Voice communication server, vehicle-mounted communication terminal, automobile voice communication system and vehicle

Abstract

The invention discloses a voice communication server side, a vehicle-mounted communication terminal, an automobile voice communication system and a vehicle, the vehicle-mounted communication terminal can realize information interaction between the vehicle and the voice communication server side, and the voice communication server side can perform information interaction with the vehicle-mounted communication terminals installed on different vehicles. The information interaction process does not need to depend on the understanding relation between different automobiles, that is, information interaction can be established even if drivers of different automobiles are unfamiliar, so that information related to driving and the like is effectively transmitted, the traffic safety is guaranteed, and the traffic operation efficiency is improved; the voice communication server performs conversion processing on the first voice information to obtain the first conversion information, and sends the first conversion information to the second vehicle, so that the privacy security of the first vehicle can be effectively protected. The invention is widely applied to the technical field of automobiles.

Description

Technical Field

[0001] The present invention relates to the field of automobile technology, and in particular to a voice communication service end, a vehicle-mounted communication terminal, a vehicle voice communication system, and a vehicle. Background Art

[0002] When driving a car in a public place, different car drivers are usually required to exchange information so that the drivers can have more information, which is conducive to making appropriate driving behaviors and ensuring traffic safety.

[0003] In current automotive technology, information exchange between vehicles while driving is primarily conducted through signal lights. However, this method transmits limited information, typically only specific information such as driving intent. While wireless communication technology has gained widespread popularity, it is currently limited to vehicles within a fleet that are acquainted with each other. In most driving scenarios, the occupants of the vehicles needing to communicate do not know each other, resulting in a lack of secure and effective information exchange channels. Summary of the Invention

[0004] In view of the technical problems such as the large limitations of current information interaction technology between vehicles, the purpose of the present invention is to provide a voice communication server, an in-vehicle communication terminal, an automobile voice communication system and a vehicle.

[0005] In one aspect, an embodiment of the present invention includes a voice communication server, comprising: A speech analysis module; the speech analysis module is configured to receive a first speech message from a first vehicle, perform semantic recognition on the first speech message, obtain semantic information, and determine a second vehicle based on the semantic information; Voice sending module; the voice sending module is used to transform the first voice information, obtain first transformed information, and send the first transformed information to the second vehicle.

[0006] Furthermore, performing semantic recognition on the first voice information to obtain semantic information includes: Converting the first voice information into text information; Extracting positioning keywords, attribute keywords, and event keywords from the text information; the positioning keywords describe the location of the target vehicle pointed to by the first voice information, the attribute keywords describe the attributes of the target vehicle pointed to by the first voice information, and the event keywords describe the event represented by the first voice information; The positioning keyword, the attribute keyword and the event keyword are used as the semantic information.

[0007] Furthermore, determining the second vehicle according to the semantic information includes: Obtaining event attributes of the event keyword; When the event attribute is a directional event, searching for vehicles according to the positioning keyword, screening a target vehicle from the searched vehicles according to the attribute keyword, and using the target vehicle as the second vehicle; When the event attribute is a broadcast event, an event range parameter is determined according to the event keyword, and a vehicle is searched according to the event range parameter, and the searched vehicle is used as the second vehicle.

[0008] Furthermore, the performing transformation processing on the first voice information to obtain first transformation information includes: Filtering the text information corresponding to the first voice information to obtain filtering information; Get the voice timbre template; The filtering information is converted into speech according to the speech timbre template to obtain the first conversion information.

[0009] Furthermore, filtering the text information corresponding to the first voice information to obtain filtering information includes: obtaining second vehicle parameters of the second vehicle; detecting a second correlation between the text information and the second vehicle parameter; Filtering and removing the event keywords corresponding to the second relevance being lower than a relevance threshold; The event keywords that have not been filtered out are reordered to obtain the filtering information.

[0010] Furthermore, the obtaining of the speech timbre template includes: Acquire a standard timbre template as the speech timbre template; or When a plurality of first voice messages are received from a plurality of first vehicles, and the number of the first voice messages is greater than a quantity threshold, performing timbre information extraction and averaging processing on all the first voice messages to obtain the voice timbre template; The voice sending module is used to transform the first voice information to obtain first transformed information, and send the first transformed information to the second vehicle.

[0011] Furthermore, the voice sending module is also used for: Acquiring first vehicle parameters of the first vehicle and second vehicle parameters of the second vehicle; detecting a first correlation between the text information and the first vehicle parameter; detecting a second correlation between the text information and the second vehicle parameter; Performing a weighted summation on the first correlation and the second correlation to obtain a third correlation; When the third relevance is lower than a relevance threshold, the first voice information is intercepted.

[0012] Furthermore, the voice communication server also includes: Voice interaction module; the voice interaction module is used to detect the call confirmation information of the second vehicle. When the call confirmation information is detected, a voice conversation between the first vehicle and the second vehicle is established, and the voice information exchanged in the voice conversation is transformed and processed.

[0013] On the other hand, an embodiment of the present invention further includes a vehicle-mounted communication terminal, which is used to establish a communication connection with the voice communication server described in the embodiment. The vehicle-mounted communication terminal is used to be installed in a first vehicle or a second vehicle, and the vehicle-mounted communication terminal includes: Automobile parameter acquisition module; the automobile parameter acquisition module is used to dynamically acquire automobile parameters and dynamically upload the automobile parameters to the voice communication server; Voice acquisition module; the voice acquisition module is used to collect voice signals; Voice transmission module; the voice transmission module is used to process the voice signal, obtain the first voice information, and send the first voice information to the voice communication server; Voice playback module; the voice playback module is used to receive the first transformation information from the voice communication server and play the first transformation information.

[0014] On the other hand, an embodiment of the present invention further includes a car voice communication system, the car voice communication system comprising: The voice communication server in the embodiment; The vehicle-mounted communication terminal in the embodiment; Roadside sensing unit; the roadside sensing unit is used to be installed on the corresponding road section, detect the full amount of vehicle data on the road section, and send the full amount of vehicle data to the voice communication service end.

[0015] On the other hand, an embodiment of the present invention further includes a vehicle, which includes the vehicle-mounted communication terminal in the embodiment.

[0016] The beneficial effects of the present invention are: the vehicle-mounted communication terminal in the embodiment can realize information interaction between the vehicle and the voice communication server, and the voice communication server in the embodiment can exchange information with the vehicle-mounted communication terminals installed on different vehicles, thereby realizing information interaction between vehicles. Such an information interaction process does not need to rely on the recognition relationship between different cars, that is, strangers between drivers of different cars can also establish information interaction, thereby effectively transmitting information related to driving, etc., which is conducive to ensuring traffic safety and improving traffic operation efficiency; the voice communication server obtains first transformed information by transforming the first voice information, and sends the first transformed information to the second vehicle, which can effectively protect the privacy security of the first vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 Schematic diagram of the structure of the vehicle-mounted communication terminal in the embodiment; Figure 2 is a schematic diagram of an in-vehicle communication terminal installed on a vehicle in an embodiment; Figure 3 Schematic diagram of the communication connection between the vehicle-mounted communication terminal and the voice communication server in the embodiment; Figure 4 Schematic diagram of data flow between the vehicle-mounted communication terminal and the voice communication server in the embodiment; Figure 5 This is a structural diagram of the voice communication server in the embodiment; Figure 6 This is a schematic diagram of steps S1-S5 performed by the voice communication server in the embodiment; Figure 7 Schematic diagram of data flow among the first vehicle, the voice communication server, and the second vehicle in the embodiment; Figure 8 This is a schematic diagram of steps S6-S10 executed by the voice communication server in the embodiment; Figure 9 Schematic diagram of data flow between the first vehicle, the voice communication server, and the second vehicle when a voice interaction module is provided in an embodiment; Figure 10 This is a structural diagram of a voice communication service terminal equipped with a roadside perception unit. DETAILED DESCRIPTION

[0018] 1. Vehicle communication terminal In this embodiment, the structure of the vehicle-mounted communication terminal is as follows: Figure 1 As shown. Figure 1 ,The vehicle communication terminal includes a vehicle parameter acquisition module, a voice acquisition module, a voice ,transmission module and a voice playback module.

[0019] Reference Figure 2, including specific vehicles such as the first vehicle and the second vehicle, each vehicle can be equipped with an on-board communication terminal. Figure 3 , the on-board communication terminal in each car can establish a communication connection with the voice communication server through wireless communication protocols such as 5G and TCP / IP.

[0020] In this embodiment, an in-vehicle communication terminal installed in one of the vehicles is taken as an example for description.

[0021] In this embodiment, the vehicle parameter acquisition module, voice acquisition module, voice transmission module and voice playback module can be in the form of hardware, for example, on the basis of the original hardware equipment of each vehicle, a hardware module with corresponding functions is installed; the vehicle parameter acquisition module, voice acquisition module, voice transmission module and voice playback module can also be in the form of software, for example, the software is installed in the vehicle computer system of each vehicle to realize the functions of these modules.

[0022] In this embodiment, when the vehicle-mounted communication terminal is initially used, the driver of the vehicle or other personnel can operate and authorize the vehicle-mounted communication terminal to exchange configuration files with the voice communication server, complete the registration of the vehicle-mounted communication terminal at the voice communication server, and make the car equipped with the vehicle-mounted communication terminal a networked vehicle with communication functions.

[0023] For example, refer to Figure 4 The vehicle parameter collection module can collect vehicle parameters of the vehicle and upload them to the voice communication server. Specifically, the vehicle parameters collected by the vehicle parameter collection module include basic vehicle information such as static vehicle data and dynamic vehicle data. Static vehicle data includes data such as vehicle number, vehicle type, vehicle size, and body color, while dynamic vehicle data includes collection timestamp, positioning coordinates, speed, heading, etc. Because vehicle dynamic data generally changes dynamically, the vehicle parameter collection module dynamically collects and uploads vehicle parameters. For example, the vehicle parameter collection module can collect vehicle parameters at multiple collection times and immediately upload the collected vehicle parameters.

[0024] The voice acquisition module collects the vehicle's voice signals. The voice acquisition module can use a microphone to collect the voice of the driver or passengers of the vehicle, thereby obtaining a voice signal and sending the voice signal to the voice transmission module in the same vehicle communication terminal.

[0025] Reference Figure 4 ,The voice transmission module is used to perform noise reduction, filtering and encoding on the ,voice signal, to obtain voice information, and send the voice information to the ,voice communication server.

[0026] Reference Figure 4The voice playback module is used to receive transformed information from the voice communication server. The transformed information is the information obtained by the voice communication server after performing certain transformations on the voice information received from other vehicles. The voice playback module can use the speakers on the vehicle to play the received transformed information.

[0027] In this embodiment, the vehicle parameters, voice information, and transformation information processed by the in-vehicle communication terminals installed in different specific vehicles can be represented by different specific names. For example, for an in-vehicle communication terminal installed in a first specific vehicle, the vehicle parameters uploaded to the voice communication server by the in-vehicle communication terminal can be referred to as first vehicle parameters, the voice information uploaded can be referred to as first voice information, and the transformation information obtained by the voice communication server after transforming the first voice information can be referred to as first transformation information. For an in-vehicle communication terminal installed in a second specific vehicle, the vehicle parameters uploaded to the voice communication server by the in-vehicle communication terminal can be referred to as second vehicle parameters, the voice information uploaded can be referred to as second voice information, and the transformation information obtained by the voice communication server after transforming the second voice information can be referred to as second transformation information. If the voice communication server chooses to send the first transformation information from the first vehicle to the second vehicle, the voice playback module in the in-vehicle communication terminal installed in the second vehicle will receive and play the first transformation information.

[0028] 2. Voice communication server In this embodiment, the structure of the voice communication server is as follows: Figure 5 As shown. Figure 5 ,The voice communication server includes a voice analysis module and a voice sending module.

[0029] In this embodiment, it is not necessary to distinguish between a vehicle and its driver or other personnel. For example, a first vehicle proactively initiating information exchange with other vehicles is used for illustration. The first vehicle may initiate information exchange because it encounters an emergency (such as severe congestion or road damage) and wishes to inform the drivers of other vehicles, or to understand current traffic conditions, or to engage in social interaction.

[0030] In this embodiment, unless otherwise specified, it is assumed that all the vehicles mentioned have established a communication connection with the voice communication server, that is, they are all networked vehicles.

[0031] When the first vehicle wants to initiate an information interaction process, the driver of the first vehicle can speak in the car. The content of the speech can be "Does the third white SUV in the right lane know the reason for the traffic jam?" or "Please pay attention, the road ahead has collapsed", etc., and the first voice message is generated through the on-board communication terminal installed in the first vehicle.

[0032] In this embodiment, refer to Figure 6 , the voice communication server performs the following steps: S1. Receiving a first voice message from a first vehicle; S2 performs semantic recognition on the first voice information to obtain semantic information; S3. Determine the second vehicle based on semantic information; S4 transforms the first voice information to obtain a first transformation information; S5. Send the first transformation information to the second vehicle.

[0033] The principles of steps S1-S5 are as follows Figure 7 shown.

[0034] The voice analysis module in the voice communication server executes step S1 to receive a first voice message sent by a vehicle-mounted communication terminal installed in a first vehicle.

[0035] The speech analysis module then executes step S2 to perform semantic recognition on the first speech information to obtain semantic information.

[0036] Specifically, when the speech analysis module executes step S2, that is, the step of performing semantic recognition on the first speech information to obtain semantic information, the speech analysis module may execute the following steps: S201. Converting the first voice message into text message; S202 extracts positioning keywords, attribute keywords and event keywords from the text information; S203. Use positioning keywords, attribute keywords and event keywords as semantic information.

[0037] In step S201, the speech analysis module can run a deep learning model such as DeepSpeech, Kaldi, Espresso, etc. to convert the first speech information into text information with the same content.

[0038] In step S202, the speech analysis module extracts keywords from the text information obtained in step S201. The targets of keyword extraction include positioning keywords, attribute keywords, and event keywords.

[0039] Among them, the content of the positioning keyword describes the position of the target vehicle pointed to by the first voice message, that is, when the first vehicle sends the first voice message, which vehicles in which positions do the first vehicle hope to receive the first voice message; the content of the attribute keyword describes the attributes of the target vehicle pointed to by the first voice message, that is, when the first vehicle sends the first voice message, which vehicles do the first vehicle hope to receive the first voice message; the content of the event keyword describes the event represented by the first voice message, such as the event experienced by the first vehicle when sending the first voice message, or the event that the first vehicle hopes to know the details of.

[0040] In this embodiment, when the speech analysis module executes step S202, it can use the knowledge graph shown in Table 1 to extract location keywords and attribute keywords from the text information.

[0041] Table 1

[0042] For example, if the content of the first speech information is "Does the third white SUV in the front right lane know the reason for the traffic jam?", after executing step S201 to convert it into text information with the same content, when the speech analysis module executes step S202, it can obtain the content ((-1.5*LANE_WIDTH < y < -0.5* LANE_WIDTH) AND (0.5* L_car < x < R_MAX_RANGE) AND (color ='white') AND (sort(distance) = 3) AND (class = 'SUV')) from the knowledge graph, where (-1.5*LANE_WIDTH < y < -0.5* LANE_WIDTH) AND (0.5* L_car < x < R_MAX_RANGE) represents the location of the target vehicle to which the first vehicle hopes to send the first speech information, that is, the location keyword; (color ='white') AND (sort(distance) = 3) AND (class = 'SUV') represents the attributes of the target vehicle to which the first vehicle hopes to send the first speech information, that is, the attribute keyword; where LANE_WIDTH represents the lane width, L_car represents the vehicle length, distance represents the distance between the target vehicle and the first vehicle, color ='white' means the color attribute of the target vehicle is white, class = 'SUV' means the vehicle type of the target vehicle is SUV, and sort(distance) = 3 means the target vehicle is the 3rd vehicle in the sorting of distances from near to far; and step S202 will extract "Does it know the reason for the traffic jam?" as the event keyword, indicating the event that the first vehicle hopes to understand the details.

[0043] For example, if the content of the first speech information is "Please all vehicles pay attention, the road ahead has collapsed", after executing step S201 to convert it into text information with the same content, when the speech analysis module executes step S202, it can obtain location keywords and attribute keywords with the content of "all" or "unlimited" from the knowledge graph, and obtain the event keyword with the content of "the road ahead has collapsed", indicating the event described by the first vehicle.

[0044] In step S203, the positioning keyword, attribute keyword, and event keyword obtained by executing step S202 are used as the semantic information obtained by executing step S2.

[0045] Specifically, when the speech analysis module executes step S3, that is, the step of determining the second vehicle based on the semantic information, the speech analysis module may execute the following steps: S301. Get event attributes of event keywords; S302. When the event attribute is a directional event, search for the vehicle based on the positioning keyword, filter out the target vehicle from the searched vehicles based on the attribute keyword, and use the target vehicle as the second vehicle; S303. When the event attribute is a broadcast event, determine an event range parameter according to the event keyword, search for a vehicle according to the event range parameter, and use the searched vehicle as the second vehicle.

[0046] In step S301, the speech analysis module obtains the event attribute of the event keyword, which is specifically a directed event or a broadcast event. If the event keyword is an event related to one or more specific vehicles, such as content indicating a first vehicle requesting collaborative communication, then the event attribute of the event keyword is a directed event. If the event keyword is an event related to multiple vehicles or an unspecified vehicle, such as an event related to traffic safety or public safety, then the event attribute of the event keyword is a broadcast event.

[0047] If the event keyword obtained in step S2 is a directional event, the voice analysis module executes step S302 to search for a vehicle at the corresponding position based on the positioning keyword extracted from the text information of the first voice information. If multiple vehicles are found, a target vehicle with the same attributes as the second vehicle can be selected from the searched vehicles based on the attribute keyword.

[0048] If the event keyword obtained in step S2 is a broadcast event, the speech analysis module proceeds to step S303 to determine an event range parameter based on the event keyword. The event range parameter may represent the scope of the event described by the event keyword. Specifically, the speech analysis module may use length-type data as the event range parameter and establish a mapping table between event keywords and event range parameters. During step S303, the speech analysis module queries the mapping table based on the event keyword to determine the event range parameter. Next, the speech analysis module may determine a search range with the first vehicle as the center and a radius corresponding to the event range parameter. The searched vehicle is then searched for vehicles within this range, with the searched vehicle being the second vehicle.

[0049] By executing steps S301-S303, the voice communication server can accurately analyze the target vehicles to which the first vehicle intends to send the first voice message. For example, if the first voice message reads, "Does the third white SUV in the right lane ahead know the cause of the traffic jam?", then executing steps S301-S303 can determine that the third white SUV in the right lane ahead of the first vehicle is the target vehicle, making it the second vehicle. If the first voice message reads, "Attention, all vehicles, the road ahead has collapsed," then executing steps S301-S303 can determine that the vehicles within a certain radius of the first vehicle are the second vehicles.

[0050] The voice sending module in the voice communication server executes step S4 to transform the first voice information to obtain first transformed information.

[0051] Specifically, the voice sending module may perform transformations such as noise reduction on the first voice information, thereby obtaining first transformed information.

[0052] In this embodiment, when the voice sending module executes step S4, that is, the step of transforming the first voice information to obtain first transformed information, the following steps may be specifically performed: S401. Filter the text information corresponding to the first voice information to obtain filtered information; S402. Get the voice timbre template; S403. Convert the filtered information into speech according to the speech timbre template to obtain first conversion information.

[0053] In step S401, the voice transmission module may establish a preset corpus and filter the text information corresponding to the first voice message based on the corpus to obtain filtered information. Specifically, the corpus may store a blacklist of uncivilized language, and detect whether the text information corresponding to the first voice message contains keywords from the blacklist. If so, the corresponding portion is deleted to obtain filtered information.

[0054] In step S401, the voice sending module can communicate with the on-board communication terminal on the second vehicle, receive the vehicle parameters sent by the on-board communication terminal on the second vehicle, namely the second vehicle parameters, which represent the vehicle number, vehicle type, vehicle size, body color, positioning coordinates, speed, heading and other information of the second vehicle, and then detect the second correlation between the text message sent by the first vehicle and the second vehicle parameters.

[0055] Specifically, the voice sending module can detect the distance between the positioning keyword in the text information and the positioning coordinates in the second vehicle parameter. The smaller the distance, the greater the second correlation; it can detect the similarity between the attribute keyword in the text information and the vehicle type, vehicle size, body color, etc. in the second vehicle parameter. The greater the similarity, the greater the second correlation, thereby determining the size of the second correlation.

[0056] Then, the voice sending module can filter out the event keywords in the text information corresponding to the second relevance lower than the relevance threshold. For the event keywords that are not filtered out, the voice sending module can reorder the remaining event keywords according to the event attributes (for example, the order from broadcast events to directed events) to obtain filtered information.

[0057] By executing step S401, the text information corresponding to the first voice information can be filtered, thereby filtering out those event keywords with low relevance to the second vehicle. The remaining event keywords with high relevance to the second vehicle constitute the filtering information, which can enable the information finally sent to the second vehicle to convey effective information and reduce the possibility of the second vehicle being disturbed by irrelevant information; and the event keywords can be re-sorted to form the filtering information, so that the information finally sent to the second vehicle can be played out by the on-board communication terminal of the second vehicle in a certain order (for example, order of importance), thereby improving the efficiency of information transmission.

[0058] In steps S402-S403, the voice transmission module may use the voice timbre template to convert the filtered information into voice, thereby obtaining first transformed information. The first transformed information is voice. When the first transformed information is played back, the voice timbre, including volume, pitch, intonation, pauses, and accent, is identical to the voice timbre template. This voice timbre is generally different from the voice timbre of the driver of the first vehicle.

[0059] By executing steps S402-S403, the polishing and synthesis processing of the first voice message is completed. The voice transmission module executes step S5 to transmit the first transformed information to the second vehicle. When the vehicle-mounted communication terminal of the second vehicle plays the first transformed information, the driver of the second vehicle will obtain the information in the first voice message, thereby achieving information transmission from the first vehicle to the second vehicle. The driver of the second vehicle hears the voice timbre of the voice timbre template, which is generally different from the voice timbre of the driver of the first vehicle, thereby protecting the privacy of the driver of the first vehicle.

[0060] The speech timbre template obtained in step S402 may be a standard timbre template, such as a standard timbre template provided by commonly used Wensheng speech software on the market.

[0061] When executing step S402, the voice sending module may also extract and average the timbre information of all the first voice information to obtain a voice timbre template if it receives multiple first voice information from multiple first vehicles and the number of the first voice information is greater than a quantity threshold (for example, 30).

[0062] For example, the first vehicle in this embodiment can be any vehicle that actively initiates information interaction. Therefore, after running for a period of time, the voice communication service end will obtain a certain number of first voice messages. After obtaining a large number of first voice messages, timbre information such as volume, pitch, pauses and accents can be extracted from these first voice messages, and averaged to obtain their average volume, average pitch, average pause duration, etc. as the volume, pitch, pauses, etc. in the voice timbre template. The voice timbre template obtained in this way has timbre information from the natural person driver of each first vehicle, but is not exactly the same as any single first voice message. Therefore, the first transformation information generated according to such a voice timbre template has a more friendly and natural playback effect in the second vehicle, which is conducive to improving the driver of the second vehicle's acceptance of the first transformation information, improving information transmission efficiency, and also protecting the privacy and security of the drivers of each first vehicle.

[0063] In this embodiment, the second vehicle's onboard communication terminal can generate a private key and a public key and send the public key to the voice transmission module. When the voice transmission module executes step S5, it uses the public key of the second vehicle's onboard communication terminal to encrypt the first transformed information and sends the encrypted information to the second vehicle's onboard communication terminal. The second vehicle's onboard communication terminal can then use its own private key to decrypt the information and obtain the first transformed information, thereby ensuring information security. Since the second vehicle can be any vehicle, the voice communication server can also collect the public keys generated by the onboard communication terminals of each vehicle and send the public keys to all vehicles. Before uploading the first voice information, the onboard terminal of the first vehicle can use each public key to encrypt the first voice information separately. The voice communication server then directly sends the encrypted first voice information as the first transformed information to the second vehicle. The onboard communication terminal of the second vehicle can then use its own private key to decrypt the information and obtain the content of the first voice information. This encryption process can prevent the first voice information from being received by vehicles that the first vehicle does not want to receive, thereby causing information leakage.

[0064] In this embodiment, refer to Figure 8 , the voice sending module can also perform the following steps: S6. Obtaining the first vehicle parameters of the first vehicle and the second vehicle parameters of the second vehicle; S7. Detecting a first correlation between the text information and the first vehicle parameter; S8. Detecting a second correlation between the text information and the second vehicle parameter; S9. Perform a weighted summation of the first correlation and the second correlation to obtain a third correlation; S10. When the third correlation is lower than the correlation threshold, the first voice information is intercepted.

[0065] In step S6, the voice sending module obtains the first vehicle parameters of the first vehicle that currently initiates the information interaction, and obtains the second vehicle parameters of all second vehicles determined by executing step S3. Therefore, step S6 may obtain multiple second vehicle parameters.

[0066] In step S7, the voice transmission module can detect the correlation between the text information and the first vehicle parameter according to the principle of step S401 to obtain a first correlation. Similarly, in step S8, the voice transmission module can detect the correlation between the text information and the second vehicle parameter according to the principle of step S401 to obtain a second correlation. Multiple second correlations may be obtained by executing step S8.

[0067] In step S9, the voice transmission module performs a weighted summation on the first correlation and the second correlation to obtain a third correlation. Specifically, the voice transmission module may assign the same weight (e.g., 1) to the first correlation and each second correlation, thereby directly adding the first correlation to each second correlation to obtain the third correlation.

[0068] In step S9, the voice transmission module may assign different weights to the first correlation and each second correlation. For example, the voice transmission module may assign a weight of 1 to the first correlation, and for any second vehicle, the closer the distance to the first vehicle, the greater the weight of the second correlation of the second vehicle parameter of the second vehicle. Furthermore, the weight of each second correlation may be assigned to be greater than the weight of the first correlation. Based on this weight distribution, a weighted sum is calculated as the third correlation.

[0069] The third correlation obtained by executing step S9 indicates the degree of correlation between the first voice message emitted by the first vehicle and the first vehicle and each second vehicle participating in the same traffic process. If the third correlation is higher than the correlation threshold, then the first voice message emitted by the first vehicle has a high degree of correlation with the first vehicle and each second vehicle as a whole (specifically, the first voice message has a high degree of correlation with the first vehicle or at least one second vehicle), indicating that the first voice message emitted by the first vehicle has high purpose and effectiveness. The voice transmission module may skip step S10 and instead execute steps S4-S5, thereby normally transmitting the first transformed information to the second vehicles. Conversely, if the third correlation is lower than the correlation threshold, then the first voice message emitted by the first vehicle has a low degree of correlation with the first vehicle and each second vehicle as a whole (specifically, the first voice message has a low degree of correlation with the first vehicle and each second vehicle), indicating that the first voice message emitted by the first vehicle has low purpose and effectiveness. The voice transmission module may execute step S10 instead of steps S4-S5, thereby intercepting the first voice message. The first transformed information corresponding to the first voice message will not be transmitted to any second vehicle, thereby reducing the possibility of low-effectiveness first voice messages being transmitted between vehicles and improving information transmission efficiency.

[0070] In step S9, by setting the weight of each second correlation degree to be greater than the weight of the first correlation degree, the weight of the second vehicle that may belong to the information receiver can be increased. By setting the weight of the second correlation degree of the second vehicle that is closer to the first vehicle to be larger, the weight of the second vehicle that is more likely to belong to the information receiver can be increased. In this way, whether to intercept the first voice information can be effectively controlled according to the situation of the second vehicle, thereby ensuring the information security of each second vehicle.

[0071] In this embodiment, refer to Figure 9 , the voice communication server also includes a voice interaction module. Figure 9 The voice interaction module can detect call confirmation information from the second vehicle after the voice transmission module has sent the first transformed information to the second vehicle. The call confirmation information is sent by the driver of the second vehicle using the vehicle-mounted communication terminal, indicating that the driver is willing to establish a real-time call with the first vehicle. Upon detecting the call confirmation information returned by the second vehicle, the voice interaction module establishes a voice session between the first and second vehicles, enabling a continuous real-time call between the first and second vehicles.

[0072] After establishing a voice conversation between the first vehicle and the second vehicle, the voice interaction module can also perform polishing and synthesis processing on the voice information sent by the first vehicle to the second vehicle during the voice conversation, as well as on the voice information sent by the second vehicle to the first vehicle during the voice conversation, so as to ensure the privacy and security of the drivers of the first vehicle and the second vehicle.

[0073] 3. Automotive Voice Communication System In this embodiment, referring to Figure 10 , the voice communication server, each vehicle-mounted communication terminal installed on each vehicle, and the roadside perception unit constitute an automotive voice communication system. The roadside perception unit is used to be installed on the corresponding road section to detect all vehicle data on the road section where it is located, and send all vehicle data to the voice communication server, so as to provide data references such as traffic flow for the voice communication server.

[0074] An operation process of the automotive voice communication system is as follows: When the driver of the first vehicle discovers a traffic accident ahead, through the vehicle-mounted communication terminal of the first vehicle, a first voice message with the content "Vehicles behind, a traffic accident has been discovered ahead" is sent; After the voice communication server receives the first voice message, it extracts that the event attribute is a broadcast event, and the target vehicle is the vehicle behind the first vehicle, that is, in the body coordinate system (-R_MAX_RANGE < x coordinate value < -0.5 * L_car); The voice sending module filters out the corresponding vehicles among all connected vehicles according to the target vehicle range (-R_MAX_RANGE < x coordinate value < -0.5 * L_car), so as to determine the second vehicle, and then converts the text information with the content "A traffic accident has been discovered ahead" into voice, obtains the first transformation information, and sends it to the second vehicle; After receiving the first transformation information, the second vehicle can choose to return voice to establish a channel. For example, if it feeds back a call confirmation message to the voice interaction module within a certain period of time (such as 10s), the voice interaction module will establish a voice conversation between the first vehicle and the second vehicle. If it does not feed back the call confirmation message after this period of time, the voice interaction module will not establish a voice conversation channel.

[0075] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, that is, they may be located in one place, or they may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0076] It should be noted that, unless otherwise specified, when a feature is referred to as being "fixed" or "connected" to another feature, it may be directly fixed or connected to the other feature, or it may be indirectly fixed or connected to the other feature. In addition, the descriptions of up, down, left, right, etc. used in this disclosure are only relative to the relative positional relationship of the components of the present disclosure in the accompanying drawings. The singular forms of "a" and "the" used in this disclosure are also intended to include the plural forms, unless the context clearly indicates otherwise. In addition, unless otherwise defined, all technical and scientific terms used in this embodiment have the same meaning as those generally understood by those skilled in the art. The terms used in the specification of this embodiment are only for describing specific embodiments and are not intended to limit the present invention. The term "and / or" used in this embodiment includes any combination of one or more related listed items.

[0077] It should be understood that, although the terms first, second, third, etc. may be used to describe various elements in the present disclosure, these elements should not be limited to these terms. These terms are only used to distinguish elements of the same type from each other. For example, without departing from the scope of the present disclosure, the first element may also be referred to as the second element, and similarly, the second element may also be referred to as the first element. The use of any and all examples or exemplary language ("for example", "such as", etc.) provided in the present embodiment is only intended to better illustrate embodiments of the present invention, and unless otherwise required, will not impose limitations on the scope of the present invention.

[0078] It should be appreciated that embodiments of the present invention can be implemented or practiced by computer hardware, a combination of hardware and software, or by computer instructions stored in a non-transitory computer-readable memory. The methods can be implemented in a computer program using standard programming techniques - including a non-transitory computer-readable storage medium configured with a computer program, wherein the storage medium so configured causes the computer to operate in a specific and predefined manner - according to the methods and figures described in the specific embodiments. Each program can be implemented in a high-level procedural or object-oriented programming language to communicate with the computer system. However, if desired, the program can be implemented in assembly or machine language. In any case, the language can be a compiled or interpreted language. In addition, the program can be run on a programmed application-specific integrated circuit for this purpose.

[0079] Furthermore, the operations of the processes described in this embodiment may be performed in any suitable order, unless otherwise indicated by this embodiment or clearly contradicted by the context in another manner. The processes described in this embodiment (or variations and / or combinations thereof) may be executed under the control of one or more computer systems configured with executable instructions and may be implemented as code (e.g., executable instructions, one or more computer programs, or one or more applications) that is executed collectively on one or more processors, by hardware, or a combination thereof. A computer program includes multiple instructions that can be executed by one or more processors.

[0080] Furthermore, the method can be implemented in any type of computing platform that is operably connected to a suitable computer, including but not limited to a personal computer, a minicomputer, a mainframe, a workstation, a network or distributed computing environment, a separate or integrated computer platform, or in communication with a charged particle tool or other imaging device, etc. Various aspects of the present invention can be implemented as machine-readable code stored on a non-transitory storage medium or device, whether removable or integrated into a computing platform, such as a hard disk, an optical read and / or write storage medium, RAM, ROM, etc., so that it can be read by a programmable computer, and when the storage medium or device is read by the computer, it can be used to configure and operate the computer to perform the process described herein. In addition, the machine-readable code, or portions thereof, can be transmitted over a wired or wireless network. When such media includes instructions or programs that implement the above steps in conjunction with a microprocessor or other data processor, the invention of this embodiment includes these and other different types of non-transitory computer-readable storage media. When programmed according to the methods and techniques of the present invention, the present invention also includes the computer itself.

[0081] The computer program can be applied to input data to perform the functions of the present embodiment, thereby converting the input data to generate output data that is stored in a non-volatile memory. The output information can also be applied to one or more output devices such as a display. In a preferred embodiment of the present invention, the converted data represents a physical and tangible object, including a specific visual depiction of the physical and tangible object produced on the display.

[0082] The above are merely preferred embodiments of the present invention. The present invention is not limited to the aforementioned embodiments. As long as the technical effects of the present invention are achieved by the same means, any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention. Within the scope of protection of the present invention, various modifications and variations of the technical solutions and / or implementation methods may be made.

Claims

1. A voice communication server, characterized in that: The voice communication service end includes: A speech analysis module; the speech analysis module is configured to receive a first speech message from a first vehicle, perform semantic recognition on the first speech message, obtain semantic information, and determine a second vehicle based on the semantic information; Voice sending module; the voice sending module is used to transform the first voice information, obtain first transformed information, and send the first transformed information to the second vehicle.

2. The voice communication server according to claim 1, wherein: The performing semantic recognition on the first voice information to obtain semantic information includes: Converting the first voice information into text information; Extracting positioning keywords, attribute keywords, and event keywords from the text information; the positioning keywords describe the location of the target vehicle pointed to by the first voice information, the attribute keywords describe the attributes of the target vehicle pointed to by the first voice information, and the event keywords describe the event represented by the first voice information; The positioning keyword, the attribute keyword and the event keyword are used as the semantic information.

3. The voice communication server according to claim 2, wherein: The determining the second vehicle according to the semantic information includes: Obtaining event attributes of the event keyword; When the event attribute is a directional event, searching for vehicles according to the positioning keyword, screening a target vehicle from the searched vehicles according to the attribute keyword, and using the target vehicle as the second vehicle; When the event attribute is a broadcast event, an event range parameter is determined according to the event keyword, and a vehicle is searched according to the event range parameter, and the searched vehicle is used as the second vehicle.

4. The voice communication server according to claim 2, wherein: The performing transformation processing on the first voice information to obtain first transformed information includes: Filtering the text information corresponding to the first voice information to obtain filtering information; Get the voice timbre template; The filtering information is converted into speech according to the speech timbre template to obtain the first conversion information.

5. The voice communication server according to claim 4, characterized in that: The filtering the text information corresponding to the first voice information to obtain filtering information includes: obtaining second vehicle parameters of the second vehicle; detecting a second correlation between the text information and the second vehicle parameter; Filtering and removing the event keywords corresponding to the second relevance being lower than a relevance threshold; The event keywords that have not been filtered out are reordered to obtain the filtering information.

6. The voice communication server according to claim 4, characterized in that: The step of obtaining a voice timbre template includes: Acquire a standard timbre template as the speech timbre template; or When a plurality of first voice messages are received from a plurality of first vehicles, and the number of the first voice messages is greater than a quantity threshold, performing timbre information extraction and averaging processing on all the first voice messages to obtain the voice timbre template; The voice sending module is used to transform the first voice information to obtain first transformed information, and send the first transformed information to the second vehicle.

7. The voice communication server according to claim 7, characterized in that: The voice sending module is also used for: Acquiring first vehicle parameters of the first vehicle and second vehicle parameters of the second vehicle; detecting a first correlation between the text information and the first vehicle parameter; detecting a second correlation between the text information and the second vehicle parameter; Performing a weighted summation on the first correlation and the second correlation to obtain a third correlation; When the third relevance is lower than a relevance threshold, the first voice information is intercepted.

8. The voice communication server according to any one of claims 1 to 7, characterized in that: The voice communication service end further includes: Voice interaction module; the voice interaction module is used to detect the call confirmation information of the second vehicle. When the call confirmation information is detected, a voice conversation between the first vehicle and the second vehicle is established, and the voice information exchanged in the voice conversation is transformed and processed.

9. A vehicle-mounted communication terminal, configured to establish a communication connection with the voice communication server according to any one of claims 1 to 8, wherein the vehicle-mounted communication terminal is configured to be installed in a first vehicle or a second vehicle, wherein: The vehicle-mounted communication terminal includes: Automobile parameter acquisition module; the automobile parameter acquisition module is used to dynamically acquire automobile parameters and dynamically upload the automobile parameters to the voice communication server; Voice acquisition module; the voice acquisition module is used to collect voice signals; Voice transmission module; the voice transmission module is used to process the voice signal, obtain voice information, and send the voice information to the voice communication server; Voice playback module; the voice playback module is used to receive transformation information from the voice communication server and play the transformation information.

10. A car voice communication system, characterized in that: The automobile voice communication system comprises: The voice communication server according to any one of claims 1 to 8; The vehicle-mounted communication terminal according to claim 9; Roadside sensing unit; the roadside sensing unit is used to be installed on the corresponding road section, detect the full amount of vehicle data on the road section, and send the full amount of vehicle data to the voice communication service end.

11. A vehicle, characterized in that: The vehicle includes the in-vehicle communication terminal according to claim 9.

Images