CN110767219B - Semantic updating method, device, server and storage medium - Google Patents
Semantic updating method, device, server and storage medium Download PDFInfo
- Publication number
- CN110767219B CN110767219B CN201910874821.0A CN201910874821A CN110767219B CN 110767219 B CN110767219 B CN 110767219B CN 201910874821 A CN201910874821 A CN 201910874821A CN 110767219 B CN110767219 B CN 110767219B
- Authority
- CN
- China
- Prior art keywords
- semantic
- text
- semantic text
- initial
- control function
- 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
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000011161 development Methods 0.000 claims abstract description 19
- 230000006870 function Effects 0.000 claims description 149
- 230000014509 gene expression Effects 0.000 claims description 56
- 230000008859 change Effects 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 3
- 230000004913 activation Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 5
- 238000013507 mapping Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000013519 translation Methods 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- 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
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3343—Query execution using phonetics
-
- 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
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/08—Speech classification or search
- G10L15/18—Speech classification or search using natural language modelling
- G10L15/1815—Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Acoustics & Sound (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Machine Translation (AREA)
Abstract
The embodiment of the invention discloses a semantic updating method, a semantic updating device, a server and a storage medium, wherein the method comprises the following steps: acquiring an initial semantic text of a target voice input by a user through a vehicle-mounted terminal; when the sound control function corresponding to the initial semantic text is not found in the preset semantic text set, generating a semantic deep analysis request of the target voice and sending the semantic deep analysis request to a semantic analysis terminal; receiving a standard semantic text corresponding to the target voice fed back by the semantic analysis terminal; updating the initial semantic text to the set of semantic texts based on the standard semantic text. The embodiment of the invention can continuously improve the coverage of the explanation support of the user by continuously collecting the target voice input by the user on the basis of developing the voice control function in the earlier stage, thereby solving the problem that the explanation set which can meet the requirements of all users cannot be customized due to limited abilities and experiences of developers and various types of explanations of the user in the earlier stage of function development.
Description
Technical Field
The embodiment of the invention relates to the technical field of semantic implementation, in particular to a semantic updating method, a semantic updating device, a server and a storage medium.
Background
With the development of automobile intellectualization and networking, vehicles have evolved from original single vehicles into a travel service medium integrating multiple entertainment, life and service into a whole. The car machine system has more and more applications, is limited by the fact that intelligent driving does not reach the level of automatic driving completely, and a driver can not release hands from a steering wheel in the driving process, so that potential safety hazards exist when the driver wants to finish the function, the driver is not convenient and fast, the rapidity and convenience of the function use of a user can be greatly improved through voice, the car machine system is the development direction of future human-computer interaction, and the car machine system is the best human-computer interaction mode in the future.
At present, a semantic implementation mode based on user's utterance is usually that a speech designer customizes an utterance set in an early stage of function development, and then a function developer completes semantic implementation of preset utterances in the utterance set, such as opening a certain vehicle-mounted application or function by speech. Therefore, the semantic realization effect of the user's utterance depends largely on the rationality and coverage of the speech designer to customize the utterance set in the early stage of functional development. However, real users of the vehicle come from north of the south of the sky and the sea of the five lakes, and the descriptions of the users are different, and dialects and the like are possible, so that even a speech designer with more experience cannot customize a description set which can meet the requirements of all users in the early stage of function development.
Disclosure of Invention
Embodiments of the present invention provide a semantic updating method, apparatus, device, and storage medium, so as to implement that embodiments of the present invention can continuously improve coverage of a user's speaking support by continuously collecting target voices input by a user on the basis of a previously developed voice control function.
In a first aspect, an embodiment of the present invention provides a semantic updating method, where the method includes:
acquiring an initial semantic text of a target voice input by a user through a vehicle-mounted terminal;
when the sound control function corresponding to the initial semantic text is not found in the preset semantic text set, generating a semantic deep analysis request of the target voice and sending the semantic deep analysis request to a semantic analysis terminal;
receiving a standard semantic text corresponding to the target voice fed back by the semantic analysis terminal;
updating the initial semantic text to the set of semantic texts based on the standard semantic text.
In a second aspect, an embodiment of the present invention further provides a semantic updating apparatus, where the apparatus includes:
the initial recognition module is used for acquiring an initial semantic text of a target voice input by a user through the vehicle-mounted terminal;
the request generation module is used for generating a semantic deep analysis request of the target voice and sending the semantic deep analysis request to a semantic analysis terminal when the sound control function corresponding to the initial semantic text is not found in a preset semantic text set;
the standard receiving module is used for receiving a standard semantic text corresponding to the target voice fed back by the semantic analysis terminal;
and the semantic updating module is used for updating the initial semantic text to the semantic text set based on the standard semantic text.
In a third aspect, an embodiment of the present invention further provides a server, where the server includes:
one or more processors;
storage means for storing one or more programs;
the one or more programs are executed by the one or more processors, so that the one or more processors implement the semantic updating method according to the first aspect of the embodiment of the present invention.
In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the semantic updating method according to the first aspect of the embodiment of the present invention.
The embodiment of the invention realizes that the voice control function of the vehicle and the coverage of the voice control function to the corresponding voice explanation support of the user are continuously improved by continuously collecting the target voice input by the user on the basis of developing the voice control function in the earlier stage, thereby solving the problem that the explanation set which can meet the requirements of all users cannot be customized due to limited abilities and experiences of developers and various user explanations in the earlier stage of function development.
Drawings
Fig. 1 is a schematic flow chart of a semantic updating method according to an embodiment of the present invention;
fig. 2 is a flowchart illustrating a semantic updating method according to a second embodiment of the present invention;
fig. 3 is an application example diagram of a semantic updating method according to a second embodiment of the present invention;
fig. 4 is a schematic structural diagram of a semantic updating apparatus according to a third embodiment of the present invention;
fig. 5 is a schematic structural diagram of a server according to a fourth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. In addition, the embodiments and features of the embodiments in the present invention may be combined with each other without conflict. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Example one
Fig. 1 is a flowchart of a schematic flow chart of a semantic updating method according to an embodiment of the present invention, where the embodiment is applicable to a situation where coverage supported by a user is continuously improved by continuously collecting target voices input by the user on the basis of a previously developed voice control function, and the method may be executed by a semantic updating device, and the device may be implemented in a software and/or hardware manner and may be integrated in a semantic updating server.
It can be understood that the implementation of the existing vehicle-mounted voice control function is completed through a customized expression set, but is limited by the ability and experience of developers, and the customized function expressions and types are limited, so that the requirements of all users cannot be met. The invention mainly aims to continuously expand the language and improve the coverage of the user language supported by the vehicle-mounted sound control function by continuously collecting the language voice input by the user on the basis of the sound control function completed by the developer, then completing the realization of the sound control function of the language and subsequently feeding back the realization of the function desired by the user.
It should be noted that, regardless of the utterance set customized by the developer in the early stage or the target speech input by the user in the later stage, the continuously updated and completed utterance set is stored in the speech cloud or the background server (i.e., the semantic update server), so that the speech cloud or the background server (i.e., the semantic update server) can be used as the execution subject of the embodiment of the present invention.
As shown in fig. 1, the semantic updating method provided in this embodiment specifically includes the following steps:
s101, acquiring an initial semantic text of a target voice input by a user through a vehicle-mounted terminal.
The vehicle-mounted terminal can be a vehicle-mounted machine system with a voice recording and/or identifying function in a vehicle, or a voice recording and/or identifying module independent of the vehicle-mounted machine system, or a third-party device which is in wired or wireless communication connection with the vehicle-mounted machine system and has the voice recording and/or identifying function. The target voice may be understood as a voice for performing a corresponding operation on a desired vehicle entered by the in-vehicle terminal by a user. The initial semantic text refers to a voice text obtained by performing voice recognition on the target voice, and the initial semantic text can be understood as a textual translation of the target voice.
Optionally, the initial semantic text may be obtained by performing voice recognition on the target voice by a vehicle-mounted terminal having a voice recognition function, and sending the initial semantic text to the semantic updating server.
Optionally, the initial semantic text may also be obtained by sending the target speech to the speech update server after the vehicle-mounted terminal acquires the target speech, and performing speech recognition on the target speech by the semantic update server.
Optionally, each user may register a personal account belonging to the user on the vehicle-mounted terminal, and after logging in the account, the target voice is entered through the vehicle-mounted terminal to experience a corresponding voice control function.
Illustratively, after a user logs in his personal account on the vehicle-mounted terminal, a voice entry button is waken up or clicked through voice through a function display interface of the vehicle-mounted terminal, a voice sentence pattern with similar semantics such as "i want …" or "i want …" is entered, while the user enters voice, the vehicle-mounted terminal starts to pick up sound and displays a voice recognition result on the function display interface in real time, and after the sound pickup is finished, a text result (namely the initial semantic text) of the voice entered by the user is displayed on a page. In addition, the user can call a keyboard of the vehicle-mounted terminal to edit and modify the text result, and after the text result is modified, the text result is confirmed to be submitted. And the vehicle-mounted terminal sends the initial semantic text submitted by the user to the semantic updating server for processing.
S102, when the sound control function corresponding to the initial semantic text is not found in the preset semantic text set, generating a semantic deep parsing request of the target voice and sending the semantic deep parsing request to a semantic parsing terminal.
The semantic text set can be understood as a descriptive set customized by a developer in the early stage of function development and continuously updated subsequently. The semantic deep parsing request can be understood as a request generated by the semantic update server to perform further semantic parsing on the initial semantic text to obtain a request corresponding to the standard semantic text of the target voice. The standard semantic text can be understood as a standard general semantic text formulated by developers and used for instructing the car machine system to execute a certain voice control function, and optionally, in the semantic text set, one standard semantic text corresponds to one voice control function.
The semantic parsing terminal can be understood as a terminal device specially used for further semantic parsing of the initial text semantics to obtain a standard semantic text corresponding to the target voice. Optionally, the semantic parsing terminal may be a terminal device having an ability to autonomously parse the initial semantic text, or a terminal device for an operator to manually parse the initial semantic text.
It can be understood that the initial semantic text is only a textual translation of the target speech, when a user instructs the car-mounted device system to execute a certain voice control function through speech, there are many corresponding expressions, and the initial semantic text is only one of the expressions, so there may be two reasons why the voice control function corresponding to the initial semantic text is not found in a preset semantic text set: firstly, the vehicle has not opened the voice control function corresponding to the initial semantic text, and secondly, the vehicle has opened the voice control function corresponding to the initial semantic text, but the initial semantic text is not collected in the semantic text set; the standard semantic text is a standard general semantic text used for instructing the car machine system to execute a certain sound control function, and for any sound control function, when the sound control function is turned on by a vehicle, the semantic text set must have the standard semantic text corresponding to the sound control function, so that in order to determine a specific reason that the sound control function corresponding to the initial semantic text is not found, the standard semantic text corresponding to the target voice can be obtained by further analyzing the initial semantic text.
Optionally, the semantic text set comprises: a text expression set with function to be opened and at least one binary information group containing opened voice control function and corresponding semantic text expression set.
The text set of the function to be opened refers to a set of semantic texts which contain all the semantic texts of which the corresponding voice control functions are not developed yet. The semantic text expression set refers to a set of all semantic texts corresponding to the same voice control function in the semantic text set.
It is understood that for any voice control function, there may be a plurality of semantic representations that instruct the car machine system to perform the voice control function; therefore, if the voice control function is activated, a semantic text expression set can be established for all semantic texts corresponding to the voice control function in the semantic text set, and the semantic text expression set comprises a standard semantic text uniquely corresponding to the voice control function; if the sound control function is not opened, the standard semantic text corresponding to the sound control function can be added to the text set of the function to be opened to wait for a developer to subsequently open the sound control function.
Optionally, the voice control function corresponding to the initial semantic text is not found in the preset semantic text set, and may be optimized as follows:
matching the initial semantic text with semantic expression items of each semantic text expression set in the semantic text set;
and if the matching fails, determining that the sound control function corresponding to the initial semantic text is not found.
It should be noted that, the sound control function corresponding to the initial semantic text in the vehicle may be already activated, so that the sound control function corresponding to the initial semantic text is not found in the preset semantic text set, because the initial semantic text is one of the numerous and multiple semantic expressions of the sound control function, and is not collected in the semantic text set, so that the mapping relationship between the initial semantic text and the sound control function is not established.
Optionally, when the sound control function corresponding to the initial semantic text is not found in the preset semantic text set, sending a feedback message that the sound control function is not activated to the vehicle-mounted terminal, so that the vehicle-mounted terminal displays the feedback message to a user.
For example, the feedback message may be "current function is not open, Please expect! "
S103, receiving a standard semantic text corresponding to the target voice fed back by the semantic analysis terminal.
It can be understood that the semantic parsing terminal may be a terminal device having an ability to autonomously parse the initial semantic text, or a terminal device for an operator to manually parse the initial semantic text, and in any parsing manner, a certain time is required for the semantic parsing terminal to feed back the standard semantic text corresponding to the target speech, and especially when the data volume of the target speech to be processed is large, the processing process may be relatively lengthy. Therefore, in order to not reduce the user experience of the user, the processing process is accelerated as much as possible, the processing time is shortened, and meanwhile, the associated semantic recommendation function can be provided for the user.
Optionally, after sending a feedback message that the sound control function is not turned on to the vehicle-mounted terminal, so that the vehicle-mounted terminal displays the feedback message to a user, the method further includes:
and sending other semantic texts which are related to the initial semantic text and have opened corresponding voice control functions to the vehicle-mounted terminal so that the vehicle-mounted terminal can recommend associated semantics to a user.
It can be understood that, by recommending associated semantics to a user, even if the user cannot experience the sound control function indicated by the target voice in time, the user can select to experience the sound control function corresponding to the associated semantics according to the recommended associated semantics, and when the initial semantic text and the associated semantics correspond to the same sound control function, the user is equivalent to experience the corresponding sound control function.
And S104, updating the initial semantic text to the semantic text set based on the standard semantic text.
It can be understood that after the standard semantic text corresponding to the target voice is acquired, whether the voice control function corresponding to the initial semantic text in the vehicle is opened or not can be determined according to the standard semantic text; specifically, if the semantic text set contains the standard semantic text, it indicates that a sound control function corresponding to the initial semantic text in the vehicle is turned on, and only the initial semantic text is not collected into the semantic text set (specifically, not collected into a semantic text expression set to which the standard semantic text belongs), that is, a mapping relationship between the initial semantic text and the corresponding sound control function is not established through the semantic text set; and if the semantic text set does not contain the standard semantic text, the fact that the voice control function corresponding to the initial semantic text in the vehicle is not opened is shown, and obviously, the initial semantic text is not collected into the semantic text set. Whether the voice control function corresponding to the initial semantic text in the vehicle is turned on or not, it can be determined that the initial semantic text is not collected into the semantic text set, and therefore, the initial semantic text needs to be collected into the semantic text set to complete updating of the semantic text set.
Optionally, when the semantic text set contains the standard semantic text, adding the initial semantic text into a semantic text expression set to which the standard semantic text belongs; and when the semantic text set does not contain the standard semantic text, adding the initial semantic text and the corresponding standard semantic text into the functional text expression set to be opened.
The embodiment of the invention realizes that the voice control function of the vehicle and the coverage of the voice control function to the corresponding voice explanation support of the user are continuously improved by continuously collecting the target voice input by the user on the basis of developing the voice control function in the earlier stage, thereby solving the problem that the explanation set which can meet the requirements of all users cannot be customized due to limited abilities and experiences of developers and various user explanations in the earlier stage of function development.
Further, as an optional embodiment of the first embodiment, the first embodiment further optimizes and includes:
and sending a personal voice list to the vehicle-mounted terminal so that the vehicle-mounted terminal displays the personal voice list to a user.
Wherein the personal voice list can be understood as a history of all input voices of the user.
Optionally, the personal voice list includes each voice input by the user, a corresponding initial semantic text, and a real-time activation state of a voice control function corresponding to each initial semantic text.
Illustratively, in the personal voice list of the user, all the semantic and related information submitted by the user is included. The semantics and the related information can be displayed from near to far according to the time submitted by the user, and the displayed content comprises an initial semantic text (which can contain associated semantics selected by the user), a target voice (which can be played), a semantic state (for example, the sound control function is activated or not activated, and the activated sound control function can support the user to experience the sound control function immediately), and the like. Aiming at all semantics and relevant information, a user can perform operations such as marking, moving up, moving down, deleting and the like according to personal preferences of the user.
Optionally, when the real-time activation state of the sound control function corresponding to any one of the initial semantic texts changes, sending state update prompting information corresponding to the change to the vehicle-mounted terminal, so that the vehicle-mounted terminal displays the state update prompting information to a user.
It can be understood that, by prompting the change information of the real-time activation state of the sound control function corresponding to the initial semantic text in time, for example, when the real-time activation state of the sound control function corresponding to a certain initial semantic text is changed from non-activation to activation, the user can experience the corresponding sound control function in time, and the user experience is improved.
Example two
Fig. 2 is a schematic flow chart of a semantic updating method according to a second embodiment of the present invention, and this embodiment is further optimized based on the first embodiment. In this embodiment, the not-found sound control function corresponding to the initial semantic text in the preset semantic text set is embodied as: matching the initial semantic text with semantic expression items of each semantic text expression set in the semantic text set; and if the matching fails, determining that the sound control function corresponding to the initial semantic text is not found.
In this embodiment, the updating the initial semantic text to the semantic text set based on the standard semantic text is further embodied as: matching the standard semantic text with semantic expression items of each semantic text expression set in the semantic text set; if the matching is successful, adding the initial semantic text into a semantic text expression set matched with the standard semantic text; and if the matching fails, adding the initial semantic text and the corresponding standard semantic text to the functional text expression set to be opened.
This embodiment has also optimized and increased: and feeding back the text information included in the functional text expression set to be opened to a function development platform so that a developer develops a corresponding sound control function on the function development platform based on the text information.
As shown in fig. 2, the semantic updating method provided in this embodiment specifically includes the following steps:
s201, acquiring an initial semantic text of a target voice input by a user through the vehicle-mounted terminal.
S202, matching the initial semantic text with semantic expression items of each semantic text expression set in a preset semantic text set, wherein the semantic text set comprises: a text expression set with function to be opened and at least one binary information group containing opened voice control function and corresponding semantic text expression set.
S203, judging whether the matching is successful; if yes, executing S204; otherwise, S205 is performed.
And S204, determining the searched sound control function corresponding to the initial semantic text.
Optionally, after determining that the sound control function corresponding to the initial semantic text is found, the method further includes:
and sending an inquiry instruction whether to start the sound control function corresponding to the initial semantic text to the vehicle-mounted terminal so that the vehicle-mounted terminal displays a dialog box corresponding to the inquiry instruction to the user.
Optionally, when receiving a message that the user agrees to turn on the sound control function corresponding to the initial semantic text, which is fed back by the vehicle-mounted terminal, the vehicle-mounted terminal is controlled to turn on the sound control function corresponding to the initial semantic text.
S205, determining that the sound control function corresponding to the initial semantic text is not found, generating a semantic deep parsing request of the target voice and sending the semantic deep parsing request to a semantic parsing terminal.
And S206, receiving a standard semantic text corresponding to the target voice fed back by the semantic analysis terminal.
And S207, matching the standard semantic text with semantic expression items of each semantic text expression set in the semantic text set.
S208, judging whether the matching is successful; if yes, go to S209; otherwise, S210 is performed.
S209, adding the initial semantic text into a semantic text expression set matched with the standard semantic text, and executing S212.
And S210, adding the initial semantic text and the corresponding standard semantic text to the functional text expression set to be opened, and executing S211.
Optionally, for any initial semantic text and corresponding standard semantic text added to the functional text expression set to be opened, when a developer subsequently opens a voice control function corresponding to the initial semantic text and the standard semantic text, the initial semantic text and the standard semantic text are removed from the functional text expression set to be opened, and a semantic text expression set containing the initial semantic text and the standard semantic text is established in the semantic text set.
S211, feeding back the text information included in the text expression set of the function to be opened to a function development platform, so that a developer develops a corresponding voice control function on the function development platform based on the text information.
It can be understood that, the sound control function development by the developer may be to directly implement mapping association between the function of the existing module component of the vehicle and the text information in the text expression set of the function to be activated, thereby implementing the corresponding sound control function, or to add a new function module on the basis of the original module component of the vehicle and implement mapping association with the text information in the text expression set of the function to be activated, thereby implementing the corresponding sound control function.
S212, sending a personal voice list to the vehicle-mounted terminal so that the vehicle-mounted terminal can display the personal voice list to a user, wherein the personal voice list comprises all voices input by the user, corresponding initial semantic texts and real-time opening states of sound control functions corresponding to the initial semantic texts.
S213, when the real-time opening state of the sound control function corresponding to any initial semantic text changes, sending state updating prompt information corresponding to the change to the vehicle-mounted terminal, so that the vehicle-mounted terminal displays the state updating prompt information to a user.
The embodiment of the invention realizes that the voice control function of the vehicle and the coverage of the voice control function to the corresponding voice explanation support of the user are continuously improved by continuously collecting the target voice input by the user on the basis of developing the voice control function in the earlier stage, thereby solving the problem that the explanation set which can meet the requirements of all users cannot be customized due to limited abilities and experiences of developers and various user explanations in the earlier stage of function development.
Further, as an optional embodiment of the second embodiment, the second embodiment further optimizes and includes:
and sending a real-time query entry related to the semantic text set to the vehicle-mounted terminal so that a user can query the semantic text in the semantic text set in real time through the real-time query entry after entering a corresponding function display interface of the vehicle-mounted intelligent terminal.
For example, a user may perform text search or voice search on the semantic text in the semantic text set through the real-time query entry, for example, text keyword search or voice keyword search, and the vehicle-mounted intelligent terminal may display the related semantic text in the semantic text set according to the text or voice input by the user.
Optionally, the real-time query entry further has a one-touch recommendation function.
For example, a corresponding function key may be set on the display interface where the real-time query entry is located, when the user clicks the function key, the system may randomly recommend the semantic text in the semantic text set to the user, and simultaneously set up a viewing record for the user, and when the system recommends the semantic text to the user each time, the system preferentially recommends the semantic text that the user has not viewed. The user can acquire one or more semantic texts recommended by the system by one key, and can submit interested semantic texts as initial semantic texts to experience corresponding voice control functions, or collect the interested semantic texts to a personal voice list, discard uninteresting semantic texts, and acquire new recommended semantic texts by one key again.
Fig. 3 is a diagram illustrating an application example of a semantic updating method according to a second embodiment of the present invention.
EXAMPLE III
Fig. 4 is a schematic structural diagram of a semantic updating apparatus according to a third embodiment of the present invention, where this embodiment is applicable to a situation where coverage supported by a user is continuously improved by continuously collecting target voices input by the user on the basis of an earlier-developed voice control function, and the apparatus may be implemented by software and/or hardware, and specifically includes: an initial identification module 301, a request generation module 302, a standard receiving module 303 and a semantic updating module 304. Wherein the content of the first and second substances,
the initial recognition module 301 is configured to obtain an initial semantic text of a target voice input by a user through the vehicle-mounted terminal;
a request generating module 302, configured to generate a semantic deep parsing request of the target speech and send the semantic deep parsing request to a semantic parsing terminal when a preset semantic text set does not find a sound control function corresponding to the initial semantic text;
a standard receiving module 303, configured to receive a standard semantic text corresponding to the target speech, where the standard semantic text is fed back by the semantic analysis terminal;
a semantic updating module 304, configured to update the initial semantic text to the semantic text set based on the standard semantic text.
On the basis of the above embodiments, the semantic text set includes:
a text expression set with function to be opened and at least one binary information group containing opened voice control function and corresponding semantic text expression set.
On the basis of the foregoing embodiments, the request generation module 302 includes:
and the first matching unit is used for matching the initial semantic text with the semantic expression items of each semantic text expression set in the semantic text set.
And the request generating unit is used for determining that the sound control function corresponding to the initial semantic text is not found if the matching fails, generating a semantic deep analysis request of the target voice and sending the semantic deep analysis request to a semantic analysis terminal.
On the basis of the foregoing embodiments, the semantic updating module 304 includes:
the second matching unit is used for matching the standard semantic text with semantic expression items of each semantic text expression set in the semantic text set;
the first adding unit is used for adding the initial semantic text into a semantic text expression set matched with the standard semantic text if the matching is successful;
and the second adding unit is used for adding the initial semantic text and the corresponding standard semantic text into the functional text expression set to be opened if the matching fails.
On the basis of the foregoing embodiments, the semantic updating apparatus further includes:
and the information feedback module is used for feeding the text information included in the functional text expression set to be opened back to the function development platform so that a developer can develop the corresponding sound control function on the function development platform based on the text information.
On the basis of the foregoing embodiments, the semantic updating apparatus further includes:
and the list display module is used for sending a personal voice list to the vehicle-mounted terminal so that the vehicle-mounted terminal can display the personal voice list to a user, wherein the personal voice list comprises all voices input by the user, corresponding initial semantic texts and real-time opening states of the sound control functions corresponding to the initial semantic texts.
On the basis of the foregoing embodiments, the semantic updating apparatus further includes:
and the updating prompt module is used for sending state updating prompt information corresponding to the change to the vehicle-mounted terminal when the real-time opening state of the sound control function corresponding to any initial semantic text changes, so that the vehicle-mounted terminal displays the state updating prompt information to a user.
The semantic updating device provided by the embodiment of the invention can execute the semantic updating method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the executing method.
Example four
Fig. 5 is a schematic structural diagram of a server according to a fifth embodiment of the present invention, and as shown in fig. 5, the server includes a processor 40, a memory 41, an input device 42, and an output device 43; the number of the processors 40 in the server may be one or more, and one processor 40 is taken as an example in fig. 5; the processor 40, the memory 41, the input device 42 and the output device 43 in the server may be connected by a bus or other means, and fig. 5 illustrates the connection by the bus as an example.
Optionally, the server establishes a communication connection with the vehicle-mounted terminal to receive the target voice input by the user through the vehicle-mounted terminal.
The memory 41 is a computer-readable storage medium, and can be used for storing software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to the semantic updating method in the embodiment of the present invention (for example, the initial identification module 301, the request generation module 302, the standard receiving module 303, and the semantic updating module 304 in the semantic updating device). The processor 40 executes various functional applications and data processing of the server by executing software programs, instructions and modules stored in the memory 41, that is, implements the semantic updating method described above.
The memory 41 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the terminal, and the like. Further, the memory 41 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, memory 41 may further include memory located remotely from processor 40, which may be connected to the server over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input device 42 may be used to receive input numeric or character information and generate key signal inputs related to user settings and function control of the server. The output device 43 may include a display device such as a display screen.
EXAMPLE five
An embodiment of the present invention further provides a storage medium containing computer-executable instructions, which when executed by a computer processor, perform a semantic updating method, including:
acquiring an initial semantic text of a target voice input by a user through a vehicle-mounted terminal;
when the sound control function corresponding to the initial semantic text is not found in the preset semantic text set, generating a semantic deep analysis request of the target voice and sending the semantic deep analysis request to a semantic analysis terminal;
receiving a standard semantic text corresponding to the target voice fed back by the semantic analysis terminal;
updating the initial semantic text to the set of semantic texts based on the standard semantic text.
Of course, the storage medium containing the computer-executable instructions provided by the embodiments of the present invention is not limited to the method operations described above, and may also perform related operations in the semantic updating method provided by any embodiment of the present invention.
From the above description of the embodiments, it is obvious for those skilled in the art that the present invention can be implemented by software and necessary general hardware, and certainly, can also be implemented by hardware, but the former is a better embodiment in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a FLASH Memory (FLASH), a hard disk or an optical disk of a computer, and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device) to execute the methods according to the embodiments of the present invention.
It should be noted that, in the embodiment of the semantic updating apparatus, the included units and modules are only divided according to functional logic, but are not limited to the above division as long as the corresponding functions can be implemented; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (9)
1. A semantic updating method, comprising:
acquiring an initial semantic text of a target voice input by a user through a vehicle-mounted terminal;
when the sound control function corresponding to the initial semantic text is not found in the preset semantic text set, generating a semantic deep analysis request of the target voice and sending the semantic deep analysis request to a semantic analysis terminal;
receiving a standard semantic text corresponding to the target voice fed back by the semantic analysis terminal;
updating the initial semantic text to the semantic text set based on the standard semantic text;
the semantic text set includes: a text expression set with function to be opened and at least one binary information group containing opened voice control function and corresponding semantic text expression set.
2. The method of claim 1, wherein the not finding a voice control function corresponding to the initial semantic text in a preset semantic text set comprises:
matching the initial semantic text with semantic expression items of each semantic text expression set in the semantic text set;
and if the matching fails, determining that the sound control function corresponding to the initial semantic text is not found.
3. The method of claim 1, wherein the updating the initial semantic text to the set of semantic texts based on the standard semantic text comprises:
matching the standard semantic text with semantic expression items of each semantic text expression set in the semantic text set;
if the matching is successful, adding the initial semantic text into a semantic text expression set matched with the standard semantic text;
and if the matching fails, adding the initial semantic text and the corresponding standard semantic text into the functional text expression set to be opened.
4. The method of claim 3, further comprising:
and feeding back the text information included in the functional text expression set to be opened to a function development platform so that a developer develops a corresponding sound control function on the function development platform based on the text information.
5. The method according to any one of claims 1-4, further comprising:
and sending a personal voice list to the vehicle-mounted terminal so that the vehicle-mounted terminal displays the personal voice list to a user, wherein the personal voice list comprises all voices input by the user, corresponding initial semantic texts and real-time opening states of the voice control functions corresponding to the initial semantic texts.
6. The method of claim 5, further comprising:
and when the real-time opening state of the sound control function corresponding to any initial semantic text changes, sending state updating prompt information corresponding to the change to the vehicle-mounted terminal, so that the vehicle-mounted terminal displays the state updating prompt information to a user.
7. A semantic updating apparatus, comprising:
the initial recognition module is used for acquiring an initial semantic text of a target voice input by a user through the vehicle-mounted terminal;
the request generation module is used for generating a semantic deep analysis request of the target voice and sending the semantic deep analysis request to a semantic analysis terminal when the sound control function corresponding to the initial semantic text is not found in a preset semantic text set;
the standard receiving module is used for receiving a standard semantic text corresponding to the target voice fed back by the semantic analysis terminal;
a semantic updating module for updating the initial semantic text to the semantic text set based on the standard semantic text;
the semantic text set includes: a text expression set with function to be opened and at least one binary information group containing opened voice control function and corresponding semantic text expression set.
8. A server, comprising:
one or more processors;
storage means for storing one or more programs;
the one or more programs are executable by the one or more processors to cause the one or more processors to implement the semantic update method of any of claims 1-6.
9. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the semantic updating method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910874821.0A CN110767219B (en) | 2019-09-17 | 2019-09-17 | Semantic updating method, device, server and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910874821.0A CN110767219B (en) | 2019-09-17 | 2019-09-17 | Semantic updating method, device, server and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110767219A CN110767219A (en) | 2020-02-07 |
| CN110767219B true CN110767219B (en) | 2021-12-28 |
Family
ID=69329629
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910874821.0A Active CN110767219B (en) | 2019-09-17 | 2019-09-17 | Semantic updating method, device, server and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110767219B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111627435A (en) * | 2020-04-30 | 2020-09-04 | 长城汽车股份有限公司 | Voice recognition method and system and control method and system based on voice instruction |
| CN111899732A (en) * | 2020-06-17 | 2020-11-06 | 北京百度网讯科技有限公司 | Voice input method and device and electronic equipment |
| CN111796577A (en) * | 2020-06-29 | 2020-10-20 | 中国第一汽车股份有限公司 | Data instruction processing method and device, vehicle and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102427558A (en) * | 2011-09-27 | 2012-04-25 | 深圳市九洲电器有限公司 | Sound control method of set top box and set top box thereof |
| CN105895090A (en) * | 2016-03-30 | 2016-08-24 | 乐视控股（北京）有限公司 | Voice signal processing method and device |
| CN109903754A (en) * | 2017-12-08 | 2019-06-18 | 北京京东尚科信息技术有限公司 | Method for voice recognition, equipment and memory devices |
| CN109920429A (en) * | 2017-12-13 | 2019-06-21 | 上海擎感智能科技有限公司 | It is a kind of for vehicle-mounted voice recognition data processing method and system |
| CN109933198A (en) * | 2019-03-13 | 2019-06-25 | 广东小天才科技有限公司 | A kind of method for recognizing semantics and device |
| CN109933774A (en) * | 2017-12-15 | 2019-06-25 | 腾讯科技（深圳）有限公司 | Method for recognizing semantics, device storage medium and electronic device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7302383B2 (en) * | 2002-09-12 | 2007-11-27 | Luis Calixto Valles | Apparatus and methods for developing conversational applications |
-
2019
- 2019-09-17 CN CN201910874821.0A patent/CN110767219B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102427558A (en) * | 2011-09-27 | 2012-04-25 | 深圳市九洲电器有限公司 | Sound control method of set top box and set top box thereof |
| CN105895090A (en) * | 2016-03-30 | 2016-08-24 | 乐视控股（北京）有限公司 | Voice signal processing method and device |
| CN109903754A (en) * | 2017-12-08 | 2019-06-18 | 北京京东尚科信息技术有限公司 | Method for voice recognition, equipment and memory devices |
| CN109920429A (en) * | 2017-12-13 | 2019-06-21 | 上海擎感智能科技有限公司 | It is a kind of for vehicle-mounted voice recognition data processing method and system |
| CN109933774A (en) * | 2017-12-15 | 2019-06-25 | 腾讯科技（深圳）有限公司 | Method for recognizing semantics, device storage medium and electronic device |
| CN109933198A (en) * | 2019-03-13 | 2019-06-25 | 广东小天才科技有限公司 | A kind of method for recognizing semantics and device |
Non-Patent Citations (1)
| Title |
|---|
| 基于OTA技术的车辆远程数据刷写研究及应用;耿琦等;《电子测试》;20170831(第15期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110767219A (en) | 2020-02-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2022001013A1 (en) | Voice interaction method, vehicle, server, system, and storage medium | |
| CN110767219B (en) | Semantic updating method, device, server and storage medium | |
| KR102112814B1 (en) | Parameter collection and automatic dialog generation in dialog systems | |
| CN105989841B (en) | Vehicle-mounted voice control method and device | |
| US8694206B2 (en) | Systems and methods for off-board voice-automated web searching | |
| DE202016008260U1 (en) | Learn pronunciations of a personalized entity | |
| CN111949240A (en) | Interaction method, storage medium, service program, and device | |
| CN112242141B (en) | Voice control method, intelligent cabin, server, vehicle and medium | |
| CN113421561B (en) | Voice control method, voice control device, server, and storage medium | |
| CN111414512A (en) | Resource recommendation method and device based on voice search and electronic equipment | |
| CN111916088A (en) | Voice corpus generation method and device and computer readable storage medium | |
| CN111681658A (en) | Voice control method and device for vehicle-mounted APP | |
| JP5986468B2 (en) | Display control apparatus, display system, and display control method | |
| JP5341548B2 (en) | Voice recognition device | |
| CN113779300B (en) | Voice input guiding method, device and car machine | |
| JP2017151578A (en) | Language setting system and language setting program | |
| US11620994B2 (en) | Method for operating and/or controlling a dialog system | |
| CN113113015A (en) | Interaction method, information processing method, vehicle and server | |
| CN107967308B (en) | Intelligent interaction processing method, device, equipment and computer storage medium | |
| CN111583918A (en) | Voice control method, vehicle-mounted terminal and vehicle | |
| CN115662430B (en) | Input data analysis method, device, electronic equipment and storage medium | |
| US11893996B1 (en) | Supplemental content output | |
| US20210406463A1 (en) | Intent detection from multilingual audio signal | |
| JP2008233009A (en) | Car navigation device, and program for car navigation device | |
| CN116805005A (en) | Guide word recommendation method, device, equipment and computer readable 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |