Method and device for generating report

Abstract

The embodiment of the invention provides a method and device for generating a report. The method comprises the steps that a first natural language instruction which is input by a user through a first area of a target interface and indicates editing of a first report is obtained; and inputting the first natural language instruction into the large language model, and updating the first report in the second area according to an obtained first output result.

Description

Technical Field

[0001] One or more embodiments of this specification relate to the field of large model technology, and in particular, to a method and apparatus for generating reports. Background Art

[0002] In the traditional solution for generating reports through a user interface, users usually need to generate reports through complex processes and cumbersome interface operations. For example: The process may include selecting a data table through the interface, determining the report calculation logic through a structured query language, creating a report through a large number of interface operations, configuring the fields or calculation metrics of the report, and generating a report according to the report configuration. Therefore, generating reports through this solution not only consumes a large amount of manual operations, but also requires users who master relatively complex configuration technologies to operate, making it difficult to generate reports efficiently. Summary of the Invention

[0003] Embodiments in this specification aim to provide a method and apparatus for generating reports, which can greatly simplify the complexity of the report generation process, limit and reduce the amount of manual operations consumed in the report generation process, thereby improving the efficiency of generating reports and solving the deficiencies of the prior art.

[0004] According to a first aspect, a method for generating a report is provided, including:

[0005] Obtain a first natural language instruction for instructing to edit a first report input by a user through a first area of a target interface;

[0006] Input the first natural language instruction into the large language model, and update the first report in a second area of the target interface according to the obtained first output result.

[0007] In a possible implementation manner, the target interface further includes a third area for displaying configuration components of the first report;

[0008] In response to a first preset operation of the user on the configuration component, update the first report in the second area.

[0009] In a possible implementation manner, updating the first report in the second area of the target interface according to the obtained first output result includes:

[0010] Update the first report in the second area according to the obtained first output result, and update the configuration components of the first report in the first area.

[0011] In a possible implementation, the configuration component of the first report includes: one or more of a configuration component for adding, deleting, and modifying fields in the first report, a configuration component for calculating metrics obtained by processing the fields, and a configuration component for adding, deleting, and modifying data dimensions included in the charts contained in the first report.

[0012] In a possible implementation, the first preset operation includes one or more of a drag operation, a click operation, and a typing operation.

[0013] In a possible implementation, the method further includes:

[0014] In response to a user's first preset operation on the configuration component, display the limiting conditions for the first preset operation in the first area.

[0015] In a possible implementation, the first report is created through the following process;

[0016] Obtain a second natural language instruction indicating the creation of a report input by the user through the first area, input the second natural language instruction into a preset large language model, and create a first report in the second area according to the obtained second output result.

[0017] In a possible implementation, the method further includes: before obtaining the second natural language instruction, display a prompt instruction for creating a report in the first area; and / or

[0018] After creating the first report, display a prompt instruction for updating the report in the first area.

[0019] In a possible implementation, the first report is created through the following process;

[0020] In response to a user's second preset operation on the report creation component in the third area, create the first report in the second area.

[0021] In a possible implementation, the target interface further includes a third area for displaying the configuration component of the first report;

[0022] The large language model includes a first large model, a second large model, and a third large model;

[0023] Input the first natural language instruction into the large language model, and update the first report in the second area according to the obtained first output result, including:

[0024] Determine the first configuration text according to the setting information in the configuration component;

[0025] Input the first natural language instruction and the first configuration text into a first large model to obtain a user intention, input the user intention into a second large model to obtain multiple execution steps, and input the multiple execution steps into a third large model to obtain display codes corresponding to the multiple execution steps;

[0026] Render an updated first report in the second area according to the display codes.

[0027] In a possible implementation manner, inputting the first natural language instruction and the first configuration text into the first large model includes:

[0028] Obtain one or more of the historical conversations between the user and the large language model, the user's usage preference information, and the historical operations on the configuration components of the report that are pre - saved, and input them together with the first natural language instruction and the first configuration text into the first large model.

[0029] According to a second aspect, there is provided a device for generating a report, the device includes:

[0030] An acquisition unit, configured to acquire a first natural language instruction input by a user through a first area of a target interface to indicate editing a first report;

[0031] An update unit, configured to acquire a first natural language instruction input by a user through a first area of a target interface to indicate editing the first report, input the first natural language instruction into the large language model, and update the first report in a second area of the target interface according to a first output result obtained. According to a third aspect, there is provided a computer - readable storage medium, on which a computer program is stored. When the computer program is executed on a computer, the computer is made to execute the method described in the first aspect.

[0032] According to a fourth aspect, there is provided a computing device, including a memory and a processor. An executable code is stored in the memory, and when the processor executes the executable code, the method described in the first aspect is implemented.

[0033] By using one or more of the methods, devices, computing devices, and storage media in the above - mentioned aspects, the complexity of the process of generating a report can be greatly simplified, the amount of manual operations consumed in the process of generating a report can be reduced, and thus the efficiency of generating a report can be improved. Description of the Drawings

[0034] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0035] Figure 1 Schematic diagram showing a solution for generating a report;

[0036] Figure 2 Schematic diagram showing a method for generating a report according to an embodiment of the present specification;

[0037] Figure 3 Flowchart showing a method for generating a report according to an embodiment of the present specification;

[0038] Figure 4 Schematic diagram showing a method for generating a report according to another embodiment of the present specification;

[0039] Figure 5 Schematic diagram showing a method for generating a report according to yet another embodiment of the present specification;

[0040] Figure 6 Schematic diagram showing a method for generating a report according to still another embodiment of the present specification;

[0041] Figure 7 Structural diagram showing a device for generating a report according to an embodiment of the present specification. Detailed implementation manners

[0042] To enable those skilled in the art of this technology to better understand the technical solutions in this specification, the following will clearly and completely describe the technical solutions in the embodiments of this specification in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only some embodiments of this specification, rather than all embodiments. Based on the embodiments in this specification, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the scope of protection of this specification.

[0043] In the traditional solution for generating a report through a user interface, usually, the user needs to generate a report through complex processes and cumbersome interface operations. Figure 1 Schematic diagram showing a solution for generating a report. As Figure 1As shown, the process may include, for example, selecting a data table through an interface (determining the data source), determining the report calculation logic through a structured query statement, generating a report through a large number of interface operations, and configuring the fields or calculation metrics of the report. Therefore, on the one hand, generating a report through this solution consumes a large amount of manual operations. For example, generating a report and configuring all the fields or calculation metrics of the report, or configuring the data dimensions in the charts included in the report, are all performed through operations on the visual configuration components on the interface. Since the number and types of report fields or calculation metrics are often numerous, the manual configuration work relying solely on visual components is rather cumbersome and involves a large amount of operations. On the other hand, for example, determining the report calculation logic through a structured query statement (such as an SQL query statement) requires the operator to be proficient in relatively complex structured query techniques, and the efficient configuration of a large number of report fields or calculation metrics through visual components also often requires the operator's familiarity with various report fields or calculation metrics. All these increase the complexity of generating a report, making it difficult for ordinary users to generate reports efficiently.

[0044] Another solution for generating a report can create a report in natural language at once, but cannot perform subsequent editing on the created report. However, in actual production scenarios, especially for reports with complex structures or calculations, users often have difficulty inputting a well-described natural language to create a report that requires no subsequent repair. And since this solution cannot edit the report, it is difficult for users to generate high-quality reports through this solution. In addition, in some scenarios, users often hope to make slight modifications to the already created report, such as slightly modifying the statistical screening time of the report, so as to reuse the already created report at different times. Through this solution, the report cannot be modified for reuse either.

[0045] To solve the above technical problems, the embodiments of this specification provide a method for generating a report. Figure 2 A schematic diagram showing a method for generating a report according to an embodiment of this specification. As Figure 2 shown, through this method, a report can be created and edited in natural language. For example, a natural language instruction can be input in the instruction input area of the report generation interface, so as to generate or update a report in the report display area of the report generation interface. The created report can also be created and edited through operations on the report configuration components in the visual component area of the report generation interface. Moreover, a report created or edited through a natural language instruction can also be continued to be edited through visual components, and a report created or edited through visual components can also be continued to be edited through natural language instructions.

[0046] The method has the following advantages: First, through this solution, reports can be directly created and edited via natural language instructions. Natural language instructions can usually directly indicate the goals of creation and editing, without the need to determine the report calculation logic through, for example, structured query statements. It can also greatly reduce the configuration operations performed through report configuration components, greatly simplifying the process and operation difficulty of users generating reports, and improving the report generation efficiency. Compared with the existing solutions that can only create but not edit reports, through this solution, high-quality reports can be generated and the reuse of generated reports is facilitated. Second, in some embodiments, through this solution, reports can be created and edited via natural language, and reports can also be created and edited via a visual configuration component. Moreover, for a report created and edited via one of natural language and the visual configuration component, it can continue to be edited via the other one until the report is completed. Thus, by cross-using the two report creation or editing methods and combining the advantages of both methods, the deficiencies of a single method can be avoided, further improving the efficiency of generating reports. For example, a user generates report Gx via natural language instructions. Then, if the user wants to modify the configuration of a specific field in this report and is not sure how to describe this modification, the user can directly modify the configuration of this field in the visual configuration component. Thus, through the cross-use of the two report creation and editing methods, the generation and editing of report Gx can be completed more efficiently.

[0047] The detailed process of this method will be further elaborated below. Figure 3 A flowchart of a method for generating a report according to an embodiment of this specification is shown. As Figure 3 described, this method at least includes the following steps:

[0048] Step S301, obtain a first natural language instruction indicating the editing of a first report input by a user through a first area of a target interface;

[0049] Step S303, input the first natural language instruction into the large language model, and update the first report in a second area of the target interface according to the obtained first output result.

[0050] First, in step S301, obtain a first natural language instruction indicating the editing of a first report input by a user through a first area of a target interface. The target interface is an interface for configuring and generating reports. In different embodiments, the target interface can be the application interface in different specific software or apps, and this specification does not limit this. The first area is the area in the target interface for inputting natural language instructions aimed at generating and editing reports. In different embodiments, the shape and position of the first area in the target interface can be different. In one embodiment, the first area can be, for example, on the right side of the target interface.

[0051] The first natural language instruction is an instruction in natural language form for instructing to edit the created first report. In different embodiments, the content of the report indicated by the first natural language instruction input by the user can be different, and this specification does not limit this. In one embodiment, the first natural language instruction input by the user can instruct to add, delete, or modify fields in the first report, calculate metrics obtained by processing the fields, and add, delete, or modify one or more of the data dimensions included in the charts contained in the first report.

[0052] In different embodiments, the creation method of the created first report can be different. In one embodiment, the first report can be created through the following process: Obtain the second natural language instruction indicating the creation of a report input by the user through the first area, input the second natural language instruction into a preset large language model, and create a first report in the second area according to the obtained second output result. The second natural language instruction is an instruction in natural language form for instructing to create a report. In different embodiments, the specific form and specific content of the report indicated by the first natural language instruction input by the user can be different, and this specification does not limit this. In one embodiment, the second natural language instruction input by the user can instruct to generate a report in tabular form. In one embodiment, the second natural language instruction input by the user can instruct to generate a report in chart form. In different specific embodiments, the second natural language instruction can instruct to generate different specific types of charts. In one specific embodiment, for example, it can be one of a bar chart, a line chart, a pie chart, and a column chart. In one specific embodiment, the first natural language instruction can also instruct to generate a chart through multiple inference steps. In one specific embodiment, before obtaining the second natural language instruction, a prompt instruction for creating a report can also be displayed in the first area; and / or, after creating the first report, a prompt instruction for updating the report can also be displayed in the first area.

[0053] Figure 4 A schematic diagram showing a method for generating a report according to another embodiment of this specification. As Figure 4 shown, for example, an instruction "Create a DAU table for using service A within N days and represent it as a bar chart" input by the user through the first area can be obtained, input this instruction into the large language model, and create a DAU (Daily Active Users) table represented by a bar chart in the second area according to the output result of the large language model.

[0054] In another embodiment, the first report can be created through the following process: the first report is created through the following process; in response to a second preset operation of the user on the report creation component in the third region, the first report is created in the second region. In different specific embodiments, the report creation component can be a visualization component for creating reports of different specific types. In different specific embodiments, the second preset operation can be operations of different specific types. In a specific embodiment, the second preset operation can be, for example, an operation of dragging the report creation component to the second region.

[0055] Figure 5 Schematic diagram showing a method for generating a report according to another embodiment of the present specification. As Figure 5 shown, for example, a component in the third region that the user can use to create a chart G2 (such as a bar chart) can be dragged to the second region to generate a bar chart in the second region.

[0056] After obtaining the first natural language instruction, in step S303, the first natural language instruction can be input into the large language model, and according to the obtained first output result, the first report is updated in the second region of the target interface.

[0057] In this specification, the Large Language Model (LLM) can also be abbreviated as the large model. A large language model is a natural language processing model based on deep learning technology, with the number of parameters usually reaching billions to hundreds of billions or even higher, and having powerful language understanding and generation capabilities. The large language model can adopt the Transformer architecture or its variants (such as GPT, BERT, etc.). This architecture uses the Attention Mechanism to achieve global modeling of sequence data, can efficiently handle long-distance dependencies, and thus performs well in natural language tasks. The large language model learns the statistical features and semantic relevance of language by pre-training on a large-scale corpus, enabling it to have good generalization ability. The core capabilities of the large language model include but are not limited to: understanding context semantics, generating coherent and grammatically correct text, performing logical reasoning, and handling multi-task scenarios. Its usage methods usually include two modes: direct inference and fine-tuning. In the direct inference mode, the user guides the large language model to generate specific outputs by designing prompts. Prompts can be task descriptions or instructions in text form, used to stimulate the semantic understanding and generation capabilities of the large language model. In the fine-tuning mode, the large language model is further trained on a small-scale dataset in a specific domain to optimize its performance on specific tasks. The powerful generalization ability and flexibility of the large language model make it an important tool in the field of artificial intelligence technology, providing an efficient and accurate solution for automated text generation and understanding.

[0058] In some embodiments, the large language model can also have the ability to understand and generate data of other modalities (such as vision, audio, etc.). In this case, the large language model can also be called a Multimodal Large Language Model (MLLMs). MLLMs provide a richer and more natural interaction experience by integrating various types of inputs and outputs such as text, images, and sounds. The core advantage of MLLMs is that they can process and understand information from different modalities and fuse this information to complete complex tasks. For example, MLLMs can analyze a picture and generate descriptive text, or generate corresponding images according to text descriptions. This cross-modal understanding and generation ability makes MLLMs have broad application prospects in multiple fields.

[0059] It should be noted that the key technologies of large language models can be found in the detailed description in the paper "A Survey of Large Language Models" (paper number: arXiv:2303.18223v16, release date: March 11, 2025, public link: https: / / doi.org / 10.48550 / arXiv.2303.18223), and this specification will not elaborate on it here.

[0060] In this step, the first natural language instruction can be input into the large language model to obtain the first output result output by the large language model. Furthermore, based on the first output result, the created first report can be updated in the second area of the target interface. In different embodiments, the large language model in this step can be different specific types of large language models or large language models with different neural network structures, and this specification does not limit this.

[0061] The second area is the area in the target interface for displaying the generated report and the edited report. In different embodiments, the shape and position of the second area in the target interface can be different. In one embodiment, for example, the second area can be in the middle position of the target interface, and the first area can be on its right.

[0062] In addition to compiling the first report through natural language, the first report can also be edited through visual configuration components. Therefore, in one embodiment, the target interface may further include a third area for displaying the configuration components of the first report. Furthermore, in response to a first preset operation by the user on the configuration components, the first report can be updated in the second area. In a specific embodiment, the first report can be updated in the second area according to the obtained first output result, and the configuration components of the first report can be updated in the first area.

[0063] In different embodiments, the types of configuration components of the first report can be different. In one embodiment, the configuration components of the first report may include one or more of: configuration components for adding, deleting, and modifying fields in the first report, configuration components for calculation metrics obtained by processing the fields, and configuration components for adding, deleting, and modifying data dimensions included in the charts contained in the first report. In different embodiments, the specific types of the first preset operation can also be different. In one embodiment, the first preset operation may include one or more of a drag operation, a click operation, and a typing operation.

[0064] In different embodiments, the specific manner of updating the first report in the second region based on the output result of the large language model may vary. In one embodiment, the large language model may include a first large model, a second large model, and a third large model. Furthermore, based on the setting information in the configuration component, the first configuration text may be determined; the first natural language instruction and the first configuration text are input into the first large model to obtain the user intent, the user intent is input into the second large model to obtain multiple execution steps, and the multiple execution steps are input into the third large model to obtain the display code corresponding to the multiple execution steps; based on the display code, the updated first report is rendered in the second region. In a specific implementation manner, one or more of the historical conversations between the user and the large language model, the user's usage preference information, and the historical operations on the configuration component for the report that are pre-saved may also be obtained and input into the first large model together with the first natural language instruction and the first configuration text. In different specific embodiments, the first large model, the second large model, and the third large model may be large models of the same type or different types of large language models, and this specification does not limit this. Through the above methods, on the one hand, by providing natural language instructions, as well as visualization configuration context and natural language context to the large language model, the quality of the report generated by the large language model can be improved. On the other hand, the report can be generated through the division of labor and cooperation of multiple large language models, reducing the complexity of generating the report by a single large model and further improving the quality of the generated report.

[0065] In an actual production scenario, there are restrictive conditions for specific configuration operations for a specific report. To facilitate user operations. In one embodiment, in response to a first preset operation by the user on the configuration component, the restrictive conditions for the first preset operation may also be displayed in the first region. For example, if the user attempts to drag a text-type field into, for example, one of the Y axes in a dual-axis chart, it may be displayed in the first region that the Y axis of the dual-axis chart should be a numeric array, thus preventing the user from being confused or repeatedly operating after an unsuccessful operation due to not knowing this restriction, and improving the user's operation experience and efficiency.

[0066] In one embodiment, the network parameters of the large language model may also be updated based on the pre-obtained samples of natural language report creation instructions or editing instructions, and the labels corresponding to the samples (correctly created or modified reports). In different embodiments, the specific manner of updating the network parameters of the preset large language model may vary. In one embodiment, for example, all the parameters of the first large model are updated through the backpropagation algorithm. In another embodiment, some parameters of the first large model may also be updated, such as the parameters of the newly added layer, the newly added low-rank parameters, or one or more of the parameters of some existing layers.

[0067] The following uses several specific examples to further illustrate a method for generating reports according to the embodiments of this specification.

[0068] Figure 4 A schematic diagram showing a method for generating a report according to another embodiment of this specification. As Figure 4 shown, for example, it is possible to obtain the natural language instruction “Create a DAU table for service A within N days and represent it as a bar chart” input by the user through the first area, input this instruction into the large language model, and create the DAU (Daily Active Users) table represented as a bar chart in the second area according to the output result of the large language model. Thereafter, the user can also input a natural language report editing instruction through the first area, such as “Change the X-axis to field B”, input this instruction into the large language model, and change the field of the X-axis of the bar chart in the second area to field B according to the output result of the large language model.

[0069] Figure 5 A schematic diagram showing a method for generating a report according to yet another embodiment of this specification. As Figure 5 shown, for example, it is possible to obtain that the user can drag the component in the third area, such as the component for creating chart G2 (for example, a bar chart), to the second area for generating a bar chart in the second area. Thereafter, the user can also input a natural language report editing instruction through the first area, such as “Change the bar color to red”, input this instruction into the large language model, and change the bar color in the bar chart in the second area to red according to the output result of the large language model.

[0070] Figure 6 A schematic diagram showing a method for generating a report according to still another embodiment of this specification. As Figure 5 shown, for example, it is possible to obtain the natural language instruction “Create a DAU table for service A within N days and represent it as a bar chart” input by the user through the first area, input this instruction into the large language model, and create the DAU (Daily Active Users) table represented as a bar chart in the second area according to the output result of the large language model. Thereafter, the user can, for example, drag the configuration component of data field a3 in the third area to the X-axis of the bar chart to change the field of the X-axis of the bar chart to data field a3. It is also possible to input a natural language report editing instruction through the first area, such as “Change the bar color to red”, input this instruction into the large language model, and change the bar color in the bar chart in the second area to red according to the output result of the large language model.

[0071] According to an embodiment of still another aspect, there is also provided a device for generating a report. Figure 7The structural diagram of a device for generating a report according to an embodiment of this specification is shown. As Figure 7 shown, the device 700 includes:

[0072] An acquisition unit 702, configured to acquire a first natural language instruction indicating to edit a first report input by a user through a first area of a target interface;

[0073] An update unit 704, configured to acquire a first natural language instruction indicating to edit the first report input through a first area of the target interface, input the first natural language instruction into the large language model, and update the first report in a second area of the target interface according to the obtained first output result.

[0074] Another aspect of the embodiments of this specification provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed on a computer, the computer is made to execute any one of the above methods.

[0075] Another aspect of the embodiments of this specification provides a computing device, including a memory and a processor. An executable code is stored in the memory. When the processor executes the executable code, any one of the above methods is implemented.

[0076] It should be understood that the descriptions such as "first" and "second" in this article are only used to distinguish similar concepts for the sake of simple description and do not have other limiting effects.

[0077] In the 1990s, it was clearly distinguishable whether an improvement to a technology was an improvement in hardware (e.g., improvement to circuit structures such as diodes, transistors, switches, etc.) or an improvement in software (improvement to method flows). However, with the development of technology, many improvements to method flows today can be regarded as direct improvements to hardware circuit structures. Almost all designers obtain the corresponding hardware circuit structures by programming the improved method flows into the hardware circuits. Therefore, it cannot be said that an improvement to a method flow cannot be implemented using a hardware entity module. For example, a programmable logic device (PLD) (e.g., a field programmable gate array (FPGA)) is such an integrated circuit whose logic function is determined by a user's programming of the device. Designers can program themselves to "integrate" a digital system onto a single PLD without having to ask a chip manufacturer to design and fabricate a dedicated integrated circuit chip. Moreover, nowadays, instead of manually fabricating integrated circuit chips, this programming is mostly implemented using "logic compiler" software, which is similar to the software compiler used in program development and writing. The original code before compilation also has to be written in a specific programming language, which is called a hardware description language (HDL). And there is not only one kind of HDL, but many kinds, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. Currently, the most commonly used are VHDL (Very-High-Speed Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also be aware that by simply making a little logical programming of the method flow using the above-mentioned several hardware description languages and programming it into an integrated circuit, it is easy to obtain the hardware circuit that implements the logical method flow.

[0078] The controller can be implemented in any suitable manner. For example, the controller can take the form of, for example, a microprocessor or a processor and a computer-readable medium storing computer-readable program code (such as software or firmware) executable by the (micro)processor, logic gates, switches, an application specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller. Examples of the controller include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91 SAM, Microchip PIC18F26K20, and Silicone Labs C8051 F320. The memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art also know that in addition to implementing the controller in the form of pure computer-readable program code, it is entirely possible to logically program the method steps to enable the controller to be implemented in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers, etc. to achieve the same function. Therefore, such a controller can be considered a hardware component, and the devices included therein for implementing various functions can also be regarded as the structures within the hardware component. Or even, the devices for implementing various functions can be regarded as either software modules for implementing the method or the structures within the hardware component.

[0079] The systems, devices, modules, or units illustrated in the above embodiments can be specifically implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a server system. Of course, this application does not exclude that with the development of future computer technologies, the computers for implementing the functions of the above embodiments can be, for example, personal computers, laptop computers, in-vehicle human-machine interaction devices, cellular phones, camera phones, smart phones, personal digital assistants, media players, navigation devices, email devices, game consoles, tablet computers, wearable devices, or any combination of these devices.

[0080] Although one or more embodiments of this specification provide method operation steps as described in the embodiments or flowcharts, more or fewer operation steps may be included based on conventional or non-creative means. The order of steps listed in the embodiments is only one way among the execution orders of numerous steps and does not represent the only execution order. When the actual device or terminal product is executing, it may be executed in the order of the method shown in the embodiments or the drawings or executed in parallel (for example, in an environment of parallel processors or multi-threaded processing, or even in a distributed data processing environment). The term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, product or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, product or device. Without further limitation, there is no exclusion of additional identical or equivalent elements in the process, method, product or device comprising the said elements. For example, if terms such as first and second are used to denote names, they do not denote any particular order.

[0081] For convenience of description, when describing the above device, it is divided into various modules according to functions for separate description. Of course, when implementing one or more of this specification, the functions of each module can be implemented in the same or multiple software and / or hardware, or the modules implementing the same function can be realized by a combination of multiple sub-modules or sub-units, etc. The device embodiments described above are only illustrative. For example, the division of the units is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection to each other can be through some interfaces. The indirect coupling or communication connection of the device or unit can be in electrical, mechanical or other forms.

[0082] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate a device for realizing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0083] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to operate in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction means that implements the function specified in one or more of the processes Figure 1 steps or a plurality of steps and / or blocks Figure 1 specified in one or more of the blocks or a plurality of blocks.

[0084] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, such that a series of operational steps are performed on the computer or other programmable apparatus to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable apparatus provide steps for implementing the function specified in one or more of the processes Figure 1 steps or a plurality of steps and / or blocks Figure 1 specified in one or more of the blocks or a plurality of blocks.

[0085] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0086] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory such as read only memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.

[0087] Computer-readable media includes both permanent and non-permanent, removable and non-removable media implemented by any method or technology for storage of information such as computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory (ROM), electrically erasable programmable read only memory (EEPROM), flash memory or other memory technologies, compact disc read only memory (CD-ROM), digital versatile discs (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage, graphene storage or other magnetic storage devices, or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory media such as modulated data signals and carrier waves.

[0088] Those skilled in the art should understand that one or more embodiments of this specification can be provided as a method, a system, or a computer program product. Therefore, one or more embodiments of this specification can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, one or more embodiments of this specification can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0089] One or more embodiments of this specification can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. One or more embodiments of this specification can also be practiced in a distributed computing environment where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0090] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for system embodiments, since they are basically similar to method embodiments, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiments. In the description of this specification, the description of reference terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of this specification. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0091] The above description is only for the embodiments of one or more embodiments of this specification and is not used to limit one or more embodiments of this specification. For those skilled in the art, one or more embodiments of this specification can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this specification shall be included within the scope of the claims.

Claims

1. A method for generating a report, comprising: Obtaining a first natural language instruction indicating the editing of a first report input by a user through a first area of a target interface; Inputting the first natural language instruction into the large language model, and updating the first report in a second area of the target interface according to the obtained first output result.

2. The method according to claim 1, wherein, The target interface further includes a third area for displaying configuration components of the first report; In response to a first preset operation of the user on the configuration components, updating the first report in the second area.

3. The method according to claim 2, wherein, Updating the first report in the second area of the target interface according to the obtained first output result includes: Updating the first report in the second area according to the obtained first output result, and updating configuration components of the first report in the first area.

4. The method according to claim 2, wherein The configuration components of the first report include one or more of: configuration components for adding, deleting, and modifying fields in the first report, configuration components for calculation metrics obtained by applying processing to the fields, and configuration components for adding, deleting, and modifying data dimensions included in the charts included in the first report.

5. The method according to claim 2, wherein, The first preset operation includes one or more of a drag operation, a click operation, and a typing operation.

6. The method according to claim 1, further comprising: In response to a first preset operation of the user on the configuration components, displaying a limitation condition for the first preset operation in the first area.

7. The method according to claim 1, wherein The first report is created through the following process; Obtaining a second natural language instruction indicating the creation of a report input by the user through the first area, inputting the second natural language instruction into a preset large language model, and creating a first report in the second area according to the obtained second output result.

8. The method according to claim 7, further comprising: Before obtaining the second natural language instruction, displaying a prompt instruction for creating a report in the first area; And / or After creating the first report, displaying a prompt instruction for updating the report in the first area.

9. The method according to claim 1, wherein, The first report is created through the following process; In response to a second preset operation of the user on a report creation component in the third area, creating the first report in the second area.

10. The method according to claim 1, wherein, The target interface further includes a third area for displaying configuration components of the first report; The large language model includes a first large model, a second large model, and a third large model; Inputting the first natural language instruction into the large language model, and updating the first report in the second area according to the obtained first output result includes: Determining a first configuration text according to the setting information in the configuration components; Inputting the first natural language instruction and the first configuration text into the first large model to obtain a user intention, inputting the user intention into the second large model to obtain multiple execution steps, and inputting the multiple execution steps into the third large model to obtain display codes corresponding to the multiple execution steps; Rendering and updating the first report in the second area according to the display codes.

11. The method according to claim 10, wherein, Inputting the first natural language instruction and the first configuration text into the first large model includes: Obtain one or more of the historical conversations between the user and the large language model that are pre - saved, the user's usage preference information, and the historical operations on the configuration components for the report, and input them, together with the first natural language instruction and the first configuration text, into the first large model.

12. A device for generating a report, the device comprising: An acquisition unit, configured to acquire a first natural language instruction indicating the editing of a first report input by the user through a first area of the target interface; An update unit, configured to acquire the first natural language instruction indicating the editing of the first report input through the first area of the target interface, input the first natural language instruction into the large language model, and update the first report in a second area of the target interface according to the obtained first output result.

13. A computer - readable storage medium, on which a computer program is stored. When the computer program is executed on a computer, the computer is made to execute the method according to any one of claims 1 - 11.

14. A computing device, comprising a memory and a processor. An executable code is stored in the memory. When the processor executes the executable code, the method according to any one of claims 1 - 11 is implemented.

Images