CN112581955A - Voice control method, server, voice control system and readable storage medium - Google Patents
Voice control method, server, voice control system and readable storage medium Download PDFInfo
- Publication number
- CN112581955A CN112581955A CN202011380283.9A CN202011380283A CN112581955A CN 112581955 A CN112581955 A CN 112581955A CN 202011380283 A CN202011380283 A CN 202011380283A CN 112581955 A CN112581955 A CN 112581955A
- Authority
- CN
- China
- Prior art keywords
- information
- voice
- template
- control
- round
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 56
- 230000004044 response Effects 0.000 claims abstract description 37
- 230000009471 action Effects 0.000 claims description 57
- 239000012634 fragment Substances 0.000 claims description 19
- 238000004590 computer program Methods 0.000 claims description 11
- 238000004378 air conditioning Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 239000000463 material Substances 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000002452 interceptive effect Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009469 supplementation Effects 0.000 description 1
- 230000001502 supplementing effect Effects 0.000 description 1
- 238000012360 testing method 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
- 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
-
- 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
- G10L2015/223—Execution procedure of a spoken command
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a voice control method, a server, a voice control system and a readable storage medium. The voice control method comprises the following steps: acquiring nth-round voice information, and determining a first rewrite template according to the nth-round voice information and a preset knowledge graph, wherein n is a natural number; acquiring the (n + 1) th round of voice information, and determining a second rewriting template according to the (n + 1) th round of voice information and the knowledge graph; generating response information corresponding to the n +1 th round of voice information according to the first rewriting template and the second rewriting template; and sending a corresponding control instruction to the vehicle according to the nth round voice information and the (n + 1) th round voice information. According to the voice control method, when a user sends a voice command in a multi-turn conversation mode, the subsequent conversation can be correspondingly rewritten according to the related information of the previous conversation, and corresponding response information is generated, so that the accuracy of voice control can be improved, and the voice conversation has fluency.
Description
Technical Field
The present invention relates to the field of intelligent voice control, and in particular, to a voice control method, a server, a voice control system, and a readable storage medium.
Background
In the related art, a task-based dialogue may be performed through an in-vehicle interactive system to control a vehicle system accordingly. Because the whole vehicle control relates to a plurality of vehicle controls, and the user often omits related information in previous conversations in a plurality of rounds of conversations, an interactive system cannot clearly determine control information corresponding to the current conversation, and the fluency of the plurality of rounds of conversations is insufficient.
Disclosure of Invention
The embodiment of the invention provides a voice control method, a server, a voice control system and a readable storage medium.
The embodiment of the invention provides a voice control method, which is used for controlling a vehicle and comprises the following steps:
acquiring nth-round voice information, and determining a first rewrite template according to the nth-round voice information and a preset knowledge graph, wherein n is a natural number;
acquiring the (n + 1) th round of voice information, and determining a second rewriting template according to the (n + 1) th round of voice information and the knowledge graph;
generating response information corresponding to the n +1 th round of voice information according to the first rewriting template and the second rewriting template;
and sending a corresponding control instruction to the vehicle according to the nth round voice information and the (n + 1) th round voice information.
According to the voice control method, when a user sends a voice command in a multi-turn conversation mode, the subsequent conversation can be correspondingly rewritten according to the related information of the previous conversation, and corresponding response information is generated, so that the accuracy of voice control can be improved, and the voice conversation has fluency.
In some embodiments, the voice control method comprises:
acquiring entity information of a control of the vehicle and mode information of the control;
determining a corresponding relation according to the entity information and the mode information;
generating a template fragment corresponding to the entity information according to the mode information;
and establishing the knowledge graph according to the entity information, the mode information, the corresponding relation and the template fragment.
In some embodiments, the vehicle includes a first control corresponding to the nth round of voice information,
acquiring the nth round of voice information, and determining a first rewriting template according to the nth round of voice information and a preset knowledge graph, wherein the method comprises the following steps:
determining first text information according to the nth round of voice information, wherein the first text information comprises entity information of the first control;
determining a template segment corresponding to the first text information according to the knowledge graph and the entity information of the first control, and generating a first mode template;
and generating the first rewriting template according to the first text information and the first mode template.
In some embodiments, the entity information includes control information, action information, and attribute information, the schema information includes control class information, action class information, and attribute class information,
generating the first rewrite template according to the first text information and the first pattern template, including:
replacing control class information in the first mode template with control information of the first control, and/or
Replacing the action class information in the first mode template with the action information of the first control, and/or
And replacing the attribute class information in the first mode template with the attribute information of the first control.
In some embodiments, the vehicle includes a second control corresponding to the n +1 th round of voice information,
acquiring the n +1 th round of voice information, and determining a second rewriting template according to the n +1 th round of voice information and the knowledge graph, wherein the steps comprise:
determining second text information according to the n +1 th round of voice information, wherein the second text information comprises entity information and matching information of the second control;
determining a template segment corresponding to the second text information according to the knowledge graph, the entity information and the matching information of the second control, and generating a second mode template;
and generating the second rewriting template according to the second text information and the second mode template.
In some embodiments, the entity information includes control information, action information, and attribute information, the schema information includes control class information, action class information, and attribute class information,
generating the second rewrite template according to the second text information and the second mode template, including:
replacing the control class information in the second mode template with the control information of the second control, and/or
Replacing the action class information in the second mode template with the action information of the second control, and/or
And replacing the attribute class information in the second mode template with the attribute information of the second control.
In some embodiments, generating response information corresponding to the n +1 th round of voice information according to the first rewrite template and the second rewrite template includes:
matching the second rewriting template with the first rewriting template, removing matching information in the second rewriting template, and determining a missing part in the second rewriting template;
generating a segment to be filled according to the first rewriting template;
filling the missing part with the fragment to be filled;
and generating an entity template and the corresponding response information under the condition that the missing part is detected to be completely filled.
In some embodiments, the voice control method comprises:
canceling the filling of the missing part in a case where it is detected that the missing part is not completely filled.
In some embodiments, the voice control method comprises:
and sending a corresponding control instruction to the second control according to the entity information in the entity template.
The server provided by the embodiment of the invention is used for controlling a vehicle and comprises a control module and a voice acquisition module, wherein the voice acquisition module is used for acquiring the nth round voice information and the (n + 1) th round voice information,
the control module is used for determining a first rewriting template according to the nth round of voice information and a preset knowledge graph, wherein n is a natural number; and
the second rewriting template is determined according to the n +1 th round of voice information and the knowledge graph; and
the response information corresponding to the n +1 th round of voice information is generated according to the first rewriting template and the second rewriting template; and
and the control device is used for sending a corresponding control instruction to the vehicle according to the nth round voice information and the (n + 1) th round voice information.
In the server, when a user sends a voice command in a multi-turn conversation mode, the subsequent conversation can be correspondingly rewritten according to the related information of the previous conversation, and corresponding response information is generated, so that the accuracy of voice control can be improved, and the voice conversation has fluency.
The embodiment of the invention provides a voice control system, which comprises:
the vehicle is used for acquiring the voice information of the nth wheel and the voice information of the (n + 1) th wheel;
the server is used for acquiring the nth round of voice information, determining a first rewriting template according to the nth round of voice information and a preset knowledge graph, wherein n is a natural number; and
the system is used for acquiring the (n + 1) th round of voice information and determining a second rewriting template according to the (n + 1) th round of voice information and the knowledge graph; and
the response information corresponding to the n +1 th round of voice information is generated according to the first rewriting template and the second rewriting template; and
and the control device is used for sending a corresponding control instruction to the vehicle according to the nth round voice information and the (n + 1) th round voice information.
In the voice control system, when a user sends a voice command in a multi-turn conversation mode, the subsequent conversation can be correspondingly rewritten according to the related information of the previous conversation, and corresponding response information is generated, so that the accuracy of voice control can be improved, and the voice conversation has fluency.
In some embodiments, the vehicle is further configured to prompt for the response message.
The embodiment of the invention provides a computer-readable storage medium, on which a computer program is stored, wherein the computer program realizes the voice control method of any one of the above embodiments when being executed by a processor.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The above and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a flow chart of a voice control method of an embodiment of the present invention;
FIG. 2 is a block diagram of a voice control system of an embodiment of the present invention;
FIG. 3 is another flow chart of a voice control method of an embodiment of the present invention;
FIG. 4 is a schematic diagram of a knowledge-graph according to an embodiment of the present invention;
FIG. 5 is another schematic diagram of a knowledge-graph according to an embodiment of the present invention;
FIG. 6 is yet another flow chart of a voice control method of an embodiment of the present invention;
FIG. 7 is yet another flow chart of a voice control method of an embodiment of the present invention;
FIG. 8 is yet another flow chart of a voice control method of an embodiment of the present invention;
FIG. 9 is a schematic diagram of a voice control system of an embodiment of the present invention.
Description of the main element symbols:
a voice control system 100;
a vehicle 10, a warning member 11;
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention.
In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implying any number of technical features indicated. Thus, features defined as "first", "second", may explicitly or implicitly include one or more of the described features. In the description of the present invention, "a plurality" means two or more unless specifically defined otherwise.
In the description of the present invention, it should be noted that the terms "mounted," "connected," and "connected" are to be construed broadly and may be, for example, fixedly connected, detachably connected, or integrally connected unless otherwise explicitly stated or limited. Either mechanically or electrically. Either directly or indirectly through intervening media, either internally or in any other relationship. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
The disclosure herein provides many different embodiments or examples for implementing different configurations of the invention. To simplify the disclosure of the present invention, the components and arrangements of specific examples are described below. Of course, they are merely examples and are not intended to limit the present invention. Furthermore, the present invention may repeat reference numerals and/or letters in the various examples, such repetition is for the purpose of simplicity and clarity and does not in itself dictate a relationship between the various embodiments and/or configurations discussed. In addition, the present invention provides examples of various specific processes and materials, but one of ordinary skill in the art may recognize applications of other processes and/or uses of other materials.
Referring to fig. 1 and 2, a voice control method according to an embodiment of the present invention is applied to a vehicle 10, and the voice control method includes:
step S110: acquiring nth-round voice information, and determining a first rewrite template according to the nth-round voice information and a preset knowledge graph, wherein n is a natural number;
step S130: acquiring the (n + 1) th round of voice information, and determining a second rewriting template according to the (n + 1) th round of voice information and the knowledge graph;
step S150: generating response information corresponding to the n +1 th round of voice information according to the first rewriting template and the second rewriting template;
step S170: and sending a corresponding control instruction to the vehicle 10 according to the nth round voice information and the (n + 1) th round voice information.
The voice control method according to the embodiment of the present invention can be implemented by the server 20 according to the embodiment of the present invention. Referring to fig. 2, the server 20 is used to control the vehicle 10. The server 20 includes a control module 21 and a voice acquisition module 23. The voice obtaining module 23 is configured to obtain the nth round voice information and the (n + 1) th round voice information. The control module 21 is configured to determine a first rewrite template according to the nth round of voice information and a preset knowledge graph, where n is a natural number; and a second rewriting template is determined according to the (n + 1) th round of voice information and the knowledge graph; the response information corresponding to the (n + 1) th round of voice information is generated according to the first rewriting template and the second rewriting template; and is used for sending a corresponding control instruction to the vehicle 10 according to the nth round voice information and the (n + 1) th round voice information.
In the voice control method and the server 20, when the user sends the voice command in a multi-turn conversation mode, the subsequent conversation can be correspondingly rewritten according to the related information of the previous conversation, and corresponding response information is generated, so that the accuracy of voice control can be improved, and the voice conversation has fluency.
In the related technology, the vehicle can recognize the conversation sent by the user in a voice interaction mode, and correspondingly control various controls on the vehicle according to the related information in the conversation, so that the effect of voice control is achieved. In practical application, a user needs to operate a plurality of different controls on a vehicle or operate the same control for a plurality of times, and in the case of performing a plurality of rounds of conversations, the user often omits part of information in subsequent conversations due to convenience.
In view of the above problems, in one embodiment of the present invention, response information corresponding to the n +1 th round of voice information may be obtained by recognizing a plurality of rounds of conversations during a conversation to form n-th round of voice information and n + 1-th round of voice information, generating a first rewrite template including information related to a vehicle control corresponding to the n-th round of voice information from the n-th round of voice information and a preset knowledge map, and generating a second rewrite template including information related to a vehicle 10 rewrite control corresponding to the n + 1-th round of voice information from the n + 1-th round of voice information and the preset knowledge map, determining omitted information in the n + 1-th round of voice information through the first rewrite template and the second rewrite template, and supplementing the omitted information in the second rewrite template according to the first rewrite template, and after determining the response information, the control instruction corresponding to the n +1 th round of voice information can be determined according to the response information, and then the control instruction corresponding to the n +1 th round of voice information and the control instruction corresponding to the n +1 th round of voice information can be sent to the vehicle 10. In other embodiments, the response information corresponding to the n +1 th round of voice information may be matched according to the first rewrite template and the second rewrite template.
In summary, when multiple rounds of conversations are performed, the relevant information in the current round of conversations and the relevant information in the previous round of conversations are determined, and the current round of conversations is rewritten in an information supplementation manner to generate corresponding response information, so that the problem that the conversation is required to be repeated due to difficulty or incapability of identifying the control instruction corresponding to the current round of conversations can be avoided, and the fluency of the conversation and the accuracy of voice control are improved.
n is a natural number, and in one embodiment, n may be equal to 0, 1, 2, etc., it being understood that round 0 may be understood as the first round of the entire human-machine session. In another embodiment, n may be other natural numbers not equal to 0. And adjusting according to specific conditions. The vehicle 10 includes, but is not limited to, a pure electric vehicle, a hybrid vehicle, an extended range electric vehicle, a hydrogen-powered vehicle, a fuel-powered vehicle, and the like.
In the embodiment shown in fig. 2, the voice acquiring module 23 is provided in the server 20, and the vehicle 10 transmits the acquired voice information to the voice acquiring module 23, so that the control module 21 can determine the corresponding rewrite template according to the acquired voice information. In another embodiment, the voice acquiring module 23 may be disposed in the vehicle 10 to directly acquire the voice information and transmit the voice information to the server by wireless transmission, so that the control module 21 may determine the corresponding rewritten template according to the acquired voice information.
Referring to fig. 3, in some embodiments, the voice control method includes:
step S210: acquiring entity information of a control of a vehicle;
step S230: acquiring mode information of a control;
step S250: determining a corresponding relation according to the entity information and the mode information;
step S270: generating a template fragment corresponding to the entity information according to the mode information;
step S290: and establishing a knowledge graph according to the entity information, the mode information, the corresponding relation and the template fragment.
The voice control method according to the embodiment of the present invention can be implemented by the server 20 according to the embodiment of the present invention. Referring to fig. 2, the control module 21 is configured to obtain entity information of a control of the vehicle 10; the method comprises the steps of acquiring mode information of a control; and is used for confirming the corresponding relation according to entity information and mode information; and a template segment for generating corresponding entity information according to the mode information; and the knowledge graph is preset according to the entity information, the mode information, the corresponding relation and the template fragment.
Therefore, the corresponding template fragments can be conveniently and quickly generated according to different controls.
Referring to fig. 4, in the embodiment shown in fig. 4, the corresponding control of the vehicle is a window, and the entity information of the window includes a window body, a specific position of the window, an opening and closing action performed on the window, an opening/closing width of the window, and an adjustment of the opening/closing width of the window. The mode information comprises control type information, action type information and attribute type information of the corresponding control, the attribute type information comprises position attribute and adjustable attribute of the control, the action type information comprises on-off action and adjusting action of the control, and the control type information is used for determining whether the corresponding control is an openable control or a control with position attribute or an adjustable control.
In the case of determining the entity information of the vehicle window, according to a specific language logic, establishing a relationship between all information in the entity information of the vehicle window to form a first corresponding relationship (corresponding to a solid line with an arrow between each information in the entity information of fig. 4). Similarly, the relationship between the related information is established in the mode information, and a second corresponding relationship is formed (corresponding to the solid line with arrows between the information in the mode information of fig. 4). And forming a third corresponding relation (corresponding to the dotted line with the arrow between the entity information and the mode information in fig. 4) according to the corresponding relation between the entity information and the mode information (for example, the car window belongs to the switchable control). And determining the corresponding relation according to the first corresponding contact, the second corresponding contact and the third corresponding contact.
According to the second corresponding relation in the mode information, a plurality of sub-mode information can be generated. Specifically, the embodiment shown in fig. 4 includes first sub-mode information, second sub-mode information, and third sub-mode information. The first sub-mode information comprises control type information and opening and closing actions of the control, the second sub-mode information comprises control type information and position attributes of the control, and the third sub-mode information comprises control type information, adjusting actions of the control and adjustable attributes of the control.
More specifically, in the embodiment shown in fig. 4, the template fragment determining the corresponding entity information may include "[ action ] [ control ]", "[ control ] [ action ]", according to the first sub-pattern information. And determining that the template segment corresponding to the entity information can comprise attribute control according to the second sub-mode information. The third sub-pattern information, the template segment for determining the corresponding entity information may include "[ control ] [ action ] [ attribute value ]", "[ action ] [ control ] [ attribute value ]", "[ control ] [ action ] [ attribute ]", "[ action ] [ control ] [ attribute ]", "[ attribute ] [ control ] [ action ] [ attribute value ]", "[ action ] [ control ] [ attribute ]", and "[ action ] [ control ] [ attribute ]".
In addition, in other embodiments, new entity information and mode information may be added or existing entity information and mode information may be adjusted according to specific situations.
And presetting the knowledge graph according to the entity information, the mode information, the corresponding relation and the template fragment, namely establishing the knowledge graph through the entity information, the mode information, the corresponding relation and the template fragment, so that the template fragment corresponding to the entity information of the control can be directly determined through the knowledge graph.
It can be understood that, in an actual situation, a control can be added to the vehicle according to a specific requirement, and in the case of determining the entity information corresponding to the added control, the entity information of the added control can be corresponded to the mode information in the knowledge graph, so that the relation among the controls (including the control characteristics, the control mode, the control range and the like) can be established, the template fragment related to the added control can be quickly generated, and the expansion of a new service can be quickly and efficiently supported.
Referring to fig. 4 and 5, in the embodiment shown in fig. 5, the corresponding vehicle control is an air conditioner, and when the entity information of the air conditioner is determined, a corresponding relationship can be quickly established between the entity information and the mode information of the air conditioner, so that an indirect connection can be formed between the vehicle window and the air conditioner, and in multiple rounds of conversations, even if the control corresponding to each round of conversation is different, the corresponding control can be obtained according to different rounds of conversations, and a corresponding template fragment can be generated. Controls for the vehicle include, but are not limited to, windows, air conditioning, tailgate, lights, seat position.
In addition, in other embodiments, the knowledgegraph includes an entity layer and a schema layer, with entity information stored within the entity layer and schema information stored within the schema layer.
It should be noted that in other embodiments, step S210 and step S230 may be executed independently, synchronously, or sequentially. In one embodiment, the voice control method may perform step S210 and then perform step S230, so that the entity information and the mode information of the vehicle control may be sequentially acquired.
Referring to fig. 6, in some embodiments, the vehicle includes a first control corresponding to the nth round of voice information. Step S110, including:
step S111: determining first text information according to the nth round of voice information, wherein the first text information comprises entity information of a first control;
step S113: determining a template segment corresponding to the first text information according to the knowledge graph and the entity information of the first control, and generating a first mode template;
step S115: and generating a first rewrite template according to the first text information and the first mode template.
The voice control method according to the embodiment of the present invention can be implemented by the server 20 according to the embodiment of the present invention. Referring to fig. 2, the control module 21 is configured to determine first text information according to the nth round of voice information, where the first text information includes entity information of the first control; the template fragment corresponding to the first text information is determined according to the knowledge graph and the entity information of the first control, and a first mode template is generated; and the first rewrite template is generated according to the first text information and the first mode template.
Thus, the entity information of the corresponding control in the nth round of voice information can be directly determined.
Specifically, referring to fig. 5, in such an embodiment, the nth round of voice information is "driving assistant window is opened in half", so that it can be determined that the entity information of the first control in the first text information includes "driving assistant", "window", "open/close", "half", and further, it can be determined that the corresponding template segment is "[ attribute ] [ control ] [ action ] [ attribute value ]" through the knowledge graph, and the template segment is used as a first pattern template, and then according to the first pattern template and the first text information, the obtained first rewrite template is "[ position: copilot ] [ control: window ] [ action: adjust ] [ attribute value: half ] ". Specific principles of other embodiments reference may be made to the principles of the above-described embodiments. The first control can be one of vehicle window, air conditioner, tail gate, light, seat position.
In some embodiments, the entity information includes control information, action information, and attribute information, and the schema information includes control class information, action class information, and attribute class information. Step S115, including:
replacing control class information in the first schema template with control information of the first control, and/or
Replacing the action class information in the first schema template with the action information of the first control, and/or
And replacing the attribute class information in the first mode template with the attribute information of the first control.
The voice control method according to the embodiment of the present invention can be implemented by the server 20 according to the embodiment of the present invention. Referring to fig. 2, the control module 21 is configured to replace the control class information in the first schema template with the control information of the first control, and/or replace the action class information in the first schema template with the action information of the first control, and/or replace the attribute class information in the first schema template with the attribute information of the first control.
Thus, the first rewrite template can be simply obtained.
Specifically, in one embodiment, in the case that the control information of the first control is determined through the first text information, the control class information in the first schema template is replaced with the control information of the first control to generate a first rewrite template (e.g., replace [ control ] in the first schema template with [ window ]). In another embodiment, in the event that control information for the first control is determined from the first text information, the action class information in the first schema template is replaced with the action information for the first control to generate a first rewrite template (e.g., replace [ control ] in the first schema template with [ adjust ]). In yet another embodiment, in the event that control information for the first control is determined via the first textual information, the property class information in the first schema template is replaced with the property information for the first control to generate a first rewrite template (e.g., replace [ control ] in the first schema template with [ copilot ]). The specific principles of other embodiments are similar to those of the above-described embodiments and will not be expanded in detail here.
Referring to fig. 7, in some embodiments, the vehicle includes a second control corresponding to the n +1 th round of voice information. Step S130, including:
step S131: determining second text information according to the n +1 th round of voice information, wherein the second text information comprises entity information and matching information of a second control;
step S133: determining a template segment corresponding to the second text information according to the knowledge graph, the entity information of the second control and the matching information, and generating a second mode template;
step S135: and generating a second rewriting template according to the second text information and the second mode template.
The voice control method according to the embodiment of the present invention can be implemented by the server 20 according to the embodiment of the present invention. Referring to fig. 2, the control module 21 is configured to determine second text information according to the n +1 th round of voice information, where the second text information includes entity information and matching information of the second control; the template splicing module is used for splicing at least one corresponding template segment according to the corresponding relation, the entity information and the matching information of the second control to generate a second mode template; and the second rewrite template is generated according to the second text information and the second mode template.
Therefore, the entity information of the corresponding control in the n +1 th round of voice information can be directly determined, and the service coverage and the quick landing of the second control are realized.
Specifically, referring to fig. 5, in such an embodiment, the nth voice message is "the second driving window is half" and the (n + 1) th voice message is "the main driving is also. According to the n +1 th round of voice information, the entity information of the second control in the second text information can be determined to comprise ' main drive ' and the matching information is ' yes ', further, the corresponding template segment can be determined to be ' attribute value ] [ same ] ' through the knowledge graph and the matching information, the template segment is used as a second mode template, and then according to the second mode template and the second text information, the obtained second rewriting template is ' position: major and minor drives ] [ same ] ". The second control can be one of vehicle window, air conditioner, tail gate, light, seat position.
In addition, in other embodiments, in the case that a plurality of template fragments corresponding to the second text information are determined according to the knowledge graph, the entity information of the second control and the matching information, the plurality of template fragments corresponding to the second text information may be fused through a specific language logic, thereby forming the second pattern template. In one embodiment, the template segments corresponding to the second text information are "[ attribute values ] [ identity ]" and "[ action ]", the template segments formed by fusion by concatenation are "[ attribute values ] [ identity ] [ action ]", and the template segments are used as the second pattern template. In other embodiments, the second pattern template can be obtained by correspondingly adding, deleting, and modifying the template segments, which is not described herein again.
In some embodiments, the entity information includes control information, action information, and attribute information, and the schema information includes control class information, action class information, and attribute class information. Step S135, including:
replacing control class information in the second schema template with control information of the second control, and/or
Replacing the action class information in the second schema template with the action information of the second control, and/or
And replacing the attribute class information in the second mode template with the attribute information of the second control.
The voice control method according to the embodiment of the present invention can be implemented by the server 20 according to the embodiment of the present invention. Referring to fig. 2, the control module 21 is configured to replace the control class information in the second schema template with the control information of the second control, and/or replace the action class information in the second schema template with the action information of the second control, and/or replace the attribute class information in the second schema template with the attribute information of the second control.
Thus, the second rewrite template can be obtained easily.
Specifically, in one embodiment, in the case where the control information of the second control is determined through the second text information, the control class information in the second schema template is replaced with the control information of the second control to generate a second rewrite template (e.g., replace [ control ] in the second schema template with [ window ]). In another embodiment, in the event that control information for a second control is determined from the second text information, the action class information in the second pattern template is replaced with the action information for the second control to generate a second rewrite template (e.g., replace [ control ] in the second pattern template with [ adjust ]). In yet another embodiment, in the event that control information for the second control is determined via the second text information, the property class information in the second schema template is replaced with the property information for the second control to generate a second rewrite template (e.g., replace [ control ] in the second schema template with [ home ]). The specific principles of other embodiments are similar to those of the above-described embodiments and will not be expanded in detail here.
Referring to fig. 8, in some embodiments, step S150 includes:
step S151: matching the second rewriting template with the first rewriting template, removing matching information in the second rewriting template, and determining a missing part in the second rewriting template;
step S153: generating a segment to be filled according to the first rewriting template;
step S155: filling the missing part with the segment to be filled;
step S157: in the event that the missing portion is detected to be completely filled, an entity template and corresponding response information are generated.
The voice control method according to the embodiment of the present invention can be implemented by the server 20 according to the embodiment of the present invention. Referring to fig. 2, the control module 21 is configured to match the second rewrite template with the first rewrite template, remove matching information in the second rewrite template, and determine a missing portion in the second rewrite template; the segment to be filled is generated according to the first rewriting template; and is used for filling the missing part with the segment to be filled; and generating an entity template and corresponding response information in case that the missing part is detected to be completely filled.
In this way, the second text information can be rewritten, and a control command corresponding to the (n + 1) th round of voice information can be obtained.
Specifically, in such an embodiment, the first rewrite template is "[ position: master drive ] [ control: air conditioning ] [ action: tune to ] [ Attribute value: eighteen degrees ] ", the second rewritten template is" [ position: the "same" in the second rewrite template is removed, and the missing part in the second rewrite template can be determined to be the "control ] [ action ] [ attribute value ]". According to the first rewrite template, generating "[ control: air conditioning ] [ action: tune to ] [ Attribute value: eighteen degrees ] "and fills the segment to be filled into the missing part of the second rewrite template until the missing part is completely filled, thereby obtaining" [ position: copilot ] [ control: air conditioning ] [ action: tune to ] [ Attribute value: eighteen degrees ] "as an entity template and generates corresponding response information, which may be" good "or" the copilot air conditioner is being adjusted to eighteen degrees ". The response information can be selected according to specific conditions, and can also be preset through actual tests.
Additionally, in other embodiments, entity templates may be generated by template parsing. In one embodiment, the template resolution may be implemented using a node matching algorithm based on a tree structure.
In some embodiments, a voice control method comprises:
in the case where it is detected that the missing part is not completely filled, the filling of the missing part is cancelled.
The voice control method according to the embodiment of the present invention can be implemented by the server 20 according to the embodiment of the present invention. Referring to fig. 2, the control module 21 is configured to cancel the filling of the missing part when detecting that the missing part is not completely filled.
In this manner, it may be determined that the session information is incomplete.
Specifically, in one embodiment, in the case where it is detected that the missing part is not completely filled, it may be determined that entity information of the missing part exists, so that filling of the missing part is stopped, and a voice prompt is issued to reconfirm the nth round voice information and/or the (n + 1) th round voice information.
In some embodiments, a voice control method comprises:
and sending a corresponding control instruction to the second control according to the entity information in the entity template.
The voice control method according to the embodiment of the present invention can be implemented by the server 20 according to the embodiment of the present invention. Referring to fig. 2, the control module 21 is configured to send a corresponding control instruction to the second control according to the entity information in the entity template.
Therefore, the corresponding control of the second control can be realized under the condition of ensuring the fluency of the conversation.
Specifically, in one embodiment, the second control is an air conditioner located on a copilot, and the entity template is "[ position: copilot ] [ control: air conditioning ] [ action: tune to ] [ Attribute value: eighteen degrees ] ", so that a control instruction can be sent to the air conditioner of the assistant driver, the air conditioner of the assistant driver is started, and the temperature is adjusted to be eighteen degrees.
Referring to fig. 9, a speech control system 100 according to an embodiment of the present invention includes:
the vehicle 10 is used for acquiring the voice information of the nth wheel and the voice information of the (n + 1) th wheel;
the server 20 is configured to obtain the nth round of voice information, determine a first rewrite template according to the nth round of voice information and a preset knowledge graph, where n is a natural number; and
the second rewrite template is used for acquiring the (n + 1) th round of voice information and determining the second rewrite template according to the (n + 1) th round of voice information and the knowledge graph; and
the response information corresponding to the (n + 1) th round of voice information is generated according to the first rewriting template and the second rewriting template; and
and is used for sending a corresponding control instruction to the vehicle 10 according to the nth round voice information and the (n + 1) th round voice information.
In the voice control system 100, when the user sends a voice command in a multi-turn conversation manner, the subsequent conversation can be correspondingly rewritten according to the related information of the previous conversation, and corresponding response information is generated, so that the accuracy of voice control can be improved, and the voice conversation can be smooth.
In particular, the knowledge graph may be stored within server 20. In one embodiment, in the case that multiple rounds of voice information are collected by the vehicle 10, the multiple rounds of voice information may be uploaded to the server 20, so that the server 20 obtains a first rewriting template and a second rewriting template corresponding to the nth round of voice information and the (n + 1) th round of voice information through a knowledge graph, respectively, and further generates response information corresponding to the (n + 1) th round of voice information. Corresponding control instructions are generated according to the nth round voice information and the (n + 1) th round voice information, the control instructions are sent to the vehicle 10, the vehicle 10 is enabled to control corresponding controls according to the control instructions, even if partial information is lost in the (n + 1) th round voice information, the conversation purpose corresponding to the (n + 1) th round voice information can be known through the nth round voice information, the (n + 1) th round voice information does not need to be confirmed again by a user, the user can conveniently send out more concise and spoken voice instructions, and the fluency of conversation is guaranteed. In one embodiment, the server 20 is a cloud.
In other embodiments, the voice control system 100 may store the rewrite template corresponding to the nth round of voice information, so that the rewrite template can be directly read in the same or similar dialog to obtain the first rewrite template. The vehicle 10 includes, but is not limited to, a pure electric vehicle, a hybrid vehicle, an extended range electric vehicle, a hydrogen-powered vehicle, and the like.
In some embodiments, the vehicle 10 is also used to prompt for response information. In this way, the user can be reminded that the vehicle 10 is controlled correspondingly according to the n +1 th round voice message.
Specifically, in some embodiments, the vehicle 10 includes a cue 11. After the vehicle 10 receives the response message, the user may be prompted for the response message through the prompting piece 11. The prompt part 11 may include a buzzer, an LED lamp, and a display screen, and the response information may include voice, alarm prompt tone, light with a specific change rule, and characters on the display screen.
The embodiment of the invention provides a computer readable storage medium, on which a computer program is stored, and the computer program realizes the voice control method of any one of the above embodiments when being executed by a processor.
For example, in the case of a computer program being executed, the following steps may be implemented:
step S110: acquiring nth-round voice information, and determining a first rewrite template according to the nth-round voice information and a preset knowledge graph, wherein n is a natural number;
step S130: acquiring the (n + 1) th round of voice information, and determining a second rewriting template according to the (n + 1) th round of voice information and the knowledge graph;
step S150: generating response information corresponding to the n +1 th round of voice information according to the first rewriting template and the second rewriting template;
step S170: and sending a corresponding control instruction to the vehicle according to the nth round voice information and the (n + 1) th round voice information.
The computer-readable storage medium may be provided in a vehicle or in a terminal such as a server, and the vehicle may communicate with the terminal to obtain the corresponding program.
It is understood that the computer-readable storage medium may include: any entity or device capable of carrying a computer program, recording medium, U-disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), software distribution medium, and the like. The computer program includes computer program code. The computer program code may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable storage medium may include: any entity or device capable of carrying computer program code, recording medium, U-disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), software distribution medium, and the like.
In some embodiments of the present invention, the control module may be a single chip integrated with a processor, a memory, a communication module, and the like. The Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and alternate implementations are included within the scope of the preferred embodiment of the present invention in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present invention.
The logic and/or steps represented in the flowcharts or otherwise described herein, such as an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processing module-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions.
In the description of the specification, references to the terms "one embodiment", "some embodiments", "certain embodiments", "illustrative embodiments", "examples", "specific examples", or "some examples", etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
While embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that: various changes, modifications, substitutions and alterations can be made to the embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.
Claims (13)
1. A voice control method for controlling a vehicle, characterized by comprising:
acquiring nth-round voice information, and determining a first rewrite template according to the nth-round voice information and a preset knowledge graph, wherein n is a natural number;
acquiring the (n + 1) th round of voice information, and determining a second rewriting template according to the (n + 1) th round of voice information and the knowledge graph;
generating response information corresponding to the n +1 th round of voice information according to the first rewriting template and the second rewriting template;
and sending a corresponding control instruction to the vehicle according to the nth round voice information and the (n + 1) th round voice information.
2. The voice control method according to claim 1, characterized in that the voice control method comprises:
acquiring entity information of a control of the vehicle and mode information of the control;
determining a corresponding relation according to the entity information and the mode information;
generating a template fragment corresponding to the entity information according to the mode information;
and establishing the knowledge graph according to the entity information, the mode information, the corresponding relation and the template fragment.
3. The voice control method of claim 2, wherein the vehicle includes a first control corresponding to the nth round of voice information,
acquiring the nth round of voice information, and determining a first rewriting template according to the nth round of voice information and a preset knowledge graph, wherein the method comprises the following steps:
determining first text information according to the nth round of voice information, wherein the first text information comprises entity information of the first control;
determining a template segment corresponding to the first text information according to the knowledge graph and the entity information of the first control, and generating a first mode template;
and generating the first rewriting template according to the first text information and the first mode template.
4. The voice control method according to claim 3, wherein the entity information includes control information, action information, and attribute information, the mode information includes control class information, action class information, and attribute class information,
generating the first rewrite template according to the first text information and the first pattern template, including:
replacing control class information in the first mode template with control information of the first control, and/or
Replacing the action class information in the first mode template with the action information of the first control, and/or
And replacing the attribute class information in the first mode template with the attribute information of the first control.
5. The voice control method of claim 3, wherein the vehicle includes a second control corresponding to the n +1 th round of voice information,
acquiring the n +1 th round of voice information, and determining a second rewriting template according to the n +1 th round of voice information and the knowledge graph, wherein the steps comprise:
determining second text information according to the n +1 th round of voice information, wherein the second text information comprises entity information and matching information of the second control;
determining a template segment corresponding to the second text information according to the knowledge graph, the entity information and the matching information of the second control, and generating a second mode template;
and generating the second rewriting template according to the second text information and the second mode template.
6. The voice control method according to claim 5, wherein the entity information includes control information, action information, and attribute information, the mode information includes control class information, action class information, and attribute class information,
generating the second rewrite template according to the second text information and the second mode template, including:
replacing the control class information in the second mode template with the control information of the second control, and/or
Replacing the action class information in the second mode template with the action information of the second control, and/or
And replacing the attribute class information in the second mode template with the attribute information of the second control.
7. The voice control method according to claim 5, wherein generating response information corresponding to the n +1 th round of voice information based on the first rewrite template and the second rewrite template includes:
matching the second rewriting template with the first rewriting template, removing matching information in the second rewriting template, and determining a missing part in the second rewriting template;
generating a segment to be filled according to the first rewriting template;
filling the missing part with the fragment to be filled;
and generating an entity template and the corresponding response information under the condition that the missing part is detected to be completely filled.
8. The voice control method according to claim 7, characterized in that the voice control method comprises:
canceling the filling of the missing part in a case where it is detected that the missing part is not completely filled.
9. The voice control method according to claim 7, characterized in that the voice control method comprises:
and sending a corresponding control instruction to the second control according to the entity information in the entity template.
10. A server for controlling a vehicle, the server comprising a control module and a voice acquisition module, the voice acquisition module being configured to acquire voice information of an nth round and voice information of an (n + 1) th round,
the control module is used for determining a first rewriting template according to the nth round of voice information and a preset knowledge graph, wherein n is a natural number; and
the second rewriting template is determined according to the n +1 th round of voice information and the knowledge graph; and
the response information corresponding to the n +1 th round of voice information is generated according to the first rewriting template and the second rewriting template; and
and the control device is used for sending a corresponding control instruction to the vehicle according to the nth round voice information and the (n + 1) th round voice information.
11. A voice control system, comprising:
the vehicle is used for acquiring the voice information of the nth wheel and the voice information of the (n + 1) th wheel;
the server is used for acquiring the nth round of voice information, determining a first rewriting template according to the nth round of voice information and a preset knowledge graph, wherein n is a natural number; and
the system is used for acquiring the (n + 1) th round of voice information and determining a second rewriting template according to the (n + 1) th round of voice information and the knowledge graph; and
the response information corresponding to the n +1 th round of voice information is generated according to the first rewriting template and the second rewriting template; and
and the control device is used for sending a corresponding control instruction to the vehicle according to the nth round voice information and the (n + 1) th round voice information.
12. The voice control system of claim 11, wherein the vehicle is further configured to prompt for the response message.
13. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the speech control method according to any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011380283.9A CN112581955B (en) | 2020-11-30 | 2020-11-30 | Voice control method, server, voice control system, and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011380283.9A CN112581955B (en) | 2020-11-30 | 2020-11-30 | Voice control method, server, voice control system, and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112581955A true CN112581955A (en) | 2021-03-30 |
| CN112581955B CN112581955B (en) | 2024-03-08 |
Family
ID=75128067
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011380283.9A Active CN112581955B (en) | 2020-11-30 | 2020-11-30 | Voice control method, server, voice control system, and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112581955B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113239178A (en) * | 2021-07-09 | 2021-08-10 | 肇庆小鹏新能源投资有限公司 | Intention generation method, server, voice control system and readable storage medium |
| CN113611297A (en) * | 2021-06-25 | 2021-11-05 | 北京智芯微电子科技有限公司 | Intelligent control method and device and intelligent product |
| CN113990299A (en) * | 2021-12-24 | 2022-01-28 | 广州小鹏汽车科技有限公司 | Voice interaction method and device, server and readable storage medium thereof |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105513593A (en) * | 2015-11-24 | 2016-04-20 | 南京师范大学 | Intelligent human-computer interaction method drove by voice |
| CN109033063A (en) * | 2017-06-09 | 2018-12-18 | 微软技术许可有限责任公司 | The machine inference of knowledge based map |
| CN109616108A (en) * | 2018-11-29 | 2019-04-12 | 北京羽扇智信息科技有限公司 | More wheel dialogue interaction processing methods, device, electronic equipment and storage medium |
| CN110313153A (en) * | 2017-02-14 | 2019-10-08 | 微软技术许可有限责任公司 | Intelligent digital assistance system |
| CN111143525A (en) * | 2019-12-17 | 2020-05-12 | 广东广信通信服务有限公司 | Vehicle information acquisition method and device and intelligent vehicle moving system |
| CN111339246A (en) * | 2020-02-10 | 2020-06-26 | 腾讯云计算（北京）有限责任公司 | Query statement template generation method, device, equipment and medium |
| CN111640432A (en) * | 2020-05-27 | 2020-09-08 | 北京声智科技有限公司 | Voice control method and device, electronic equipment and storage medium |
| CN111930913A (en) * | 2020-08-14 | 2020-11-13 | 上海茂声智能科技有限公司 | Knowledge graph-based question and answer method, system, device, equipment and medium |
-
2020
- 2020-11-30 CN CN202011380283.9A patent/CN112581955B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105513593A (en) * | 2015-11-24 | 2016-04-20 | 南京师范大学 | Intelligent human-computer interaction method drove by voice |
| CN110313153A (en) * | 2017-02-14 | 2019-10-08 | 微软技术许可有限责任公司 | Intelligent digital assistance system |
| CN109033063A (en) * | 2017-06-09 | 2018-12-18 | 微软技术许可有限责任公司 | The machine inference of knowledge based map |
| CN109616108A (en) * | 2018-11-29 | 2019-04-12 | 北京羽扇智信息科技有限公司 | More wheel dialogue interaction processing methods, device, electronic equipment and storage medium |
| CN111143525A (en) * | 2019-12-17 | 2020-05-12 | 广东广信通信服务有限公司 | Vehicle information acquisition method and device and intelligent vehicle moving system |
| CN111339246A (en) * | 2020-02-10 | 2020-06-26 | 腾讯云计算（北京）有限责任公司 | Query statement template generation method, device, equipment and medium |
| CN111640432A (en) * | 2020-05-27 | 2020-09-08 | 北京声智科技有限公司 | Voice control method and device, electronic equipment and storage medium |
| CN111930913A (en) * | 2020-08-14 | 2020-11-13 | 上海茂声智能科技有限公司 | Knowledge graph-based question and answer method, system, device, equipment and medium |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113611297A (en) * | 2021-06-25 | 2021-11-05 | 北京智芯微电子科技有限公司 | Intelligent control method and device and intelligent product |
| CN113239178A (en) * | 2021-07-09 | 2021-08-10 | 肇庆小鹏新能源投资有限公司 | Intention generation method, server, voice control system and readable storage medium |
| CN113990299A (en) * | 2021-12-24 | 2022-01-28 | 广州小鹏汽车科技有限公司 | Voice interaction method and device, server and readable storage medium thereof |
| WO2023116500A1 (en) * | 2021-12-24 | 2023-06-29 | 广州小鹏汽车科技有限公司 | Speech interaction method and apparatus, server, and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112581955B (en) | 2024-03-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112581955A (en) | Voice control method, server, voice control system and readable storage medium | |
| CN109421731B (en) | Reliability verification module, driving assistance system and method for calibrating sensor | |
| CA2960140C (en) | Information providing device and non-transitory computer readable medium storing information providing program | |
| US20190205744A1 (en) | Distributed Architecture for Enhancing Artificial Neural Network | |
| RU2692300C2 (en) | Adaptive combination of driver identifications | |
| US11514908B2 (en) | Voice command recognition device and method thereof | |
| US20230286513A1 (en) | Safety mechanism for assuring driver engagement during autonomous drive | |
| US10475466B2 (en) | Adaptive vehicle state-based hands-free phone noise reduction with learning capability | |
| WO2019133194A1 (en) | Self-learning in distributed architecture for enhancing artificial neural network | |
| US11027745B2 (en) | Indirect vehicle parametrization via user profiles | |
| CN111007999A (en) | User adaptive volume selection | |
| US9896049B2 (en) | Voice recognition device and voice recognition system | |
| CN112634888A (en) | Voice interaction method, server, voice interaction system and readable storage medium | |
| DE102018125564A1 (en) | RESPONSE RAPID ACTIVATION OF A VEHICLE FEATURE | |
| US10106173B2 (en) | Systems and methods of an adaptive interface to improve user experience within a vehicle | |
| CA3095590A1 (en) | Diagnostic system and method for processing data of a motor vehicle | |
| WO2023125002A1 (en) | Voice interaction method and apparatus, model training method, vehicle and storage medium | |
| CN114299929A (en) | Voice interaction method and device, server and storage medium | |
| CN114023324B (en) | Voice interaction method and device, vehicle and storage medium | |
| CN112440900A (en) | Vehicle control method and device, control equipment and automobile | |
| GB2577488A (en) | Improvements to system controllers | |
| CN112883221B (en) | Semantic information correction method and device and intelligent cabin | |
| WO2024126023A1 (en) | Computing systems and methods for generating user-specific automated vehicle actions | |
| US20210158810A1 (en) | Voice interface for selection of vehicle operational modes | |
| CN116729062A (en) | Demisting control method and system for vehicle-mounted air conditioner |
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 |