Information processing method and related equipment

Abstract

The invention provides an information processing method and related equipment, the method is applied to a robot process automation (RPA) system, and the method comprises the following steps: the RPA system obtains to-be-processed information, inputs the to-be-processed information into a natural language processing (NLP) model, and obtains feature information of the to-be-processed information; and then, the RPA system sends target information to a think tank display system according to the feature information and a preset condition, so that the think tank display system displays the target information to the user, and the target information is generated based on the to-be-processed information. According to the method, on one hand, a digital RPA system is adopted, efficient work is achieved, manual operation errors are avoided, and the information obtaining efficiency is improved; on the other hand, feature extraction is carried out on the text information through the NLP model, user requirements can be more accurately matched, and the information obtaining accuracy and the user experience feeling are improved. In addition, the RPA system adopted by the method can quickly complete deployment and is simple and convenient to implement under the condition of not interfering and not changing the existing enterprise system.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular, to an information processing method, a robotic process automation system, a computer device, a computer-readable storage medium, and a computer program product. Background Art

[0002] With the rapid development of the information age, the demand of enterprises or individuals for timely, accurate, and comprehensive information acquisition is increasing day by day. For example, enterprises need to quickly retrieve relevant information with high timeliness for industry analysis, scholars need to retrieve the most cutting-edge scientific research materials and related background technologies for in-depth academic research, and so on.

[0003] Traditional information collection methods mainly rely on manual search and collation. This method is not only inefficient but also difficult to ensure the comprehensiveness and accuracy of information. Therefore, how to efficiently obtain the latest and most valuable information has become an urgent problem to be solved. Summary of the Invention

[0004] This application provides an information processing method, which can efficiently obtain the latest and most user-needed information and improve the efficiency of information acquisition.

[0005] In a first aspect, this application provides an information processing method, which is applied to a robotic process automation (RPA) system. The method includes:

[0006] Obtain information to be processed, where the information to be processed is text information obtained based on at least one information source;

[0007] Input the information to be processed into a natural language processing (NLP) model to obtain feature information of the information to be processed;

[0008] Send target information to a think tank display system according to the feature information and preset conditions, so that the think tank display system displays the target information to the user, and the target information is generated based on the information to be processed.

[0009] In some possible implementation manners, the sending target information to the think tank display system according to the feature information and preset keywords includes:

[0010] Determine target information according to the relevance between the feature information and the preset conditions;

[0011] Send the target information to the think tank display system.

[0012] In some possible implementations, determining the target information according to the relevance between the feature information and the preset condition includes:

[0013] Determining candidate target information according to the relevance between the feature information and the preset condition;

[0014] When the difference between the first relevance between the feature information of the first candidate target information and the preset condition and the second relevance between the feature information of the second target information and the preset condition is less than the threshold, determining one of the first candidate target information and the second candidate target information as the target information to be sent.

[0015] In some possible implementations, the method further includes:

[0016] Receiving feedback information sent by the user through the think tank display system, where the feedback information indicates that the feature information of the target information does not match the preset condition;

[0017] Sending the feedback information to the NLP model to update the NLP model.

[0018] In some possible implementations, obtaining the information to be processed includes:

[0019] Periodically obtaining the information to be processed according to the first preset time information;

[0020] Alternatively, in response to a request for obtaining information triggered by the user, obtaining the information to be processed.

[0021] In some possible implementations, receiving the feedback information sent by the user through the think tank display system includes:

[0022] Periodically receiving the feedback information sent by the user through the think tank display system according to the second preset time information;

[0023] Alternatively, in response to a request for feedback information triggered by the user, receiving the feedback information sent by the user through the think tank display system.

[0024] In some possible implementations, the feature information includes at least one of the theme, author, keyword, release time, or information source of the text information.

[0025] In a second aspect, the present application provides an RPA system. The system includes:

[0026] An acquisition module, configured to obtain information to be processed, where the information to be processed is text information obtained based on at least one information source;

[0027] The first processing module is configured to input the information to be processed into a natural language processing (NLP) model to obtain the feature information of the information to be processed;

[0028] The second processing module sends target information to the think tank display system according to the feature information and preset conditions, so that the think tank display system displays the target information to the user, and the target information is generated based on the information to be processed.

[0029] This system can also be used to execute the information processing method described in any implementation manner of the first aspect.

[0030] In a third aspect, the present application provides a computer device, which includes a processor and a memory.

[0031] The processor is configured to execute the instructions stored in the memory, so that the computer device executes the information processing method described in the first aspect or any implementation manner of the first aspect.

[0032] In a fourth aspect, the present application provides a computer-readable storage medium. The computer-readable storage medium includes instructions, which, when running on a computer device, cause the computer device to execute the information processing method described in the first aspect or any implementation manner of the first aspect.

[0033] In a fifth aspect, the present application provides a computer program product containing instructions, which, when running on a computer device, cause the server to execute the information processing method described in the first aspect or any implementation manner of the first aspect.

[0034] Based on the implementation manners provided in the above aspects, the present application can be further combined to provide more implementation manners.

[0035] As can be seen from the above technical solutions, the embodiments of the present application have the following advantages:

[0036] The embodiments of the present application provide an information processing method. On the one hand, the method can adopt an RPA system to introduce digital labor, achieve efficient work all day long and avoid human operation errors, and improve the efficiency of information acquisition; on the other hand, by using an NLP model to extract features from text information, it can more accurately match the information required by users, improve the accuracy of information acquisition and the user experience. In addition, the RPA system adopted by the method can be quickly deployed without interfering with or changing the existing enterprise system, and is easy to implement. Description of the Drawings

[0037] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the accompanying drawings required for the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0038] Figure 1 It is a flowchart of an information processing method provided by an embodiment of the present application;

[0039] Figure 2 It is a schematic structural diagram of an RPA system provided by an embodiment of the present application. Detailed implementation manners

[0040] The following will describe the solutions in the embodiments provided by the present application in conjunction with the accompanying drawings in the present application.

[0041] The terms used in the following embodiments are only for the purpose of describing specific embodiments and are not intended to limit the present application. The terms "first" and "second" in the embodiments of the present application are only used for descriptive purposes and cannot be understood as indicating or implying relative importance, the order of operation time, or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features.

[0042] To facilitate the understanding of the technical solutions of the present application, some technical terms related to the present application will be introduced first.

[0043] Robotic Process Automation (RPA) is a business process automation technology based on software robots and artificial intelligence (AI). Without modifying the original system, it can simulate manual operations through simple configuration to help enterprises or employees complete repetitive and monotonous process-based work.

[0044] Natural Language Processing (NLP) belongs to the interdisciplinary field of artificial intelligence and linguistics. Its core goal is to achieve the intelligence of human-computer interaction through machine learning technology, improve the interaction method between users and computers, and enable computers to more effectively process and analyze a large amount of natural language data. The NLP model is trained based on large-scale data, for example, a language model (such as BERT, GPT series) is trained based on a neural network (such as the Transformer architecture), so as to support semantic parsing, reasoning, and generation in the form of text and speech.

[0045] With the rapid development of the information age, the demand of enterprises or individuals for timely, accurate and comprehensive information acquisition is increasing day by day. The traditional information collection methods mainly rely on manual search and collation, which are not only inefficient, but also difficult to ensure the comprehensiveness and accuracy of information. For example, think tanks need to fill in the articles published on the official accounts every day. Collecting manually not only takes time, but also may not be able to track the updates of articles in a timely manner and import them into the local think tank in time. Another example is that when collecting content on professional websites (such as academic websites), operators in non-related technical fields may also collect articles with low relevance to the target content, reducing the accuracy of information.

[0046] In view of this, the embodiments of the present application provide an information processing method, which is applied to a robotic process automation (RPA) system. Specifically, the method includes: the RPA system obtains the information to be processed, and inputs the information to be processed into a natural language processing (NLP) model to obtain the feature information of the information to be processed. Wherein, the information to be processed is text information obtained based on at least one information source. Then, the RPA system sends the target information to the think tank display system according to the feature information and preset conditions, so that the think tank display system displays the target information to the user, and the target information is generated based on the information to be processed.

[0047] On the one hand, this method can adopt the RPA system to introduce digital labor, achieve efficient work all day long and avoid human operation errors, improving the efficiency of information acquisition; on the other hand, by using the NLP model to extract features from text information, it can more accurately match the information required by users, improving the accuracy of information acquisition and the user experience. In addition, the RPA system adopted by this method can be quickly deployed without interfering with or changing the existing enterprise system, achieving simplicity.

[0048] Next, the information processing method provided by the embodiments of the present application will be introduced in conjunction with the accompanying drawings.

[0049] See Figure 1 The flowchart of the information processing method shown, which is applied to the RPA system. Among them, RPA is a business process automation technology based on software robots and artificial intelligence. Without changing the original system, it can simulate manual operations through simple configuration to help enterprises or employees complete repetitive and monotonous process work. The method specifically includes the following steps:

[0050] S102: The RPA system obtains the information to be processed.

[0051] The information to be processed refers to the text information obtained based on at least one information source. Among them, the information to be processed can be the directly obtained text information (such as official account articles, officially released news, academic papers, etc.), or the text information converted from videos, audios or images through technologies such as Automatic Speech Recognition (ASR) or Optical Character Recognition (OCR).

[0052] In some possible implementation manners, the RPA system can periodically obtain the information to be processed according to the first preset time information. The RPA system can automatically obtain the information to be processed according to the preset time period, such as every 10 minutes, 1 hour, 1 day, or a fixed time period every day, etc. Of course, the period for the RPA system to obtain the information to be processed can also be variable. For example, when tracking a hot event, the information to be processed can be obtained at a smaller time interval during the important node interval of the event, and at a larger time interval after the event is basically over, so that valuable information can be obtained more efficiently.

[0053] In some possible implementation manners, the RPA system can also obtain the information to be processed in response to the information acquisition request triggered by the user. For example, when the user temporarily needs to obtain the information to be processed, the RPA system can also obtain the information in response to the request triggered by the user, so as to increase the flexibility of the system.

[0054] In some possible implementation manners, the RPA system can configure multiple sub-workflows for the acquisition operation for different information sources and synchronously display the acquisition process to relevant technical personnel. In this way, concurrent operations can be realized to improve the acquisition efficiency, and at the same time, it is convenient for relevant technical personnel to manage and maintain. Among them, the workflow executed by the RPA system can execute the information acquisition task by operating the browser.

[0055] S104: The RPA system inputs the information to be processed into the NLP model to obtain the feature information of the information to be processed.

[0056] NLP belongs to the interdisciplinary field of artificial intelligence and linguistics. Its core goal is to realize the intelligence of human-computer interaction through machine learning technology, improve the interaction mode between users and computers, and enable computers to more effectively process and analyze a large amount of natural language data. The NLP model is trained based on large-scale data, such as training language models (such as BERT, GPT series) based on neural networks (such as the Transformer architecture), so as to support semantic parsing, reasoning and generation in text and speech forms.

[0057] The NLP model can be deployed on any server or terminal with the required computing power, and information interaction with the RPA system can be achieved through an interface. The RPA system can input the information to be processed collected into the NLP model, and through the NLP model, content recognition and extraction are performed to obtain the feature information of the information to be processed. Among them, the feature information of the information to be processed may include at least one of the theme, author, keywords, release time, or information source of the text information in the information to be processed. In this way, the feature information of the information to be processed can be refined, facilitating the classification and possible further understanding and processing of the information to be processed using the feature information.

[0058] It should be noted that the specific model structure and training method of the NLP model in the embodiments of the present application are not limited in any way, that is, the NLP model used in the embodiments of the present application is any artificial intelligence model that can implement text parsing and feature information extraction.

[0059] S106: The RPA system sends the target information to the think tank display system according to the feature information and preset conditions, so that the think tank display system displays the target information to the user, and the target information is generated based on the information to be processed.

[0060] In some possible implementation manners, the RPA system can determine the target information according to the feature information returned by the NLP model and the preset conditions, and then send the target information to the think tank display system. Specifically, the RPA system can determine the target information according to the relevance between the feature information and the preset conditions. For example, if the preset condition is the transaction information of Company A, the RPA system can determine that the information to be processed corresponding to keywords such as "Company A" and "transaction" included in the feature information returned by the NLP model is the target information, and then send the target information to the display system.

[0061] Furthermore, the RPA system can determine the target information according to the magnitude of the relevance between the specific feature information and the preset conditions. For example, the RPA system can first screen out candidate target information from the information to be processed according to the feature information and the preset conditions, and then the RPA system can set a threshold for the magnitude of the relevance, and use all or part of the candidate target information whose relevance exceeds the threshold as the target information to be sent to the think tank display system. Another example is that the RPA system can sort the candidate target information according to the magnitude of the relevance (such as sorting from large to small according to the relevance), and determine the target information to be sent to the think tank display system according to the sorting result.

[0062] In some possible implementation manners, there may be a high similarity among the information to be processed collected by the RPA system. For example, for a certain news event, both website B and website C have published official news bulletins. In this case, when the RPA system collects information from website B and website C through independent sub-workflows respectively, the same information may be collected. Another example is that the tracking of a certain data indicator may not change much over a long period of time. The user expects the RPA system to send relevant information to the think tank display system only when the data indicator changes, so as to display it to the user. Therefore, the RPA system can perform duplicate removal processing on multiple similar pieces of information that have been determined as candidate target information, and then determine the target information to be sent to the think tank display system.

[0063] Specifically, the RPA system can first determine candidate target information according to the feature information and preset conditions. Then, when the difference between the first relevance between the feature information of the first candidate target information and the preset conditions and the second relevance between the feature information of the second target information and the preset conditions is less than a threshold, one of the first candidate target information and the second candidate target information is determined as the target information to be sent to the display system. In this way, duplicate removal processing of the target information can be achieved, information redundancy in the display system can be reduced, the information volume and information density in each piece of target information can be increased, which is conducive to users obtaining information more efficiently.

[0064] In some possible implementation manners, on the basis of sending the target information, the RPA system can also receive feedback from the user on the target information. For example, it is the feedback information on the matching degree between the feature information of the target information and the preset conditions after the user reads the specific target information. Among them, if the feedback information indicates that the feature information of the target information does not match the preset conditions, and the reason for the mismatch is that the extraction of the feature information is not accurate enough, the RPA system can send the feedback information to the NLP model, so that the NLP model can perform parameter update to obtain an NLP model with improved performance. It should be noted that the embodiments of the present application do not make any limitations on how the NLP model performs parameter update and model update according to the feedback information.

[0065] In some possible implementation manners, the RPA system may periodically receive feedback information sent by a user through the think tank display system according to second preset time information. The RPA system may automatically obtain feedback information according to a preset time period, such as every 10 minutes, 1 hour, 1 day, or a fixed time period every day, etc. In this way, the RPA system can automatically obtain feedback information, obtain more training data for the NLP model, and make the update of the NLP model more timely. Generally speaking, since the speed of information generation is often faster than the speed of user feedback information, and the quantity of information to be processed is much larger than the quantity of target information after screening, the RPA system may set the time interval corresponding to the second preset time information to be greater than the time interval corresponding to the second preset time information. Among them, the feedback information may be triggered by an input device. For example, the input device may be at least one of a mouse, a keyboard, a stylus, and a finger.

[0066] In some possible implementation manners, the RPA system may also obtain feedback information in response to a feedback information request triggered by a user. For example, when technicians related to NLP model training conduct centralized training and update the model, a feedback request may be triggered according to the think tank display system.

[0067] In some possible implementation manners, the RPA system may also access an information source according to preset conditions to obtain information more efficiently. For example, when the preset condition is knowledge in a certain specific technical field, the RPA system will tend to access information sources related to academics according to this preset condition, and reduce access to information sources related to, for example, life information. For example, the RPA system may allocate more computing power resources to the sub-workflow of the information source related to academics and give priority to transmitting the information in this workflow.

[0068] In some possible implementation manners, the RPA system may also generate target information according to the information to be processed. For example, it may perform format conversion to convert the information to be processed into the PDF format to reduce the possibility of information being tampered with. Another example is that the RPA system may perform information integration to generate a list of all eligible information to be processed and save and integrate it, etc.

[0069] The think tank display system in the embodiments of this application is specifically a visualization interaction tool based on a database, which can realize the intuitive display and efficient utilization of information through structured data management, dynamic chart presentation, and user interaction operations. This system supports multi-role user permission control to realize information interaction in different scenarios. For example, an administrator user, a general verification user, etc. can be created. The general verification user can access the front-end page of the system through a browser to conduct consultations and views. At the same time, the think tank display system may allocate a dedicated account and related permissions to the RPA system for logging in, sending target information, and receiving user feedback information.

[0070] It should be noted that the embodiments of the present application do not limit the specific hardware deployment relationship of the RPA system, the think tank display system, and the NLP model. That is, the RPA system, the think tank display system, and the NLP model can run independently on different terminals or servers when the network is interconnected, or all or part of them can be deployed on a single terminal or server for running under allowable conditions.

[0071] Based on the above description, the embodiments of the present application provide an information processing method, which is applied to a robotic process automation (RPA) system. On the one hand, this method can introduce digital labor by using the RPA system to achieve efficient work around the clock and avoid human operation errors, thereby improving the efficiency of information acquisition. On the other hand, by using the NLP model to extract feature information from text information, it can more accurately match the information that meets the user's needs, improving the accuracy of information acquisition and the user experience. In addition, the RPA system adopted by this method can be quickly deployed without interfering with or changing the existing enterprise system, achieving simplicity.

[0072] The present application also provides an RPA system. The RPA system of the present application will be introduced in detail below with reference to the accompanying drawings.

[0073] See Figure 2 A schematic structural diagram of an RPA system 200 as shown in Figure 2 As shown, the RPA system includes:

[0074] An acquisition module 202, configured to obtain information to be processed, where the information to be processed is text information obtained based on at least one information source;

[0075] A first processing module 204, configured to input the information to be processed into a natural language processing (NLP) model to obtain feature information of the information to be processed;

[0076] A second processing module 206, configured to send target information to the think tank display system according to the feature information and preset conditions, so that the think tank display system displays the target information to the user, and the target information is generated based on the information to be processed.

[0077] In some possible implementation manners, when the second processing module 206 sends the target information to the think tank display system according to the feature information and preset keywords, it is specifically configured to:

[0078] Determine the target information according to the relevance between the feature information and the preset conditions, and then send the target information to the think tank display system.

[0079] In some possible implementation manners, when the second processing module 206 determines the target information according to the relevance between the feature information and the preset conditions, it is specifically configured to:

[0080] Determine candidate target information based on the relevance between the feature information and the preset conditions. When the difference between the first relevance between the feature information of the first candidate target information and the preset conditions and the second relevance between the feature information of the second target information and the preset conditions is less than the threshold, determine that one of the first candidate target information or the second candidate target information is the target information to be sent.

[0081] In some possible implementation manners, when the first processing module 204 obtains the information to be processed, it is specifically used for:

[0082] Periodically obtain the information to be processed according to the first preset time information, or obtain the information to be processed in response to the information acquisition request triggered by the user.

[0083] In some possible implementation manners, the RPA system further includes a third processing module 208, and this module is specifically used for:

[0084] Receive the feedback information sent by the user through the think tank display system, where the feedback information indicates that the feature information of the target information does not match the preset conditions. Then, send the feedback information to the NLP model to update the NLP model.

[0085] In some possible implementation manners, when the third processing module 208 receives the feedback information sent by the user through the think tank display system, it is specifically used for:

[0086] Periodically receive the feedback information sent by the user through the think tank display system according to the second preset time information, or receive the feedback information sent by the user through the think tank display system in response to the feedback information request triggered by the user.

[0087] This application provides a computer device for implementing an information processing method. The computer device includes a processor and a memory. The processor and the memory communicate with each other. The processor is used to execute the instructions stored in the memory so that the computer device executes the above information processing method.

[0088] This application provides a computer-readable storage medium, in which instructions are stored, and when it runs on a computer device, it causes the computer device to execute the above information processing method.

[0089] This application provides a computer program product containing instructions, and when it runs on a computer device, it causes the computer device to execute the above information processing method.

[0090] In addition, it should be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. In addition, in the attached drawings of the device embodiments provided in this application, the connection relationships between the modules indicate that they have communication connections, which can be specifically implemented as one or more communication buses or signal lines.

[0091] Through the description of the above embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general hardware, and of course, it can also be implemented by dedicated hardware including application-specific integrated circuits, dedicated CPUs, dedicated memories, dedicated components, etc. Generally, functions completed by computer programs can be easily implemented by corresponding hardware, and the specific hardware structures for implementing the same function can also be various, such as analog circuits, digital circuits or dedicated circuits, etc. However, for this application, in more cases, software program implementation is a better implementation method. Based on such an understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a readable storage medium, such as a floppy disk, USB flash drive, mobile hard disk, ROM, RAM, magnetic disk or optical disc of a computer, and includes several instructions to enable a computer device (which can be a personal computer, training device, or network device, etc.) to execute the methods described in various embodiments of this application.

[0092] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product.

[0093] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from one website, computer, training device, or data center to another website, computer, training device, or data center by wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that can be stored by a computer or a data storage device such as a training device or a data center that includes one or more integrated available media. The available medium may be a magnetic medium (such as a floppy disk, a hard disk, a magnetic tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid state disk (SSD)).

[0094] The foregoing description of the disclosed embodiments enables those skilled in the art to practice or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An information processing method, characterized in that, Applied to a robotic process automation (RPA) system, the method includes: Obtain information to be processed, where the information to be processed is text information obtained based on at least one information source; Input the information to be processed into a natural language processing (NLP) model to obtain feature information of the information to be processed; Send target information to a think tank display system according to the feature information and preset conditions, so that the think tank display system displays the target information to the user, and the target information is generated based on the information to be processed.

2. The method according to claim 1, characterized in that, The sending of the target information to the think tank display system according to the feature information and preset keywords includes: Determine the target information according to the relevance between the feature information and the preset conditions; Send the target information to the think tank display system.

3. The method according to claim 2, wherein The determining of the target information according to the relevance between the feature information and the preset conditions includes: Determine candidate target information according to the relevance between the feature information and the preset conditions; When the difference between the first relevance between the feature information of the first candidate target information and the preset conditions and the second relevance between the feature information of the second target information and the preset conditions is less than a threshold, determine one of the first candidate target information or the second candidate target information as the target information to be sent.

4. The method according to claim 1, wherein The method further includes: Receive feedback information sent by the user through the think tank display system, where the feedback information indicates that the feature information of the target information does not match the preset conditions; Send the feedback information to the NLP model to update the NLP model.

5. The method according to claim 1, wherein The obtaining of the information to be processed includes: Periodically obtain the information to be processed according to first preset time information; Alternatively, in response to a request for obtaining information triggered by the user, obtain the information to be processed.

6. The method according to claim 4, characterized in that, The receiving of the feedback information sent by the user through the think tank display system includes: Periodically receive the feedback information sent by the user through the think tank display system according to second preset time information; Alternatively, in response to a request for feedback information triggered by the user, receive the feedback information sent by the user through the think tank display system.

7. The method according to any one of claims 1 to 6, characterized in that The feature information includes at least one of the theme, author, keywords, release time, or information source of the text information.

8. A robotic process automation (RPA) system, characterized in that, The RPA system includes: A collection module for obtaining information to be processed, where the information to be processed is text information obtained based on at least one information source; A first processing module for inputting the information to be processed into a natural language processing (NLP) model to obtain feature information of the information to be processed; A second processing module for sending target information to a think tank display system according to the feature information and preset conditions, so that the think tank display system displays the target information to the user, and the target information is generated based on the information to be processed.

9. A computer device, characterized in that, The computer device includes: A memory for storing computer programs or computer instructions; A processor for executing the computer programs or computer instructions stored in the memory, so that the computer device executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store a computer program, which, when executed, is used to implement the method according to any one of claims 1 to 7.

Images