JP7697257B2 - Message processing method and message processing device - Google Patents

Description

The present invention relates to a message processing method and a message processing device.

Patent document 1 proposes a technology in which the destination vehicle receives information indicating the voice, image, and emotions of the driver of the vehicle that is the source of the inter-vehicle communication and displays it on a display device.

JP 2010-218568 A

However, if the voice, image, and information indicating the emotions of the driver of the sending vehicle are presented to the driver of the other party as is, there is a risk that the driver of the other party may be offended by this information.
The present invention aims to avoid offending occupants of one vehicle by verbal or non-verbal messages detected from occupants of another vehicle when these messages are presented to the occupants of another vehicle.

A message processing method according to one aspect of the present invention causes a computer to execute the following processes: receiving message information including a verbal or non-verbal message detected from a first occupant who is an occupant of a first vehicle; determining whether the received message information includes a predefined provocative expression; correcting the received message information to message information that does not include the provocative expression if it is determined that the received message information includes a provocative expression; and outputting the corrected message information as message information to be presented to a second occupant who is an occupant of a second vehicle.

According to the present invention, when a verbal or non-verbal message detected from an occupant of one vehicle is presented to an occupant of another vehicle, it is possible to avoid offending the occupant of the other vehicle with such a message.

1 is a diagram illustrating an overall configuration of an example of an inter-vehicle communication system according to an embodiment; FIG. 2 is a block diagram illustrating an example of a functional configuration of the server device of FIG. 1 . 4 is a flowchart of an example of processing by a driving performance determination unit. 13 is a flowchart of an example of a process performed by a provocation determination unit. 13 is a flowchart of a first example of a process by an information correction unit. 13 is a flowchart of a second example of a process by the information correction unit.

Below, an embodiment of the present invention will be described with reference to the drawings. Note that each drawing is a schematic view and may differ from the actual product. Furthermore, the embodiment of the present invention shown below is an example of an apparatus and method for embodying the technical concept of the present invention, and the technical concept of the present invention does not limit the structure, arrangement, etc. of the components to those described below. The technical concept of the present invention can be modified in various ways within the technical scope defined by the claims.

(composition)
1, the inter-vehicle communication system 100 according to the embodiment includes an in-vehicle device 10 mounted in a vehicle 1, an in-vehicle device 20 mounted in a vehicle 2, and a server device 3.
The in-vehicle device 10 includes a positioning device 11, an in-vehicle camera 12, a vehicle sensor 13, a user interface 14, a communication device 15, and a controller 16. In the drawings, the interface is represented as “I/F.” The configuration of the in-vehicle device 20 of the vehicle 2 may be the same as the configuration of the in-vehicle device 10.
The positioning device 11 measures the current position of the vehicle 1. The positioning device 11 may include, for example, a Global Navigation System (GNSS) receiver. The GNSS receiver is, for example, a Global Positioning System (GPS) receiver, and receives radio waves from a plurality of navigation satellites to measure the current position of the vehicle 1. The measurement result of the current position of the vehicle 1 is output to the controller 16 as vehicle state information.
The on-board camera 12 includes an exterior camera that captures images of the environment surrounding the vehicle 1, and an interior camera that captures images of passengers (e.g., the driver) of the vehicle 1. The on-board camera 12 outputs captured images generated by the interior camera to the controller 16. The on-board camera 12 also outputs captured images by the exterior camera to the controller 16 as vehicle state information.

The vehicle sensor 13 detects various information obtained from the vehicle 1. The vehicle sensor 13 may include, for example, a vehicle speed sensor that detects the speed of the vehicle 1, a wheel speed sensor that detects the rotational speed of each tire equipped on the vehicle 1, a three-axis acceleration sensor (G sensor) that detects the acceleration (including deceleration) in three axial directions of the vehicle 1, a steering angle sensor that detects the steering angle (including the turning angle), a gyro sensor that detects the angular velocity generated in the vehicle 1, and a yaw rate sensor that detects the yaw rate.
The vehicle sensor 13 outputs information on the vehicle speed, wheel speed, acceleration, steering angle, and angular velocity of the vehicle 1, as well as information on the operation status of the horn and headlights of the vehicle 1, to the controller 16 as vehicle status information.

The user interface 14 is a human-machine interface device that transmits and receives information between the controller 16 and the occupant. The user interface 14 includes a display device (e.g., a display screen of a navigation system) that can be viewed by the occupant of the vehicle 1, and a speaker and a buzzer for outputting warning sounds, notification sounds, and audio information.
The user interface 14 also includes an operator that accepts operational input from the occupant to the controller 16. The operator may be a mechanical interface device such as a button, a switch, a lever, a dial, a keyboard, or the like, or may be a button, a switch, a lever, a dial, a keyboard, or the like displayed on a touch panel. The user interface 14 also includes a voice input device (e.g., a microphone) that acquires voice (voice, words) uttered by the occupant.

The communication device 15 provides a communication function between the in-vehicle device 10 and an external device. The communication method by the communication device 15 may be, for example, wireless communication by a public mobile phone network, vehicle-to-vehicle communication, road-to-vehicle communication, or satellite communication. In this embodiment, the in-vehicle device 10 communicates with the server device 3 via the communication network NW using the communication function of the communication device 15.
The controller 16 acquires a voice signal uttered by an occupant of the vehicle 1 from the voice input device of the user interface 14. The controller 16 also acquires an image of the occupant of the vehicle 1 captured by the in-vehicle camera of the on-board camera 12.
The controller 16 transmits information including the voice signals and captured images of the occupants of the vehicle 1 to the server device 3 via the communication device 15. In addition, the controller 16 transmits vehicle state information of the vehicle 1 to the server device 3 via the communication device 15.

Here, the voice signal of the occupant of the vehicle 1 includes the words spoken by the occupant as a verbal message. The voice signal also includes the tone of the voice spoken by the occupant (e.g., tone, intonation) as a non-verbal message. Meanwhile, the captured image of the occupant of the vehicle 1 includes the facial expressions and gestures of the occupant as non-verbal messages. For this reason, information including the voice signal and captured image of the occupant of the vehicle 1 is referred to as "message information."
The controller 16 is a computer including a processor 17 and peripheral components such as a storage device 18. The processor 17 may be, for example, a CPU (Central Processing Unit) or an MPU (Micro-Processing Unit). The storage device 18 may include a semiconductor storage device, a magnetic storage device, an optical storage device, or the like. The functions of the controller 16 described in this specification are realized by the processor 17 executing a computer program stored in the storage device 18.

Similarly, the in-vehicle device 20 of the vehicle 2 transmits message information including voice signals and captured images of the occupants of the vehicle 2 and vehicle state information of the vehicle 2 to the server device 3 .
When the server device 3 receives message information and vehicle status information from the in-vehicle device 10, it converts the received message information into information to be presented to occupants (e.g., drivers) of other vehicles (e.g., vehicle 2) around vehicle 1 (hereinafter referred to as "presentation information") and transmits it to the other vehicles around vehicle 1.
The presentation information may include a voice signal generated based on words contained in a voice signal of an occupant of the vehicle 1 .
The presentation information may also include a control signal for an avatar of an occupant of the vehicle 1. The server device 3 generates a control signal for an avatar of the occupant of the vehicle 1 based on the tone of voice of the occupant of the vehicle 1, facial expressions and gestures shown in the captured image of the occupant of the vehicle 1.

Similarly, message information and vehicle status information are received from the in-vehicle device 20, converted into presentation information to be presented to occupants of other vehicles (e.g., vehicle 1) around vehicle 2, and transmitted to other vehicles around vehicle 2.
The server device 3 is a computer including a processor 30 and peripheral components such as a storage device 31 and a communication interface 32. The processor 30 may be, for example, a CPU or an MPU. The storage device 31 may include a semiconductor storage device, a magnetic storage device, an optical storage device, or the like. The server device 3 communicates with the in-vehicle devices 10, 20 via the communication network NW using the communication function of the communication interface 32. The functions of the server device 3 described in this specification are realized by the processor 30 executing a computer program stored in the storage device 31. The functions realized by the server device 3 will be described in detail later.

When the controller 16 of the in-vehicle device 10, 20 of the vehicle 1, 2 receives the presentation information from the server device 3, the controller 16 outputs the received presentation information from the user interface 14 to present it to the occupant.
For example, audio information included in the presentation information may be output from a speaker of the user interface 14. Also, for example, an avatar may be displayed on a display device of the user interface 14 based on an avatar control signal included in the presentation information.
For example, when message information transmitted from vehicle 1 is converted to generate presentation information and transmitted to vehicle 2, audio information may be output from the speaker of the user interface 14 of vehicle 2, and an avatar of the occupant of vehicle 1 may be displayed on the display device. When message information transmitted from vehicle 2 is converted to generate presentation information and transmitted to vehicle 1, audio information may be output from the speaker of the user interface 14 of vehicle 1, and an avatar of the occupant of vehicle 2 may be displayed on the display device.
This allows a verbal or non-verbal message detected from an occupant of one vehicle (e.g., vehicle 1) to be presented to an occupant of another vehicle (e.g., vehicle 2).

In this way, if a message detected from an occupant of one vehicle is presented to an occupant of another vehicle, the presented message may upset the occupant of the other vehicle. For example, if an occupant of vehicle 1 maliciously performs an inappropriate driving operation that violates driving etiquette (e.g., forcibly cutting in, sudden braking, sudden acceleration, sudden steering), the occupant may behave provocatively toward other vehicles in the vicinity. In such a case, if a message detected from an occupant of vehicle 1 (e.g., words, tone of voice, facial expression, gestures) is presented to the occupant of the other vehicle as is, the occupant of the other vehicle may be upset.
On the other hand, if the occupant of the vehicle 1 has no malicious intent and regrets his/her inappropriate driving operation, it is conceivable that he/she may express regret to the other vehicles around him/her. In this case, it is more preferable to generate presentation information according to the message detected from the occupant of the vehicle 1 and present it to the occupants of the other vehicles.

The server device 3 executes a process of determining whether or not a predefined provocative expression is included in message information received from a certain vehicle, a process of correcting the received message information to message information that does not include the provocative expression when it is determined that the received message information includes the provocative expression, and a process of outputting the corrected message information as presentation information to be presented to the occupants of the other vehicle. The predefined provocative expressions are stored in a storage device accessible from the server device 3.
This makes it possible to prevent messages detected from an occupant of one vehicle from offending the occupants of other vehicles when the messages are presented to the occupants of other vehicles.

The following describes the functional configuration of the server device 3. Fig. 2 is a block diagram of an example of the functional configuration of the server device 3. The server device 3 functions as an information receiving unit 40, a driving performance determination unit 41, a provocation determination unit 42, and an information correction unit 43.
The information receiving unit 40 receives message information and vehicle state information transmitted from the vehicles 1 and 2 while they are moving.
The driving operation determination unit 41 selects a vehicle that has performed an inappropriate driving operation that violates driving manners (for example, a forceful cut-in, sudden braking, sudden acceleration, or sudden steering) as a vehicle to be subject to provocation determination. The vehicle to be subject to provocation determination is an example of the "first vehicle" described in the claims.

FIG. 3 is a flowchart of an example of processing performed by the driving performance determination unit 41.
When the information receiving unit 40 receives vehicle state information transmitted from a traveling vehicle, the driving performance determining unit 41 acquires the vehicle state information from the information receiving unit 40 in step S1.
In step S2, the driving operation determination unit 41 determines whether any vehicle has performed an inappropriate driving operation that violates driving etiquette (e.g., tailgating, sudden braking, sudden acceleration, sudden steering, abnormal operation of the horn, or abnormal flashing operation) based on the acquired vehicle state information. If an inappropriate driving operation has been performed (step S2: Y), the process proceeds to step S3. If an inappropriate driving operation has not been performed (step S2: N), the process of the driving operation determination unit 41 ends.

For example, the driving operation judgment unit 41 may detect signals such as sudden braking, sudden acceleration, and sudden steering from vehicle status information, or detect sudden approaching or cutting in between vehicles from images captured by an exterior camera, and determine whether inappropriate driving operations (operations that violate driving etiquette) such as tailgating have been performed.
For example, the driving performance determination unit 41 may detect the operation status of the horn from the vehicle state information, detect an abnormality based on the frequency of operation, and detect abnormal operation of the horn as an inappropriate driving performance.

For example, the driving operation judgment unit 41 may detect the operation status of the headlights from the vehicle state information, and detect an abnormality when the flashing frequency is high and the duration is long, and detect abnormal passing operation as an inappropriate driving operation.
In step S3, the driving performance judgment unit 41 selects the vehicle in which the inappropriate driving has been performed as a provocation judgment target vehicle, and then ends the processing of the driving performance judgment unit 41.
In the following, an example in which the provocation determination target vehicle is vehicle 1 will be described.

Please refer to Fig. 2. The provocation determination unit 42 determines whether or not the message information detected from the occupant of the vehicle 1, which is the provocation determination target vehicle, includes a provocative expression.
For example, when the message information includes a captured image of the face of an occupant of the vehicle 1, the provocation determination unit 42 analyzes the facial image to estimate the facial expression of the occupant. For example, the provocation determination unit 42 may recognize the positions and shapes of the occupant's eyes, eyebrows, nose, cheeks, mouth, etc., and estimate the facial expression, such as joy, surprise, fear, sadness, anger, or disgust, based on the recognition results.
When the facial expression of the occupant of the vehicle 1 is a predefined and stored provocative expression (for example, an expression of anger or disgust), the provocation determination unit 42 determines that a provocative expression is included.

Furthermore, for example, the provocation determination unit 42 may estimate the intention of the gesture of the occupant when the message information includes a captured image showing the action of the occupant of the vehicle 1. When the gesture of the occupant of the vehicle 1 is a predefined and stored provocative gesture (for example, when the occupant shows irritation by hitting the steering wheel), the provocation determination unit 42 determines that a provocative expression is included.
For example, when the message information includes a voice signal uttered by an occupant of the vehicle 1, the provocation determination unit 42 may estimate whether the occupant's tone of voice is provocative or not. For example, when the amplitude of the waveform of the voice signal uttered by the occupant is greater than a predefined stored determination threshold (e.g., the amplitude of the occupant's normal voice in the vehicle 1), the provocation determination unit 42 may determine that the occupant's tone of voice is provocative. It is preferable that the determination threshold is individually calibrated according to the occupant of the vehicle 1 and the voice input device.
The provocation determination unit 42 determines that a provocative expression is included when the occupant's tone of voice is provocative.

Furthermore, for example, when the message information includes a voice signal uttered by an occupant of the vehicle 1, the provocation determination unit 42 may convert the voice signal into text information by performing voice recognition on the voice signal. When the converted text information includes a provocative word defined and stored in advance, such as a bad word, an imperative expression (e.g., "get out of the way"), or a critical expression (e.g., "you're slow"), the provocation determination unit 42 determines that the provocative expression is included.
FIG. 4 is a flowchart of an example of a process performed by the provocation determination unit 42. As shown in FIG.
When the information receiving unit 40 receives message information transmitted from a vehicle subject to provocation determination (vehicle 1 in this example), the provocation determination unit 42 acquires the message information from the information receiving unit 40 in step S10.

In step S11, the provocation determination unit 42 determines whether the facial expression of the occupant of the vehicle 1 included in the message information is provocative or not. If the facial expression is provocative (step S11: Y), the process proceeds to step S15. If the facial expression is not provocative (step S11: N), the process proceeds to step S12.
In step S12, the provocation determination unit 42 determines whether or not the gesture of the occupant of the vehicle 1 included in the message information is provocative. If it is a provocative gesture (step S12: Y), the process proceeds to step S15. If it is not a provocative gesture (step S12: N), the process proceeds to step S13.

In step S13, the provocation determination unit 42 determines whether the tone of the occupant of the vehicle 1 included in the message information is provocative or not. If the tone of the occupant of the vehicle 1 is provocative (step S13: Y), the process proceeds to step S15. If the tone of the occupant is not provocative (step S13: N), the process proceeds to step S14.
In step S14, the provocation determination unit 42 determines whether the words spoken by the occupant of the vehicle 1, which are included in the message information, are provocative or not. If the words are provocative (step S14: Y), the process proceeds to step S15. If the words are not provocative (step S14: N), the process proceeds to step S16.

In step S15, the provocation determination unit 42 determines that a provocative expression is included in the message information transmitted from the vehicle 1. After that, the processing of the provocation determination unit 42 ends.
In step S16, the provocation determination unit 42 determines that no provocative expression is included in the message information transmitted from the vehicle 1. After that, the processing of the provocation determination unit 42 ends.

Please refer to Fig. 2. When it is determined that the message information received from the provocation judgment target vehicle (vehicle 1 in this example) contains a provocative expression, the information correction unit 43 corrects the received message information to message information that does not contain the provocative expression, and generates presentation information to be presented to occupants of other vehicles around the provocation judgment target vehicle.
The information correction unit 43 transmits the presentation information generated from the corrected message information to an in-vehicle device of another vehicle (e.g., the in-vehicle device 20 of the vehicle 2) around the provocation determination target vehicle. The vehicle to which the presentation information is output is an example of the "second vehicle" described in the claims. Here, an example of presenting the presentation information to an occupant of the vehicle 2 will be described.

As described above, the presentation information may include a voice signal generated based on words included in a voice signal of an occupant of the vehicle 1. The presentation information may include a control signal for an avatar of the occupant of the vehicle 1.
The in-vehicle device 20 of the vehicle 2 may output an audio signal included in the received presentation information from a speaker of the user interface 14 of the in-vehicle device 20. Also, based on an avatar control signal included in the received presentation information, the in-vehicle device 20 may display an avatar of an occupant of the vehicle 1 on a display device of the user interface 14 of the in-vehicle device 20.

5 is a flowchart of a first example of processing by the information correction unit 43. In this example, presentation information including an audio signal and an avatar control signal is generated.
In step S20, the information correction unit 43 determines whether or not the provocation determination unit 42 has determined that the message information from the vehicle 1 includes a provocative expression. If a provocative expression is included (S20: Y), the process proceeds to step S21. If a provocative expression is not included (S20: N), the process proceeds to step S26.
In step S21, the information correction unit 43 converts the voice signal included in the message information from the vehicle 1 into text information by performing voice recognition on the voice signal. Note that, if the provocation determination unit 42 has already converted the voice signal into text information, the information correction unit 43 may obtain the text information from the provocation determination unit 42.

In step S22, the information correcting unit 43 corrects the text information including the provocative expression to text information not including the provocative expression.
For example, abusive language included in the text information may be deleted. Also, for example, when the text information includes imperative expressions or critical expressions, the text information may be replaced with suggestions corresponding to these expressions. For this reason, the information correction unit 43 may predefine and store text information of suggestions corresponding to various imperative expressions or critical expressions.
For example, the suggestion "move into the next lane" may be pre-associated with the imperative expression "move out of the way" and stored. Also, the suggestion "observe the minimum driving speed" may be pre-associated with the critical expression "slow" and stored. The information correction unit 43 may acquire the driving environment around the vehicle 1 (lane information, speed limit information, traffic signal information) from a map database based on the current position information included in the vehicle state information of the vehicle 1, and may adopt a suggestion that is suitable for the driving environment around the vehicle 1.
Furthermore, for example, when the text information is in plain language, the information correction unit 43 may convert it into honorific language (for example, polite language).

In step S23, the information correction unit 43 performs a voice synthesis process on the text information corrected in step S22 to generate a synthetic voice having the voice features of the avatar. By generating a synthetic voice from the text information in this manner, even if the message information from the vehicle 1 includes a voice signal with a provocative tone, the voice signal can be corrected to one that does not include a provocative tone (i.e., a provocative expression).
In step S24, the information correcting unit 43 generates a gentle expression (e.g., a smiling expression, a gentle expression, a happy expression, or a joyful expression) as the expression of the avatar of the occupant of the vehicle 1. For example, the information correcting unit 43 may predefine and store the positions and shapes of the avatar's eyes, eyebrows, nose, cheeks, mouth, and other parts as parameters that determine the avatar's expression, and set these parameters as control signals for controlling the expression of the avatar of the occupant of the vehicle 1.

In step S25, the information correction unit 43 changes the facial expression parameters (i.e., the positions and shapes of the eyes, eyebrows, nose, cheeks, mouth, etc.) generated in step S24 so that the avatar appears to be speaking the audio signal generated in step S23, and synchronizes the avatar's facial expression with the audio signal. The information correction unit 43 generates the parameters synchronized with the audio signal as a control signal for the avatar's facial expression. Processing then proceeds to step S28.

On the other hand, if it is determined in step S20 that the message information from vehicle 1 does not contain a provocative expression (step S20: N), in step S26, the information correction unit 43 converts the voice signal contained in the message information from vehicle 1 into a synthetic voice having the voice features of the avatar.
In step S27, the information correction unit 43 warps the facial expression of the occupant of the vehicle 1, which is included in the message information from the vehicle 1, with the face of the avatar. For example, the information correction unit 43 recognizes the positions and shapes of the eyes, eyebrows, nose, cheeks, mouth, etc. from the facial image of the occupant of the vehicle 1, and generates a control signal for the facial expression of the avatar so that the positions and shapes of the avatar's eyes, eyebrows, nose, cheeks, mouth, etc. are the recognized positions and shapes. Then, the process proceeds to step S28.
In step S28, the information correction unit 43 outputs presentation information including the synthetic voice generated in step S23 or S26 and the control signal for the avatar's facial expression generated in step S25 or S27 to the in-vehicle device 20 of the vehicle 2. Thereafter, the processing of the information correction unit 43 ends.

6 is a flowchart of a second example of processing by the information correcting unit 43. In this example, presentation information that does not include an audio signal and an avatar control signal is generated.
In step S30, the information correcting unit 43 converts the voice signal included in the message information from the vehicle 1 into text information by performing voice recognition on the voice signal. The information correcting unit 43 may obtain the converted text information from the provocation determining unit 42.
In step S31, the information correction unit 43 determines whether or not the provocation determination unit 42 has determined that the message information from the vehicle 1 includes a provocative expression. If a provocative expression is included (S31: Y), the process proceeds to step S32. If a provocative expression is not included (S31: N), the process proceeds to step S34.

In step S32, the information correcting unit 43 corrects the text information including the provocative expression to text information not including the provocative expression by the same process as in step S22 of FIG.
In step S33, the information correction unit 43 performs a voice synthesis process on the text information corrected in step S32 to generate synthetic voice having voice features of a polite tone (or a gentle tone). After that, the process proceeds to step S35.

On the other hand, if it is determined in step S31 that the message information from the vehicle 1 does not include a provocative expression (step S31: N), in step S34, the information correction unit 43 estimates the emotion of the occupant of the vehicle 1 (e.g., calm, relaxed, sorry) from the occupant and gesture of the occupant included in the message information. The information correction unit 43 performs a voice synthesis process on the text information converted in step S30 to generate a synthetic voice having voice features of the estimated emotion. The process then proceeds to step S35.
In step S35, the presentation information including the synthetic voice generated in step S33 or step S34 is output to the in-vehicle device 20 of the vehicle 2. Thereafter, the process of the information correction unit 43 ends.
In addition, if the message information from vehicle 1 contains provocative expressions, instead of steps S32 and S33, background music that calms the occupants of vehicle 2 may be obtained, and presentation information including the background music may be output to the in-vehicle device 20 of vehicle 2 in step S35.

In the above description, the server device 3 functions as the information receiving unit 40, the driving operation determination unit 41, the provocation determination unit 42, and the information correction unit 43, but the vehicle-to-vehicle communication system 100 of this embodiment is not limited to this. For example, the in-vehicle device 20 mounted on the vehicles 1 and 2 may function as the information receiving unit 40, the driving operation determination unit 41, the provocation determination unit 42, and the information correction unit 43.

(Effects of the embodiment)
(1) The computer performs the following processes: receiving message information including a verbal message or a non-verbal message detected from a first occupant who is an occupant of a first vehicle; determining whether the received message information contains a predefined provocative expression; if it is determined that the received message information contains a provocative expression, correcting the received message information to message information that does not contain the provocative expression; and outputting the corrected message information as presentation information to be presented to a second occupant who is an occupant of a second vehicle.
This makes it possible to avoid the occupants of the second vehicle being offended by verbal or non-verbal messages detected from the occupants of the first vehicle when these messages are presented to the occupants of the second vehicle.

(2) The message information may include audio information, image information, or text information. Since the message information is defined in this way, the audio information, image information, or text information can be used to determine whether the expression is provocative.
(3) As provocative expressions in verbal messages, candidates of words that may cause anger or disgust may be predefined and stored in a storage device accessible by a computer. As provocative expressions in non-verbal messages, facial expressions, tones, or gestures that may cause anger or disgust may be predefined and stored in a storage device.
Since provocative expressions are defined in this way, it is possible to determine whether or not the gestures, words, facial expressions, and tone of voice of the occupant of the first vehicle are provocative to the occupant of the second vehicle.

(4) The provocative expression of the language message may be abusive, an imperative, or a critical expression, thereby making it possible to determine the provocative expression based on the voice information.
(5) The computer may correct the message information to one that does not include provocative expressions by deleting abusive language contained in the language message. This makes it possible to convey information to the occupants of the second vehicle without negative emotions.
(6) The computer may amend the message information to include no provocative expression by replacing the imperative expression or critical expression included in the language message with a predefined suggestion corresponding to the imperative expression or critical expression, thereby conveying information to the occupant of the second vehicle in a more polite and calm manner.

(7) The computer may output a control signal for an avatar representing the corrected message information as presentation information to be presented to the second occupant, thereby outputting an avatar that conveys the corrected information to an occupant of the second vehicle.
(8) If the received message information includes a facial image of the first occupant, the computer may determine whether the facial expression of the first occupant included in the received message information contains a provocative expression by estimating whether the facial expression of the first occupant expresses disgust or anger based on the facial image.
This makes it possible to determine whether a provocative expression is present based on a facial image of one occupant.

(9) The computer may execute a process of outputting an avatar control signal representing a facial expression of the first occupant included in the received message information as presentation information to be presented to the second occupant. When the computer estimates that the facial expression of the first occupant represents disgust or anger, the computer may correct the received message information to message information that does not include provocative expressions by not reflecting the facial expression representing disgust or anger in the facial expression of the avatar. This makes it possible to convey information to the occupant of the second vehicle while removing negative emotions.
(10) The computer may receive vehicle status information on the status of a traveling vehicle, determine whether the vehicle has performed a driving operation that violates driving manners based on the vehicle status information, and select the vehicle as the first vehicle if the vehicle has performed a driving operation that violates driving manners. This makes it possible to determine which vehicle is likely to perform inappropriate driving and make provocative expressions.

100... Vehicle-to-vehicle communication system, 1, 2... Vehicle, 3... Server device, NW... Network, 10, 20... Vehicle-mounted device, 11... Positioning device, 12... Vehicle-mounted camera, 13... Vehicle sensor, 14... User interface, 15... Communication device, 16... Controller, 17... Processor, 18... Storage device, 30... Processor, 31... Storage device, 32... Communication interface, 40... Information receiving unit, 41... Driving operation determination unit, 42... Provocation determination unit, 43... Information correction unit

Claims (9)

receiving vehicle status information relating to a status of a traveling vehicle;
A process of determining whether the vehicle has performed a driving operation that violates driving manners based on the vehicle state information, and selecting the vehicle as a first vehicle when the vehicle has performed a driving operation that violates driving manners;
receiving message information including a detected verbal or non-verbal message from a first occupant of the first vehicle;
A process of determining whether the received message information contains a predefined provocative expression;
When it is determined that the provocative expression is included in the received message information, the received message information is corrected to message information that does not include the provocative expression;
outputting the corrected message information as presentation information to be presented to a second occupant of the second vehicle;
A message processing method comprising: causing a computer to execute the steps of: The message processing method according to claim 1, characterized in that the message information is audio information, image information or text information. The message processing method according to claim 1 or 2, characterized in that, as the provocative expression in the verbal message, candidates for words that may cause anger or disgust are predefined and stored in a storage device accessible to the computer, and as the provocative expression in the non-verbal message, facial expressions, tones, or gestures that may cause anger or disgust are predefined and stored in the storage device. The message processing method according to claim 3, characterized in that the provocative expression in the language message is an insult, an imperative expression, or a critical expression. The message processing method according to claim 4, characterized in that the message information is corrected to not include the provocative expression by deleting the abusive language contained in the language message. The message processing method according to claim 4, characterized in that the message information is corrected to not include the provocative expression by replacing the imperative expression or critical expression contained in the linguistic message with a predefined suggestion corresponding to the imperative expression or critical expression. The message processing method according to any one of claims 1 to 6, characterized in that a control signal for an avatar expressing the corrected message information is output as the presentation information. if the received message information includes a facial image of the first occupant, estimating whether the facial expression of the first occupant expresses disgust or anger based on the facial image, thereby determining whether the facial expression of the first occupant included in the received message information includes a provocative expression;
4. The method of claim 3, wherein the message is processed by the message processor. receiving vehicle status information relating to a status of a traveling vehicle;
A process of determining whether the vehicle has performed a driving operation that violates driving manners based on the vehicle state information, and selecting the vehicle as a first vehicle when the vehicle has performed a driving operation that violates driving manners;
receiving message information including a detected verbal or non-verbal message from a first occupant of the first vehicle;
A process of determining whether the received message information contains a predefined provocative expression;
When it is determined that the provocative expression is included in the received message information, the received message information is corrected to message information that does not include the provocative expression;
outputting the corrected message information as presentation information to be presented to a second occupant of the second vehicle;
A message processing device comprising a computer that executes the above.

Images