WO2024026811A1

WO2024026811A1 - Control system for controlling slow vehicle by using speech

Info

Publication number: WO2024026811A1
Application number: PCT/CN2022/110453
Authority: WO
Inventors: 李威勋
Original assignee: 信昌宏工业股份有限公司
Priority date: 2022-08-05
Filing date: 2022-08-05
Publication date: 2024-02-08

Abstract

A control system for controlling a slow vehicle by using speech. The control system is assembled in a slow vehicle body (10), and comprises: a vehicle-mounted speech sound box (1), a network module (2), a plurality of physiological sensor modules (3), and a vehicle state monitoring module (4). A user may interact with the vehicle-mounted speech sound box (1) by means of speech; a processing unit (14) performs analysis according to a speech instruction, which is received by a receiving unit (11), and obtains answer information, which is given in response, by means of the network module (2), or by means of the physiological sensor modules (3) or the vehicle state monitoring module (4) according to a requirement of the speech instruction; and a speech integration and output unit (15) replies with an answer or the requirement, such that speech intelligence is closer to human usage requirements.

Description

Control system for local train using voice control

Technical field

The present invention relates to the technical field of using voice to control local trains, and in particular, to a control system for using voice to control local trains that can utilize a voice interactive system to control the traveling speed of local trains and monitor the physiological state of driving.

Background technique

With the development of information technology, artificial intelligence technology has also continued to flourish. In recent years, the combination of artificial intelligence and the Internet of Things has enabled artificial intelligence to continuously learn to interact with humans based on collected information; and many manufacturers are currently actively developing the easiest Interaction method – voice, for example, it can help people solve life problems through voice input.

Intelligent voice interaction has changed the previous touch input method to another brand-new way. Therefore, in addition to smart mobile devices (mobile phones, tablets), many manufacturers have invested in the technical field of smart speakers. Most of the current smart speaker technologies are used in playback Music, weather report, alarm clock setting.

technical problem

However, most of the aforementioned smart speakers are used in indoor environments, and currently no smart speaker functions have been used on bicycles or slow trains (such as electric wheelchairs and assistive devices).

How to integrate artificial voice control technology into bicycles or slow cars has become a topic actively developed by technicians in the field.

Technical solutions

The main purpose of the present invention is to provide a control system that uses voice to control a local train. It is assembled on a local train body and includes: a vehicle-mounted voice speaker, a network module, a plurality of physiological sensor modules and a Vehicle condition monitoring module.

The vehicle-mounted voice speaker includes a receiving unit, a sequencing unit, a storage unit, a processing unit and a voice integrated output unit; the receiving unit is used to receive multiple voice commands; the sequencing unit is connected to the receiving unit to The voice command is edited into a segmentation information, and a time information is defined according to the time point when the segmentation information is received; the storage unit stores the segmentation information respectively according to the time information; the processing unit, the storage unit, the voice integrated output unit, and the network The module, these physiological sensor modules and the vehicle status monitoring module are connected. The processing unit analyzes the segment information and time information, and is connected to the aforementioned network module or these physiological sensors according to the analysis results. The module or the vehicle status monitoring module requests feedback of answer information, and the answer information is output by the voice integrated output unit.

The network module is connected to the processing unit, and is connected to a cloud database through the network module. It searches for corresponding information based on the sentence segmentation information and sends it back to the processing unit.

These physiological sensor modules are installed on the local train body, and each physiological sensor module is connected to the processing unit. Each physiological sensor module is used to monitor the user's physiological status, and then The information is sent back to the processing unit for analysis and processing.

The vehicle status monitoring module is installed on the local train body. The vehicle status monitoring module is used to monitor the vehicle condition of the local train body. The aforementioned vehicle conditions include: vehicle speed, direction of travel, tire pressure, objects adjacent to the vehicle body, and vehicles. Usage Information.

In this way, the user can interact with the vehicle-mounted voice speaker through voice, and the processing unit analyzes the voice instructions received by the receiving unit, and passes the network module or these physiological sensor modules according to the needs of the voice instructions. , or the vehicle status monitoring module obtains the response information, and the voice integrated output unit replies the answer or demand, making voice intelligence closer to human needs.

In an embodiment of the present invention, the vehicle-mounted voice speaker includes a casing and a substrate. The aforementioned substrate is installed in the casing. The local train body is a bicycle, and the casing is combined with a faucet of the bicycle. The substrate provides The aforementioned receiving unit, sequencing unit, storage unit, processing unit and voice integrated output unit are installed.

In the aforementioned embodiment, the housing is further provided with a control panel, which is connected to the processing unit and used to display the answer information analyzed by the processing unit.

In the foregoing embodiments, the substrate can provide the network module for embedded assembly, and the network module is a wireless network card.

In the aforementioned embodiment, the physiological sensor module is installed on the handle and seat cushion of the local train body.

beneficial effects

Through the above description, the advantages obtained by the present invention are as follows:

1. When driving a slow vehicle (such as a bicycle), users can interact with artificial intelligence through voice, such as starting the vehicle system, turning off the vehicle system, turning on and off lights, accelerating and decelerating, planning travel routes, or knowing the length of riding time. Or it can grasp the user's physiological status (such as heartbeat, calorie consumption), etc. The user does not need to use manual control when riding a slow bike, which can increase the safety of use.

2. When more complex or real-time answer information is needed, such as weather conditions and road conditions, the network module is used to connect to the cloud database to obtain relevant answers. This can save the storage space of the storage unit and reduce the overall size of the structure. .

3. With the installation of physiological sensor modules on the slow bike handlebars and seats, it can monitor the user's heartbeat, riding time, calories burned and other information. For example: after riding for 1 hour, the heartbeat is 100, and the calories burned are 100. Card and other voice information.

4. Through the vehicle status monitoring module installed on the slow train body, you can use voice commands to learn information such as tire pressure or whether there is any abnormal information before use. During use, you can use the vehicle status monitoring module to monitor such as vehicle speed, The driving distance, whether there are objects that are too close nearby, etc., therefore, improve the safety of users when using local trains.

Description of drawings

Figure 1 is an overall structural diagram of an embodiment of the present invention;

Figure 2 is a system diagram of an embodiment of the present invention;

Figure 3 is a structural configuration diagram of a vehicle-mounted voice speaker according to an embodiment of the present invention;

Figure 4 is a structural configuration diagram of a network module according to an embodiment of the present invention;

Figure 5 is a structural configuration diagram of a physiological sensor module according to an embodiment of the present invention;

Figure 6 is a structural configuration diagram of a vehicle status monitoring module according to an embodiment of the present invention;

Figure 7 is a schematic diagram of the action of inputting voice commands according to the embodiment of the present invention;

Figure 8 is a schematic diagram of using a network module to request answer information according to voice commands according to an embodiment of the present invention;

Figure 9 is a schematic diagram of using a physiological sensor module to request answer information according to voice commands according to an embodiment of the present invention;

Figure 10 is a schematic diagram of using a physiological sensor module to request answer information according to voice commands according to an embodiment of the present invention;

Figure 11 is a schematic diagram of the use of the control instrument panel according to the embodiment of the present invention.

Explanation of reference signs

10 Idle car body

1 car voice speaker

11 receiving unit

12 sequencing units

13 storage units

14 processing units

15 Voice integrated output unit

16 shell

17 substrate

2 Network modules

3 Physiological sensor module

4 Vehicle status monitoring module

5 Control Dashboard

6 Cloud database.

Best Mode of Carrying Out the Invention

In order to enable those skilled in the art to further understand and recognize the features and characteristics of the present invention, the following preferred embodiments are enumerated and explained with reference to the accompanying drawings:

Please refer to Figures 1 to 2. The control system for using voice to control local trains of the present invention is assembled on a local train body 10. The control system for using voice to control local trains mainly includes: a vehicle-mounted voice speaker 1 and a network module. 2. Multiple physiological sensor modules 3 and a vehicle status monitoring module 4. In the embodiment of the present invention, a bicycle is used as an example, but in fact, it can also be used in assistive devices such as wheelchairs and electric wheelchairs.

As shown in Figures 1, 2, and 3, the vehicle voice speaker 1 includes a receiving unit 11, a sequencing unit 12, a storage unit 13, a processing unit 14, and a voice integrated output unit 15; the receiving unit 11 Used to receive multiple voice commands; the sequencing unit 12 is connected to the receiving unit 11, edits the voice commands into segmentation information, and defines a time information based on the time point when the segmentation information is received; the storage unit 13 is based on the time information Store segmentation information respectively; the processing unit 14 is connected to the storage unit 13, the voice integrated output unit 15, the network module 2, the physiological sensor modules 3 and the vehicle status monitoring module 4. The processing unit 14 14 Analyze according to the sentence segment information and time information, and connect to the aforementioned network module 2, or these physiological sensor modules 3, or the vehicle status monitoring module 4 according to the analysis results to request feedback answer information, and the answer information is provided by The speech integrated output unit 15 outputs.

Please continue to refer to Figures 1 to 3. The vehicle-mounted voice speaker 1 includes a shell 16 and a base plate 17. The aforementioned base plate 17 is installed in the outer shell 16. The local train body 10 is a bicycle, and the outer shell 16 is assembled on As a faucet of the bicycle, the base plate 17 provides for the installation of the aforementioned receiving unit 11, sequencing unit 12, storage unit 13, processing unit 14 and voice integrated output unit 15.

Please refer to FIGS. 1 to 3 . In the aforementioned embodiment, the housing 16 is also provided with a control dashboard 5 . The control dashboard 5 is connected to the processing unit 14 and is used to display the answer information analyzed by the processing unit.

As shown in Figures 2 and 4, the network module 2 is connected to the processing unit 14. In the embodiment of the present invention, it can be a wireless network card and is embedded on the substrate 17. Through the network module 2 Connected to a cloud database 6, the corresponding information is found according to the sentence segmentation information and returned to the processing unit 14.

Please refer to Figures 2 and 5. These physiological sensor modules 3 are installed on the local train body 10. In this embodiment, the local train body 10 is a bicycle, and the physiological sensor modules 3 are installed on the handles and seat cushions. At , each physiological sensor module 3 is connected to the processing unit 14. Each physiological sensor module 3 is used to monitor the user's physiological state (for example: heartbeat, riding time), and return the sensed information. to the processing unit 14 for analysis and processing.

As shown in Figures 2 and 6, the vehicle status monitoring module 4 is installed on the local train body 10. The vehicle status monitoring module 4 is used to monitor the vehicle conditions of the local train body 10. The aforementioned vehicle conditions include: vehicle speed, Direction of travel, tire pressure, objects adjacent to the vehicle body, and vehicle usage information.

In this way, the user can interact with the vehicle voice speaker 1 through voice. The processing unit 14 analyzes the voice instructions received by the receiving unit 11, and according to the needs of the voice instructions through the network module 2 or through these physiological senses. The detector module 3 or the vehicle status monitoring module 4 obtains the response answer information, and the voice integrated output unit 15 replies with answers or requirements, making voice intelligence closer to human needs.

The above is an introduction to the functions of each module of the present invention. The operation mode of the present invention and the advantages that can be obtained will be introduced later.

As shown in Figure 7, the user inputs a voice command, such as: "What time is it now?" or "Please help me plan a route to a certain scenic spot." After the receiving unit 11 receives the voice command, the sequencing unit 12 The editing is to edit the time information and corresponding sentence segmentation information according to the time of the voice command. In other words, the combination of voice commands is analyzed in time order. If there is only a single voice command, the sequencing unit 12 function can be skipped. If it is "Please "Help me plan a route to a certain scenic spot, I want to arrive in 5 minutes", the voice command is split into "Plan a route to a certain scenic spot" as the first sentence segment information, and "I want to arrive in 5 minutes" as the first sentence segment. Sentence segmentation information; the storage unit 13 stores the sentence segmentation information respectively according to the time information, and the processing unit 14 performs textual analysis of the voice command. The textual analysis of voice commands must be based on the functions of the network module 2, or the physiological sensor module 3, or the vehicle status sensing module 4. For example, when the user says "heartbeat", then The physiological sensor module 3 obtains and provides relevant data, and the corresponding device replies with answer information. The processing unit 14 receives the answer information, analyzes it, and outputs the relevant answer through the voice integrated output unit 15 .

As shown in Figure 8, when the vehicle-mounted voice speaker 1 receives a question that needs to be answered through the network, such as: planning a route, or today's weather, or the departure time of the next train; the processing unit 14 will pass the relevant question through the network. Module 2 obtains the answer, and the network module 2 is connected to the cloud database 6, and the cloud database 6 can be searched using requests such as google search, bing search, etc. After obtaining the relevant answer, the answer information is returned to the processing unit 14. Relevant answers are output through the voice integrated output unit 15 .

As shown in Figure 9, when the car voice speaker 1 receives a question that requires the user's physiological state, such as heartbeat and calories burned, the processing unit 14 will answer the relevant question through the physiological sensor module 3. Physiological sensor modules 3 installed on handles and chair cushions monitor the user's physiological state, transmit answer information back to the processing unit 14, and output relevant answers through the voice integrated output unit 15.

As shown in Figure 10, when the vehicle voice speaker 1 receives a question requiring vehicle conditions, such as the current vehicle speed, or whether there is a car coming from behind, or vehicle condition, the processing unit 14 will pass the relevant questions through the vehicle status sensing module. 4 answers relevant questions, and the functions of the vehicle status sensing module 4 can include vehicle speed monitoring, tire pressure monitoring, radar monitoring and other related functions, and the answer information is returned to the processing unit 14, and the relevant answers are output through the voice integrated output unit 15.

As shown in FIG. 11 , in addition to replying answers through voice, the answer information analyzed by the processing unit 14 can also be displayed through the control dashboard 5 .

It should be stated that the above are the technical principles directly used in the specific implementation of the present invention. If changes are made according to the concept of the present invention and the resulting functions do not exceed the spirit covered by the description and drawings, they should be Within the scope of the present invention, all are stated.

Claims

A control system that uses voice to control local trains, which is characterized in that it is assembled on a local train body and includes: a vehicle-mounted voice speaker, a network module, a plurality of physiological sensor modules and a vehicle status monitoring module ;

The vehicle-mounted voice speaker includes a receiving unit, a sequencing unit, a storage unit, a processing unit and a voice integrated output unit; the receiving unit is used to receive multiple voice commands; the sequencing unit is connected to the receiving unit to The voice command is edited into a segmentation information, and a time information is defined according to the time point when the segmentation information is received; the storage unit stores the segmentation information respectively according to the time information; the processing unit, the storage unit, the voice integrated output unit, and the network The module, these physiological sensor modules and the vehicle status monitoring module are connected. The processing unit analyzes the segment information and time information, and is connected to the aforementioned network module or these physiological sensors according to the analysis results. The module, or the vehicle status monitoring module, requests feedback of answer information, and the answer information is output by the voice integrated output unit;

The network module is connected to the processing unit, connected to a cloud database through the network module, searches for corresponding information based on the sentence segmentation information and sends it back to the processing unit;

These physiological sensor modules are installed on the local train body, and each physiological sensor module is connected to the processing unit. Each physiological sensor module is used to monitor the user's physiological status, and then The information is sent back to the processing unit for analysis and processing;

In this way, the user can interact with the vehicle-mounted voice speaker through voice, and the processing unit analyzes the voice instructions received by the receiving unit, and passes the network module or these physiological sensor modules according to the needs of the voice instructions. , or the vehicle status monitoring module obtains the response answer information, and the voice integrated output unit replies the answer or demand.
The control system using voice to control the local train according to claim 1, characterized in that the vehicle-mounted voice speaker includes a shell and a substrate, the aforementioned substrate is installed in the shell, the local train body is a bicycle, and the shell When combined on a faucet of the bicycle, the substrate provides the installation of the aforementioned receiving unit, sequencing unit, storage unit, processing unit and voice integrated output unit.
The control system for local train using voice control according to claim 1, wherein the housing is further provided with a control instrument panel, which is connected to the processing unit and used to display the answer information analyzed by the processing unit.
The control system using voice to control local trains according to claim 2, characterized in that the substrate can provide the network module for embedded assembly, and the network module is a wireless network card.
The control system for using voice to control local trains according to claim 1, characterized in that the physiological sensor module is installed with the handles and seat cushions of the local train body.