News processing method and device combining RPA and AI
By combining RPA and AI news processing methods, NLP and OCR technology are used to automatically obtain and process news from the website, solving the problems of low efficiency and high error rates of manual operations by enterprises or organizations, and achieving an efficient and immediate news processing process.
Patent Information
- Application Number
- CN202110693940.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-06-22
- Publication Date
- 2024-11-01
- Estimated Expiration
- 2041-06-22
AI Technical Summary
In the prior art, enterprises or organizations need to manually copy, adjust and fill in news into internal systems, resulting in low efficiency, poor timeliness and high error rates.
Using news processing methods combining robot process automation (RPA) and artificial intelligence (AI), we can obtain topic-related news from preset websites through natural language processing (NLP), automatically extract information and generate local documents without manual participation, including Optical character recognition (OCR) processing and graphic code processing, fill in the user system and publish news.
It greatly saves the working time of the responsible personnel, improves efficiency and immediacy, reduces error rates, and realizes an automated news processing process.
Smart Images

Figure CN113553812B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical fields of Robotic Process Automation (RPA) and Artificial Intelligence (AI), and in particular to a news processing method and device combining RPA and AI. Background Art
[0002] Robotic Process Automation (RPA) uses specific "robot software" to simulate human operations on computers and automatically execute process tasks according to rules.
[0003] Artificial Intelligence (AI) is a technical science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence.
[0004] RPA and AI technologies have the advantages of high automation, high accuracy and low cost. With the widespread application of RPA robots, more and more human work is taken over by RPA robots. Using artificial intelligence technology to help enterprises or organizations understand relevant trends or consult news has become an urgent problem for enterprises or organizations.
[0005] In the related art, each enterprise or organization needs a dedicated person to manually copy, adjust and fill the news into the internal system of each enterprise or organization. Manual operations require a large number of repetitive operations, take a lot of time, have low efficiency, poor timeliness and high error rate. Summary of the invention
[0006] The present application aims to solve one of the technical problems in the related art at least to some extent.
[0007] To this end, the first purpose of this application is to propose a news processing method that combines RPA and AI, which does not require human involvement, greatly saves the working time of responsible personnel, has high efficiency, high immediacy, and low error rate.
[0008] The second purpose of this application is to propose a news processing device that combines RPA and AI.
[0009] The third object of the present application is to provide a computing device.
[0010] A fourth objective of the present application is to provide a computer-readable storage medium.
[0011] To achieve the above-mentioned objectives, the first aspect embodiment of the present application proposes a news processing method combining RPA and AI, including: obtaining news related to a preset topic from a preset website based on natural language processing NLP; extracting information of preset fields from the news based on natural language processing NLP to obtain target news content; and generating a local document based on the target news content.
[0012] The news processing method combining RPA and AI proposed in the embodiment of the present application obtains news related to a preset topic from a preset website based on natural language processing NLP, extracts information of preset fields from the news based on natural language processing NLP, obtains target news content, and generates a local document based on the target news content. In this embodiment, the RPA robot automatically obtains news related to a preset topic from a preset website based on natural language processing NLP, and automatically edits the news content and generates a local document without manual participation, which greatly saves the working time of the responsible personnel, with high efficiency, high immediacy and low error rate.
[0013] According to an embodiment of the present application, the news processing method further includes: filling in the user system according to the local document to generate news to be published; publishing the news to be published to a preset location to be published; and sending review reminder information to the user.
[0014] According to one embodiment of the present application, generating a local document based on the target news content includes: judging whether the target news content contains pictures based on optical character recognition (OCR); if the target news content does not contain pictures, opening office software, performing a first regularization process on the target news content, and generating the local document; if the target news content contains pictures, opening office software, performing a second regularization process and graphic coding process on the target news content, and generating the local document.
[0015] According to one embodiment of the present application, the first regularization processing includes adjustment of any one or more of the following: font size, font size, font color, paragraphs, indents and format; the first regularization processing includes adjustment of any one or more of the following: font size, font size, font color, paragraphs, indents, format, image format and image size.
[0016] According to an embodiment of the present application, the graphic-text coding process includes: converting the text content in the graphic-text format in the target news content into a preset code.
[0017] According to an embodiment of the present application, the preset fields include any one or more of the following: main title, subtitle, source, date, text content, text, author and link.
[0018] According to one embodiment of the present application, filling in the user system according to the local document includes: if the local document does not include the preset code, then filling in the user system according to the preset field according to the local document to generate the news to be published; if the local document includes the preset code, then filling in the user system according to the local document according to the target preset field in the preset field, and importing the preset code into the text content to generate the text content in a graphic format, and the preset field includes the text content and the target preset field.
[0019] To achieve the above-mentioned purpose, the second aspect embodiment of the present application proposes a news processing device combining RPA and AI, including: an acquisition module, used to obtain news related to a preset topic from a preset website based on natural language processing NLP; an extraction module, used to extract information of preset fields from the news by natural language processing NLP to obtain target news content; a generation module, used to generate a local document based on the target news content.
[0020] The news processing device combining RPA and AI proposed in the embodiment of the present application obtains news related to a preset topic from a preset website based on natural language processing NLP, extracts information of preset fields from the news based on natural language processing NLP, obtains target news content, and generates a local document based on the target news content. In this embodiment, the RPA robot automatically obtains news related to a preset topic from a preset website based on natural language processing NLP, and automatically edits the news content and generates a local document without manual participation, which greatly saves the working time of the responsible personnel, with high efficiency, high immediacy and low error rate.
[0021] According to one embodiment of the present application, the news processing device also includes: a filling module, which is used to fill in the user system according to the local document to generate news to be published; a publishing module, which is used to publish the news to be published to a preset location to be published; and a sending module, which is used to send review reminder information to the user.
[0022] According to one embodiment of the present application, the generation module includes: a judgment unit, which is used to judge whether the target news content contains pictures based on optical character recognition (OCR); a first generation unit, which is used to open the office software if the target news content does not contain pictures, perform a first regularization process on the target news content, and generate the local document; a second generation unit, which is used to open the office software if the target news content contains pictures, perform a second regularization process and graphic coding process on the target news content, and generate the local document.
[0023] According to one embodiment of the present application, the first regularization processing includes adjustment of any one or more of the following: font size, font size, font color, paragraphs, indents and format; the first regularization processing includes adjustment of any one or more of the following: font size, font size, font color, paragraphs, indents, format, image format and image size.
[0024] According to an embodiment of the present application, the graphic-text coding process includes: converting the text content in the graphic-text format in the target news content into a preset code.
[0025] According to an embodiment of the present application, the preset fields include any one or more of the following: main title, subtitle, source, date, text content, text, author and link.
[0026] According to one embodiment of the present application, the filling module includes: if the local document does not include the preset code, then the user system is filled in according to the preset field based on the local document to generate the news to be published; if the local document includes the preset code, then the user system is filled in according to the target preset field in the preset field based on the local document, and the preset code is imported into the text content to generate the text content in a graphic format, and the preset field includes the text content and the target preset field.
[0027] To achieve the above-mentioned purpose, the third aspect embodiment of the present application proposes a computing device, comprising: a memory storing executable program code; a processor coupled to the memory; the processor calls the executable program code stored in the memory to execute the news processing method combining RPA and AI as described in the first aspect embodiment of the present application.
[0028] To achieve the above-mentioned objectives, the fourth aspect embodiment of the present application proposes a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the news processing method combining RPA and AI as described in the first aspect embodiment of the present application is implemented. BRIEF DESCRIPTION OF THE DRAWINGS
[0029] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings that are often needed in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0030] Figure 1 It is a flowchart of a news processing method combining RPA and AI provided in an embodiment of the present application;
[0031] Figure 2This is a news example diagram obtained by a news processing method combining RPA and AI provided in an embodiment of the present application;
[0032] Figure 3 is a flowchart of another news processing method combining RPA and AI provided in an embodiment of the present application;
[0033] Figure 4 This is a user system filling interface diagram in a news processing method combining RPA and AI provided in an embodiment of the present application;
[0034] Figure 5 is a flowchart of another news processing method combining RPA and AI provided in an embodiment of the present application;
[0035] Figure 6 is a flowchart of another news processing method combining RPA and AI provided in an embodiment of the present application;
[0036] Figure 7 This is an overall flow chart of a news processing method combining RPA and AI provided in an embodiment of the present application;
[0037] Figure 8 This is a schematic diagram of another news processing device combining RPA and AI provided in an embodiment of the present application. DETAILED DESCRIPTION
[0038] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.
[0039] The following describes the news processing method and system combining RPA and AI in an embodiment of the present application with reference to the accompanying drawings.
[0040] Figure 1 is a flowchart of a news processing method combining RPA and AI according to an embodiment of the present application. Figure 1 As shown, the news processing method combining RPA and AI includes the following steps:
[0041] S101, obtaining news related to a preset topic from a preset website based on natural language processing (NLP).
[0042] The execution subject of the news processing method combining RPA and AI in the embodiment of the present application may be the news processing device combining RPA and AI in the embodiment of the present application, and the above-mentioned news processing device combining RPA and AI can be configured in the RPA system of any electronic device to execute the news processing method combining RPA and AI in the embodiment of the present application. Optionally, the above-mentioned RPA system may include an RPA robot. RPA is a business process automation technology based on software robots and artificial intelligence. The RPA robot can intelligently understand the existing applications of the enterprise through the user interface, automate the routine operations based on rules, automatically and repeatedly read emails, read Office components, operate databases and web pages and client software, etc., collect data, perform tedious calculations, generate files and reports in large quantities, and complete boring file inspections and other tasks. It can greatly reduce the investment in labor costs, effectively improve the existing office efficiency, and complete the work accurately, stably and quickly. In the embodiment of the present application, the RPA robot can intelligently understand the user system through the user interface, automatically log in to the user system according to the login user information provided by the user, and open the relevant news information and dynamic pages.
[0043] In the embodiment of the present application, the RPA robot automatically obtains news related to a preset topic from a preset website based on natural language processing (NLP). The preset website may specifically include but is not limited to websites such as "People's Daily Online" and "** News Network", and the preset topic may specifically include but is not limited to party building, current affairs, etc.
[0044] S102, extracting information of preset fields from the news based on natural language processing (NLP) to obtain target news content.
[0045] In the embodiment of the present application, the RPA robot automatically extracts information of preset fields from the news related to the preset topic obtained in step S101 based on natural language processing NLP intelligence to obtain the target news content. The preset field information may specifically include but is not limited to the main title, subtitle, source, date, content, text, picture, author, link, etc. of the news.
[0046] For example Figure 2 In the news example shown, after the RPA robot obtains the news, it classifies the content of the news according to the subject, source, date, content, text, author, and link, and then extracts information from the relevant classified title content. At the same time, it removes information such as "People's Daily (Page 4, June 8, 2021)" that users do not pay attention to, forming the cleaned data, namely the target news content.
[0047] S103, generating a local document according to the target news content.
[0048] In the embodiment of the present application, the RPA robot automatically generates a local document based on the target news content obtained in step S102.
[0049] The news processing method combining RPA and AI proposed in the embodiment of the present application obtains news related to a preset topic from a preset website based on natural language processing NLP, extracts information of preset fields from the news based on natural language processing NLP, obtains target news content, and generates a local document based on the target news content. In this embodiment, the RPA robot automatically obtains news related to a preset topic from a preset website based on natural language processing NLP, and automatically edits the news content and generates a local document without manual participation, which greatly saves the working time of the responsible personnel, with high efficiency, high immediacy and low error rate.
[0050] Figure 3 is a flowchart of another news processing method combining RPA and AI provided in an embodiment of the present application. Figure 3 As shown in the above Figure 1 Based on the illustrated embodiment, the news processing method combining RPA and AI proposed in this embodiment specifically includes the following steps:
[0051] S301, obtaining news related to a preset topic from a preset website based on natural language processing (NLP).
[0052] S302, extracting information of preset fields from the news based on natural language processing (NLP) to obtain target news content.
[0053] S303: Generate a local document according to the target news content.
[0054] In the embodiment of the present application, steps S301-S303 are the same as steps S101-S103 in the above embodiment and are not described again here.
[0055] S304, filling in the user system according to the local document to generate news to be published.
[0056] In the embodiment of the present application, the RPA robot can automatically fill in the user system according to the local document generated in step S303 to generate news to be published. The filling interface of the user system can be as follows Figure 4 As shown, the RPA robot can automatically select the publishing column, fill in the sub-column, fill in the title, select the media type, add external links, complete the filling of news content, select the news source, fill in the author, and fill in the source URL based on the local document.
[0057] S305, publishing the news to be published to a preset publishing location.
[0058] In the embodiment of the present application, the RPA robot automatically selects the publishing time, the sorting time, and the browsing permissions, and publishes the news to be published generated in step S304 to a preset location to be published, which may be the "to be published" information column of the user system.
[0059] S306, sending a review reminder message to the user.
[0060] In an embodiment of the present application, the RPA robot can automatically send review reminder information to the user through the user system, specifically, it can send an email to the user's mailbox or send a text message to the user's mobile terminal. The embodiment of the present application does not impose too many restrictions on this.
[0061] The news processing method combining RPA and AI proposed in the embodiment of the present application obtains news related to a preset topic from a preset website based on natural language processing NLP, extracts information of preset fields from the news based on natural language processing NLP, obtains target news content, and generates local documents based on the target news content. In this embodiment, the RPA robot automatically obtains news related to a preset topic from a preset website based on natural language processing NLP, automatically edits the news content, generates local documents, and automatically fills in the user system based on the local documents, publishes the news to be published to a preset place, and sends a review reminder message at the same time, without the need for human intervention, which greatly saves the working time of the responsible personnel, with high efficiency, high immediacy, and low error rate. The RPA robot can operate on a daily basis, and the entire process has a high accuracy rate, avoiding missed and wrong news.
[0062] Figure 5 is a flowchart of another news processing method combining RPA and AI provided in an embodiment of the present application. Figure 5 As shown in the above Figure 3 Based on the illustrated embodiment, step S303 "generating a local document according to target news content" may specifically include:
[0063] S501, judging whether the target news content contains pictures based on optical character recognition (OCR).
[0064] In the embodiment of the present application, the RPA robot automatically determines whether the target news content obtained in step S302 contains pictures based on optical character recognition (OCR), that is, determines whether the target news content is pure text content or graphic content.
[0065] S502: If the target news content does not contain pictures, the office software is opened to perform a first regularization process on the target news content to generate a local document.
[0066] In the embodiment of the present application, if the target news content does not contain pictures, the RPA robot automatically opens the office software, performs the first regularization processing on the target news content, and generates a local document. The office software may specifically include but is not limited to Office (Microsoft Office) or WPS (Word Processing System), and the first regularization processing specifically includes but is not limited to adjusting any one or more of the following: font size, font size, font color, paragraph, indentation and format, etc.
[0067] S503, if the target news content contains pictures, the office software is opened to perform a second regularization process and a picture-text coding process on the target news content to generate a local document.
[0068] In the embodiment of the present application, if the target news content contains pictures, the RPA robot automatically opens the office software, performs the second regularization and image-text coding processing on the target news content, and generates a local document. Among them, the office software specifically includes but is not limited to Office or WPS, and the second regularization processing specifically includes but is not limited to adjusting any one or more of the following: font size, font size, font color, paragraph, indentation, format, picture format and picture size, etc.
[0069] Furthermore, the "text and image coding processing" of step S503 includes: converting the text content in the text and image format of the target news content into a preset code. After the RPA robot performs the second regularization processing on the target news content, it codes the text content in the text and image format and converts the text and image information into a preset code to facilitate subsequent operations. Among them, the preset code can be specifically base64 code, etc.
[0070] The news processing method combining RPA and AI proposed in the embodiment of the present application obtains news related to a preset topic from a preset website based on natural language processing NLP, extracts information of preset fields from the news based on natural language processing NLP, obtains target news content, and generates local documents based on the target news content. In this embodiment, the RPA robot automatically obtains news related to a preset topic from a preset website based on natural language processing NLP, and automatically edits the news content to generate a local document without manual participation, which greatly saves the working time of the responsible personnel, with high efficiency, high immediacy and low error rate. The RPA robot can automatically control office software such as Office or WPS, and automatically standardize the obtained information according to user requirements, greatly reducing the error rate of manual sorting.
[0071] Figure 6 is a flowchart of another news processing method combining RPA and AI provided in an embodiment of the present application. Figure 6 As shown in the above Figure 3 Based on the illustrated embodiment, step S304 "filling in the user system according to the local document" may specifically include:
[0072] S601, if the local document does not include a preset code, the user system is filled in according to the preset fields in the local document to generate news to be published.
[0073] In the embodiment of the present application, if the local document does not include the preset code, the local document is plain text information, and the RPA robot fills the user system according to the preset fields based on the local document generated in step S303. The preset fields specifically include but are not limited to any one or more of the following: main title, subtitle, source, date, text content, text, author, and link, etc.
[0074] S602, if the local document includes a preset code, the user system is filled in according to the local document according to the target preset field in the preset field, and the preset code is imported into the text content to generate the text content in a graphic format. The preset fields include the text content and the target preset field.
[0075] In the embodiment of the present application, if the local document includes a preset code, then the local document is graphic information, and the RPA robot fills in the user system according to the target preset fields except the text content in the preset fields according to the local document generated in step S303, and imports the preset code into the text content to generate the text content in a graphic format supporting multiple images. Among them, the preset code can be specifically a converted base64 code, etc.
[0076] The news processing method combining RPA and AI proposed in the embodiment of the present application obtains news related to a preset topic from a preset website based on natural language processing NLP, extracts information of preset fields from the news based on natural language processing NLP, obtains target news content, and generates local documents based on the target news content. In this embodiment, the RPA robot automatically obtains news related to a preset topic from a preset website based on natural language processing NLP, and automatically edits the news content to generate a local document without manual participation, which greatly saves the working time of the responsible personnel, with high efficiency, high immediacy and low error rate. If the local document is plain text information, fill in the user system according to the preset fields. If the local document is graphic information, fill in the user system according to the preset fields except the text, and then import the converted base64 code into the news content to automatically generate graphic information. The RPA robot runs a standard process with high speed.
[0077] Figure 7 This is an overall flow chart of a news processing method combining RPA and AI provided by an embodiment of the present application. Figure 7 As shown, the following steps are included:
[0078] S701, the RPA robot automatically logs in to the user system.
[0079] S702, the RPA robot obtains news related to a preset topic from a preset website based on natural language processing NLP.
[0080] S703: The RPA robot determines whether the target news content contains pictures based on optical character recognition (OCR).
[0081] If the target news content does not contain pictures, steps S704 to S705 are executed; if the target news content contains pictures, steps S706 to S707 are executed.
[0082] S704, opening office software, performing a first regularization process on the target news content, and generating a local document.
[0083] S705, the RPA robot fills in the user system according to the preset fields based on the local document and generates news to be published. Then proceed to S708.
[0084] S706, opening office software, performing second regularization processing and graphic coding processing on the target news content, and generating a local document.
[0085] S707, the RPA robot fills in the user system according to the target preset fields in the preset fields based on the local document, and imports the preset code into the text content to generate the news to be published in the graphic format.
[0086] S708, the RPA robot publishes the news to be released to the "to be released" information column.
[0087] S709: The RPA robot sends a reminder message to notify the responsible person to conduct a review.
[0088] In order to implement the above embodiment, the present application embodiment also proposes a news processing device combining RPA and AI. Figure 8 As shown, the news processing device 800 proposed in the embodiment of the present application may specifically include: an acquisition module 801, an extraction module 802 and a generation module 803, wherein:
[0089] The acquisition module 801 is used to acquire news related to a preset topic from a preset website based on natural language processing (NLP).
[0090] The extraction module 802 is used to extract information of preset fields from the news based on natural language processing (NLP) to obtain target news content.
[0091] The generating module 803 is used to generate a local document according to the target news content.
[0092] Furthermore, in a possible implementation of the embodiment of the present application, the news processing device 800 also includes: a filling module, which is used to fill in the user system according to the local document to generate news to be published; a publishing module, which is used to publish the news to be published to a preset location to be published; and a sending module, which is used to send review reminder information to the user.
[0093] Furthermore, in a possible implementation of the embodiment of the present application, the generation module 803 includes: a judgment unit, which is used to judge whether the target news content contains pictures based on optical character recognition (OCR); a first generation unit, which is used to open the office software if the target news content does not contain pictures, perform a first regularization process on the target news content, and generate a local document; a second generation unit, which is used to open the office software if the target news content contains pictures, perform a second regularization process and graphic coding process on the target news content, and generate a local document.
[0094] Furthermore, in a possible implementation method of an embodiment of the present application, the first regularization processing includes adjustment of any one or more of the following: font size, font size, font color, paragraphs, indents and format; the second regularization processing includes adjustment of any one or more of the following: font size, font size, font color, paragraphs, indents, format, image format and image size.
[0095] Furthermore, in a possible implementation of the embodiment of the present application, the text-graphic coding process includes: converting the text content in the target news content in the text-graphic format into a preset code.
[0096] Furthermore, in a possible implementation of the embodiment of the present application, the preset fields include any one or more of the following: main title, subtitle, source, date, text content, text, author and link.
[0097] Furthermore, in a possible implementation method of the embodiment of the present application, the filling module includes: if the local document does not include the preset code, then the user system is filled in according to the preset field based on the local document to generate news to be published; if the local document includes the preset code, then the user system is filled in according to the target preset field in the preset field based on the local document, and the preset code is imported into the text content to generate the text content in a graphic format, and the preset fields include the text content and the target preset field.
[0098] It should be noted that the above explanation of the embodiment of the news processing method combining RPA and AI is also applicable to the news processing device combining RPA and AI in this embodiment, and will not be repeated here.
[0099] The news processing device combining RPA and AI proposed in the embodiment of the present application obtains news related to a preset topic from a preset website based on natural language processing NLP, extracts information of preset fields from the news based on natural language processing NLP, obtains target news content, and generates a local document based on the target news content. In this embodiment, the RPA robot automatically obtains news related to a preset topic from a preset website based on natural language processing NLP, and automatically edits the news content and generates a local document without manual participation, which greatly saves the working time of the responsible personnel, with high efficiency, high immediacy and low error rate.
[0100] In the various embodiments of the present application, it should be understood that the size of the serial numbers of the above-mentioned processes does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.
[0101] In the embodiments provided in the present application, it should be understood that "B corresponding to A" means that B is associated with A, and B can be determined according to A. However, it should also be understood that determining B according to A does not mean determining B only according to A, and B can also be determined according to A and / or other information.
[0102] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0103] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-accessible memory. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product, which is stored in a memory and includes several requests for a computer device (which can be a personal computer, a server or a network device, etc., specifically a processor in a computer device) to perform some or all of the steps of the above-mentioned methods of various embodiments of the present application.
[0104] Those skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable rewritable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.
[0105] The above is a detailed introduction to a news processing method and device combining RPA and AI disclosed in an embodiment of the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for general technical personnel in this field, according to the idea of the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.
Claims
1. A news processing method combining RPA and AI, characterized in that: include: Obtain news related to a preset topic from a preset website based on natural language processing (NLP); Extracting information of preset fields from the news based on natural language processing (NLP) to obtain target news content, including: after the RPA robot obtains news related to the preset topic, classifying the content in the news according to topic, source, date, content, text, author, and link, and then extracting information from relevant classified title content, while removing information that the user does not care about, to form cleaned data as the target news content; Generating a local document according to the target news content includes: judging whether the target news content contains pictures based on optical character recognition (OCR); if the target news content does not contain pictures, opening office software, performing a first regularization process on the target news content, and generating the local document; if the target news content contains pictures, opening office software, performing a second regularization process and graphic coding process on the target news content, and generating the local document, wherein the RPA robot automatically selects a publishing column, fills in a sub-column, fills in a title, selects a media type, adds an external link, completes the filling of news content, selects a news source, fills in an author, and fills in a source URL according to the local document; Also includes: Fill in the user system according to the local document to generate news to be published, wherein the RPA robot automatically selects the publishing column, fills in the sub-column, fills in the title, selects the media type, adds external links, completes the filling of news content, selects the news source, fills in the author, and fills in the source URL according to the local document; The news to be published is published to a preset location to be published, wherein the RPA robot automatically selects a publishing time, a sorting time, and a browsing permission, and publishes the generated news to be published to a preset location to be published; Send review reminders to users; Wherein, filling in the user system according to the local document includes: If the local document does not include a preset code, the user system is filled in according to the preset fields in the local document to generate the news to be published; If the local document includes the preset code, the user system is filled in according to the local document according to the target preset field in the preset field, and the preset code is imported into the text content to generate the text content in a graphic format. The preset field includes the text content and the target preset field.
2. The news processing method according to claim 1, characterized in that: The first regularization process includes adjusting any one or more of the following: font size, font size, font color, paragraphs, indents and formats; The second regularization process includes adjusting any one or more of the following: font size, font size, font color, paragraph, indentation, format, picture format and picture size.
3. The news processing method according to claim 1, characterized in that: The graphic coding process includes: The text content in the target news content in the graphic format is converted into a preset code.
4. The news processing method according to claim 1, characterized in that: The preset fields include any one or more of the following: Main title, subtitle, source, date, body content, text, author and link.
5. A news processing device combining RPA and AI, characterized in that: include: An acquisition module, used for acquiring news related to a preset topic from a preset website based on natural language processing (NLP); An extraction module is used to extract information of preset fields from the news based on natural language processing (NLP) to obtain target news content, including: after the RPA robot obtains news related to the preset topic, it classifies the content in the news according to the topic, source, date, content, text, author, and link, and then extracts information from the relevant classified title content, while removing information that the user does not care about, to form cleaned data as the target news content; A generating module, used for generating a local document according to the target news content; Also includes: A filling module is used to fill in the user system according to the local document to generate news to be published, wherein the RPA robot automatically selects a publishing column, fills in a sub-column, fills in a title, selects a media type, adds an external link, completes the filling of news content, selects a news source, fills in an author, and fills in a source URL according to the local document; A publishing module, used to publish the news to be published to a preset location to be published, wherein the RPA robot automatically selects a publishing time, a sorting time, and a browsing permission, and publishes the generated news to be published to a preset location to be published; The sending module is used to send review reminder information to users; The filling module includes: A first filling unit is used for filling the user system according to the preset fields according to the local document to generate the news to be published if the local document does not include the preset code; A second filling unit is used for filling the user system according to the local document according to the target preset field in the preset field when the local document includes the preset code, and importing the preset code into the text content to generate the text content in a graphic format, wherein the preset field includes the text content and the target preset field; The generation module comprises: A judging unit, configured to judge whether the target news content contains pictures based on optical character recognition (OCR); A first generating unit, configured to, if the target news content does not contain pictures, open office software, perform a first regularization process on the target news content, and generate the local document; A second generating unit is used for opening office software when the target news content contains pictures, performing second regularization processing and image-text coding processing on the target news content, and generating the local document; Among them, the RPA robot automatically selects the publishing column, fills in the sub-column, fills in the title, selects the media type, adds external links, completes the filling of news content, selects the news source, fills in the author, and fills in the source URL according to the local document.
6. The news processing device according to claim 5, characterized in that: The first regularization process includes adjusting any one or more of the following: font size, font size, font color, paragraphs, indents and formats; The second regularization process includes adjusting any one or more of the following: font size, font size, font color, paragraph, indentation, format, picture format and picture size.
7. The news processing device according to claim 5, characterized in that: The graphic coding process includes: The text content in the image and text format of the target news content is converted into a preset code.
8. The news processing device according to claim 5, characterized in that: The preset fields include any one or more of the following: Main title, subtitle, source, date, body content, text, author and link.
9. A computing device, characterized in that include: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the news processing method combining RPA and AI as described in any one of claims 1-4.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, a news processing method combining RPA and AI as described in any one of claims 1 to 4 is implemented.
