CN117636855A - Device configuration method, computer device and computer-readable storage medium - Google Patents
Device configuration method, computer device and computer-readable storage medium Download PDFInfo
- Publication number
- CN117636855A CN117636855A CN202311213013.2A CN202311213013A CN117636855A CN 117636855 A CN117636855 A CN 117636855A CN 202311213013 A CN202311213013 A CN 202311213013A CN 117636855 A CN117636855 A CN 117636855A
- Authority
- CN
- China
- Prior art keywords
- configuration
- instruction
- computer
- equipment
- command
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/08—Speech classification or search
- G10L15/18—Speech classification or search using natural language modelling
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- Machine Translation (AREA)
Abstract
本申请涉及一种设备配置方法、计算机设备及计算机可读存储介质。基于本申请提供的设备配置方法，工程人员可以直接以其惯用的自然语言描述针对目标设备的配置目的，计算机设备自动将工程人员输入的自然语言转换为服务对目标设备进行配置的指令语言，省却了工程人员人工编写配置指令的繁琐过程，这不仅降低了对工程人员专业知识与专业经验的要求，而且，因为用于对目标设备进行配置的指令语言由计算机设备提供，避免了人为失误，提升了设备配置的准确性。同时，计算机设备基于自然语言提供相应指令语言的过程快捷迅速，避免了目标设备长时间处于配置阶段，显著提升了配置效率。
The present application relates to a device configuration method, computer equipment and computer-readable storage media. Based on the device configuration method provided by this application, engineers can directly describe the configuration purpose of the target device in their usual natural language, and the computer device automatically converts the natural language input by the engineer into an instruction language for configuring the target device, eliminating the need for This eliminates the cumbersome process of manually writing configuration instructions for engineers, which not only reduces the requirements for professional knowledge and experience of engineers, but also because the instruction language used to configure the target device is provided by the computer device, human errors are avoided and improvements are made. Ensure the accuracy of device configuration. At the same time, the process of computer equipment providing corresponding instruction language based on natural language is quick and fast, which avoids the target equipment being in the configuration stage for a long time and significantly improves the configuration efficiency.
Description
Technical Field
The present disclosure relates to the field of computer technologies, and in particular, to a device configuration method, a computer device, and a computer readable storage medium.
Background
In the related art, when the network equipment is configured, a configuration instruction needs to be manually written, and an operator is required to have abundant technical knowledge and experience in the configuration mode, so that the configuration threshold is high. Meanwhile, the configuration instruction is complicated to write, and the configuration instruction is complex, so that errors are easy to occur in the configuration process, and the stability and the safety of the network are threatened. There is thus a need to provide a simple and reliable device configuration.
Disclosure of Invention
In order to reduce equipment configuration difficulty and improve equipment configuration accuracy, the application provides an equipment configuration method, computer equipment and a computer readable storage medium.
In a first aspect, the present application provides a device configuration method, including:
receiving an initial configuration command described in natural language, wherein the initial configuration command is used for describing a configuration target for configuring target equipment;
converting the initial configuration command into an intent vector;
matching a plurality of original intention answers corresponding to the intention vectors in a data resource library, wherein the data resource library comprises a plurality of answer data described in an instruction language;
and configuring the target equipment based on the original intention answer.
By adopting the technical scheme, the computer equipment supports to receive the initial configuration command described in the natural language, converts the initial configuration command into the intention vector, then matches the intention vector with answer data described in the instruction language in the data resource library to obtain a plurality of original intention answers corresponding to the intention vector, and then configures the target equipment based on the original intention answers. Based on the equipment configuration scheme, engineering personnel can directly describe the configuration purpose of target equipment by using the conventional natural language, and the computer equipment automatically converts the natural language input by the engineering personnel into the instruction language for configuring the target equipment by service, so that the complicated process of manually writing configuration instructions by the engineering personnel is omitted, the requirements on the professional knowledge and the professional experience of the engineering personnel are reduced, and because the instruction language for configuring the target equipment is provided by the computer equipment, human errors are avoided, and the accuracy of equipment configuration is improved. Meanwhile, the process of providing the corresponding instruction language by the computer equipment based on the natural language is quick and rapid, the target equipment is prevented from being in a configuration stage for a long time, and the configuration efficiency is remarkably improved.
Optionally, the converting the initial-configuration command into an intent vector includes:
sentence segmentation is carried out on the initial configuration command to obtain a plurality of keywords;
and performing part-of-speech tagging and dependency syntactic analysis on the keywords to obtain the intention vector.
According to the technical scheme, the keywords are obtained by sentence segmentation of the initial configuration command, and then part-of-speech tagging and dependency syntactic analysis (Dependency Syntactic Parsing) are carried out on the keywords, so that the intention vector capable of accurately representing the configuration target can be obtained, and the accuracy of the matched original intention answers is further improved.
Optionally, the performing sentence segmentation on the initial configuration command to obtain a plurality of keywords includes:
and carrying out sentence segmentation on the initial configuration command by adopting a Prompt (Prompt) engine to obtain a plurality of keywords.
Optionally, the performing part-of-speech tagging and dependency syntactic analysis on the keyword to obtain the intent vector includes:
and performing part-of-speech tagging and dependency syntactic analysis on the keywords by adopting a large-scale language model (Large Language Model, LLM) to obtain the intent vector.
In the technical scheme, LLM is adopted to perform part-of-speech labeling and dependency syntactic analysis on the keywords to obtain the intention vector, and LLM is an open-source language processing model, so that the implementation cost of the equipment configuration scheme can be reduced.
Optionally, the configuring the target device based on the original intention answer includes:
performing secondary processing on a plurality of original intention answers matched from the data resource base by adopting a language processing model to obtain a configuration instruction corresponding to the initial configuration command;
and configuring the target equipment according to the configuration instruction.
By adopting the technical scheme, after the original intention answers are matched from the data resource library, the original intention answers are subjected to secondary processing, so that a configuration instruction with higher adaptation degree with the initial configuration command is obtained, and the target equipment is configured according to the configuration instruction, so that the workload of engineering personnel is further reduced, and the accuracy of equipment configuration is improved.
Optionally, the language processing model comprises LLM.
Optionally, before the configuring the target device according to the configuration instruction, the method further includes:
displaying the configuration instruction through a human-computer interaction interface;
and receiving a confirmation instruction aiming at the configuration instruction, wherein the confirmation instruction characterizes that a configuration user approves the configuration of the target equipment according to the configuration instruction.
By adopting the technical scheme, before the target equipment is configured according to the configuration instruction, the configuration instruction can be presented to engineering personnel through a man-machine interaction interface, so that the engineering personnel can take care of the configuration, the configuration accuracy is further improved, and the probability that the target equipment cannot normally provide service due to the fact that the computer equipment configures the target equipment by adopting the inaccurate or even wrong configuration instruction is avoided.
Optionally, the target device is an optical line terminal (Optical Line Terminal, OLT), and configuring the target device according to the configuration instruction includes: and sending the configuration instruction to the optical line terminal, and indicating the optical line terminal to perform configuration according to the configuration instruction.
In a second aspect, the present application provides a computer device comprising a processor, a memory and a communication bus for enabling a communication connection between the processor and the memory, the processor being for executing a computer program stored in the memory for enabling the device configuration method of any of the preceding claims.
In a third aspect, the present application provides a computer-readable storage medium storing a computer program; the computer program is executable by a processor to implement the device configuration method of any of the preceding claims.
By adopting the technical scheme, a carrier of a computer program of the equipment configuration method is provided.
In summary, the present application includes at least the following beneficial technical effects:
1. the engineering personnel only need to describe the configuration target aiming at the target equipment by adopting natural language, configuration instruction writing is not needed, and the difficulty and threshold of equipment configuration are reduced;
2. the computer equipment provides the corresponding instruction language according to the natural language of engineering personnel, so that various errors caused by manual instruction writing are avoided, the accuracy of equipment configuration is improved, and the safe and stable operation of the equipment is guaranteed.
Drawings
Fig. 1 is a schematic flow chart of one method of configuring a device according to the first embodiment of the present application;
FIG. 2 is a schematic diagram of an interactive interface of a computer device in a device configuration scheme according to a first embodiment of the present application;
fig. 3 is a schematic flow chart of a computer device acquiring an intent vector in a device configuration scheme according to an embodiment of the present application;
fig. 4 is a schematic flow chart of a configuration instruction for configuring a target device by a computer device in a device configuration scheme according to an embodiment of the present application;
FIG. 5 is a schematic diagram of an interactive interface of a computer device in a device configuration scheme according to a first embodiment of the present application;
fig. 6 is a schematic flow chart of one method of configuring a device according to the second embodiment of the present application;
FIG. 7 is a schematic diagram of an implementation of the device configuration provided in the first embodiment of the present application;
fig. 8 is a schematic structural diagram of a device configuration apparatus provided in a third embodiment of the present application;
fig. 9 is a schematic hardware structure of a computer device according to a third embodiment of the present application.
Reference numerals illustrate:
80-device configuration means; an 802-command receiving module; 804-a vector acquisition module; 806-an answer acquisition module; 808-a device configuration module; 90-computer device; 91-a processor; 92-memory; 93-communication bus.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
Embodiment one:
in order to reduce the threshold and difficulty of equipment configuration and improve the accuracy and stability of equipment configuration, the embodiment provides an equipment configuration method, please refer to a flow chart of the equipment configuration method shown in fig. 1:
s102: the computer device receives an initial-configuration command described in natural language.
The initial configuration command is used to describe a configuration target for the target device, which expresses a configuration desire of an engineer for the target device, for example, the initial configuration command "configure the operation mode of the port a to be the mode a" expresses that the engineer desires the port a to operate according to the mode a.
The target device refers to a device to be configured, which may be various network devices including, but not limited to, OLT, optical network units (Optical Network Unit, ONUs), routers, switches, servers, base stations, modems, optical terminals, optical fiber transceivers, etc.; but also various types of terminal equipment including, but not limited to, medical equipment, traffic equipment (e.g., rail traffic control equipment, etc.), industrial production equipment, etc.
The initial configuration command is described in Natural language, where Natural language (Natural language) is a major tool of human communication and thinking, and generally refers to a language that naturally evolves with culture, such as chinese, english, japanese, spanish, french, hebrew, arabic, etc., all belong to Natural language, and in addition to that, various places, such as guan, wu, tibetan, etc., also belong to Natural language. In this embodiment, the computer device is supported to receive an initial configuration command described in natural language, so that an engineer can describe the configuration target for the target device in his conventional natural language, for example, for a chinese engineer, it can describe the configuration target in chinese, or chinese dialect such as cantonese, while a us engineer can describe the configuration target in english. In some examples of this embodiment, the computer device supports the multilingual description configuration requirement, which may facilitate the engineering personnel to flexibly select a working language, and promote the efficiency of generating the initial configuration command. Moreover, in some examples, the computer device also supports the engineer to enter initial configuration commands in a mixed language (e.g., chinese and English inclusion, chinese and French inclusion, chinese, guangdong and English inclusion).
The computer device may receive the initial-configuration command through an input device including at least one of a keyboard, a mouse, a touch screen, an audio input unit (microphone), and the like. More commonly, the initial configuration command is input through a keyboard, and an engineering person can directly input the initial configuration command in a text form through the keyboard in a man-machine interaction interface for receiving the initial configuration command by the computer equipment, as shown in fig. 2. The mouse is usually matched with a keyboard or a soft keyboard provided by a computer device for input, and the input mode based on the touch screen is a common input mode, so that the two input modes are not repeated here. In some examples, the computer device may also receive the initial configuration command through the microphone, in which case, the engineer only needs to speak the configuration target for the target device into the microphone, and after the computer device obtains the sound data collected by the microphone, the computer device may perform voice recognition on the sound data, so as to obtain the text version initial configuration command corresponding to the sound data.
S104: the computer device converts the initial-configuration command into an intent vector.
After the computer device obtains the initial configuration command, the initial configuration command can be converted to obtain a corresponding intention vector, wherein the intention vector refers to a configuration target of engineering personnel or a vector value of the vectorized configuration intention, and the vector value is a representation of the initial configuration command.
In some examples of this embodiment, the computer device may convert the initial-configuration command into an intent vector with reference to the flow illustrated in fig. 3:
s302: the computer equipment performs sentence segmentation on the initial configuration command to obtain a plurality of keywords.
Because the initial configuration command is described in natural language, the computer device may segment the initial configuration command into keywords, e.g., for an initial configuration command of "configure GE port 0/0/1 into trunk mode", the computer device may segment it into "will", "GE port", "configure", "into", "trunk", "mode"; for the initial configuration command "configure port a's operation mode is mode a", the computer device may divide it into "configure", "port a", "operation mode", "mode a".
In some examples of this embodiment, the computer device may employ a Prompt engine to sentence-segment the initial-configuration command. Promt is a text Prompt that directs artificial intelligence (Artificial Intelligence, AI) to perform specific tasks, such as generating text, translating, answering questions, etc., which is equivalent to "giving instructions" to the AI to let the AI work as desired. The application scene of Prompt is very rich: in the chat robot field, promt can be used to generate more humanized, intelligent conversations; in the search engine field, promt can be used to optimize the quality of search results; in the intelligent customer service field, the promt can be used for improving the response speed and the resolution of customer service; even in the art, promt can be used to create artwork, such as poetry, painting, and the like. In general, promt is an important trend in the field of artificial intelligence, and it can make AI complete tasks more efficiently, accurately and intelligently, so as to bring more convenience and innovation for human life.
S304: the computer equipment carries out part-of-speech tagging and dependency syntactic analysis on the keywords to obtain an intention vector.
After obtaining the keywords corresponding to the initial configuration command, the computer device may perform part-of-speech tagging on the keywords. Part-of-speech tagging, also known as grammar tagging or part-of-speech disambiguation, is a text data processing technique in corpus linguistics that tags parts-of-speech of words in a corpus by their meaning and context.
Part-of-speech tagging may be accomplished manually or by a specific algorithm, for example, in this embodiment the computer may implement part-of-speech tagging for keywords using, but not limited to, hidden Markov models (Hidden Markov Model, HMM), maximum entropy Markov models (Maximum Entropy Markov Model, MEMM), conditional random fields (Conditional random fields, CRFs), recurrent neural networks (Recurrent Neural Network, RNN) algorithms, and the like.
The computer equipment also carries out dependency syntax analysis on the keywords, wherein the dependency syntax analysis is used for identifying the dependency relationship among words in sentences and revealing the syntax structure of the dependency syntax analysis, including main-predicate relationship, dynamic guest relationship, core relationship and the like, and the dependency syntax analysis adopts dependency linguistics to understand semantics and accurately grasp user intention.
In some examples of this embodiment, the computer device may employ training-based LLM to part-of-speech tagging and dependency syntax analysis of keywords to obtain intent vectors. In order to make LLM suitable for part-of-speech tagging and dependency syntax analysis of keywords corresponding to an initial configuration command in this embodiment, training sets in a device configuration field may be pre-adopted to train LLM, where the training sets in the device configuration field include a large number of common keywords in the device configuration field. In some examples, the part-of-speech labeling and dependency syntactic analysis can be performed on keywords by selecting but not limited to ChatGPT (Chat Generative Pre-trained Transformer, chat generation pre-training converter) in LLM model, chatGLM (dialogue robot supporting Chinese-English bilingual developed by intelligent spectrum AI of company with conversion of the results of the Qinghai technology), GPT-3.5, GPT-4, bard (chat robot pushed by Google), LLaMA (large language model developed by Meta) and the like.
S106: the computer device matches in the data repository a number of original intent answers corresponding to the intent vector.
After the computer equipment acquires the intention vector, the intention vector can be matched in a data resource library, and an original intention answer corresponding to the intention vector is obtained. In some examples of this embodiment, the data repository may be an external data repository (External Cognitive Assets). The data resource library includes a plurality of answer data described in instruction language, and it will be understood by those skilled in the art that the computer device may match the intent vector in the data resource library according to a matching rule corresponding to the data resource library, so as to match one or more answer data corresponding to the intent vector from the plurality of answer data, and use the matched answer data as an original intent answer of the intent vector.
The data repository may be obtained by training LLM in some examples, but it will be appreciated by those skilled in the art that the data repository may be obtained by training other models in other examples of the present embodiment.
S108: the computer device configures the target device based on the original intent answer.
Because the answer data in the data resource library is described in the instruction language, the matched original intention answers are described in the instruction language, so that the original intention answers are instructions which can be identified by the target equipment, and the computer equipment can configure the target equipment based on the original intention answers.
In the configuration process aiming at the target equipment, no engineering personnel is required to write configuration instructions, and only natural language is required to describe the configuration target aiming at the target equipment to the computer equipment, so that the computer equipment can automatically provide instruction language for realizing the configuration target, and the target equipment is configured based on the instruction language, thereby reducing the capability requirement of equipment configuration on the engineering personnel, reducing the threshold of the configuration personnel, and being beneficial to reducing the operation and maintenance cost of the equipment; meanwhile, because the instruction language for configuring the target equipment is provided by the computer equipment, no matter the configuration process is complex or simple, and the instruction language is more or less, no human error occurs, the accuracy of equipment configuration is obviously improved, and the stability and safety of the configured target equipment are guaranteed.
In some examples of this embodiment, the computer device matches more than one original intent answer from the data repository, and in some examples, when the computer device matches the target device based on the original intent answers, the computer device uses a language processing model to perform secondary processing on the original intent answers, so as to obtain a configuration instruction with higher matching performance with the initial configuration command. The language processing model used by the computer device for the secondary processing may be implemented using a LLM model, such as the LLaMA or GPT-4 model described above, or other LLMs may be selected. In some examples, the secondary processing performed by the computer device is to filter the multiple original intention answers, and select one with the highest matching degree with the initial configuration command as the configuration instruction. In other examples, the computer device may further refine and refine the original answer to better conform to the configuration scenario of the target device, for example, the instruction language used in configuring the OLT may be significantly different from the instruction language used in configuring the base station. The computer equipment obtains the configuration instruction with higher matching degree with the initial configuration command by perfecting and refining the original intention answer.
In some examples, the original intent answer matched from the data repository may form an original intent answer list, which the computer device may input into the LLM, causing the LLM to perform a secondary processing on the original intent answer list, resulting in the configuration instructions.
After obtaining the configuration instruction, in some examples, the computer device may directly use the configuration instruction to configure the target device, for example, when the OLT is used as the target device, the computer device may send the configuration instruction to the OLT through a network communication protocol (for example, a simple file transfer protocol (Trivial File Transfer Protocol, TFTP)) with the OLT, so that the OLT implements configuration according to the configuration instruction.
In other examples, the computer device may display the configuration instructions to the engineering personnel through a human-machine interaction interface, which may be a command line interface (Command Line Interface, CLI) in some examples, where the engineering personnel confirms the configuration instructions; in other examples, to promote human-machine interaction friendliness, the computer device may display configuration instructions in a graphical user interface (Graphical User Interface, GUI). If the engineering personnel determines that the configuration instruction is correct, the engineering personnel can send a confirmation instruction to the computer equipment, and the computer equipment adopts the configuration instruction to configure the target equipment after detecting the confirmation instruction. In some examples, if the engineer is not satisfied with the configuration instruction presented by the computer device through the man-machine interaction interface, for example, too many errors in the configuration instruction may cause a problem of reporting errors or system crashes of the target device, the engineer may issue a discard instruction to the computer device, so that the computer device discards configuring the target device with the configuration instruction.
In some examples of this embodiment, after the computer device presents the configuration instruction to the engineer, the engineer may also modify and adjust the configuration instruction, for example, please refer to a schematic flow chart of the computer device shown in fig. 4 for configuring the target device according to the configuration instruction:
s402: the computer equipment displays the configuration instruction through the man-machine interaction interface.
For example, in some examples, for an engineer "configure GE port 0/0/1 into trunk mode", the configuration instruction provided by the computer device is "interface GE 0/0;vlan mode 1 trunk; vlan trunk 1 1000; which may then display the configuration instruction through a human-machine interface, as shown in FIG. 5.
S404: the computer device receives an input instruction.
The computer device may receive input instructions from an engineer through at least one of several input units such as a keyboard, a touch screen, a microphone, etc.
S406: the computer device determines whether the input instruction is a abort instruction.
In this example, since the input instruction of the engineer may be a confirmation instruction, or may be a discard instruction indicating discarding the configuration of the target device with the configuration instruction or an adjustment instruction indicating modifying the configuration instruction, the computer device needs to recognize the type of the input instruction after receiving the input instruction. If the computer device determines that the input instruction is a discard instruction, the flow may be ended, otherwise S408 is executed.
S408: the computer device determines whether the input instruction is a confirmation instruction.
If yes, then execution is S410, otherwise execution is S412.
S410: the computer device configures the target device with the confirmed configuration instruction.
After the computer device receives the confirmation instruction, it may configure the target device with the configuration instruction that has been confirmed by the engineering personnel, for example, the computer device sends the configuration instruction that has been confirmed by the engineering personnel to the OLT to configure the OLT.
S412: the computer equipment receives the editing instruction and updates the configuration instruction according to the editing instruction.
If the computer equipment determines that the input instruction of the engineering personnel is not the abandon instruction and the confirm instruction after the judgment, the input instruction is the adjustment instruction. In this case, the computer device may show an instruction editing interface through the display screen in which the current configuration instruction may be displayed, but the configuration instruction in the editing interface is in an editable state. Meanwhile, the computer equipment receives an editing instruction sent by engineering personnel through the input unit, modifies the configuration instruction according to the editing instruction, and displays the updated configuration instruction.
The engineering personnel can modify the configuration instruction according to the actual situation until the engineering personnel considers that the configuration instruction is correct, and after the engineering personnel can be used for configuring the target equipment, a confirmation instruction can be input into the computer equipment, and the computer equipment can execute S404.
According to the equipment configuration method provided by the example, an engineer describes a configuration target for target equipment to computer equipment in a conventional natural language, a computer can perform intention vector conversion through an initial configuration command of the engineer, an original intention answer corresponding to the intention vector is matched in a data resource library, then the original intention answer is subjected to secondary processing by adopting a language processing model such as LLM (logical level management) to obtain a configuration command, the computer equipment displays the configuration command to the engineer, the engineer can adjust and revise the configuration command so as to enable the configuration command to be more in accordance with the configuration specification, and finally the computer equipment configures the target equipment according to the configuration command confirmed by the engineer. In the equipment configuration scheme, configuration instructions are mainly provided by computer equipment according to the natural language of configuration personnel, so that the instruction writing workload in the configuration process is reduced, program errors caused by manual instruction writing are avoided, meanwhile, engineering personnel can check and keep watch on the configuration instructions provided by the computer equipment, the accuracy of equipment configuration is improved, and the safety and stability of target equipment are ensured.
Embodiment two:
in order to make the details and advantages of the solution in the foregoing embodiments more clear for those skilled in the art, the present embodiment will further describe the device configuration solution by taking the target device to be configured as the OLT, please refer to fig. 6 and fig. 7:
s602: the computer device receives an initial-configuration command described in natural language by an engineer.
Assume here that the initial configuration instruction received by the computer device through the keyboard is "configure GE port 0/0/1 into trunk mode".
S604: the computer equipment performs sentence segmentation on the initial configuration command through a Prompt engine to obtain a plurality of keywords.
After receiving the initial configuration command, the computer device may preprocess the initial configuration command, for example, the computer device may divide the initial configuration command into keywords by using a Prompt engine, for example, the computer device may divide the initial configuration command into "will", "GE port", "configure", "get", "trunk", "mode".
S606: the computer equipment adopts LLM to carry out part-of-speech tagging and dependency syntactic analysis on the keywords to obtain an intention vector.
Then, the computer device adopts LLM to carry out part-of-speech tagging and dependency syntax analysis on the obtained keywords, determines the syntax structure of the initial configuration command and the intention corresponding to the initial configuration command, and further generates an intention vector corresponding to the initial configuration command.
S608: the computer device matches the original intent answer for the intent vector in External Cognitive Assets, generating a list of original intent answers.
After obtaining the intent vector, the computer device may match the intent vector with rules in External Cognitive Assets and answer data, thereby obtaining a plurality of original intent answers corresponding to the intent vector, and the computer device may form an original intent answer list according to the plurality of original intent answers.
S610: the computer device adopts LLM to carry out secondary processing on the original intention answer list, and displays configuration instructions to engineering personnel.
After the original intention answer list is obtained, the computer equipment can adopt LLM to carry out secondary processing on the original intention answer list, so as to obtain a configuration instruction meeting the requirement of the OLT. The computer device then displays the configuration instructions to the engineering personnel via either the GUI or the CLI, such as shown in FIG. 5.
S612: and the computer equipment receives the confirmation instruction of the engineering personnel and sends the configuration instruction to the OLT.
After the engineering personnel checks the configuration instruction through the GUI or the CLI of the computer equipment, if the configuration instruction is confirmed to be correct, the computer equipment can send the confirmation instruction to the computer equipment, and the computer equipment sends the configuration instruction confirmed by the user to the OLT according to the confirmation instruction so as to be configured by the OLT. If the engineering personnel consider that the configuration instruction has more problems and is not available, the engineering personnel can send a discard instruction to the computer equipment, so that the computer equipment does not configure the OLT according to the configuration instruction. If the engineer determines that some problems exist in the configuration instructions but the problems are not more, the engineer can send an adjustment instruction to the computer equipment to control the computer equipment to enter an editing mode, and then the engineer can send the editing instruction to the computer equipment to modify and update the configuration instructions. After the revision is completed, the engineering personnel can send a confirmation instruction to the computer equipment, so that the computer equipment can send the revised and updated configuration instruction to the OLT, and the OLT can complete the configuration.
In some examples of this embodiment, when the engineer determines that the accuracy of the configuration instruction provided by the computer device is insufficient, a secondary configuration command described in natural language may also be input to the computer device, where the secondary configuration command is used to further describe the configuration target based on the initial configuration command, so as to help the computer device understand the actual configuration target of the engineer. After the computer device receives the secondary configuration command, basically similar processing can be adopted for the secondary configuration command and the initial configuration command, for example, sentence segmentation, part-of-speech labeling, dependency syntax analysis and the like are carried out for the secondary configuration command, the intention vector is obtained, then the corresponding original intention answer is matched based on the intention vector, and then the corresponding configuration instruction is provided for the engineering personnel to confirm and modify based on the original intention answer. It will be appreciated that the engineer may decide whether to continue to enter new secondary configuration commands depending on the accuracy of the configuration instructions provided by the computer device.
S614: and the computer equipment receives the feedback information of the OLT equipment and feeds back a configuration result to the configuration engineering personnel according to the feedback information.
After the OLT receives the configuration instruction sent by the computer, the OLT configures the OLT according to the configuration instruction, after the configuration is completed, the OLT can carry the configuration result in feedback information and send the feedback information to the computer equipment, and the computer equipment can output the configuration result to engineering personnel so as to enable the engineering personnel to know whether the configuration of the OLT is successful or not.
The device configuration method provided by the embodiment realizes the conversion from natural language to the network device configuration instruction by using the AI technology, thereby greatly simplifying the configuration steps, reducing the configuration difficulty and the configuration threshold, enabling non-professional persons to configure the network device, and improving the configuration efficiency and the accuracy and promoting the popularization and the application of the network device.
Embodiment III:
the present embodiment first provides a device configuration apparatus 80, please refer to fig. 8: the device configuration apparatus 80 includes a command receiving module 802, a vector retrieving module 804, an answer retrieving module 806, and a device configuration module 808. Wherein, the command receiving module 802 is configured to receive an initial configuration command described in a natural language; the vector acquisition module 804 is configured to convert the initial configuration command into an intent vector; the answer obtaining module 806 is configured to match, in the data resource library, a plurality of original intention answers corresponding to the intention vectors; the device configuration module 808 is configured to configure the target device based on the original intent answer.
It should be understood that various modifications and specific examples of the device configuration method provided in the foregoing embodiment are equally applicable to the device configuration apparatus 80 in this embodiment, and those skilled in the art will clearly know the implementation method of the device configuration apparatus 80 in this embodiment through the foregoing detailed description of the device configuration method, which is not described in detail herein for brevity of description.
In order to better execute the program of the above method, the embodiment of the present application further provides a computer device 90, as shown in fig. 9, where the computer device 90 includes a processor 91, a memory 92, and a communication bus 93, where the communication bus 93 is used to implement a communication connection between the processor 91 and the memory 92. The memory 92 stores one or more computer programs, and the processor 91 is configured to execute the one or more computer programs stored in the memory 92, so as to implement the device configuration method provided in any one of the foregoing examples, and specific details of the device configuration method may be referred to the description of the foregoing embodiments, which are not repeated herein.
Wherein the memory 92 may be used to store instructions, programs, code sets, or instruction sets. The memory 92 may include a storage program area and a storage data area, wherein the storage program area may store instructions for implementing an operating system, instructions for at least one function, instructions for implementing the device configuration method provided by the above-described embodiments, and the like; the storage data area may store data and the like involved in the device configuration method provided in the above embodiment.
Processor 91 may include one or more processing cores. The processor 91 performs various functions of the present application and processes data by executing or executing instructions, programs, code sets, or instruction sets stored in the memory 92, invoking data stored in the memory 92. The processor 91 may be at least one of an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), a digital signal processor (Digital Signal Processor, DSP), a digital signal processing device (Digital Signal Processing Device, DSPD), a programmable logic device (Programmable Logic Device, PLD), a field programmable gate array (Field Programmable Gate Array, FPGA), a central processing unit (Central Processing Unit, CPU), a controller, a microcontroller, and a microprocessor. It will be appreciated that the electronic device for implementing the functions of the processor 91 may be other for different apparatuses, and the embodiments of the present application are not specifically limited.
The various modifications and specific examples of the device configuration method provided in the foregoing embodiment are equally applicable to the computer device 90 of the present embodiment, and those skilled in the art will clearly know the implementation method of the computer device 90 of the present embodiment through the foregoing detailed description of the device configuration method, which is not described in detail herein for brevity of description.
The computer device 90 provided in this embodiment may be implemented by at least one of a notebook computer, a desktop computer, a tablet computer, and even a mobile phone.
Embodiments of the present application provide a computer-readable storage medium, for example, comprising: a U-disk, a removable hard disk, a Read Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes. The computer-readable storage medium stores a computer program capable of being loaded by the processor 91 and executing the device configuration method of the above-described embodiment.
The foregoing embodiments are only used for describing the technical solution of the present application in detail, but the descriptions of the foregoing embodiments are only used for helping to understand the method and the core idea of the present application, and should not be construed as limiting the present application. Variations or alternatives that are readily contemplated by those skilled in the art within the scope of the present disclosure are intended to be encompassed within the scope of the present disclosure.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311213013.2A CN117636855A (en) | 2023-09-19 | 2023-09-19 | Device configuration method, computer device and computer-readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311213013.2A CN117636855A (en) | 2023-09-19 | 2023-09-19 | Device configuration method, computer device and computer-readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117636855A true CN117636855A (en) | 2024-03-01 |
Family
ID=90029363
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311213013.2A Pending CN117636855A (en) | 2023-09-19 | 2023-09-19 | Device configuration method, computer device and computer-readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117636855A (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110046227A (en) * | 2019-04-17 | 2019-07-23 | 腾讯科技（深圳）有限公司 | Configuration method, exchange method, device, equipment and the storage medium of conversational system |
| CN111400340A (en) * | 2020-03-12 | 2020-07-10 | 杭州城市大数据运营有限公司 | Natural language processing method and device, computer equipment and storage medium |
| CN115847400A (en) * | 2022-11-24 | 2023-03-28 | 珠海格力电器股份有限公司 | Robot control method, device, computer-readable storage medium and electronic equipment |
| CN116541497A (en) * | 2023-04-25 | 2023-08-04 | 百度时代网络技术（北京）有限公司 | Task type dialogue processing method, device, equipment and storage medium |
| CN116561251A (en) * | 2023-04-24 | 2023-08-08 | 北京芯水科技有限公司 | A method of natural language processing |
| CN116595029A (en) * | 2023-04-17 | 2023-08-15 | 深圳市和讯华谷信息技术有限公司 | Automatic SQL sentence generation method and related equipment |
| CN116644145A (en) * | 2023-07-26 | 2023-08-25 | 北京仁科互动网络技术有限公司 | Session data processing method, device, equipment and storage medium |
| WO2023161630A1 (en) * | 2022-02-22 | 2023-08-31 | Unlikely Artificial Intelligence Limited | Computer implemented methods for the automated analysis or use of data, including use of a large language model |
| CN116700839A (en) * | 2023-07-31 | 2023-09-05 | 腾讯科技（深圳）有限公司 | A task processing method, device, equipment, storage medium and program product |
-
2023
- 2023-09-19 CN CN202311213013.2A patent/CN117636855A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110046227A (en) * | 2019-04-17 | 2019-07-23 | 腾讯科技（深圳）有限公司 | Configuration method, exchange method, device, equipment and the storage medium of conversational system |
| CN111400340A (en) * | 2020-03-12 | 2020-07-10 | 杭州城市大数据运营有限公司 | Natural language processing method and device, computer equipment and storage medium |
| WO2023161630A1 (en) * | 2022-02-22 | 2023-08-31 | Unlikely Artificial Intelligence Limited | Computer implemented methods for the automated analysis or use of data, including use of a large language model |
| CN115847400A (en) * | 2022-11-24 | 2023-03-28 | 珠海格力电器股份有限公司 | Robot control method, device, computer-readable storage medium and electronic equipment |
| CN116595029A (en) * | 2023-04-17 | 2023-08-15 | 深圳市和讯华谷信息技术有限公司 | Automatic SQL sentence generation method and related equipment |
| CN116561251A (en) * | 2023-04-24 | 2023-08-08 | 北京芯水科技有限公司 | A method of natural language processing |
| CN116541497A (en) * | 2023-04-25 | 2023-08-04 | 百度时代网络技术（北京）有限公司 | Task type dialogue processing method, device, equipment and storage medium |
| CN116644145A (en) * | 2023-07-26 | 2023-08-25 | 北京仁科互动网络技术有限公司 | Session data processing method, device, equipment and storage medium |
| CN116700839A (en) * | 2023-07-31 | 2023-09-05 | 腾讯科技（深圳）有限公司 | A task processing method, device, equipment, storage medium and program product |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11720756B2 (en) | Deriving multiple meaning representations for an utterance in a natural language understanding (NLU) framework | |
| CN108847241B (en) | Method for recognizing conference voice as text, electronic device and storage medium | |
| US10970487B2 (en) | Templated rule-based data augmentation for intent extraction | |
| CN111402861B (en) | Voice recognition method, device, equipment and storage medium | |
| CN101189659B (en) | Interactive dialogue for cognitively overloaded device users | |
| CN107193807B (en) | Language conversion processing method, device and terminal based on artificial intelligence | |
| US20210209164A1 (en) | Method, apparatus, and storage medium for recommending interactive information | |
| CN110765759B (en) | Intention recognition method and device | |
| WO2015147702A1 (en) | Voice interface method and system | |
| US8509396B2 (en) | Automatic creation of complex conversational natural language call routing system for call centers | |
| KR20210156223A (en) | Method and device for training machine translation model, electronic equipment and storage medium | |
| CN109522564B (en) | Speech translation method and device | |
| CN111667833A (en) | Speech recognition based on conversation | |
| CN104679733B (en) | A kind of voice dialogue interpretation method, apparatus and system | |
| CN112466289A (en) | Voice instruction recognition method and device, voice equipment and storage medium | |
| CN111399629B (en) | Operation guiding method of terminal equipment, terminal equipment and storage medium | |
| CN111968646A (en) | Voice recognition method and device | |
| CN112818096A (en) | Dialog generating method and device | |
| WO2024187581A1 (en) | Multi-round dialogue method and apparatus for dynamic government affair updating, and electronic device | |
| CN104062910A (en) | Command generation device, and equipment intelligent control method and system | |
| KR20210051523A (en) | Dialogue system by automatic domain classfication | |
| CN117636855A (en) | Device configuration method, computer device and computer-readable storage medium | |
| CN111161735A (en) | Voice editing method and device | |
| CN117291196A (en) | Methods, devices, electronic devices and media for speech translation | |
| CN116312472A (en) | Robot speech group design method, device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20240301 |
|
| RJ01 | Rejection of invention patent application after publication |