Information sorting method and device combining RPA and AI

Abstract

The present application discloses an information sorting method and apparatus combining RPA and AI. Among them, the information sorting method includes: the RPA system obtains the information to be sorted; the RPA system inputs the information into a classification model based on natural language processing NLP, wherein the classification model is used to obtain the classification result of the information; the RPA system determines the push object of the information according to the classification result; the RPA system pushes the information to the push object. Thus, the RPA system can classify the information through the classification model, obtain the push object according to the classification result and perform automatic push of the information, thereby realizing automatic sorting of the information. Compared with the related art where most information sorting relies on manual labor, a large amount of manpower and material resources are saved, which helps to improve the efficiency and accuracy of information sorting.

Description

Technical Field

[0001] This application relates to the technical fields of Robotic Process Automation (RPA) and AI (Artificial Intelligence), and particularly relates to an information sorting method, device, equipment, and medium that combines RPA and AI. Background Art

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

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

[0004] Currently, RPA and AI technologies have the advantages of high automation, high precision, and low cost, and have been widely applied.

[0005] In related technologies, most information sorting relies on manual labor, with a large number of repetitive operations, consuming a large amount of human and material resources. The efficiency of information sorting is low and errors are prone to occur. Summary of the Invention

[0006] This application aims to at least solve one of the technical problems in the above technologies to a certain extent.

[0007] To this end, one objective of this application is to propose an information sorting method that combines RPA and AI. The RPA system can classify information through a classification model, obtain the push target according to the classification result, and perform automatic push of information, thus realizing automatic sorting of information. Compared with the related technologies where most information sorting relies on manual labor, it saves a large amount of human and material resources and helps improve the efficiency and accuracy of information sorting.

[0008] The second objective of this application is to propose an information sorting device that combines RPA and AI.

[0009] The third objective of this application is to propose an electronic device.

[0010] The fourth objective of this application is to propose a computer-readable storage medium.

[0011] To achieve the above object, an information sorting method combining RPA and AI according to an embodiment of the first aspect of the present application includes: an RPA system obtains information to be sorted; the RPA system inputs the information into a classification model based on natural language processing (NLP), where the classification model is used to obtain a classification result of the information; the RPA system determines a push object of the information according to the classification result; the RPA system pushes the information to the push object.

[0012] According to the information sorting method combining RPA and AI of the embodiments of the present application, the RPA system can input the information to be sorted into a classification model based on natural language processing (NLP), obtain the classification result of the information through the classification model, and then determine the push object according to the classification result and push the information. Thus, the RPA system can classify the information through the classification model, obtain the push object according to the classification result and perform automatic push of the information, that is, automatic sorting of the information can be realized. Compared with most of the related technologies that rely on manual information sorting, a large amount of manpower and material resources are saved, which helps to improve the efficiency and accuracy of information sorting.

[0013] In addition, the information sorting method combining RPA and AI according to the above embodiments of the present application may further have the following additional technical features:

[0014] In an embodiment of the present application, before inputting the information into a classification model based on natural language processing (NLP), it further includes: the RPA system obtains a historical information library, and the historical information library includes sorted historical information; the RPA system obtains the similarity between the information and the historical information, and identifies whether the information is duplicate information according to the similarity; the RPA system responds that the information is non-duplicate information.

[0015] In an embodiment of the present application, it further includes: the RPA system responds that the information is duplicate information; the RPA system obtains the historical push object of the historical information with the highest similarity, and uses the historical push object as the push object of the information.

[0016] In an embodiment of the present application, it further includes: the RPA system obtains a sample information library, and the sample information library includes sample information; the RPA system obtains the similarity between the information and the sample information, and identifies whether the information is first target information according to the similarity; the RPA system responds that the information is first target information, obtains the sample push information of the sample information with the highest similarity, and pushes the sample push information to the initiator of the information.

[0017] In one embodiment of the present application, before pushing the information to the push object, it includes: the RPA system sends the information to be verified of the information to a verification object for manual review, where the information to be verified includes at least one of the classification result and the push object; the RPA system receives the confirmation message sent by the verification object.

[0018] In one embodiment of the present application, it further includes: the RPA system identifies the information as the second target information; the RPA system sends the information to a judgment object, and the judgment object obtains the classification result and the push object.

[0019] In one embodiment of the present application, obtaining the information to be sorted includes: the RPA system opens an information platform; the RPA system logs in to the information platform using a first account; the RPA system reads the information to be sorted from the information reading page of the information platform.

[0020] In one embodiment of the present application, pushing the information to the push object includes: the RPA system opens a communication tool; the RPA system logs in to the communication tool using a second account; the RPA system establishes a session page with the push object in the communication tool; the RPA system sends a notification message to the push object through the session page, and the notification message carries the information.

[0021] To achieve the above object, an information sorting device combining RPA and AI according to a second aspect embodiment of the present application includes: a first acquisition module for acquiring the information to be sorted; a classification module for inputting the information into a classification model based on natural language processing NLP, where the classification model is used to obtain the classification result of the information; a determination module for determining the push object of the information according to the classification result; a first push module for pushing the information to the push object.

[0022] The information sorting device combining RPA and AI according to the embodiments of the present application can input the information to be sorted into a classification model based on natural language processing NLP, obtain the classification result of the information through the classification model, and then determine the push object according to the classification result and push the information. Thus, the information can be classified by the classification model, the push object can be obtained according to the classification result, and the information can be automatically pushed, that is, the automatic sorting of the information can be realized. Compared with the related art that mostly relies on manual information sorting, a large amount of manpower and material resources are saved, which helps to improve the efficiency and accuracy of information sorting.

[0023] In addition, the information sorting device combining RPA and AI according to the above embodiments of the present application may further have the following additional technical features:

[0024] In one embodiment of the present application, the classification module is further configured to: obtain a historical information library, where the historical information library includes sorted historical information; obtain the similarity between the information and the historical information, and identify whether the information is duplicate information according to the similarity; and in response to the information being non-duplicate information.

[0025] In one embodiment of the present application, the classification module is further configured to: in response to the information being duplicate information; obtain the historical push object of the historical information with the highest similarity, and use the historical push object as the push object of the information.

[0026] In one embodiment of the present application, it further includes: a second acquisition module, configured to obtain a sample information library, where the sample information library includes sample information; a first identification module, configured to obtain the similarity between the information and the sample information, and identify whether the information is first target information according to the similarity; a second push module, configured to in response to the information being first target information, obtain the sample push information of the sample information with the highest similarity, and push the sample push information to the initiating object of the information.

[0027] In one embodiment of the present application, the first push module is further configured to: send the information to be verified of the information to a verification object for manual review, where the information to be verified includes at least one of the classification result and the push object; and receive the confirmation message sent by the verification object.

[0028] In one embodiment of the present application, it further includes: a second identification module, configured to identify the information as second target information; a sending module, configured to send the information to a judgment object, and the judgment object obtains the classification result and the push object.

[0029] In one embodiment of the present application, the first acquisition module is further configured to: open an information platform; log in to the information platform using a first account; and read the information to be sorted from the information reading page of the information platform.

[0030] In one embodiment of the present application, the first push module is further configured to: open a communication tool; log in to the communication tool using a second account; establish a session page with the push object in the communication tool; and send a notification message carrying the information to the push object through the session page.

[0031] To achieve the above object, an embodiment of the third aspect of the present application provides an electronic device, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the information sorting method combining RPA and AI as described in the embodiment of the first aspect of the present application.

[0032] In the electronic device according to the embodiment of the present application, by the processor executing the instructions stored in the memory, the RPA system can input the information to be sorted into a classification model based on natural language processing (NLP), and obtain the classification result of the information through the classification model, and then determine the push object according to the classification result and push the information. Thus, the RPA system can classify the information through the classification model, obtain the push object according to the classification result and perform automatic push of the information, that is, automatic sorting of the information can be realized. Compared with the related art that mostly relies on manual information sorting, a large amount of manpower and material resources are saved, which helps to improve the efficiency and accuracy of information sorting.

[0033] To achieve the above object, an embodiment of the fourth aspect of the present application provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, it implements the information sorting method combining RPA and AI as described in the embodiment of the first aspect of the present application.

[0034] In the computer-readable storage medium according to the embodiment of the present application, by storing a computer program and being executed by a processor, the RPA system can input the information to be sorted into a classification model based on natural language processing (NLP), and obtain the classification result of the information through the classification model, and then determine the push object according to the classification result and push the information. Thus, the RPA system can classify the information through the classification model, obtain the push object according to the classification result and perform automatic push of the information, that is, automatic sorting of the information can be realized. Compared with the related art that mostly relies on manual information sorting, a large amount of manpower and material resources are saved, which helps to improve the efficiency and accuracy of information sorting. Description of the Drawings

[0035] The above and / or additional aspects and advantages of the present application will become obvious and easy to understand from the following description of the embodiments in conjunction with the drawings, where:

[0036] Figure 1 FIG. is a schematic flowchart of an information sorting method combining RPA and AI according to an embodiment of the present application;

[0037] Figure 2 FIG. is a schematic flowchart of an information sorting method combining RPA and AI according to another embodiment of the present application;

[0038] Figure 3 A schematic flow diagram after obtaining the information to be sorted in the information sorting method combining RPA and AI according to an embodiment of the present application; and

[0039] Figure 4 A block diagram of an information sorting device combining RPA and AI according to an embodiment of the present application. Detailed implementation manners

[0040] Embodiments of the present application will be described in detail below. Examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to explain the present application, and should not be construed as a limitation on the present application.

[0041] The information sorting method, device, electronic device, and computer-readable storage medium combining RPA and AI according to the embodiments of the present application will be described below with reference to the accompanying drawings.

[0042] Figure 1 A schematic flow diagram of an information sorting method combining RPA and AI according to an embodiment of the present application.

[0043] As Figure 1 shown, the information sorting method combining RPA and AI according to the embodiments of the present application includes:

[0044] S101. The RPA system obtains the information to be sorted.

[0045] It should be noted that the execution subject of the information sorting method combining RPA and AI according to the embodiments of the present application may be a robotic process automation (RPA) system, or may also be the information sorting device combining RPA and AI according to the embodiments of the present application. The above RPA system and / or the information sorting device combining RPA and AI can be configured in any electronic device to execute the information sorting method combining RPA and AI according to the embodiments of the present application. Optionally, the above RPA system may include an RPA robot.

[0046] In the embodiments of the present application, the RPA system may obtain the information to be sorted. It should be noted that there are no excessive limitations on the type of the information to be sorted. For example, the information to be sorted includes, but is not limited to, emails, text messages, platform usage records, etc., and the platform usage records include, but are not limited to, interactive records such as platform messages.

[0047] In one implementation, obtaining the information to be sorted may include the RPA system opening the information platform, the RPA system logging in to the information platform using the first account, and the RPA system reading the information to be sorted from the information reading page of the information platform. Herein, the first account is the login account for the RPA system to log in to the information platform, which can be set according to actual situations and will not be overly limited herein.

[0048] It can be understood that the user can enter information in the information entry page of the information platform. Correspondingly, the RPA system can open and log in to the information platform using the first account, and read the information to be sorted from the information reading page of the information platform. Thus, in this method, the RPA system can automatically open and log in to the information platform, and automatically read the information to be sorted from the information reading page of the information platform, realizing the automatic acquisition of the information to be sorted.

[0049] S102. The RPA system inputs the information into a classification model based on natural language processing (NLP), where the classification model is used to obtain the classification result of the information.

[0050] In an embodiment of the present application, after the RPA system obtains the information to be sorted, it can input the information into a classification model based on Natural Language Processing (NLP), where the classification model is used to obtain the classification result of the information.

[0051] In one implementation, the classification model can classify the information based on natural language processing to obtain the classification result of the information. For example, the classification model can extract keywords from the information based on natural language processing, and obtain the classification result of the information based on the extracted keywords. For instance, if the information contains words such as high-speed rail and opening to traffic, the classification result of the information can be identified as public transportation; if the information contains words such as medical treatment, reimbursement, and expenses, the classification result of the information can be identified as social security.

[0052] It should be noted that the classification model can be set according to actual situations and will not be overly limited herein. For example, the classification model can be a deep learning model.

[0053] In one implementation, training sample information and the sample classification result of the training sample information can be obtained, and the candidate classification model can be trained using the training sample information and the sample classification result of the training sample information to generate a classification model. For example, the training sample information can be input into the candidate classification model, the candidate classification model outputs the predicted classification result of the training sample information, and the parameters of the candidate classification model are adjusted using the error between the sample classification result and the predicted classification result until the model training end condition is reached to generate a classification model. Herein, the model training end condition can be set according to actual situations and will not be overly limited herein.

[0054] S103. The RPA system determines the information push target according to the classification result.

[0055] In the embodiments of the present application, there is a corresponding relationship between the classification result of the information and the information push target. The RPA system can determine the information push target according to the classification result. For example, if the classification result of the information is public transportation, the information push target can be determined as the transportation department; if the classification result of the information is social security, the information push target can be determined as the social security department; if the classification result of the information is education, the information push target can be determined as the education department.

[0056] In one implementation manner, a mapping relationship or mapping table between the classification result and the push target can be established in advance. After the RPA system obtains the classification result of the information, it can query the mapping relationship or mapping table to obtain the push target mapped by the classification result. It should be noted that the above mapping relationship or mapping table can be set according to the actual situation and is preset in the storage space of the RPA system.

[0057] S104. The RPA system pushes the information to the push target.

[0058] In the embodiments of the present application, the RPA system can push the information to the push target, and then the push target can process the information. For example, when the information is a question, the push target can reply with the answer to the information.

[0059] It should be noted that in the embodiments of the present application, the push method is not overly limited. For example, the RPA system can push the information to the push target by means of email, text message, system node transfer, etc.

[0060] In one implementation manner, pushing the information to the push target may include the RPA system opening a communication tool, the RPA system logging in to the communication tool using a second account, the RPA system establishing a session page with the push target in the communication tool, and the RPA system sending a notification message to the push target through the session page, where the notification message carries the information. The communication tool includes but is not limited to an instant messaging application (Application, APP), etc. The second account is the login account for the RPA system to log in to the communication tool, which can be set according to the actual situation and is not overly limited here.

[0061] It can be understood that the RPA system can open and log in to the communication tool using the second account, establish a session page with the push target in the communication tool, and send a notification message carrying the information to the push target through the session page. Thus, in this method, the RPA system can automatically open and log in to the communication tool, automatically establish a session page with the push target, and push the information to the push target through the session page, realizing the automatic push of the information.

[0062] In one embodiment, before pushing information to a push object, the RPA system may send the information to be verified of the information to a verification object for manual verification. The information to be verified includes at least one of a classification result and a push object, and the RPA system receives a confirmation message sent by the verification object. It should be noted that the verification object refers to an object that can perform manual verification on the information to be verified of the information. Thus, in this method, after the RPA system sends the information to be verified of the information to the verification object for manual verification and receives the confirmation message sent by the verification object, and then pushes the information to the push object, the accuracy of the classification result of the information and the push object can be improved, and further the accuracy of information sorting can be improved.

[0063] In one embodiment, the RPA system may also receive a correction message sent by the verification object. The correction message carries correction information of the information to be verified, and extracts the correction information of the information to be verified from the correction message, and corrects the information to be verified according to the correction information. Thus, in this method, the RPA system can also correct the information to be verified according to the correction information in the correction message, which can improve the accuracy of the classification result of the information and the push object, and further improve the accuracy of information sorting.

[0064] In summary, according to the information sorting method combining RPA and AI in the embodiments of the present application, the RPA system can input the information to be sorted into a classification model based on natural language processing (NLP), and obtain the classification result of the information through the classification model, and then determine the push object according to the classification result and push the information. Thus, the RPA system can classify the information through the classification model, obtain the push object according to the classification result and perform automatic push of the information, and thus realize automatic sorting of the information. Compared with the related art where most information sorting relies on manual labor, a large amount of manpower and material resources are saved, which helps to improve the efficiency and accuracy of information sorting.

[0065] Figure 2 It is a schematic flowchart of an information sorting method combining RPA and AI according to another embodiment of the present application.

[0066] As Figure 2 shown, the information sorting method combining RPA and AI in the embodiments of the present application includes:

[0067] S201, the RPA system obtains the information to be sorted.

[0068] It should be noted that the relevant content of step S201 can be referred to the above embodiments and will not be elaborated here.

[0069] S202, the RPA system obtains a historical information library, and the historical information library includes the sorted historical information.

[0070] In an embodiment of the present application, a historical information library may be established in advance, and the historical information library includes sorted historical information. Optionally, the historical information library may be preset in the storage space of the RPA system.

[0071] In one implementation, the RPA system may obtain the storage duration of the historical information in the historical information library, and clear the historical information with a storage duration greater than a preset threshold from the historical information library. Among them, the preset threshold can be set according to the actual situation. For example, it can be set to one week, and no more limitations are made here. Thus, in this method, the RPA system can clear the historical information with a longer storage duration in the historical information library, which can improve the timeliness of the historical information library.

[0072] S203, the RPA system obtains the similarity between the information and the historical information, and identifies whether the information is duplicate information according to the similarity.

[0073] In one implementation, obtaining the similarity between the information and the historical information may include that the RPA system inputs the information and the historical information into a similarity model, where the similarity model is used to obtain the similarity between the information and the historical information. Optionally, the similarity model can be set according to the actual situation, and no more limitations are made here.

[0074] In an embodiment of the present application, identifying whether the information is duplicate information according to the similarity may include identifying the magnitude relationship between the similarity and a preset threshold. If the similarity is greater than or equal to the preset threshold, it indicates that the similarity is large, then the information can be identified as duplicate information. On the contrary, if the similarity is less than the preset threshold, it indicates that the similarity is small, then the information can be identified as non-duplicate information. Among them, the preset threshold can be set according to the actual situation. For example, it can be set to 80%, and no more limitations are made here.

[0075] S204, the RPA system responds to the information being non-duplicate information.

[0076] S205, the RPA system inputs the information into a classification model based on natural language processing (NLP), where the classification model is used to obtain the classification result of the information.

[0077] S206, the RPA system determines the push object of the information according to the classification result.

[0078] In an embodiment of the present application, when the RPA system responds to the information being non-duplicate information, it may input the information into the classification model to obtain the classification result of the information, and determine the push object of the information according to the classification result. That is, when the information is non-duplicate information, the RPA system can obtain the classification result and the push object of the information in real time.

[0079] It should be noted that the relevant content of steps S205 - S206 can be referred to the above embodiments, and will not be elaborated here.

[0080] S207. The RPA system responds that the information is duplicate information.

[0081] S208. The RPA system obtains the historical push object of the historical information with the highest similarity, and uses the historical push object as the push object of the information.

[0082] In the embodiments of the present application, if the RPA system responds that the information is duplicate information, it can directly use the historical push object of the historical information with the highest similarity as the push object of the information, without the need to obtain the push object of the information in real time.

[0083] For example, if information 1 is duplicate information, and the similarities between information 1 and historical information A, B, and C are 20%, 90%, and 70% respectively, and the historical push objects of historical information A, B, and C are the transportation department, the social security department, and the education department respectively, then the RPA system can obtain the historical push object of the historical information B with the highest similarity, which is the social security department, and use the social security department as the push object of information 1.

[0084] S209. The RPA system pushes the information to the push object.

[0085] It should be noted that the relevant content of step S209 can be referred to the above embodiments and will not be elaborated here.

[0086] In summary, according to the information sorting method combining RPA and AI in the embodiments of the present application, the RPA system can automatically identify whether the information is duplicate information. When the information is non-duplicate information, it can obtain the classification result of the information in real time through the classification model, and then obtain the push object of the information in real time according to the classification result. When the information is duplicate information, it can directly obtain the push object of the information based on the historical push object of the historical information, which can save the information sorting time and improve the information sorting efficiency.

[0087] On the basis of any of the above embodiments, as Figure 3 shown, after obtaining the information to be sorted in step S101, it may include:

[0088] S301. The RPA system obtains a sample information library, and the sample information library includes sample information.

[0089] In the embodiments of the present application, a sample information library can be established in advance, and the sample information library includes sample information. Optionally, the sample information library can be pre-set in the storage space of the RPA system.

[0090] In one embodiment, the sample information may include information with a relatively high frequency of occurrence. For example, the RPA system can count the frequency of occurrence of information, and use the information with a frequency of occurrence greater than a preset threshold as the sample information. Among them, the preset threshold can be set according to the actual situation. For example, it can be set to 10 times per day, and there is no excessive limitation here.

[0091] S302, the RPA system obtains the similarity between the information and the sample information, and identifies whether the information is the first target information according to the similarity.

[0092] It should be noted that for the relevant content of step S302, reference can be made to the relevant content of step S203 in the above embodiment, and it will not be elaborated here.

[0093] S303, in response to the information being the first target information, the RPA system obtains the sample push information of the sample information with the highest similarity, and pushes the sample push information to the originator of the information.

[0094] In the embodiments of the present application, in response to the information being the first target information, the RPA system can obtain the sample push information of the sample information with the highest similarity, and push the sample push information to the originator of the information. Among them, the originator of the information refers to the publisher of the information. For example, when the information is a question, the corresponding originator is the questioner.

[0095] It should be noted that in the embodiments of the present application, there is no excessive limitation on the type of the sample push information. For example, when the sample information is a question, the sample push information includes but is not limited to the answer to the question, cases, etc.

[0096] For example, information 1 is the first target information, and the similarities between information 1 and sample information A, B, and C are 20%, 90%, and 70% respectively. The sample push information of sample information A, B, and C are sample push information a, b, and c respectively. Then the RPA system can obtain the sample push information b of the sample information B with the highest similarity, and push the sample push information b to the originator of information 1.

[0097] Thus, in this method, when the RPA system identifies that the information is the first target information, it directly pushes the sample push information of the sample information with the highest similarity to the originator of the information, which can promptly push the push information to the originator, enabling the originator to obtain the push information in a timely manner, shortening the waiting time of the originator, and improving the information processing efficiency.

[0098] Based on any of the above embodiments, after obtaining the information to be sorted in step S101, the RPA system can identify that the information is the second target information, and send the information to the judgment object, and the judgment object obtains the classification result and the push object.

[0099] It should be noted that the second target information refers to the information that the RPA system cannot automatically sort, and the judgment object refers to the classification result of the information that can be obtained and the object of the push object.

[0100] In an embodiment of the present application, the RPA system can identify whether the information is the second target information. After identifying that the information is the second target information, the information can be sent to the judgment object, and the judgment object can obtain the classification result of the information and the push object. Thus, for the information that the RPA system cannot automatically sort, manual sorting can be performed.

[0101] Figure 4 It is a block diagram of an information sorting device combining RPA and AI according to an embodiment of the present application.

[0102] As Figure 4 shown, the information sorting device 100 combining RPA and AI in the embodiment of the present application includes: a first acquisition module 110, a classification module 120, a determination module 130, and a first push module 140.

[0103] The first acquisition module 110 is used to acquire the information to be sorted;

[0104] The classification module 120 is used to input the information into a classification model based on natural language processing (NLP), where the classification model is used to obtain the classification result of the information;

[0105] The determination module 130 is used to determine the push object of the information according to the classification result;

[0106] The first push module 140 is used to push the information to the push object.

[0107] In an embodiment of the present application, the classification module 120 is further used to: acquire a historical information library, where the historical information library includes the sorted historical information; acquire the similarity between the information and the historical information, and identify whether the information is duplicate information according to the similarity; in response to the information being non-duplicate information.

[0108] In an embodiment of the present application, the classification module 120 is further used to: in response to the information being duplicate information; acquire the historical push object of the historical information with the highest similarity, and use the historical push object as the push object of the information.

[0109] In one embodiment of the present application, it further includes: a second acquisition module, configured to acquire a sample information library, where the sample information library includes sample information; a first recognition module, configured to acquire the similarity between the information and the sample information, and recognize whether the information is first target information according to the similarity; a second push module, configured to, in response to the information being first target information, acquire the sample push information of the sample information with the highest similarity, and push the sample push information to the initiator of the information.

[0110] In one embodiment of the present application, the first push module 140 is further configured to: send the information to be verified of the information to a verification object for manual verification, where the information to be verified includes at least one of the classification result and the push object; receive the confirmation message sent by the verification object.

[0111] In one embodiment of the present application, it further includes: a second recognition module, configured to recognize that the information is second target information; a sending module, configured to send the information to a judgment object, and the judgment object acquires the classification result and the push object.

[0112] In one embodiment of the present application, the first acquisition module 110 is further configured to: open an information platform; log in to the information platform using a first account; read the information to be sorted from the information reading page of the information platform.

[0113] In one embodiment of the present application, the first push module 140 is further configured to: open a communication tool; log in to the communication tool using a second account; establish a session page with the push object in the communication tool; send a notification message to the push object through the session page, and the notification message carries the information.

[0114] It should be noted that for the details not disclosed in the information sorting device combining RPA and AI in the embodiments of the present application, please refer to the details disclosed in the information sorting method combining RPA and AI in the above embodiments of the present invention, which will not be elaborated here.

[0115] In summary, the information sorting device combining RPA and AI in the embodiments of the present application can input the information to be sorted into a classification model based on natural language processing (NLP), and obtain the classification result of the information through the classification model. Then, according to the classification result, the push object is determined and the information is pushed. Thus, the information can be classified by the classification model, the push object can be obtained according to the classification result, and the information can be automatically pushed, thereby realizing the automatic sorting of information. Compared with the related art where most information sorting relies on manual labor, it saves a large amount of manpower and material resources, and helps to improve the efficiency and accuracy of information sorting.

[0116] To implement the above embodiments, the present application further provides an electronic device, including at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the above information sorting method combining RPA and AI.

[0117] In the electronic device according to the embodiments of the present application, by the processor executing the instructions stored in the memory, the RPA system can input the information to be sorted into a classification model based on natural language processing (NLP), and obtain the classification result of the information through the classification model, and then determine the push object according to the classification result and push the information. Thus, the RPA system can classify the information through the classification model, obtain the push object according to the classification result and perform automatic push of the information, that is, automatic sorting of the information can be realized. Compared with the related art where most information sorting relies on manual labor, a large amount of manpower and material resources are saved, which helps to improve the efficiency and accuracy of information sorting.

[0118] To implement the above embodiments, the present application further provides a computer-readable storage medium storing a computer program, which when executed by a processor implements the above information sorting method combining RPA and AI.

[0119] In the computer-readable storage medium according to the embodiments of the present application, by storing the computer program and executing it by the processor, the RPA system can input the information to be sorted into a classification model based on natural language processing (NLP), and obtain the classification result of the information through the classification model, and then determine the push object according to the classification result and push the information. Thus, the RPA system can classify the information through the classification model, obtain the push object according to the classification result and perform automatic push of the information, that is, automatic sorting of the information can be realized. Compared with the related art where most information sorting relies on manual labor, a large amount of manpower and material resources are saved, which helps to improve the efficiency and accuracy of information sorting.

[0120] In various embodiments of the present application, it should be understood that the magnitudes of the serial numbers of the above processes do not necessarily mean the order of execution is necessarily sequential. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0121] In the embodiments provided by the present application, it should be understood that "B corresponding to A" means that B is associated with A, and B can be determined according to A. However, it should also be understood that determining B according to A does not mean determining B only according to A, and B can also be determined according to A and / or other information.

[0122] In addition, in each embodiment of the present application, each functional unit can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0123] When the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-accessible memory. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc., specifically, the processor in the computer device) to execute some or all of the steps of the above-mentioned methods in each embodiment of the present application.

[0124] Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing relevant hardware through a program. This program can be stored in a computer-readable storage medium. The storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electrically-erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM), or other optical disc memories, magnetic disk memories, tape memories, or any other medium that can be used to carry or store data and is readable by a computer.

[0125] The above has introduced in detail an information sorting method, training method, device, equipment and medium combining RPA and AI disclosed in the embodiments of the present application. Specific examples are used in this article to elaborate on the principle and implementation manner of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for those of ordinary skill in the art, according to the idea of the present application, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present application.

Claims

1. An information sorting method combining RPA and AI, characterized in that, Executed by the RPA system, including: The RPA system obtains the information to be sorted. The RPA system inputs the information into a classification model based on natural language processing (NLP), where the classification model is used to obtain the classification result of the information. The RPA system determines the push target of the information according to the classification result. The RPA system pushes the information to the push target. Wherein, before inputting the information into the classification model based on natural language processing (NLP), it further includes: The RPA system obtains a historical information library, and the historical information library includes historical information that has been sorted. The RPA system obtains the similarity between the information and the historical information, and identifies whether the information is duplicate information according to the similarity. The RPA system responds that the information is non-duplicate information. It further includes: The RPA system responds that the information is duplicate information. The RPA system obtains the historical push target of the historical information with the highest similarity, and uses the historical push target as the push target of the information. The RPA system obtains a sample information library, and the sample information library includes sample information. The RPA system obtains the similarity between the information and the sample information, and identifies whether the information is first target information according to the similarity. The RPA system responds that the information is first target information, obtains the sample push information of the sample information with the highest similarity, and pushes the sample push information to the initiating object of the information. The RPA system identifies the information as second target information, and the second target information is information that the RPA system cannot automatically sort. The RPA system sends the information to a judgment object, and the judgment object obtains the classification result and the push target. The judgment object is an object that obtains the classification result and push target of the information.

2. The method according to claim 1, characterized in that, Before pushing the information to the push target, it includes: The RPA system sends the information to be verified of the information to a verification object for manual verification, where the information to be verified includes at least one of the classification result and the push target. The RPA system receives the confirmation message sent by the verification object.

3. The method according to any one of claims 1-2, characterized in that, The obtaining of the information to be sorted includes: The RPA system opens an information platform. The RPA system logs in to the information platform using a first account. The RPA system reads the information to be sorted from the information reading page of the information platform.

4. The method according to any one of claims 1-2, characterized in that, The pushing of the information to the push target includes: The RPA system opens a communication tool. The RPA system logs in to the communication tool using a second account. The RPA system establishes a session page with the push target in the communication tool. The RPA system sends a notification message carrying the information to the push target through the session page.

5. An information sorting device combining RPA and AI, characterized in that, It includes: A first obtaining module for obtaining the information to be sorted. A classification module for inputting the information into a classification model based on natural language processing (NLP), where the classification model is used to obtain the classification result of the information. A determination module, configured to determine a push object of the information according to the classification result; A first push module, configured to push the information to the push object; The classification module is further configured to: Obtain a historical information library, where the historical information library includes sorted historical information; Obtain the similarity between the information and the historical information, and identify whether the information is duplicate information according to the similarity; In response to the information being non-duplicate information; The classification module is further configured to: In response to the information being duplicate information; Obtain the historical push object of the historical information with the highest similarity, and use the historical push object as the push object of the information; Further includes: A second acquisition module, configured to acquire a sample information library, where the sample information library includes sample information; A first identification module, configured to obtain the similarity between the information and the sample information, and identify whether the information is first target information according to the similarity; A second push module, configured to, in response to the information being first target information, obtain sample push information of the sample information with the highest similarity, and push the sample push information to the initiating object of the information; A second identification module, configured to identify that the information is second target information, where the second target information is information that cannot be automatically sorted by the RPA system; A sending module, configured to send the information to a judgment object, and the judgment object obtains the classification result and the push object, where the judgment object is an object that obtains the classification result and push object of the information.

6. The device according to claim 5, wherein The first push module is further configured to: Send the information to-be-verified information to a verification object for manual verification, where the to-be-verified information includes at least one of the classification result and the push object; Receive a confirmation message sent by the verification object.

7. The device according to any one of claims 5-6, characterized in that, The first acquisition module is further configured to: Open an information platform; Log in to the information platform using a first account; Read the information to be sorted from an information reading page of the information platform.

8. The device according to any one of claims 5-6, characterized in that The first push module is further configured to: Open a communication tool; Log in to the communication tool using a second account; Establish a session page with the push object in the communication tool; Send a notification message to the push object through the session page, where the notification message carries the information.

9. An electronic device, characterized in that, Includes: At least one processor; And A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the information sorting method combining RPA and AI according to any one of claims 1-4.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by a processor, it implements the information sorting method combining RPA and AI according to any one of claims 1-4.

Images