CN115033677A - Event processing method, device, equipment and medium based on conversation robot - Google Patents
Event processing method, device, equipment and medium based on conversation robot Download PDFInfo
- Publication number
- CN115033677A CN115033677A CN202210769373.XA CN202210769373A CN115033677A CN 115033677 A CN115033677 A CN 115033677A CN 202210769373 A CN202210769373 A CN 202210769373A CN 115033677 A CN115033677 A CN 115033677A
- Authority
- CN
- China
- Prior art keywords
- event processing
- instruction
- information
- event
- emergency
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
- G06F40/35—Discourse or dialogue representation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The disclosure provides an event processing method based on a conversation robot, which can be applied to the technical field of artificial intelligence and the technical field of finance. The method comprises the following steps: receiving session information from terminal equipment, wherein the session information carries an event processing request; carrying out rule analysis on the event processing request by using a rule analysis library to generate an event processing instruction; according to the event processing instruction, determining response information matched with the event processing instruction in an instruction configuration table; and sending response information to the emergency auxiliary system so that the emergency auxiliary system executes the response information to obtain an event processing result. The present disclosure also provides an event processing apparatus, device and medium based on the dialogue robot.
Description
Technical Field
The present disclosure relates to the field of artificial intelligence and financial technologies, and more particularly, to an event processing method, apparatus, device, and medium based on a conversation robot.
Background
In the related art, the emergency event processing flow generally includes that an event needing emergency processing is detected through monitoring, an event processing list is generated, and then, on-site operation and maintenance personnel send the event processing list to remote operation and maintenance personnel, so that the remote personnel can assist the on-site operation and maintenance personnel in processing through telephone communication, mails and the like according to the event processing list. In the emergency processing process, manual jumping query among a plurality of systems is generally needed, a large amount of information also needs to be manually acquired and analyzed, and remote operation and maintenance personnel are difficult to quickly respond to assistance operation required by field operation and maintenance personnel during emergency processing when busy in processing problems, so that the problems of long emergency processing time, slow processing and low emergency processing efficiency are caused, and the current emergency processing method is difficult to meet the requirement of quick emergency processing.
Disclosure of Invention
In view of the foregoing, the present disclosure provides a conversation robot-based event processing method, apparatus, device, medium, and product that can improve emergency processing efficiency.
One aspect of the present disclosure provides an event processing method based on a conversation robot, including: receiving session information from terminal equipment, wherein the session information carries an event processing request; utilizing a rule analysis library to perform rule analysis on the event processing request to generate an event processing instruction; according to the event processing instruction, determining response information matched with the event processing instruction in an instruction configuration table; and sending the response information to an emergency auxiliary system so that the emergency auxiliary system executes the response information to obtain an event processing result.
According to an embodiment of the present disclosure, the performing a rule analysis on the event processing request by using a rule analysis library, and generating an event processing instruction includes: based on a regular expression, inquiring whether text information matched with the event processing request exists in the rule analysis library; and generating the event processing command based on the text information when the text information matching the event processing request exists in the rule analysis library.
According to an embodiment of the present disclosure, the method further includes: and generating the event processing command by performing feature analysis on the event processing request when the text information matching the event processing request does not exist in the rule analysis library.
According to an embodiment of the present disclosure, the performing feature analysis on the event processing request and generating the event processing command includes: extracting feature information in the event processing request by using a text processing model based on natural language processing; and generating the event processing command based on the characteristic information.
According to the embodiment of the disclosure, a rule analysis library is utilized to perform rule analysis on the event processing request or perform feature analysis on the event processing request, and an event identifier associated with an event to be processed is obtained; the determining, according to the event processing instruction, response information that matches the event processing instruction in an instruction configuration table includes: according to the event processing instruction, searching a target instruction corresponding to the event processing instruction in the instruction configuration table; analyzing an application programming interface corresponding to the target instruction according to the target instruction; and filling the event identifier into the application programming interface to obtain the response information.
According to an embodiment of the present disclosure, the method further includes: acquiring input information, wherein the input information at least comprises one or more of texts, voices and images; and generating the event processing request based on the input information.
According to an embodiment of the present disclosure, the method further includes: extracting the content in the event result; splicing the content in the event result and the information template to generate event processing information; and sending the event processing information to the terminal equipment.
Another aspect of the present disclosure also provides an event processing apparatus including: the receiving module is used for receiving session information from the terminal equipment, wherein the session information carries an event processing request; the first analysis module is used for carrying out rule analysis on the event processing request by utilizing a rule analysis library to generate an event processing instruction; the determining module is used for determining response information matched with the event processing instruction in an instruction configuration table according to the event processing instruction; and the first sending module is used for sending the response information to the emergency auxiliary system so that the emergency auxiliary system executes the response information to obtain an event processing result.
Another aspect of the present disclosure also provides an electronic device including: one or more processors; storage means for storing one or more programs; wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to perform the method for session robot based event handling.
Another aspect of the present disclosure also provides a computer-readable storage medium having stored thereon executable instructions that, when executed by a processor, cause the processor to perform the above-described conversation robot-based event processing method.
Another aspect of the present disclosure also provides a computer program product comprising a computer program which, when executed by a processor, is used to implement the above-mentioned conversation robot-based event processing method.
According to the embodiment of the disclosure, the conversation robot receives the event processing request from the terminal equipment, the rule analysis library is used for carrying out rule analysis on the event processing request to obtain an event processing instruction, response information matched with the event processing instruction is quickly found in the instruction configuration table according to the event processing instruction, the conversation robot can make an emergency scheme according to the response information, and the emergency scheme is sent to the emergency auxiliary system for subsequent processing. Through the interactive mode of handling of conversation robot in emergency treatment process, this conversation robot can quick response incident processing request, obtain emergent scheme, not only liberate the manpower, can also shorten the time length of emergency treatment, at least partially overcome in the correlation technique because need manual work to handle or remote personnel when busy in handling the problem, the difficult problem that the emergency treatment time is long that leads to with the required assistance operation of quick response field personnel when emergency treatment, and then reached and made emergency treatment operation fast, improve the technological effect of emergency treatment efficiency, in order to satisfy the demand of quick emergency treatment.
Drawings
The foregoing and other objects, features and advantages of the disclosure will be apparent from the following description of embodiments of the disclosure, which proceeds with reference to the accompanying drawings, in which:
FIG. 1 schematically illustrates a system architecture diagram of a conversation robot-based event processing method and apparatus according to an embodiment of the present disclosure;
FIG. 2 schematically illustrates a flow diagram of a conversation robot-based event processing method in accordance with an embodiment of the present disclosure;
FIG. 3 schematically illustrates a conversation robot-based emergency event processing system, in accordance with an embodiment of the present disclosure;
fig. 4 schematically shows a block diagram of a structure of a conversation robot-based event processing apparatus according to an embodiment of the present disclosure;
fig. 5 schematically shows a block diagram of an electronic device adapted to implement a conversation robot-based business process method in accordance with an embodiment of the present disclosure.
Detailed Description
Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. It should be understood that these descriptions are illustrative only and are not intended to limit the scope of the present disclosure. In the following detailed description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the disclosure. It may be evident, however, that one or more embodiments may be practiced without these specific details. Moreover, in the following description, descriptions of well-known structures and techniques are omitted so as to not unnecessarily obscure the concepts of the present disclosure.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. The terms "comprises," "comprising," and the like, as used herein, specify the presence of stated features, steps, operations, and/or components, but do not preclude the presence or addition of one or more other features, steps, operations, or components.
All terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art unless otherwise defined. It is noted that the terms used herein should be interpreted as having a meaning that is consistent with the context of this specification and should not be interpreted in an idealized or overly formal sense.
Where a convention analogous to "at least one of A, B and C, etc." is used, in general such a construction is intended in the sense one having skill in the art would understand the convention (e.g., "a system having at least one of A, B and C" would include but not be limited to systems that have a alone, B alone, C alone, a and B together, a and C together, B and C together, and/or A, B, C together, etc.). Where a convention analogous to "A, B or at least one of C, etc." is used, in general such a construction is intended in the sense one having skill in the art would understand the convention (e.g., "a system having at least one of A, B or C" would include but not be limited to systems that have a alone, B alone, C alone, a and B together, a and C together, B and C together, and/or A, B, C together, etc.).
With the development of information technology, transaction services such as transfer and payment can be handled through banks not only in offline modes such as a website and a self-service machine, but also in online modes such as the internet. Different business scenarios may require different emergency plans. When the transaction service is abnormal, a first time is needed for response. In the related art, when an operation and maintenance worker handles an emergency, the operation and maintenance worker generally needs to jump to query among a plurality of systems, and particularly when the operation and maintenance worker is remote across specialties, departments, regions and the like, the operation and maintenance worker is difficult to quickly and accurately find corresponding emergency plans from a large number of emergency plans, and when the operation and maintenance worker handles other problems, the operation and maintenance worker is difficult to respond to query of various information required by the operation and maintenance worker on site for troubleshooting problems, so that the processing efficiency of the emergency is low.
In view of the above, the present disclosure provides a conversation robot-based event processing method, a conversation robot-based event processing apparatus, an electronic device, an overall readable storage medium, and a computer program product. The processing efficiency of emergency events can be improved. The method can comprise the following steps: receiving session information from terminal equipment, wherein the session information carries an event processing request; carrying out rule analysis on the event processing request by using a rule analysis library to generate an event processing instruction; according to the event processing instruction, determining response information matched with the event processing instruction in an instruction configuration table; and sending response information to the emergency auxiliary system so that the event processing system executes the response information to obtain an event processing result.
It should be noted that the method and the device for processing events based on the conversation robot, which are determined by the embodiments of the present disclosure, can be used in the technical field of artificial intelligence and the technical field of finance. The method and the device for processing the events based on the conversation robot, which are determined by the embodiment of the disclosure, can be used in any fields except the technical field of artificial intelligence and the technical field of finance. The application fields of the determined event processing method and device based on the conversation robot are not limited in the embodiment of the disclosure.
In the technical scheme of the disclosure, the collection, storage, use, processing, transmission, provision, disclosure, application and other processing of the personal information of the related user are all in accordance with the regulations of related laws and regulations, necessary confidentiality measures are taken, and the customs of the public order is not violated. In the technical scheme of the disclosure, before the personal information of the user is acquired or collected, the authorization or the consent of the user is acquired.
Fig. 1 schematically shows a system architecture diagram of a conversation robot-based event processing method and apparatus according to an embodiment of the present disclosure.
As shown in fig. 1, the system architecture 100 according to this embodiment may include terminal devices 101, 102, 103, a network 104, and a server 105. Network 104 is the medium used to provide communication links between terminal devices 101, 102, 103 and server 105. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
The user may use the terminal devices 101, 102, 103 to interact with the server 105 via the network 104 to receive or send message conversation information, event processing requests, and the like. The terminal devices 101, 102, 103 may have installed thereon various communication client applications, such as an emergency handling application, a shopping application, a web browser application, a search application, an instant messaging tool, a mailbox client, social platform software, etc. (by way of example only).
The terminal devices 101, 102, 103 may be various electronic devices having a display screen, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like.
The server 105 may be a conversation robot, and the server 105 may analyze or otherwise process conversation information or an event processing request transmitted by a user using the terminal apparatuses 101, 102, and 103, and feed back a processing result (e.g., an emergency processing result obtained from the event processing request) to the terminal apparatus.
It should be noted that the event processing method based on the conversation robot provided by the embodiment of the present disclosure may be generally executed by the server 105. Accordingly, the event processing device based on the conversation robot provided by the embodiment of the present disclosure may be generally disposed in the server 105. The event processing method based on the conversation robot provided by the embodiment of the present disclosure may also be executed by a server or a server cluster that is different from the server 105 and is capable of communicating with the terminal devices 101, 102, 103 and/or the server 105. Accordingly, the event processing device based on the conversation robot provided by the embodiment of the present disclosure may also be disposed in a server or a server cluster different from the server 105 and capable of communicating with the terminal devices 101, 102, 103 and/or the server 105.
It should be understood that the number of terminal devices, networks, and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for an implementation.
The conversation robot-based event processing method of the disclosed embodiment will be described in detail below with fig. 2 based on the scenario described in fig. 1.
Fig. 2 schematically shows a flowchart of a conversation robot-based event processing method according to an embodiment of the present disclosure.
As shown in fig. 2, the method includes operations S210 to S240.
In operation S210, session information from the terminal device is received, where the session information carries an event processing request.
In operation S220, the rule analysis library is used to perform rule analysis on the event processing request, and an event processing instruction is generated.
In operation S230, response information matching the event processing instruction is determined in the instruction configuration table according to the event processing instruction.
In operation S240, the response message is transmitted to the emergency assistance system, so that the emergency assistance system executes the response message, resulting in an event processing result.
According to the embodiment of the disclosure, the conversation robot can automatically listen to the conversation content of a plurality of operation and maintenance personnel, can also listen to the conversation sent by the operation and maintenance robot, and replies the emergency treatment result obtained according to the conversation content to the user. The event processing request in the dialogue content can be an emergency event needing to be processed, such as payment abnormity, transfer abnormity and the like in the transaction process, and can also be inquiry, analysis and the like operations needed in the process of processing the payment abnormity and the transfer abnormity.
According to an embodiment of the present disclosure, performing a rule analysis on the event processing request may be understood as performing a semantic analysis on the dialog content to convert the emergency event processing request into an emergency event processing instruction. Specifically, the dialog rule analysis library may be configured with a plurality of emergency event processing instructions, and during the rule analysis, the emergency event processing request and the emergency event processing instructions in the rule analysis library may be matched by a regular expression, so as to obtain an event processing instruction corresponding to the emergency event processing request in the rule analysis library. The rule analysis library can also enrich the emergency event processing instructions in the library continuously according to manual operation and maintenance experience so as to improve the diversity of the conversation robot in the aspect of response service.
According to an embodiment of the disclosure, a number of emergency event handling operations may be included in the instruction configuration table, which may serve as response information for the dialog robot to the emergency event handling request. The conversation robot can match the emergency event processing instruction obtained by analyzing the conversation content with the emergency event processing operation in the instruction configuration table to obtain the processing operation corresponding to the emergency event processing instruction, and send the emergency event processing operation to the emergency auxiliary system for execution. The emergency event processing operation in the instruction configuration table can be continuously enriched according to the manual operation and maintenance experience so as to improve the diversity of the conversation robot in the response service aspect.
According to the embodiment of the disclosure, the emergency assistance system may be a system for performing emergency event handling operations, and specifically, may be composed of platforms for providing services related to emergency, such as monitoring, performance capacity, log system, impact analysis, emergency plans, and emergency automation, where each platform is provided with an application programming interface, and the application programming interface may be called by an execution engine when emergency event handling operations need to be performed.
According to the embodiment of the disclosure, the emergency event processing result may be obtained by performing an emergency event processing operation, and may include, for example, invoked monitoring, a queried performance capacity parameter, an analyzed event processing influence, a queried emergency plan, and the like.
According to the embodiment of the disclosure, the conversation robot receives the event processing request from the terminal device, the rule analysis library is used for carrying out rule analysis on the event processing request to obtain an event processing instruction, response information matched with the event processing instruction is quickly found in the instruction configuration table according to the event processing instruction, the conversation robot can make an emergency plan according to the response information, and the emergency plan is sent to the emergency auxiliary system for subsequent processing. Through the interactive mode of handling of conversation robot in emergency treatment process, this conversation robot can quick response incident processing request, obtain emergent scheme, not only liberate the manpower, can also shorten the time length of emergency treatment, at least partially overcome in the correlation technique because need manual work to handle or remote personnel when busy in handling the problem, the difficult problem that the emergency treatment time is long that leads to with the required assistance operation of quick response field personnel when emergency treatment, and then reached and made emergency treatment operation fast, improve the technological effect of emergency treatment efficiency, in order to satisfy the demand of quick emergency treatment.
According to the embodiment of the disclosure, the emergency event processing request can be obtained not only by automatic listening of the conversation robot, but also by generating the emergency event processing request according to the input information, and specifically, the input information can be obtained, wherein the input information at least comprises one or more of text, voice and image; based on the input information, an event processing request is generated.
According to the embodiment of the disclosure, when the input information is a character, voice or an image, the subsequent semantic analysis can be directly performed, and the voice or the image can be preprocessed so as to convert the recognized content in the voice or the image into a character form and then perform the subsequent semantic analysis.
According to an embodiment of the present disclosure, operation S220 may further include the operations of: based on the regular expression, inquiring whether text information matched with the event processing request exists in the rule analysis library; in the case where text information matching the event processing request exists in the rule analysis library, an event processing instruction is generated based on the text information.
According to the embodiment of the disclosure, under the condition that the text information matched with the event processing request does not exist in the rule analysis library, the event processing request is subjected to feature analysis, and an event processing instruction is generated.
According to the embodiment of the disclosure, performing feature analysis on the event processing request, and generating the event processing instruction includes: extracting feature information in the event processing request by using a text processing model based on natural language processing; based on the characteristic information, an event processing instruction is generated.
According to the embodiment of the disclosure, the process of analyzing the emergency processing request to obtain the emergency processing instruction may be performed by rule analysis or feature analysis, for example, the rule analysis may be a priority rule, and in particular, in a case that the emergency processing instruction cannot be obtained after the rule analysis is performed on the emergency processing request, the feature analysis is further adopted to extract the emergency processing instruction.
According to an embodiment of the present disclosure, the text information may be a plurality of emergency event handling instructions configured in a dialog rules analysis library. And matching the emergency event processing request with the emergency event processing instruction in the rule analysis library through the regular expression in the rule analysis process, and finding the event processing instruction corresponding to the emergency event processing request in the rule analysis library. In the process of matching based on the regular expression, event identification associated with the event to be processed can be obtained from the emergency event processing request. The rule analysis library can also continuously enrich emergency event processing instructions in the library according to manual operation and maintenance experience so as to improve the diversity of the conversation robot in the response service aspect.
According to the embodiment of the disclosure, in a part of abnormal scenarios, since the content of the received emergency event processing request is complex, or the format or semantics of the received emergency event processing request may not be standard, it is difficult to match the event processing instruction corresponding to the emergency event processing request in the rule analysis library through the regular expression, and at this time, feature analysis needs to be performed on the emergency event processing request. In particular, features in the event processing request may be extracted using a natural language training model based on an intelligent machine learning algorithm. For example, in the case where the emergency event processing request is "query 123.4.5.6cpu usage", the extracted emergency processing instruction may be "query cpu", and the event id "123.4.5.6" may also be extracted. For another example, in a case where the emergency event request is "view 123.4.5.6 network connection status", the extracted emergency processing command may be "exec cmd", and the first event identifier "netstat" and the second event identifier "123.4.5.6" may also be extracted. The extracted event identifications may be subjected to regular expression filtering data to ensure that the extracted event identifications can be used in the subsequent process of determining emergency information.
According to the embodiment of the disclosure, the natural language training model based on the intelligent machine learning algorithm used in the feature analysis is trained by using a targeted corpus, such as a general Chinese and English corpus and an instruction type corpus. During training, the token and the dependency relation machine dependency vocabulary entry are emphasized to conduct training so as to extract the instruction. Compared with a natural language training model in the related technology, the natural language training model used in the method has the advantages of being more targeted to emergency events, and not needing massive corpora, so that the training process is simpler and more convenient.
According to the embodiment of the disclosure, the rule analysis is simpler, more convenient and faster than the characteristic analysis, so that the rule analysis is set to be preferentially adopted, and the conversation robot can further conveniently and rapidly carry out emergency event processing operation in the emergency processing process, so that the emergency processing efficiency is improved. In addition, by setting the characteristic analysis, the event processing request of which the rule analysis can not obtain the emergency event processing instruction can be analyzed, so that the emergency event processing request can be identified and processed more comprehensively, and the diversity and the flexibility of the conversation robot in the aspect of response service are improved.
According to an embodiment of the present disclosure, operation S230 may further include the operations of: according to the event processing instruction, searching a target instruction corresponding to the event processing instruction in an instruction configuration table; analyzing an application programming interface corresponding to the target instruction according to the target instruction; and filling the event identifier into an application programming interface to obtain response information.
According to the embodiment of the present disclosure, the target instruction found in the instruction configuration table according to the event processing instruction may be one or more of (query _ cpu, query _ mem, exec _ cmd … …); further, each instruction needs to be parsed to obtain an application programming interface corresponding to each target instruction, and the parsing process is, for example, (/ query/cpu,/query/mem,/exec/cmd … …); finally, the event identifier needs to be filled into the application program interface to obtain the response information, which can also be understood as obtaining the emergency treatment operation. The response information may be represented by ('/query/cpu/ip) 123.4.5.6', '/exec/cmd/script netstat & ip 123.4.5.6' …). The response information can be sent to an application programming interface corresponding to each emergency assistance platform in the emergency assistance system by an execution engine of the conversation robot, and various emergency treatment operations can be executed through the application programming interface.
According to the embodiment of the disclosure, in the execution process of the emergency auxiliary system, the application programming interface is adopted to be in butt joint with the existing emergency platforms such as monitoring, performance capacity, log system, influence analysis, emergency plan, emergency automation and the like, so that the problem that the information cannot be rapidly acquired on a plurality of systems by manpower is solved, and the efficiency of emergency treatment is improved.
According to the embodiment of the disclosure, after the event processing result is obtained, extracting the content in the event result; splicing the content in the event result and the information template to generate event processing information; and sending the event processing information to the terminal equipment.
According to the embodiment of the disclosure, after the emergency assistance system executes the response message, the application programming interface feeds back the execution result of the emergency event to the conversation robot. The dialogue robot can select silent reception and not feed back to the terminal equipment according to the execution result; or directly feeding back the execution result to the terminal equipment. For example, when the execution result is that the query is not available, the query content is not available, the data is empty, and the like, silent non-feedback may be selected, and these results may also be fed back to the terminal device. In the case where data or the like can be found or obtained, a corresponding event processing result may be fed back to the terminal device. The feedback can be made in one or more of text, voice and image.
According to the embodiment of the disclosure, when the event processing result is fed back to the terminal device, the content in the event information processing, such as the inquired data of performance, capacity, parameters and the like, can be extracted and combined with the originally set information template through content splicing to obtain and send the event processing information to the terminal device.
It should be noted that, unless explicitly stated that there is an execution sequence between different operations or there is an execution sequence between different operations in technical implementation, the execution sequence between multiple operations may not be sequential, or multiple operations may be executed simultaneously in the flowchart in this disclosure.
Fig. 3 schematically illustrates a conversation robot-based emergency event processing system according to an embodiment of the present disclosure.
As shown in fig. 3, the system may include a multi-person conversation module 301, a conversation bot module 302, and an emergency assistance module 303. The dialogue robot module may include a robot configuration submodule 3021 and a man-machine dialogue submodule 3022. The robot configuration submodule 3021 may further include a rule analysis library and an instruction configuration table. The man-machine conversation submodule 3022 further includes a conversation listening unit, a conversation analyzing unit, an instruction executing unit, and a question-answering and speaking unit.
According to the embodiment of the present disclosure, the multi-person dialogue module 301 may include dialogues of a plurality of operation and maintenance personnel, and may also be dialogues sent by the operation and maintenance robot. The multi-person conversation module 301 may be a front-end conversation interaction module, and is responsible for interactive presentation of the speech content, which may include text, voice, images, and video.
According to the embodiment of the disclosure, the interaction process with the conversation robot can be manually and actively sent to the conversation robot, and the conversation robot replies after receiving the instruction; the robot can also automatically listen to the multi-person conversation content and automatically answer. The dialogue listening unit listens to multi-person dialogue contents including characters, images and voice in the whole process. The dialogue analysis unit can carry out semantic analysis on the dialogue content to complete instruction extraction. The instruction execution unit can match the extracted instruction with the instruction configuration table, and the matched post-execution engine executes the related action. And the question-answering speaking unit determines whether to speak or not according to the instruction execution result, and if the speaking is required, the execution result is sent to the specified session, so that the cooperative emergency of the event is completed.
According to an embodiment of the present disclosure, the dialog analysis unit may further include a rule analysis and a feature analysis. And analyzing characters, voice and images related to the conversation content by using rule analysis and feature analysis, and extracting instructions.
According to the embodiment of the disclosure, the instruction configuration table is configured by the corresponding table of the instruction and the execution service, and the diversity of the response service of the conversation robot can be realized by continuously enriching the instruction configuration table. The instruction execution process may be to perform instruction matching in the instruction configuration table, find a corresponding service action after the instruction, and initiate instruction execution by the execution engine, where the specific instruction service corresponds to the application programming interface related to the emergency assistance system.
According to the embodiment of the disclosure, the emergency assistance module 303 may be a platform for monitoring, performance capacity, a log system, impact analysis, emergency plans, emergency automation, and the like, which are required for emergency decision analysis, emergency implementation, and emergency feedback in an emergency process.
According to the embodiment of the present disclosure, the answering and speaking process may be that the question and answering and speaking unit makes a judgment whether to answer or not according to a result of the instruction execution, and if speaking needs to be answered, the result of the instruction execution is sent to the multi-person conversation module 301, and the speaking content is characters, images or voice.
According to the embodiment of the disclosure, the requirements of diversity and rapidity of the required emergency auxiliary information in the emergency process are met by using a robot response mode, and the emergency timeliness is shortened; in addition, a multi-person collaborative conversation type emergency system is provided, which is more convenient for cross-department and cross-ground remote collaborative emergency and response processing of conversation contents in a real-time emergency collaborative process. The response rule adopts an instruction configuration table, semantic analysis is carried out on conversation contents in the conversation analysis process by using rule analysis and feature analysis, an instruction is extracted and then is delivered to an instruction execution engine for real-time execution, and more operation instructions can be supplemented in the instruction configuration table according to the experience of operation and maintenance personnel so as to realize the problems of diversity and flexibility of instruction rule configuration; the instruction execution service adopts an application programming interface mode to be connected with the existing emergency related systems such as monitoring, performance capacity, a log system, influence analysis, emergency plan, emergency automation and the like, the problem that the information can not be quickly acquired on a plurality of systems by manpower is solved, and the efficiency of emergency treatment is improved.
It should be noted that, the event processing system part based on the conversation robot in the embodiment of the present disclosure corresponds to the event processing method part based on the conversation robot in the embodiment of the present disclosure, and the description of the event processing system part based on the conversation robot specifically refers to the event processing method part based on the conversation robot, and is not described herein again.
Based on the event processing method based on the conversation robot, the disclosure also provides an event processing device based on the conversation robot. The apparatus will be described in detail below with reference to fig. 4.
Fig. 4 schematically shows a block diagram of a structure of a conversation robot-based event processing apparatus according to an embodiment of the present disclosure.
As shown in fig. 4, the conversation robot-based event processing apparatus 400 of this embodiment includes a receiving module 410, a first analyzing module 420, a determining module 430, and a first transmitting module 440.
The receiving module 410 is configured to receive session information from a terminal device, where the session information carries an event processing request.
The first analysis module 420 is configured to perform rule analysis on the event processing request by using the rule analysis library to generate an event processing instruction.
And the determining module 430 is configured to determine, according to the event processing instruction, response information matched with the event processing instruction in the instruction configuration table.
The first sending module 440 is configured to send the response message to the emergency assistance system, so that the emergency assistance system executes the response message to obtain an event processing result.
According to an embodiment of the present disclosure, the first analysis module further includes a first query unit and a first generation unit.
And the first searching unit is used for inquiring whether text information matched with the event processing request exists in the rule analysis library or not based on the regular expression.
And the first generation unit is used for generating the event processing instruction based on the text information under the condition that the text information matched with the event processing request exists in the rule analysis library.
According to an embodiment of the present disclosure, the conversation robot-based event processing apparatus may further include a second analysis module.
And the second analysis module is used for performing characteristic analysis on the event processing request to generate an event processing instruction under the condition that the text information matched with the event processing request does not exist in the rule analysis library.
According to an embodiment of the present disclosure, the second analysis module further comprises an extraction unit and a second generation unit.
And the extraction unit is used for extracting the characteristic information in the event processing request by using a text processing model based on natural language processing.
And the second generation unit is used for generating an event processing instruction based on the characteristic information.
According to an embodiment of the present disclosure, the determining module further includes a second lookup unit, a parsing unit, and a padding unit.
And the second searching unit is used for searching a target instruction corresponding to the event processing instruction in the instruction configuration table according to the event processing instruction.
And the analysis unit is used for analyzing the application programming interface corresponding to the target instruction according to the target instruction.
And the filling unit is used for filling the event identifier into the application programming interface to obtain the response information.
According to an embodiment of the present disclosure, the conversation robot-based event processing apparatus may further include an acquisition module and a generation module.
The acquisition module is used for acquiring input information, wherein the input information at least comprises one or more of text, voice and pictures.
And the generation module is used for generating an event processing request based on the input information.
According to an embodiment of the present disclosure, the conversation robot-based event processing apparatus may further include an extraction module, a concatenation module, and a second transmission module.
And the extraction module is used for extracting the content in the event result.
And the splicing module is used for splicing the identity and information templates in the event result to generate event processing information.
And the second sending module is used for sending the event processing information to the terminal equipment.
According to an embodiment of the present disclosure, any plurality of the receiving module 410, the first analyzing module 420, the determining module 430, and the first transmitting module 440 may be combined into one module to be implemented, or any one of them may be split into a plurality of modules. Alternatively, at least part of the functionality of one or more of these modules may be combined with at least part of the functionality of the other modules and implemented in one module. According to an embodiment of the present disclosure, at least one of the receiving module 410, the first analyzing module 420, the determining module 430, and the first sending module 440 may be implemented at least partially as a hardware circuit, such as a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a system on a chip, a system on a substrate, a system on a package, an Application Specific Integrated Circuit (ASIC), or may be implemented in hardware or firmware by any other reasonable manner of integrating or packaging a circuit, or implemented in any one of three implementations of software, hardware, and firmware, or in a suitable combination of any of them. Alternatively, at least one of the receiving module 410, the first analyzing module 420, the determining module 430 and the first transmitting module 440 may be at least partially implemented as a computer program module, which when executed, may perform a corresponding function.
It should be noted that, the part of the event processing device based on the conversational robot in the embodiment of the present disclosure corresponds to the part of the event processing method based on the conversational robot in the embodiment of the present disclosure, and the description of the part of the event processing device based on the conversational robot specifically refers to the part of the event processing method based on the conversational robot, and is not repeated here.
Fig. 5 schematically shows a block diagram of an electronic device adapted to implement a dialogue robot-based business process method according to an embodiment of the present disclosure.
As shown in fig. 5, an electronic device 500 according to an embodiment of the present disclosure includes a processor 501 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM)502 or a program loaded from a storage section 508 into a Random Access Memory (RAM) 503. The processor 501 may comprise, for example, a general purpose microprocessor (e.g., a CPU), an instruction set processor and/or associated chipset, and/or a special purpose microprocessor (e.g., an Application Specific Integrated Circuit (ASIC)), among others. The processor 501 may also include onboard memory for caching purposes. Processor 501 may include a single processing unit or multiple processing units for performing different actions of a method flow according to embodiments of the disclosure.
In the RAM 503, various programs and data necessary for the operation of the electronic apparatus 500 are stored. The processor 501, the ROM 502, and the RAM 503 are connected to each other through a bus 504. The processor 501 performs various operations of the method flows according to embodiments of the present disclosure by executing programs in the ROM 502 and/or RAM 503. Note that the program may also be stored in one or more memories other than the ROM 502 and the RAM 503. The processor 501 may also perform various operations of method flows according to embodiments of the present disclosure by executing programs stored in the one or more memories.
According to an embodiment of the present disclosure, electronic device 500 may also include an input/output (I/O) interface 505, input/output (I/O) interface 505 also being connected to bus 504. The electronic device 500 may also include one or more of the following components connected to the I/O interface 505: an input portion 506 including a keyboard, a mouse, and the like; an output portion 507 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage portion 508 including a hard disk and the like; and a communication section 509 including a network interface card such as a LAN card, a modem, or the like. The communication section 509 performs communication processing via a network such as the internet. The driver 510 is also connected to the I/O interface 505 as necessary. A removable medium 511 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 510 as necessary, so that a computer program read out therefrom is mounted into the storage section 508 as necessary.
The present disclosure also provides a computer-readable storage medium, which may be embodied in the device/apparatus/system described in the above embodiments; or may exist separately and not be assembled into the device/apparatus/system. The computer-readable storage medium carries one or more programs which, when executed, implement the method according to an embodiment of the disclosure.
According to embodiments of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, which may include, for example but is not limited to: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. For example, according to embodiments of the present disclosure, a computer-readable storage medium may include ROM 502 and/or RAM 503 and/or one or more memories other than ROM 502 and RAM 503 described above.
Embodiments of the present disclosure also include a computer program product comprising a computer program containing program code for performing the method illustrated in the flow chart. When the computer program product runs in a computer system, the program code is used for causing the computer system to realize the event processing method based on the conversation robot provided by the embodiment of the disclosure.
The computer program performs the above-described functions defined in the system/apparatus of the embodiments of the present disclosure when executed by the processor 501. The systems, apparatuses, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the present disclosure.
In one embodiment, the computer program may be hosted on a tangible storage medium such as an optical storage device, a magnetic storage device, or the like. In another embodiment, the computer program may also be transmitted, distributed in the form of a signal on a network medium, downloaded and installed through the communication section 509, and/or installed from the removable medium 511. The computer program containing program code may be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.
In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 509, and/or installed from the removable medium 511. The computer program, when executed by the processor 501, performs the above-described functions defined in the system of the embodiments of the present disclosure. The systems, devices, apparatuses, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the present disclosure.
In accordance with embodiments of the present disclosure, program code for executing computer programs provided by embodiments of the present disclosure may be written in any combination of one or more programming languages, and in particular, these computer programs may be implemented using high level procedural and/or object oriented programming languages, and/or assembly/machine languages. The programming language includes, but is not limited to, programming languages such as Java, C + +, python, the "C" language, or the like. The program code may execute entirely on the user computing device, partly on the user device, partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., through the internet using an internet service provider).
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
Those skilled in the art will appreciate that various combinations and/or combinations of features recited in the various embodiments and/or claims of the present disclosure can be made, even if such combinations or combinations are not expressly recited in the present disclosure. In particular, various combinations and/or combinations of the features recited in the various embodiments and/or claims of the present disclosure may be made without departing from the spirit or teaching of the present disclosure. All such combinations and/or associations are within the scope of the present disclosure.
The embodiments of the present disclosure have been described above. However, these examples are for illustrative purposes only and are not intended to limit the scope of the present disclosure. Although the embodiments are described separately above, this does not mean that the measures in the embodiments cannot be used in advantageous combination. The scope of the disclosure is defined by the appended claims and equivalents thereof. Various alternatives and modifications can be devised by those skilled in the art without departing from the scope of the present disclosure, and such alternatives and modifications are intended to be within the scope of the present disclosure.
Claims (11)
1. An event processing method based on a conversation robot comprises the following steps:
receiving session information from terminal equipment, wherein the session information carries an event processing request;
carrying out rule analysis on the event processing request by using a rule analysis library to generate an event processing instruction;
according to the event processing instruction, determining response information matched with the event processing instruction in an instruction configuration table;
and sending the response information to an emergency auxiliary system so that the emergency auxiliary system executes the response information to obtain an event processing result.
2. The method of claim 1, wherein the performing a rule analysis on the event processing request using a rule analysis repository, generating event processing instructions comprises:
based on a regular expression, inquiring whether text information matched with the event processing request exists in the rule analysis library;
and under the condition that text information matched with the event processing request exists in the rule analysis library, generating the event processing instruction based on the text information.
3. The method of claim 2, further comprising:
and under the condition that the text information matched with the event processing request does not exist in the rule analysis library, performing characteristic analysis on the event processing request to generate the event processing instruction.
4. The method of claim 3, wherein the performing a feature analysis on the event processing request, generating the event processing instruction comprises:
extracting feature information in the event processing request by using a text processing model based on natural language processing;
and generating the event processing instruction based on the characteristic information.
5. The method according to claim 1, wherein a rule analysis library is used for performing rule analysis on the event processing request or performing feature analysis on the event processing request, and an event identifier associated with the event to be processed is obtained;
the step of determining, according to the event processing instruction, response information matched with the event processing instruction in an instruction configuration table includes:
according to the event processing instruction, searching a target instruction corresponding to the event processing instruction in the instruction configuration table;
analyzing an application programming interface corresponding to the target instruction according to the target instruction;
and filling the event identifier into the application programming interface to obtain the response information.
6. The method of claim 1, further comprising:
acquiring input information, wherein the input information at least comprises one or more of text, voice and image;
generating the event processing request based on the input information.
7. The method of claim 1, further comprising:
extracting the content in the event result;
splicing the content in the event result and the information template to generate event processing information;
and sending the event processing information to the terminal equipment.
8. An event processing apparatus comprising:
the terminal equipment comprises a receiving module, a processing module and a sending module, wherein the receiving module is used for receiving dialogue information from the terminal equipment, and the dialogue information carries an event processing request;
the first analysis module is used for carrying out rule analysis on the event processing request by utilizing a rule analysis library to generate an event processing instruction;
the determining module is used for determining response information matched with the event processing instruction in an instruction configuration table according to the event processing instruction;
and the first sending module is used for sending the response information to an emergency auxiliary system so that the emergency auxiliary system executes the response information to obtain an event processing result.
9. An electronic device, comprising:
one or more processors;
a storage device for storing one or more programs,
wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to perform the method of any of claims 1-7.
10. A computer readable storage medium having stored thereon executable instructions which, when executed by a processor, cause the processor to perform the method of any one of claims 1 to 7.
11. A computer program product comprising a computer program which, when executed by a processor, implements a method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210769373.XA CN115033677A (en) | 2022-06-30 | 2022-06-30 | Event processing method, device, equipment and medium based on conversation robot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210769373.XA CN115033677A (en) | 2022-06-30 | 2022-06-30 | Event processing method, device, equipment and medium based on conversation robot |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115033677A true CN115033677A (en) | 2022-09-09 |
Family
ID=83129515
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210769373.XA Pending CN115033677A (en) | 2022-06-30 | 2022-06-30 | Event processing method, device, equipment and medium based on conversation robot |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115033677A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116992001A (en) * | 2023-08-07 | 2023-11-03 | 北京百度网讯科技有限公司 | Knowledge question-answering method, device, equipment, sound box and storage medium |
| CN117076649A (en) * | 2023-10-13 | 2023-11-17 | 卓世科技(海南)有限公司 | Emergency information query method and device based on large model thinking chain |
-
2022
- 2022-06-30 CN CN202210769373.XA patent/CN115033677A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116992001A (en) * | 2023-08-07 | 2023-11-03 | 北京百度网讯科技有限公司 | Knowledge question-answering method, device, equipment, sound box and storage medium |
| CN117076649A (en) * | 2023-10-13 | 2023-11-17 | 卓世科技(海南)有限公司 | Emergency information query method and device based on large model thinking chain |
| CN117076649B (en) * | 2023-10-13 | 2024-01-26 | 卓世科技(海南)有限公司 | Emergency information query method and device based on large model thinking chain |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115033677A (en) | Event processing method, device, equipment and medium based on conversation robot | |
| US9766868B2 (en) | Dynamic source code generation | |
| US9619209B1 (en) | Dynamic source code generation | |
| CN116644145B (en) | Session data processing method, device, equipment and storage medium | |
| KR20200092499A (en) | Method and apparatus for counseling support using interactive artificial intelligence technology | |
| US10839168B2 (en) | Dynamic automation of pipeline creation | |
| CN110309931A (en) | A kind of service optimization method and device | |
| CN107728783A (en) | Artificial intelligence process method and its system | |
| US20150179165A1 (en) | System and method for caller intent labeling of the call-center conversations | |
| US20220050968A1 (en) | Intent resolution for chatbot conversations with negation and coreferences | |
| CN116521841A (en) | Method, device, equipment and medium for generating reply information | |
| CN117112065B (en) | Large model plug-in calling method, device, equipment and medium | |
| KR102382421B1 (en) | Method and apparatus for outputting analysis abnormality information in spoken language understanding | |
| CN111695360B (en) | Semantic analysis method, semantic analysis device, electronic equipment and storage medium | |
| CN115905490B (en) | Man-machine interaction dialogue method, device and equipment | |
| US20230244878A1 (en) | Extracting conversational relationships based on speaker prediction and trigger word prediction | |
| CN113051895A (en) | Method, apparatus, electronic device, medium, and program product for speech recognition | |
| CN113111658A (en) | Method, device, equipment and storage medium for checking information | |
| US10609221B2 (en) | System for processing voice responses using a natural language processing engine | |
| US20200159824A1 (en) | Dynamic Contextual Response Formulation | |
| US11727937B2 (en) | Channel-agnostic conversation intelligence service | |
| CN113360630B (en) | Interactive information prompting method | |
| CN112837159B (en) | Transaction guiding method and device based on scene element, electronic equipment and medium | |
| CN113744712A (en) | Intelligent outbound voice splicing method, device, equipment, medium and program product | |
| CN114613350A (en) | Test method, test device, electronic 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 |