CN116820895B - Log grabbing method, device, equipment and medium based on artificial intelligence - Google Patents
Log grabbing method, device, equipment and medium based on artificial intelligence Download PDFInfo
- Publication number
- CN116820895B CN116820895B CN202311093994.1A CN202311093994A CN116820895B CN 116820895 B CN116820895 B CN 116820895B CN 202311093994 A CN202311093994 A CN 202311093994A CN 116820895 B CN116820895 B CN 116820895B
- Authority
- CN
- China
- Prior art keywords
- log
- target
- grabbing
- current
- preset
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3003—Monitoring arrangements specially adapted to the computing system or computing system component being monitored
- G06F11/3024—Monitoring arrangements specially adapted to the computing system or computing system component being monitored where the computing system component is a central processing unit [CPU]
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3051—Monitoring arrangements for monitoring the configuration of the computing system or of the computing system component, e.g. monitoring the presence of processing resources, peripherals, I/O links, software programs
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3065—Monitoring arrangements determined by the means or processing involved in reporting the monitored data
- G06F11/3072—Monitoring arrangements determined by the means or processing involved in reporting the monitored data where the reporting involves data filtering, e.g. pattern matching, time or event triggered, adaptive or policy-based reporting
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3089—Monitoring arrangements determined by the means or processing involved in sensing the monitored data, e.g. interfaces, connectors, sensors, probes, agents
- G06F11/3093—Configuration details thereof, e.g. installation, enabling, spatial arrangement of the probes
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Quality & Reliability (AREA)
- Mathematical Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Debugging And Monitoring (AREA)
Abstract
The application discloses a log grabbing method, device, equipment and medium based on artificial intelligence, wherein the method comprises the following steps: acquiring a current log grabbing instruction; the current log grabbing instruction is in any one of text and voice; extracting a target keyword in a current log grabbing instruction by using a target artificial intelligence pre-training transformation model, and screening a target communication protocol and a target log protocol corresponding to the target keyword from a plurality of preset communication protocols and a plurality of preset log protocols; and grabbing log information from a target chip platform corresponding to the current log grabbing instruction based on the target communication protocol and the target log protocol, if the data volume of the log information is larger than a preset threshold value, segmenting the log information to obtain a plurality of sub-log information, and sequentially storing the sub-log information to a target storage disk. The difficulty and complexity of log grabbing are reduced, and the log grabbing efficiency is improved.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a log grabbing method, device, equipment and medium based on artificial intelligence.
Background
When log data capture is performed, the communication protocols and log protocols for log capture are different for the wireless modules under different chip platforms, that is, users need to rely on log capture tools of specific communication protocols and log protocols when capturing the related log data of the wireless module side under different chip platforms, so that the communication protocols and the log protocols corresponding to different chip platforms cannot be mutually adapted, multiplexed and commonly used, related codes are required to be independently developed and maintained for log capture under different chip platforms, the complexity of log capture is increased, and the existing log capture tools are mechanized and solidified, namely, professionals are required to capture the log according to instruction manuals, so that the difficulty of log capture is improved, and the efficiency is reduced.
In summary, how to reduce the difficulty and complexity of log grabbing and improve the log grabbing efficiency is a problem to be solved in the field.
Disclosure of Invention
In view of the above, the present invention aims to provide a log grabbing method, device, equipment and medium based on artificial intelligence, which reduce the difficulty and complexity of log grabbing and improve the log grabbing efficiency. The specific scheme is as follows:
In a first aspect, the present application discloses a log grabbing method based on artificial intelligence, which is applied to a preset general log grabbing tool deployed in a host, and includes:
acquiring a current log grabbing instruction; the format of the current log grabbing instruction is any one format of words and voices;
extracting a target keyword in the current log grabbing instruction by using a target artificial intelligence pre-training transformation model, and screening a target communication protocol and a target log protocol corresponding to the target keyword from a plurality of preset communication protocols and a plurality of preset log protocols;
based on the target communication protocol and the target log protocol, capturing log information from a target chip platform corresponding to the current log capturing instruction, and judging whether the data volume of the log information is larger than a preset threshold value;
if yes, dividing the log information to obtain a plurality of sub-log information, and sequentially storing the sub-log information to a target storage disk.
Optionally, the extracting the target keyword in the current log grabbing instruction by using the target artificial intelligence pre-training transformation model includes:
identifying and analyzing the current log grabbing instruction by utilizing a target artificial intelligence pre-training transformation model so as to convert the language form of the current log grabbing instruction from a natural language form to a machine language form, and obtaining a converted log grabbing instruction;
And extracting target keywords in the converted log grabbing instruction.
Optionally, the extracting the target keyword in the current log grabbing instruction by using a target artificial intelligence pre-training transformation model and screening a target communication protocol and a target log protocol corresponding to the target keyword from a plurality of preset communication protocols and a plurality of preset log protocols include:
extracting target keywords in the current log grabbing instruction by using a target artificial intelligence pre-training transformation model; the target key words comprise chip types and belonged items corresponding to the current log grabbing instructions;
generating corresponding first prompt information based on the target keyword, so that a user can judge whether to execute a grabbing task corresponding to the current log grabbing instruction based on the first prompt information, and feeding back a judging result to the preset general log grabbing tool;
and if the judging result represents that the grabbing task is executed, screening a target communication protocol and a target log protocol corresponding to the chip type and the item by utilizing the target artificial intelligence pre-training transformation model from a plurality of preset communication protocols and a plurality of preset log protocols.
Optionally, the screening, by using the target artificial intelligence pre-training transformation model, the target communication protocol and the target log protocol corresponding to the chip type and the item to which the chip type belongs from a plurality of preset communication protocols and a plurality of preset log protocols includes:
determining a target chip platform corresponding to the current log grabbing instruction based on the chip type and the item, and judging whether the target chip platform is connected with the host;
if the target chip platform is connected with the host, judging whether a target port for connecting the target chip platform with the host exists in the host;
and if the target port exists in the host, screening a target communication protocol and a target log protocol corresponding to the chip type and the item by utilizing the target artificial intelligence pre-training transformation model from a plurality of preset communication protocols and a plurality of preset log protocols.
Optionally, the sequentially storing the sub-log information to a target storage disk includes:
determining a target storage disk for storing the log information, and judging whether the current storable space of the target storage disk is smaller than the required storage space of the log information;
And if the current storable space of the target storage disk is not smaller than the required storage space of the log information, displaying the storage path of the target storage disk in a preset user interface, and sequentially storing the sub-log information to the target storage disk.
Optionally, before the obtaining the current log grabbing instruction, the method further includes:
collecting training data; the training data comprises a history log type, a history chip type, a history log acquisition mode, a history log segmentation mode, a preset log protocol, a preset communication protocol, a text format history log grabbing instruction and a voice format history log grabbing instruction;
and training the initial artificial intelligence pre-training transformation model by utilizing the training data to obtain a target artificial intelligence pre-training transformation model which accords with the expected training ending condition.
Optionally, the log grabbing method based on artificial intelligence further includes:
determining a current grabbing execution stage corresponding to the current moment;
generating second prompt information corresponding to the current grabbing execution stage, and displaying the second prompt information in a preset user interface;
determining a next capturing execution stage corresponding to the next moment, taking the next capturing execution stage as a current capturing execution stage, and re-jumping to the step of generating second prompt information corresponding to the current capturing execution stage, and displaying the second prompt information in a preset user interface.
In a second aspect, the application discloses a log grabbing device based on artificial intelligence, which is applied to a preset general log grabbing tool deployed in a host, and comprises:
the instruction acquisition module is used for acquiring a current log grabbing instruction; the format of the current log grabbing instruction is any one format of words and voices;
the protocol screening module is used for extracting target keywords in the current log grabbing instruction by using a target artificial intelligence pre-training transformation model and screening target communication protocols and target log protocols corresponding to the target keywords from a plurality of preset communication protocols and a plurality of preset log protocols;
the threshold judging module is used for grasping log information from a target chip platform corresponding to the current log grasping instruction based on the target communication protocol and the target log protocol and judging whether the data volume of the log information is larger than a preset threshold or not;
and the log storage module is used for dividing the log information if yes to obtain a plurality of sub-log information, and sequentially storing the sub-log information to a target storage disk.
In a third aspect, the present application discloses an electronic device comprising:
A memory for storing a computer program;
and a processor for executing the computer program to implement the steps of the artificial intelligence based log grabbing method disclosed above.
In a fourth aspect, the present application discloses a computer-readable storage medium for storing a computer program; wherein the computer program when executed by a processor implements the steps of the artificial intelligence based log grabbing method disclosed above.
The beneficial effects of the application are that: the application is applied to a preset universal log grabbing tool deployed in a host, and comprises the following steps: acquiring a current log grabbing instruction; the format of the current log grabbing instruction is any one format of words and voices; extracting a target keyword in the current log grabbing instruction by using a target artificial intelligence pre-training transformation model, and screening a target communication protocol and a target log protocol corresponding to the target keyword from a plurality of preset communication protocols and a plurality of preset log protocols; based on the target communication protocol and the target log protocol, capturing log information from a target chip platform corresponding to the current log capturing instruction, and judging whether the data volume of the log information is larger than a preset threshold value; if yes, dividing the log information to obtain a plurality of sub-log information, and sequentially storing the sub-log information to a target storage disk. Therefore, the format of the current log grabbing instruction obtained by the method can be any one format of words and voices, then the target key words in the current log grabbing instruction are extracted by using the target artificial intelligence pre-training transformation model, that is, log grabbing is completed in a man-machine interaction mode, the format of the current log grabbing instruction input by a user is not required, the operation is not required according to an instruction manual, the professional requirement on the user is reduced, the user can conveniently grab the log, further, the target communication protocol and the target log protocol corresponding to the target key words are screened from a plurality of preset communication protocols and a plurality of preset log protocols by using the target artificial intelligence pre-training transformation model, namely, the preset general log grabbing tool integrates the plurality of preset communication protocols and the preset log protocols, so that log grabbing can be completed for different chip platforms and log types, the universality is higher, log grabbing cannot be completed for different reasons such as the chip platforms and the log types, and the difficulty of log grabbing is reduced.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present invention, and that other drawings may be obtained according to the provided drawings without inventive effort to a person skilled in the art.
FIG. 1 is a flow chart of an artificial intelligence based log grabbing method disclosed in the present application;
FIG. 2 is a flowchart of a specific log grabbing method based on artificial intelligence disclosed in the present application;
FIG. 3 is a flowchart of another specific artificial intelligence based log grabbing method disclosed herein;
FIG. 4 is a diagram of a specific log grabbing structure disclosed herein;
FIG. 5 is a schematic diagram of a specific log collection disclosed herein;
fig. 6 is a schematic structural diagram of a log grabbing device disclosed in the present application;
fig. 7 is a block diagram of an electronic device disclosed in the present application.
Detailed Description
The following description of the technical solutions in the embodiments of the present application will be made clearly and completely with reference to the drawings in the embodiments of the present application, and it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
When log data capture is performed, the communication protocols and log protocols for log capture are different for the wireless modules under different chip platforms, that is, users need to rely on log capture tools of specific communication protocols and log protocols when capturing the related log data of the wireless module side under different chip platforms, so that the communication protocols and the log protocols corresponding to different chip platforms cannot be mutually adapted, multiplexed and commonly used, related codes are required to be independently developed and maintained for log capture under different chip platforms, the complexity of log capture is increased, and the existing log capture tools are mechanized and solidified, namely, professionals are required to capture the log according to instruction manuals, so that the difficulty of log capture is improved, and the efficiency is reduced.
Therefore, the log grabbing scheme is correspondingly provided, the difficulty and complexity of log grabbing are reduced, and the log grabbing efficiency is improved.
Referring to fig. 1, an embodiment of the present application discloses a log grabbing method based on artificial intelligence, which is applied to a preset general log grabbing tool deployed in a host, and includes:
Step S11: acquiring a current log grabbing instruction; the format of the current log grabbing instruction is any one format of words and voices.
In this embodiment, before the obtaining the current log grabbing instruction, the method further includes: collecting training data; the training data comprises a history log type, a history chip type, a history log acquisition mode, a history log segmentation mode, a preset log protocol, a preset communication protocol, a text format history log grabbing instruction and a voice format history log grabbing instruction; and training the initial artificial intelligence pre-training transformation model by utilizing the training data to obtain a target artificial intelligence pre-training transformation model which accords with the expected training ending condition. It can be understood that the initial artificial intelligence Pre-training transformation model (generating Pre-Trained Transformer, i.e. GPT) needs to be trained, so that the target artificial intelligence Pre-training transformation model obtained after training can be used for identifying log capturing instructions in various formats input by subsequent users, i.e. acquiring training data including a history log type, a history chip type, a history log acquisition mode, a history log segmentation mode, a preset log protocol, a preset communication protocol, a history log capturing instruction in a Text format and a history log capturing instruction in a voice format, the training data can be stored in a Text format, for example, a TXT File (Text File), the training data needs to be imported into a local environment or a cloud platform environment, then the training data is loaded into the GPT model, and appropriate training parameters are selected, then the initial artificial intelligence Pre-training transformation model is trained by using the training data until the training data accords with the expected end conditions, wherein the expected training end conditions can be iteration times in the training process, and can also be monitored by using a visual tool in the training process, i.e. monitoring the history log capturing instruction in the Text format, the history log capturing instruction in the voice format, the training data can also meet the expected training end conditions, the expected training request can be deployed by the model, and the learning source learning cost can be met by deploying the training model by the special learning source, the training platform, the training model can meet the requirements of the Pre-training model, and the learning cost can be met, and the specific learning environment cost can be met, and the training environment can be met, and the training model can be deployed by the training model is based on the special learning cost.
The input interface of the current log grabbing instruction can be provided on a preset user interface, the input interface can be a first input box for typing in a text format, and can also be a second input box for typing in a voice format, so that a user can select the format of the current log grabbing instruction according to specific conditions, a preset universal log grabbing tool can set a voice broadcasting function to interact with the user in a voice mode, a voice-to-text function and a text-to-voice function can be provided, and the current log grabbing instruction is converted in a format. The target artificial intelligence pre-training transformation model can be oriented to log grabbing instructions of different chip platforms, log types and different formats to complete log grabbing tasks, and the obtained current log grabbing instruction is, for example, a text format of ' I need grab the medemlog (modem log) of the B item in the chip platform A ', wherein the target keywords are the chip platform A and the B item ', that is, the current log grabbing instruction does not need to contain specific implementation details and only needs to contain corresponding requirements; it should be noted that, the current log grabbing instruction may further include other target keywords, such as a communication protocol, a log protocol, and keywords of how to divide log information later.
Step S12: extracting a target keyword in the current log grabbing instruction by using a target artificial intelligence pre-training transformation model, and screening a target communication protocol and a target log protocol corresponding to the target keyword from a plurality of preset communication protocols and a plurality of preset log protocols.
In this embodiment, the extracting, by using the target artificial intelligence pre-training transformation model, the target keyword in the current log grabbing instruction includes: identifying and analyzing the current log grabbing instruction by utilizing a target artificial intelligence pre-training transformation model so as to convert the language form of the current log grabbing instruction from a natural language form to a machine language form, and obtaining a converted log grabbing instruction; and extracting target keywords in the converted log grabbing instruction. It can be understood that the target artificial intelligence pre-training transformation model is required to be used for identifying and analyzing the current log grabbing instruction so as to convert the language form of the current log grabbing instruction from the natural language form to the machine language form, so that the target keywords in the converted log grabbing instruction can be extracted.
The target keyword may include a chip type corresponding to the current log grabbing instruction and an item to which the target keyword belongs, and further, the target artificial intelligence pre-training transformation model screens out a corresponding target communication protocol and a corresponding target log protocol from a plurality of preset communication protocols and a plurality of preset log protocols according to the chip type and the item to which the target artificial intelligence pre-training transformation model belongs; it should be noted that if the current log grabbing instruction includes not only the chip type and the item to which the current log grabbing instruction belongs, but also the communication protocol and the log protocol required in log grabbing, the communication protocol and the log protocol in the current log grabbing instruction can be directly used as the target communication protocol and the target log protocol.
Step S13: and grabbing log information from a target chip platform corresponding to the current log grabbing instruction based on the target communication protocol and the target log protocol, and judging whether the data volume of the log information is larger than a preset threshold value.
After the target communication protocol and the target log protocol are determined, log information can be captured from the target chip platform corresponding to the current log capturing instruction based on the target communication protocol and the target log protocol, whether the data volume of the log information is larger than a preset threshold value or not needs to be judged, if the data volume of the log information is not larger than the preset threshold value, namely if the data volume of the log information is smaller, the log information does not need to be divided, and the log information can be directly stored to a corresponding target storage disk.
Step S14: if yes, dividing the log information to obtain a plurality of sub-log information, and sequentially storing the sub-log information to a target storage disk.
If the data volume of the log information is larger and larger than the preset threshold, the log information can be segmented, and a plurality of sub-log information obtained after segmentation is sequentially transmitted to a target storage disk and stored, wherein the preset threshold can be preset by a user and can be contained in the current log grabbing instruction.
In this embodiment, the method further includes: determining a current grabbing execution stage corresponding to the current moment; generating second prompt information corresponding to the current grabbing execution stage, and displaying the second prompt information in a preset user interface; determining a next capturing execution stage corresponding to the next moment, taking the next capturing execution stage as a current capturing execution stage, and re-jumping to the step of generating second prompt information corresponding to the current capturing execution stage, and displaying the second prompt information in a preset user interface. In order to better provide man-machine interaction for users, prompt information for representing the grabbing progress can be displayed in real time, namely, the current grabbing execution stage corresponding to the current moment is determined, second prompt information for representing the current grabbing execution stage is displayed in a preset user interface, and updating of the current grabbing execution stage can be stopped when the current grabbing execution stage is the grabbing task ending stage.
The beneficial effects of the application are that: the application is applied to a preset universal log grabbing tool deployed in a host, and comprises the following steps: acquiring a current log grabbing instruction; the format of the current log grabbing instruction is any one format of words and voices; extracting a target keyword in the current log grabbing instruction by using a target artificial intelligence pre-training transformation model, and screening a target communication protocol and a target log protocol corresponding to the target keyword from a plurality of preset communication protocols and a plurality of preset log protocols; based on the target communication protocol and the target log protocol, capturing log information from a target chip platform corresponding to the current log capturing instruction, and judging whether the data volume of the log information is larger than a preset threshold value; if yes, dividing the log information to obtain a plurality of sub-log information, and sequentially storing the sub-log information to a target storage disk. Therefore, the format of the current log grabbing instruction obtained by the method can be any one format of words and voices, then the target key words in the current log grabbing instruction are extracted by using the target artificial intelligence pre-training transformation model, that is, log grabbing is completed in a man-machine interaction mode, the format of the current log grabbing instruction input by a user is not required, the operation is not required according to an instruction manual, the professional requirement on the user is reduced, the user can conveniently grab the log, further, the target communication protocol and the target log protocol corresponding to the target key words are screened from a plurality of preset communication protocols and a plurality of preset log protocols by using the target artificial intelligence pre-training transformation model, namely, the preset general log grabbing tool integrates the plurality of preset communication protocols and the preset log protocols, so that log grabbing can be completed for different chip platforms and log types, the universality is higher, log grabbing cannot be completed for different reasons such as the chip platforms and the log types, and the difficulty of log grabbing is reduced.
Referring to fig. 2, an embodiment of the present application discloses a specific log grabbing method based on artificial intelligence, which is applied to a preset general log grabbing tool deployed in a host, and includes:
step S21: acquiring a current log grabbing instruction; the format of the current log grabbing instruction is any one format of words and voices.
Step S22: extracting target keywords in the current log grabbing instruction by using a target artificial intelligence pre-training transformation model; the target key word comprises a chip type and an item corresponding to the current log grabbing instruction.
Step S23: and generating corresponding first prompt information based on the target keyword so that a user can judge whether to execute a grabbing task corresponding to the current log grabbing instruction based on the first prompt information and feed back a judging result to the preset general log grabbing tool.
In a first specific embodiment, the first prompt information generated according to the target keyword may represent that the log grabbing task corresponding to the target keyword has been performed currently, and then the user determines, based on the first prompt information, whether the grabbing task corresponding to the current log grabbing instruction needs to be executed again, so as to generate a determination result, and presets the general log grabbing tool to acquire the determination result.
In a second specific embodiment, the first prompt information generated according to the target keyword may represent a currently ready-to-execute crawling task, and the user may determine whether the currently ready-to-execute crawling task is consistent with a crawling task corresponding to the current log crawling instruction, so as to generate a determination result, and preset the general log crawling tool to obtain the determination result.
Step S24: and if the judging result represents that the grabbing task is executed, screening a target communication protocol and a target log protocol corresponding to the chip type and the item by utilizing the target artificial intelligence pre-training transformation model from a plurality of preset communication protocols and a plurality of preset log protocols.
In this embodiment, the screening, by using the target artificial intelligence pre-training transformation model, the target communication protocol and the target log protocol corresponding to the chip type and the item to which the chip type belongs from a plurality of preset communication protocols and a plurality of preset log protocols includes: determining a target chip platform corresponding to the current log grabbing instruction based on the chip type and the item, and judging whether the target chip platform is connected with the host; if the target chip platform is connected with the host, judging whether a target port for connecting the target chip platform with the host exists in the host; and if the target port exists in the host, screening a target communication protocol and a target log protocol corresponding to the chip type and the item by utilizing the target artificial intelligence pre-training transformation model from a plurality of preset communication protocols and a plurality of preset log protocols. It can be understood that before executing the grabbing task, it needs to determine whether the target chip platform to be subjected to log grabbing is connected with the host, if so, whether a target port for connecting the target chip platform with the host exists in the host, and only when the target port for connecting the target chip platform with the host exists in the host, the subsequent log grabbing task can be performed.
Step S25: and grabbing log information from a target chip platform corresponding to the current log grabbing instruction based on the target communication protocol and the target log protocol, and judging whether the data volume of the log information is larger than a preset threshold value.
Step S26: if yes, dividing the log information to obtain a plurality of sub-log information, and sequentially storing the sub-log information to a target storage disk.
Therefore, the method and the device support log grabbing instructions in various formats, provide various ways for users to input the current log grabbing instructions, improve user experience, and reduce requirements and difficulty for user expertise without specific implementation of grabbing details of user relations; before log grabbing, judging whether a host is connected with a target chip platform or not and whether a port connected with the target chip exists or not, so that task grabbing can be completed later, task grabbing under the condition that the host and the target chip are not successfully connected is avoided, and working procedures and time are wasted; the preset general log grabbing tool integrates a plurality of preset communication protocols and preset log protocols in advance, so log grabbing can be completed aiming at different chip platforms and projects, and the general log grabbing tool is higher in universality and more stable.
Referring to fig. 3, an embodiment of the present application discloses a log grabbing method based on artificial intelligence, which is applied to a preset general log grabbing tool deployed in a host, and includes:
step S31: acquiring a current log grabbing instruction; the format of the current log grabbing instruction is any one format of words and voices.
Step S32: extracting a target keyword in the current log grabbing instruction by using a target artificial intelligence pre-training transformation model, and screening a target communication protocol and a target log protocol corresponding to the target keyword from a plurality of preset communication protocols and a plurality of preset log protocols.
In this embodiment, on the one hand, a communication mechanism adapting function of different projects under different chip platforms is provided, which mainly supports COM (Communication) communication, socket communication, webSocket communication, MBIM (Mobile Broadband Interface Model, i.e., mobile broadband interface module) communication, IPC communication (Inter-Process Communication, i.e., network Inter-process communication), RPC (Remote Procedure Call Protocol, i.e., remote procedure call protocol) communication and callable function interfaces corresponding to each communication protocol thereof; on the other hand, log protocol adaptation functions of different items under different chip platforms are also provided, for example: support TVL (Tag Length Value) codec functions, support high-pass 7E instruction set codec functions, etc.
Step S33: and grabbing log information from a target chip platform corresponding to the current log grabbing instruction based on the target communication protocol and the target log protocol, and judging whether the data volume of the log information is larger than a preset threshold value.
Step S34: if yes, dividing the log information to obtain a plurality of sub-log information, determining a target storage disk for storing the log information, and judging whether the current storable space of the target storage disk is smaller than the required storage space of the log information.
It can be understood that before log information storage is performed, it is required to ensure that the target storage disk can store log information, that is, determine whether the current storable space of the target storage disk is smaller than the required storage space of the log information, and if the current storable space of the target storage disk is smaller than the required storage space of the log information, generate corresponding early warning information, so that a user can change the disk for storing the log information according to the early warning information.
Step S35: and if the current storable space of the target storage disk is not smaller than the required storage space of the log information, displaying the storage path of the target storage disk in a preset user interface, and sequentially storing the sub-log information to the target storage disk.
If the current storable space of the target storage disk is not smaller than the required storage space of the log information, a storage path of the target storage disk is generated and displayed in a preset user interface, so that a user can select whether the disk for storing the log information is higher or not, and if not, all sub-log information can be stored to the target storage disk.
Therefore, the method provides a set of design ideas with modularization, universality, reusability, high efficiency, tailorability, loose coupling, high cohesiveness, easy usability, robustness and robustness for the development of the preset general log grabbing tool, ensures that the developed preset general log grabbing tool is efficient, and simultaneously avoids the immeasurable errors in the use process of a user caused by the unstable factors of the preset general log grabbing tool. In addition, the design of the preset user interface of the preset general log grabbing tool follows the layout principles of easy operation, easy understanding, high efficiency and simplicity, and aims to enable a user to conveniently operate and quickly get on hand, so that the log grabbing difficulty is greatly reduced.
For example, a specific log capturing architecture diagram shown in fig. 4 is configured, a preset general log capturing tool is disposed in a host, a chip platform is located at a module side, the preset general log capturing tool includes a real-time data display component, a communication interface adapting component, and a target artificial intelligence pre-training transformation Model, the target artificial intelligence pre-training transformation Model includes a text voice recognition and analysis component, a log data acquisition and storage component, and a log protocol adapting component, where the real-time data display component is configured to display second prompt information for characterizing a current capturing execution stage in real time, the communication interface adapting component is configured to determine a corresponding target communication protocol by using the target artificial intelligence pre-training transformation Model, the text voice recognition and analysis component is configured to recognize and analyze a current log capturing instruction in text format or voice format, and further extract a target keyword, the log data acquisition and storage component is configured to acquire log information and store the acquired log information to a target disk, and the log protocol adapting component is configured to screen out a target log protocol. The following describes the present application by taking a specific log collection schematic diagram shown in fig. 5 as an example:
Step 1), acquiring a current log grabbing instruction of a file format or a current log grabbing instruction of a voice format input by a user; the current log grabbing instruction comprises a chip type and an item to which the chip type belongs;
step 2) identifying and analyzing the current log grabbing instruction by utilizing a target artificial intelligence pre-training transformation model so as to convert the language form of the current log grabbing instruction from a natural language form to a machine language form and obtain a converted log grabbing instruction;
step 3) extracting target keywords in the converted log grabbing instruction, namely the chip type and the item to which the converted log grabbing instruction belongs;
step 4) generating corresponding first prompt information based on the target keywords so that a user can judge whether to execute a grabbing task corresponding to the current log grabbing instruction or not based on the first prompt information;
step 5), if the obtained judgment result represents that the grabbing task is not executed, jumping to the step 1), and obtaining a next log grabbing instruction; if the obtained judging result represents that the grabbing task is executed, determining a target chip platform corresponding to the current log grabbing instruction based on the chip type and the item, and judging whether the target chip platform is connected with the host;
Step 6) if the target chip platform is connected with the host, judging whether a target port for connecting the target chip platform with the host exists in the host;
step 7) if a target port exists in the host, screening a target communication protocol and a target log protocol corresponding to the chip type and the item from a plurality of preset communication protocols and a plurality of preset log protocols by using a target artificial intelligence pre-training transformation model;
step 8) grabbing log information from a target chip platform corresponding to the current log grabbing instruction based on the target communication protocol and the target log protocol, and receiving an ending instruction when the log grabbing is completed;
step 9) displaying the grabbing result and a storage path of a target storage disk for storing the log information, and storing the log information into the target storage disk.
Referring to fig. 6, an embodiment of the present application discloses a log grabbing device based on artificial intelligence, which is applied to a preset general log grabbing tool deployed in a host, and includes:
the instruction acquisition module 11 is used for acquiring a current log grabbing instruction; the format of the current log grabbing instruction is any one format of words and voices;
The protocol screening module 12 is configured to extract a target keyword in the current log grabbing instruction by using a target artificial intelligence pre-training transformation model, and screen a target communication protocol and a target log protocol corresponding to the target keyword from a plurality of preset communication protocols and a plurality of preset log protocols;
a threshold value judging module 13, configured to grasp log information from a target chip platform corresponding to the current log grasping instruction based on the target communication protocol and the target log protocol, and judge whether a data amount of the log information is greater than a preset threshold value;
and the log saving module 14 is configured to divide the log information if yes, obtain a plurality of sub-log information, and sequentially save the sub-log information to the target storage disk.
The beneficial effects of the application are that: the application is applied to a preset universal log grabbing tool deployed in a host, and comprises the following steps: acquiring a current log grabbing instruction; the format of the current log grabbing instruction is any one format of words and voices; extracting a target keyword in the current log grabbing instruction by using a target artificial intelligence pre-training transformation model, and screening a target communication protocol and a target log protocol corresponding to the target keyword from a plurality of preset communication protocols and a plurality of preset log protocols; based on the target communication protocol and the target log protocol, capturing log information from a target chip platform corresponding to the current log capturing instruction, and judging whether the data volume of the log information is larger than a preset threshold value; if yes, dividing the log information to obtain a plurality of sub-log information, and sequentially storing the sub-log information to a target storage disk. Therefore, the format of the current log grabbing instruction obtained by the method can be any one format of words and voices, then the target key words in the current log grabbing instruction are extracted by using the target artificial intelligence pre-training transformation model, that is, log grabbing is completed in a man-machine interaction mode, the format of the current log grabbing instruction input by a user is not required, the operation is not required according to an instruction manual, the professional requirement on the user is reduced, the user can conveniently grab the log, further, the target communication protocol and the target log protocol corresponding to the target key words are screened from a plurality of preset communication protocols and a plurality of preset log protocols by using the target artificial intelligence pre-training transformation model, namely, the preset general log grabbing tool integrates the plurality of preset communication protocols and the preset log protocols, so that log grabbing can be completed for different chip platforms and log types, the universality is higher, log grabbing cannot be completed for different reasons such as the chip platforms and the log types, and the difficulty of log grabbing is reduced.
Further, the embodiment of the application also provides electronic equipment. Fig. 7 is a block diagram of an electronic device 20, according to an exemplary embodiment, and the contents of the diagram should not be construed as limiting the scope of use of the present application in any way.
Fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present application. Specifically, the method comprises the following steps: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input output interface 25, and a communication bus 26. Wherein the memory 22 is configured to store a computer program that is loaded and executed by the processor 21 to implement the relevant steps of the artificial intelligence based log grabbing method performed by an electronic device as disclosed in any of the foregoing embodiments.
In this embodiment, the power supply 23 is configured to provide an operating voltage for each hardware device on the electronic device; the communication interface 24 can create a data transmission channel between the electronic device and an external device, and the communication protocol to be followed is any communication protocol applicable to the technical solution of the present application, which is not specifically limited herein; the input/output interface 25 is used for acquiring external input data or outputting external output data, and the specific interface type thereof may be selected according to the specific application requirement, which is not limited herein.
Processor 21 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 21 may be implemented in at least one hardware form of DSP (Digital Signal Processing ), FPGA (Field-Programmable Gate Array, field programmable gate array), PLA (Programmable Logic Array ). The processor 21 may also comprise a main processor, which is a processor for processing data in an awake state, also called CPU (Central Processing Unit ); a coprocessor is a low-power processor for processing data in a standby state. In some embodiments, the processor 21 may integrate a GPU (Graphics Processing Unit, image processor) for rendering and drawing of content required to be displayed by the display screen. In some embodiments, the processor 21 may also include an AI (Artificial Intelligence ) processor for processing computing operations related to machine learning.
The memory 22 may be a carrier for storing resources, such as a read-only memory, a random access memory, a magnetic disk, or an optical disk, and the resources stored thereon include an operating system 221, a computer program 222, and data 223, and the storage may be temporary storage or permanent storage.
The operating system 221 is used for managing and controlling various hardware devices on the electronic device and the computer program 222, so as to implement the operation and processing of the processor 21 on the mass data 223 in the memory 22, which may be Windows, unix, linux. The computer program 222 may further include a computer program that can be used to perform other specific tasks in addition to the computer program that can be used to perform the artificial intelligence based log grabbing method performed by the electronic device as disclosed in any of the previous embodiments. The data 223 may include, in addition to data received by the electronic device and transmitted by the external device, data collected by the input/output interface 25 itself, and so on.
Further, the application also discloses a computer readable storage medium for storing a computer program; wherein the computer program, when executed by the processor, implements the artificial intelligence based log grabbing method disclosed above. For specific steps of the method, reference may be made to the corresponding contents disclosed in the foregoing embodiments, and no further description is given here.
In this specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, so that the same or similar parts between the embodiments are referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative elements and steps are described above generally in terms of functionality in order to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application. The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. The software modules may be disposed in random access Memory (Random Access Memory), memory, read-Only Memory (ROM), electrically programmable EPROM (Erasable Programmable Read Only Memory), electrically erasable programmable EEPROM (Electrically Erasable Programmable Read Only Memory), registers, hard disk, removable disk, CD-ROM (Compact Disc Read-Only Memory), or any other form of storage medium known in the art.
Finally, it is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The log grabbing method, device, equipment and medium based on artificial intelligence provided by the invention are described in detail, and specific examples are applied to illustrate the principle and implementation of the invention, and the description of the above examples is only used for helping to understand the method and core ideas of the invention; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present invention, the present description should not be construed as limiting the present invention in view of the above.
Claims (8)
1. The log grabbing method based on the artificial intelligence is characterized by being applied to a preset general log grabbing tool deployed in a host machine and comprising the following steps of:
acquiring a current log grabbing instruction; the format of the current log grabbing instruction is any one format of words and voices;
extracting a target keyword in the current log grabbing instruction by using a target artificial intelligence pre-training transformation model, and screening a target communication protocol and a target log protocol corresponding to the target keyword from a plurality of preset communication protocols and a plurality of preset log protocols;
based on the target communication protocol and the target log protocol, capturing log information from a target chip platform corresponding to the current log capturing instruction, and judging whether the data volume of the log information is larger than a preset threshold value;
if yes, dividing the log information to obtain a plurality of sub-log information, and sequentially storing the sub-log information to a target storage disk;
the extracting the target keyword in the current log grabbing instruction by using the target artificial intelligence pre-training transformation model and screening the target communication protocol and the target log protocol corresponding to the target keyword from a plurality of preset communication protocols and a plurality of preset log protocols comprises the following steps:
Extracting target keywords in the current log grabbing instruction by using a target artificial intelligence pre-training transformation model; the target key words comprise chip types and belonged items corresponding to the current log grabbing instructions; generating corresponding first prompt information based on the target keyword, so that a user can judge whether to execute a grabbing task corresponding to the current log grabbing instruction based on the first prompt information, and feeding back a judging result to the preset general log grabbing tool; if the judging result represents that the grabbing task is executed, screening a target communication protocol and a target log protocol corresponding to the chip type and the item by utilizing the target artificial intelligence pre-training transformation model from a plurality of preset communication protocols and a plurality of preset log protocols;
the screening, by using the target artificial intelligence pre-training transformation model, a target communication protocol and a target log protocol corresponding to the chip type and the item include:
determining a target chip platform corresponding to the current log grabbing instruction based on the chip type and the item, and judging whether the target chip platform is connected with the host; if the target chip platform is connected with the host, judging whether a target port for connecting the target chip platform with the host exists in the host; and if the target port exists in the host, screening a target communication protocol and a target log protocol corresponding to the chip type and the item by utilizing the target artificial intelligence pre-training transformation model from a plurality of preset communication protocols and a plurality of preset log protocols.
2. The method for capturing logs based on artificial intelligence according to claim 1, wherein the extracting the target keyword in the current log capturing instruction by using the target artificial intelligence pre-training transformation model comprises:
identifying and analyzing the current log grabbing instruction by utilizing a target artificial intelligence pre-training transformation model so as to convert the language form of the current log grabbing instruction from a natural language form to a machine language form, and obtaining a converted log grabbing instruction;
and extracting target keywords in the converted log grabbing instruction.
3. The artificial intelligence based log grabbing method of claim 1 or 2, wherein the sequentially saving the sub-log information to a target storage disk comprises:
determining a target storage disk for storing the log information, and judging whether the current storable space of the target storage disk is smaller than the required storage space of the log information;
and if the current storable space of the target storage disk is not smaller than the required storage space of the log information, displaying the storage path of the target storage disk in a preset user interface, and sequentially storing the sub-log information to the target storage disk.
4. The method for capturing logs based on artificial intelligence according to claim 1, further comprising, before the step of obtaining the current log capturing instruction:
collecting training data; the training data comprises a history log type, a history chip type, a history log acquisition mode, a history log segmentation mode, a preset log protocol, a preset communication protocol, a text format history log grabbing instruction and a voice format history log grabbing instruction;
and training the initial artificial intelligence pre-training transformation model by utilizing the training data to obtain a target artificial intelligence pre-training transformation model which accords with the expected training ending condition.
5. The artificial intelligence based log grabbing method of claim 1, further comprising:
determining a current grabbing execution stage corresponding to the current moment;
generating second prompt information corresponding to the current grabbing execution stage, and displaying the second prompt information in a preset user interface;
determining a next capturing execution stage corresponding to the next moment, taking the next capturing execution stage as a current capturing execution stage, and re-jumping to the step of generating second prompt information corresponding to the current capturing execution stage, and displaying the second prompt information in a preset user interface.
6. An artificial intelligence based log grabbing device, which is applied to a preset general log grabbing tool deployed in a host machine, comprising:
the instruction acquisition module is used for acquiring a current log grabbing instruction; the format of the current log grabbing instruction is any one format of words and voices;
the protocol screening module is used for extracting target keywords in the current log grabbing instruction by using a target artificial intelligence pre-training transformation model and screening target communication protocols and target log protocols corresponding to the target keywords from a plurality of preset communication protocols and a plurality of preset log protocols;
the threshold judging module is used for grasping log information from a target chip platform corresponding to the current log grasping instruction based on the target communication protocol and the target log protocol and judging whether the data volume of the log information is larger than a preset threshold or not;
the log storage module is used for dividing the log information to obtain a plurality of sub-log information if yes, and sequentially storing the sub-log information to a target storage disk;
the protocol screening module is specifically configured to:
extracting target keywords in the current log grabbing instruction by using a target artificial intelligence pre-training transformation model; the target key words comprise chip types and belonged items corresponding to the current log grabbing instructions; generating corresponding first prompt information based on the target keyword, so that a user can judge whether to execute a grabbing task corresponding to the current log grabbing instruction based on the first prompt information, and feeding back a judging result to the preset general log grabbing tool; if the judging result represents that the grabbing task is executed, screening a target communication protocol and a target log protocol corresponding to the chip type and the item by utilizing the target artificial intelligence pre-training transformation model from a plurality of preset communication protocols and a plurality of preset log protocols;
The protocol screening module is specifically configured to:
determining a target chip platform corresponding to the current log grabbing instruction based on the chip type and the item, and judging whether the target chip platform is connected with the host; if the target chip platform is connected with the host, judging whether a target port for connecting the target chip platform with the host exists in the host; and if the target port exists in the host, screening a target communication protocol and a target log protocol corresponding to the chip type and the item by utilizing the target artificial intelligence pre-training transformation model from a plurality of preset communication protocols and a plurality of preset log protocols.
7. An electronic device, comprising:
a memory for storing a computer program;
a processor for executing the computer program to implement the steps of the artificial intelligence based log grabbing method of any one of claims 1 to 5.
8. A computer-readable storage medium storing a computer program; wherein the computer program when executed by a processor implements the steps of the artificial intelligence based log grabbing method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311093994.1A CN116820895B (en) | 2023-08-29 | 2023-08-29 | Log grabbing method, device, equipment and medium based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311093994.1A CN116820895B (en) | 2023-08-29 | 2023-08-29 | Log grabbing method, device, equipment and medium based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116820895A CN116820895A (en) | 2023-09-29 |
| CN116820895B true CN116820895B (en) | 2024-01-05 |
Family
ID=88122469
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311093994.1A Active CN116820895B (en) | 2023-08-29 | 2023-08-29 | Log grabbing method, device, equipment and medium based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116820895B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111611021A (en) * | 2020-04-17 | 2020-09-01 | 深圳市广和通无线股份有限公司 | Log data transmission method and device, computer equipment and storage medium |
| CN111628967A (en) * | 2020-04-20 | 2020-09-04 | 深圳市广和通无线股份有限公司 | Log data transmission method and device, computer equipment and storage medium |
| CN111930592A (en) * | 2020-07-20 | 2020-11-13 | 国网浙江省电力有限公司嘉兴供电公司 | Method and system for detecting log sequence abnormity in real time |
| CN115576805A (en) * | 2022-09-27 | 2023-01-06 | 北京字跳网络技术有限公司 | Log display method, device, readable medium and electronic device |
-
2023
- 2023-08-29 CN CN202311093994.1A patent/CN116820895B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111611021A (en) * | 2020-04-17 | 2020-09-01 | 深圳市广和通无线股份有限公司 | Log data transmission method and device, computer equipment and storage medium |
| CN111628967A (en) * | 2020-04-20 | 2020-09-04 | 深圳市广和通无线股份有限公司 | Log data transmission method and device, computer equipment and storage medium |
| CN111930592A (en) * | 2020-07-20 | 2020-11-13 | 国网浙江省电力有限公司嘉兴供电公司 | Method and system for detecting log sequence abnormity in real time |
| CN115576805A (en) * | 2022-09-27 | 2023-01-06 | 北京字跳网络技术有限公司 | Log display method, device, readable medium and electronic device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116820895A (en) | 2023-09-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106992001B (en) | Voice instruction processing method, device and system | |
| CN109429522A (en) | Voice interactive method, apparatus and system | |
| CN103152244B (en) | A kind of method, device and communication system controlling immediate communication platform and communicate | |
| CN110992955A (en) | A voice operation method, device, device and storage medium of a smart device | |
| CN111462741B (en) | Voice data processing method, device and storage medium | |
| CN106504748A (en) | Voice control method and device | |
| CN106898349A (en) | A kind of Voice command computer method and intelligent sound assistant system | |
| US12277940B2 (en) | Packet loss recovery method for audio data packet, electronic device and storage medium | |
| CN111310071A (en) | A garbage classification method, device, equipment and storage medium | |
| JPH07222248A (en) | Method of using voice information in portable information terminals | |
| CN117749899A (en) | Protocol conversion framework, device communication method, device and computer storage medium | |
| CN116755844B (en) | Data processing method, device and equipment of simulation engine and storage medium | |
| CN116820895B (en) | Log grabbing method, device, equipment and medium based on artificial intelligence | |
| CN103079180A (en) | Method and system for remote assistance | |
| CN117111804A (en) | Information processing methods, devices, electronic equipment and storage media | |
| CN118972430A (en) | Device control method, system and storage medium | |
| CN115022304A (en) | Cross-platform file processing method, device and system for realizing IA (IA) based on RPA (resilient packet Access) and AI (Artificial Intelligence architecture) | |
| JP5041990B2 (en) | Software component extraction support device | |
| CN118012852A (en) | Method, system, electronic equipment and storage medium for processing session information | |
| CN114942890B (en) | User interface testing method, device, equipment and medium | |
| CN207051898U (en) | Information retrieval categorizing system based on cloud computing | |
| CN117672212A (en) | Voice interaction control method and device, electronic equipment and storage medium | |
| CN115762523A (en) | Fault record acquisition method and device, electronic equipment and readable storage medium | |
| CN118211570A (en) | Report automatic generation method, device, computer equipment and storage medium | |
| CN107283429A (en) | Control method, device, system and terminal based on artificial intelligence |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |