by the target recommendation object, and meanwhile, the execution process of the declaration operation of the target recommendation object can be effectively and conveniently carried out.

Fig. 6 is a schematic structural diagram of an information generating apparatus that combines RPA and AI according to an embodiment of the present disclosure.

Referring to fig. 6, the RPA and AI combined information generating apparatus 600 includes:

an obtaining module 601, configured to obtain a standardized file, where the standardized file includes: element information to be processed;

a first determining module 602, configured to determine an element type corresponding to the standardized document;

a second determining 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

and the processing module 604 is configured to process the element information to be processed according to the object description information to obtain the target element information.

Optionally, in some embodiments, referring to fig. 7, fig. 7 is a schematic structural diagram of an information generating apparatus combining an RPA and an AI according to another embodiment of the present disclosure, where the obtaining module 601 includes:

a first determining submodule 6011, configured to determine content of a file to be processed, where the content of the file to be processed has a corresponding file form;

the first processing submodule 6012 is configured to perform normalization processing on content of a corresponding to-be-processed file according to a file format to obtain a corresponding normalized file; and

and the parsing submodule 6013 is configured to parse and identify the standardized file to obtain the information of the to-be-processed element.

Optionally, in some embodiments, parsing submodule 6013 is specifically configured to:

performing Optical Character Recognition (OCR) processing on the standardized file based on an Artificial Intelligence (AI) technology to obtain a standardized text;

and identifying element information to be processed from the standardized text based on Natural Language Processing (NLP).

Optionally, in some embodiments, the first determining module 602 includes:

a second determination sub-module 6021 for determining the type of information corresponding to the standardized text;

the second processing sub-module 6022 is configured to use the information type as an element type corresponding to the standardized file to which the standardized text belongs.

Optionally, in some embodiments, the second determining submodule 6021 is further configured to:

and inputting the standardized text into the pre-trained information classification model to obtain the information type which is output by the information classification model and corresponds to the standardized text.

Optionally, in some embodiments, parsing submodule 6013 is further configured to:

determining a target element information extraction model corresponding to the information type;

inputting the standardized text into a target element information extraction model to obtain element information to be processed output by the element information extraction model;

the target recommendation element information extraction model belongs to a plurality of trained element information extraction models, and the element information extraction models respectively correspond to a plurality of information types.

Optionally, in some embodiments, the processing module 604 includes:

a third determining sub-module 6041 configured to determine whether the object description information and the element information to be processed satisfy a matching condition;

and a third processing sub-module 6042 configured to use the element information to be processed as the target element information when the object description information and the element information to be processed satisfy the matching condition.

Optionally, in some embodiments, the third determining sub-module 6041 is further configured to:

determining the matching degree value of the object description information and the element information to be processed;

if the matching degree value is larger than or equal to the matching degree threshold value, determining that the object description information and the element information to be processed meet the matching condition;

and if the matching degree value is smaller than the matching degree threshold value, determining that the object description information and the element information to be processed do not meet the matching condition.

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

a fourth determination sub-module 6043 configured to determine, after the element information to be processed is taken as the target element information, a standardized text to which the target element information belongs, and supply the standardized text to the target recommendation object.

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

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

a generation submodule 6045 for generating a declaration operation link according to the standardized text; and

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 the declaration operation based on the declaration operation link and the declaration operation information.

It should be noted that, the functions and specific implementation principles of the above modules in the embodiments of the present disclosure may refer to the above method embodiments, and are not described herein again.

In order to implement the above embodiment, the present disclosure also provides an electronic device, including: the information generating method includes the steps of storing information in a memory, storing the information in the memory, and executing the information generating method by a processor.

Fig. 8 is a schematic diagram of a hardware structure of an electronic device according to an embodiment of the present disclosure. As shown in fig. 8, the electronic device 800 includes: a memory 810 and a processor 820, the memory 810 having stored therein computer programs operable on the processor 820. The processor 820 implements the information generation method combining the RPA and the AI in the above-described embodiment when executing the computer program. The number of the memory 810 and the processor 820 may be one or more.

The electronic device further includes:

and a communication interface 830, configured to communicate with an external device, and perform data interactive transmission.

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 may be connected to each other through a bus and perform communication with each other. The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended ISA (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown in FIG. 8, but this is not intended to represent only one bus or type of bus.

Optionally, in an implementation, if the memory 810, the processor 820 and the communication interface 830 are integrated on a chip, the memory 810, the processor 820 and the communication interface 830 may complete communication with each other through an internal interface.

The present disclosure also provides a computer-readable storage medium storing a computer program which, when executed by a processor, implements an information generating method combining RPA and AI as set forth in the foregoing embodiments of the present disclosure.

The present disclosure also provides a computer program product, which when executed by an instruction processor in the computer program product, implements the information generation method combining RPA and AI as set forth in the foregoing embodiments of the present disclosure.

It should be understood that the processor may be a Central Processing Unit (CPU), other general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or any conventional processor or the like. It is noted that the processor may be a processor supporting an Advanced reduced instruction set machine (ARM) architecture.

Further, optionally, the memory may include a read-only memory and a random access memory, and may further include a nonvolatile random access memory. The memory may be either volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The non-volatile Memory may include a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically Erasable PROM (EEPROM), or a flash Memory. Volatile Memory can include Random Access Memory (RAM), which acts as external cache Memory. By way of example, and not limitation, many forms of RAM are available. For example, Static Random Access Memory (Static RAM, SRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic Random Access Memory (SDRAM), Double Data rate Synchronous Dynamic Random Access Memory (DDR SDRAM), Enhanced SDRAM (ESDRAM), SLDRAM (SLDRAM), and Direct Memory bus RAM (DR RAM).

In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, 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. The procedures or functions according to the present disclosure may be fully or partially generated upon loading and execution of the computer program instructions on a computer. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. 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.

In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present disclosure. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.

Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present disclosure, "a plurality" means two or more unless specifically limited otherwise.

Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps in the process. And the scope of the preferred embodiments of the present disclosure includes additional implementations in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved.

The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied 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, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions.

It should be understood that portions of the present disclosure may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. All or part of the steps of the method of the above embodiments may be implemented by hardware that is configured to be instructed to perform the relevant steps by a program, which may be stored in a computer-readable storage medium, and which, when executed, includes one or a combination of the steps of the method embodiments.

In addition, functional units in the embodiments of the present disclosure may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module may also be stored in a computer-readable storage medium if it is implemented in the form of a software functional module and sold or used as a separate product. The storage medium may be a read-only memory, a magnetic or optical disk, or the like.

The above description is only for the specific embodiments of the present disclosure, but the scope of the present disclosure is not limited thereto, and any person skilled in the art can easily conceive of various changes or substitutions within the technical scope of the present disclosure, which should be covered by the 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, applied to an RPA robot, the method comprising:

obtaining a standardized file, wherein the standardized file comprises: element information to be processed;

determining an element type corresponding to the standardized file;

determining a target recommendation object matched with the element type, wherein the target recommendation object has corresponding object description information; and

and processing the element information to be processed according to the object description information to obtain target element information.

2. The method of claim 1, wherein said obtaining a standardized file comprises:

determining the content of a file to be processed, wherein the content of the file to be processed has a corresponding file form;

standardizing the content of the corresponding file to be processed according to the file form to obtain a corresponding standardized file; and

and analyzing and identifying the standardized file to obtain the element information to be processed.

3. The method of claim 2, wherein the parsing and identifying the standardized file to obtain the element information to be processed comprises:

and identifying and obtaining the element information to be processed from the standardized text based on Natural Language Processing (NLP).

4. The method of claim 3, wherein said determining the element type corresponding to the standardized document comprises:

determining an information type corresponding to the standardized text;

and taking the information type as an element type corresponding to the standardized file to which the standardized text belongs.

5. The method of claim 4, wherein said determining a type of information corresponding to said standardized text comprises:

and inputting the standardized text into a pre-trained information classification model to obtain the information type which is output by the information classification model and corresponds to the standardized text.

6. The method according to claim 4, wherein the identifying the element information to be processed from the normalized text based on the NLP comprises:

inputting the standardized text into the target element information extraction model to obtain the element information to be processed output by the element information extraction model;

the target recommended element information extraction model belongs to a plurality of trained element information extraction models, and the element information extraction models respectively correspond to a plurality of information types.

7. The method according to claim 2, wherein the processing the element information to be processed according to the object description information to obtain target element information comprises:

determining whether the object description information and the element information to be processed meet a matching condition;

and if the object description information and the element information to be processed meet the matching condition, taking the element information to be processed as the target element information.

8. The method of claim 7, wherein the determining whether the object description information and the to-be-processed element information satisfy a matching condition comprises:

if the matching degree value is larger than or equal to a matching degree threshold value, determining that the object description information and the element information to be processed meet the matching condition;

9. The method according to claim 7, further comprising, after said taking the to-be-processed element information as the target element information:

and determining a standardized text to which the target element information belongs, and providing the standardized text to the target recommendation object.

10. The method of claim 7, further comprising:

analyzing 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 a target recommendation object, wherein the target recommendation object executes declaration operation based on the declaration operation link and the declaration operation information.

11. An information generating apparatus combining RPA and AI, applied to an RPA robot, the apparatus comprising:

an obtaining module, configured to obtain a standardized file, where the standardized file includes: element information to be processed;

a first determining module, configured to determine an element type corresponding to the standardized file;

the second determination module is used for determining a target recommendation object matched with the element type, wherein the target recommendation object has corresponding object description information; and

and the processing module is used for processing the element information to be processed according to the object description information to obtain target element information.

12. The apparatus of claim 11, wherein the acquisition module comprises:

the first determining submodule is used for determining the content of a file to be processed, wherein the content of the file to be processed has a corresponding file form;

the first processing submodule is used for carrying out standardization processing on the corresponding to-be-processed file content according to the file form so as to obtain a corresponding standardized file; and

and the analysis submodule is used for analyzing and identifying the standardized file to obtain the element information to be processed.

13. The apparatus of claim 12, wherein the parsing submodule is specifically configured to:

14. An electronic device, comprising: a processor and a memory, the memory storing instructions therein that are loaded and executed by the processor to implement the information generating method in combination with RPA and AI according to any one of claims 1 to 10.

15. A computer-readable storage medium, characterized in that a computer program is stored in the computer-readable storage medium, which computer program, when being executed by a processor, implements the information generating method in combination with RPA and AI according to any one of claims 1-10.