Cross-application service scheduling execution method and system in vehicle-mounted environment

Abstract

The invention provides a cross-application service scheduling execution method and system in a vehicle-mounted environment, and relates to the technical field of intelligent vehicle-mounted systems, and the method comprises the steps: obtaining the service related data of a known vehicle-mounted system, the environment perception data of the vehicle-mounted environment, and the user voice information; analyzing the user voice information to obtain target demand information, intention associated information and voice feature information; on the basis of the environment perception data, scene adaptation parameters are formed, and on the basis of the target demand information, multiple second instruction transmission signals are generated; and detecting each piece of target demand information based on the service related data, the intention associated information, the voice feature information and the scene adaptation parameters to obtain a detection result, performing scheduling execution of a plurality of cross-application services in the vehicle-mounted environment in combination with a second instruction transmission signal, generating a service scheduling execution result, and sending the service scheduling execution result to the server. Dynamic coordination and ordered scheduling of cross-application services are realized, and the response accuracy and execution safety of the vehicle-mounted system in a complex driving scene are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent vehicle-mounted system, and particularly relates to a service scheduling execution method and system across applications in a vehicle-mounted environment. BACKGROUND

[0002] Under the background of rapid development of intelligent vehicles, vehicle-mounted systems increasingly integrate navigation, entertainment, communication, driving assistance and other application services. Users often trigger multiple cross-application operations through voice instructions during driving, such as navigating while playing music or making a phone call. Such scenarios pose technical requirements of high real-time performance, low interference and environmental adaptability for the system, requiring the vehicle-mounted platform to comprehensively perceive the current in-vehicle and external state and user intent, efficiently coordinate the execution order and resource allocation of multiple services under the premise of ensuring driving safety.

[0003] Existing solutions usually adopt a priority scheduling mechanism based on preset rules, combine voice recognition results and vehicle basic state information, assign fixed priorities to different service requests, and determine the execution order according to the priorities. However, this solution lacks joint analysis capability for dynamic driving environment and deep semantic of user voice, making it difficult to accurately judge the potential conflict and resource competition relationship between services. When the vehicle is in complex road conditions or the user issues ambiguous and multi-intent voice instructions, the fixed priority strategy is prone to cause delay in response of key services or excessive occupation of system resources by non-key services, thereby reducing overall interaction efficiency and driving safety. SUMMARY

[0004] The present application aims to provide a service scheduling execution method and system across applications in a vehicle-mounted environment to solve the problem of service conflict and unbalanced resource allocation caused by the inability of the fixed priority strategy to adapt to dynamic environment and multi-intent voice in the prior art.

[0005] To solve the above technical problems, in a first aspect, the present application provides a service scheduling execution method across applications in a vehicle-mounted environment, comprising: obtaining known service-related data of a vehicle-mounted system, and environment perception data and user voice information of a vehicle-mounted environment; analyzing the user voice information through voice recognition technology to obtain target demand information, intent association information and voice feature information of multiple cross-application services; forming scenario adaptation parameters based on the environment perception data, and generating multiple first instruction transmission signals corresponding to each cross-application service based on the target demand information; optimizing the first instruction transmission signals using an amplifier to obtain multiple second instruction transmission signals; Based on the service-related data, intention association information, voice feature information, and scene adaptation parameters, the conflict coordination engine performs resource occupation detection and execution order detection on each target demand information to obtain a detection result. According to the detection result, a target service execution sequence adapted to the vehicle driving state is generated, and in combination with the second instruction transmission signal, scheduling and execution of multiple cross-application services in a vehicle environment are performed to generate a service scheduling and execution result.

[0006] Optionally, based on the environment perception data, scene adaptation parameters are formed, and based on the target demand information, multiple first instruction transmission signals corresponding to each cross-application service are generated, including: The environment perception data is associated and analyzed to generate information association features, and according to the information association features, different driving scene types are divided; According to the information association features and the signal transmission requirements and trigger conditions of cross-application service execution, adaptation rules related to cross-application service execution for different driving scene types are set; According to the parameter identification specification of the vehicle system, each type of adaptation rule is converted into a scene adaptation parameter recognizable by the vehicle system; The target demand information of each cross-application service is decomposed into execution actions, operation objects, and operation parameters, and the execution actions, operation objects, and operation parameters corresponding to each target demand information are respectively converted into first instruction transmission signals conforming to the signal transmission specification of the vehicle system.

[0007] Optionally, the first instruction transmission signals are optimized using an amplifier to obtain multiple second instruction transmission signals, including: According to the signal type of the first instruction transmission signal and the scene adaptation parameters, the transmission characteristic parameters of each first instruction transmission signal are determined; According to the intensity reference value and the interference threshold value of signal transmission under different driving scene types in the scene adaptation parameters, in combination with each transmission characteristic parameter, the initial gain parameter and the initial filtering parameter of the amplifier are adjusted to generate an adaptation parameter set corresponding to each first instruction transmission signal; According to each adaptation parameter set, the corresponding first instruction transmission signal is frequency band calibrated to obtain multiple preprocessed signals; The corresponding preprocessed signals are optimized by the amplifier according to each adaptation parameter set to obtain multiple optimized signals; Based on the intensity reference value and the interference threshold value, the optimized signals are subjected to signal intensity verification and anti-interference capability verification, and the optimized signals that pass the verification are used as second instruction transmission signals.

[0008] Optionally, according to the intensity reference value and the interference threshold value of signal transmission under different driving scene types in the scene adaptation parameter, combined with each transmission characteristic parameter, the initial gain parameter and the initial filtering parameter of the amplifier are adjusted to generate an adaptation parameter set corresponding to each first instruction transmission signal, including: According to the signal transmission requirements of each driving scene type, the parameter deviation of each transmission characteristic parameter from the intensity reference value and the interference threshold value is analyzed to generate a deviation data set; According to the deviation data set, the initial gain parameter of the amplifier is adjusted by grade, and the initial filtering parameter of the amplifier is adjusted by frequency band adaptation according to the numerical range of each interference threshold value to generate a parameter adjustment record; From the parameter adjustment record, a candidate parameter set matching the transmission characteristic parameter and the deviation data set of each first instruction transmission signal is selected; The candidate parameter set corresponding to each first instruction transmission signal is verified to identify a parameter set without parameter conflict, adapting to the signal transmission requirements of the corresponding driving scene type and the corresponding transmission characteristic parameter as the adaptation parameter set.

[0009] Optionally, the detection result includes a resource conflict detection result and a sequence detection result; Based on the service related data, the intention association information, the voice feature information and the scene adaptation parameter, the conflict coordination engine is used to perform resource occupation detection and execution sequence detection on each target demand information to obtain a detection result, including: According to the resource configuration information of the vehicle-mounted system and each target demand information, the hardware resource type and the software resource occupation required for executing each target demand information are determined to form a resource demand list; According to the service related data, the occupation state of each hardware resource type in the vehicle-mounted system and the remaining available amount of each software resource are analyzed, and the historical time consumption data of each resource executing cross-application services are combined to generate a resource state data set; From the scene adaptation parameter, resource scheduling constraint conditions corresponding to different driving scene types are extracted; According to the intention association information, the execution association relationship between each target demand information is analyzed, and based on the voice feature information, the expression feature corresponding to each target demand information is determined; Based on the resource demand list and the resource state data set, the conflict coordination engine is used to perform resource occupation analysis on each target demand information to generate a resource conflict detection result; Based on the resource conflict detection result, the resource scheduling constraint condition, the execution association relationship and the expression feature, the conflict coordination engine is used to perform conflict resolution processing on all target demand information to generate a sequence detection result.

[0010] Optionally, based on the resource conflict detection result, resource scheduling constraint condition, execution association relationship and expression feature, the conflict resolution engine is used to perform conflict resolution processing on all target demand information to generate a sequence detection result, including: Based on the resource conflict detection result, resource scheduling constraint condition, execution association relationship and expression feature, the conflict resolution engine determines the conflict resolution priority of each target demand information; According to the resource conflict detection result, the conflict information and corresponding associated demand information existing resource occupation conflict are identified, and the resource conflict type and resource influence range of the conflict information and associated demand information are confirmed; According to the execution association relationship and the conflict resolution priority of each target demand information, the conflict information and associated demand information are resolved to obtain non-conflict information; All non-conflict information is checked, and the non-conflict information that passes the check is integrated according to the execution association relationship to form a sequence detection result.

[0011] Optionally, according to the detection result, a target service execution sequence adapted to the vehicle driving state is generated, and combined with the second instruction transmission signal, the scheduling and execution of multiple cross-application services in the vehicle environment are performed to generate a service scheduling and execution result, including: According to the detection result and the service execution constraint corresponding to different driving scene types in the scene adaptation parameter, an initial service execution sequence is generated; The second instruction transmission signal corresponding to each target demand information is bound to the corresponding service execution node in the initial service execution sequence to form a target service execution sequence; According to the target service execution sequence, an execution trigger instruction is sent to the corresponding functional module of the vehicle system to trigger the start of the first cross-application service corresponding to the first service execution node. After confirming that the first cross-application service completes the preset operation according to the target service execution sequence and the second instruction transmission signal, the cross-application service corresponding to the next service execution node is triggered to start based on the target service execution sequence, until all cross-application services corresponding to the service execution node complete the preset operation. The execution feedback information of each cross-application service is integrated to form a service scheduling and execution result.

[0012] In a second aspect, the application provides a cross-application service scheduling and execution system in a vehicle environment, including: An acquisition module is configured to acquire known service-related data of a vehicle system, as well as environment perception data and user voice information of a vehicle environment; An analysis module is configured to analyze the user voice information through voice recognition technology to obtain target demand information, intent association information and voice feature information of multiple cross-application services; The generating module is configured to form a scene adaptation parameter based on the environment perception data, and generate a plurality of first instruction transmission signals corresponding to respective cross-application services based on the target demand information. The optimizing module is configured to optimize the first instruction transmission signals by using an amplifier to obtain a plurality of second instruction transmission signals. The detecting module is configured to perform resource occupation detection and execution sequence detection on each target demand information by using a conflict coordination engine based on the service-related data, the intention association information, the voice feature information, and the scene adaptation parameter to obtain a detection result. The executing module is configured to generate a target service execution sequence adapted to a vehicle driving state according to the detection result, combine the second instruction transmission signals, and perform scheduling and execution of a plurality of cross-application services in a vehicle environment to generate a service scheduling and execution result.

[0013] In a third aspect, the present application provides a computing device including a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement the steps of the method for scheduling and executing cross-application services in a vehicle environment according to the first aspect.

[0014] In a fourth aspect, the present application provides a computer storage medium, which stores a computer program; when the computer program is executed by a computer, the steps of the method for scheduling and executing cross-application services in a vehicle environment according to the first aspect are implemented.

[0015] The method for scheduling and executing cross-application services in a vehicle environment provided by the present application has the following beneficial effects: by obtaining service performance data of a vehicle system and multi-dimensional environment and voice information, accurate analysis of user cross-application service demand can be realized, and scene adaptation parameters are generated based on a dynamic driving state to guide the generation of instruction signals; then, the initial instruction signals are optimized by using an amplifier to improve the transmission reliability of the signals in a complex vehicle environment; then, by combining service history performance, voice semantic features, and scene context, intelligent evaluation of resource occupation and execution timing of each service request is performed by using a conflict coordination mechanism, and finally, a service execution sequence highly matched with the current driving state is formed and scheduling and execution are completed, so that the coordination ability and response adaptability of the system to concurrent requests with multiple intentions are enhanced under the premise of ensuring driving safety.

[0016] Further, the application dynamically configures the gain and filtering parameters of the amplifier according to the type of the instruction signal and the current driving scene, performs frequency band calibration and optimization processing on the initial instruction signal, and introduces a signal strength and anti-interference checking mechanism based on scene characteristics, to ensure that the optimized instruction signal has good transmission stability and environmental robustness; overcomes the service mis-triggering or response failure problem caused by signal distortion or interference under complex driving conditions with the traditional fixed strategy, so that the cross-application scheduling instruction can be more reliably transmitted and executed, thereby supporting the system to maintain stable and orderly service coordination capability in high dynamic and multi-task scenarios. BRIEF DESCRIPTION OF DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or prior art description will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0018] Figure 1 A flowchart of a service scheduling execution method across applications in a vehicle environment provided by an embodiment of the present application; Figure 2 A specific implementation schematic diagram of a service scheduling execution method across applications in a vehicle environment provided by an embodiment of the present application; Figure 3 A structure schematic diagram of a service scheduling execution system across applications in a vehicle environment provided by an embodiment of the present application. DETAILED DESCRIPTION

[0019] In view of the problem that the existing scheduling mechanism is difficult to adapt to complex driving states and multi-intention voice instruction concurrent scenes due to the dependence on fixed priority, the present application provides a service scheduling execution method across applications in a vehicle environment. The core idea of the method is to build a collaborative scheduling framework that integrates vehicle dynamic environment perception, service historical performance data and user voice deep semantic understanding. The method generates scene adaptation parameters by real-time extraction of multiple source information such as vehicle speed, vibration, environment and voice characteristics, and dynamically generates and optimizes the instruction signal of cross-application service according to the parameters. In combination with the joint detection mechanism of resource occupation and execution order, a service execution sequence matched with the current driving state is formed, so as to realize the orderly, coordinated and reliable scheduling of multiple service requests while ensuring driving safety.

[0020] For those skilled in the art to better understand the present application, the present application will be further described in detail below in combination with the drawings and specific embodiments. Obviously, the described embodiments are only part of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0021] The core of the present application is to provide a service scheduling execution method across applications in a vehicle-mounted environment. The flowchart of a specific embodiment of the method is shown in Figure 1 The method comprises the following steps: Step 101: Obtain known service-related data of vehicle-mounted systems, and environment perception data and user voice information of the vehicle-mounted environment.

[0022] In this step, the service-related data refers to various service running data generated by the vehicle-mounted system in the historical execution of cross-application services, including service response data and service delay data.

[0023] The environment perception data refers to the vehicle-mounted environment-related data collected by various sensors on the vehicle, including driving speed information, vehicle body vibration information, and environmental information.

[0024] The user voice information refers to the voice command data issued by the user through the vehicle-mounted voice interaction device.

[0025] In the embodiment of the present application, first, all known service-related data of vehicle-mounted systems stored in the historical data storage module of the vehicle-mounted system is retrieved, and the vehicle speed sensor, vehicle body vibration sensor, and environmental sensor are started to collect the driving speed information, vehicle body vibration information, and environmental information of the vehicle in real time, respectively. The three types of data are integrated to obtain the environment perception data of the vehicle-mounted environment, and the vehicle-mounted voice collection device is started to collect the voice command data issued by the user in real time to obtain the user voice information.

[0026] Step 102: Analyze the user voice information by voice recognition technology to obtain target demand information, intent association information, and voice feature information of multiple cross-application services.

[0027] In this step, the target demand information of cross-application services refers to the service demand content of multiple function modules based on the user voice information analysis and expected to be executed by the vehicle-mounted system.

[0028] The intent association information refers to the logical execution association relationship between the target demand information of each cross-application service based on the user voice information analysis.

[0029] The voice feature information refers to the acoustic attribute feature data of the voice itself extracted based on the user voice information.

[0030] In the embodiment of the present application, first, the user voice information stored in the summary is preprocessed, and the noise reduction processing and the frame processing of the voice signal are sequentially completed to remove the environmental noise in the voice information, and the preprocessed voice signal is obtained; then the preprocessed voice signal is divided into a plurality of voice frames, and the voice recognition technology is used to analyze the semantics of the voice frames to extract the target demand information of a plurality of cross-application services expected to be executed by the user; then the logical association relationship between the target demand information of each cross-application service is analyzed to obtain the intention association information corresponding to each target demand information; secondly, the acoustic property features such as the tone, the speech rate, and the voiceprint of the voice are extracted from the voice frames, and finally the voice feature information is obtained.

[0031] Step 103: Based on the environmental perception data, scene adaptation parameters are formed, and based on the target demand information, a plurality of first instruction transmission signals corresponding to each cross-application service are generated.

[0032] In this step, the scene adaptation parameter refers to a parameter that can be recognized by the vehicle-mounted system and is obtained through association analysis and rule conversion based on the environmental perception data, which is used to adapt the execution and signal transmission of the cross-application service in different driving scene types.

[0033] The cross-application service refers to a service that is cooperatively executed by multiple functional modules in the vehicle-mounted system, which is corresponding to the target demand information analyzed from the user voice information and is completed by relying on the cooperation of multiple modules.

[0034] The first instruction transmission signal refers to a signal that is converted from the execution action, the operation object, and the operation parameter after the target demand information is disassembled, which conforms to the signal transmission specification of the vehicle-mounted system and is used to trigger the vehicle-mounted system to execute the corresponding cross-application service.

[0035] In the embodiment of the present application, step 103 specifically includes the following steps: Step 301: The environmental perception data is subjected to association analysis to generate information association features, and different driving scene types are divided according to the information association features.

[0036] In this step, the information association feature refers to a feature obtained by associating and analyzing various data in the environmental perception data, and the number of the feature can be multiple, so that a feature set can be formed, which can reflect the association relationship between the driving speed information, the vehicle body vibration information, and the environmental information.

[0037] The driving scene type refers to the vehicle driving scene category divided based on the difference in the feature value of the information association feature.

[0038] In the embodiment of the present application, firstly, all data features of the driving speed information, the vehicle body vibration information and the environmental information in the environmental perception data are extracted, and the three types of data features are analyzed to mine the internal correlation rules between different data, and finally the information correlation features are generated by integrating the correlation rules; secondly, the driving scene types are divided according to the preset division basis and the feature value difference of the information correlation features.

[0039] Step 302: According to the information correlation features, the signal transmission requirements and the trigger conditions of the cross-application service execution, the adaptation rules related to the cross-application service execution for different driving scene types are set.

[0040] In this step, the signal transmission requirements refer to the requirements of signal strength, anti-interference ability, transmission rate and the like required by the instruction transmission in the cross-application service execution process, and the specific form of the requirements is not limited in the embodiment.

[0041] The trigger condition refers to the prerequisite condition for starting the cross-application service execution and the corresponding instruction signal transmission, and the specific content of the condition is not limited in the embodiment, and can be set according to the actual situation.

[0042] The adaptation rule refers to the rule set for different driving scene types, which is formulated based on the information correlation features, and is used to coordinate the execution requirements and the signal transmission strategy of the cross-application service to ensure that the two are matched with the current scene.

[0043] In the embodiment of the present application, firstly, the information correlation features corresponding to each driving scene type are analyzed to clarify the vehicle environmental characteristics in different scenes, and then the signal transmission adaptation rules and the service execution trigger adaptation rules corresponding to each driving scene type are set in combination with the signal transmission requirements and the service trigger conditions in the cross-application service execution, so that all the adaptation rules are matched with the information correlation features of the corresponding driving scene type, and the reasonable execution of the cross-application service in the corresponding scene is ensured.

[0044] Step 303: According to the parameter recognition specification of the vehicle-mounted system, the adaptation rules are converted into the scene adaptation parameters recognizable by the vehicle-mounted system.

[0045] In this step, the parameter recognition specification of the vehicle-mounted system refers to the unified specification requirements of the parameter format, coding mode, data type and the like that can be directly recognized and analyzed by the vehicle-mounted system, and the specific content of the specification is not limited in the embodiment.

[0046] In the embodiment of the present application, first, the parameter identification specification of the vehicle-mounted system is called, and then each type of adaptation rule set for different driving scene types is processed by format conversion and coding one by one according to the specification, the rule content in the form of words is converted into a parameter form recognizable by the vehicle-mounted system, and finally all the converted parameters are integrated to generate scene adaptation parameters.

[0047] Step 304: Each target demand information of the cross-application service is disassembled into an execution action, an operation object, and an operation parameter, and the execution action, the operation object, and the operation parameter corresponding to each target demand information are respectively converted into a first instruction transmission signal conforming to the signal transmission specification of the vehicle-mounted system.

[0048] In this step, the execution action refers to the specific operation action that needs to be completed when the cross-application service is executed.

[0049] The operation object refers to the specific object of the vehicle-mounted system function module, service content, etc. to which the execution action is directed.

[0050] The operation parameter refers to various parameter indicators required in the execution process of the execution action, which is used to limit the range, degree, and manner of operation.

[0051] In the embodiment of the present application, first, according to the service execution logic of the vehicle-mounted system, each target demand information corresponding to the cross-application service is disassembled into a specific execution action, a corresponding operation object, and an operation parameter required for the action; then the signal transmission specification of the vehicle-mounted system is called, and the disassembled execution action, operation object, and operation parameter are respectively signal encoded and format converted according to the specification, so that each part of the content conforms to the signal transmission requirements of the vehicle-mounted system, and finally the converted signals are integrated to generate the first instruction transmission signal corresponding to each cross-application service.

[0052] The embodiment of the present application realizes the deep adaptation of the driving scene and the execution of the cross-application service and signal transmission, provides a core adaptation basis and a basic instruction signal for the optimization of the first instruction transmission signal and the resource scheduling of the cross-application service, and guarantees the scene targeting and system compatibility of the vehicle-mounted cross-application service scheduling.

[0053] Step 104: The first instruction transmission signal is optimized by using an amplifier to obtain a plurality of second instruction transmission signals.

[0054] In this step, the amplifier refers to a device in the vehicle-mounted system for adjusting the strength of the instruction transmission signal and filtering interference signals to optimize the signal quality.

[0055] The second instruction transmission signal refers to a high-quality signal obtained after the first instruction transmission signal is subjected to frequency band calibration, amplifier optimization processing, and double verification.

[0056] In the embodiment of the present application, asFigure 2 As shown, step 104 specifically includes the following steps: Step 401: Determine the transmission characteristic parameter of each first instruction transmission signal according to the signal type of the first instruction transmission signal and the scene adaptation parameter.

[0057] In this step, the signal type refers to the signal category corresponding to the first instruction transmission signal, such as control category signal, data category signal, etc., and the transmission requirements of different types of signals are different.

[0058] The transmission characteristic parameter refers to a parameter reflecting the transmission performance of the first instruction transmission signal, which includes signal bandwidth, transmission rate, signal amplitude, etc.

[0059] In the embodiments of the present application, first, each first instruction transmission signal is classified to determine its corresponding signal type; then the signal transmission requirements under the corresponding driving scene type in the scene adaptation parameter are retrieved, and the transmission characteristic parameter corresponding to each first instruction transmission signal is determined in combination with the inherent attributes of the signal type, so as to ensure that the parameter matches the signal type and the scene requirement.

[0060] Step 402: Adjust the initial gain parameter and the initial filter parameter of the amplifier according to the intensity reference value and the interference threshold value of signal transmission under different driving scene types in the scene adaptation parameter, in combination with each transmission characteristic parameter, to generate an adaptation parameter set corresponding to each first instruction transmission signal.

[0061] In this step, the intensity reference value refers to the standard intensity value that the signal transmission under the corresponding driving scene type needs to reach, which is preset in the scene adaptation parameter.

[0062] The interference threshold value refers to the maximum allowable interference signal intensity value under the corresponding driving scene type, which is preset in the scene adaptation parameter, and exceeding this value will affect signal transmission.

[0063] The initial gain parameter and the initial filter parameter respectively refer to the amplification coefficient of the signal intensity before the amplifier is adjusted and the frequency band parameter used for filtering the interference signal.

[0064] The adaptation parameter set refers to the set of amplifier gain parameters and filter parameters that match the first instruction transmission signal and the scene requirement after adjustment.

[0065] In the embodiments of the present application, step 402 specifically includes the following steps: Step 411: Analyze the parameter deviation of each transmission characteristic parameter from the intensity reference value and the interference threshold value according to the signal transmission requirements of each driving scene type, to generate a deviation data set.

[0066] In this step, the parameter deviation refers to the difference between the actual value of each transmission characteristic parameter and the intensity reference value, the difference between the signal anti-interference capability corresponding to the transmission characteristic parameter and the interference threshold, reflecting the gap between the transmission characteristic and the scene standard requirement.

[0067] The deviation dataset refers to the dataset formed by integrating the parameter deviations corresponding to all transmission characteristic parameters.

[0068] In the embodiments of the present application, first, the intensity reference value and the interference threshold of the corresponding scene are retrieved according to the signal transmission requirements corresponding to each driving scene type; then the difference between the actual value of each transmission characteristic parameter and the intensity reference value is calculated, and the difference between the signal anti-interference capability corresponding to the transmission characteristic parameter and the interference threshold is calculated, and all the calculated parameter deviations are grouped and sorted according to the first instruction transmission signal to generate the deviation dataset.

[0069] Step 412: According to the deviation dataset, the initial gain parameter of the amplifier is adjusted by grade, and at the same time, according to the numerical range of each interference threshold, the initial filter parameter of the amplifier is adjusted by frequency band to generate a parameter adjustment record.

[0070] In this step, the parameter adjustment record refers to the document recording the initial parameters of the amplifier, the adjustment grade, the adjustment amplitude, the adjusted parameters and the corresponding first instruction transmission signal.

[0071] In the embodiments of the present application, first, a plurality of adjustment grades are divided according to the deviation size of the deviation dataset, each grade corresponds to a fixed gain parameter adjustment amplitude, and then the initial gain parameter of the amplifier is adjusted according to the corresponding grade; at the same time, the interference signal frequency band to be filtered is determined in combination with the numerical range of the interference threshold of each driving scene, the initial filter parameter of the amplifier is adjusted to adapt to the frequency band, and the complete information of each parameter adjustment is recorded one by one to generate the parameter adjustment record.

[0072] Step 413: From the parameter adjustment record, a candidate parameter set matching the transmission characteristic parameters of each first instruction transmission signal and the deviation dataset is selected.

[0073] In this step, the candidate parameter set refers to the amplifier parameter combination selected from the parameter adjustment record and matched with the transmission characteristic parameters of the first instruction transmission signal and the deviation dataset.

[0074] In the embodiments of the present application, the parameter adjustment record is traversed, and the parameter combination whose adjusted parameter is adapted to the transmission characteristic parameter of each first instruction transmission signal and whose adjustment amplitude matches the deviation dataset is selected, and the selected parameter combination is taken as the candidate parameter set corresponding to the first instruction transmission signal.

[0075] Step 414: verifying the candidate parameter set corresponding to each first instruction transmission signal to identify a parameter set without parameter conflict, adaptive to the signal transmission requirement of the corresponding driving scene type and the transmission characteristic parameter as the adaptive parameter set.

[0076] In this step, the parameter conflict refers to the case that the gain parameter and the filtering parameter in the candidate parameter set have mutual influence and cannot simultaneously meet the signal optimization requirement.

[0077] In the embodiment of the present application, first, each candidate parameter set is verified. Specifically, whether the gain parameter and the filtering parameter in the set have parameter conflict is checked, and the parameter combination with conflict is removed. Then, whether the remaining parameter combination is adaptive to the signal transmission requirement of the corresponding driving scene type and matches the transmission characteristic parameter of the first instruction transmission signal is verified. Finally, the parameter combination that passes the verification is determined as the adaptive parameter set.

[0078] Step 403: calibrating the frequency band of the corresponding first instruction transmission signal according to each adaptive parameter set to obtain a plurality of preprocessed signals.

[0079] In this step, the preprocessed signal refers to the signal obtained after the first instruction transmission signal is calibrated in frequency band.

[0080] In the embodiment of the present application, first, for each first instruction transmission signal, the corresponding adaptive parameter set is called to extract the filtering parameter requirement in these adaptive parameter sets. Then, the transmission frequency band of the first instruction transmission signal is adjusted by the signal processing module to correct the frequency band offset, so that the signal frequency band accurately matches the filtering parameter requirement to obtain the preprocessed signal.

[0081] Step 404: optimizing the corresponding preprocessed signal according to each adaptive parameter set by an amplifier to obtain a plurality of optimized signals.

[0082] In this step, the optimized signal refers to the signal in which the intensity meets the standard and the interference signal is effectively filtered after the preprocessed signal is optimized by the amplifier.

[0083] In the embodiment of the present application, each preprocessed signal is input into the amplifier, the amplifier calls the corresponding adaptive parameter set, and the gain parameter in the adaptive parameter set is used to amplify the intensity of the preprocessed signal to the range meeting the intensity reference value, while the filtering parameter is used to filter out the interference signal exceeding the interference threshold, and finally the optimized signal is output.

[0084] Step 405: verifying the signal intensity and the anti-interference ability of each optimized signal based on the intensity reference value and the interference threshold, and taking the optimized signal that passes the verification as the second instruction transmission signal.

[0085] In the embodiments of the present application, the optimized signals are first checked one by one, specifically: first, it is detected whether the intensity of the optimized signal meets the intensity reference value requirement, and then the interference signal environment corresponding to the scene is simulated to test whether the anti-interference capability of the optimized signal meets the interference threshold requirement; the optimized signal that passes both checks is determined as the second instruction transmission signal, and the one that does not pass is returned to re-optimization processing.

[0086] The embodiments of the present application realize the scene-based accurate optimization of the first instruction transmission signal, improve the signal strength and anti-interference capability, provide high-quality instruction support for subsequent stable scheduling and execution of cross-application services, and avoid service execution delay or failure caused by signal problems.

[0087] Step 105: Based on the service-related data, intent association information, voice feature information, and scene adaptation parameters, the conflict coordination engine performs resource occupation detection and execution order detection on each target demand information to obtain a detection result.

[0088] In this step, the detection result refers to the result set obtained after resource occupation detection and execution order detection, which includes resource conflict detection results and sequence detection results.

[0089] In the embodiments of the present application, step 105 specifically includes the following steps: Step 501: According to the resource configuration information of the vehicle-mounted system and each target demand information, determine the hardware resource type and software resource occupation required for executing each target demand information to form a resource demand list.

[0090] In this step, the resource configuration information refers to basic information such as the type and quantity of hardware resources and the capacity and function distribution of software resources in the vehicle-mounted system.

[0091] The hardware resource type refers to the category of vehicle-mounted hardware devices required to execute the target demand information, such as navigation modules, audio modules, etc.

[0092] The software resource occupation refers to the software resource capacity and computing power required to execute the target demand information.

[0093] The resource demand list refers to a list formed by integrating the hardware resource type and software resource occupation corresponding to each target demand information.

[0094] In the embodiments of the present application, first, the resource configuration information of the vehicle-mounted system is retrieved to determine the available hardware resource type and software resource capacity; then, for each target demand information, the corresponding cross-application service content is combined to analyze and determine the hardware resource type required to execute the demand, and the software resource occupation required to consume is calculated, and the above two types of information are sorted according to the target demand information to form a resource demand list.

[0095] Step 502: According to the service-related data, the occupancy state of each hardware resource type in the vehicle-mounted system, the remaining available amount of each software resource, and the historical time consumption data of each resource executing cross-application services are analyzed to generate a resource state data set.

[0096] In this step, the hardware resource occupancy state refers to whether each hardware resource type is currently occupied, the degree of occupation, and the occupation duration.

[0097] The remaining available amount of software resources refers to the capacity and computing power that can be allocated after deducting the occupied part.

[0098] The historical time consumption data refers to the time data required by each type of resource to execute cross-application services in the past, which is used to assist in judging the rationality of resource occupation.

[0099] The resource state data set refers to the data set formed by integrating the hardware resource occupancy state, the remaining available amount of software resources, and the historical time consumption data.

[0100] In the embodiments of the present application, the historical occupation records of each hardware resource and the consumption records of software resources are extracted from the service-related data to analyze the occupancy state of each hardware resource type and calculate the remaining available amount of each software resource. At the same time, the historical time consumption data of each resource executing cross-application services is extracted, and the three types of data are grouped and sorted according to the resource type to generate a resource state data set.

[0101] Step 503: Extract the resource scheduling constraint conditions corresponding to different driving scene types from the scene adaptation parameters.

[0102] In this step, the resource scheduling constraint condition refers to the pre-set resource allocation restriction rules for different driving scene types in the scene adaptation parameters. This constraint condition includes resource allocation priority, maximum occupation duration of single resource, upper limit of resource parallel allocation, etc.

[0103] In the embodiments of the present application, the scene adaptation parameters are classified and disassembled according to different driving scene types to determine the adaptation rules related to resource scheduling under each scene type. Then these rules are used as initial resource scheduling restriction rules to compare the rule contents of different scenes, eliminate duplicates to avoid constraint conflicts, and supplement the rule application range, execution boundary, etc. to ensure that the rules are clear and can be implemented on the ground to obtain processed rules. Finally, the processed rules are sorted and integrated according to the driving scene types to form a resource scheduling constraint condition set.

[0104] Step 504: According to the intention association information, the execution association relationship between each target demand information is analyzed, and based on the voice feature information, the expression features corresponding to each target demand information are determined.

[0105] In this step, the execution relationship between the target demand information refers to the inherent logical execution relationship between the target demand information, which includes three types of execution, namely, sequential execution, parallel execution and mutual exclusion execution.

[0106] The expression feature refers to a feature reflecting the user's emphasis on the target demand information, which is determined based on the voice feature information, and includes tone, speed, etc.

[0107] In the embodiment of the application, first, the intention association information is parsed, the execution relationship between the target demand information is analyzed, and it is determined whether it belongs to sequential execution, parallel execution or mutual exclusion execution, and then the attributes such as tone and speed in the voice feature information are extracted, and these attributes are converted into expression features reflecting the emphasis on the demand in combination with the user's voice interaction habits, and the expression features are bound to the corresponding target demand information.

[0108] Step 505: Based on the resource demand list and the resource state data set, the resource occupation of each target demand information is analyzed by the conflict coordination engine to generate a resource conflict detection result. In this step, the resource occupation analysis refers to comparing the resource demand of each target demand information with the current resource state to determine whether there is a situation where multiple demands compete for the same resource.

[0109] The resource conflict detection result refers to the result data recording the target demand information, the conflict resource type, the conflict degree and the conflict range.

[0110] In the embodiment of the application, the resource demand list and the resource state data set are input into the conflict coordination engine, and the engine compares the resource demand of each target demand information with the current state of the corresponding resource one by one to determine whether there is a situation where multiple target demand information competes for the same hardware resource or software resource, and mark the demand information involved in the conflict, the conflict resource type and the conflict range, and finally integrate these marked information to form the resource conflict detection result.

[0111] Step 506: Based on the resource conflict detection result, the resource scheduling constraint condition, the execution relationship and the expression feature, the conflict resolution processing of all target demand information is performed by the conflict coordination engine to generate a sequence detection result.

[0112] In this step, the sequence detection result refers to the reasonable execution order and resource allocation scheme of each target demand information after conflict resolution.

[0113] In the embodiment of the application, step 506 specifically includes the following steps: Step 511: Based on the resource conflict detection result, the resource scheduling constraint condition, the execution association relationship and the expression feature, the conflict resolution priority of each target demand information is determined by the conflict coordination engine.

[0114] In this step, the conflict resolution priority refers to the priority of the target demand information for processing resource conflict determined by the conflict coordination engine. The priority is determined based on the resource scheduling constraint condition, the expression feature and the execution association relationship. The demand with high priority is preferentially allocated with resources.

[0115] In the embodiment of the present application, the conflict resolution priority of each target demand information is determined by the conflict coordination engine. The specific process includes: first, determining the basic priority according to the resource scheduling constraint condition; then, adjusting the priority according to the expression feature, for example, the priority of the demand with high user importance is improved; finally, correcting the priority in combination with the execution association relationship, for example, the demands in mutual exclusion are sorted according to the association logic, and the conflict resolution priority of each target demand information is finally determined.

[0116] Step 512: According to the resource conflict detection result, the conflict information and the corresponding associated demand information existing resource occupation conflict are identified, and the resource conflict type and the resource influence range of the conflict information and the associated demand information are confirmed.

[0117] In this step, the conflict information refers to the target demand information marked in the resource conflict detection result and existing resource occupation conflict.

[0118] The associated demand information refers to other target demand information competing for the same resource as the conflict information.

[0119] The resource conflict type refers to the specific form of conflict, which includes hardware resource conflict, software resource conflict and mixed hardware and software conflict.

[0120] The resource influence range refers to the number of resources involved in the conflict, the number of associated demand information and the influence degree on the overall service scheduling.

[0121] In the embodiment of the present application, first, the conflict information and the corresponding associated demand information existing resource occupation conflict are screened out according to the resource conflict detection result, and the resources involved in the conflict are determined to be hardware, software or mixed type one by one to determine the resource conflict type. At the same time, the number of resources involved in the conflict and the number of associated demand information are counted to analyze the potential influence of the conflict on the overall service scheduling and determine the resource influence range.

[0122] Step 513: According to the execution association relationship and the conflict resolution priority of each target demand information, the conflict information and the associated demand information are resolved to obtain non-conflict information.

[0123] In this step, the conflict-free information refers to the target demand information set after the conflict resolution process, which eliminates resource occupation conflicts, meets the execution association relationship, and is sorted by priority.

[0124] In the embodiments of the present application, the conflict information and the associated demand information are adjusted for resource allocation according to the order of conflict resolution priority from high to low. Specifically, high-priority demand is preferentially allocated the required resources, and low-priority demand adjusts the execution time or replaces the resources according to the remaining resources; at the same time, the execution association relationship is combined to ensure that the execution order after adjustment meets the logic, eliminates all resource occupation conflicts, and obtains conflict-free information.

[0125] Step 514: Check all conflict-free information, and integrate the conflict-free information that passes the check according to the execution association relationship to form a sequential detection result.

[0126] In the embodiments of the present application, the conflict-free information is checked one by one, and the specific checking steps include: checking whether there is an uneliminated implicit resource conflict, whether it meets the resource scheduling constraint condition of the corresponding driving scene, and whether it fits the execution association relationship; then, the information that fails to pass the check is removed and re-adjusted, the conflict-free information that passes the check is sorted according to the execution association relationship, the resource allocation scheme and the execution order are integrated, and the sequential detection result is formed.

[0127] The embodiments of the present application solve the execution confusion problem of vehicle-mounted cross-application services caused by resource contention, guarantee the orderliness of service scheduling and the rationality of resource utilization, and provide a reliable basis for subsequent generation of target service execution sequence.

[0128] Step 106: According to the detection result, a target service execution sequence adapted to the vehicle-mounted driving state is generated, and a plurality of cross-application services are scheduled and executed in the vehicle-mounted environment in combination with the second instruction transmission signal to generate a service scheduling execution result.

[0129] In this step, the vehicle-mounted driving state refers to the real-time running state of the vehicle determined based on the environmental perception data, which includes driving speed, vehicle body vibration, and comprehensive state of the external environment.

[0130] The target service execution sequence refers to the sequence formed after scene adaptation and instruction binding, which clearly indicates the execution order of each cross-application service and the corresponding instruction, and is used to guide the orderly scheduling of services.

[0131] The service scheduling execution result refers to the final result formed by integrating the service execution feedback information after all cross-application services are completed, which reflects the overall situation of service scheduling execution.

[0132] In the embodiments of the present application, step 106 specifically includes the following steps: Step 601: generating an initial service execution sequence according to the detection result and service execution constraints corresponding to different driving scene types in the scene adaptation parameter.

[0133] In this step, the service execution constraint refers to a preset limit condition of service execution corresponding to the driving scene type in the scene adaptation parameter, and the service execution constraint includes an upper limit of service execution duration, an upper limit of the number of parallel services, etc.

[0134] The initial service execution sequence refers to a preliminary sequence that clearly defines the service execution order, which is generated based on the order detection result in the detection result and in combination with the service execution constraint.

[0135] In the embodiment of the application, first, the service execution constraint corresponding to the driving scene type is extracted according to the scene adaptation parameter, and then the execution order in the order detection result is adjusted by referring to the constraint condition, and the arrangement mode that does not conform to the constraint is eliminated, to generate an initial service execution sequence that clearly defines the service execution order, so as to ensure that the sequence adapts to the current vehicle driving state.

[0136] Step 602: binding the second instruction transmission signal corresponding to each target demand information with the corresponding service execution node in the initial service execution sequence to form a target service execution sequence.

[0137] In this step, the service execution node refers to a node corresponding to each cross-application service in the initial service execution sequence, and each node corresponds to a target demand information and an associated cross-application service.

[0138] The target service execution sequence refers to a complete sequence that clearly defines the service execution order and is accompanied by an execution instruction after the second instruction transmission signal is bound with the service execution node.

[0139] In the embodiment of the application, the second instruction transmission signal is first associated and matched with the corresponding target demand information, and then the target demand information corresponding to each service execution node in the initial service execution sequence is located, and the matched second instruction transmission signal is bound with the corresponding service execution node one by one, so that each node contains execution order information and is accompanied by an instruction that can trigger service execution, and the target service execution sequence is integrated and formed.

[0140] Step 603: according to the target service execution sequence, sending an execution trigger instruction to the corresponding functional module of the vehicle system to trigger the first cross-application service corresponding to the first service execution node to start, after confirming that the first cross-application service completes the preset operation according to the target service execution sequence and the second instruction transmission signal, triggering the cross-application service corresponding to the next service execution node to start based on the target service execution sequence, until all cross-application services corresponding to the service execution nodes complete the preset operation, integrating the execution feedback information of each cross-application service to form a service scheduling execution result.

[0141] In this step, the execution trigger instruction is generated based on the second instruction transmission signal of the target service execution sequence to start the cross-application service.

[0142] The first cross-application service refers to the cross-application service corresponding to the service execution node ranked first in the target service execution sequence.

[0143] The execution feedback information refers to the execution status, result, and whether the result is qualified after each cross-application service is completed.

[0144] In the embodiments of the present application, first, the second instruction transmission signal bound to the first service execution node is extracted according to the order of the target service execution sequence, the corresponding execution trigger instruction is generated and sent to the corresponding functional module of the vehicle to trigger the start of the first cross-application service; the execution process of the service is monitored in real time, and after confirming that the service completes the preset operation according to the target service execution sequence and the second instruction transmission signal, the instruction of the next service execution node is extracted and the corresponding cross-application service is triggered, and the cycle is repeated in turn until all services are executed. Finally, the execution feedback information of each cross-application service is collected and integrated into the service scheduling execution result to complete the scheduling and execution of the entire cross-application service of the vehicle.

[0145] The embodiments of the present application realize the scenario-based and orderly scheduling of the cross-application service of the vehicle, which not only ensures that the service execution meets the current driving state and user demand, but also ensures the service execution quality through successive confirmation and feedback integration, and finally outputs the complete scheduling result, provides data support for service optimization of the vehicle system, and perfects the entire cross-application service scheduling link.

[0146] Figure 3 FIG. 1 is a structural schematic diagram of a specific embodiment of a cross-application service scheduling and execution system in a vehicle environment provided by the present application. Figure 3 The system can include: The acquisition module 31 is configured to acquire service-related data of a known vehicle system, environment perception data of a vehicle environment, and user voice information. The analysis module 32 is configured to analyze the user voice information through voice recognition technology to obtain target demand information, intention association information, and voice feature information of a plurality of cross-application services. The generation module 33 is configured to form scenario adaptation parameters based on the environment perception data, and generate a plurality of first instruction transmission signals corresponding to the cross-application services based on the target demand information. The optimization module 34 is configured to optimize the first instruction transmission signals using an amplifier to obtain a plurality of second instruction transmission signals. The detection module 35 is configured to perform resource occupation detection and execution sequence detection on the target demand information by the conflict coordination engine based on the service-related data, the intention association information, the voice feature information, and the scene adaptation parameter, and obtain a detection result. The execution module 36 is configured to generate a target service execution sequence adapted to the in-vehicle driving state according to the detection result, perform scheduling and execution of multiple cross-application services in the in-vehicle environment in combination with the second instruction transmission signal, and generate a service scheduling and execution result.

[0147] The service scheduling and execution system in the in-vehicle environment according to the embodiment of the present application is used to implement the service scheduling and execution method in the in-vehicle environment as described above, and thus the specific embodiments of the service scheduling and execution system in the in-vehicle environment can refer to the embodiment part of the service scheduling and execution method in the in-vehicle environment as described above. The specific embodiments can refer to the description of the respective embodiment parts, and will not be described herein again.

[0148] The present application further provides a computing device including a processing component and a storage component. The storage component stores one or more computer instructions. The one or more computer instructions are used to be invoked and executed by the processing component to implement the steps of the service scheduling and execution method in the in-vehicle environment as described above.

[0149] The present application further provides a computer storage medium having a computer program stored thereon. When the computer program is executed by a computer, the steps of the service scheduling and execution method in the in-vehicle environment as described above are implemented.

[0150] In an exemplary embodiment, the computer storage medium as described above can include but is not limited to a U disk, a read-only memory, a random access memory, a mobile hard disk, a magnetic disk or an optical disk, and various media that can store computer programs.

[0151] The embodiment of the present application further provides a computer program product including a computer program. When the computer program is executed by a processor, the steps of the service scheduling and execution method in the in-vehicle environment as described above are implemented.

[0152] Those skilled in the art will further realize that the mere concepts, teachings, and embodiments described herein are merely meant to provide an enabling description of embodiments of the present application and that various modifications can be made thereto without departing from the scope of the present application. Accordingly, the appended claims are intended to embrace all such alterations, modifications, and variations of the embodiments described herein that are within the scope of this application, including all the preferred embodiments.

[0153] The above provides a kind of vehicle-mounted environment cross-application service scheduling execution method and system provided in the present application in detail.The principle and implementation of the present application are described in the specific examples in this paper, the above example is only used to help understanding the method of the present application and its core idea.It should be pointed out that, for the ordinary skilled in the art, without departing from the principle of the present application, the present application can be improved and modified, these improvements and modifications also fall within the scope of the present application.

Claims

1. A cross-application service scheduling and execution method in a vehicle environment, characterized in that, include: Acquire known service-related data from in-vehicle systems, as well as environmental perception data and user voice information from the in-vehicle environment; The user's voice information is analyzed using speech recognition technology to obtain target demand information, intent association information, and voice feature information across multiple application services; Based on the environmental perception data, scene adaptation parameters are formed, and based on the target requirement information, multiple first instruction transmission signals corresponding to each cross-application service are generated. The first command transmission signal is optimized using an amplifier to obtain multiple second command transmission signals; Based on the service-related data, intent association information, voice feature information, and scene adaptation parameters, the conflict coordination engine performs resource occupancy detection and execution order detection on each target requirement information to obtain the detection results. Based on the detection results, a target service execution sequence adapted to the vehicle driving state is generated. Combined with the second instruction transmission signal, multiple cross-application services are scheduled and executed in the vehicle environment, and a service scheduling execution result is generated.

2. The method according to claim 1, characterized in that, Based on the environmental perception data, scene adaptation parameters are formed. Based on the target requirement information, multiple first instruction transmission signals corresponding to each cross-application service are generated, including: The environmental perception data is subjected to correlation analysis to generate information correlation features, and different driving scenario types are classified based on the information correlation features. Based on the aforementioned information association characteristics, and the signal transmission requirements and triggering conditions for cross-application service execution, adaptation rules related to cross-application service execution are set for different driving scenario types. Based on the parameter recognition specifications of the vehicle system, various adaptation rules are transformed into scene adaptation parameters that can be recognized by the vehicle system. The target requirement information of each cross-application service is broken down into execution actions, operation objects, and operation parameters, and the execution actions, operation objects, and operation parameters corresponding to each target requirement information are converted into first instruction transmission signals that conform to the signal transmission specifications of the vehicle system.

3. The method according to claim 1, characterized in that, The first command transmission signal is optimized using an amplifier to obtain multiple second command transmission signals, including: Based on the signal type of the first instruction transmission signal and the scenario adaptation parameters, determine the transmission characteristic parameters of each first instruction transmission signal; Based on the signal transmission strength benchmark value and interference threshold under different driving scenario types in the scenario adaptation parameters, and combined with each transmission characteristic parameter, the initial gain parameter and initial filtering parameter of the amplifier are adjusted to generate an adaptation parameter set corresponding to each first command transmission signal. According to each set of adaptation parameters, the corresponding first instruction transmission signal is calibrated in frequency band to obtain multiple preprocessed signals; The preprocessed signals are optimized by the amplifier according to each set of adaptation parameters to obtain multiple optimized signals; Based on the strength benchmark value and interference threshold, the signal strength and anti-interference capability of each optimized signal are verified, and the optimized signal that passes the verification is used as the second instruction transmission signal.

4. The method according to claim 3, characterized in that, Based on the signal transmission strength benchmark and interference threshold under different driving scenario types in the scenario adaptation parameters, and combined with various transmission characteristic parameters, the initial gain parameters and initial filtering parameters of the amplifier are adjusted to generate an adaptation parameter set corresponding to each first command transmission signal, including: Based on the signal transmission requirements of various driving scenarios, the parameter deviations of each transmission characteristic parameter from the strength benchmark value and interference threshold are analyzed, and a deviation dataset is generated. Based on the deviation dataset, the initial gain parameters of the amplifier are adjusted in stages, and the initial filter parameters of the amplifier are adjusted for frequency band adaptation based on the numerical range of each interference threshold, so as to generate parameter adjustment records. From the parameter adjustment records, a candidate parameter set is selected that matches the transmission characteristic parameters and deviation dataset of each first command transmission signal; The candidate parameter sets corresponding to each first instruction transmission signal are verified to identify the parameter set that has no parameter conflicts, is adapted to the signal transmission requirements and corresponding transmission characteristic parameters of the corresponding driving scenario type, and is used as the adaptation parameter set.

5. The method according to claim 1, characterized in that, The detection results include resource conflict detection results and sequence detection results; Based on the service-related data, intent association information, voice feature information, and scene adaptation parameters, the conflict coordination engine performs resource occupancy detection and execution order detection on each target requirement information to obtain detection results, including: Based on the resource configuration information of the vehicle system and the target requirement information, determine the types of hardware resources and the amount of software resources required to execute each target requirement information, so as to form a resource requirement list; Based on the service-related data, analyze the occupancy status of each hardware resource type in the vehicle system, the remaining availability of each software resource, and combine the historical time consumption data of each resource executing cross-application services to generate a resource status dataset. Extract resource scheduling constraints corresponding to different driving scenario types from the scenario adaptation parameters; Based on the intent association information, the execution association relationship between each target requirement information is analyzed, and based on the voice feature information, the expression features corresponding to each target requirement information are determined; Based on the resource demand list and resource status dataset, the conflict coordination engine performs resource occupancy analysis on the target demand information and generates resource conflict detection results. Based on the resource conflict detection results, resource scheduling constraints, execution relationships, and expression characteristics, the conflict coordination engine performs conflict resolution processing on all target requirement information to generate sequence detection results.

6. The method according to claim 5, characterized in that, Based on the resource conflict detection results, resource scheduling constraints, execution relationships, and expression features, the conflict coordination engine performs conflict resolution processing on all target requirement information to generate sequence detection results, including: Based on the resource conflict detection results, resource scheduling constraints, execution relationships, and expression characteristics, the conflict coordination engine determines the conflict resolution priority of each target requirement information. Based on the resource conflict detection results, identify conflict information and corresponding related demand information where resource occupation conflicts exist, and confirm the resource conflict type and resource impact range of the conflict information and related demand information; Based on the execution association and the conflict resolution priority of each target requirement information, the conflict information and associated requirement information are resolved to obtain conflict-free information. All conflict-free information is verified, and the verified conflict-free information is integrated according to the execution association to form a sequential detection result.

7. The method according to claim 1, characterized in that, Based on the detection results, a target service execution sequence adapted to the vehicle's driving state is generated. Combined with the second instruction transmission signal, multiple cross-application services are scheduled and executed in the vehicle environment, generating service scheduling and execution results, including: Based on the detection results and the service execution constraints corresponding to different driving scenario types in the scenario adaptation parameters, an initial service execution sequence is generated. The second instruction transmission signal corresponding to each target requirement information is bound to the corresponding service execution node in the initial service execution sequence to form a target service execution sequence; According to the target service execution sequence, an execution trigger instruction is sent to the corresponding functional module of the vehicle system to trigger the startup of the first cross-application service corresponding to the first service execution node. After confirming that the first cross-application service has completed the preset operation according to the target service execution sequence and the second instruction transmission signal, the startup of the cross-application service corresponding to the next service execution node is triggered based on the target service execution sequence. This continues until all cross-application services corresponding to all service execution nodes have completed the preset operation. Then, the execution feedback information of each cross-application service is integrated to form a service scheduling execution result.

8. A cross-application service scheduling and execution system in a vehicle environment, characterized in that, include: The acquisition module is used to acquire known service-related data of the in-vehicle system, as well as environmental perception data of the in-vehicle environment and user voice information; The parsing module is used to parse the user's voice information using speech recognition technology to obtain target demand information, intent association information, and voice feature information across multiple application services; The generation module is used to form scene adaptation parameters based on the environmental perception data and generate multiple first instruction transmission signals corresponding to each cross-application service based on the target requirement information. An optimization module is used to optimize the first command transmission signal using an amplifier to obtain multiple second command transmission signals; The detection module is used to perform resource occupancy detection and execution order detection on each target requirement information based on the service-related data, intent association information, voice feature information and scene adaptation parameters, and obtain the detection results through the conflict coordination engine. The execution module is used to generate a target service execution sequence adapted to the vehicle driving state based on the detection results, and, in conjunction with the second instruction transmission signal, to schedule and execute multiple cross-application services in the vehicle environment, and generate service scheduling and execution results.

9. A computing device, characterized in that, It includes a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are invoked and executed by the processing component to implement a cross-application service scheduling and execution method in a vehicle environment as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that, The system contains a computer program that, when executed by a computer, implements a cross-application service scheduling and execution method in a vehicle environment as described in any one of claims 1 to 7.

Images