CN115658852B - Automobile intelligent question-answering system based on knowledge base - Google Patents
Automobile intelligent question-answering system based on knowledge base Download PDFInfo
- Publication number
- CN115658852B CN115658852B CN202211687840.0A CN202211687840A CN115658852B CN 115658852 B CN115658852 B CN 115658852B CN 202211687840 A CN202211687840 A CN 202211687840A CN 115658852 B CN115658852 B CN 115658852B
- Authority
- CN
- China
- Prior art keywords
- information
- user
- voice
- module
- unit
- 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
- 238000012937 correction Methods 0.000 claims abstract description 95
- 238000012790 confirmation Methods 0.000 claims abstract description 26
- 238000004458 analytical method Methods 0.000 claims description 41
- 239000012634 fragment Substances 0.000 claims description 34
- 238000012098 association analyses Methods 0.000 claims description 17
- 238000012216 screening Methods 0.000 claims description 17
- 238000001914 filtration Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 2
- 230000008451 emotion Effects 0.000 abstract description 3
- 230000002996 emotional effect Effects 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 5
- 230000006978 adaptation Effects 0.000 description 2
- 238000000034 method Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application provides an intelligent automobile question-answering system based on a knowledge base, which comprises the following steps: the knowledge base module stores local information aiming at automobile knowledge; the problem acquisition module acquires user voice to obtain user problem voice or user correction voice; the voice recognition module performs voice recognition on the user problem voice or the user correction voice to obtain user problem information or user correction information; the confirmation correction module feeds the user problem information back to the user for confirmation, and corrects the information according to the user correction information to obtain problem request information; the matching retrieval module matches in the knowledge base module according to the question request information to obtain answer information; the answer feedback module feeds answer information back to the user. According to the application, the correction module is calibrated aiming at the problem information, so that the accuracy of the intelligent question-answering system of the automobile is improved, the satisfaction degree of a user is improved, the influence on the emotion of the user is avoided, and meanwhile, the driving danger caused by emotional driving is also avoided.
Description
Technical Field
The application relates to the technical field of intelligence, in particular to an automobile intelligent question-answering system based on a knowledge base.
Background
As one of the most important applications in the field of artificial intelligence, the intelligent question-answering system is increasingly focused by various industries in recent years, and a good question-answering system is also urgently needed in the automotive field to help users solve problems encountered in purchasing or driving vehicles, so that user experience in driving vehicles is high. However, in the existing automobile intelligent question-answering system, the same problems are often repeatedly presented by the user due to inaccurate recognition, so that bad experience can be caused for the user, and the emotion of the user can be influenced.
Disclosure of Invention
The application aims to provide an intelligent automobile question-answering system based on a knowledge base, which aims to solve the problems in the background technology.
In order to achieve the above purpose, the present application provides the following technical solutions: an intelligent automotive question-answering system based on a knowledge base, comprising: comprising the following steps: the system comprises a knowledge base module, a question acquisition module, a voice recognition module, a confirmation correction module, a matching retrieval module and an answer feedback module; the knowledge base module is used for storing local information aiming at automobile knowledge; the problem acquisition module is used for acquiring user voice and obtaining user problem voice or user correction voice; the voice recognition module is used for carrying out voice recognition on the user problem voice or the user correction voice to obtain user problem information or user correction information; the confirmation correction module is used for feeding back the user problem information to the user for confirmation, and correcting the information according to the user correction information to obtain problem request information; the matching retrieval module is used for matching in the knowledge base module according to the question request information to obtain answer information; the answer feedback module is used for feeding back the answer information to the user.
Further, the confirmation correction module starts time recording after feeding back user problem information to a user for confirmation, in a preset time range, when the problem acquisition module acquires user correction voice and obtains user correction information through the voice recognition module, the user correction information is utilized to correct the user problem information, problem request information is obtained, the problem request information is conveyed to the matching search module, and when the user correction information is not received in the preset time range, the user problem information is used as problem request information and is conveyed to the matching search module.
Further, the voice recognition module includes: the system comprises a voice recognition unit, a semantic analysis unit and an information screening unit;
the voice recognition unit is used for recognizing the voice acquired by the problem acquisition module to obtain voice recognition information;
the semantic analysis unit is used for carrying out semantic analysis on the voice recognition information, determining the content of the voice, judging whether the voice is boring voice or question voice aiming at the intelligent question-answering system, and obtaining a semantic analysis result;
the information screening unit is used for screening and filtering the voice recognition information according to the semantic analysis result, filtering the recognition information of the boring voice, and obtaining the user problem voice or the user corrected voice.
Further, the semantic analysis unit performs association analysis on the problem voice in the semantic analysis result, including:
splitting the voice recognition information according to a voice sentence breaking rule to obtain a plurality of voice recognition fragment information;
performing association analysis on the voice recognition fragment information in combination with adjacent voice recognition fragment information, and determining whether two adjacent voice fragments are voices of the same problem or not to obtain association analysis results;
and carrying out association binding on the voice recognition fragment information according to the association analysis result, and obtaining user problem voice or user correction voice according to the problem in an information screening unit.
Further, the knowledge base module is composed of a database, and the database comprises: configuration information and state data information of the automobile, and the data information in the database is updated in real time along with the state of the automobile.
Further, the matching retrieval module includes: the system comprises a management center unit, a data matching unit and an answer sorting unit;
the management center unit is used for analyzing the problem sequence according to the problem request information and sequentially transmitting the problem sequence to the data matching unit;
the data matching unit searches knowledge information in the database through a matching model and a knowledge base module according to the problem transmitted by the management center unit, and a search result is obtained;
the answer sorting unit performs sentence combination on the search result to obtain answer information.
Further, the data matching units comprise a plurality of data matching units, the data matching units are mutually independent, each data matching unit is used for searching knowledge information in the database through a matching model in combination with the knowledge base module according to the problem transmitted by the management center unit to obtain a searching result, when only one problem exists in the management center unit, one data matching unit in the plurality of data matching units is started for matching searching, the data matching unit is started for standby, and when a plurality of problems exist in the management center unit, the plurality of data matching units are used for matching searching in parallel according to the number of the problems.
Further, the matching retrieval module further comprises a fault analysis unit, when the problem in the management center unit is a problem for inquiring the cause of the automobile fault, the fault analysis unit determines fault associated information according to the fault condition, acquires state data information in the database according to the fault associated information to obtain fault associated state data information, and analyzes and determines the cause of the fault according to the fault associated state data information to obtain answer information.
Further, the matching retrieval module further comprises a network connection unit and a network retrieval unit; when the search result obtained by the data matching unit through the matching model and the knowledge base module in combination with the knowledge information in the database is blank, the management center unit requests the network connection unit to carry out network connection, and then carries out answer search on the Internet through the network search unit aiming at the questions in the question request information to obtain answer information.
Further, the answer feedback module includes: the answer feedback module plays the answer information in a voice mode when the answer information is fed back to the user, and meanwhile the answer information is displayed and processed in the image-text display unit, wherein the voice playing sound of the voice broadcasting unit is automatically adjusted according to the sound size in the automobile, and the voice playing sound is adjusted again according to the interference information of the user after the user interferes with the automatic adjustment.
Additional features and advantages of the application will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the application. The objectives and other advantages of the application will be realized and attained by the structure particularly pointed out in the written description and claims thereof as well as the appended drawings.
The technical scheme of the application is further described in detail through the drawings and the embodiments.
Drawings
The accompanying drawings are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate the application and together with the embodiments of the application, serve to explain the application. In the drawings:
FIG. 1 is a schematic diagram of a knowledge base-based intelligent automotive question-answering system according to the present application;
FIG. 2 is a schematic diagram of a speech recognition module in the knowledge base-based intelligent automotive question-answering system according to the present application;
FIG. 3 is a schematic diagram of a matching search module in the knowledge base-based intelligent automotive question-answering system according to the present application;
FIG. 4 is a schematic diagram of a matching search module in the knowledge base-based intelligent automotive question-answering system according to the present application;
fig. 5 is a schematic diagram of a matching search module in the knowledge base-based intelligent automotive question-answering system according to the present application.
Detailed Description
The preferred embodiments of the present application will be described below with reference to the accompanying drawings, it being understood that the preferred embodiments described herein are for illustration and explanation of the present application only, and are not intended to limit the present application.
As shown in fig. 1, an embodiment of the present application provides an intelligent question-answering system for an automobile based on a knowledge base, including: the system comprises a knowledge base module, a question acquisition module, a voice recognition module, a confirmation correction module, a matching retrieval module and an answer feedback module; the knowledge base module is used for storing local information aiming at automobile knowledge; the problem acquisition module is used for acquiring user voice and obtaining user problem voice or user correction voice; the voice recognition module is used for carrying out voice recognition on the user problem voice or the user correction voice to obtain user problem information or user correction information; the confirmation correction module is used for feeding back the user problem information to the user for confirmation, and correcting the information according to the user correction information to obtain problem request information; the matching retrieval module is used for matching in the knowledge base module according to the question request information to obtain answer information; the answer feedback module is used for feeding back the answer information to the user.
The technical scheme provides an automobile intelligent question-answering system based on a knowledge base, which comprises the following steps: the system comprises a knowledge base module, a question acquisition module, a voice recognition module, a confirmation correction module, a matching search module and an answer feedback module, wherein the question acquisition module is connected with the voice recognition module, the voice recognition module is also connected with the confirmation correction module, the other end of the confirmation correction module is connected with the matching search module, the matching search module is also connected with the knowledge base module and the answer feedback module, when a question is answered through an automobile intelligent question-answering system, the question acquisition module acquires user question voice by adopting user voice, then the voice recognition module recognizes the user voice, determines user question information, then the confirmation correction module confirms the user question information to the user in a voice mode, meanwhile, the question acquisition module acquires feedback voice of the user for the confirmation information again, obtains user correction voice, corrects the user correction information for the user question information after the voice recognition module recognizes the user correction voice, analyzes the question request information, carries out automobile related knowledge retrieval according to the question request information, determines knowledge corresponding to the question request information, obtains answer information, and then carries out feedback on the answer information by the answer feedback module, so that the user obtains a question answer.
According to the technical scheme, the question and answer of the user and the automobile are realized through the automobile intelligent question and answer system, so that the user can realize intelligent dialogue in the driving process, the correction of the user question and answer voice is realized through the confirmation correction module, the accuracy of the question and answer can be improved, the repeated question and answer of the user aiming at the problem with wrong recognition can be avoided, the influence on the emotion of the user is avoided, the satisfaction of the user is improved, the driving danger caused by emotional driving is avoided, in addition, the question and answer can be performed under the condition that no network exists in time through the local storage of the knowledge base module, the voice information of the user is recognized and converted through the language recognition module, the voice information is semantemized, and the matching retrieval module can realize intelligent automatic processing, so that the answer information of the question and answer is obtained rapidly.
In one embodiment provided by the application, the confirmation correction module starts to record time after the user problem information is fed back to the user for confirmation, and in a preset time range, when the problem acquisition module acquires user correction voice and obtains the user correction information through the voice recognition module, the user correction information is utilized to correct the user problem information to obtain problem request information, the problem request information is transmitted to the matching retrieval module, and when the user correction information is not received in the preset time range, the user problem information is used as the problem request information and is transmitted to the matching retrieval module.
The confirmation correction module in the technical scheme starts to record time after feeding back the user problem information to the user for confirmation, judges according to the time record, and in a preset time range, if the problem acquisition module acquires the user correction voice, the user correction voice is identified through the voice identification module to obtain the user correction information, the user correction information is utilized to carry out difference correction on the user problem information, the segment corresponding to the user correction information in the user problem information is changed and replaced to obtain the problem request information, then the problem request information is conveyed to the matching search module, if the user correction information is not received in the preset time range, the default user does not need to carry out correction, the user problem information is taken as the problem request information at the moment, and then the problem request information is conveyed to the matching search module. When the user correction information is utilized to carry out difference correction on the user problem information, the user correction information is firstly split into a plurality of information fragments in sequence, and then the information fragments are matched with the user correction information in sequence through the following formulas:
wherein ,represent the firstThe degree of matching of the pieces of information with the user-corrected information,represent the firstThe number of pieces of information,indicating that the user has corrected the information,representing a semantic similarity calculation formula;
then analyze the firstMatching degree of individual information pieces and user correction informationWhen (when)Determining the information piece at that timeAnd in the user problem information in the form of information piecesFor starting point, obtaining information fragmentsThe latter information set；
The corrected replacement data is determined by the following formula:
in the above-mentioned formula(s),representing a modified set of replacement data,representing a set of user correction information,indicating that the correction data is in the left neighborhood of the user correction information,information indicating that correction data is in the right neighborhood of the user correction information;
replacing data sets according to correctionsWill modify the replacement data setThe whole is replaced in the user problem information, so that correction is realized.
According to the technical scheme, the user problem information is fed back to the user to confirm and then time recording is started, so that the response time of the user to the feedback of the identified user problem information can be determined, the situation that the follow-up step cannot be carried out when the user problem information is corrected and waiting for a long time is avoided, the accuracy of an automobile question-answering system can be improved through correction, and the situation that answer information does not correspond to the problem presented by the user is avoided. In addition, when the user correction information is utilized to carry out difference correction on the user problem information, the position of the user correction information in the user problem information can be better locked through the information fragments, so that fragment correction can be carried out more efficiently, and less interleaving information exists between correction replacement data and the user problem information through the left neighborhood and the right neighborhood, so that integral replacement can be efficiently and accurately realized.
In one embodiment provided by the present application, a speech recognition module includes: the system comprises a voice recognition unit, a semantic analysis unit and an information screening unit;
the voice recognition unit is used for recognizing the voice acquired by the problem acquisition module to obtain voice recognition information;
the semantic analysis unit is used for carrying out semantic analysis on the voice recognition information, determining the content of the voice, judging whether the voice is boring voice or question voice aiming at the intelligent question-answering system, and obtaining a semantic analysis result;
the information screening unit is used for screening and filtering the voice recognition information according to the semantic analysis result, filtering the recognition information of the boring voice, and obtaining the user problem voice or the user corrected voice.
As shown in fig. 2, the voice recognition module in the above technical solution includes: the voice recognition unit is connected with the problem acquisition module, the voice recognition unit is also connected with the semantic analysis unit and the information screening unit, the connection relationship exists between the semantic analysis unit and the information screening unit, when the voice recognition module carries out voice recognition on the problem voice of a user or the corrected voice of the user, the voice recognition unit carries out recognition on the voice acquired by the problem acquisition module to obtain voice recognition information, then the semantic analysis unit carries out semantic analysis on the voice recognition information to determine the content of the voice and judges whether the voice is boring voice or the problem voice of the intelligent question-answering system to obtain a semantic analysis result; and the information screening unit is used for screening and filtering the voice recognition information according to the semantic analysis result, filtering the recognition information of the boring voice, and obtaining the user problem voice or the user corrected voice.
According to the technical scheme, the voice collected by the voice analysis unit aiming at the problem collection module is analyzed, so that invalid response to the boring voice of the user in the intelligent question-answering system of the automobile is avoided, meanwhile, resource occupation of the boring voice to the intelligent question-answering system of the automobile is avoided, and response efficiency of the intelligent question-answering system of the automobile aiming at the problem voice is improved.
In one embodiment provided by the present application, the semantic analysis unit further performs association analysis on the problem speech in the semantic analysis result, including:
splitting the voice recognition information according to a voice sentence breaking rule to obtain a plurality of voice recognition fragment information;
performing association analysis on the voice recognition fragment information in combination with adjacent voice recognition fragment information, and determining whether two adjacent voice fragments are voices of the same problem or not to obtain association analysis results;
and carrying out association binding on the voice recognition fragment information according to the association analysis result, and obtaining user problem voice or user correction voice according to the problem in an information screening unit.
The semantic analysis unit in the above technical solution further performs association analysis on the problem voice in the semantic analysis result, including: splitting the voice recognition information according to a voice sentence breaking rule to obtain a plurality of voice recognition fragment information; performing association analysis on the voice recognition fragment information in combination with adjacent voice recognition fragment information, and determining whether two adjacent voice fragments are voices of the same problem or not to obtain association analysis results; and carrying out association binding on the voice recognition fragment information according to the association analysis result, and obtaining user problem voice or user correction voice according to the problem in an information screening unit.
According to the technical scheme, the voice recognition fragment information is combined with the adjacent voice recognition fragment information to carry out association analysis, so that the voice fragments can be associated with the front voice and the rear voice, ambiguity caused by the voice fragments is avoided, and meanwhile, analysis errors of the problems are avoided.
In one embodiment of the present application, the knowledge base module is formed by a database, and the database includes: configuration information and state data information of the automobile, and the data information in the database is updated in real time along with the state of the automobile.
The knowledge base module in the technical scheme is composed of a database, wherein the database comprises: configuration information and state data information of the automobile, and the data information in the database is updated in real time along with the state of the automobile.
According to the technical scheme, the intelligent automobile question-answering system can accurately answer the state answer about the automobile according to the questions of the user by the aid of the configuration information and the state data information of the automobile, and the database is always the latest data information by means of real-time updating of the data information in the database along with the state of the automobile, so that the answer information answered by the intelligent automobile question-answering system is ensured to be the information about the current state of the automobile.
In one embodiment provided by the present application, the matching retrieval module includes: the system comprises a management center unit, a data matching unit and an answer sorting unit;
the management center unit is used for analyzing the problem sequence according to the problem request information and sequentially transmitting the problem sequence to the data matching unit;
the data matching unit searches knowledge information in the database through a matching model and a knowledge base module according to the problem transmitted by the management center unit, and a search result is obtained;
the answer sorting unit performs sentence combination on the search result to obtain answer information.
As shown in fig. 3, the matching search module in the above technical solution includes: the system comprises a management center unit, a data matching unit and an answer sorting unit; the management center unit is connected with the data matching unit and the confirmation correction module, the data matching unit is also connected with the knowledge base module and the answer arrangement unit, when the matching retrieval module matches in the knowledge base module according to the problem request information, the management center unit firstly analyzes the problem sequence according to the problem request information, determines the sequence of the problems and sequentially transmits the problems to the data matching unit; and then the data matching unit searches knowledge information in the database through a matching model and a knowledge base module according to the questions transmitted by the management center unit to obtain search results, and finally the answer sorting unit performs sentence combination on the search results to obtain answer information.
According to the technical scheme, the matching and searching module realizes the association between the problem and the knowledge base module, so that matching and searching are carried out in the knowledge base module according to the problem information, knowledge information corresponding to the problem information is obtained, a matching result can be obtained efficiently and accurately by adopting a matching model through the data matching unit, and the matching model can be reused for multiple times.
In one embodiment provided by the application, the data matching units comprise a plurality of data matching units, the data matching units are mutually independent, each data matching unit searches knowledge information in a database through a matching model and a knowledge base module according to the problem transmitted by the management center unit to obtain a search result, when only one problem exists in the management center unit, one data matching unit in the plurality of data matching units is started for matching search, the data matching unit is started for standby, and when a plurality of problems exist in the management center unit, the plurality of data matching units are matched and searched in parallel according to the number of the problems.
The data matching unit in the technical scheme comprises a plurality of data matching small units, the data matching small units are mutually independent, each data matching small unit searches knowledge information in a database through a matching model and a knowledge base module according to the problem transmitted by the management center unit to obtain a search result, when only one problem exists in the management center unit, one data matching small unit in the plurality of data matching small units is started to perform matching search, the data matching small unit is started to serve as a standby, and when a plurality of problems exist in the management center unit, the plurality of data matching small units are matched and searched in parallel according to the number of the problems.
According to the technical scheme, the plurality of data matching small units are arranged in the data matching unit, so that the continuous questions can be processed in parallel, and answer information of all the questions can be obtained rapidly when a user continuously asks the questions.
In one embodiment of the present application, the matching search module further includes a fault analysis unit, where when the problem in the management center unit is a problem of inquiring a cause of a fault of the automobile, the fault analysis unit determines fault associated information according to a fault condition, and performs status data information acquisition in the database according to the fault associated information to obtain fault associated status data information, and performs analysis on the fault associated status data information to determine the cause of the fault, so as to obtain answer information.
As shown in fig. 4, the matching search module in the above technical solution further includes a fault analysis unit, where when the problem in the management center unit is a problem of inquiring the cause of the automobile fault, the fault analysis unit determines fault associated information according to the fault condition, and performs status data information acquisition in the database according to the fault associated information to obtain fault associated status data information, and analyzes and determines the cause of the fault according to the fault associated status data information to obtain answer information.
According to the technical scheme, the fault analysis unit can analyze and confirm the fault reason by combining the state data information in the database when a user inquires the fault reason of the automobile, so that the user can determine whether the current state of the automobile leads to the automobile fault, the user can be confused, and the current state of the automobile can be reflected.
In one embodiment provided by the application, the matching retrieval module further comprises a network connection unit and a network retrieval unit; when the search result obtained by the data matching unit through the matching model and the knowledge base module in combination with the knowledge information in the database is blank, the management center unit requests the network connection unit to carry out network connection, and then carries out answer search on the Internet through the network search unit aiming at the questions in the question request information to obtain answer information.
As shown in fig. 5, the matching retrieval module in the above technical solution further includes a network connection unit and a network retrieval unit; the network connection unit is connected with the network retrieval unit and the management center unit, if the retrieval result obtained by the data matching unit through the matching model and the knowledge base module in the database is blank, the management center unit analyzes whether the network is connected or not, if the network is connected, answer searching is carried out on the Internet for the questions in the question request information through the network retrieval unit to obtain answer information, if the network is not connected, the network connection unit is requested to carry out network connection, and then answer searching is carried out on the Internet for the questions in the question request information through the network retrieval unit to obtain answer information.
According to the technical scheme, the matching retrieval module further comprises the network connection unit and the network retrieval unit, so that the automobile intelligent question-answering system can answer according to local data stored in the knowledge base module, answer searching can be conducted on the Internet through network connection to obtain answer information when the knowledge base module does not have the answer information, and the knowledge universality of the automobile intelligent question-answering system is improved.
In one embodiment provided by the present application, the answer feedback module includes: the answer feedback module plays the answer information in a voice mode when the answer information is fed back to the user, and meanwhile the answer information is displayed and processed in the image-text display unit, wherein the voice playing sound of the voice broadcasting unit is automatically adjusted according to the sound size in the automobile, and the voice playing sound is adjusted again according to the interference information of the user after the user interferes with the automatic adjustment.
According to the technical scheme, the answer feedback module is provided with the voice broadcasting unit and the image-text display unit, wherein the voice broadcasting unit is used for broadcasting answer information, the image-text display unit is used for displaying answer information, when the answer feedback module feeds back the answer information to a user, the voice broadcasting unit plays the answer information in a voice mode, meanwhile, the image-text display unit displays the answer information, the voice broadcasting sound of the voice broadcasting unit can be automatically adjusted according to the sound size of the interior of the automobile, when the interior of the automobile is quite, the voice broadcasting is conducted in a smaller sound range audible to the user, when the interior of the automobile is quite noisy, the voice broadcasting is conducted in a larger sound range audible to the user, particularly, if the voice broadcasting unit conducts voice broadcasting in the process according to the voice broadcasting sound after the automatic adjustment, the voice broadcasting sound is conducted by the user, and then the voice broadcasting sound is adjusted again according to the interference condition of the user.
The technical proposal is provided with the voice broadcasting unit and the image-text display unit through the answer feedback module, so that a user can obtain answer information more conveniently without excessive distraction, the safety is improved, the voice broadcasting sound through the voice broadcasting unit can be automatically regulated according to the sound size in the automobile, the voice broadcasting unit can not hear the user or frighten the user due to overlarge sound caused by overlarge sound when broadcasting, and the user can also interfere the sound size, thereby being very convenient,
it will be appreciated by those skilled in the art that the first and second aspects of the present application refer only to different phases of application.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any adaptations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It is to be understood that the present disclosure is not limited to the precise arrangements and instrumentalities shown in the drawings, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims (7)
1. An intelligent automobile question-answering system based on a knowledge base is characterized by comprising: the system comprises a knowledge base module, a question acquisition module, a voice recognition module, a confirmation correction module, a matching retrieval module and an answer feedback module; the knowledge base module is used for storing local information aiming at automobile knowledge; the problem acquisition module is used for acquiring user voice and obtaining user problem voice or user correction voice; the voice recognition module is used for carrying out voice recognition on the user problem voice or the user correction voice to obtain user problem information or user correction information; the confirmation correction module is used for feeding back the user problem information to the user for confirmation, and correcting the information according to the user correction information to obtain problem request information; the matching retrieval module is used for matching in the knowledge base module according to the question request information to obtain answer information; the answer feedback module is used for feeding back answer information to the user;
wherein, the speech recognition module includes: the system comprises a voice recognition unit, a semantic analysis unit and an information screening unit; the voice recognition unit is used for recognizing the voice acquired by the problem acquisition module to obtain voice recognition information; the semantic analysis unit is used for carrying out semantic analysis on the voice recognition information, determining the content of the voice, judging whether the voice is boring voice or question voice aiming at the intelligent question-answering system, obtaining a semantic analysis result, and carrying out association analysis on the question voice in the semantic analysis result, wherein the semantic analysis unit comprises the following steps: splitting the voice recognition information according to a voice sentence breaking rule to obtain a plurality of voice recognition fragment information; performing association analysis on the voice recognition fragment information in combination with adjacent voice recognition fragment information, and determining whether two adjacent voice fragments are voices of the same problem or not to obtain association analysis results; carrying out association binding on the voice recognition fragment information according to the association analysis result, and obtaining user problem voice or user correction voice according to the problem in an information screening unit; the information screening unit is used for screening and filtering the voice recognition information according to the semantic analysis result, filtering the recognition information of the boring voice, and obtaining the user problem voice or the user corrected voice;
the confirmation correction module starts time recording after feeding back user problem information to a user for confirmation, in a preset time range, when the problem acquisition module acquires user correction voice and obtains user correction information through the voice recognition module, the user correction information is utilized to correct the user problem information to obtain problem request information, the problem request information is transmitted to the matching search module, and when the user correction information is not received in the preset time range, the problem request information is transmitted to the matching search moduleThe user problem information is used as problem request information and is transmitted to a matching retrieval module; when the user correction information is utilized to carry out difference correction on the user problem information, the user correction information is firstly split into a plurality of information fragments in sequence, and then the information fragments are matched with the user correction information in sequence through the following formulas:；
wherein ,indicate->Matching degree of the individual information pieces with the user correction information, < >>Indicate->Personal information piece,/->Representing user correction information->Representing a semantic similarity calculation formula;
then analyze the firstMatching degree of personal information fragment and user correction information +.>When->Determining the information fragment at this time when > 0And in the user question information in the information piece +.>For the starting point, information fragment +.>The latter information set->；
The corrected replacement data is determined by the following formula:；
in the above-mentioned formula(s),representing a modified replacement data set, ">Representing a user correction information set,/->Information representing correction data in the left neighborhood of the user correction information,/and/or>Information indicating that correction data is in the right neighborhood of the user correction information;
replacing data sets according to correctionsCorrection of the replacement data set +.>The whole is replaced in the user problem information, so that correction is realized.
2. The knowledge base based intelligent automotive question-answering system according to claim 1, wherein the knowledge base module is comprised of a database comprising: configuration information and state data information of the automobile, and the data information in the database is updated in real time along with the state of the automobile.
3. The knowledge base based automotive intelligent question-answering system according to claim 2, wherein the match retrieval module comprises: the system comprises a management center unit, a data matching unit and an answer sorting unit;
the management center unit is used for analyzing the problem sequence according to the problem request information and sequentially transmitting the problem sequence to the data matching unit;
the data matching unit searches knowledge information in the database through a matching model and a knowledge base module according to the problem transmitted by the management center unit, and a search result is obtained;
the answer sorting unit performs sentence combination on the search result to obtain answer information.
4. The knowledge base-based intelligent automobile question-answering system according to claim 2, wherein the data matching units comprise a plurality of data matching small units, the data matching small units are mutually independent, knowledge information is searched in the database by combining a knowledge base module through a matching model according to the problems transmitted by the management center unit to obtain a search result, when only one problem exists in the management center unit, one of the plurality of data matching small units is started to perform matching search, the data matching small unit is started to serve as a standby, and when a plurality of problems exist in the management center unit, the plurality of data matching small units are matched and searched in parallel according to the number of the problems.
5. The knowledge base-based intelligent automobile question-answering system according to claim 3, wherein the matching search module further comprises a fault analysis unit, when the problem in the management center unit is a problem for inquiring the cause of an automobile fault, the fault analysis unit determines fault associated information according to the fault condition, and performs status data information acquisition in the database according to the fault associated information to obtain fault associated status data information, and analyzes and determines the cause of the fault according to the fault associated status data information to obtain answer information.
6. The intelligent knowledge base based automotive question-answering system according to claim 3, wherein,
the matching retrieval module also comprises a network connection unit and a network retrieval unit; when the search result obtained by the data matching unit through the matching model and the knowledge base module in combination with the knowledge information in the database is blank, the management center unit requests the network connection unit to carry out network connection, and then carries out answer search on the Internet through the network search unit aiming at the questions in the question request information to obtain answer information.
7. The knowledge base based automotive intelligent question-answering system according to claim 1, wherein the answer feedback module comprises: the answer feedback module plays the answer information in a voice mode when the answer information is fed back to the user, and meanwhile the answer information is displayed and processed in the image-text display unit, wherein the voice playing sound of the voice broadcasting unit is automatically adjusted according to the sound size in the automobile, and the voice playing sound is adjusted again according to the interference information of the user after the user interferes with the automatic adjustment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211687840.0A CN115658852B (en) | 2022-12-28 | 2022-12-28 | Automobile intelligent question-answering system based on knowledge base |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211687840.0A CN115658852B (en) | 2022-12-28 | 2022-12-28 | Automobile intelligent question-answering system based on knowledge base |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115658852A CN115658852A (en) | 2023-01-31 |
| CN115658852B true CN115658852B (en) | 2023-10-24 |
Family
ID=85022563
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211687840.0A Active CN115658852B (en) | 2022-12-28 | 2022-12-28 | Automobile intelligent question-answering system based on knowledge base |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115658852B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2009033339A1 (en) * | 2007-09-14 | 2009-03-19 | Zte Corporation | Intelligently interactive question answer system and processing method |
| CN106202301A (en) * | 2016-07-01 | 2016-12-07 | 武汉泰迪智慧科技有限公司 | A kind of intelligent response system based on degree of depth study |
| CN112331191A (en) * | 2021-01-07 | 2021-02-05 | 广州华源网络科技有限公司 | Voice recognition system and method based on big data |
| WO2021082982A1 (en) * | 2019-10-29 | 2021-05-06 | 平安科技（深圳）有限公司 | Graphic knowledge base-based question and answer method and device, storage medium, and apparatus |
| CN113505209A (en) * | 2021-07-09 | 2021-10-15 | 吉林大学 | Intelligent question-answering system for automobile field |
| CN115238101A (en) * | 2022-09-23 | 2022-10-25 | 中国电子科技集团公司第十研究所 | Multi-engine intelligent question-answering system oriented to multi-type knowledge base |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9460085B2 (en) * | 2013-12-09 | 2016-10-04 | International Business Machines Corporation | Testing and training a question-answering system |
-
2022
- 2022-12-28 CN CN202211687840.0A patent/CN115658852B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2009033339A1 (en) * | 2007-09-14 | 2009-03-19 | Zte Corporation | Intelligently interactive question answer system and processing method |
| CN106202301A (en) * | 2016-07-01 | 2016-12-07 | 武汉泰迪智慧科技有限公司 | A kind of intelligent response system based on degree of depth study |
| WO2021082982A1 (en) * | 2019-10-29 | 2021-05-06 | 平安科技（深圳）有限公司 | Graphic knowledge base-based question and answer method and device, storage medium, and apparatus |
| CN112331191A (en) * | 2021-01-07 | 2021-02-05 | 广州华源网络科技有限公司 | Voice recognition system and method based on big data |
| CN113505209A (en) * | 2021-07-09 | 2021-10-15 | 吉林大学 | Intelligent question-answering system for automobile field |
| CN115238101A (en) * | 2022-09-23 | 2022-10-25 | 中国电子科技集团公司第十研究所 | Multi-engine intelligent question-answering system oriented to multi-type knowledge base |
Non-Patent Citations (1)
| Title |
|---|
| 基于自动生成知识库的智能问答系统设计;王飞鸿;;中国科技信息(第12期);第53-55页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115658852A (en) | 2023-01-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10929390B2 (en) | Method and apparatus for correcting query based on artificial intelligence | |
| US9020819B2 (en) | Recognition dictionary system and recognition dictionary system updating method | |
| WO2021017612A1 (en) | Question and answer method and apparatus based on speech analysis, device and storage medium | |
| EP1050872A2 (en) | Method and system for selecting recognized words when correcting recognized speech | |
| US8626506B2 (en) | Method and system for dynamic nametag scoring | |
| CN111177359A (en) | Multi-turn dialogue method and device | |
| US20180166079A1 (en) | Query Rewrite Corrections | |
| US7310602B2 (en) | Navigation apparatus | |
| CN108682419A (en) | Sound control method and equipment, computer readable storage medium and equipment | |
| US7496562B2 (en) | Music data selection apparatus, music data selection method, and information recording medium on which music data selection program is computer-readably recorded | |
| WO2009158581A2 (en) | System and method for spoken topic or criterion recognition in digital media and contextual advertising | |
| CN103635962A (en) | Voice recognition system, recognition dictionary logging system, and audio model identifier series generation device | |
| CN111477231B (en) | Man-machine interaction method, device and storage medium | |
| CN106537492A (en) | Motor vehicle operating device with a correction strategy for voice recognition | |
| CN107885720B (en) | Keyword generation device and keyword generation method | |
| CN115103225B (en) | Video clip extraction method, device, electronic equipment and storage medium | |
| CN115658852B (en) | Automobile intelligent question-answering system based on knowledge base | |
| CN118486310B (en) | Vehicle-mounted voice guiding method and device and vehicle-mounted terminal | |
| JP7107228B2 (en) | Information processing device, information processing method, and program | |
| WO2024045926A1 (en) | Multimedia recommendation method and recommendation apparatus, and head unit system and storage medium | |
| JP3617826B2 (en) | Information retrieval device | |
| CN111382230B (en) | Fuzzy recognition method for legal consultation options | |
| CN110543636B (en) | Training data selection method for dialogue system | |
| CN111324719B (en) | Fuzzy recognition system for legal consultation | |
| Howell et al. | Detection of supralexical dysfluencies in a text read by children who stutter |
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 |