Information processing method and device in electric power scene, equipment and storage medium

Abstract

The invention relates to an information processing method and device in an electric power scene, equipment and a storage medium, and relates to the technical field of artificial intelligence. The method comprises the following steps: acquiring power questioning information input by a user in a power scene; inputting the electric power question information into a trained electric power question and answer large model, and determining a target electric power business intention category to which the electric power question information belongs from a plurality of preset candidate electric power business intention categories through the electric power question and answer large model; the large power question and answer model comprises business processing units corresponding to a plurality of candidate power business intention categories; and processing the power question information through a business processing unit corresponding to the target power business intention category to generate power answer information for the power question information. By adopting the method, the information processing efficiency in an electric power scene can be improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to an information processing method, device, equipment and storage medium in an electric power scenario. Background Art

[0002] With the development of computer technology, many power companies have developed exclusive power question and answer systems for each power business. The power question and answer system for power business can assist power industry staff in performing related power operations to improve power operation efficiency and bring greater benefits to power companies. In traditional technology, the power question and answer system in the power industry is mainly based on the search system of structured databases and combined with traditional NLP (Natural Language Processing) technology to implement each power business. However, the traditional power question and answer system is not intelligent enough and can only do some simple question and answer searches, and can only read and process structured information. The processing ability of unstructured information (such as pictures, voice, text, etc.) is poor, resulting in low information processing efficiency in power scenarios. Summary of the invention

[0003] Based on this, it is necessary to provide an information processing method, device, equipment and storage medium in an electric power scenario that can improve information processing efficiency in response to the above technical problems.

[0004] In a first aspect, the present application provides an information processing method in an electric power scenario, the method comprising:

[0005] Obtaining power question information input by users in power scenarios;

[0006] The power question information is input into the trained power question and answer big model, so as to determine the target power business intention category to which the power question information belongs from a plurality of preset candidate power business intention categories through the power question and answer big model; the power question and answer big model includes business processing units corresponding to each of the plurality of candidate power business intention categories;

[0007] The power question information is processed by a service processing unit corresponding to the target power service intention category to generate power answer information for the power question information.

[0008] In a second aspect, the present application provides an information processing device in an electric power scenario, the device comprising:

[0009] An acquisition module is used to acquire power question information input by a user in a power scenario;

[0010] A determination module, used for inputting the power question information into a trained power question and answer big model, so as to determine the target power business intention category to which the power question information belongs from a plurality of preset candidate power business intention categories through the power question and answer big model; the power question and answer big model includes business processing units corresponding to each of the plurality of candidate power business intention categories;

[0011] A generating module is used to process the power question information through a business processing unit corresponding to the target power business intention category to generate power answer information for the power question information.

[0012] In one embodiment, the power question and answer big model is a power multimodal question and answer big model; the power question information includes at least one of power question text information, power question voice information or power question visual information.

[0013] In one embodiment, the plurality of candidate power business intent categories include a power data chart generation category, a power picture and power presentation retrieval category, a power text map category, a power picture target defect detection category, a power intelligent search category, and a power text generation category.

[0014] In one embodiment, the acquisition module is also used to acquire historical power questioning information of the power questioning information, and to acquire historical power answer information for the historical power questioning information; the generation module is also used to process the power questioning information based on the historical power questioning information and the historical power answer information through the business processing unit corresponding to the target power business intention category, so as to generate power answer information for the power questioning information.

[0015] In one embodiment, the apparatus further comprises:

[0016] A training module is used to obtain multiple power training sample pairs under the power scenario; each of the power training sample pairs includes a power question sample information and a power answer sample information for the power question sample information; the power question sample information is input into the power question and answer big model to be trained, so as to generate power answer prediction information for the power question sample information based on the power question sample information through the power question and answer big model to be trained; and the power question and answer big model to be trained is trained through the difference between the power answer prediction information and the power answer sample information to obtain the trained power question and answer big model.

[0017] In one embodiment, the power question and answer big model to be trained is a power multimodal question and answer big model to be trained; the power question sample information includes at least one of power question text sample information, power question voice sample information or power question visual sample information.

[0018] In a third aspect, the present application provides a computer device including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the steps in the method embodiments of the present application are implemented.

[0019] In a fourth aspect, the present application provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps in the method embodiments of the present application.

[0020] In a fifth aspect, the present application provides a computer program product, including a computer program, which implements the steps in the method embodiments of the present application when the computer program is executed by a processor.

[0021] The above-mentioned information processing method, device, equipment and storage medium in the power scenario obtains the power question information input by the user in the power scenario; inputs the power question information into the trained power question and answer big model, so as to determine the target power business intention category to which the power question information belongs from multiple preset candidate power business intention categories through the power question and answer big model; the power question and answer big model contains business processing units corresponding to multiple candidate power business intention categories; the power question information is processed by the business processing unit corresponding to the target power business intention category to generate power answer information for the power question information. Compared with the traditional power question and answer system, the present application can directly generate rich and accurate power answer information for the power question information by inputting structured or unstructured power question information into the trained power question and answer big model through the powerful information understanding and generation capabilities of the power question and answer big model, thereby improving the information processing efficiency in the power scenario. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 An application environment diagram of an information processing method in an electric power scenario in an embodiment;

[0023] Figure 2 It is a flowchart of an information processing method in a power scenario in one embodiment;

[0024] Figure 3 A schematic diagram of a framework of a large power question-and-answer model in one embodiment;

[0025] Figure 4 A schematic diagram of a chatbot architecture with a unified micro-entry in one embodiment;

[0026] Figure 5 A schematic diagram of the training and application process of a large electric power question-answering model in one embodiment;

[0027] Figure 6 is a structural block diagram of an information processing device in an electric power scenario in an embodiment;

[0028] Figure 7 is a structural block diagram of an information processing device in an electric power scenario in another embodiment;

[0029] Figure 8 is an internal structure diagram of a computer device in one embodiment;

[0030] FIG. 9 is a diagram showing the internal structure of a computer device in another embodiment. DETAILED DESCRIPTION

[0031] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0032] The information processing method in the power scenario provided in this application can be applied to Figure 1 In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can be set up separately and can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other servers. Among them, the terminal 102 can be, but is not limited to, various desktop computers, laptops, smart phones, tablet computers, vehicle-mounted terminals, intelligent voice interaction devices, aircraft, smart home appliances and portable wearable devices. Smart home appliances can be smart speakers, smart TVs and smart air conditioners. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The server 104 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, cloud security, host security and other network security services, CDN, and basic cloud computing services such as big data and artificial intelligence platforms. The terminal 102 and the server 104 can be directly or indirectly connected by wired or wireless communication, and this application is not limited here.

[0033] The server 104 can obtain the power question information input by the user in the power scenario from the terminal 102, and input the power question information into the trained power question and answer big model, so as to determine the target power business intention category to which the power question information belongs from the preset multiple candidate power business intention categories through the power question and answer big model; the power question and answer big model contains business processing units corresponding to each of the multiple candidate power business intention categories. The server 104 can process the power question information through the business processing unit corresponding to the target power business intention category to generate power answer information for the power question information.

[0034] It is understood that the process of generating the power answer information can also be independently implemented by the terminal 102 after the terminal 102 obtains the power question information, and this embodiment does not limit this. It is understood that Figure 1 The application scenarios are only for illustration and are not limited to this.

[0035] In one embodiment, Figure 2 As shown, a method for information processing in an electric power scenario is provided, which can be applied to a computer device, which can be a terminal or a server, that is, the method can be executed by the terminal or the server alone, or can be implemented through interaction between the terminal and the server. It can be understood that the computer device can be an electric power device in the electric power industry, for example, the electric power device can specifically be a power distribution device for power supply or distribution. This embodiment is described by taking the method applied to a computer device as an example, and includes the following steps:

[0036] Step 202: Obtain power question information input by the user in the power scenario.

[0037] The power question information is the question information input by the user in the power scenario. The power question information includes at least one of power question text information, power question voice information, or power question visual information. It can be understood that the power question information can be a question sentence used to ask questions in the power scenario, or a declarative sentence used to indicate content query or content generation.

[0038] Step 204, input the power question information into the trained power question and answer big model, so as to determine the target power business intention category to which the power question information belongs from a plurality of preset candidate power business intention categories through the power question and answer big model; the power question and answer big model includes business processing units corresponding to each of the plurality of candidate power business intention categories.

[0039] Among them, the power question-answering big model is a big model used for question-answering in power scenarios. The power question-answering big model is implemented based on a large-scale language model.

[0040] Specifically, the electric power question and answer big model is pre-set with business processing units corresponding to multiple candidate electric power business intention categories. It can be understood that the business processing units corresponding to different candidate electric power business intention categories have different business processing capabilities. The computer device can input the electric power question information into the trained electric power question and answer big model to analyze the electric power question information through the electric power question and answer big model, and determine the target electric power business intention category to which the electric power question information belongs from the preset multiple candidate electric power business intention categories. It can be understood that the target electric power business intention category is any one of the multiple candidate electric power business intention categories contained in the electric power question and answer big model.

[0041] Step 206 : Process the power question information through the service processing unit corresponding to the target power service intention category to generate power answer information for the power question information.

[0042] In one embodiment, the computer device may collect power question information, collect power answer information for the power question information, and analyze and correct the collected power answer information for the power question information. Furthermore, the computer device may further fine-tune the trained power question and answer big model through the collected power question information and the corrected power answer information for the power question information, so as to further improve the accuracy of the power answer information generated by the power question and answer big model.

[0043] In the above-mentioned information processing method in the power scenario, the power question information input by the user in the power scenario is obtained; the power question information is input into the trained power question and answer big model, so as to determine the target power business intention category to which the power question information belongs from multiple preset candidate power business intention categories through the power question and answer big model; the power question and answer big model contains business processing units corresponding to multiple candidate power business intention categories; the power question information is processed by the business processing unit corresponding to the target power business intention category to generate power answer information for the power question information. Compared with the traditional power question and answer system, the present application can directly generate rich and accurate power answer information for the power question information by inputting structured or unstructured power question information into the trained power question and answer big model through the powerful information understanding and generation capabilities of the power question and answer big model, thereby improving the information processing efficiency in the power scenario.

[0044] In addition, the traditional information processing method in the power scenario requires the development of a dedicated power question-and-answer system for each power business, which results in a waste of human resources and computer resources, and is not conducive to the unified management of the power question-and-answer system, resulting in low efficiency in the question-and-answer of power information. However, this application can provide a unified inquiry portal for multiple power businesses through a trained power question-and-answer large model, and can provide question-and-answer services for different power businesses, avoiding the waste of human resources and computer resources, and is also conducive to the unified management of the power question-and-answer system, thereby improving the efficiency of the question-and-answer of power information.

[0045] In one embodiment, the power question and answer big model is a power multimodal question and answer big model; the power question information includes at least one of power question text information, power question voice information or power question visual information.

[0046] In one embodiment, a computer device may obtain power question information input by a user in a power scenario, wherein the power question information includes at least one of power question text information, power question voice information, or power question visual information. The computer device may input the power question information into a trained power multimodal question-answering large model, so as to determine the target power business intention category to which the power question information belongs from a plurality of preset candidate power business intention categories through the power multimodal question-answering large model; the power multimodal question-answering large model includes business processing units corresponding to each of the plurality of candidate power business intention categories. The computer device may process the power question information through the business processing unit corresponding to the target power business intention category to generate power answer information for the power question information. It can be understood that multimodality refers to information in several modes such as text, voice, and vision (including images and videos).

[0047] In the above embodiment, the large model of electric power multimodal question and answer can process electric power question information in multiple modes and generate electric power answer information. Compared with the processing method of electric power question information that only supports the input of a single mode, the efficiency of question and answer in electric power scenarios and the richness of question and answer forms are improved.

[0048] In one embodiment, the plurality of candidate power business intent categories include a power data chart generation category, a power picture and power presentation retrieval category, a power text map category, a power picture target defect detection category, a power intelligent search category, and a power text generation category.

[0049] In one embodiment, Figure 3As shown, the implementation framework of the information processing method in the power scenario of the present application includes an interactive message unit, a power question and answer big model and a data iteration unit. The power question and answer big model includes a power data chart generation unit, a power picture and power presentation retrieval unit, a power cultural graph unit, a power picture target defect detection unit, a power intelligent search unit and a power text generation unit. Among them, the power data chart generation unit is a business processing unit corresponding to the power data chart generation category. The power picture and power presentation retrieval unit is a business processing unit corresponding to the power picture and power presentation retrieval category. The power cultural graph unit is a business processing unit corresponding to the power cultural graph category. The power picture target defect detection unit is a business processing unit corresponding to the power picture target defect detection category. The power intelligent search unit is a business processing unit corresponding to the power intelligent search category. The power text generation unit is a business processing unit corresponding to the power text generation category.

[0050] Continue to see Figure 3 It can be understood that the interactive message unit can be used to realize the communication between the user's terminal and the power question and answer big model, that is, the interactive message unit can receive the power question information input by the user and send the power question information to the power question and answer big model. The power question and answer big model can be used to generate power answer information for the power question information input by the user. The data iteration unit can be used to collect power question information and power answer information, and further optimize and train the power question and answer big model based on the collected power question information and power answer information, so as to further improve the accuracy of the power answer information generated by the power question and answer big model.

[0051] In one embodiment, Figure 4 As shown, the present application provides a unified micro-entry for power data chart generation services, power image and power presentation retrieval services, power cultural image services, power image target defect detection services, power intelligent search services, and power text generation services, and uses the same power question and answer big model to achieve unified power answer information output.

[0052] In one embodiment, the computer device can also integrate the power question and answer big model with other power services in the power scenario to provide a unified micro-entry and unified output.

[0053] In the above embodiment, a trained large power question and answer model is used to provide a unified inquiry portal and question and answer service for power data chart generation business, power image and power presentation retrieval business, power cultural image business, power image target defect detection business, power intelligent search business and power text generation business, thereby avoiding the waste of human resources and computer resources, and is also conducive to the unified management of the power question and answer system, thereby improving the question and answer efficiency of power information.

[0054] In one embodiment, the method also includes: obtaining historical power questioning information of power questioning information, and obtaining historical power answer information for the historical power questioning information; processing the power questioning information through a business processing unit corresponding to a target power business intention category to generate power answer information for the power questioning information, including: processing the power questioning information based on the historical power questioning information and the historical power answer information through a business processing unit corresponding to a target power business intention category to generate power answer information for the power questioning information.

[0055] In one embodiment, the computer device may obtain the power question information input by the user in the power scenario, obtain the historical power question information of the power question information, and obtain the historical power answer information for the historical power question information. The computer device may input the power question information, the historical power question information, and the historical power answer information into the trained power question and answer big model, so as to determine the target power business intention category to which the power question information belongs from a plurality of preset candidate power business intention categories through the power question and answer big model. The computer device may process the power question information based on the historical power question information and the historical power answer information through the business processing unit corresponding to the target power business intention category, so as to generate power answer information for the power question information.

[0056] In the above embodiment, by combining the historical power question information and the historical power answer information of the current question, more abundant basis information can be provided for the generation of the current power answer information, thereby further improving the accuracy of the power answer information finally generated.

[0057] In one embodiment, the method also includes: obtaining multiple power training sample pairs under the power scenario; each power training sample pair includes a power question sample information and a power answer sample information for the power question sample information; inputting the power question sample information into the power question and answer big model to be trained, so as to generate power answer prediction information for the power question sample information based on the power question sample information through the power question and answer big model to be trained; training the power question and answer big model to be trained through the difference between the power answer prediction information and the power answer sample information, and obtaining the trained power question and answer big model.

[0058] In one embodiment, the computer device can determine the loss value through the difference between the power answer prediction information and the power answer sample information, and iteratively train the power question and answer large model to be trained in the direction of reducing the loss value until the iteration stop condition is met, thereby obtaining the trained power question and answer large model. The iteration stop condition can specifically be that the number of iterations reaches a preset number of iterations, or that the loss value is less than a preset loss value.

[0059] In the above embodiment, by training the power question and answer big model with multiple power training samples in the power scenario, a power question and answer big model suitable for the power scenario can be obtained, thereby ensuring the accuracy of the power answer information generated by the power question and answer big model.

[0060] In one embodiment, the power question and answer big model to be trained is a power multimodal question and answer big model to be trained; the power question sample information includes at least one of power question text sample information, power question voice sample information or power question visual sample information.

[0061] In one embodiment, Figure 5 As shown, the computer device can obtain multiple power training sample pairs in the power scenario; each power training sample pair includes a power question sample information and a power answer sample information for the power question sample information. The power question sample information includes at least one of power question text sample information, power question voice sample information, or power question visual sample information. The computer device can input the power question sample information into the power multimodal question and answer large model to be trained, so as to generate power answer prediction information for the power question sample information based on the power question sample information through the power multimodal question and answer large model to be trained. The computer device can fine-tune the power multimodal question and answer large model to be trained through the difference between the power answer prediction information and the power answer sample information, and obtain the trained power multimodal question and answer large model. It can be understood that the power question information input by the user is input into the trained power multimodal question and answer large model, and the power answer information for the power question information can be output.

[0062] In the above embodiment, the large model of electric power multimodal question and answer to be trained can process the electric power question sample information in multiple modes to generate electric power answer sample information. Compared with the processing method of electric power question sample information that only supports the input of a single mode, the efficiency of question and answer in the electric power scenario and the richness of question and answer forms are improved.

[0063] It should be understood that, although each step in the flow chart of the above-mentioned embodiments is shown in order, these steps are not necessarily performed in order. Unless there is a clear explanation in this article, the execution of these steps does not have strict order restrictions, and these steps can be performed in other orders. Moreover, at least a portion of the steps in the above-mentioned embodiments may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in order, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0064] In one embodiment, Figure 6As shown, an information processing device 600 in an electric power scenario is provided, and the device specifically includes:

[0065] The acquisition module 602 is used to acquire the power question information input by the user in the power scenario;

[0066] The determination module 604 is used to input the power question information into the trained power question and answer big model, so as to determine the target power business intention category to which the power question information belongs from a plurality of preset candidate power business intention categories through the power question and answer big model; the power question and answer big model includes business processing units corresponding to each of the plurality of candidate power business intention categories;

[0067] The generating module 606 is used to process the power question information through the business processing unit corresponding to the target power business intention category to generate power answer information for the power question information.

[0068] In one embodiment, the power question and answer big model is a power multimodal question and answer big model; the power question information includes at least one of power question text information, power question voice information or power question visual information.

[0069] In one embodiment, the plurality of candidate power business intent categories include a power data chart generation category, a power picture and power presentation retrieval category, a power text map category, a power picture target defect detection category, a power intelligent search category, and a power text generation category.

[0070] In one embodiment, the acquisition module 602 is also used to acquire historical power question information of the power question information, and to acquire historical power answer information for the historical power question information; the generation module 606 is also used to process the power question information based on the historical power question information and the historical power answer information through the business processing unit corresponding to the target power business intention category, so as to generate power answer information for the power question information.

[0071] In one embodiment, Figure 7 As shown, the information processing device 600 in the power scenario also includes:

[0072] The training module 608 is used to obtain multiple power training sample pairs in the power scenario; each power training sample pair includes a power question sample information and a power answer sample information for the power question sample information; the power question sample information is input into the power question and answer big model to be trained, so as to generate power answer prediction information for the power question sample information based on the power question sample information through the power question and answer big model to be trained; and the power question and answer big model to be trained is trained through the difference between the power answer prediction information and the power answer sample information to obtain the trained power question and answer big model.

[0073] In one embodiment, the power question and answer big model to be trained is a power multimodal question and answer big model to be trained; the power question sample information includes at least one of power question text sample information, power question voice sample information or power question visual sample information.

[0074] The information processing device in the above-mentioned power scenario obtains the power question information input by the user in the power scenario; inputs the power question information into the trained power question and answer big model, so as to determine the target power business intention category to which the power question information belongs from multiple preset candidate power business intention categories through the power question and answer big model; the power question and answer big model contains business processing units corresponding to multiple candidate power business intention categories; and processes the power question information through the business processing units corresponding to the target power business intention category to generate power answer information for the power question information. Compared with the traditional power question and answer system, the present application can directly generate rich and accurate power answer information for the power question information by inputting structured or unstructured power question information into the trained power question and answer big model through the powerful information understanding and generation capabilities of the power question and answer big model, thereby improving the information processing efficiency in the power scenario.

[0075] In addition, the traditional information processing method in the power scenario requires the development of a dedicated power question-and-answer system for each power business, which results in a waste of human resources and computer resources, and is not conducive to the unified management of the power question-and-answer system, resulting in low efficiency in the question-and-answer of power information. However, this application can provide a unified inquiry portal for multiple power businesses through a trained power question-and-answer large model, and can provide question-and-answer services for different power businesses, avoiding the waste of human resources and computer resources, and is also conducive to the unified management of the power question-and-answer system, thereby improving the efficiency of the question-and-answer of power information.

[0076] Each module in the information processing device in the above power scenario can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0077] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 8As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, an information processing method in an electric power scenario is implemented.

[0078] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be shown in FIG9. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, the memory, and the input / output interface are connected via a system bus, and the communication interface, the display unit, and the input device are connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, an information processing method in an electric power scenario is implemented. The display unit of the computer device is used to form a visually visible image, and can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covered on the display screen, or a button, trackball or touchpad set on the computer device casing, or an external keyboard, touchpad or mouse, etc.

[0079] Those skilled in the art will understand that Figure 8 The structure shown in FIG. 9 is merely a block diagram of a portion of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0080] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0081] In one embodiment, a computer-readable storage medium is provided, storing a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0082] In one embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0083] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions.

[0084] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0085] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0086] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. An information processing method in an electric power scenario, characterized in that: The method comprises: Obtaining power question information input by users in power scenarios; The power question information is input into the trained power question and answer big model, so as to determine the target power business intention category to which the power question information belongs from a plurality of preset candidate power business intention categories through the power question and answer big model; the power question and answer big model includes business processing units corresponding to each of the plurality of candidate power business intention categories; The power question information is processed by a service processing unit corresponding to the target power service intention category to generate power answer information for the power question information.

2. The method according to claim 1, characterized in that The power question and answer big model is a power multimodal question and answer big model; the power question information includes at least one of power question text information, power question voice information or power question visual information.

3. The method according to claim 1, characterized in that: The multiple candidate power business intention categories include a power data chart generation category, a power picture and power presentation retrieval category, a power text map category, a power picture target defect detection category, a power intelligent search category and a power text generation category.

4. The method according to claim 1, characterized in that: The method further comprises: Acquire historical power question information of the power question information, and acquire historical power answer information for the historical power question information; The processing of the power question information by the service processing unit corresponding to the target power service intention category to generate power answer information for the power question information includes: The power questioning information is processed by a service processing unit corresponding to the target power service intention category based on the historical power questioning information and the historical power answering information to generate power answering information for the power questioning information.

5. The method according to claim 1, characterized in that The method further comprises: Acquire a plurality of power training sample pairs in the power scenario; each of the power training sample pairs includes a power question sample information and a power answer sample information for the power question sample information; Inputting the power question sample information into the power question and answer big model to be trained, so as to generate power answer prediction information for the power question sample information based on the power question sample information through the power question and answer big model to be trained; The electric power question and answer big model to be trained is trained by using the difference between the electric power answer prediction information and the electric power answer sample information to obtain the trained electric power question and answer big model.

6. The method according to claim 5, characterized in that The electric power question and answer big model to be trained is an electric power multimodal question and answer big model to be trained; the electric power question sample information includes at least one of electric power question text sample information, electric power question voice sample information or electric power question visual sample information.

7. An information processing device in an electric power scenario, characterized in that: The device comprises: An acquisition module is used to acquire power question information input by a user in a power scenario; A determination module, used for inputting the power question information into a trained power question and answer big model, so as to determine the target power business intention category to which the power question information belongs from a plurality of preset candidate power business intention categories through the power question and answer big model; the power question and answer big model includes business processing units corresponding to each of the plurality of candidate power business intention categories; A generating module is used to process the power question information through a business processing unit corresponding to the target power business intention category to generate power answer information for the power question information.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images