Operation and maintenance information feedback method and device, electronic equipment and storage medium

Abstract

The invention discloses an operation and maintenance information feedback method and device, electronic equipment and a storage medium. The method comprises the steps that in response to interactive input operation of an operation and maintenance execution object, interactive input information is determined, and the interactive input information comprises voice input information and / or text input information; the input interactive input information and intranet information in an intranet information base are processed through an operation and maintenance auxiliary large model, feedback operation and maintenance information corresponding to the interactive input information is determined, and the operation and maintenance auxiliary large model is obtained by training an initial large model through a multi-modal training sample; the feedback operation and maintenance information is fed back to the operation and maintenance execution object in a target feedback mode, and the target feedback mode comprises a voice feedback mode and / or a text feedback mode. Based on the technical scheme of the invention, the convenience of carrying out system operation and maintenance by a user based on the fed-back operation and maintenance information can be effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of computer application technology, and in particular to an operation and maintenance information feedback method, device, electronic device and storage medium. Background Art

[0002] System operation and maintenance refers to the maintenance, management and support of information technology systems. It includes monitoring, maintenance, troubleshooting, and upgrading of system resources such as hardware, software, networks, and databases. Effective system operation and maintenance can ensure the stability, security, and availability of information technology systems.

[0003] In the related art, the operation and maintenance staff usually searches for relevant operation and maintenance files in the file library, and then analyzes one or more relevant operation and maintenance files to determine the target system operation and maintenance method to perform system operation and maintenance operations. However, in general, the content of the operation and maintenance files is complex and difficult to understand, so that the convenience of system operation and maintenance in this way is poor. Summary of the invention

[0004] The present invention provides an operation and maintenance information feedback method, device, electronic device and storage medium to solve the technical problem of poor convenience in system operation and maintenance through operation and maintenance file query.

[0005] According to one aspect of the present invention, a method for operation and maintenance information feedback is provided, the method comprising:

[0006] In response to an interactive input operation of the operation and maintenance execution object, determining interactive input information, wherein the interactive input information includes voice input information and / or text input information;

[0007] The interactive input information and the intranet information in the intranet information library are processed by the operation and maintenance auxiliary large model to determine the feedback operation and maintenance information corresponding to the interactive input information, wherein the operation and maintenance auxiliary large model is obtained by training the initial large model through multimodal training samples;

[0008] The feedback operation and maintenance information is fed back to the operation and maintenance execution object through a target feedback method, wherein the target feedback method includes a voice feedback method and / or a text feedback method.

[0009] According to another aspect of the present invention, there is provided an operation and maintenance information feedback device, the device comprising:

[0010] An interactive input module, configured to determine interactive input information in response to an interactive input operation of the operation and maintenance execution object, wherein the interactive input information includes voice input information and / or text input information;

[0011] An information processing module is used to process the interactive input information and the intranet information in the intranet information library through an operation and maintenance auxiliary large model to determine feedback operation and maintenance information corresponding to the interactive input information, wherein the operation and maintenance auxiliary large model is obtained by training the initial large model through multimodal training samples;

[0012] The information feedback module is used to feed back the feedback operation and maintenance information to the operation and maintenance execution object through a target feedback method, wherein the target feedback method includes a voice feedback method and / or a text feedback method.

[0013] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0014] at least one processor; and

[0015] a memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the operation and maintenance information feedback method described in any embodiment of the present invention.

[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the operation and maintenance information feedback method described in any embodiment of the present invention when executed.

[0018] The technical solution of the embodiment of the present invention determines the interactive input information by responding to the interactive input operation of the operation and maintenance execution object, wherein the interactive input information includes voice input information and / or text input information; the interactive input information and the intranet information in the intranet information library are processed by the operation and maintenance auxiliary large model to determine the feedback operation and maintenance information corresponding to the interactive input information, wherein the auxiliary large model is obtained by training the initial large model with multimodal training samples; the feedback operation and maintenance information is fed back to the operation and maintenance execution object by the target feedback method, wherein the target feedback method includes voice feedback method and / or text feedback method. The present invention can realize the feedback operation and maintenance information that matches the interactive input information in a targeted manner, that is, it can improve the conciseness of the fed back operation and maintenance information, and improve the matching degree of the fed back data with the interactive input information. The operation and maintenance information feedback method can effectively improve the convenience of the operation and maintenance execution object to perform system operation and maintenance based on the fed back operation and maintenance information, and improve the user experience.

[0019] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0021] Figure 1 is a flow chart of an operation and maintenance information feedback method provided according to Embodiment 1 of the present invention;

[0022] Figure 2 This is a flow chart of an operation and maintenance information feedback method provided according to Embodiment 2 of the present invention;

[0023] Figure 3 This is an application flow chart of an operation and maintenance auxiliary large model provided according to an embodiment of the present invention;

[0024] Figure 4 2 is a schematic diagram of the structure of an operation and maintenance information feedback device provided according to Embodiment 3 of the present invention;

[0025] Figure 5 It is a structural schematic diagram of an electronic device for implementing the operation and maintenance information feedback method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0026] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0027] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0028] Embodiment 1

[0029] Figure 1 A flowchart of an operation and maintenance information feedback method is provided for the first embodiment of the present invention. This embodiment is applicable to the case where system operation and maintenance is performed by information feedback. The method can be executed by an operation and maintenance information feedback device. The operation and maintenance information feedback device can be implemented in the form of hardware and / or software. The operation and maintenance information feedback device can be configured in a computer. Figure 1 As shown, the method includes:

[0030] S110 . Determine interactive input information in response to an interactive input operation of the operation and maintenance execution object.

[0031] The operation and maintenance execution object may be understood as an object that performs an operation and maintenance operation. In the embodiment of the present invention, the operation and maintenance execution object may be preset according to the scenario requirements, and is not specifically limited here. Optionally, the operation and maintenance execution object may be a user.

[0032] The interactive input operation can be understood as an interactive operation for inputting target information. The interactive operation can be an operation between the operation and maintenance execution object and a user input interface. Optionally, the interactive input operation includes a voice input operation and / or a text input operation.

[0033] The interactive input information may be understood as target information input based on the interactive input operation, and the interactive input information includes voice input information and / or text input information.

[0034] In the embodiment of the present invention, voice information and text information can be simultaneously input based on the interactive input operation to more accurately indicate the user's intention.

[0035] In the embodiment of the present invention, the interactive input information may be an information retrieval condition or a target execution task.

[0036] The information retrieval condition may be a retrieval condition input by a user. The retrieval condition may be a question or a statement. For example, the information retrieval condition may be how to upgrade the target system, how to handle a target system crash, how to install plugin A, or query the operation and maintenance data for time period B.

[0037] The target execution task may be an execution task input by the user. For example, the target execution task may be to prepare an operation and maintenance report or statement related to C operation and maintenance data, to monitor D operation and maintenance data and give prompts when abnormalities occur, or to predict in real time the probability of abnormalities of E operation and maintenance data in the future F time period and give prediction warnings when the probability exceeds G threshold, etc.

[0038] In the embodiment of the present invention, the target system may be an information technology system.

[0039] S120: Process the interactive input information and the intranet information in the intranet information library through the operation and maintenance auxiliary big model to determine the feedback operation and maintenance information corresponding to the interactive input information.

[0040] The operation and maintenance auxiliary large model can be understood as a large model used to assist operation and maintenance personnel in system operation and maintenance. In an embodiment of the present invention, the maintenance and maintenance auxiliary large model is obtained by training the initial large model through multi-modal training samples.

[0041] The information processing of the technical solution of the present invention is for the intranet information in the intranet information database, and the present invention can ensure the information security in the process of feedback of operation and maintenance information.

[0042] Optionally, the multimodal training sample includes log files, operation and maintenance manuals, and historical operation and maintenance records. In an embodiment of the present invention, the log files, operation and maintenance manuals, and historical operation and maintenance records in the multimodal training sample may all be related to the target system.

[0043] The intranet information base can be understood as an intranet information base related to the target system, that is, the intranet information contained in the intranet information base is all operation and maintenance information related to the target system.

[0044] Optionally, the intranet information may include log files related to the target system, operation and maintenance manuals related to the target system, and operation and maintenance records related to the target system.

[0045] The feedback operation and maintenance information may be an information retrieval result or a task execution result based on the interactive input information feedback.

[0046] The information retrieval result may be understood as a feedback result related to the information retrieval condition. Optionally, the information retrieval result may be an operation and maintenance guidance of the target system or retrieval operation and maintenance data. Exemplarily, the operation and maintenance guidance of the target system may be specific guidance steps for upgrading the target system, and the retrieval operation and maintenance data may be operation and maintenance data for time period B.

[0047] The task execution result can be understood as a feedback result related to the target execution task. Optionally, the task execution result includes a target task report or an operation and maintenance monitoring result. Exemplarily, the target task report can be an operation and maintenance report related to C operation and maintenance data, and the operation and maintenance monitoring result can be a prompt message when D operation and maintenance data is abnormal, or a prediction and warning of E operation and maintenance data, etc.

[0048] Optionally, after determining the feedback operation and maintenance information corresponding to the interactive input information, the method further includes:

[0049] In response to an abnormal prompt operation of the operation and maintenance execution object, abnormal prompt information is determined, wherein the abnormal prompt operation includes an abnormal trigger operation and / or a prompt input operation, and the abnormal trigger operation indicates that the feedback operation and maintenance information does not match the interactive input information;

[0050] The model parameters of the operation and maintenance auxiliary model are adjusted according to the abnormal prompt information to obtain the operation and maintenance auxiliary model after parameter adjustment.

[0051] Furthermore, after obtaining the operation and maintenance auxiliary large model after parameter adjustment, if interactive input information is received again, information feedback is performed through the operation and maintenance auxiliary large model after parameter adjustment.

[0052] The abnormal prompt operation may be understood as an operation that prompts that the feedback operation and maintenance information is abnormal.

[0053] In the embodiment of the present invention, the abnormal prompt operation may include an abnormal trigger operation and / or a prompt word input operation.

[0054] The abnormal triggering operation may be an operation triggered when the user believes that the feedback operation and maintenance information does not match the interactive input information. Optionally, the abnormal triggering operation may be an operation of triggering a feedback abnormality control, or an operation of inputting a voice indicating abnormal feedback information.

[0055] The prompt input operation may be a user marking an abnormal position in the feedback operation and maintenance information; a user marking an abnormal content in the feedback operation and maintenance information; or a user inputting a prompt word, which may represent an abnormal feature of the feedback operation and maintenance information, etc.

[0056] The abnormal prompt information can be understood as information determined based on the abnormal prompt operation. Optionally, the abnormal prompt information can include abnormal location, abnormal content or prompt words, etc.

[0057] Based on the above implementation scheme, the model parameters of the operation and maintenance assistance big model can be adjusted based on the user's abnormal prompts to further optimize the operation and maintenance assistance big model.

[0058] Optionally, the step of processing the interactive input information and the intranet information in the intranet information database by the operation and maintenance auxiliary big model to determine the feedback operation and maintenance information corresponding to the interactive input information includes:

[0059] Performing information cleaning on the interactive input information to obtain cleaned input information, and performing semantic recognition on the first input information to obtain semantic text information;

[0060] Performing word segmentation processing on the semantic text information to obtain target word segments, and performing vectorization processing on the target word segments to obtain word segmentation vectors;

[0061] The word segmentation vector and the intranet information in the intranet information library are processed through the operation and maintenance auxiliary large model to determine the feedback operation and maintenance information corresponding to the interactive input information.

[0062] In the implementation of the present invention, the specific methods of information cleaning, semantic recognition, word segmentation processing and vectorization processing can be preset according to the scenario requirements and are not specifically limited here.

[0063] Based on the above implementation plan, the interactive input information is pre-processed before the operation and maintenance assistance big model processes the information, which can clarify and simplify the semantic features of the interactive input information and clarify the user's intention, so as to further improve the efficiency and accuracy of information processing by the operation and maintenance assistance big model, ensure the efficiency of data feedback, and improve the matching degree between the feedback data and the interactive input information.

[0064] S130: Feedback the feedback operation and maintenance information to the operation and maintenance execution object in a target feedback manner.

[0065] The target feedback method may be understood as a specific method of feeding back the feedback operation and maintenance information to the operation and maintenance execution object.

[0066] Optionally, the target feedback mode includes a voice feedback mode and / or a text feedback mode.

[0067] Specifically, information feedback may be provided in the form of voice feedback; information feedback may also be provided in the form of text feedback; information feedback may also be provided based on both voice feedback and text feedback.

[0068] The technical solution of the embodiment of the present invention determines the interactive input information by responding to the interactive input operation of the operation and maintenance execution object, wherein the interactive input information includes voice input information and / or text input information; the interactive input information and the intranet information in the intranet information library are processed by the operation and maintenance auxiliary large model to determine the feedback operation and maintenance information corresponding to the interactive input information, wherein the auxiliary large model is obtained by training the initial large model with multimodal training samples; the feedback operation and maintenance information is fed back to the operation and maintenance execution object by the target feedback method, wherein the target feedback method includes voice feedback method and / or text feedback method. The present invention can realize the feedback operation and maintenance information that matches the interactive input information in a targeted manner, that is, it can improve the conciseness of the fed back operation and maintenance information, and improve the matching degree of the fed back data with the interactive input information. The operation and maintenance information feedback method can effectively improve the convenience of the operation and maintenance execution object to perform system operation and maintenance based on the fed back operation and maintenance information, and improve the user experience.

[0069] Embodiment 2

[0070] Figure 2 This is a flow chart of a method for feedback of operation and maintenance information provided in Embodiment 2 of the present invention. This embodiment is to add feedback operation and maintenance information corresponding to the interactive input information as described in the above embodiment. Figure 2 As shown, the method includes:

[0071] S210: Determine interactive input information in response to an interactive input operation of the operation and maintenance execution object.

[0072] S220: Process the interactive input information and the intranet information in the intranet information library through the operation and maintenance auxiliary model to determine feedback operation and maintenance information corresponding to the interactive input information.

[0073] S230: Generate operation and maintenance record information in response to the target operation and maintenance operation of the operation and maintenance execution object.

[0074] The target operation and maintenance operation may be an operation performed by the operation and maintenance execution object based on the feedback operation and maintenance information. Optionally, the target operation and maintenance operation may be an operation of upgrading the target system, or an operation of installing plug-in A.

[0075] The operation and maintenance record information may include an operation and maintenance operation record and system feedback information related to the operation and maintenance operation record. The operation and maintenance operation record may be a record of an operation and maintenance operation performed by a user. The system feedback information may be information fed back by a target system under an operation and maintenance operation performed by a user. The information fed back by the target system may be an operation and maintenance success or an operation and maintenance failure, etc. Exemplarily, an operation and maintenance success may be an upgrade success or a plug-in installation success, etc., and an operation and maintenance failure may be an upgrade failure or a plug-in installation failure, etc.

[0076] S240: When the operation and maintenance record information meets the new sample condition, use the operation and maintenance record information as a new training sample.

[0077] Among them, the newly added sample condition can be used to determine whether the information similarity between the operation and maintenance record information and the multimodal training sample exceeds the target similarity.

[0078] The newly added training samples can be understood as newly added samples used for incremental training of the operation and maintenance auxiliary large model.

[0079] Optionally, when the operation and maintenance record information meets a new sample condition, using the operation and maintenance record information as a new training sample includes:

[0080] Acquire the multimodal training sample, and determine the information similarity between the operation and maintenance record information and the multimodal training sample;

[0081] When the information similarity does not exceed the target similarity, the operation and maintenance record information is used as a new training sample.

[0082] The information similarity may represent the similarity between the operation and maintenance record information and the multimodal training sample. For example, the information similarity may be 10%, 50%, or 80%.

[0083] The target similarity can be understood as a preset similarity threshold. In the embodiment of the present invention, the target similarity can be preset according to the scene requirements, and is not specifically limited here. Exemplarily, the target similarity can be 70%, 80% or 90%, etc.

[0084] Optionally, after taking the operation and maintenance record information as a newly added training sample, the method further includes:

[0085] The newly added training samples are stored in the intranet information library.

[0086] Based on the above embodiment scheme, when the information similarity between the operation and maintenance record information and the multimodal training samples is low, the operation and maintenance record information is used as a new training sample to ensure the effectiveness of optimizing the maintenance-assisted large model through the new training samples.

[0087] S250. Incrementally train the operation and maintenance assistance large model using the newly added training samples to obtain an updated operation and maintenance assistance large model.

[0088] Furthermore, after obtaining the updated operation and maintenance auxiliary model, if interactive input information is received again, information feedback is performed through the updated operation and maintenance auxiliary model.

[0089] S260: Feedback the feedback operation and maintenance information to the operation and maintenance execution object through a target feedback method.

[0090] The technical solution of the embodiment of the present invention generates operation and maintenance record information by responding to the target operation and maintenance operation of the operation and maintenance execution object, wherein the target operation and maintenance operation is performed based on the feedback operation and maintenance information; when the operation and maintenance record information meets the new sample conditions, the operation and maintenance record information is used as a new training sample; the operation and maintenance auxiliary big model is incrementally trained through the new training samples to obtain an updated operation and maintenance auxiliary big model. The above embodiment scheme can further effectively optimize the operation and maintenance auxiliary big model based on the effective new training samples, so as to improve the accuracy of the operation and maintenance information feedback through the optimized operation and maintenance auxiliary big model.

[0091] Figure 3 This is an application flow chart of an operation and maintenance auxiliary model provided according to an embodiment of the present invention. Figure 3 As shown, the application of the operation and maintenance auxiliary model is further explained as follows:

[0092] The operation and maintenance auxiliary model in the present invention is trained based on multimodal information such as the operation and maintenance manual, the historical change records of the target system (historical operation and maintenance records), and the historical alarm monitoring records. The operation and maintenance auxiliary model can provide emergency prompts, change reminders, and monitoring warnings. The operation and maintenance auxiliary model can also optimize parameters based on the correction information fed back by users. The operation and maintenance auxiliary model is based on the knowledge base of the intranet for operation and maintenance information feedback.

[0093] In summary, the operation and maintenance auxiliary large model of the present invention has the performance of high intelligence, self-incremental training, high-security intranet information processing and self-correction parameter optimization.

[0094] Embodiment 3

[0095] Figure 4This is a schematic diagram of the structure of an operation and maintenance information feedback device provided in Embodiment 3 of the present invention. Figure 4 As shown, the device includes: an interactive input module 310 , an information processing module 320 and an information feedback module 330 .

[0096] Among them, the interactive input module 310 is used to determine the interactive input information in response to the interactive input operation of the operation and maintenance execution object, wherein the interactive input information includes voice input information and / or text input information; the information processing module 320 is used to process the input interactive input information and the intranet information in the intranet information library through the operation and maintenance auxiliary big model, and determine the feedback operation and maintenance information corresponding to the interactive input information, wherein the operation and maintenance auxiliary big model is obtained by training the initial big model through multimodal training samples; the information feedback module 330 is used to feed back the feedback operation and maintenance information to the operation and maintenance execution object through a target feedback method, wherein the target feedback method includes a voice feedback method and / or a text feedback method.

[0097] The technical solution of the embodiment of the present invention determines the interactive input information by responding to the interactive input operation of the operation and maintenance execution object, wherein the interactive input information includes voice input information and / or text input information; the interactive input information and the intranet information in the intranet information library are processed by the operation and maintenance auxiliary large model to determine the feedback operation and maintenance information corresponding to the interactive input information, wherein the auxiliary large model is obtained by training the initial large model with multimodal training samples; the feedback operation and maintenance information is fed back to the operation and maintenance execution object by the target feedback method, wherein the target feedback method includes voice feedback method and / or text feedback method. The present invention can realize the feedback operation and maintenance information that matches the interactive input information in a targeted manner, that is, it can improve the conciseness of the fed back operation and maintenance information, and improve the matching degree of the fed back data with the interactive input information. The operation and maintenance information feedback method can effectively improve the convenience of the operation and maintenance execution object to perform system operation and maintenance based on the fed back operation and maintenance information, and improve the user experience.

[0098] Optionally, the operation and maintenance information feedback device further includes: an operation and maintenance record generation module, a training sample addition module and a model incremental training module;

[0099] The operation and maintenance record generation module is used to generate operation and maintenance record information in response to a target operation and maintenance operation of the operation and maintenance execution object after determining the feedback operation and maintenance information corresponding to the interactive input information, wherein the target operation and maintenance operation is performed based on the feedback operation and maintenance information;

[0100] The training sample adding module is used to use the operation and maintenance record information as a new training sample when the operation and maintenance record information meets the new sample condition;

[0101] The model incremental training module is used to perform incremental training on the operation and maintenance auxiliary large model through the newly added training samples to obtain an updated operation and maintenance auxiliary large model.

[0102] Optionally, the training sample newly added module is specifically used for:

[0103] Acquire the multimodal training sample, and determine the information similarity between the operation and maintenance record information and the multimodal training sample;

[0104] When the information similarity does not exceed the target similarity, the operation and maintenance record information is used as a new training sample.

[0105] Optionally, the operation and maintenance information feedback device further includes: a feedback abnormality prompt module and a model parameter adjustment module;

[0106] The feedback abnormal prompt module is used to determine abnormal prompt information in response to an abnormal prompt operation of the operation and maintenance execution object after determining the feedback operation and maintenance information corresponding to the interactive input information, wherein the abnormal prompt operation includes an abnormal trigger operation and / or a prompt input operation, and the abnormal trigger operation indicates that the feedback operation and maintenance information does not match the interactive input information;

[0107] The model parameter adjustment module is used to adjust the model parameters of the operation and maintenance auxiliary large model according to the abnormal prompt information to obtain the operation and maintenance auxiliary large model after parameter adjustment.

[0108] Optionally, the multimodal training samples include log files, operation and maintenance manuals, and historical operation and maintenance records.

[0109] Optionally, the interactive input information includes information retrieval conditions or target execution tasks; the feedback operation and maintenance information includes information retrieval results or task execution results; the information retrieval results include operation and maintenance instructions for the target system or retrieval of operation and maintenance data, and the task execution results include target task reports or operation and maintenance monitoring results.

[0110] Optionally, the information processing module 320 is specifically configured to:

[0111] Performing information cleaning on the interactive input information to obtain cleaned input information, and performing semantic recognition on the first input information to obtain semantic text information;

[0112] Performing word segmentation processing on the semantic text information to obtain target word segments, and performing vectorization processing on the target word segments to obtain word segmentation vectors;

[0113] The word segmentation vector and the intranet information in the intranet information library are processed through the operation and maintenance auxiliary large model to determine the feedback operation and maintenance information corresponding to the interactive input information.

[0114] The operation and maintenance information feedback device provided in the embodiment of the present invention can execute the operation and maintenance information feedback method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0115] Embodiment 4

[0116] Figure 5 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) 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 invention described and / or required herein.

[0117] like Figure 5 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0118] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0119] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the operation and maintenance information feedback method.

[0120] In some embodiments, the operation and maintenance information feedback method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the operation and maintenance information feedback method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the operation and maintenance information feedback method in any other appropriate manner (e.g., by means of firmware).

[0121] 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), load 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.

[0122] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program 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.

[0123] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. 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.

[0124] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device 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 a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0125] The systems and techniques described herein may be implemented in a computing system that includes backend 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 frontend 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 backend components, middleware components, or frontend 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), a blockchain network, and the Internet.

[0126] A computing 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 client and server relationship 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.

[0127] 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 described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0128] The above specific implementations do not constitute a limitation on the protection scope of the present invention. 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 invention should be included in the protection scope of the present invention.

Claims

1. A method for feedback of operation and maintenance information, characterized in that: include: In response to an interactive input operation of the operation and maintenance execution object, determining interactive input information, wherein the interactive input information includes voice input information and / or text input information; The interactive input information and the intranet information in the intranet information library are processed by the operation and maintenance auxiliary large model to determine the feedback operation and maintenance information corresponding to the interactive input information, wherein the operation and maintenance auxiliary large model is obtained by training the initial large model through multimodal training samples; The feedback operation and maintenance information is fed back to the operation and maintenance execution object through a target feedback method, wherein the target feedback method includes a voice feedback method and / or a text feedback method.

2. The method according to claim 1, characterized in that: After the feedback operation and maintenance information corresponding to the interactive input information is determined, the method further includes: In response to a target operation of the operation and maintenance execution object, generating operation and maintenance record information, wherein the target operation and maintenance operation is performed based on the feedback operation and maintenance information; When the operation and maintenance record information meets the new sample condition, the operation and maintenance record information is used as a new training sample; The operation and maintenance assistance large model is incrementally trained using the newly added training samples to obtain an updated operation and maintenance assistance large model.

3. The method according to claim 2, characterized in that When the operation and maintenance record information meets the new sample condition, using the operation and maintenance record information as a new training sample includes: Acquire the multimodal training sample, and determine the information similarity between the operation and maintenance record information and the multimodal training sample; When the information similarity does not exceed the target similarity, the operation and maintenance record information is used as a new training sample.

4. The method according to claim 1, characterized in that: After the feedback operation and maintenance information corresponding to the interactive input information is determined, the method further includes: In response to an abnormal prompt operation of the operation and maintenance execution object, abnormal prompt information is determined, wherein the abnormal prompt operation includes an abnormal trigger operation and / or a prompt input operation, and the abnormal trigger operation indicates that the feedback operation and maintenance information does not match the interactive input information; The model parameters of the operation and maintenance auxiliary model are adjusted according to the abnormal prompt information to obtain the operation and maintenance auxiliary model after parameter adjustment.

5. The method according to claim 1, characterized in that The multimodal training samples include log files, operation and maintenance manuals, and historical operation and maintenance records.

6. The method according to claim 1, characterized in that The interactive input information includes information retrieval conditions or target execution tasks; the feedback operation and maintenance information includes information retrieval results or task execution results; the information retrieval results include operation and maintenance operation instructions for the target system or retrieval of operation and maintenance data, and the task execution results include target task reports or operation and maintenance monitoring results.

7. The method according to claim 1, characterized in that The step of processing the interactive input information and the intranet information in the intranet information database by the operation and maintenance auxiliary big model to determine the feedback operation and maintenance information corresponding to the interactive input information includes: Performing information cleaning on the interactive input information to obtain cleaned input information, and performing semantic recognition on the first input information to obtain semantic text information; Performing word segmentation processing on the semantic text information to obtain target word segments, and performing vectorization processing on the target word segments to obtain word segmentation vectors; The word segmentation vector and the intranet information in the intranet information library are processed through the operation and maintenance auxiliary large model to determine the feedback operation and maintenance information corresponding to the interactive input information.

8. An operation and maintenance information feedback device, characterized in that: include: An interactive input module, configured to determine interactive input information in response to an interactive input operation of the operation and maintenance execution object, wherein the interactive input information includes voice input information and / or text input information; An information processing module is used to process the interactive input information and the intranet information in the intranet information library through an operation and maintenance auxiliary large model to determine feedback operation and maintenance information corresponding to the interactive input information, wherein the operation and maintenance auxiliary large model is obtained by training the initial large model through multimodal training samples; The information feedback module is used to feed back the feedback operation and maintenance information to the operation and maintenance execution object through a target feedback method, wherein the target feedback method includes a voice feedback method and / or a text feedback method.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the operation and maintenance information feedback method described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the operation and maintenance information feedback method according to any one of claims 1 to 7 when executed.

Images