Data processing method, device and equipment based on large model

Abstract

The invention provides a data processing method, device and equipment based on a large model, and relates to the technical field of artificial intelligence, in particular to the technical fields of intelligent cloud, large models and the like. The data processing method based on the large model comprises the steps of obtaining a target trigger instruction of a target function in a plurality of candidate functions for a target scene through a unified application program; obtaining target input data and target prompt information corresponding to the target function based on the target trigger instruction; inputting the target input data and the target prompt information into a large model to obtain target output data corresponding to the target function output by the large model; and displaying the target output data through the unified application program.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, specifically to the technical fields of intelligent cloud, big models, etc., and in particular to a data processing method, device and equipment based on big models. Background Art

[0002] Big models have been a hot topic in the field of artificial intelligence in recent years. Big models are a type of pre-trained language model that has learned a wealth of language knowledge and world knowledge through pre-training on massive text data, thus being able to achieve amazing results in various natural language processing (NLP) and image generation tasks. Summary of the invention

[0003] The present invention provides a data processing method, device and equipment based on a large model.

[0004] According to one aspect of the present disclosure, a data processing method based on a big model is provided, comprising: obtaining, through a unified application, a target trigger instruction of a target function among multiple candidate functions for a target scenario; based on the target trigger instruction, obtaining target input data and target prompt information corresponding to the target function; inputting the target input data and the target prompt information into a big model to obtain target output data corresponding to the target function output by the big model; and displaying the target output data through the unified application.

[0005] According to another aspect of the present disclosure, a data processing device based on a large model is provided, including: a first acquisition module, used to acquire a target trigger instruction of a target function among multiple candidate functions for a target scenario through a unified application; a second acquisition module, used to acquire target input data and target prompt information corresponding to the target function according to the target trigger instruction; a third acquisition module, used to input the target input data and the target prompt information into the large model to obtain target output data corresponding to the target function output by the large model; and a display module, used to display the target output data through the unified application.

[0006] According to another aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute any method as described in any of the above aspects.

[0007] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute any one of the methods according to any one of the above aspects.

[0008] According to another aspect of the present disclosure, a computer program product is provided, including a computer program, wherein when the computer program is executed by a processor, the computer program implements any one of the methods described in any one of the above aspects.

[0009] The present disclosure can improve data processing efficiency and accuracy.

[0010] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0012] Figure 1 is a schematic diagram according to a first embodiment of the present disclosure;

[0013] Figure 2 is a schematic diagram of an application scenario for implementing the large model-based data processing method provided in an embodiment of the present disclosure;

[0014] Figure 3 is a schematic diagram of a process from different perspectives provided according to an embodiment of the present disclosure;

[0015] Figure 4 is a schematic diagram according to a second embodiment of the present disclosure;

[0016] Figure 5 is a schematic diagram of candidate functions provided according to an embodiment of the present disclosure;

[0017] Figure 6 is a schematic diagram according to a third embodiment of the present disclosure;

[0018] Figure 7 It is a schematic diagram of an electronic device used to implement the large model-based data processing method of an embodiment of the present disclosure. DETAILED DESCRIPTION

[0019] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0020] For specific scenarios, such as telecommunications anti-fraud scenarios, related technologies usually use manual methods to organize data, which results in the need to improve data processing efficiency and accuracy.

[0021] In order to improve data processing efficiency and accuracy, the present disclosure provides the following embodiments.

[0022] Figure 1 is a schematic diagram according to the first embodiment of the present disclosure. This embodiment provides a data processing method based on a large model, the method comprising:

[0023] 101. Obtain a target trigger instruction of a target function from among multiple candidate functions for a target scenario through a unified application.

[0024] 102. Based on the target trigger instruction, obtain target input data and target prompt information corresponding to the target function.

[0025] 103. Input the target input data and the target prompt information into the large model to obtain the target output data corresponding to the target function output by the large model.

[0026] 104. Display the target output data through the unified application.

[0027] Among them, the target scenario refers to the scenario of the data to be processed, such as the telecommunications anti-fraud scenario.

[0028] The target scenario includes multiple candidate functions, and the user can select one or more of the multiple candidate functions as the target function according to their needs.

[0029] The unified application (Application, APP) refers to the APP corresponding to the target scenario. Different candidate functions should correspond to the same APP. The APP can be a mobile APP, a web APP, etc., without limitation.

[0030] In the related art, when data is sorted manually, different functional data usually comes from different systems, so it is necessary for humans to interact with multiple systems, which increases the complexity of the interaction.

[0031] In this embodiment, the interaction is performed through a unified APP, which can simplify the interaction operation and improve the interaction efficiency.

[0032] The function button corresponding to each candidate function can be displayed on the unified APP. After the user clicks a function button, the candidate function corresponding to the clicked function button is used as the target function, and a target trigger instruction of the target function is generated.

[0033] When using the large model, prompt information and input data may be input into the large model to guide the large model to process the input data according to the prompt information to obtain output data.

[0034] In this embodiment, the input data, prompt information and output data corresponding to the target function are respectively referred to as target input data, target prompt information and target output data. Generally speaking, different target functions will correspond to different target input data, target prompt information and target output data.

[0035] The execution subject of the method may be called a data processing system, and the data processing system may be pre-connected to a database, and the database may store data from multiple sources, so as to obtain target input data corresponding to the target function after receiving a target trigger instruction for the target function. Specifically, the target trigger instruction may include a target function identifier, and the data processing system may pre-configure a correspondence between the function identifier and the data type. Therefore, based on the correspondence and the target function identifier included in the target trigger instruction, the target data type corresponding to the target function identifier may be determined, and then the data corresponding to the target data type may be obtained as the target input data.

[0036] In addition, the data processing system can also pre-configure the correspondence between the trigger instruction and the prompt information, and based on the correspondence, the target prompt information corresponding to the target trigger instruction can be obtained. For example, the first trigger instruction corresponds to the first prompt information, and the second trigger instruction corresponds to the second prompt information. If the target trigger instruction is the first trigger instruction, the target prompt information is the first prompt information. The specific content of the first prompt information, the second prompt information, etc. is pre-configured and can be updated. By updating the prompt information, the large model operation can be better guided and the data processing effect can be improved.

[0037] In this way, the data processing system can automatically determine the prompt information according to the trigger instruction generated by the user, without the need for the user to input the prompt information, thereby simplifying user operations and improving processing efficiency.

[0038] After obtaining the target input data and target prompt information, they are input into the large model. The large model processes the target input data based on the target prompt information to obtain the target output data.

[0039] In this way, based on the different target functions, corresponding reasonable and accurate target output data can be obtained.

[0040] After obtaining the target output data, the target output data is displayed to the user.

[0041] In this embodiment, a large model is used to obtain target output data, and the excellent performance of the large model can be used to improve the accuracy of the target output data and improve processing efficiency. In addition, processing is performed through a unified application, rather than each candidate function corresponding to an interactive system, which can simplify interactive operations and improve interactive efficiency. Target input data and target prompt information are obtained based on target trigger instructions, and automatic acquisition of target input data and target prompt information is achieved without the need for user input, which can simplify user operations and improve data processing efficiency.

[0042] In order to better understand the embodiments of the present disclosure, application scenarios to which the embodiments of the present disclosure can be applied are described.

[0043] Figure 2 It is a schematic diagram of an application scenario for implementing the data processing method based on a large model provided by an embodiment of the present disclosure. The scenario includes: a user terminal 201 and a server 202, and the user terminal 201 may include: a personal computer (PC), a mobile device (such as a mobile phone), a tablet computer, a laptop computer, a smart wearable device, etc. The server 202 may be a cloud server or a local server, and the user terminal 201 and the server 202 may communicate using a communication network, and the communication network may include, for example, a wired network and / or a wireless network.

[0044] A unified APP for the target scenario is deployed on the user terminal, and the interaction between the user and the internal processing system is realized through the unified APP. For example, the interactive interface is displayed to the user through the unified APP, and the interactive interface may include a trigger button corresponding to each candidate function of the target scenario. After the user clicks the trigger button of a candidate function, the candidate function clicked by the user is used as the target function, and a target trigger instruction for the target function is generated. The target trigger instruction is sent to the internal processing system deployed on the server. After the internal processing system receives the target trigger instruction, it obtains the target input data and target prompt information corresponding to the target function based on the target trigger instruction, and inputs the target input data and target prompt information into the large model. The large model processes the target input data based on the target prompt information, and the output is the target output data. The large model returns the target output data to the unified APP through the internal processing system, and the unified APP displays it to the user.

[0045] Figure 3 It is a flowchart of different perspectives provided according to an embodiment of the present disclosure.

[0046] like Figure 3 As shown, from the user's perspective: the user interacts with the unified APP. Specifically, the user generates a target trigger instruction through the unified APP, and the target trigger instruction is sent to the internal processing system for processing; and, after the internal processing system obtains the target output data based on the target trigger instruction, the target output data is sent to the unified APP, which is displayed to the user by the unified APP.

[0047] From the perspective of the internal processing system: the internal processing system may include a data service interface, through which it interacts with the unified APP. Specifically, after receiving the target trigger instruction through the data service interface, the target input data corresponding to the target trigger instruction is obtained from the pre-connected database; and, based on the correspondence between the pre-configured trigger instruction and the prompt information, the target prompt information corresponding to the target trigger instruction is obtained. After obtaining the target input data and the target prompt information, they are input into the large model, and the large model processes the target input data based on the target prompt information to obtain the target output data. Afterwards, the target output data is sent to the unified APP through the data service interface and displayed to the user by the unified APP.

[0048] In combination with the above application scenarios, the present disclosure also provides the following embodiments.

[0049] Figure 4 is a schematic diagram according to a second embodiment of the present disclosure. This embodiment provides a data processing method based on a large model, the method comprising:

[0050] 401. Displaying an interactive interface to a user through a unified application, wherein the interactive interface includes candidate function buttons corresponding to multiple candidate functions of a target scenario;

[0051] 402. Based on a click operation of the user on the candidate function button, the candidate function corresponding to the click operation is used as a target function, and a target trigger instruction for the target function is generated.

[0052] In this embodiment, candidate function buttons are displayed through an interactive interface, and the candidate function corresponding to the user's click operation is used as the target function, and a corresponding target trigger instruction is generated, so that the target function can be determined and the target trigger instruction can be obtained simply and efficiently.

[0053] 403. Acquire the target input data corresponding to the target trigger instruction from a plurality of source data recorded in a pre-connected database.

[0054] 404. Based on the pre-configured correspondence between the trigger instruction and the prompt information, obtain target prompt information corresponding to the target trigger instruction.

[0055] In this embodiment, by connecting with a database and recording data from multiple sources in the database, basic data can be provided for the target function, so that the target input data can be obtained in a timely manner.

[0056] Furthermore, based on the correspondence between the pre-configured trigger instructions and the data types, a target data type corresponding to the target trigger instruction can be obtained from the multiple source data; and the data corresponding to the target data type can be used as the target input data.

[0057] In this embodiment, the target data type corresponding to the target trigger instruction is obtained based on the correspondence between the trigger instruction and the data type, and then the data corresponding to the target data type is obtained as the target input data, so that the target input data can be obtained simply and efficiently.

[0058] 405. Input the target input data and the target prompt information into the large model to obtain the target output data corresponding to the target function output by the large model.

[0059] 406. Display the target output data through the unified application.

[0060] Figure 5 It is a schematic diagram of candidate functions provided according to an embodiment of the present disclosure.

[0061] like Figure 5 As shown, the multiple candidate functions include: preliminary processing function, mind map generation function, address reasoning function and report generation function.

[0062] The user clicks on one of the multiple candidate functions as the target function according to his or her own needs and generates a target trigger instruction. After that, the target input data corresponding to the target trigger instruction is obtained from the database, and the target prompt information corresponding to the target trigger instruction is obtained based on the pre-configured corresponding relationship. Then, the large model is called to obtain the target output data based on the target input data and the target prompt information.

[0063] Usually, under different target functions, the corresponding target input data, target prompt information, and target output data are different.

[0064] For example, if the target function is a preliminary processing function:

[0065] The corresponding target input data may include: original event data corresponding to the target scene;

[0066] Take the target scenario of telecommunications anti-fraud as an example: the original event data can be the case text data obtained based on the alarm information.

[0067] Accordingly, the target prompt information is used to trigger the understanding and summarizing capabilities of the large model.

[0068] For example, the target prompt information is information that triggers the understanding and summarizing ability of the large model, and the specific content is configurable, such as "Please summarize the data based on the following data, extract the elements, and give suggestions on whether to process it."

[0069] The target output data includes: summary data of the original event data, and / or element data extracted from the original event data.

[0070] For example, the target output data includes summary data and element data. Summary data, for example, summarizes the long text case text data into a short text of 1-2 sentences and gives suggestions on whether to investigate the case; element data is extracted from the long text, such as relevant personnel, mobile phone numbers, crime scene address, etc.

[0071] In this embodiment, for the preliminary processing function, the understanding and summarizing capabilities of the large model can be used to provide intuitive and concise information for user reference, thereby improving the processing effect.

[0072] For example, if the target function is to generate a mind map:

[0073] The corresponding target input data may include: original event data corresponding to the target scene, and associated data related to the original event data.

[0074] For example, based on the above target scenario example: the original event data is case text data, and the associated data may include: transcript text data, on-site investigation data, third-party data (such as takeaway data, address library data, express delivery data, etc.), etc.

[0075] The target prompt information is used to trigger the reasoning ability of the large model.

[0076] The specific content of the target prompt information is configurable, such as "Please generate a mind map for the case based on the following data."

[0077] Accordingly, the target output data may include: a mind map; the mind map is used to describe the processing flow for the target scenario.

[0078] For example, based on the above target prompt information, the large model can infer the above target input data (such as original event data and its related data) and output a mind map representing the processing flow.

[0079] In addition, in order to improve the reasoning ability of mind maps, when fine-tuning the large model, the knowledge of domain experts can be used to generate mind map samples, and then fine-tune the large model. This effectively precipitates the knowledge of domain experts and improves the accuracy of the mind maps generated by the large model.

[0080] In this embodiment, for mind map generation, the reasoning ability of the large model can be used to generate the mind map based on multi-source data. Compared with the method of manually drawing the mind map, the processing efficiency and accuracy can be improved.

[0081] For another example, if the target function is address reasoning function:

[0082] The corresponding target input data may include: third-party data.

[0083] For example, based on the above target scenario example: third-party data may include takeaway data, address library data, express delivery data, operator base station data, etc.

[0084] The target prompt information is used to trigger the reasoning capability of the large model.

[0085] The specific content is configurable, such as "Please infer the address of the target object based on the following data."

[0086] Accordingly, the target output data may include: address data of a target object involved in the target scene.

[0087] For example, the target output data includes: the latest address of the suspected object. Specifically, the large model can take the intersection of the express delivery data and the operator base station data to obtain the address data of the suspected object.

[0088] In this embodiment, for address reasoning, the reasoning ability of the large model can be used to obtain the address information of the target object, which is beneficial to event processing of the target scene and then quickly obtains the event processing result.

[0089] For another example, if the target function is a report generation function:

[0090] The target input data may include: processing process data for the target scenario.

[0091] For example, based on the above target scenario example: the processing data may include: case text data, transcript text data of the parties involved, etc. The report data may include: case closing report, investigation report, etc.

[0092] The target prompt information is used to trigger the generation capability of the large model.

[0093] The specific content of the target prompt information is configurable, such as "Generate a report based on the following data."

[0094] Correspondingly, the target output data includes: report data, and the report data is used to describe the processing process and results of the target scenario.

[0095] For example, according to the different contents of the target prompt information, various required types of reports such as analysis reports and conclusion reports can be generated.

[0096] In this embodiment, for report generation, the generation capability of the large model can be used to automatically generate various reports to improve processing effects.

[0097] Figure 6 is a schematic diagram according to the third embodiment of the present disclosure. This embodiment provides a data processing device based on a large model, such as Figure 6 As shown, the device 600 includes: a first acquisition module 601 , a second acquisition module 602 , a third acquisition module 603 and a display module 604 .

[0098] The first acquisition module 601 is used to obtain the target trigger instruction of the target function among multiple candidate functions for the target scene through a unified application; the second acquisition module 602 is used to obtain the target input data and target prompt information corresponding to the target function according to the target trigger instruction; the third acquisition module 603 is used to input the target input data and the target prompt information into the large model to obtain the target output data corresponding to the target function output by the large model; the display module 604 is used to display the target output data through the unified application.

[0099] In this embodiment, a large model is used to obtain target output data, and the excellent performance of the large model can be used to improve the accuracy of the target output data and improve processing efficiency. In addition, processing is performed through a unified application, rather than each candidate function corresponding to an interactive system, which can simplify interactive operations and improve interactive efficiency. Target input data and target prompt information are obtained based on target trigger instructions, and automatic acquisition of target input data and target prompt information is achieved without the need for user input, which can simplify user operations and improve data processing efficiency.

[0100] In some embodiments, the first acquisition module 601 is further used to:

[0101] By means of a unified application, an interactive interface is presented to the user, wherein the interactive interface includes candidate function buttons corresponding to a plurality of candidate functions of the target scenario;

[0102] Based on a user's click operation on the candidate function button, the candidate function corresponding to the click operation is used as a target function, and a target trigger instruction for the target function is generated.

[0103] In this embodiment, candidate function buttons are displayed through an interactive interface, and the candidate function corresponding to the user's click operation is used as the target function, and a corresponding target trigger instruction is generated, so that the target function can be determined and the target trigger instruction can be obtained simply and efficiently.

[0104] In some embodiments, the second acquisition module 602 is further used to:

[0105] Acquire the target input data corresponding to the target trigger instruction from a plurality of source data recorded in a pre-connected database; and / or,

[0106] Based on the pre-configured correspondence between the trigger instruction and the prompt information, the target prompt information corresponding to the target trigger instruction is obtained.

[0107] In this embodiment, by connecting with a database and recording data from multiple sources in the database, basic data can be provided for the target function, so that the target input data can be obtained in a timely manner.

[0108] In some embodiments, the second acquisition module 602 is further used to:

[0109] Based on the pre-configured correspondence between the trigger instruction and the data type, acquiring a target data type corresponding to the target trigger instruction from the multiple source data;

[0110] The data corresponding to the target data type is used as the target input data.

[0111] In this embodiment, the target data type corresponding to the target trigger instruction is obtained based on the correspondence between the trigger instruction and the data type, and then the data corresponding to the target data type is obtained as the target input data, so that the target input data can be obtained simply and efficiently.

[0112] In some embodiments, if the target function is a preliminary processing function, the target input data, the target prompt information, and the target output data satisfy at least one of the following items:

[0113] The target input data includes: original event data corresponding to the target scene;

[0114] The target prompt information is used to trigger the understanding and summarizing ability of the large model;

[0115] The target output data includes: summary data of the original event data, and / or element data extracted from the original event data.

[0116] In this embodiment, for the preliminary processing function, the understanding and summarizing capabilities of the large model can be used to provide intuitive and concise information for user reference, thereby improving the processing effect.

[0117] In some embodiments, if the target function is a mind map generation function, the target input data, the target prompt information, and the target output data satisfy at least one of the following items:

[0118] The target input data includes: original event data corresponding to the target scene, and associated data related to the original event data;

[0119] The target prompt information is used to trigger the reasoning ability of the large model;

[0120] The target output data includes: a mind map; the mind map is used to describe the processing flow for the target scenario.

[0121] In this embodiment, for mind map generation, the reasoning ability of the large model can be used to generate the mind map based on multi-source data. Compared with the method of manually drawing the mind map, the processing efficiency and accuracy can be improved.

[0122] In some embodiments, if the target function is an address reasoning function, the target input data, the target prompt information, and the target output data satisfy at least one of the following items:

[0123] The target input data includes: third-party data;

[0124] The target prompt information is used to trigger the reasoning ability of the large model;

[0125] The target output data includes: address data of a target object involved in the target scene.

[0126] In this embodiment, for address reasoning, the reasoning ability of the large model can be used to obtain the address information of the target object, which is beneficial to event processing of the target scene and then quickly obtains the event processing result.

[0127] In some embodiments, if the target function is a report generation function, the target input data, the target prompt information, and the target output data satisfy at least one of the following items:

[0128] The target input data includes: processing process data for the target scenario;

[0129] The target prompt information is used to trigger the generation capability of the large model;

[0130] The target output data includes: report data, and the report data is used to describe the processing process and results of the target scenario.

[0131] In this embodiment, for report generation, the generation capability of the large model can be used to automatically generate various reports to improve processing effects.

[0132] It can be understood that in the embodiments of the present disclosure, the same or similar contents in different embodiments can be referenced to each other.

[0133] It can be understood that the “first”, “second”, etc. in the embodiments of the present disclosure are only used for distinction and do not indicate the degree of importance, time sequence, etc.

[0134] It is understandable that, unless otherwise specified, the order of the steps in the process indicates that the timing relationship between these steps is not limited.

[0135] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0136] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0137] Figure 7 A schematic block diagram of an example electronic device 700 that can be used to implement an embodiment of the present disclosure is shown. The electronic device 700 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0138] like Figure 7 As shown, the electronic device 700 includes a computing unit 701, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 702 or a computer program loaded from a storage unit 708 into a random access memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the electronic device 700 can also be stored. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0139] Multiple components in the electronic device 700 are connected to the I / O interface 705, including: an input unit 706, such as a keyboard, a mouse, etc.; an output unit 707, such as various types of displays, speakers, etc.; a storage unit 708, such as a disk, an optical disk, etc.; and a communication unit 709, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 709 allows the electronic device 700 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0140] The computing unit 701 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 701 performs the various methods and processes described above, such as a data processing method based on a large model. For example, in some embodiments, the data processing method based on a large model may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 708. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 700 via ROM 702 and / or communication unit 707. When the computer program is loaded into RAM 703 and executed by the computing unit 701, one or more steps of the data processing method based on the large model described above may be performed. Alternatively, in other embodiments, the computing unit 701 may be configured to perform a data processing method based on a large model in any other appropriate manner (e.g., by means of firmware).

[0141] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0142] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0143] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0144] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0145] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0146] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services ("Virtual Private Server", or "VPS" for short). The server may also be a server of a distributed system, or a server combined with a blockchain.

[0147] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0148] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A data processing method based on a large model, comprising: Obtaining a target trigger instruction of a target function from among multiple candidate functions for a target scenario through a unified application; Based on the target trigger instruction, obtaining target input data and target prompt information corresponding to the target function; Inputting the target input data and the target prompt information into the large model to obtain the target output data corresponding to the target function output by the large model; The target output data is displayed through the unified application.

2. The method according to claim 1, wherein: The step of obtaining a target trigger instruction of a target function from among multiple candidate functions for a target scenario through a unified application program includes: By means of a unified application, an interactive interface is presented to the user, wherein the interactive interface includes candidate function buttons corresponding to a plurality of candidate functions of the target scenario; Based on a user's click operation on the candidate function button, the candidate function corresponding to the click operation is used as a target function, and a target trigger instruction for the target function is generated.

3. The method according to claim 1, wherein: The acquiring, based on the target trigger instruction, target input data and target prompt information corresponding to the target function, includes: Acquire the target input data corresponding to the target trigger instruction from a plurality of source data recorded in a pre-connected database; and / or, Based on the pre-configured correspondence between the trigger instruction and the prompt information, the target prompt information corresponding to the target trigger instruction is obtained.

4. The method according to claim 3, wherein: The step of acquiring the target input data corresponding to the target trigger instruction from the multiple source data recorded in the pre-connected database includes: Based on the pre-configured correspondence between the trigger instruction and the data type, acquiring a target data type corresponding to the target trigger instruction from the multiple source data; The data corresponding to the target data type is used as the target input data.

5. The method according to any one of claims 1 to 4, wherein: If the target function is a preliminary processing function, the target input data, the target prompt information and the target output data satisfy at least one of the following items: The target input data includes: original event data corresponding to the target scene; The target prompt information is used to trigger the understanding and summarizing ability of the large model; The target output data includes: summary data of the original event data, and / or element data extracted from the original event data.

6. The method according to any one of claims 1 to 4, wherein: If the target function is a mind map generation function, the target input data, the target prompt information and the target output data satisfy at least one of the following items: The target input data includes: original event data corresponding to the target scene, and associated data related to the original event data; The target prompt information is used to trigger the reasoning ability of the large model; The target output data includes: a mind map; the mind map is used to describe the processing flow for the target scenario.

7. The method according to any one of claims 1 to 4, wherein: If the target function is an address inference function, the target input data, the target prompt information, and the target output data satisfy at least one of the following items: The target input data includes: third-party data; The target prompt information is used to trigger the reasoning ability of the large model; The target output data includes: address data of a target object involved in the target scene.

8. The method according to any one of claims 1 to 4, wherein: If the target function is a report generation function, the target input data, the target prompt information, and the target output data satisfy at least one of the following items: The target input data includes: processing process data for the target scenario; The target prompt information is used to trigger the generation capability of the large model; The target output data includes: report data, and the report data is used to describe the processing process and results of the target scenario.

9. A data processing device based on a large model, comprising: A first acquisition module is used to acquire a target trigger instruction of a target function from among multiple candidate functions for a target scenario through a unified application program; A second acquisition module, used to acquire target input data and target prompt information corresponding to the target function according to the target trigger instruction; A third acquisition module is used to input the target input data and the target prompt information into the large model to obtain the target output data corresponding to the target function output by the large model; A display module is used to display the target output data through the unified application.

10. The device according to claim 9, wherein: The first acquisition module is further used for: By means of a unified application, an interactive interface is presented to the user, wherein the interactive interface includes candidate function buttons corresponding to a plurality of candidate functions of the target scenario; Based on a user's click operation on the candidate function button, the candidate function corresponding to the click operation is used as a target function, and a target trigger instruction for the target function is generated.

11. The device according to claim 9, wherein: The second acquisition module is further used for: Acquire the target input data corresponding to the target trigger instruction from a plurality of source data recorded in a pre-connected database; and / or, Based on the pre-configured correspondence between the trigger instruction and the prompt information, the target prompt information corresponding to the target trigger instruction is obtained.

12. The device according to claim 11, wherein The second acquisition module is further used for: Based on the pre-configured correspondence between the trigger instruction and the data type, acquiring a target data type corresponding to the target trigger instruction from the multiple source data; The data corresponding to the target data type is used as the target input data.

13. The device according to any one of claims 9 to 12, wherein: If the target function is a preliminary processing function, the target input data, the target prompt information and the target output data satisfy at least one of the following items: The target input data includes: original event data corresponding to the target scene; The target prompt information is used to trigger the understanding and summarizing ability of the large model; The target output data includes: summary data of the original event data, and / or element data extracted from the original event data.

14. The device according to any one of claims 9 to 12, wherein: If the target function is a mind map generation function, the target input data, the target prompt information and the target output data satisfy at least one of the following items: The target input data includes: original event data corresponding to the target scene, and associated data related to the original event data; The target prompt information is used to trigger the reasoning ability of the large model; The target output data includes: a mind map; the mind map is used to describe the processing flow for the target scenario.

15. The device according to any one of claims 9 to 12, wherein: If the target function is an address inference function, the target input data, the target prompt information, and the target output data satisfy at least one of the following items: The target input data includes: third-party data; The target prompt information is used to trigger the reasoning ability of the large model; The target output data includes: address data of a target object involved in the target scene.

16. The device according to any one of claims 9 to 12, wherein: If the target function is a report generation function, the target input data, the target prompt information, and the target output data satisfy at least one of the following items: The target input data includes: processing process data for the target scenario; The target prompt information is used to trigger the generation capability of the large model; The target output data includes: report data, and the report data is used to describe the processing process and results of the target scenario.

17. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 8.

18. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-8.

19. A computer program product, comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 8.

Images