Intelligent batch operation method and system based on natural language driving

Abstract

The invention relates to the technical field of data processing, and provides an intelligent batch operation method and system based on natural language driving, and the method comprises the steps: receiving and analyzing a natural language instruction inputted by a user, and extracting operation object information, operation condition information and operation action information; filtering the data according to the extracted operation object information and operation condition information, and screening to obtain an operation object; and performing batch operation on the screened operation objects according to the extracted operation action information, and outputting an operation result. According to the intelligent batch operation method and system based on natural language driving, manual configuration steps can be reduced, the user learning cost can be reduced, the user experience can be optimized, the system intelligence can be enhanced, and the efficiency and convenience of batch operation can be remarkably improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, and particularly relates to a natural language driven intelligent batch operation method and system. BACKGROUND

[0002] In today's digital age, data processing and operation have become the core task of many fields (such as enterprise resource management, data analysis, software development, etc.). With the explosive growth of data, users need to efficiently and conveniently perform batch operations on a large amount of data to improve work efficiency and decision-making speed. However, the existing data processing system has significant limitations in user interaction, which limits the user's efficient operation ability on data.

[0003] The current market screening and batch operation method is essentially "user adapting to system", users need to convert natural language intent into system recognizable instruction format to complete the operation. For example, in a typical data table, if a user wants to filter out all instances with "status as started" and "field 3 containing label A, label C", and perform a close operation on them, they need to manually select "status" -> "started" in the filter of the table header and trigger the filter operation, then select "label" -> "label A, label C" and trigger the filter operation. The whole process needs 6 steps, after filtering the corresponding data to be executed, full selection is performed, and the close operation is executed. The whole process of filtering and executing batch operation needs 9 steps. This interaction method is particularly cumbersome in the case of massive data and complex filtering conditions, and the user needs to click multiple times in the filtering operation, resulting in low operation efficiency, high learning cost, poor user experience, and other problems.

[0004] Chinese patent with publication number CN108108094A provides a learning processing method, terminal and computer readable medium. In actual application, the scheme has the following deficiencies: 1. Highly dependent on pre-stored instruction extraction rules, which need to be pre-defined and set by the user side or terminal side. In the face of complex and variable natural language input, pre-stored rules may not cover all possible expression methods, resulting in the system's inability to accurately recognize and process some instructions that are not pre-defined; with the continuous change of user demand and the increasing diversification of natural language expression, pre-stored rules need to be frequently updated and maintained to adapt to new instruction forms and operation requirements. This not only increases the maintenance cost of the system, but also challenges the real-time performance and adaptability of the system.

[0005] 2、The preprocessing means are relatively single, mainly focusing on basic operations such as text conversion, word segmentation processing, and part-of-speech tagging. For complex natural language inputs, especially instructions containing ambiguous semantics, polysemous words, or semantic metaphors, it is difficult to effectively extract key information, affecting the accuracy of instruction extraction. Lack of deep semantic understanding of natural language, when processing complex natural language instructions, leads to instruction extraction errors or execution results that do not meet user expectations.

[0006] 3、It performs well in specific fields (such as smart home device control), but its applicability may be limited for more extensive application scenarios, such as enterprise-level data processing and complex data analysis. This is because the operation objects, operation conditions, and operation actions differ greatly in different fields, making it difficult for pre-existing rules to remain efficient and accurate in cross-field applications. When dealing with complex data structures (such as multi-dimensional data and associated data), it is difficult to effectively filter and manipulate data, and its instruction extraction rules are mainly based on simple operation objects and operation actions, making it difficult to meet the diverse operation needs in complex data environments.

[0007] Therefore, how to provide a more efficient, accurate, reliable, and highly applicable batch operation method has become a technical problem to be solved. SUMMARY

[0008] Therefore, in order to overcome the shortcomings of the prior art, the present application aims to provide an intelligent batch operation method and system based on natural language driving.

[0009] According to a first aspect of the present application, an intelligent batch operation method based on natural language driving is provided, which comprises: Step S1: receiving and analyzing the user's input natural language instruction, extracting operation object information, operation condition information, and operation action information; Step S2: filtering data according to the extracted operation object information and operation condition information, and selecting operation objects; Step S3: performing batch operations on the selected operation objects according to the extracted operation action information, and outputting the operation results.

[0010] Optionally, in the intelligent batch operation method based on natural language driving of the present application, the user's input natural language instruction is received through an input box in the user interface, and an interactive interface is displayed when the input box is activated, guiding the user to input the natural language instruction.

[0011] Optionally, in the natural language driven intelligent batch operation method, in step S1, the input natural language instruction is subjected to semantic analysis through a preset semantic model to extract operation object information, operation condition information and operation action information, wherein the semantic analysis comprises keyword recognition, syntax analysis and semantic understanding.

[0012] Optionally, in the natural language driven intelligent batch operation method, in step S1, when analyzing the user input natural language instruction, the natural language instruction is subjected to syntax and semantic checking, and whether the user input natural language instruction conforms to syntax rules and semantic logic is checked through a preset checking rule, and if not, the user is prompted to re-input.

[0013] Optionally, in the natural language driven intelligent batch operation method, in step S1, the input history of the user is recorded and stored, and a machine learning algorithm is used to provide the user with optional input suggestions according to the input history of the user.

[0014] Optionally, in the natural language driven intelligent batch operation method, in step S2, a screening strategy is dynamically generated according to the operation object information and the operation condition information, and the data is filtered by using the dynamically generated screening strategy to obtain the operation object.

[0015] Optionally, in the natural language driven intelligent batch operation method, in step S3, an operation instruction is dynamically generated according to the operation action information, and the operation object is subjected to batch operation by using the dynamically generated operation instruction.

[0016] Optionally, in the natural language driven intelligent batch operation method, in step S3, before the batch operation is executed, the user is prompted to confirm the operation through a pop-up window in the user interface, the specific content and the influence range of the operation are displayed in the pop-up window, and after the user confirms, the batch operation is executed.

[0017] Optionally, in the natural language driven intelligent batch operation method, in step S3, the operation result is displayed through a prompt box or a pop-up window in the user interface, and the operation result comprises the number of operation objects that are successfully operated and the reason for the operation failure.

[0018] According to a second aspect of the present application, a natural language driven intelligent batch operation system is provided, which comprises a batch operation server, and the batch operation server comprises: an operation information collection module, configured to receive and analyze a user input natural language instruction, and extract operation object information, operation condition information and operation action information; an operation object screening module, configured to filter data according to the extracted operation object information and operation condition information, and screen and obtain operation objects; The operation action execution module is configured to execute batch operations on the screened operation objects according to the extracted operation action information, and output operation results.

[0019] According to a third aspect of the present application, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method according to the first aspect of the present application.

[0020] The natural language driven intelligent batch operation method and system can reduce manual configuration steps, reduce user learning costs, optimize user experience, enhance system intelligence, significantly improve the efficiency and convenience of batch operations, and provide an efficient, intelligent and friendly solution for users in massive data processing and complex operation demand scenarios. BRIEF DESCRIPTION OF DRAWINGS

[0021] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0022] Figure 1 An architecture example diagram of a natural language driven intelligent batch operation system according to an embodiment of the present application; Figure 2 An architecture example diagram of a batch operation service end of a natural language driven intelligent batch operation system according to an embodiment of the present application; Figure 3 A step flowchart of a natural language driven intelligent batch operation method according to an embodiment of the present application; Figure 4 A first execution example diagram of a natural language driven intelligent batch operation method according to an embodiment of the present application; Figure 5 A second execution example diagram of a natural language driven intelligent batch operation method according to an embodiment of the present application; Figure 6 A third execution example diagram of a natural language driven intelligent batch operation method according to an embodiment of the present application; Figure 7 A fourth execution example diagram of a natural language driven intelligent batch operation method according to an embodiment of the present application; Figure 8 A fifth execution example diagram of a natural language driven intelligent batch operation method according to an embodiment of the present application; Figure 9 FIG6 is a sixth example diagram of executing the natural language-driven intelligent batch operation method according to an embodiment of the present invention; Figure 10 This is a schematic structural diagram of the device provided by the present invention. DETAILED DESCRIPTION

[0023] The embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0024] It should be noted that, in the absence of conflict, the following embodiments and features in the embodiments may be combined with each other; and, based on the embodiments in this disclosure, all other embodiments obtained by persons of ordinary skill in the art without creative work are within the scope of protection of this disclosure.

[0025] It should be noted that various aspects of the embodiments within the scope of the appended claims are described below. It should be apparent that the aspects described herein can be embodied in a wide variety of forms, and any specific structure and / or function described herein is merely illustrative. Based on this disclosure, it should be understood by those skilled in the art that an aspect described herein can be implemented independently of any other aspect, and two or more of these aspects can be combined in various ways. For example, any number of aspects described herein can be used to implement an apparatus and / or practice a method. In addition, other structures and / or functionalities other than one or more of the aspects described herein can be used to implement this apparatus and / or practice this method.

[0026] Figure 1 FIG. 1 is an example diagram of an architecture of an intelligent batch operating system driven by natural language according to an embodiment of the present invention, as shown in FIG. Figure 1 As shown, the system may include a batch operation server 101, a communication network 102 and / or one or more batch operation clients 103. Figure 1 The example in FIG. 1 is a plurality of batch operation clients 103 .

[0027] The batch operation server 101 can be any appropriate server for storing information, data, programs and / or any other suitable type of content. In some embodiments, the batch operation server 101 can perform appropriate functions. For example, in some embodiments, the batch operation server 101 can be used to perform intelligent batch operations based on natural language driving. As an optional example, in some embodiments, the batch operation server 101 can be used to: receive and parse natural language instructions input by the user, extract operation object information, operation condition information and operation action information; filter data based on the extracted operation object information and operation condition information, and filter and obtain operation objects; perform batch operations on the filtered operation objects based on the extracted operation action information, and output the operation results.

[0028] Figure 2 As shown in FIG. 1, the batch operation service end of the natural language driven intelligent batch operation system according to the embodiments of the present application includes: Figure 2 An operation information collection module, configured to receive and analyze the natural language instruction input by the user, and extract operation object information, operation condition information and operation action information; An operation object screening module, configured to filter data according to the extracted operation object information and operation condition information, and screen and obtain operation objects; An operation action execution module, configured to execute batch operation on the screened operation objects according to the extracted operation action information, and output operation results.

[0029] As another example, in some embodiments, the batch operation service end 101 can send the natural language driven intelligent batch operation method to the batch operation client 103 for the user to use according to the request of the batch operation client 103.

[0030] As an optional example, in some embodiments, the batch operation client 103 is configured to provide a visual batch operation interface, the visual batch operation interface being configured to receive a selection input operation of the user for the natural language driven intelligent batch operation, and being configured to, in response to the selection input operation, obtain and display a batch operation interface corresponding to an option selected by the selection input operation from the batch operation service end 101, the batch operation interface at least displaying information for the natural language driven intelligent batch operation and operation options for the information for the natural language driven intelligent batch operation.

[0031] ​In some embodiments, the communication network 102 can be any suitable combination of one or more wired and / or wireless networks. For example, the communication network 102 can include any one or more of the following: the Internet, an intranet, a wide-area network (WAN), a local-area network (LAN), a personal area network (PAN), a wireless network, a digital subscriber line (DSL) network, a frame relay network, an asynchronous transfer mode (ATM) network, a virtual private network (VPN), and / or any other suitable communication network. The bulk operation client 103 can connect to the communication network 102 through one or more communication links (e.g., communication link 104), which can link to the bulk operation server 101 via one or more communication links (e.g., communication link 105). The communication links can be any communication links suitable for communicating data among the bulk operation client 103 and the bulk operation server 101 such as network links, dial-up links, wireless links, hard-wired links, any other suitable communication links, or any suitable combination of such links.

[0032] The bulk operation client 103 can include any one or more clients that present interfaces related to intelligent bulk operations based on natural language driving in a suitable form for use and operation by a user. In some embodiments, the bulk operation client 103 can include any suitable type of device. For example, in some embodiments, the bulk operation client 103 can include a mobile device, a tablet computer, a laptop computer, a desktop computer, and / or any other suitable type of client device.

[0033] Although the bulk operation server 101 is illustrated as one device, in some embodiments, any suitable number of devices can be used to perform the functions performed by the bulk operation server 101. For example, in some embodiments, multiple devices can be used to implement the functions performed by the bulk operation server 101. Alternatively, cloud services can be used to implement the functions of the bulk operation server 101.

[0034] Based on the above system, embodiments of the present application provide an intelligent bulk operation method based on natural language driving, which is illustrated by the following embodiments.

[0035] Figure 3 A flowchart of steps of an intelligent bulk operation method based on natural language driving according to an embodiment of the present application is shown in FIG. 1. As shown in FIG. 1, the intelligent bulk operation method based on natural language driving of the present embodiment can be performed on a bulk operation server, and the intelligent bulk operation method based on natural language driving includes the following steps: Figure 3 Step S1: receiving and parsing a natural language instruction input by a user, extracting operation object information, operation condition information, and operation action information.

[0036] ​In this embodiment, the natural language instruction input by the user is received through an input box in the user interface, and an interactive interface is displayed when the input box is activated to guide the user to input the natural language instruction.

[0037] To ensure accurate collection and extraction of user intent, in this embodiment, the input natural language instruction is subjected to semantic analysis through a preset semantic model to extract operation object information, operation condition information, and operation action information, wherein the semantic analysis includes keyword recognition, syntax parsing, and semantic understanding.

[0038] The semantic analysis of this embodiment is further described in detail in a specific scenario below.

[0039] In this scenario, the semantic model is used to understand and parse the natural language instruction input by the user, and the main function of the semantic model is to extract key information such as operation object, operation condition, and operation action from the text input by the user.

[0040] The semantic model first extracts key information from the natural language instruction input by the user according to keywords. The keywords can be operation objects, operation conditions, or operation actions. For example, in "close all instances with status as on", "close" is the operation action, "status as on" is the operation condition, and "instance" is the operation object. The semantic model analyzes the grammatical structure of the natural language instruction input by the user through syntax parsing to determine the relationship between the keywords. For example, by analyzing the subject-predicate-object structure of the sentence, the relationship between the operation action and the operation object is determined. The semantic model further analyzes the semantic content of the natural language instruction input by the user through semantic understanding, which includes disambiguating polysemous words, handling ambiguous semantics, and understanding context. For example, the relationship between "close" and "status as on" in "close all instances with status as on" needs to be determined through semantic understanding.

[0041] For example, the natural language instruction input by the user is: "Please help me close all instances with status as on or field 3 containing label A, label C." The processing process of the semantic model is as follows: 1. Keyword recognition Operation object: instance Operation condition: status as on, field 3 containing label A, field 3 containing label C Operation action: close 2. Syntax parsing Sentence structure analysis: The instruction input by the user is a complex sentence containing multiple conditions and one action.

[0042] Condition relationship analysis: The conditions are in an "or" relationship, i.e., instances that meet any one of the conditions "status as on" or "field 3 containing label A" or "field 3 containing label C" need to be closed.

[0043] 3. Semantic understanding Ambiguous word disambiguation: In the context, "close" explicitly represents an operation action without ambiguity.

[0044] Fuzzy semantic processing: The "contains" in the user input "Field 3 contains Label A, Label C" is a fuzzy semantic, and the semantic model needs to understand its specific meaning, i.e., Field 3 contains Label A or Label C.

[0045] Contextual understanding: The semantic model needs to understand that "state is on" is a state condition, and "Field 3 contains Label A, Label C" is an attribute condition.

[0046] 4. Output of semantic model Parse the user input natural language instruction into the following structured information: Operation object: Instance Operation condition: State is on Field 3 contains Label A Field 3 contains Label C Operation action: Close In practical applications, this embodiment uses a semantic model to process natural language instructions, which has the following advantages: 1. Improve the accuracy of instruction recognition: Through keyword recognition, syntax parsing and semantic understanding, the semantic model can accurately extract the key information in the user input natural language instruction, reducing the recognition errors caused by ambiguous semantics or ambiguous words.

[0047] 2. Enhance the flexibility of the system: The semantic model can handle various natural language expressions, even if the form of the user input instruction changes, the system can accurately understand and execute. For example, the user inputs "Close all instances that are on" or "Turn off all instances that are on", the semantic model can correctly parse and execute.

[0048] 3. Improve user experience: The semantic model allows users to interact with the system directly using natural language, without the need to learn complex instruction formats, reducing the user's learning cost, improving the system's ease of use and user experience.

[0049] In practical applications, in order to further improve the effectiveness of the input instruction, this embodiment performs syntax and semantic verification on the user input natural language instruction when parsing the user input natural language instruction, checks whether the user input natural language instruction conforms to the syntax rules and semantic logic through the preset verification rules, and if not, prompts the user to re-input.

[0050] As an optional example, the method also includes recording and storing the history of the natural language instructions and the operation results of the user, and the user can view and trace the operation history through the history recording function in the user interface, so as to facilitate the user to manage and review the operation process and improve the work efficiency and experience of the user.

[0051] As an optional example, the method also includes intelligently recommending the natural language instructions. As an optional example, the input history of the user is recorded and stored, and the input suggestions of the user are provided through a machine learning algorithm according to the input history and operation habits of the user, such as automatically completing the input of the user and recommending similar operation instructions, so as to improve the operation efficiency of the user.

[0052] Compared with the prior art, the user needs to manually set a complex filtering condition and perform an operation step, for example, when filtering data, the user needs to click a menu to select a condition step by step, which is tedious and has many steps. In the embodiment, the user only needs to input a natural language instruction, and the system can automatically identify the operation object, condition and action, trigger batch operation, and there is no need for the user to manually configure the filtering condition and perform the operation, which greatly reduces the operation steps and significantly improves the operation efficiency.

[0053] In addition, the natural language interaction is adopted, the user does not need to learn the system instruction format, and the operation intention can be directly expressed by using the natural language, the system can automatically understand and execute, so that the user can quickly start, without going through a tedious learning process, and the learning threshold of the user is reduced.

[0054] Step S2: filtering the data according to the extracted operation object information and operation condition information to obtain the operation object.

[0055] In the embodiment, the filtering strategy is dynamically generated according to the operation object information and the operation condition information, the data is filtered by using the dynamically generated filtering strategy, and the operation object is obtained. In actual application, the analysis result and the filtering result of the operation can also be fed back in real time, and the user can clearly see whether the understanding of the system to the natural language instruction is accurate and whether the filtered data meets the expectation.

[0056] In the face of massive data and complex filtering conditions, the traditional method will make the user spend a lot of time and effort in the filtering and operation process, is easy to make mistakes and is low in efficiency. The embodiment can quickly analyze the complex natural language instruction input by the user, accurately filter the data meeting the condition and perform batch operation, even for complex multi-condition filtering and operation, the operation can also be quickly completed, and the work efficiency of the user in the complex data environment is effectively improved.

[0057] Step S3: performing batch operations on the filtered operation objects according to the extracted operation action information, and outputting the operation results.

[0058] Dynamically generate operation instructions based on the operation action information, and use the dynamically generated operation instructions to perform batch operations on the operation objects. In practical applications, this embodiment can flexibly adjust the operation logic according to the input of different users, thereby improving the flexibility and adaptability of the system.

[0059] The method of this embodiment also includes a second confirmation before executing the batch operation to prevent incorrect operation. As an optional example, before executing the batch operation, this embodiment prompts the user to confirm the operation through a pop-up window in the user interface. The pop-up window displays the specific content of the operation and the scope of impact. After the user confirms, the batch operation is executed.

[0060] As an optional example, this embodiment displays the operation result through a prompt box or pop-up window in the user interface. The operation result includes the number of operation objects that are successfully operated and the reason for the operation failure.

[0061] The following is a further explanation of the natural language driven intelligent batch operation method of this embodiment in a specific scenario. Figure 4 This is a first example diagram of executing the natural language driven intelligent batch operation method according to an embodiment of the present invention; Figure 5 FIG2 is a second example diagram of executing the natural language driven intelligent batch operation method according to an embodiment of the present invention; Figure 6 FIG3 is a third example diagram of executing the natural language-driven intelligent batch operation method according to an embodiment of the present invention; Figure 7 FIG4 is a fourth example diagram of executing the natural language driven intelligent batch operation method according to an embodiment of the present invention; Figure 8 FIG5 is a fifth example diagram of executing the natural language driven intelligent batch operation method according to an embodiment of the present invention; Figure 9 FIG6 is a sixth example diagram of an intelligent batch operation method based on natural language driving according to an embodiment of the present invention. Figures 4 to 9 As shown, in this scenario, Figure 4 It is the default interface for the start, and can be activated by clicking Figure 4 The input box in the interface has evolved into Figure 5 ; By Figure 5 Enter "Please help me close all instances where the status is enabled or field 3 contains label A or label C" in the input box, and the interface will change to Figure 6 By clicking Figure 6 The send icon on the right side of the input box will display the content obtained by parsing the user input language in the drop-down floating layer. The interface evolves to Figure 7 By clicking Figure 7Click the "Confirm" button in the confirmation pop-up window, and the interface evolves into Figure 8 Click the "Confirm" button in the confirmation pop-up window, and the interface evolves into Figure 8 Click the "Confirm" button in the confirmation pop-up window, and the interface evolves into Figure 9 , Figure 9 In the above-mentioned process, the data state that meets the condition is changed to "closed".

[0062] In practical applications, the natural language driven intelligent batch operation method and system based on the embodiment can significantly improve the efficiency and convenience of batch operation by reducing manual configuration steps, reducing user learning costs, optimizing user experience, and enhancing system intelligence, thereby providing an efficient, intelligent, and friendly solution for users in massive data processing and complex operation demand scenarios.

[0063] As shown in Figure 10 The application further provides a device, which includes a processor 210, a communication interface 220, a memory 230 for storing a processor executable computer program, and a communication bus 240. The processor 210, the communication interface 220, and the memory 230 can communicate with each other through the communication bus 240. The processor 210 can realize the natural language driven intelligent batch operation method described above by running the executable computer program.

[0064] The computer program in the memory 230 can be implemented in the form of a software functional unit and sold or used as an independent product. When used, the computer program can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the embodiments of the present application. The aforementioned storage medium includes a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various program code storage media.

[0065] The system embodiments described above are only schematic, and the units illustrated as separate components can or can not be physically separated, and the components illustrated as units can or can not be physical units, i.e., they can be located in one place or distributed on multiple network units. Some or all of the modules can be selected based on actual needs to achieve the purpose of the embodiments. Those skilled in the art can understand and implement it without creative labor.

[0066] Those skilled in the art can clearly understand the implementation of the embodiments by the description of the above embodiments, and the embodiments can be implemented by means of software and necessary universal hardware platforms, and of course, can also be implemented by hardware. Based on such understanding, the above technical solutions can be embodied in the form of a software product, and the computer software product can be stored in a computer readable storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, etc., and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the method of each embodiment or some parts of the embodiment.

[0067] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical range disclosed by the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. An intelligent batch operation method based on natural language driving, characterized in that: The method comprises: Step S1: receiving and parsing the natural language instructions input by the user, extracting the operation object information, operation condition information and operation action information; Step S2: filtering the data according to the extracted operation object information and operation condition information to select and obtain the operation object; Step S3: performing batch operations on the filtered operation objects according to the extracted operation action information, and outputting the operation results.

2. The natural language driven intelligent batch operation method according to claim 1, characterized in that: In step S1, a natural language instruction input by a user is received through an input box in a user interface, and an interactive interface is displayed when the input box is activated to guide the user to input a natural language instruction.

3. The natural language driven intelligent batch operation method according to claim 1, characterized in that: In step S1, a semantic analysis is performed on the input natural language instruction through a preset semantic model to extract operation object information, operation condition information and operation action information, wherein the semantic analysis includes keyword recognition, grammatical parsing and semantic understanding.

4. The natural language driven intelligent batch operation method according to claim 1, characterized in that: In step S1, when parsing the natural language instructions input by the user, the natural language instructions are subjected to grammatical and semantic verification, and the preset verification rules are used to check whether the natural language instructions input by the user comply with the grammatical rules and semantic logic. If not, the user is prompted to re-enter.

5. The natural language driven intelligent batch operation method according to claim 1, characterized in that: Step S1 also includes: recording and storing the user's input history, and using a machine learning algorithm to provide the user with optional input suggestions based on the user's input history.

6. The natural language driven intelligent batch operation method according to claim 1, characterized in that: In step S2, a screening strategy is dynamically generated according to the operation object information and the operation condition information, and the data is filtered using the dynamically generated screening strategy to obtain the operation object.

7. The natural language driven intelligent batch operation method according to claim 1, characterized in that: In step S3, an operation instruction is dynamically generated according to the operation action information, and batch operations are performed on the operation objects using the dynamically generated operation instruction.

8. The natural language driven intelligent batch operation method according to claim 1, characterized in that: In step S3, before executing the batch operation, a pop-up window in the user interface prompts the user to confirm the operation, and the pop-up window displays the specific content and scope of the operation. After the user confirms, the batch operation is executed.

9. The natural language driven intelligent batch operation method according to claim 1, characterized in that: In step S3, the operation result is displayed through a prompt box or a pop-up window in the user interface, and the operation result includes the number of operation objects that are successfully operated and the reason for the operation failure.

10. An intelligent batch operation system driven by natural language, characterized in that: The system includes a batch operation server, which includes: The operation information collection module is used to receive and analyze the natural language instructions input by the user, and extract the operation object information, operation condition information and operation action information; The operation object screening module is used to filter the data according to the extracted operation object information and operation condition information, and screen and obtain the operation object; The operation action execution module is used to perform batch operations on the filtered operation objects according to the extracted operation action information and output the operation results.

Images