Data processing method and device, computing equipment and storage medium

Abstract

Embodiments of the present specification provide a data processing method and apparatus, a computing device and a storage medium, the data processing method comprising: obtaining a natural language instruction for an initial data file, the natural language instruction being an instruction for performing a target operation on data in the initial data file and / or the initial data file; based on a data processing model, executing the target operation on data in the initial data file and / or the initial data file according to the natural language instruction to obtain a target data file; and sending target data in the target data file to a data receiving end according to prompt configuration information corresponding to the target data file, so as to display the target data through the data receiving end.

Description

Technical Field

[0001] The embodiments in this specification relate to the fields of artificial intelligence technology and data processing technology, and particularly to data processing methods and apparatus, computing devices and storage media. Background Technology

[0002] In practical applications, warehouse management systems can be used for warehouse inventory management, inbound and outbound operations, task allocation, and job tracking. In actual operation, warehouse management systems continuously generate a large amount of real-time or near-real-time production data, such as order processing volume, picking efficiency, and error reports.

[0003] Typically, warehouse planners need to make scheduling decisions based on data, such as whether to increase manpower or whether there are any abnormal processes. Warehouse employees usually need to manually export data from the warehouse management system and use spreadsheet tools to create reports and analyze trends. This is highly dependent on manual labor, and the same data processing logic is repeatedly executed manually, resulting in wasted manpower. Furthermore, frequent data export from the warehouse management system will also increase the system load, consume computing resources, increase labor costs, and may also increase system maintenance costs, further affecting the stability of the warehouse management system. Therefore, there is an urgent need for an effective technical solution to solve the above problems. Summary of the Invention

[0004] In view of the above, embodiments of this specification provide a data processing method. One or more embodiments of this specification also relate to a data processing apparatus, a computing device, a computer-readable storage medium, and a computer program product, to address the technical deficiencies existing in the prior art.

[0005] According to a first aspect of the embodiments of this specification, a data processing method is provided, comprising: Obtain natural language instructions for an initial data file, wherein the natural language instructions are instructions for performing target operations on data in the initial data file and / or the initial data file; Based on the data processing model, the target operation is performed on the data in the initial data file and / or the initial data file according to the natural language instructions to obtain the target data file; Based on the configuration information corresponding to the target data file, the target data in the target data file is sent to the data receiving end so that the target data can be displayed through the data receiving end.

[0006] According to a second aspect of the embodiments of this specification, a data processing apparatus is provided, comprising: The acquisition module is configured to acquire natural language instructions for an initial data file, wherein the natural language instructions are instructions for performing target operations on data in the initial data file and / or the initial data file; The execution module is configured to perform the target operation on the data in the initial data file and / or the initial data file according to the natural language instructions, based on the data processing model, to obtain the target data file; The sending module is configured to send the target data in the target data file to the data receiving end according to the prompt configuration information corresponding to the target data file, so as to display the target data through the data receiving end.

[0007] According to a third aspect of the embodiments of this specification, a computing device is provided, comprising: Memory and processor; The memory is used to store computer programs / instructions, and the processor is used to execute the computer programs / instructions, which, when executed by the processor, implement the steps of the above-described data processing method.

[0008] According to a fourth aspect of the embodiments of this specification, a computer-readable storage medium is provided that stores a computer program / instructions that, when executed by a processor, implement the steps of the data processing method described above.

[0009] According to a fifth aspect of the embodiments of this specification, a computer program product is provided, including a computer program / instructions that, when executed by a processor, implement the steps of the above-described data processing method.

[0010] One embodiment of this specification provides a data processing method, comprising: acquiring natural language instructions for an initial data file, wherein the natural language instructions are instructions for performing a target operation on data in the initial data file and / or the initial data file; performing the target operation on the data in the initial data file and / or the initial data file according to the natural language instructions based on a data processing model to obtain a target data file; and sending target data in the target data file to a data receiving end according to the prompt configuration information corresponding to the target data file, so as to display the target data through the data receiving end.

[0011] In the above method, by obtaining natural language instructions for the initial data file, and utilizing a data processing model, the corresponding target operations are automatically performed on the data and / or the initial data file according to the natural language instructions to obtain the target data file. This achieves the process of automatically updating the initial data file to obtain the target data file based on the data processing model, thereby realizing automated data processing logic without the need for repeated manual calculations. Furthermore, after obtaining the target data file, the target data in the target data file can be sent to the hi data receiving end according to the corresponding prompt configuration information, realizing the automatic push of the target data in the updated target data file. This achieves full-process automation of data acquisition, data collection, and data distribution, improving efficiency and operational quality, thereby reducing labor costs and system maintenance costs. It also eliminates the need for frequent data export from the warehouse management system, ensuring the stability of the warehouse management system. Attached Figure Description

[0012] Figure 1 This is a schematic diagram illustrating an application scenario of a data processing method provided in one embodiment of this specification; Figure 2 This is a flowchart illustrating a data processing method provided in one embodiment of this specification; Figure 3 This is a flowchart illustrating a data processing method provided in one embodiment of this specification; Figure 4 This is a schematic diagram illustrating the generation of an instruction execution template in a data processing method provided in one embodiment of this specification; Figure 5 This is a schematic diagram illustrating the calling of an instruction execution template in a data processing method provided in one embodiment of this specification; Figure 6 This is a schematic diagram of the structure of a data processing apparatus provided in one embodiment of this specification; Figure 7 This is a structural block diagram of a computing device provided in one embodiment of this specification. Detailed Implementation

[0013] Many specific details are set forth in the following description to provide a full understanding of this specification. However, this specification can be implemented in many other ways than those described herein, and those skilled in the art can make similar extensions without departing from the spirit of this specification. Therefore, this specification is not limited to the specific implementations disclosed below.

[0014] The terminology used in one or more embodiments of this specification is for the purpose of describing particular embodiments only and is not intended to be limiting of the one or more embodiments of this specification. The singular forms “a,” “described,” and “the” as used in one or more embodiments of this specification and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used in one or more embodiments of this specification refers to and includes any or all possible combinations of one or more associated listed items.

[0015] It should be understood that although the terms first, second, etc., may be used to describe various information in one or more embodiments of this specification, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, first may also be referred to as second without departing from the scope of one or more embodiments of this specification, and similarly, second may also be referred to as first. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to a determination."

[0016] Furthermore, it should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in one or more embodiments of this specification are all information and data authorized by the user or fully authorized by all parties. Moreover, the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0017] In one or more embodiments of this specification, a large model refers to a deep learning model with a large number of model parameters, typically containing hundreds of millions, tens of billions, hundreds of billions, trillions, or even tens of trillions of model parameters. A large model can also be called a foundation model. It is pre-trained using large-scale unlabeled corpora to produce a pre-trained model with hundreds of millions of parameters. Such models can adapt to a wide range of downstream tasks and have good generalization ability. Examples include Large Language Models (LLMs) and multi-modal pre-training models.

[0018] In practical applications, large models only require a small number of samples to fine-tune the pre-trained model before they can be applied to different tasks. Large models can be widely used in fields such as Natural Language Processing (NLP) and Computer Vision. Specifically, they can be applied to computer vision tasks such as Visual Question Answering (VQA), Image Captioning (IC), and Image Generation, as well as NLP tasks such as text-based sentiment classification, text summarization, and machine translation. The main application scenarios for large models include digital assistants, intelligent robots, search, online education, office software, e-commerce, and intelligent design.

[0019] First, the terms and concepts used in one or more embodiments of this specification will be explained.

[0020] API: Application Programming Interface, is a set of predefined functions, protocols, or tools that allow different software to communicate and exchange data.

[0021] Python: A widely used programming language with concise syntax and a rich ecosystem, it can be used for data analysis, automation scripts, and artificial intelligence development.

[0022] Agent: In artificial intelligence, an agent refers to a software module that can perceive its environment, make autonomous decisions, and take actions. It can be a simple rule engine or an intelligent agent based on a large model.

[0023] Sheet: A worksheet is a two-dimensional table in an Excel file, consisting of rows and columns.

[0024] Excel: Spreadsheet.

[0025] UI operations: User Interface Interaction, refers to the actions of users interacting with software or systems through a graphical interface (such as buttons, menus, input boxes, icons, etc.).

[0026] In practical applications, the production progress playback process within logistics warehouses typically relies on highly manual, repetitive operations. Specifically, it requires manual, repetitive exporting of multiple data sources to the local machine, manually processing complex data in spreadsheet files and their formulas, and then sequentially taking screenshots and sending them to the corresponding data receivers for broadcasting the results. Considering the demands of practical applications, a single warehouse usually requires a multi-person team to perform multiple data broadcasts throughout the day, with repetitive tasks every hour, each session taking approximately 5-10 minutes. Manual login to multiple systems and manual export of data from each production system result in low and complex data acquisition efficiency. Data needs to be manually entered into different templates, and adding new data processing logic relies on manually written formulas, making the process cumbersome. Historical data also needs to be manually archived, further reinforcing the reliance on manual logic in the data processing workflow. Furthermore, broadcasting data processing results requires taking screenshots of each item and sending them manually, limiting distribution efficiency and coverage. Therefore, an effective technical solution is urgently needed to address these issues.

[0027] This specification provides a data processing method, and also relates to a data processing apparatus, a computing device, a computer-readable storage medium, and a computer program product, which will be described in detail in the following embodiments.

[0028] See Figure 1 , Figure 1 A schematic diagram illustrating an application scenario of a data processing method provided according to an embodiment of this specification is shown.

[0029] Figure 1 It includes a data processing terminal 102, which can be used to call the data processing model to execute the above data processing method.

[0030] In practice, the data processing terminal 102 can determine the initial data file to be imported based on the user's selection operation on the display interface. The display interface of the data processing terminal 102 can display the file information of the initial data file, the data in the initial data file, and the dialogue interface between the user and the data processing model. The user can input natural language commands in the dialogue interface. After receiving the natural language commands, the data processing model performs the target operation on the initial data file according to the natural language commands to obtain the target data file after the operation. The display interface can also record the historical natural language commands for the initial data file.

[0031] like Figure 1As shown, the initial data file displays data related to Product 1, Product 2, Product 3, etc. The user's input natural language command is "Add a new column named 'Product Total'". The target data file obtained after performing the target operation on the initial data file based on this command is as follows: Figure 1 As shown. Furthermore, after receiving a natural language instruction, the data processing model can also output a reply message such as "Dear customer, we have successfully executed your instruction and added it to the instruction details..." if the instruction is successfully executed.

[0032] Furthermore, the data processing model can also send the target data from the target data file to the data receiving end for display.

[0033] The data processing terminal 102 may include a browser, an app (application), or a web application such as an H5 (Hypertext Markup Language 5) application, a lightweight application (also known as a mini-program), or a cloud application. The terminal device can be developed based on the software development kit (SDK) provided by the server, such as a Real-Time Communication (RTC) SDK. The terminal device can be deployed in an electronic device and depends on the device's operation or certain apps within the device to run. The electronic device may have a display screen and support information browsing, such as a personal mobile terminal like a mobile phone, tablet, or personal computer. Various other types of applications can also be configured in the electronic device, such as human-computer interaction applications, model training applications, text processing applications, web browser applications, shopping applications, search applications, instant messaging tools, email clients, and social media platform software.

[0034] See Figure 2 , Figure 2 A flowchart of a data processing method according to an embodiment of this specification is shown, which specifically includes the following steps.

[0035] Step 202: Obtain natural language instructions for the initial data file, wherein the natural language instructions are instructions for performing target operations on the data in the initial data file and / or the initial data file.

[0036] Specifically, the data processing methods provided in the embodiments of this specification can be applied to data management in warehouses, such as production data management and logistics data management in warehouses.

[0037] The initial data file can be understood as the data file before the target operation is performed. This data file could be a spreadsheet file. Natural language instructions can be understood as instructions expressed by humans in everyday speech or writing, instructing the computer or intelligent system to perform a specific task. An example of a natural language instruction is "Wake me up at 8 AM tomorrow." Natural language instructions for the initial data file could include "Add a row to the table showing the outbound time of product A," "Calculate today's outbound quantity of a certain type of product in the table," or "Delete data from a column in the table." The target operation can be understood as the operation of adding, deleting, modifying, or calculating data in the initial data file. For example, if the natural language instruction is "Add a row to the table showing the outbound time of product A," then the target operation is a data addition operation. If the instruction is "Calculate today's outbound quantity of a certain type of product in the table," then the target operation is a data calculation operation. If the instruction is "Delete data from a column in the table," then the target operation is a data deletion operation.

[0038] Understandably, when the target operation of a natural language instruction is data addition, since the target operation of data addition is actually adding data that was not originally in the initial data file, the natural language instruction is an instruction to perform a target operation on the initial data file. Similarly, when the target operation of a natural language instruction is data deletion, data modification, or data calculation, since the operations of data deletion, data modification, and data calculation are actually deleting, modifying, or calculating data that originally existed in the initial data file, the natural language instruction is an instruction to perform a target operation on the data in the initial data file. A natural language instruction can be an instruction to perform a target operation on the data in the initial data file, or an instruction to perform a target operation on the initial data file itself, or an instruction to perform a target operation on both the data in the initial data file and the initial data file. For example, it could be an instruction to delete certain data in the initial data file and add data to a specific line in the initial data file. This specification does not limit this to the embodiments described herein.

[0039] Based on this, it is possible to receive natural language instructions from users for the initial data file, which are used to instruct on the target operation on the data in the initial data file and / or the initial data file itself.

[0040] In practical applications, the data processing methods provided in the embodiments of this specification can be applied to a data processing end, which can be a client or a server. The embodiments of this specification do not limit this.

[0041] Natural language commands can be input by the user through the client or output by the user directly in the form of speech. The data processing end can receive the audio of the user's speech, convert the audio, and obtain the natural language command.

[0042] Step 204: Based on the data processing model, perform the target operation on the data in the initial data file and / or the initial data file according to the natural language instructions to obtain the target data file.

[0043] The data processing model can be used to process the initial data file and the data within it. Examples of data processing models include large language models, trained machine learning models, and deep learning models. The target data file can be understood as the data file obtained after performing target operations on the initial data file.

[0044] Specifically, after receiving natural language instructions for the initial data file, the natural language instructions and the initial data file can be input into the data processing model. The data processing model then executes the natural language instructions to perform target operations on the data in the initial data file and / or the initial data file itself, thereby obtaining the target data file.

[0045] In specific implementation, the step of performing the target operation on the data in the initial data file and / or the initial data file according to the natural language instructions based on the data processing model to obtain the target data file includes: The natural language instruction is input into the data processing model, and the intention of the natural language instruction is recognized based on the data processing model to obtain the target operation corresponding to the natural language instruction. Based on the target operation, determine the execution code corresponding to the target operation; The execution code is run based on the data processing model to perform the target operation on the data in the initial data file and / or the initial data file to obtain the target data file.

[0046] The execution code corresponding to the target operation can be understood as the executable code generated by the data processing model that can perform the target operation. The execution code can be, for example, a Python script.

[0047] Specifically, after inputting natural language instructions into the data processing model, the intention of the natural language instructions can be recognized based on the data processing model to obtain the target operation corresponding to the natural language instructions. Based on the target operation, the execution code of the target operation is generated, and the execution code is run to perform the target operation on the data in the initial data file and / or the initial data file to obtain the target data file.

[0048] In practical applications, after the data processing model outputs executable code, the executable code can be run by calling the code executor.

[0049] In summary, by utilizing a data processing model to automatically generate executable code, automated data processing of initial data files is achieved. Through natural language input and shortcut command input, the initial data file can be processed quickly with a single line of natural language, reducing manual operation and comprehension costs.

[0050] Further, the step of performing intent recognition on the natural language instruction based on the data processing model to obtain the target operation corresponding to the natural language instruction includes: Based on the data processing model, the natural language instruction is subjected to intent recognition to obtain the intent recognition result; Based on the intent recognition result, the target task corresponding to the natural language instruction is determined, and the target operation corresponding to the target task is determined.

[0051] Specifically, when using a data processing model to perform intent recognition on natural language instructions, the model's language understanding capabilities, gained through training on large-scale corpora, can be leveraged to map the natural language text corresponding to the instruction to one or more predefined intent categories, and extract key information to obtain intent recognition results. Subsequently, based on the intent recognition results, the data processing model can determine the target task corresponding to the natural language instruction and the target operation corresponding to that task. For example, if the target task is to calculate the total amount of a certain line of data in the initial data file, then the target operation corresponding to the target task is a calculation operation.

[0052] In practical applications, when the data processing model is a large language model, it can determine the intent based on the input natural language instructions and prompts, as well as the historical context information of the tasks it has processed. Alternatively, the large language model can encode the natural language text corresponding to the natural language instructions, obtaining high-dimensional vectors, and then perform intent recognition by calculating the similarity of these high-dimensional vectors. Furthermore, due to its generalization ability, the large language model can perform part-of-speech tagging on the natural language text corresponding to the natural language instructions, extracting verbs and objects from the natural language text, and inferring intent through keyword combinations. Moreover, before executing the above data processing methods, the large language model can be fine-tuned on datasets in the field of data file operations to achieve automatic operations on data files and the data within them. In specific implementation, determining the execution code corresponding to the target operation based on the target operation includes: The target operation is classified and identified to obtain the task type corresponding to the target operation; Based on the task type, retrieve the execution code corresponding to the task type from the code sample library.

[0053] The code sample library can be understood as a database used to store reference code samples corresponding to different target operations, and the task type corresponding to the target operation can be understood as the operation type corresponding to the target operation.

[0054] Specifically, the target operation can be classified and identified to determine the operation type corresponding to the target operation, and based on the operation type, the execution code corresponding to the operation type can be determined from multiple reference code examples in the code example library.

[0055] Furthermore, if the natural language instruction indicates that a formula needs to be added to the initial data file, the data processing model can generate the formula based on the natural language instruction and the initial data file, and insert the formula into the initial data file. Furthermore, the step of performing intent recognition on the natural language instruction based on the data processing model to obtain the target operation corresponding to the natural language instruction further includes: Based on the data processing model, the natural language instruction is subjected to intent recognition to obtain the intent recognition result; If the intention recognition result determines that the natural language instruction does not meet the operation conditions, a response message is generated based on the natural language instruction, wherein the response message is used to prompt for supplementary information to the natural language instruction; Receive the next natural language instruction in response to the reply information, and continue to execute the steps of inputting the natural language instruction into the data processing model and performing intent recognition on the natural language instruction based on the data processing model.

[0056] In this case, the natural language instruction does not meet the operation conditions, which can be understood as the natural language instruction being unclear, thus causing the data processing model to be unable to accurately identify the intent.

[0057] Specifically, the data processing model performs intent recognition on natural language commands. After obtaining the intent recognition result, if it is determined that the natural language command is unclear based on the intent recognition result, it can generate response information based on the current natural language command and return the response information to the user. The user can then continue to input the next natural language command based on the response information. The data processing terminal receives the next natural language command and can continue to execute the above steps of inputting the natural language command into the data processing model and performing intent recognition on the natural language command based on the data processing model. Through multi-turn dialogue interaction between the data processing model and the user, the subsequent determination of the target operation is realized, thereby improving the accuracy of the target operation. In practical applications, the first intelligent processing unit can be used to output the overall analytical thought process and the specific analytical tasks for each step, based on billing information and task descriptions, and to provide conclusions. The second intelligent processing unit can be used to generate data analysis execution code based on specific sub-tasks and initial data files. This code can then be executed by calling a code executor to obtain the analysis results of the sub-tasks. The code executor's inputs are the execution code and the initial data file, and its output is the code execution result.

[0058] See Figure 3 , Figure 3 A schematic flowchart of a data processing method according to one embodiment of this specification is shown. Figure 3 As shown, users can interact with the data processing unit through natural language dialogue or UI operations on the client side. All interactions can be recorded as contextual information for subsequent analysis. The data processing unit can include an intelligent processing unit, which can be an agent. The functions performed by the intelligent processing unit can also be executed by the aforementioned data processing model. The intelligent processing unit can receive natural language commands input by the user and the corresponding initial data file. This initial data file can be displayed to the user through a view representation. When the intelligent processing unit determines that the user's input natural language command expresses a question, it can ask questions to clarify the intent and achieve conversational guidance. When the user's input natural language command is ambiguous, it can predict possible target tasks and target operations based on contextual information. When the user's input natural language command contains only partially valid content, it can automatically supplement information based on common sense, experience, or historical context information to rewrite the task. When the user's input natural language command is clear and the intent is explicit, it can initiate a new task. These paths can rely on the view representation component, which can transform the user interface state into structured data input to the intelligent processing unit so that the intelligent processing unit can understand the current scenario. Furthermore, system constraints, operational guidelines, and knowledge bases can provide support to help the intelligent processing unit understand the rules. After initiating a new task, once the natural language instruction is clear and the intent is explicit, the intelligent processing unit can classify and identify the task based on the instruction, determining whether it is a data analysis task, a routine task, a formula generation task, or a customized task, etc., thereby identifying the target operation. Based on the code example library, the unit retrieves the corresponding execution code for the target operation and runs it. During the execution, the unit manipulates the view, performing the target operation on the initial data file represented in the view to obtain the target data file. Moreover, throughout this process, the processing status can be fed back to the user, and each step of the process can be recorded.

[0059] Furthermore, after obtaining the target data file by performing the target operation on the data in the initial data file and / or the initial data file according to the natural language instructions based on the data processing model, the method further includes: Record the data processing model, and perform the target operation on the data in the initial data file and / or the initial data file according to the natural language instructions to obtain the process information of the target data file; Based on the process information, an instruction execution template corresponding to the natural language instruction is generated; In response to the next natural language instruction, if it is determined that the next natural language instruction is the same as the previous natural language instruction, the instruction execution template is invoked to execute the next natural language instruction.

[0060] The instruction execution template can be understood as a process template for executing natural language instructions.

[0061] Based on this, the data processing model can be recorded to perform the target operation on the data in the initial data file and / or the initial data file according to the natural language instructions, obtain all process information of the target data file, generate an instruction execution template corresponding to the natural language instructions based on the process information, and directly call the instruction execution template to execute the same natural language instructions in the future.

[0062] In practical applications, see Figure 4 , Figure 4 This diagram illustrates the generation of an instruction execution template in a data processing method according to an embodiment of this specification, such as... Figure 4As shown, the Command Star template can be generated by recording the processing of natural language commands. Specifically, after receiving the user's natural language command and the corresponding initial data file (including data table 1, data table 2, and data table 3), the initial data file can be loaded, and the relationship between tables (i.e., the relationship between data table 1, data table 2, and data table 3) can be identified, the table type can be determined, and a data table representation (i.e., sheet representation) can be generated. The task type of the target task corresponding to the natural language command can also be determined. Then, Python code can be generated through formula generation agents, code generation agents, and interface calling agents. This Python code is then executed by a code executor, outputting the target data file (the processed data tables 1, data table 2, and data table 3). Furthermore, the code generation agent can determine the execution code corresponding to the currently received natural language command through the mapping relationship between commands and code examples stored in the code example library. Moreover, during the generation and execution of the execution code, and during the interface calling agent, a reflection mechanism is used to determine whether the currently generated execution code and the called interface are accurate. The language interaction agent records each action of the aforementioned agent and outputs statements. The output statements can be responses to the user, or prompts the user that the natural language command has been successfully executed.

[0063] See Figure 5 , Figure 5 This diagram illustrates a method for invoking an instruction execution template in a data processing method according to an embodiment of this specification, such as... Figure 5 As shown, the process of calling the instruction execution template can be a replay process of the instruction execution template. After the user uploads the initial data file to be processed, during the replay of the instruction execution template, risk checks can be performed on each step. The data table view before code execution can be compared, and the execution code can be run to determine whether the execution code is successful. If execution fails, the intelligent processing unit is used to correct the execution code until the execution code is completely matched and the final target data file is output. If the correction count is greater than or equal to 2, it indicates a mismatch, and an error message is generated. If execution is successful, it is determined whether the execution code has been corrected. If so, the corrected execution code is used to run, perform target operations on the initial data file, obtain the target data file, and compare it with the target data file in the instruction execution template. If no correction has been performed, it is determined whether the data table view has changed during the execution code. If not, the final target data file is output. If so, the intelligent processing unit is used to perform a post-view comparison to determine the risk. If there is no risk, the final target data file is output; if there is a risk, the output stops. Figure 5The "1" indicates that the risk check passed, while "-1" and "0" indicate that the risk check failed. The risk severity of "-1" is greater than that of "0". The comparison objects are the initial data file and the target data file in the instruction execution template, as well as the initial data file and the target data file in the playback process.

[0064] Based on this, the instruction recording module can generate and record operation codes (i.e., execution codes) using natural language for multi-sheet and complex structured tables. In the playback module, the recorded operation code fragments are assembled, adaptively adjusted for the data table file requiring playback, and the complete operation process is executed without requiring repetitive user operations. In the inference and analysis module, deep inference tasks can be completed based on a data processing model for multiple sets of complex structured files. The self-service broadcast module automatically broadcasts and pushes information about the data processing process, achieving closed-loop automatic execution of the entire process.

[0065] Furthermore, different users can execute different target operations by inputting different natural language commands, generating a variety of command execution templates. The permissions for different users' command execution templates are open; users can reference or copy other people's command execution templates, reducing repetitive work, improving work efficiency, and ensuring the controllability of command usage.

[0066] In summary, by constructing an instruction execution template after processing a natural language instruction, it can be reused at zero cost. The construction of the instruction execution template is driven by the natural language instruction, and the processing is modular. It supports the logical adaptive evolution and reuse of the instruction execution template, and the data can be automatically archived and retained to ensure historical traceability in the time dimension.

[0067] Step 206: Based on the prompt configuration information corresponding to the target data file, send the target data in the target data file to the data receiving end so that the target data can be displayed through the data receiving end.

[0068] The prompt configuration information can be understood as the pre-set configuration information for pushing target data files. For example, the prompt configuration information can be used to prompt which data in the target data file will be pushed to which data receiving end.

[0069] Specifically, the target data in the target data file can be sent to the data receiving end according to the pre-set configuration information, so that the target data can be displayed through the data receiving end.

[0070] In specific implementation, the step of sending the target data in the target data file to the data receiving end according to the prompt configuration information corresponding to the target data file, so as to display the target data through the data receiving end, includes: Based on the data configuration information in the prompt configuration information corresponding to the target data file, determine the target data from the data in the target data file, and determine the data receiving end corresponding to the target data; According to the time configuration information in the prompt configuration information, the target data is sent to the data receiving end so that the target data can be displayed through the data receiving end.

[0071] The data configuration information is used to indicate the data in the target data file that needs to be pushed and broadcast. The target data can be understood as the data within the target data file that needs to be pushed and played, such as pushing and playing the hourly outbound volume from the target data file to the data receiving end. The time configuration information can be understood as the push time of the target data, such as pushing it once every 1 hour, once every 2 hours, etc. The data receiving end can be understood as the end that receives the target data.

[0072] Specifically, based on the data configuration information, the target data to be pushed and played in the target data file can be determined, and the receiving end to receive the target data can be determined. According to the time configuration information, the target data is sent to the data receiving end, and the target data is displayed through the data receiving end.

[0073] Furthermore, in practical applications, target data can be sent to a specific group chat in the corresponding application. Based on this, the data processing model can call the group chat broadcast API in the application and push the target data to the specific group chat based on the group chat broadcast API.

[0074] In summary, the above-mentioned automatic push mechanism enables accurate push notifications without human intervention, reduces labor costs, and ensures stability and reliability.

[0075] In one embodiment of this specification, prior to obtaining the natural language instructions for the initial data file, the method further includes: In response to a data acquisition instruction, the initial data file is retrieved from the data source corresponding to the data acquisition instruction, and the data in the initial data file is displayed. After the data processing model, based on the natural language instructions, performs the target operation on the data in the initial data file and / or the initial data file to obtain the target data file, the method further includes: Display the data in the target data file; In response to a selection instruction for a data filter item in the target data file, the data corresponding to the data filter item is displayed.

[0076] In this context, the data acquisition command can be understood as the data upload command executed by the user through the data processing terminal. The data source corresponding to the data acquisition command can be understood as the data source selected by the user when uploading the initial data file. The data filtering options can be understood as the data filtering options displayed on the target data file. In practical applications, the data processing terminal can import data files from multiple data sources, achieving efficient data file capture and integration by connecting to multiple data sources.

[0077] Specifically, the data processing terminal can respond to the user's data upload command, import the initial data file from the user-selected data source, and display the initial data file and its data through a display interface. The display interface can also show a dialogue interface with the data processing model. Users can input natural language commands in this interface, and the data processing model receives these commands, performs the target operation on the initial data file, and then displays the target data file in the display interface, enabling a data preview and allowing users to verify the accuracy of the data processing model's target operation.

[0078] Furthermore, users can select data filters on the data processing terminal's display interface. The data processing terminal responds to this selection by displaying the data corresponding to the selected filters. By directly modifying data filters on the display interface, there is no need to re-upload data files, saving operational costs.

[0079] Furthermore, in one embodiment of this specification, the user can first upload an initial data file and then input natural language instructions for that initial data file into the data processing model. In another embodiment of this specification, the user can directly input natural language instructions carrying file identification information of the initial data file into the data processing model. When parsing the natural language instructions, the data processing model can first determine the file identification information carried in the natural language instructions and determine the initial data file to which the natural language instructions are applied based on the file identification information, so as to achieve the subsequent target operation on the initial data file. For example, if the natural language instruction is "Add a row of production data to the XX data table", then the "XX data table" can be understood as file identification information.

[0080] Furthermore, after sending the target data in the target data file to the data receiving end according to the prompt configuration information corresponding to the target data file, the method further includes: Generate execution report information corresponding to the natural language instructions; The execution report information includes creation information, modification information, prompt configuration information, and data transmission status information corresponding to the natural language instruction.

[0081] Specifically, during natural language instruction processing, execution report information corresponding to the natural language instruction can be recorded. This execution report information can be the instruction execution template information. The data processing end can display this execution report information through a display interface.

[0082] In practical applications, the execution report information includes the following: creation information (creator information and report name information of the execution instruction template), modification information (modifier information and modification time information of the execution instruction template), prompt configuration information (time configuration information and data configuration information of the execution instruction template), and data transmission status information (status information such as whether the initial data table was operated correctly during the natural language instruction processing and whether the target data was accurately pushed to the data receiving end).

[0083] Furthermore, if the data transmission status information indicates a transmission failure, the reason for the failure can be displayed, facilitating timely adjustments based on that reason.

[0084] In summary, the above method acquires natural language instructions for the initial data file and, using a data processing model, automatically performs corresponding target operations on the data and / or the initial data file based on these instructions to obtain the target data file. This achieves the process of automatically updating the initial data file to obtain the target data file based on the data processing model, thereby enabling automated data processing logic without the need for repeated manual calculations. Furthermore, after obtaining the target data file, the target data in the target data file can be sent to the hi data receiving end according to the corresponding configuration information, achieving automatic push of the updated target data in the target data file. This automates the entire process of data acquisition, collection, and distribution, improving efficiency and operational quality, thereby reducing labor costs and system maintenance costs. It also eliminates the need for frequent data export from the warehouse management system, ensuring the stability of the warehouse management system.

[0085] Corresponding to the above method embodiments, this specification also provides data processing apparatus embodiments. Figure 6 A schematic diagram of the structure of a data processing apparatus according to one embodiment of this specification is shown. Figure 6 As shown, the device includes: The acquisition module 602 is configured to acquire natural language instructions for an initial data file, wherein the natural language instructions are instructions for performing target operations on data in the initial data file and / or the initial data file; Execution module 604 is configured to perform the target operation on the data in the initial data file and / or the initial data file according to the natural language instructions based on the data processing model, thereby obtaining the target data file; The sending module 606 is configured to send the target data in the target data file to the data receiving end according to the prompt configuration information corresponding to the target data file, so as to display the target data through the data receiving end.

[0086] In an optional embodiment, the execution module 604 is further configured to: The natural language instruction is input into the data processing model, and the intention of the natural language instruction is recognized based on the data processing model to obtain the target operation corresponding to the natural language instruction. Based on the target operation, determine the execution code corresponding to the target operation; The execution code is run based on the data processing model to perform the target operation on the data in the initial data file and / or the initial data file to obtain the target data file.

[0087] In an optional embodiment, the execution module 604 is further configured to: Based on the data processing model, the natural language instruction is subjected to intent recognition to obtain the intent recognition result; Based on the intent recognition result, the target task corresponding to the natural language instruction is determined, and the target operation corresponding to the target task is determined.

[0088] In an optional embodiment, the execution module 604 is further configured to: The target operation is classified and identified to obtain the task type corresponding to the target operation; Based on the task type, retrieve the execution code corresponding to the task type from the code sample library.

[0089] In an optional embodiment, the execution module 604 is further configured to: Based on the data processing model, the natural language instruction is subjected to intent recognition to obtain the intent recognition result; If the intention recognition result determines that the natural language instruction does not meet the operation conditions, a response message is generated based on the natural language instruction, wherein the response message is used to prompt for supplementary information to the natural language instruction; Receive the next natural language instruction in response to the reply information, and continue to execute the steps of inputting the natural language instruction into the data processing model and performing intent recognition on the natural language instruction based on the data processing model.

[0090] In an optional embodiment, the execution module 604 is further configured to: Record the data processing model, and perform the target operation on the data in the initial data file and / or the initial data file according to the natural language instructions to obtain the process information of the target data file; Based on the process information, an instruction execution template corresponding to the natural language instruction is generated; In response to the next natural language instruction, if it is determined that the next natural language instruction is the same as the previous natural language instruction, the instruction execution template is invoked to execute the next natural language instruction.

[0091] In an optional embodiment, the sending module 606 is further configured to: Based on the data configuration information in the prompt configuration information corresponding to the target data file, determine the target data from the data in the target data file, and determine the data receiving end corresponding to the target data; According to the time configuration information in the prompt configuration information, the target data is sent to the data receiving end so that the target data can be displayed through the data receiving end.

[0092] In an optional embodiment, the acquisition module 602 is further configured to: In response to a data acquisition instruction, the initial data file is retrieved from the data source corresponding to the data acquisition instruction, and the data in the initial data file is displayed. Display the data in the target data file; In response to a selection instruction for a data filter item in the target data file, the data corresponding to the data filter item is displayed.

[0093] In an optional embodiment, the execution module 604 is further configured to: Generate execution report information corresponding to the natural language instructions; The execution report information includes creation information, modification information, prompt configuration information, and data transmission status information corresponding to the natural language instruction.

[0094] In summary, the aforementioned device acquires natural language instructions for the initial data file and, using a data processing model, automatically performs corresponding target operations on the data and / or the initial data file based on these instructions to obtain the target data file. This achieves the process of automatically updating the initial data file to obtain the target data file based on the data processing model, thereby enabling automated data processing logic without the need for repeated manual calculations. Furthermore, after obtaining the target data file, the device can send the target data in the target data file to the hi data receiving end according to the corresponding configuration information, achieving automatic push of the updated target data in the target data file. This automates the entire process of data acquisition, collection, and distribution, improving efficiency and operational quality, thereby reducing labor costs and system maintenance costs. It also eliminates the need for frequent data export from the warehouse management system, ensuring the stability of the warehouse management system.

[0095] The above is an illustrative scheme of a data processing apparatus according to this embodiment. It should be noted that the technical solution of this data processing apparatus and the technical solution of the data processing method described above belong to the same concept. For details not described in detail in the technical solution of the data processing apparatus, please refer to the description of the technical solution of the data processing method described above.

[0096] Figure 7 A structural block diagram of a computing device 700 according to one embodiment of this specification is shown. The components of the computing device 700 include, but are not limited to, a memory 710 and a processor 720. The processor 720 is connected to the memory 710 via a bus 730, and a database 750 is used to store data.

[0097] The computing device 700 also includes an access device 740, which enables the computing device 700 to communicate via one or more networks 760. Examples of these networks include Public Switched Telephone Network (PSTN), Local Area Network (LAN), Wide Area Network (WAN), Personal Area Network (PAN), or combinations of communication networks such as the Internet. The access device 740 may include one or more of any type of wired or wireless network interface (e.g., a network interface card (NIC)), such as an IEEE 802.11 Wireless Local Area Network (WLAN) wireless interface, a Wi-MAX (Worldwide Interoperability for Microwave Access) interface, an Ethernet interface, a Universal Serial Bus (USB) interface, a cellular network interface, a Bluetooth interface, or a Near Field Communication (NFC) interface.

[0098] In one embodiment of this specification, the above-described components of the computing device 700 and Figure 7 Other components, not shown, can also be connected to each other, for example, via a bus. It should be understood that... Figure 7 The block diagram of the computing device shown is for illustrative purposes only and is not intended to limit the scope of this specification. Those skilled in the art can add or replace other components as needed.

[0099] The computing device 700 can be any type of stationary or mobile computing device, including mobile computers or mobile computing devices (e.g., tablet computers, personal digital assistants, laptop computers, notebook computers, netbooks, etc.), mobile phones (e.g., smartphones), wearable computing devices (e.g., smartwatches, smart glasses, etc.) or other types of mobile devices, or stationary computing devices such as desktop computers or personal computers (PCs). The computing device 700 can also be a mobile or stationary server.

[0100] The processor 720 is used to execute the following computer program / instructions, which, when executed by the processor, implement the steps of the above-described data processing method.

[0101] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the computing device embodiments are basically similar to the data processing method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the data processing method embodiments.

[0102] An embodiment of this specification also provides a computer-readable storage medium storing a computer program / instructions that, when executed by a processor, implement the steps of the above-described data processing method.

[0103] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the computer-readable storage medium embodiments are basically similar to the data processing method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the data processing method embodiments.

[0104] An embodiment of this specification also provides a computer program product, including a computer program / instructions that, when executed by a processor, implement the steps of the above-described data processing method.

[0105] The above is an illustrative scheme of a computer program product according to this embodiment. It should be noted that the technical solution of this computer program product and the technical solution of the data processing method described above belong to the same concept. For details not described in detail in the technical solution of the computer program product, please refer to the description of the technical solution of the data processing method described above.

[0106] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0107] The computer instructions include computer program code, which may be in the form of source code, object code, executable file, or certain intermediate forms. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording media, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium may be appropriately added or removed according to the requirements of patent practice. For example, in some regions, according to patent practice, computer-readable media may not include electrical carrier signals and telecommunication signals.

[0108] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that the embodiments in this specification are not limited to the described order of actions, because according to the embodiments in this specification, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in this specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to the embodiments in this specification.

[0109] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0110] The preferred embodiments disclosed above are merely illustrative of this specification. The optional embodiments do not exhaustively describe all details, nor do they limit the invention to the specific implementations described. Clearly, many modifications and variations can be made based on the embodiments described herein. These embodiments are selected and specifically described in this specification to better explain the principles and practical applications of the embodiments, thereby enabling those skilled in the art to better understand and utilize this specification. This specification is limited only by the claims and their full scope and equivalents.

Claims

1. A data processing method, comprising: Obtain natural language instructions for an initial data file, wherein the natural language instructions are instructions for performing target operations on data in the initial data file and / or the initial data file; Based on the data processing model, the target operation is performed on the data in the initial data file and / or the initial data file according to the natural language instructions to obtain the target data file; Based on the configuration information corresponding to the target data file, the target data in the target data file is sent to the data receiving end so that the target data can be displayed through the data receiving end.

2. The method according to claim 1, wherein the step of performing the target operation on the data in the initial data file and / or the initial data file according to the natural language instruction based on the data processing model to obtain the target data file includes: The natural language instruction is input into the data processing model, and the intention of the natural language instruction is recognized based on the data processing model to obtain the target operation corresponding to the natural language instruction. Based on the target operation, determine the execution code corresponding to the target operation; The execution code is run based on the data processing model to perform the target operation on the data in the initial data file and / or the initial data file to obtain the target data file.

3. The method according to claim 2, wherein the step of performing intent recognition on the natural language instruction based on the data processing model to obtain the target operation corresponding to the natural language instruction further includes: Based on the data processing model, the natural language instruction is subjected to intent recognition to obtain the intent recognition result; If the intention recognition result determines that the natural language instruction does not meet the operation conditions, a response message is generated based on the natural language instruction, wherein the response message is used to prompt for supplementary information to the natural language instruction; Receive the next natural language instruction in response to the reply information, and continue to execute the steps of inputting the natural language instruction into the data processing model and performing intent recognition on the natural language instruction based on the data processing model.

4. The method according to any one of claims 1-3, wherein after performing the target operation on the data in the initial data file and / or the initial data file according to the natural language instructions based on the data processing model to obtain the target data file, it further includes: Record the data processing model, and perform the target operation on the data in the initial data file and / or the initial data file according to the natural language instructions to obtain the process information of the target data file; Based on the process information, an instruction execution template corresponding to the natural language instruction is generated; In response to the next natural language instruction, if it is determined that the next natural language instruction is the same as the previous natural language instruction, the instruction execution template is invoked to execute the next natural language instruction.

5. The method according to any one of claims 1-3, wherein sending the target data in the target data file to the data receiving end according to the prompt configuration information corresponding to the target data file, so as to display the target data through the data receiving end, includes: Based on the data configuration information in the prompt configuration information corresponding to the target data file, determine the target data from the data in the target data file, and determine the data receiving end corresponding to the target data; According to the time configuration information in the prompt configuration information, the target data is sent to the data receiving end so that the target data can be displayed through the data receiving end.

6. The method according to any one of claims 1-3, further comprising, before obtaining the natural language instructions for the initial data file: In response to a data acquisition instruction, the initial data file is retrieved from the data source corresponding to the data acquisition instruction, and the data in the initial data file is displayed. After the data processing model, based on the natural language instructions, performs the target operation on the data in the initial data file and / or the initial data file to obtain the target data file, the method further includes: Display the data in the target data file; In response to a selection instruction for a data filter item in the target data file, the data corresponding to the data filter item is displayed.

7. The method according to any one of claims 1-3, wherein after sending the target data in the target data file to the data receiving end according to the prompt configuration information corresponding to the target data file, it further includes: Generate execution report information corresponding to the natural language instructions; The execution report information includes creation information, modification information, prompt configuration information, and data transmission status information corresponding to the natural language instruction.

8. A computing device, comprising: Memory and processor; The memory is used to store computer programs / instructions, and the processor is used to execute the computer programs / instructions, which, when executed by the processor, implement the steps of the method according to any one of claims 1 to 7.

9. A computer-readable storage medium storing a computer program / instructions that, when executed by a processor, implement the steps of the method according to any one of claims 1 to 7.

10. A computer program product comprising a computer program / instructions that, when executed by a processor, implement the steps of the method according to any one of claims 1 to 7.

Images