Online business processing method, device and electronic device combining RPA and AI

Abstract

The present application relates to an online business processing method, device and electronic device combining RPA and AI, and relates to the field of RPA and AI technology, and is applied to chatbots. The method includes: obtaining a target business item in an online business; obtaining business data of multiple business elements corresponding to the target business item; issuing a call instruction to the RPA robot, and the call instruction is used to call the RPA robot to process the target business item based on the business data of multiple business elements based on the OCR technology and / or NLP technology. The business data of multiple business elements corresponding to the target business item is obtained through the chatbot, and the RPA robot is called to replace manual labor to process the target business item based on the business data of multiple business elements, which reduces labor costs and improves business processing efficiency. In addition, by calling the RPA robot to process the target business item based on the OCR technology and / or NLP technology, the accuracy of online business processing is improved.

Description

Technical Field

[0001] The present application relates to the field of robotic process automation and artificial intelligence technology, and in particular to an online business processing method, device and electronic 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] At present, many businesses can be handled online. For example, when a company needs to apply for a business license, it can apply through the relevant online website and submit the information required for the business license. The acceptance department will then review the information and issue the business license if the review is passed. However, in this way of handling business online, the acceptance department still uses manual review to review the information, which wastes a lot of manpower and time costs, and cannot guarantee the accuracy of business handling. How to improve the efficiency and accuracy of online business handling and reduce labor costs has become a problem that needs to be solved urgently. Summary of the invention

[0005] The present application provides an online business processing method, device and electronic device combining RPA and AI to solve the technical problems of low business processing efficiency, poor accuracy and high labor cost existing in the online business processing methods in related technologies.

[0006] The first aspect of the present application provides an online business processing method combining RPA and AI, which is applied to a chat robot. The method includes: obtaining a target business item in an online business; obtaining business data of multiple business elements corresponding to the target business item; and issuing a call instruction to an RPA robot, where the call instruction is used to call the RPA robot to process the target business item based on the business data of multiple business elements based on optical character recognition OCR technology and / or natural language processing NLP technology.

[0007] The second aspect of the present application provides an online business processing device combining RPA and AI, which is applied to a chat robot. The device includes: a first acquisition module, used to acquire a target business item in an online business; a second acquisition module, used to acquire business data of multiple business elements corresponding to the target business item; a sending module, used to issue a call instruction to the RPA robot, and the call instruction is used to call the RPA robot to process the target business item based on the business data of multiple business elements based on OCR technology and / or NLP technology.

[0008] The third aspect embodiment of the present application proposes an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the method described in the first aspect embodiment of the present application, or implements the method described in the second aspect embodiment of the present application.

[0009] The fourth aspect embodiment of the present application proposes a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, it implements the method described in the first aspect embodiment of the present application, or implements the method described in the second aspect embodiment of the present application.

[0010] The fifth aspect embodiment of the present application proposes a computer program product, including a computer program, which, when executed by a processor, implements the method described in the first aspect embodiment of the present application, or implements the method described in the second aspect embodiment of the present application.

[0011] The technical solution provided by the embodiments of the present application may have the following beneficial effects:

[0012] The chatbot obtains the business data of multiple business elements corresponding to the target business items, and calls the RPA robot to handle the target business items based on the business data of multiple business elements instead of humans, thereby reducing labor costs and improving business handling efficiency. In addition, the RPA robot is called to handle the target business items based on OCR technology and / or NLP technology, thereby improving the accuracy of online business handling.

[0013] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In the accompanying drawings, unless otherwise specified, the same reference numerals throughout the multiple drawings represent the same or similar parts or elements. These drawings are not necessarily drawn to scale. It should be understood that these drawings only depict some embodiments disclosed in the present application and should not be regarded as limiting the scope of the present application.

[0015] Figure 1 It is a flowchart of an online business processing method combining RPA and AI according to the first embodiment of the present application;

[0016] Figure 2 It is a flowchart of an online business handling method combining RPA and AI according to the second embodiment of the present application;

[0017] Figure 3 This is an example diagram of first prompt information of multiple business elements in a guidance process displayed in a dialog manner according to the second embodiment of the present application;

[0018] Figure 4 This is an example diagram of first prompt information of multiple business elements in a guidance process displayed in a form according to the second embodiment of the present application;

[0019] Figure 5 It is a flowchart of an online business handling method combining RPA and AI according to the third embodiment of the present application;

[0020] Figure 6 4 is a schematic diagram of the structure of an online business processing device combining RPA and AI according to the fourth embodiment of the present application;

[0021] Figure 7 It is a block diagram of an electronic device used to implement the online business processing method combining RPA and AI in an embodiment of the present application. DETAILED DESCRIPTION

[0022] Embodiments of the present application / disclosure are described in detail below, examples of which 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 only used to explain the present application / disclosure, and cannot be understood as limiting the present application / disclosure.

[0023] These and other aspects of the embodiments of the present application / disclosure will be apparent with reference to the following description and drawings. In these descriptions and drawings, some specific implementations of the embodiments of the present application / disclosure are specifically disclosed to represent some ways of implementing the principles of the embodiments of the present application / disclosure, but it should be understood that the scope of the embodiments of the present application / disclosure is not limited thereto. On the contrary, the embodiments of the present application / disclosure include all changes, modifications and equivalents that fall within the spirit and connotation of the appended claims.

[0024] It should be noted that the acquisition, storage and application of user personal information involved in the technical solution of the present disclosure application are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0025] In the description of the present application / disclosure, the term "plurality" refers to two or more than two.

[0026] The present application provides an idea of ​​automatically replacing manual online business processing by combining RPA robots, chatbots and AI. Among them, after the chatbot obtains the target business items in the online business, it can obtain the business data of multiple business elements corresponding to the target business elements, and issue a call instruction to the RPA robot, and the call instruction is used to call the RPA robot to handle the target business items based on the business data of multiple business elements based on OCR technology and / or NLP technology. Thus, the business data of multiple business elements corresponding to the target business items are obtained through the chatbot, and the RPA robot is called to replace manual processing of the target business items based on the business data of multiple business elements, thereby reducing labor costs and improving business processing efficiency. In addition, by calling the RPA robot to handle the target business items based on OCR technology and / or NLP technology, the accuracy of online business processing is improved.

[0027] In order to clearly illustrate the embodiments of the present invention, the technical terms involved in the embodiments of the present invention are first explained.

[0028] In the description of this application, "RPA robot" refers to a software robot that can automatically handle online business by combining AI technology and RPA technology. RPA robots have two characteristics: "connector" and "non-intrusive". By simulating human operation methods, they extract, integrate and connect data from different systems in a non-intrusive way without changing the information system.

[0029] In the description of this application, "chatbot" refers to a software robot that can be interacted with through voice or text. Among them, chatbots can help imitate human interactions, recognize voice and text inputs, understand their meaning and translate them into various languages ​​by combining natural language processing with machine learning and continuously improving AI algorithms, which are suitable for a variety of business processes. Chatbots draw on technologies such as speech recognition, text-to-speech conversion, voice biometrics, NLP (Natural Language Processing) and ML (Machine Learning). Chatbots make it easier for users to get support through automated systems because the complexity of interactions can be greatly simplified.

[0030] In the description of this application, "online business" refers to business conducted online. "Business matters" refers to a specific business in online business, such as "setting up a training institution" and "applying for a business license". "Business elements" refer to the key elements that need to be provided to successfully handle business matters. For example, to set up a training institution, it is necessary to provide key information such as office location, office area, number of employees, etc. These key information are the business elements corresponding to the business matter of "setting up a training institution". "Business data" refers to the data, information and other data provided by the user for each business element. For example, for the business element "office location" corresponding to the business matter of "setting up a training institution", the "No. X, Road X, District X, City X" provided by the user is the business data of the business element "office location".

[0031] In the description of this application, "guidance process" refers to a process pre-built according to multiple business elements corresponding to a business item in order to guide users to handle business matters. Different business items may correspond to different guidance processes, and the guidance process includes the first prompt information of multiple business elements corresponding to the business item, wherein the first prompt information is used to prompt the user to input or upload the business data of the corresponding business element. For example, for the business item of "setting up a training institution", a guidance process can be pre-built according to multiple business elements corresponding to the business item, and the guidance process includes the first prompt information of the "office location" business element, "May I ask your office location?", the first prompt information of the "office area" business element, "your office area?", and the first prompt information of the "number of employees" business element, "your number of employees."

[0032] In addition, you can also set a corresponding priority for the first prompt information of each business element, so that the chat robot displays each first prompt information according to the priority corresponding to each first prompt information. For example, you can set the first prompt information of the "office location" business element to have the highest priority, the first prompt information of the "office area" business element to have the second highest priority, and the first prompt information of the "number of employees" business element to have a lower priority than the above two first prompt information. Then the chat robot can first display the first prompt information of the "office location" business element "May I ask your office location", and after obtaining the business data of the "office location" business element input by the user, display the first prompt information of the "office area" business element "Your office area", and after obtaining the business data of the "office area" business element input by the user, display the first prompt information of the "number of employees" business element "Your number of employees".

[0033] In the description of this application, "auxiliary information" refers to information used to assist users in inputting or uploading business data. For example, the auxiliary information may include sample forms, sample images, etc., which assist users in filling out forms.

[0034] In the description of this application, "OCR (Optical Character Recognition)" specifically refers to the process in which an electronic device examines characters printed on paper, determines their shapes by detecting dark and light patterns, and then translates the shapes into computer text using character recognition methods; that is, for printed characters, an optical method is used to convert the text in a paper document into a black and white dot matrix image file, and recognition software is used to convert the text in the image into a text format for further editing and processing by word processing software.

[0035] In the embodiment of the present application, the RPA robot can recognize the text in documents, bills, forms, and pictures by combining OCR technology. The documents can be various types of documents such as contracts, reports, documents, and documents in various formats such as jpeg, jpg, png, pdf, bmp, tiff, etc. In addition, the RPA robot can handle various complex scenes such as rotation, occlusion, tilt, dense text, complex background, uneven lighting, jitter blur, etc., and the accuracy rate of printed text recognition can reach 99%. In addition, for the recognition of handwriting, the training algorithm model can be customized to achieve the ideal recognition accuracy.

[0036] In addition, based on OCR technology, RPA robots can also automatically detect whether seals are affixed to contracts, bills, cards, forms, and other documents, and return information such as the seal's location, color, and content. In addition, RPA robots can accurately identify seals of various colors, such as red and blue, and seals of various shapes, such as round, elliptical, and diamond, as well as incomplete seals. In addition, if there are multiple seals on a picture, RPA robots can also accurately identify seals.

[0037] In the description of this application, "NLP (Natural Language Processing)" refers to the ability of machines to understand and interpret the way humans write and speak. The goal of NLP is to make computers / machines as intelligent as humans in understanding language. The task of NLP is to understand human language and convert it into machine language.

[0038] In the embodiment of the present application, the RPA robot can understand the content of the text and make decisions by combining NLP technology, and can extract structured data from unstructured text, such as company name, address, amount, date, etc. In addition, users can customize extraction templates to quickly realize customized information extraction capabilities, and support a hybrid mode of models and templates in a text.

[0039] In the description of this application, "business acceptance department" refers to the department that accepts business matters of online business. Different business matters may correspond to the same business acceptance department or different business acceptance departments, and the same business matter may correspond to one or more business acceptance departments. For example, the business acceptance department corresponding to the business matter of "applying for an ID card" is the Public Security Bureau. The business acceptance departments corresponding to the business matter of "opening a restaurant" include the Market Supervision Bureau, the Taxation Bureau, the Public Security Bureau, etc.

[0040] In the description of this application, "business system" refers to the online system used by the business acceptance department to handle business matters, such as the supervision system of the Market Supervision Bureau, the tax system of the Tax Bureau, the public security system of the Public Security Bureau, etc.

[0041] In the description of this application, "specific system" refers to a system with certain special functions, such as a publicity system for credit publicity, an electronic certificate generation system for generating electronic certificates, etc.

[0042] In the description of this application, "online business acceptance system" refers to a business system that accepts online business.

[0043] The following describes, in conjunction with the accompanying drawings, an online business processing method, device, electronic device, and storage medium combining RPA and AI according to the embodiments of the present application / disclosure.

[0044] First, with reference to the accompanying drawings, the online business processing method combining RPA and AI applied to a chat robot in an embodiment of the present application is described.

[0045] Figure 1 1 is a flow chart of an online business processing method combining RPA and AI according to the first embodiment of the present application. Figure 1 As shown, the method may include the following steps:

[0046] Step 101: Obtain target business items in online business.

[0047] It should be noted that the online business processing method combining RPA and AI in the embodiment of the present application can be executed by an online business processing device combining RPA and AI, and the online business processing device combining RPA and AI is referred to as the online business processing device below. Among them, the online business processing device can be implemented by a chat robot, for example, the online business processing device can be a chat robot, or the online business processing device can be configured in the chat robot, and this application does not limit this.

[0048] The chatbot can be configured in an electronic device, which may include but is not limited to a terminal device, a server, etc. This embodiment does not specifically limit the electronic device. The embodiment of the present application takes the chatbot installed in the terminal device as an example for explanation.

[0049] The chatbot in this embodiment can execute the method in real time in a specific time period or throughout the day, and this application does not limit this. The specific time period can be set as needed.

[0050] Alternatively, the chatbot may also be started based on receiving a start instruction. For example, the staff of the online business acceptance system may trigger the start instruction for the chatbot through a conversation. The triggering of the start instruction for the chatbot may be implemented in a variety of ways, for example, the chatbot start instruction may be triggered by voice and / or text, or by triggering a specified control on the human-computer interaction interface, and the embodiments of the present application do not specifically limit this.

[0051] In a possible implementation form, the chatbot can obtain business items in online business by interacting with the user. For example, the chatbot can provide a human-computer interaction interface, and the user can enter "I want to set up a training institution" on the human-computer interaction interface. Correspondingly, the chatbot can obtain the target business item "set up a training institution".

[0052] In another possible implementation form, the online business acceptance system may provide an input box for the target business item, and the user may input the target business item in the input box, so that the chat robot may obtain the target business item from the online business acceptance system.

[0053] It should be noted that the above-mentioned method of obtaining the target business items is only an exemplary description and cannot be understood as a limitation of the present technical solution. In practical applications, technical personnel in this field can set the chatbot to obtain the target business items in any other way, and the present application does not impose any restrictions on this.

[0054] Step 102, obtaining business data of multiple business elements corresponding to the target business item.

[0055] In an embodiment of the present application, in order to guide users to handle various business matters, for each business matter, a guidance process can be pre-built according to multiple business elements corresponding to the business matter, and the guidance process includes the first prompt information of multiple business elements corresponding to the business matter, wherein the first prompt information is used to prompt the user to input or upload business data of the corresponding business element, and then after the chat robot obtains the target business matter in the online business, the first prompt information of multiple business elements in the guidance process corresponding to the target business matter can be displayed in a preset manner. After the chat robot displays the first prompt information of multiple business elements in the guidance process corresponding to the target business matter in a preset manner, the user can reply to each business element according to the first prompt information of each business element, and input or upload business data of the corresponding business element, and then the chat robot can obtain the business data of multiple business elements corresponding to the target business matter according to the detected reply information for each business element.

[0056] The preset mode is a preset display mode of the first prompt information, such as a dialogue mode, a form mode, etc.

[0057] Step 103: Send a call instruction to the RPA robot. The call instruction is used to call the RPA robot to handle the target business items based on the business data of multiple business elements based on optical character recognition OCR technology and / or natural language processing NLP technology.

[0058] The online business processing method combining RPA and AI provided in the embodiment of the present application is that the chat robot obtains the target business item in the online business, obtains the business data of multiple business elements corresponding to the target business item, and issues a call instruction to the RPA robot, and the call instruction is used to call the RPA robot to process the target business item based on the business data of multiple business elements based on the optical character recognition OCR technology and / or natural language processing NLP technology. Thus, the business data of multiple business elements corresponding to the target business item is obtained through the chat robot, and the RPA robot is called to replace manual labor to handle the target business item based on the business data of multiple business elements, which reduces labor costs and improves business processing efficiency. In addition, by calling the RPA robot to handle the target business item based on OCR technology and / or NLP technology, the accuracy of online business processing is improved.

[0059] Combine the following Figure 2 , further illustrating the online business processing method combining RPA and AI provided in the embodiment of the present application. Figure 2 is a flow chart of an online business handling method combining RPA and AI according to the second embodiment of the present application, such as Figure 2 As shown, the method includes:

[0060] Step 201: Obtain target business items in online business.

[0061] Step 202 , according to the guidance process corresponding to the target business item, first prompt information of multiple business elements in the guidance process is displayed in a preset manner, and the first prompt information is used to prompt the user to input or upload business data of the corresponding business element.

[0062] In an embodiment of the present application, the chat robot can display the first prompt information of multiple business elements in the guidance process in a dialogue or form manner.

[0063] For example, for the business item of "establishing a training institution", the guidance process of the business item can be built in advance based on the multiple business elements corresponding to the business item, such as "office location", "office area", "whether it is in person", and "number of employees". The guidance process includes the first prompt information of each business element, and two display methods, dialogue method and form method, can be generated. In the case that the target business item obtained by the chatbot is the "establishment of a training institution" item, it can be Figure 3 The dialogue mode shown shows the first prompt information of multiple business elements in the guidance process corresponding to the target business item. Figure 3 The left side of the figure shows the chatbot and the first prompt information it displays, and the right side shows the user account and the business data for each business element entered by the user. It should be noted that in order to improve the user experience, the guidance process corresponding to the business item can also include the following: Figure 3 Alternatively, if the target business item obtained by the chatbot is "opening a training institution", you can Figure 4 The form shown shows the first prompt information of multiple business elements in the guidance process corresponding to the target business item. The user can fill in the business data of each business element in the form.

[0064] It should be noted that the online business acceptance system can provide a preset selection button to allow the user to flexibly select the display method of the first prompt information of multiple business elements in the guidance process corresponding to the target business item according to needs.

[0065] Step 203 : in response to detecting reply information for each business element, obtaining business data of the corresponding business element according to the reply information.

[0066] In an embodiment of the present application, after the chat robot displays the first prompt information of multiple business elements in the guidance process corresponding to the target business item, the user can reply to each business element according to the first prompt information of each business element, and input or upload the business data of the corresponding business element. Then, the chat robot can respond to the detection of reply information for each business element and obtain the business data of multiple business elements corresponding to the target business item according to the reply information for each business element.

[0067] The chatbot prompts the user to input or upload the business data of the corresponding business elements according to the first prompt information of multiple business elements in the guidance process corresponding to the target business item, so that the user can quickly and accurately understand the data required to handle the target business item according to the first prompt information of each business element, and input or upload the business data, thereby improving the efficiency and accuracy of business handling. In addition, by displaying the first prompt information of multiple business elements in the guidance process in a dialogue manner and obtaining the business data of each business element input or uploaded by the user, it is equivalent to combining the advantages of online handling that can be handled anywhere with the advantages of offline handling with interactive guidance, so that the user can provide the business data required to handle the target business item to the online business acceptance system through guided interaction.

[0068] It should be noted that, in a possible implementation form, for the first prompt information of any one of the multiple business elements displayed by the chatbot, there may be a situation where the user does not know how to enter or upload the business data of the business element, or does not know where to upload the business data of the business element, etc. At this time, the user may enter "I don't know how to fill it out" or "I don't know where to upload" in the human-computer interaction interface provided by the chatbot in voice or text form for consultation. Then, in the embodiment of the present application, in response to detecting the reply information for each business element, the chatbot can also understand the user's intention based on the reply information, and when it is determined that the user's intention is not to consult, the business data of the corresponding business element is obtained based on the reply information.

[0069] Among them, chatbots can use speech recognition, NLP technology and other means to understand user intentions based on user response information.

[0070] In addition, in the embodiment of the present application, for each business element corresponding to each business matter, candidate auxiliary information used to assist users in inputting or uploading business data can be pre-configured, such as precautions, reference examples (sample tables, sample pictures, etc.), instructions, etc. After the chat robot displays the first prompt information of any one of the multiple business elements, when the user replies in the human-computer interaction interface provided by the chat robot in voice or text form "I don't know how to fill it in" or "I don't know where to upload", etc., an auxiliary request for the business element can be triggered. In the embodiment of the present application, the business element is referred to as the first target element, and the first target element can be any one of the multiple business elements. The chat robot can understand the user's intention based on the user's reply information. When it is determined that the user's intention is to consult, it can be determined that the user has triggered an auxiliary request for the first target element, and then in response to obtaining the auxiliary request for the first target element, the target auxiliary information corresponding to the auxiliary request can be obtained from the candidate auxiliary information corresponding to the first target element, and the target auxiliary information can be displayed. Among them, the method of displaying the target auxiliary information is the same as the method of displaying the first prompt information of each business element.

[0071] For example, it is assumed that the multiple business elements corresponding to the target business item include the "instruction book" business element, and the candidate auxiliary information corresponding to the pre-set business element includes the sample form of the instruction book, sample pictures, and text instructions on how to upload the instruction book. After the chat robot displays the first prompt information "Please upload the instruction book" of the business element "instruction book" in the form of a dialogue through the human-computer interaction interface, when the user does not know how to fill in the instruction book, he can enter "I don't know how to fill in" in the human-computer interaction interface to trigger an auxiliary request for the "instruction book" business element. Correspondingly, the chat robot can use speech recognition, NLP technology and other means to understand the user's intention based on the information entered by the user. When it is determined that the user's intention is "consulting how to fill in the instruction book", it can be determined that the user has triggered an auxiliary request for the "instruction book" business element. Then, in response to obtaining the auxiliary request for the "instruction book" business element, the sample form and sample pictures of the instruction book can be obtained from the candidate auxiliary information corresponding to the "instruction book" business element, and the sample form and sample pictures of the instruction book can be displayed. The user can then fill in the instruction book according to the sample form and sample pictures in the instruction book, and send the filled-in instruction book to the chat robot through the human-computer interaction interface.

[0072] By pre-configuring candidate auxiliary information for each business element corresponding to each business item, and combining the guidance process of each business item, interacting with the user in a preset manner, the business item handling process and the business item handling guidance are combined, so that users can consult at any time before or during the handling of business items, and can obtain instant guidance from the chatbot.

[0073] Further, in response to obtaining the business data of the second target element among the multiple business elements, the chatbot can review the business data of the second target element based on the OCR technology and / or NLP technology according to the review rules corresponding to the target business item to obtain the review result of the business data of the second target element, and when the review result of the business data of the second target business element is not passed, display the second prompt information to prompt the user to re-enter or upload the business data of the second target business element. When the review result of the business data of the second target business element is passed, the chatbot can continue to execute subsequent steps.

[0074] Among them, the second target element can be any one of the multiple business elements.

[0075] Audit rules are pre-set rules for auditing whether business data meets the requirements. There may be different audit rules for business data corresponding to different business matters.

[0076] For example, assuming that the multiple business elements corresponding to the target business item include the "ID card picture" and "declaration form" business elements, the review rules corresponding to the target business item include: the ID card has not expired and is the person's ID card, the declaration form includes the expert's signature and the company's seal, and the seal information is consistent with the company entity.

[0077] After obtaining the business data of the "ID card" business element corresponding to the target business item, that is, the ID card image, the chat robot can identify the ID card image based on OCR technology to obtain the validity period, name and ID card number in the ID card image, and determine whether the current time is within the validity period, and determine whether the ID card image is the user's own ID card image based on the name and ID card number. If so, the review is determined to be passed, otherwise, the review is failed.

[0078] After obtaining the business data of the "declaration form" business element corresponding to the target business item, that is, the scanned copy of the declaration form, the chatbot can identify the content in the scanned copy of the declaration form based on OCR technology, and parse the recognition result based on NLP technology, and then judge whether there is an expert's signature and the company's seal in the declaration form according to the parsing result, and judge whether the seal information is consistent with the corporate entity. If so, the review is determined to be passed, otherwise, the review is failed.

[0079] Step 204: Send a call instruction to the RPA robot. The call instruction is used to call the RPA robot to handle the target business items based on the business data of multiple business elements based on the optical character recognition OCR technology and / or natural language processing NLP technology.

[0080] In summary, the online business processing method combining RPA and AI provided in the embodiment of the present application prompts the user to input or upload the business data of the corresponding business element according to the first prompt information of multiple business elements in the guide process corresponding to the target business item through the chat robot, so that the user can quickly and accurately understand the data required to handle the target business item according to the first prompt information of each business element, and input or upload the business data, thereby improving the efficiency and accuracy of business processing, and by using the RPA robot to replace manual processing based on OCR technology and / or NLP technology to handle the target business items according to the business data, the labor cost is greatly reduced, and the business processing efficiency is further improved. In addition, by reviewing the business data of each business element obtained in real time during the interaction between the chat robot and the user, and prompting the user to re-enter or upload the business data in a timely manner when the review result is not passed, the situation of extending the online business processing cycle due to errors in the business data uploaded by the user is avoided, and the business processing efficiency is further improved.

[0081] Combine the following Figure 5 , an online business processing method combining RPA and AI applied to an RPA robot in an embodiment of the present application is described.

[0082] Figure 5 is a flow chart of an online business handling method combining RPA and AI according to the third embodiment of the present application, such as Figure 5 As shown, the method may also include:

[0083] Step 501: Obtain target business items in online business.

[0084] Step 502: Acquire business data of multiple business elements corresponding to the target business item.

[0085] The specific implementation process and principle of steps 501-502 may refer to the description of the above embodiment and will not be repeated here.

[0086] Step 503: Send a call instruction to the RPA robot. The call instruction is used to call the RPA robot to review the business data set generated by integrating the business data of multiple business elements according to the review rules corresponding to the target business item, and handle the target business item according to the review result corresponding to the obtained business data set.

[0087] Among them, the audit rules are pre-set rules for auditing whether business data meets the requirements. There may be different audit rules for business data corresponding to different business items.

[0088] In an embodiment of the present application, after the RPA robot receives the call instruction issued by the chat robot, it can perform an overall review of the business data set in accordance with the review rules corresponding to the target business item based on OCR technology and / or NLP technology, such as reviewing whether there are conflicts between the business data of each business element, whether the information is consistent, etc., and obtain the review results corresponding to the business data set.

[0089] For example, suppose that the target business item includes multiple business elements such as "ID card picture" and "driver's license" business elements, and the audit rules corresponding to the target business item include: the ID card and the driver's license belong to the same person and are not expired. After obtaining the business data of the "ID card" business element corresponding to the target business item, i.e., the ID card picture, and the business data of the "driver's license" business element, i.e., the driver's license picture, the RPA robot can identify the ID card picture and the driver's license picture based on OCR technology to obtain the validity period and name in the ID card picture, and the validity period and name in the driver's license, and then determine whether the current time is within the validity period of the ID card and the driver's license, and determine whether the name in the ID card picture is consistent with the name in the driver's license picture. If so, the audit is passed, otherwise, the audit is not passed.

[0090] In an embodiment of the present application, for certain business matters, the online business acceptance system may only need to approve the business data of various business elements corresponding to the business matters. For these business matters, after the RPA robot reviews the business data set, it can handle the target business matters based on the review results obtained.

[0091] In an embodiment of the present application, for certain business matters, after the online business acceptance system has reviewed the business data of each business element corresponding to the business matter, it may be necessary to further review it by one or more other business acceptance departments. When the target business matter is one of these business matters, the RPA robot can enter the business data set into the business system of each business acceptance department when the review result is passed, so that each business acceptance department can further handle the target business matter according to the business data set in the corresponding business system.

[0092] That is, the target business item corresponds to at least one business acceptance department; the calling instruction is also used to: call the RPA robot to enter the business data set into the business system of each business acceptance department when the review result corresponding to the business data set is passed, so that each business acceptance department can further handle the target business item according to the business data set in the corresponding business system.

[0093] As a result, the RPA robot can automatically enter business data sets into the business systems of various business acceptance departments, reducing labor costs.

[0094] In an embodiment of the present application, when the RPA robot determines that the confidence level of the audit result corresponding to the business data set is low, the audit result can be confirmed manually to improve the accuracy of the audit result, thereby improving the accuracy of business handling. That is, the call instruction is also used to: call the RPA robot to display the audit result corresponding to the business data set through the human-computer interaction interface, and determine the confirmation instruction of obtaining the audit result corresponding to the business data set.

[0095] In an embodiment of the present application, the RPA robot can provide a human-computer interaction interface and display the audit results through the human-computer interaction interface. When the audit results are manually determined to be correct, the confirmation instruction of the audit results can be triggered by clicking a confirmation button, etc., and then the RPA robot determines that the confirmation instruction of the audit results has been obtained, and can continue to perform subsequent processing on the target business items according to the audit results. When the audit results are manually confirmed to be incorrect, the audit results can be modified and the correct audit results can be returned to the RPA robot, and then the RPA robot can continue to perform subsequent processing on the target business items according to the correct audit results.

[0096] Step 504, obtain the processing status of the target business item; wherein the processing status is obtained by the RPA robot from the business system of each business acceptance department and sent to the chat robot.

[0097] Step 505, display the processing status.

[0098] In an embodiment of the present application, after the RPA robot enters the business data set into the business system of each business acceptance department, each business acceptance department can review the business data set according to its own business requirements, and handle the business matters according to the review results, and enter the handling status into the corresponding business system. The RPA robot can track the handling status in the business system of each business acceptance department, obtain the handling status of the target business matters from each business system, and send the handling status to the chat robot, and then the chat robot can display the handling status. Thus, it is realized that the handling status of the target business matters can be automatically tracked by the RPA robot, and the handling progress of the business matters can be provided to the user in a timely manner through the chat robot.

[0099] In addition, when a business acceptance department has not handled business items according to the business data set for a long time, the RPA robot can also automatically send reminder information to the business acceptance department to urge the handling process of the business items to improve the handling efficiency of the business. That is, the call instruction is also used to call the RPA robot to send reminder information to the business acceptance department.

[0100] In an embodiment of the present application, for certain business matters, it may be necessary to enter the processing results into a specific system after the processing is completed. For example, for certain electronic certificate processing matters, after the business data required for the processing of the electronic certificate is reviewed, the business data and the results of the review need to be entered into the electronic certificate generation system to generate the electronic certificate through the electronic certificate generation system. Correspondingly, the call instruction is also used to: call the RPA robot when the processing status is completed, obtain the processing results of the target business matter, and enter the processing results into a specific system. In this way, the processing results are automatically entered into a specific system through the RPA robot.

[0101] In order to implement the above embodiments, the present application also proposes an online business processing device that combines RPA and AI. Figure 6 It is a structural diagram of an online business processing device combining RPA and AI according to the fourth embodiment of the present application.

[0102] like Figure 6 As shown, the online business processing device 600 combining RPA and AI is applied to a chat robot, including: a first acquisition module 601, a first review module 602 and a processing module 603.

[0103] The first acquisition module 601 is used to acquire target business items in online business;

[0104] The second acquisition module 602 is used to acquire business data of multiple business elements corresponding to the target business item;

[0105] The sending module 603 is used to send a call instruction to the RPA robot, and the call instruction is used to call the RPA robot to handle the target business items based on the business data of multiple business elements based on OCR technology and / or NLP technology.

[0106] It should be noted that the online business processing device 600 combining RPA and AI in the embodiment of the present application can execute the online business processing method combining RPA and AI provided in the above embodiment. Among them, the online business processing device 600 combining RPA and AI can be implemented by a chat robot. For example, the online business processing device 600 combining RPA and AI can be a chat robot, or the online business processing device can be configured in the chat robot, and the present application does not limit this.

[0107] The chatbot can be configured in an electronic device, which may include but is not limited to a terminal device, a server, etc. This embodiment does not specifically limit the electronic device. The embodiment of the present application takes the chatbot installed in the terminal device as an example for explanation.

[0108] In one embodiment of the present application, the second acquisition module 602 is used to:

[0109] According to the guidance process corresponding to the target business item, first prompt information of multiple business elements in the guidance process is displayed in a preset manner, and the first prompt information is used to prompt the user to input or upload business data of the corresponding business element;

[0110] In response to detecting reply information for each business element, business data of the corresponding business element is acquired according to the reply information.

[0111] In one embodiment of the present application, the second acquisition module 602 is used to:

[0112] According to the guidance process corresponding to the target business item, the first prompt information of multiple business elements in the guidance process is displayed in a dialogue or form manner.

[0113] In one embodiment of the present application, the apparatus 600 further includes:

[0114] A third acquisition module is used for, in response to obtaining an assistance request for a first target element among the multiple business elements, acquiring target assistance information corresponding to the assistance request from candidate assistance information corresponding to the first target element;

[0115] The first display module is used to display target auxiliary information.

[0116] In one embodiment of the present application, the apparatus 600 further includes:

[0117] An audit module, configured to, in response to obtaining the business data of a second target element among the multiple business elements, audit the business data of the second target element based on the OCR technology and / or the NLP technology and in accordance with the audit rules corresponding to the target business item, so as to obtain an audit result of the business data of the second target element;

[0118] The second display module is used to display second prompt information when the audit result of the business data of the second target element is failure, so as to prompt the user to re-enter or upload the business data of the second target business element.

[0119] In one embodiment of the present application, the call instruction is specifically used to:

[0120] Call the RPA robot to review the business data set generated by integrating the business data of multiple business elements according to the review rules corresponding to the target business item, and handle the target business item based on the review results corresponding to the obtained business data set.

[0121] In one embodiment of the present application, the target business item corresponds to at least one business acceptance department; the calling instruction is also used to:

[0122] When the RPA robot is called and the audit result corresponding to the business data set is passed, the business data set is entered into the business system of each business acceptance department, so that each business acceptance department can further handle the target business items according to the business data set in the corresponding business system.

[0123] In one embodiment of the present application, the apparatus 600 further includes:

[0124] The fourth acquisition module is used to obtain the processing status of the target business item; the processing status is obtained by the RPA robot from the business system of each business acceptance department and sent to the chat robot;

[0125] The third display module is used to display the processing status.

[0126] In one embodiment of the present application, the call instruction is also used to:

[0127] When the RPA robot is in the completed status, it will obtain the processing results of the target business items and enter the processing results into a specific system.

[0128] In one embodiment of the present application, the call instruction is also used to:

[0129] Call the RPA robot to display the audit results corresponding to the business data set through the human-computer interaction interface, and confirm the confirmation instructions for obtaining the audit results corresponding to the business data set.

[0130] It should be noted that the aforementioned explanation of the embodiment of the online business processing method combining RPA and AI is also applicable to the online business processing device combining RPA and AI in this embodiment. The details not disclosed in the embodiment of the online business processing device combining RPA and AI in this application will not be repeated here.

[0131] In summary, the online business processing device combining RPA and AI in the embodiment of the present application obtains the target business item in the online business, obtains the business data of multiple business elements corresponding to the target business item, and issues a call instruction to the RPA robot, and the call instruction is used to call the RPA robot to handle the target business item based on the business data of multiple business elements based on the optical character recognition OCR technology and / or natural language processing NLP technology. Thus, the business data of multiple business elements corresponding to the target business item is obtained through the chat robot, and the RPA robot is called to replace manual labor to handle the target business item based on the business data of multiple business elements, which reduces labor costs and improves business processing efficiency. In addition, by calling the RPA robot to handle the target business item based on OCR technology and / or NLP technology, the accuracy of online business processing is improved.

[0132] In order to implement the above embodiments, the embodiments of the present application also propose an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, an online business processing method combining RPA and AI as described in any of the above method embodiments is implemented.

[0133] In order to implement the above embodiments, the embodiments of the present application also propose a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the online business processing method combining RPA and AI as described in any of the above method embodiments is implemented.

[0134] In order to implement the above embodiments, the embodiments of the present application also propose a computer program product. When the instruction processor in the computer program product is executed, the online business processing method combining RPA and AI as described in any of the above method embodiments is implemented.

[0135] Figure 7 A block diagram of an exemplary electronic device suitable for implementing the embodiments of the present application is shown. Figure 7 The electronic device 12 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0136] like Figure 7 As shown, the electronic device 12 is in the form of a general purpose computing device. The components of the electronic device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that connects various system components (including the memory 28 and the processing unit 16).

[0137] The bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor or a local bus using any of a variety of bus structures. For example, these architectures include but are not limited to Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus and Peripheral Component Interconnection (PCI) bus.

[0138] The electronic device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the electronic device 12, including volatile and non-volatile media, removable and non-removable media.

[0139] The memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. The electronic device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 may be used to read and write non-removable, non-volatile magnetic media ( Figure 7 not shown, usually called a "hard drive"). Although Figure 7 Not shown, a disk drive for reading and writing a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing a removable non-volatile optical disk (e.g., a compact disc read only memory (CD-ROM), a digital versatile disc read only memory (DVD-ROM), or other optical media) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data medium interfaces. The memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present application.

[0140] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in the memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. The program modules 42 generally perform the functions and / or methods of the embodiments described herein.

[0141] The electronic device 12 may also communicate with one or more external devices 14 (e.g., keyboards, pointing devices, displays 24, etc.), one or more devices that enable a user to interact with the electronic device 12, and / or any device that enables the electronic device 12 to communicate with one or more other computing devices (e.g., network cards, modems, etc.). Such communication may be performed through an input / output (I / O) interface 22. Furthermore, the electronic device 12 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through a network adapter 20. Figure 7 As shown, the network adapter 20 communicates with other modules of the electronic device 12 via the bus 18. It should be understood that although Figure 7 Not shown, other hardware and / or software modules may be used in conjunction with the electronic device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0142] The processing unit 16 executes various functional applications and data processing by running the programs stored in the memory 28, such as implementing the methods mentioned in the above embodiments.

[0143] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0144] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0145] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0146] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute the instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0147] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0148] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0149] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0150] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present application. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. An online business processing method combining RPA and AI, characterized in that: Applied to a chatbot, the method comprises: Get target business items in online business; According to the guidance process corresponding to the target business item, first prompt information of multiple business elements in the guidance process is displayed in a preset manner, where the first prompt information is used to prompt the user to input or upload business data of the corresponding business element; In response to detecting reply information for each of the business elements, acquiring business data of the corresponding business element according to the reply information; A calling instruction is issued to the RPA robot, wherein the calling instruction is used to call the RPA robot to process the target business item based on the business data of the plurality of business elements based on the optical character recognition (OCR) technology and / or the natural language processing (NLP) technology; The method further comprises: Understanding the user's intention according to the user's reply information, and when determining that the user's intention is to consult, determining that the user triggers an auxiliary request for the first target element; In response to obtaining an assistance request for a first target element among the plurality of business elements, obtaining target assistance information corresponding to the assistance request from candidate assistance information corresponding to the first target element; The target auxiliary information is displayed.

2. The method according to claim 1, characterized in that The first prompt information of multiple business elements in the guidance process is displayed in a preset manner according to the guidance process corresponding to the target business item, including: According to the guidance process corresponding to the target business item, first prompt information of multiple business elements in the guidance process is displayed in a dialogue manner or a form manner.

3. The method according to claim 1, characterized in that The method further comprises: In response to obtaining the business data of a second target element among the plurality of business elements, based on the OCR technology and / or the NLP technology, and in accordance with the audit rules corresponding to the target business item, the business data of the second target element is audited to obtain an audit result of the business data of the second target element; When the audit result of the business data of the second target business element is failure, second prompt information is displayed to prompt the user to re-enter or upload the business data of the second target business element.

4. The method according to any one of claims 1 to 3, characterized in that: The calling instruction is specifically used for: The RPA robot is called to review the business data set generated by integrating the business data of the multiple business elements according to the review rules corresponding to the target business item, and the target business item is handled according to the review result corresponding to the business data set obtained.

5. The method according to claim 4, characterized in that The target business item corresponds to at least one business acceptance department; the calling instruction is also used to: When the RPA robot is called and the audit result corresponding to the business data set is passed, the business data set is entered into the business system of each business acceptance department, so that each business acceptance department can further handle the target business matters according to the business data set in the corresponding business system.

6. The method according to claim 5, characterized in that The method further comprises: Obtaining the processing status of the target business item; wherein the processing status is obtained by the RPA robot from the business system of each business acceptance department and sent to the chat robot; Display the processing status.

7. The method according to claim 6, characterized in that The call instruction is also used to: The RPA robot is called to obtain the processing result of the target business item when the processing status is completed, and the processing result is entered into a specific system.

8. The method according to claim 4, characterized in that The call instruction is also used to: The RPA robot is called to display the audit result corresponding to the business data set through a human-computer interaction interface, and a confirmation instruction is determined to obtain the audit result corresponding to the business data set.

9. An online business processing device combining RPA and AI, characterized in that: Applied to a chat robot, the device comprises: The first acquisition module is used to acquire target business items in online business; A second acquisition module is used to display, according to the guidance process corresponding to the target business item, first prompt information of multiple business elements in the guidance process in a preset manner, wherein the first prompt information is used to prompt the user to input or upload business data of the corresponding business element; in response to detecting reply information for each of the business elements, obtain the business data of the corresponding business element according to the reply information; A sending module, used to send a call instruction to the RPA robot, wherein the call instruction is used to call the RPA robot to handle the target business item based on the business data of the plurality of business elements based on the OCR technology and / or the NLP technology; The device is also used for: Understand the user's intention based on the user's reply information, and when it is determined that the user's intention is to consult, determine that the user triggers an auxiliary request for the first target element; in response to obtaining the auxiliary request for the first target element among multiple business elements, obtain target auxiliary information corresponding to the auxiliary request from candidate auxiliary information corresponding to the first target element; and display the target auxiliary information.

10. The device according to claim 9, characterized in that The second acquisition module is used to: According to the guidance process corresponding to the target business item, first prompt information of multiple business elements in the guidance process is displayed in a dialogue manner or a form manner.

11. An electronic device, characterized in that: The method comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method according to any one of claims 1 to 8 is implemented.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images