Man-machine interaction system for central control screen of commercial vehicle

Abstract

The invention discloses a commercial vehicle central control screen man-machine interaction system, which relates to the technical field of man-machine interaction, and comprises an information acquisition module, a keyword extraction module, a disassembly analysis module, a voice screening module, a space analysis module and a vehicle machine execution module, the system has the advantages that through cooperation of the keyword extraction module and the disassembly analysis module, deep understanding of semantics of voice instructions is facilitated, the accuracy of the instructions is ensured through multi-dimensional analysis, the system can process the voice instructions more comprehensively and reliably, the accuracy and stability of man-machine interaction are improved, and the system is suitable for popularization and application. The central control screen man-machine starting and dormancy are more flexible, the spatial analysis module is beneficial to understanding the source direction and intensity of a voice instruction, effective voice can be better collected in a multi-sound-source environment, interference of environmental noise can be effectively reduced through the voice screening module, and it is ensured that collected voice information is clear and effective.

Description

Technical Field

[0001] The present invention relates to the field of human-computer interaction technology, and in particular to a human-computer interaction system for a central control screen of a commercial vehicle. Background Art

[0002] Human-computer interaction in the automotive field refers to the way users exchange information with automotive systems, including sending commands to the car through various input devices, and obtaining feedback such as vehicle status, navigation information, and multimedia content through the car's output devices. Reasonable human-computer interaction design can minimize the time the driver takes his eyes off the road and his hands off the steering wheel when operating vehicle functions. Human-computer interaction is an important manifestation of automotive intelligence. With the continuous development of automotive technology, vehicles need to interact with users in a more complex and intelligent way. When in use, the common central control screen human-computer interaction system is prone to capture too much voice of the people in the car, affecting the user experience of the people in the car. The lack of effective voice screening means leads to a lot of noise in the collected voice information, affecting the accuracy and clarity of voice recognition and voice calls. It does not fully consider the keyword combination, sentence structure and other factors in the voice, and cannot ensure the accuracy of the instructions. For this reason, we propose a commercial vehicle central control screen human-computer interaction system. Summary of the invention

[0003] The object of the present invention is to provide a human-computer interaction system for a central control screen of a commercial vehicle.

[0004] In order to solve the problems raised in the above background technology, the present invention provides the following technical solutions: A commercial vehicle central control screen human-computer interaction system, comprising an information collection module, the information collection module is used to collect in-vehicle information, and also includes a keyword extraction module, a disassembly analysis module, a voice screening module, a space analysis module and a vehicle execution module; The keyword extraction module obtains the voice of the occupant when waking up the central control screen human machine, and then converts the voice into text information, and establishes a startup instruction unit, which is used to control the state of the central control screen human machine, and then extracts keywords from the text information, generates operation instruction information, and transmits the operation instruction information to the vehicle computer execution module; The disassembly and analysis module extracts text information, then splits the text information into single-word information, generates single-word information, and then segments the single-word information into different segments to generate different segment languages, and simultaneously analyzes the meanings of different segment languages ​​to generate verification instructions, and then transmits the verification instructions to the vehicle computer execution module; The spatial analysis module installs a voice collection device near the door in the car, extracts the voice information initially collected by different voice collection devices, locates the position of the voice by measuring the decibel level of the voice, obtains the location information of the sound source, and then calculates the distance between different voice collection devices and the location information of the sound source; The voice screening module uses the voice collection device to collect voice information in the car. When collecting voice and making calls, a decibel limiting unit will be established to limit the decibel range of the collected voice information; The vehicle computer execution module is used to receive operation instruction information, and then prepare the control of the in-vehicle equipment according to the content of the operation instruction information. When the verification instruction information is received, the operation instruction information is confirmed using the verification instruction information. Only then will the in-vehicle equipment be controlled. At the same time, when voice information is received, the voice information is denoised.

[0005] As a further solution of the present invention: when the keyword extraction module obtains the voice information of the occupant of the vehicle, the start instruction unit includes verb information of starting and shutting down the device, and after converting the voice information into text information, the text information will be synchronously analyzed to determine the relevant content of the start instruction unit therein; When the text information contains the content of the start instruction unit, it starts to analyze the keywords in the text information and generates an operation instruction; When the content of the startup command unit does not exist in the text message, the voice message and text message will be directly deleted, and the car's central control screen will be put into sleep mode.

[0006] As a further solution of the present invention: when waking up the central control screen human-machine interface, the keyword extraction module will synchronously establish a default collection unit, wherein the default collection unit refers to the number of sentences of the default collection sentence, and the number of paragraphs of the default collection unit is set to X. When the person in the car wakes up the central control screen human-machine interface, the keyword extraction module will collect X language information by default and extract keywords within X language information.

[0007] As a further solution of the present invention: when extracting text information, the disassembly and analysis module will simultaneously establish a software word priority unit, use the software word priority unit to record all the names of the software in the car, generate software name information, and then first retrieve the software name information existing in the language information and confirm it. When splitting the text information into single word information, the confirmed software name information will not be split into words.

[0008] As a further solution of the present invention: when generating different segmented languages, the disassembly and analysis module will establish a word-continuation unit, and then record the two-character words and four-character words used in combination into the word-continuation unit. When generating different segmented languages, different words and sentences will be generated in sequence. The word information in the word-continuation unit is set as , let the different words generated be ; S1: S2: S3: Then analyze the output results of S1, S2 and S3 in turn.

[0009] As a further solution of the present invention: after obtaining the output results of S1, S2 and S3, the disassembly analysis module sets priority use rights for S1, S2 and S3, wherein the priority use rights are in the following order: , the word information used in the language information is obtained according to the above method. When S1, S2 and S3 do not output words, they will be used as single word information.

[0010] As a further solution of the present invention: when the spatial analysis module calculates the distance between different voice collection devices and the sound source position information, the distance between the sound source position and the voice collection device is , let the effect of distance on speech decibel be , let P be the number of voice collection devices, let the actual decibel of the voice information be ;

[0011] The actual decibel of the voice information is calculated according to the above formula.

[0012] As a further solution of the present invention: when the voice screening module uses the decibel limiting unit to limit the decibel range of the collected voice information, the decibel limiting unit will be set to 30 decibels by default. When the decibel of the collected voice information is lower than 30 decibels, it will be removed as noise, and then the voice information higher than 30 decibels will be recorded, and the voice information higher than 30 decibels, including the voice information equal to 30 decibels, will be released during voice collection and calls. At the same time, the user can edit the decibel information in the default decibel limiting unit as needed.

[0013] As a further solution of the present invention: after receiving the verification instruction information, the vehicle computer execution module sets the operation instruction information to , assuming the verification instruction information is ,when When the operation instruction information is determined, the in-vehicle equipment is controlled according to the operation instruction information. , the operation instruction information will be canceled and deleted.

[0014] By adopting the above technical solution, compared with the prior art, the beneficial effects of the present invention are: 1. The present invention helps to deeply understand the semantics of voice commands through the cooperation of keyword extraction module and disassembly analysis module, ensures the accuracy of commands through multi-dimensional analysis, makes the system process voice commands more comprehensive and reliable, improves the accuracy and stability of human-computer interaction, makes the startup and sleep of the central control screen more flexible, helps to understand the source direction and intensity of voice commands through the spatial analysis module, can better collect effective voice in a multi-sound source environment, and can effectively reduce the interference of environmental noise through the voice screening module, ensuring that the collected voice information is clear and effective; 2. The present invention can screen out effective voice commands through the keyword extraction module, avoid interference from invalid information, improve the accuracy of system response, be more flexible in waking up the central control screen human-machine and putting the central control screen human-machine to sleep, avoid excessive capture of the voices of people in the car, improve the efficiency of the system in obtaining commands and the speed of interactive response, and avoid the software name from being destroyed when the word is split through the disassembly analysis module, ensure the integrity and accuracy of software-related commands, make the system understand the voice commands related to software operations more accurately, and improve the ability to understand complex voice commands; 3. The present invention can optimize the instruction analysis process by disassembling the analysis module, making the system more accurate in processing diversified voice commands. The spatial analysis module helps to accurately judge the source and strength of voice commands in complex environments, improve the flexibility and applicability of the system, and enable users to optimize the voice interaction experience according to actual conditions. The vehicle-computer execution module can ensure the accuracy and effectiveness of operating instructions, avoid the impact of misoperation on in-vehicle equipment, ensure the reliability and safety of in-vehicle equipment control, and improve users' trust in the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 Schematic diagram of the system flow in an embodiment of the present invention. DETAILED DESCRIPTION

[0016] The specific embodiments of the present invention will be further described below in conjunction with the accompanying drawings. It should be noted that the description of these embodiments is used to help understand the present invention, but does not constitute a limitation of the present invention.

[0017] In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0018] Embodiment 1: Therefore, in order to effectively solve the above problems, the present application proposes a commercial vehicle central control screen human-computer interaction system, as shown in the accompanying drawings of the specification. Figure 1 As shown, a commercial vehicle central control screen human-computer interaction system includes an information collection module, which is used to collect in-vehicle information, and also includes a keyword extraction module, a disassembly analysis module, a voice screening module, a space analysis module and a vehicle computer execution module; The keyword extraction module obtains the voice of the occupant when waking up the central control screen human machine, and then converts the voice into text information, and establishes a startup instruction unit, which is used to control the state of the central control screen human machine, and then extracts keywords from the text information, generates operation instruction information, and transmits the operation instruction information to the vehicle computer execution module; And establish a timbre unit, which includes a weight unit and a normal processing unit. The timbre in the weight unit requires the user to actively record the voice of the corresponding person, and then analyze the timbre of the voice and record it in the weight unit. The timbre that does not belong to the weight unit is included in the normal processing unit. The normal processing unit will not record the timbre of the voice. At the same time, the priority processing authority of the weight unit is higher than the priority processing authority of the normal processing unit; The disassembly and analysis module extracts text information, then splits the text information into single-word information, generates single-word information, and then segments the single-word information into different segments to generate different segment languages, and simultaneously analyzes the meanings of different segment languages ​​to generate verification instructions, and then transmits the verification instructions to the vehicle computer execution module; The spatial analysis module installs a voice collection device near the door in the car, extracts the voice information initially collected by different voice collection devices, locates the position of the voice by measuring the decibel level of the voice, obtains the location information of the sound source, and then calculates the distance between different voice collection devices and the location information of the sound source; The voice screening module uses the voice collection device to collect voice information in the car. When collecting voice and making calls, a decibel limiting unit will be established to limit the decibel range of the collected voice information; The vehicle computer execution module is used to receive the operation instruction information, and then control the in-vehicle equipment according to the content of the operation instruction information. When the verification instruction information is received, the operation instruction information is confirmed by using the verification instruction information. Only then will the in-vehicle equipment be controlled. At the same time, when the voice information is received, the voice information is de-noised; Specific workflow: Collect in-car information. When waking up the central control screen human-machine interface, obtain the voice of the person in the car, establish a startup command unit, use the startup command unit to control the state of the central control screen human-machine interface, generate operation command information, extract text information, generate verification instructions, calculate the voice collection device closest to the sound source location information, use the decibel limiter unit to limit the decibel range of the collected voice information, prepare for in-car device control according to the content of the operation command information, and when receiving the verification command information, use the verification command information to confirm the operation command information. Only then will the in-car device be controlled. When receiving voice information, the voice information will be processed; Furthermore, the cooperation of the keyword extraction module and the disassembly and analysis module can help to deeply understand the semantics of voice commands, ensure the accuracy of commands through multi-dimensional analysis, make the system's processing of voice commands more comprehensive and reliable, improve the accuracy and stability of human-computer interaction, and make the startup and sleep of the central control screen more flexible. The spatial analysis module helps to understand the source direction and intensity of voice commands, and can better collect effective voice in a multi-sound source environment. The voice screening module can effectively reduce the interference of environmental noise and ensure that the collected voice information is clear and effective.

[0019] Embodiment 2: Based on the first embodiment, as shown in the accompanying drawings of the specification Figure 1 As shown, when the keyword extraction module obtains the voice information of the occupants, the start command unit includes the verb information of starting and shutting down the device. After converting the voice information into text information, the text information will be analyzed synchronously to determine the relevant content of the start command unit therein; When the text information contains the content of the start instruction unit, it starts to analyze the keywords in the text information and generates an operation instruction; When the content of the startup command unit does not exist in the text message, the voice message and text message will be directly deleted, and the car's central control screen will be put into sleep mode; Build a verb synonym, antonym library and a custom word library. When users use synonyms or antonyms to express startup or shutdown instructions, the system can also accurately identify them. The content in the custom word library needs to be actively edited by the user. When waking up the central control screen human-machine interface, the keyword extraction module will synchronously establish a default collection unit, where the default collection unit refers to the number of sentences of the default collection sentence. Assuming that the number of paragraphs of the default collection unit is X, when the occupant of the vehicle wakes up the central control screen human-machine interface, the keyword extraction module will collect X pieces of language information by default and extract keywords within X pieces of language information; When extracting text information, the disassembly and analysis module will simultaneously establish a software word priority unit, use the software word priority unit to record all the names of the software in the car, generate software name information, and then first retrieve the software name information existing in the language information and confirm it. When splitting the text information into single word information, the confirmed software name information will not be split into words; When the disassembly analysis module generates different segmented languages, it will establish a word-continuation unit, and then record the two-character words and four-character words used in conjunction into the word-continuation unit. When generating different segmented languages, it will generate different words and sentences in sequence. Let the word information in the word-continuation unit be , let the different words generated be ; S1: S2: S3: Then analyze the output results of S1, S2 and S3 in turn; Specific workflow: The startup command unit contains verb information for starting and shutting down devices. When the startup command unit exists in the text information, the keywords in the text information will be analyzed. When the startup command unit does not exist in the text information, the voice information and text information will be directly deleted, and the central control screen human-machine interface will be put into sleep mode. When the occupants of the vehicle wake up the central control screen human-machine interface, the keyword extraction module will collect X pieces of language information by default, and extract keywords from the language information within X pieces. The software word priority unit will be used to record all the names of the software in the vehicle, and the software name information in the language information will be retrieved first and confirmed. Furthermore, the keyword extraction module can screen out effective voice commands, avoid interference from invalid information, improve the accuracy of system response, be more flexible in waking up the central control screen human-machine interface and putting the central control screen human-machine interface to sleep, avoid excessive capture of the voices of people in the car, and improve the efficiency of the system in obtaining commands and the speed of interactive response. The disassembly and analysis module can be used to avoid the software name from being destroyed when the words are split, thereby ensuring the integrity and accuracy of software-related commands, making the system understand voice commands involving software operations more accurately and improving the ability to understand complex voice commands.

[0020] Embodiment three: Based on the second embodiment, as shown in the accompanying drawings of the specification Figure 1 As shown, after obtaining the output results of S1, S2 and S3, the disassembly analysis module sets priority usage rights for S1, S2 and S3, where the priority usage rights are in the following order: , according to the above method, word information used in the language information is obtained, and when S1, S2 and S3 do not output a word, it will be used as single word information; When the spatial analysis module calculates the distance between different voice collection devices and the sound source location information, the distance between the sound source location and the voice collection device is set to , let the effect of distance on speech decibel be , let P be the number of voice collection devices, let the actual decibel of the voice information be ;

[0021] According to the above formula, the actual decibel of the voice information is calculated; When the voice screening module uses the decibel limit unit to limit the decibel range of the collected voice information, the default decibel limit unit will be 30 decibels. When the decibel of the collected voice information is lower than 30 decibels, it will be removed as noise, and then the voice information higher than 30 decibels will be recorded, and the voice information higher than 30 decibels, including the voice information equal to 30 decibels, will be released during voice collection and calls. At the same time, the user can edit the decibel information in the default decibel limit unit as needed; By building a user voice habit learning model, the system can analyze the voice volume of users in different scenarios and the user's feedback on the accuracy of voice recognition. When the driver often speaks at a low volume, the system can appropriately lower the threshold of the decibel limit unit according to the driver's habits, monitor the ambient noise level inside and outside the car in real time, and based on the frequency, intensity and change trend of the noise, when continuous low-frequency noise is detected in the car, the system will design a filter to effectively remove the noise within this frequency range; After receiving the verification instruction information, the vehicle execution module sets the operation instruction information to , assuming the verification instruction information is ,when When the operation instruction information is determined, the in-vehicle equipment is controlled according to the operation instruction information. , the operation instruction information will be canceled and deleted; Specific workflow: set priority for S1, S2 and S3, obtain the word information used in the language information, calculate the actual decibel of the voice information, record the voice information higher than 30 decibels, and release the voice information higher than 30 decibels during voice collection and calls, including the voice information equal to 30 decibels, and delete the voice information lower than 30 decibels. When the operation instruction information is determined, the in-vehicle equipment is controlled according to the operation instruction information. , the operation instruction information will be canceled and deleted; Furthermore, by disassembling the analysis module, the command analysis process can be optimized, making the system more accurate in handling diversified voice commands. The spatial analysis module can help accurately determine the source and strength of voice commands in complex environments, thereby improving the flexibility and applicability of the system and enabling users to optimize the voice interaction experience based on actual conditions. The vehicle-mounted computer execution module can ensure the accuracy and effectiveness of operating instructions, avoid the impact of misoperation on in-vehicle equipment, ensure the reliability and safety of in-vehicle equipment control, and increase user trust in the system.

[0022] The above shows and describes the basic principles, main features and advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A commercial vehicle central control screen human-computer interaction system, comprising an information collection module, the information collection module is used to collect in-vehicle information, characterized in that: It also includes keyword extraction module, disassembly analysis module, voice screening module, space analysis module and vehicle execution module; The keyword extraction module obtains the voice of the occupant when waking up the central control screen human machine, and then converts the voice into text information, and establishes a startup instruction unit, which is used to control the state of the central control screen human machine, and then extracts keywords from the text information, generates operation instruction information, and transmits the operation instruction information to the vehicle computer execution module; The disassembly and analysis module extracts text information, then splits the text information into single-word information, generates single-word information, and then segments the single-word information into different segments to generate different segment languages, and simultaneously analyzes the meanings of different segment languages ​​to generate verification instructions, and then transmits the verification instructions to the vehicle computer execution module; The spatial analysis module installs a voice collection device near the door in the car, extracts the voice information initially collected by different voice collection devices, locates the position of the voice by measuring the decibel level of the voice, obtains the location information of the sound source, and then calculates the distance between different voice collection devices and the location information of the sound source; The voice screening module uses the voice collection device to collect voice information in the car. When collecting voice and making calls, a decibel limiting unit will be established to limit the decibel range of the collected voice information; The vehicle computer execution module is used to receive operation instruction information, and then prepare the control of the in-vehicle equipment according to the content of the operation instruction information. When the verification instruction information is received, the operation instruction information is confirmed using the verification instruction information. Only then will the in-vehicle equipment be controlled. At the same time, when voice information is received, the voice information is denoised.

2. A commercial vehicle central control screen human-computer interaction system according to claim 1, characterized in that: When the keyword extraction module obtains the voice information of the occupant, the start command unit includes the verb information of starting and shutting down the device. After converting the voice information into text information, the keyword extraction module will simultaneously analyze the text information to determine the relevant content of the start command unit therein; When the text information contains the content of the start instruction unit, it starts to analyze the keywords in the text information and generates an operation instruction; When there is no content in the startup command unit in the text message, the voice message and text message will be directly deleted, and the car's central control screen will be put into sleep mode.

3. A commercial vehicle central control screen human-computer interaction system according to claim 2, characterized in that: When waking up the central control screen human-machine interface, the keyword extraction module will synchronously establish a default collection unit, where the default collection unit refers to the number of sentences of the default collection sentence. Assuming that the number of paragraphs of the default collection unit is X, when the person in the car wakes up the central control screen human-machine interface, the keyword extraction module will collect X pieces of language information by default and extract keywords within X pieces of language information.

4. A commercial vehicle central control screen human-computer interaction system according to claim 1, characterized in that: When extracting text information, the disassembly and analysis module will simultaneously establish a software word priority unit, use the software word priority unit to record all the names of the software in the car, generate software name information, and then first retrieve the software name information existing in the language information and confirm it. When splitting the text information into single-word information, the confirmed software name information will not be split into words.

5. A commercial vehicle central control screen human-computer interaction system according to claim 4, characterized in that: When generating different segmented languages, the disassembly and analysis module will establish a word-continuation unit, and then record the two-character words and four-character words used in combination into the word-continuation unit. When generating different segmented languages, different words and sentences will be generated in sequence. The word information in the word-continuation unit is set as , let the different words generated be ; S1： S2： S3： Then analyze the output results of S1, S2 and S3 in turn.

6. A commercial vehicle central control screen human-computer interaction system according to claim 5, characterized in that: After obtaining the output results of S1, S2 and S3, the disassembly analysis module sets priority usage rights for S1, S2 and S3, where the priority usage rights are in the following order: , the word information used in the language information is obtained according to the above method. When S1, S2 and S3 do not output words, they will be used as single word information.

7. The commercial vehicle central control screen human-computer interaction system according to claim 1, characterized in that: When the spatial analysis module calculates the distance between different voice collection devices and the sound source position information, the distance between the sound source position and the voice collection device is , let the effect of distance on speech decibel be , let P be the number of voice collection devices, let the actual decibel of the voice information be ; The actual decibel of the voice information is calculated according to the above formula.

8. The commercial vehicle central control screen human-computer interaction system according to claim 1, characterized in that: When the voice screening module uses the decibel limit unit to limit the decibel range of the collected voice information, the default decibel limit unit will be 30 decibels. When the decibel of the collected voice information is lower than 30 decibels, it will be removed as noise, and then the voice information higher than 30 decibels will be recorded, and the voice information higher than 30 decibels, including the voice information equal to 30 decibels, will be released during voice collection and calls. At the same time, the user can edit the decibel information in the default decibel limit unit as needed.

9. The commercial vehicle central control screen human-computer interaction system according to claim 1, characterized in that: After receiving the verification instruction information, the vehicle execution module sets the operation instruction information to , assuming the verification instruction information is ,when When the operation instruction information is determined, the in-vehicle equipment is controlled according to the operation instruction information. , the operation instruction information will be canceled and deleted.

Images