Method and system for identifying running scene of vehicle-mounted operating system in real time

Abstract

The invention discloses a real-time identification method and system for a running scene of a vehicle-mounted operating system, and the method comprises the steps: collecting system log data in real time, and carrying out the preprocessing of the system log data, and obtaining scene parameters; calculating an actual scene recognition value according to a preset algorithm and the scene parameters; and obtaining an actual scene association value through a pre-trained relation model of the scene association value and the scene identification value and the actual scene identification value, the actual scene association value being a scene identified by the system. The vehicle-mounted operation system can dynamically identify different operation scenes so as to provide an intelligent basis for automatic adjustment of resource configuration, so that the response speed, the resource utilization efficiency and the user experience of the system are remarkably improved, and meanwhile, the technical scheme also has good expansibility and is suitable for popularization and application. The method can adapt to novel application scenes and function requirements, and ensures that the system always keeps the optimal performance in a complex and changeable environment.

Description

Technical Field

[0001] The present invention relates to the field of intelligent vehicle-mounted technology, and in particular to a method and system for real-time identification of vehicle-mounted operating system operation scenarios. Background Art

[0002] With the rapid development of automotive electronic technology, intelligent vehicle operating systems have become an important part of modern cars. Intelligent vehicle operating systems provide users with a variety of functions such as navigation, entertainment, safety alarms, and vehicle monitoring. However, existing vehicle operating systems usually optimize performance in a single or specific scenario. Existing vehicle operating systems usually adopt fixed resource allocation and performance optimization strategies, but lack the ability to recognize and adapt to complex and diverse scenarios in real time. This results in the vehicle operating system being slow to respond and having low resource utilization in some scenarios, thus failing to provide the best user experience.

[0003] In the existing solutions, most in-vehicle operating systems pre-allocate fixed system resources, such as CPU, memory, and storage space, for various applications and services during design. The advantage of this approach is that it is simple to implement and can be optimized for specific applications during design.

[0004] In the prior art, some vehicle-mounted operating systems also perform resource scheduling in an event-driven manner. When a specific event (such as navigation startup, phone call incoming) occurs, the system will start a predefined resource allocation plan to ensure the priority and response speed of key tasks.

[0005] At the same time, some more advanced in-vehicle operating systems may also preset several common scenarios, such as navigation scenarios, entertainment scenarios, safety alarm scenarios, etc., and optimize performance for these scenarios. For example, in the navigation scenario, the system will give priority to ensuring the resource requirements of the navigation application.

[0006] Although the existing in-vehicle operating system can guarantee the normal operation of functions to a certain extent, with the diversification of automobile functions and the improvement of user needs, the existing technology has obvious deficiencies in the following aspects: (i) Lack of real-time scene recognition capability: The existing fixed resource allocation strategy is generally based on preset scenes and cannot recognize real-time complex and changeable scenes. In actual driving, the in-vehicle operating system may frequently switch between different scenes, such as the mixed use of navigation and entertainment, sudden safety incidents, etc. If this scene switching cannot be recognized and resources optimized in time, it may cause the system response to slow down or freeze, affecting the user experience. (ii) Low system resource utilization: Since the resource allocation scheme is usually pre-defined, it fails to fully consider the diversity and dynamic changes of actual scenes, resulting in low utilization of system resources. For example, in some cases, the system may allocate too many resources to unimportant background applications, while critical tasks do not receive sufficient resource support. (iii) Poor scene scalability: Most of the existing technologies are based on pre-defined scenes and fixed optimization strategies, which are difficult to expand or adapt to new application scenarios and functional requirements. With the continuous increase in the functions of the in-vehicle operating system, this limitation will become more apparent, restricting the improvement of system performance. (IV) Poor user experience: Since the system cannot be dynamically optimized according to the actual scenario, some user experience problems may occur, such as navigation delays, music playback freezes, and voice control sluggish response. These problems not only affect user satisfaction, but may also bring safety risks at critical moments.

[0007] Therefore, there is an urgent need for a technical solution that can identify different scenarios of the vehicle operating system in real time, provide a basis for the subsequent automatic adjustment of the operating system parameters, and improve the overall performance and user experience of the vehicle system. Summary of the invention

[0008] One of the purposes of the embodiments of the present invention is to provide a method and system for real-time identification of vehicle operating system operating scenarios, so as to be able to identify different scenarios of the vehicle operating system in real time and provide a basis for subsequent automatic adjustment of the operating system operating parameters to improve the overall performance of the vehicle system and user experience.

[0009] In order to solve the above technical problems, in a first aspect, an embodiment of the present invention provides a method for real-time identification of a vehicle operating system operation scene, the method comprising:

[0010] Collecting system log data in real time, and preprocessing the system log data to obtain scene parameters;

[0011] Calculating an actual scene recognition value according to a preset algorithm and the scene parameters;

[0012] The actual scene association value is obtained by using the pre-trained relationship model between the scene association value and the scene recognition value, and the actual scene recognition value. The actual scene association value is the scene recognized by the system.

[0013] Preferably, the system log data is represented as D={d1, d2, ..., d N}, each data record d i Corresponding to the scene parameters.

[0014] Furthermore, the method further comprises:

[0015] The operating scenarios of the vehicle operating system are classified in advance, and the operating scenarios include but are not limited to: driving scenario classification, entertainment scenario classification, navigation scenario and vehicle phone scenario, and the operating status under each scenario is divided.

[0016] Preferably, the training of the pre-trained relationship model between the scene association value and the scene recognition value specifically includes:

[0017] Obtaining scene-related values ​​in advance and obtaining sample data of the scene-related values;

[0018] Pre-calculating scene recognition values ​​to obtain sample data of the scene recognition values;

[0019] A relationship model between the scene association value and the scene identification value is established, and sample data of the scene association value and sample data of the scene identification value are input into the relationship model for training to obtain a trained relationship model.

[0020] Preferably, the obtaining of the scene association value specifically includes:

[0021] Collecting vehicle status data and system log data, and preprocessing the system log data;

[0022] Performing feature extraction on the preprocessed data to obtain different types of feature vectors, wherein the features include time features, text features, and numerical features;

[0023] The extracted feature vectors of different types are concatenated to obtain the log vector. The formula for obtaining the scene association value based on the log vector is as follows:

[0024] Scenario association value SA=driving scenario weight Wd×driving scenario score Sd+entertainment scenario weight We×entertainment scenario score Se+navigation scenario weight Wn×navigation scenario score Sn+car phone scenario weight Wp×car phone scenario score Sp.

[0025] Preferably, the calculating the actual scene recognition value according to the preset algorithm and the scene parameter specifically includes:

[0026] According to the scene parameters, a characteristic function of the scene is obtained;

[0027] The calculation formula of the preset algorithm is: SR = ∑ [ω i ×F i ], where SR represents the actual scene recognition value, F i Represents the characteristic functions of different scenarios, which characterize different system operation scenarios, ω i is the weight coefficient of the corresponding characteristic function, which is adjusted according to the actual situation, and:

[0028] ∑ω i =1.

[0029] Preferably, the relationship model between the scene association value and the scene identification value is:

[0030] SA=θ0+θ1SR+θ2x1+θ3x2+…+θ m+1 x m +∈;

[0031] Among them, the scene recognition value SR and the feature vector X = (x1, x2, ... x m ) is the input, θ0, θ1, …, θ m+1 is the parameter of the model, ∈ is the error term, and SA is the scene association value;

[0032] In the process of training the relationship, the least square method is used to minimize the error between the predicted scene association value and the actual scene association value, thereby obtaining a relationship model between the trained scene association value and the scene recognition value:

[0033]

[0034] Where N is the number of training samples, SA i and SR i is the actual scene association value and scene recognition value of the i-th training sample, x ij is the ith eigenvalue of the ith training sample.

[0035] In a second aspect, an embodiment of the present invention further provides a real-time recognition system for an in-vehicle operating system operation scenario, the system comprising:

[0036] A data collection module, used for collecting system log data and preprocessing the system log data;

[0037] A calculation module, used to calculate the actual scene recognition value according to a preset algorithm and the scene parameters;

[0038] The scene recognition module is used to obtain the actual scene association value through the pre-trained relationship model between the scene association value and the scene recognition value, and the actual scene recognition value. The actual scene association value is the scene recognized by the system.

[0039] In a third aspect, an embodiment of the present invention further provides a vehicle-mounted computing device, which includes a processor or a calculator and a memory, wherein the memory is used to store a computer program, and the computer program includes program instructions, and the processor or the calculator is configured to call the program instructions to execute the method as described above.

[0040] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor or a computer, the processor or the computer executes the method as described above.

[0041] Compared with the prior art, the method and system for real-time identification of vehicle operating system operation scenarios provided by the embodiments of the present invention have at least the following beneficial effects:

[0042] The vehicle-mounted operating system of the embodiment of the present invention can dynamically identify different operating scenarios, thereby providing an intelligent basis for the subsequent automatic adjustment of resource configuration, thereby significantly improving the system's response speed, resource utilization efficiency and user experience. At the same time, the technical solution also has good scalability and can adapt to new application scenarios and functional requirements, ensuring that the system always maintains optimal performance in a complex and changing environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The preferred implementation modes will be described below in a clear and understandable manner with reference to the accompanying drawings to further illustrate the above-mentioned characteristics, technical features, advantages and implementation methods of the present invention.

[0044] Figure 1 This is a flow chart of a method for real-time identification of vehicle operating system operation scenarios according to an embodiment of the present invention;

[0045] Figure 2 This is a schematic diagram of a real-time recognition system for an in-vehicle operating system operation scenario according to an embodiment of the present invention;

[0046] Figure 3 The present invention is a schematic diagram of the structure of an in-vehicle computing device for implementing a method for real-time identification of an in-vehicle operating system operation scenario according to an embodiment of the present invention. DETAILED DESCRIPTION

[0047] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the specific implementation methods of the present invention will be described below with reference to the accompanying drawings. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings and other implementation methods can be obtained based on these drawings without creative work.

[0048] In order to simplify the drawings, only the parts related to the invention are schematically shown in each figure, and they do not represent the actual structure of the product. In addition, in order to simplify the drawings and facilitate understanding, in some figures, only one of the parts with the same structure or function is schematically drawn or marked. In this article, "one" not only means "only one", but also means "more than one".

[0049] The following mainly takes some specific embodiments as examples to describe in detail the implementation of the technical solution of the present invention.

[0050] like Figure 1 As shown, in order to achieve the purpose of the invention, an embodiment of the invention provides a method for real-time identification of a vehicle operating system operation scene, the method comprising:

[0051] S1. Collect system log data in real time and pre-process the system log data to obtain scene parameters;

[0052] S2. Calculate the actual scene recognition value using a preset algorithm and the scene parameters;

[0053] S3. Obtain an actual scene association value through a pre-trained relationship model between scene association values ​​and scene recognition values, and the actual scene recognition value. The actual scene association value is a scene recognized by the system.

[0054] The embodiment of the present invention collects vehicle operation status data and system performance data in real time through vehicle sensors, system logs, user operation records, etc. The collected data includes but is not limited to vehicle speed, acceleration, navigation status, CPU usage, memory usage, etc., and preprocesses the collected data, including the following:

[0055] For system log data, the log data set D = {d1, d2, ..., d N}, each log record d i Associated with specific system operation scenarios, system log data reflects the system operation status parameters in different application scenarios.

[0056] Preferably, the training of the pre-trained relationship model between the scene association value and the scene recognition value specifically includes:

[0057] Obtaining scene-related values ​​in advance and obtaining sample data of the scene-related values;

[0058] Pre-calculating scene recognition values ​​to obtain sample data of the scene recognition values;

[0059] A relationship model between the scene association value and the scene identification value is established, and sample data of the scene association value and sample data of the scene identification value are input into the relationship model for training to obtain a trained relationship model.

[0060] Preferably, the obtaining of the scene association value specifically includes:

[0061] Collect vehicle status data and system log data, and pre-process the collected data sets;

[0062] Performing feature extraction on the preprocessed data to obtain different types of feature vectors, wherein the features include time features, text features, and numerical features;

[0063] The extracted feature vectors of different types are concatenated to obtain the log vector. The formula for obtaining the scene association value based on the log vector is as follows:

[0064] Scenario association value SA=driving scenario weight Wd×driving scenario score Sd+entertainment scenario weight We×entertainment scenario score Se+navigation scenario weight Wn×navigation scenario score Sn+car phone scenario weight Wp×car phone scenario score Sp.

[0065] That is, the collected log data is preprocessed to remove irrelevant information and noise to ensure the quality and validity of the data. The preprocessed log data is subjected to feature extraction, including time features, text features, and numerical features.

[0066] For time features, time information is extracted from log data, and the timestamp can be converted into a specific time format, such as year, month, day, hour, minute, second, etc. Time intervals can also be calculated, such as the time difference between two events. These time features can be used as part of a vector. For example, if the timestamp of an event recorded in the log is 1627225200 (indicating July 25, 2021 12:00:00), it can be converted into a time vector representation such as [2021,7,25,12,0,0].

[0067] For text features, natural language processing technology is used to extract features from text information in log data, such as event descriptions, error messages, etc. In the embodiment of the present invention, a bag-of-words model can be used to extract features from logs. For example, when using a bag-of-words model, the text in the log can be segmented, and then the number of times each word appears in the log is counted to form a word frequency vector.

[0068] If the event in the log is described as "out of memory error", after word segmentation, we get ["memory", "insufficient", "error"], and assuming that the entire log set contains different words ["memory", "insufficient", "error", "disk", "space"], then the word frequency vector of the log can be expressed as [1,1,1,0,0].

[0069] In addition, numerical feature extraction is also performed. Since the log data may contain some numerical information, such as CPU usage, memory usage, network traffic, etc., these numerical values ​​are directly used as part of the vector. For example, if the CPU usage recorded in the log is 75% and the memory usage is 60%, these numerical values ​​can be directly used as the two dimensions of the vector, that is, [75,60].

[0070] Again, the extracted feature information is normalized to ensure that different features are comparable in value so that the neural network can better learn the feature patterns in different scenarios. The normalization formula is:

[0071]

[0072] Among them, x ij is the original eigenvalue, x′ ij is the normalized eigenvalue, min(x j ) and max(x j ) are the minimum and maximum values ​​of feature j, respectively.

[0073] For example, use Min-Max normalization to normalize the CPU usage and memory usage to the range [0,1]. Assuming the CPU usage range is [0,100] and the memory usage range is [0,80], if the CPU usage is 75%, the normalized value is 75 / 100 = 0.75; if the memory usage is 60%, the normalized value is 60 / 80 = 0.75. The normalized vector becomes [0.75,0.75].

[0074] Finally, vector concatenation is performed to concatenate the extracted feature vectors of different types to form a comprehensive log vector. The concatenation order can be determined according to the importance of the features or specific requirements.

[0075] For example, the time feature vector [2021,7,25,12,0,0], the text feature vector [1,1,1,0,0], and the numerical feature vector [0.75,0.75] are concatenated to obtain a complete log vector [2021,7,25,12,0,0,1,1,1,0,0,0.75,0.75].

[0076] The embodiment of the present invention pre-classifies the scenarios of the intelligent vehicle operating system, including but not limited to: driving scenario classification, entertainment scenario classification, navigation scenario and vehicle phone scenario.

[0077] Taking driving scene classification as an example, it is divided into the following categories:

[0078] High-speed driving scenario: The vehicle speed is usually above 80 km / h, the road is relatively flat, and the vehicle travels stably.

[0079] Urban road scene: the vehicle speed is relatively low, there are many traffic lights and pedestrians, and the road conditions are relatively complex.

[0080] Mountain road scene: The terrain is undulating, with many bends and slopes, which places high demands on the vehicle's power and control.

[0081] Congestion scenario: vehicles are moving slowly, stopping and going, and traffic flow is heavy.

[0082] Taking entertainment scene classification as an example, it is divided into the following categories:

[0083] Music playback scenario: The car audio system is playing music, and the user may switch songs, adjust the volume, etc.

[0084] Video playback scenario: The in-vehicle display is playing a video, which usually appears when the car is parked or passengers are riding.

[0085] Radio listening scenario: The user is listening to a radio program.

[0086] Taking navigation scene classification as an example, it is divided into the following categories:

[0087] Route planning scenario: The user is using the navigation system to plan the route and input information such as the destination.

[0088] Navigation guidance scenario: The navigation system is providing real-time navigation guidance, including voice prompts and map display.

[0089] The call scenarios include the following:

[0090] In-call scenario: The user is making a car phone call.

[0091] Call waiting scenario: There is an incoming call waiting for the user to answer.

[0092] Call end scenario: The car phone call has just ended.

[0093] The embodiment of the present invention further marks the log data as a category label corresponding to the scenario.

[0094] For example, scenarios can be classified according to different system operating states, business process stages, or abnormal situations.

[0095] Furthermore, the embodiment of the present invention can also mark the log data into different scenario categories according to actual needs.

[0096] For example, logs can be divided into normal operation scenarios, abnormal warning scenarios, serious failure scenarios, etc.

[0097] Each label y i ∈{1, 2, 3…K} represents a specific scenario and provides a clear goal for subsequent model training.

[0098] Preferably, the scene annotation of log data specifically includes:

[0099] Information such as time, vehicle speed, acceleration, navigation status, entertainment system usage, and vehicle phone status are extracted from the vehicle system log and annotated.

[0100] For example, when the vehicle speed is above 80 km / h, the navigation system is active, the entertainment system is not in use, and the car phone is in a call, it is marked as a high-speed driving scene, a navigation guidance scene, and a call scene.

[0101] For another example, if there is a call waiting and the vehicle speed is low, and the vehicle is in a city road scene, it is marked as a city road scene and a call waiting scene.

[0102] Preferably, data from vehicle-mounted sensors, such as acceleration sensors, gyroscopes, etc., are also used to mark the driving status of the vehicle, while combining information such as the signal strength of the vehicle-mounted phone.

[0103] For example, when the acceleration sensor detects a large longitudinal acceleration, it may mean that the vehicle is accelerating or decelerating, and it can be marked as different scenes in combination with information such as vehicle speed. If the signal strength of the car phone is weak at this time, it can be marked as the corresponding scene and the phone signal status can be recorded.

[0104] The scene categories after annotation are marked with scene-related values, including:

[0105] Scenario association value (S) = driving scenario weight (Wd) × driving scenario score (Sd) + entertainment scenario weight (We) × entertainment scenario score (Se) + navigation scenario weight (Wn) × navigation scenario score (Sn) + car phone scenario weight (Wp) × car phone scenario score (Sp)

[0106] Through this formula, a scene association value can be calculated according to the scores and weights of different scenes, so as to comprehensively judge the scene status of the current vehicle system and provide a basis for the adaptive adjustment of the system.

[0107] The above formula can be extended according to the definition of scene categories.

[0108] Among them, the driving scene score (Sd) is set as:

[0109] High-speed driving scenario: If the vehicle speed is greater than or equal to 80 km / h and the road is relatively flat, the acceleration change is small, and it is recorded as 80 points; if some conditions are met, the score can be appropriately lowered, that is, the score can be fine-tuned, and the embodiment of the present invention does not make a sole limitation.

[0110] Urban road scene: the vehicle speed is low, there are many traffic lights and pedestrians, and the score range is 40-70 points based on comprehensive judgment of factors such as the degree of congestion and the frequency of traffic lights. This range can be fine-tuned and is not limited to this in the embodiment of the present invention.

[0111] Mountain road scene: Based on a comprehensive assessment of factors such as terrain undulations, curves and slopes, and vehicle control difficulty, the score is in the range of 50-80 points. This range can be fine-tuned and is not limited to this in the embodiments of the present invention.

[0112] Congestion scenario: vehicles are moving slowly, stopping and going, and the traffic flow is heavy. According to the severity of the congestion, the range is 30-60 points. This range can be fine-tuned and is not limited to this in the embodiment of the present invention.

[0113] The entertainment scene score (Se) is set as:

[0114] Music playback scenario: determined based on factors such as playback duration and song switching frequency, ranging from 40 to 70 minutes. This range can be fine-tuned and is not limited solely by the embodiment of the present invention.

[0115] Video playback scenario: Determined based on factors such as playback duration and video type, the range is 30-60 minutes and can be fine-tuned.

[0116] Radio listening scenario: This is determined based on factors such as listening time and channel switching frequency. The range is 30-60 minutes and can be fine-tuned.

[0117] The navigation scenario score (Sn) is set as:

[0118] Route planning scenario: determined based on factors such as planning time and destination complexity, with a range of 40-70 points. This range can be fine-tuned and is not limited solely to this embodiment of the present invention.

[0119] Navigation guidance scenario: determined based on factors such as navigation accuracy and voice prompt frequency, ranging from 50 to 80 points. This range can be fine-tuned and is not limited solely to this embodiment of the present invention.

[0120] The car phone scenario score (Sp) is set as:

[0121] In-call scenario: determined based on call duration, signal strength and other factors, the range is 40-70 minutes. This range can be fine-tuned and is not limited to this in the embodiment of the present invention.

[0122] Call waiting scenario: determined based on factors such as waiting time and importance, ranging from 30 to 60 minutes. This range can be fine-tuned and is not limited in the embodiment of the present invention.

[0123] Call ending scenario: determined based on factors such as call duration and whether there are subsequent operations, ranging from 20 to 50 minutes. This range can be fine-tuned and is not limited in the embodiment of the present invention.

[0124] For the weight setting part, it can be set as:

[0125] The driving scenario weight (Wd), entertainment scenario weight (We), navigation scenario weight (Wn), and car phone scenario weight (Wp) can be set according to actual needs and importance.

[0126] For example, if driving safety is the primary consideration, the driving scenario weight can be set higher, such as 0.4; the entertainment scenario and car phone scenario weights can be relatively low, such as 0.2; and the navigation scenario weight can be set to 0.2.

[0127] The settings of the above scores and weight parameters should not be understood as the sole limitation of the technical solution of the present invention. After debugging the vehicle-mounted operating system during actual implementation, a person skilled in the art may fine-tune the settings of the above parameters according to specific circumstances. The fine-tuned scores or weight parameter values ​​should be within the protection scope of the present invention.

[0128] Preferably, the calculating the actual scene recognition value according to the preset algorithm and the scene parameter specifically includes:

[0129] According to the scene parameters, a characteristic function of the scene is obtained;

[0130] The calculation formula of the preset algorithm is: SR = ∑ [ω i ×F i ], where F i Represents the characteristic functions of different scenarios, which characterize different system operation scenarios, ω i is the weight coefficient of the corresponding characteristic function, which is adjusted according to the actual situation, and:

[0131] ∑ω i =1.

[0132] F irepresents different feature functions, representing various factors related to a specific scenario, for example, in some embodiments:

[0133] f1 (Speed ​​and Acceleration Features) is the speed and acceleration feature function, F1 = V α ×A β .

[0134] The current vehicle speed, acceleration change rate and other factors can be comprehensively considered. Among them, V is the vehicle speed, A is the acceleration, α and β are adjustable weight parameters, which are used to adjust the importance of vehicle speed and acceleration in the characteristic function.

[0135] The speed and acceleration characteristic function provides an effective feature description for the on-board system scene recognition by comprehensively considering the two important vehicle dynamic parameters of speed and acceleration, helping the system to more accurately judge the scene in which the vehicle is located, thereby achieving corresponding optimization and adjustment.

[0136] F2 (Navigation Status Features) is the navigation status feature function, F2 = N γ ×C δ ×D τ .

[0137] Consider whether navigation is turned on, the complexity of the current navigation route, the distance to the destination, etc.

[0138] Among them, N represents the navigation on state (on is 1, off is 0), C represents the quantitative value of the route complexity, D represents the distance, and γ, δ, and τ are weight parameters.

[0139] The complexity of the navigation route (C) consists of three parts:

[0140] N = T × R × L;

[0141] The number of turns (T) is used to count the number of turns expected in the navigation route. The more turns there are, the more complex the route is. The number of turns can be determined based on the route planning information provided by the navigation software. The number of turns is normalized.

[0142] Road type (R) is used to assign values ​​to different types of roads and then count the number of different types of roads in the route. For example, a highway can be assigned a value of 1, a city trunk road can be assigned a value of 2, a secondary trunk road can be assigned a value of 3, a branch road can be assigned a value of 4, and so on. The higher the sum of the road type assignments that appear in the route, the greater the diversity of road types and the more complex the route. If a route contains a section of highway and two sections of city secondary trunk roads, then the numerical representation of the diversity of road types can be 1+3+3=7.

[0143] The numerical representation of the traffic restriction factor (L) is used to comprehensively consider the traffic restriction factors in the route, such as one-way streets, construction areas, traffic congestion areas, etc.

[0144] In the embodiment of the present invention, a weight may be assigned to each traffic restriction factor, and then a numerical representation may be obtained by multiplying the number of traffic restriction factors appearing in the route by the corresponding weight.

[0145] For example, the weight of a one-way street is 1, the weight of a construction area is 2, and the weight of a traffic congestion area is 3. If there is a construction area and a traffic congestion area on a route, the numerical representation of the traffic restriction factor is 2+3=5.

[0146] F3 (Entertainment Usage Features) is the characteristic function of entertainment usage status:

[0147]

[0148] Including music playing status, video playing status, radio listening status, etc.

[0149] Where M represents the music playing state (1 for playing and 0 for not playing), V represents the video playing state, B represents the radio listening state, ∈, θ and is the weight parameter.

[0150] F4 (Phone Call Features) is the car phone feature function:

[0151] F4=P μ ×S π ;

[0152] It covers the phone call status, signal strength, etc., where P represents the call status (1 for call in progress, 0 for no call), S represents the quantized value of signal strength, and μ and π are weight parameters.

[0153] F5 (Sensor Data Features) is the sensor data feature function:

[0154] F5=T ρ ×L σ ;

[0155] Data from temperature sensors, light sensors, etc. can be used, where T represents the quantized value of temperature, L represents the quantized value of light intensity, and ρ and σ are weight parameters.

[0156] ω i are the weight coefficients of the corresponding feature functions. These weight coefficients can be adjusted according to the actual situation to reflect the importance of different features in scene recognition. The sum of the weight coefficients is 1, that is:

[0157] ∑ω i =1.

[0158] An empirical method can be used to assign an initial weight value to each feature function, or a gradient descent method can be used to gradually adjust the weight coefficients by calculating the gradient of the scene recognition value with respect to each weight coefficient, so that the scene recognition value more accurately reflects the scene label of the sample data.

[0159] By adjusting the weight coefficients of each feature function, a scene recognition model suitable for the vehicle system can be constructed according to different application requirements and data characteristics. This formula can flexibly adapt to different combinations of scene factors and provide accurate scene recognition results for the vehicle system so that corresponding intelligent adjustments and optimizations can be made.

[0160] Preferably, in the embodiment of the present invention, the relationship model between the scene association value and the scene recognition value is trained as follows:

[0161] SA=θ0+θ1SR+θ2x1+θ3x2+…+θ m+1 x m +∈;

[0162] Among them, the scene recognition value SR and the feature vector X = (x1, x2, ... x m ) is the input, θ0, θ1, …, θ m+1 is the parameter of the model, ∈ is the error term, and SA is the scene association value;

[0163] In the process of training the relationship, the least square method is used to minimize the error between the predicted scene association value and the actual scene association value, thereby obtaining a relationship model between the trained scene association value and the scene recognition value:

[0164]

[0165] Where N is the number of training samples, SA i and SR i is the actual scene association value and scene recognition value of the i-th training sample, x ij is the ith eigenvalue of the ith training sample.

[0166] Deploy the trained model to the actual system, perform real-time analysis and prediction on the newly generated log data, and provide timely decision support for system monitoring, fault diagnosis, and performance optimization by quickly and accurately identifying the scenarios to which the log data belongs.

[0167] According to the different scenarios identified by the model, the CPU operating frequency is adjusted in real time. For example, in navigation mode, the CPU frequency priority of navigation-related processes is increased to ensure that tasks such as map loading and route planning are completed quickly. In entertainment mode, the frequency of the navigation process can be appropriately reduced to allocate more frequency resources for entertainment applications.

[0168] Set high process priority for critical tasks, such as setting the process priority of the vehicle safety monitoring system to the highest in driving mode to ensure timely response. Set lower priority for non-critical tasks, such as background updates.

[0169] Adjust the cache strategy for different scenarios. For example, in navigation mode, cache more map data and route information to reduce loading time. In entertainment mode, cache music and video files to improve playback smoothness.

[0170] Dynamically allocate memory based on scenario requirements. For example, when watching high-definition videos, more memory is allocated to the video playback application, while its memory usage is appropriately reduced in other scenarios.

[0171] Determine the allocation of network bandwidth based on the scenario. In navigation mode, prioritize the bandwidth required for navigation software data updates and real-time traffic conditions. In entertainment mode, reasonably allocate bandwidth to music and video streaming services.

[0172] Automatically switch network connection mode according to the scenario. For example, when driving at high speed, it will prioritize connecting to the more stable 4G / 5G network; when parking, it can switch to the Wi-Fi network to save traffic.

[0173] Data preloading: Predict user needs based on scenarios and load the data that may be used into storage in advance. For example, on routes that users often travel, preload the map data and points of interest information of the area in advance.

[0174] Regularly clean up unnecessary temporary files and caches to free up storage resources. When storage is low, prioritize cleaning up cache data of non-critical apps.

[0175] The vehicle-mounted operating system of the embodiment of the present invention can dynamically identify different usage scenarios and automatically adjust resource configuration, thereby significantly improving the system's response speed, resource utilization efficiency and user experience. At the same time, the technical solution also has good scalability and can adapt to new application scenarios and functional requirements, ensuring that the system always maintains optimal performance in a complex and changing environment.

[0176] like Figure 2 As shown, an embodiment of the present invention further provides a real-time recognition system for an in-vehicle operating system operation scene, the system comprising:

[0177] A data collection module, used for collecting system log data and preprocessing the system log data;

[0178] A calculation module, used to calculate the actual scene recognition value according to a preset algorithm and the scene parameters;

[0179] The scene recognition module is used to obtain the actual scene association value through the pre-trained relationship model between the scene association value and the scene recognition value, and the actual scene recognition value. The actual scene association value is the scene recognized by the system.

[0180] In the system embodiment, its implementation method is the same as the method implementation method, and will not be repeated here.

[0181] Compared with the prior art, the method and system for real-time identification of vehicle operating system operation scenarios provided by the embodiments of the present invention have at least the following beneficial effects:

[0182] The vehicle-mounted operating system of the embodiment of the present invention can dynamically identify different operating scenarios, thereby providing an intelligent basis for the subsequent automatic adjustment of resource configuration, thereby significantly improving the system's response speed, resource utilization efficiency and user experience. At the same time, the technical solution also has good scalability and can adapt to new application scenarios and functional requirements, ensuring that the system always maintains optimal performance in a complex and changing environment.

[0183] Deploy the trained model to the actual system to perform real-time analysis and prediction on the newly generated log data. By quickly and accurately identifying the scenarios to which the log data belongs, timely decision support is provided for system monitoring, fault diagnosis, and performance optimization.

[0184] In a third aspect, an embodiment of the present invention further provides a vehicle-mounted computing device, which includes a processor or a calculator and a memory, wherein the memory is used to store a computer program, and the computer program includes program instructions, and the processor or the calculator is configured to call the program instructions to execute the method as described above.

[0185] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor or a computer, the processor or the computer executes the method as described above.

[0186] like Figure 3As shown, an embodiment of the present application provides an in-vehicle computing device, the in-vehicle computing device 1000 includes a processor or a calculator (not shown in the figure) 1001 and a memory 1002, and the processor or the calculator 1001 and the memory 1002 can be interconnected through a communication bus 1003. The communication bus 1003 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus 1003 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the memory 1002 is used to store a computer program, the computer program includes program instructions, the processor 1001 is configured to call the program instructions, and the above program includes a method for executing some or all of the steps in the aforementioned method.

[0187] The processor 1001 may be a general purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of the above program.

[0188] The memory 1002 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory may exist independently and be connected to the processor via a bus. The memory may also be integrated with the processor.

[0189] The electronic device 1000 may further include a communication module 1004 and a display 1005. The communication module 1004 may be connected to the optical tracking device for communication. The communication module 1004 may be a wireless communication module (eg, a WiFi module, a Bluetooth module, etc.) or a wired communication module.

[0190] In addition, the electronic device 1000 may also include common components such as a communication interface (eg, a USB interface, a microphone interface, etc.), an antenna, etc., which will not be described in detail here.

[0191] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0192] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0193] In the several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0194] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0195] In addition, the functional units in the various embodiments of the application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated units may be implemented in the form of hardware or in the form of software program modules.

[0196] If the integrated unit is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM), random access memory (RAM), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0197] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, which can include: a flash drive, a read-only memory, a random access memory, a magnetic disk or an optical disk, etc.

[0198] The embodiments of the present application are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

[0199] It should be noted that the above embodiments can be freely combined as needed. The above are only preferred embodiments of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be regarded as the protection scope of the present invention.

Claims

1. A method for real-time identification of vehicle operating system operation scenarios, characterized in that: The method comprises: Collecting system log data in real time, and preprocessing the system log data to obtain scene parameters; Calculating an actual scene recognition value according to a preset algorithm and the scene parameters; The actual scene association value is obtained by using the pre-trained relationship model between the scene association value and the scene recognition value, and the actual scene recognition value. The actual scene association value is the scene recognized by the system.

2. The method for real-time identification of vehicle operating system operation scenarios according to claim 1, characterized in that: The system log data is represented as D={d1, d2, ..., d N }, each data record d i Corresponding to the scene parameters.

3. The method for real-time identification of vehicle operating system operation scenarios according to claim 2, characterized in that: The method further comprises: The operating scenarios of the vehicle operating system are classified in advance, and the operating scenarios include but are not limited to: driving scenario classification, entertainment scenario classification, navigation scenario and vehicle phone scenario, and the operating status under each scenario is divided.

4. The method for real-time identification of vehicle operating system operation scenarios according to claim 1, characterized in that: The training of the pre-trained relationship model between the scene association value and the scene recognition value specifically includes: Obtaining scene-related values ​​in advance and obtaining sample data of the scene-related values; Pre-calculating scene recognition values ​​to obtain sample data of the scene recognition values; A relationship model between the scene association value and the scene identification value is established, and sample data of the scene association value and sample data of the scene identification value are input into the relationship model for training to obtain a trained relationship model.

5. The method for real-time identification of vehicle operating system operation scenarios according to claim 4, characterized in that: The pre-obtaining of scene association values ​​specifically includes: Collecting system log data and preprocessing the system log data; Performing feature extraction on the preprocessed data to obtain different types of feature vectors, wherein the features include time features, text features, and numerical features; The extracted feature vectors of different types are concatenated to obtain the log vector. The formula for obtaining the scene association value based on the log vector is as follows: Scenario association value SA=driving scenario weight Wd×driving scenario score Sd+entertainment scenario weight We×entertainment scenario score Se+navigation scenario weight Wn×navigation scenario score Sn+car phone scenario weight Wp×car phone scenario score Sp.

6. The method for real-time identification of vehicle operating system operation scenarios according to claim 1, characterized in that: The calculating the actual scene recognition value according to the preset algorithm and the scene parameter specifically includes: According to the scene parameters, a characteristic function of the scene is obtained; The calculation formula of the preset algorithm is: SR = ∑ [ω i ×F i ], where SR represents the actual scene recognition value, F i Represents the characteristic functions of different scenarios, which characterize different system operation scenarios, ω i is the weight coefficient of the corresponding characteristic function, which is adjusted according to the actual situation, and: ∑ω i =1。 7. The method for real-time identification of vehicle operating system operation scenarios according to any one of claims 4 to 6, characterized in that: The relationship model between the pre-trained scene association value and the scene recognition value is: SA=θ0+θ1SR+θ2x1+θ3x2+…+θ m+1 x m +∈; Among them, the scene recognition value SR and the feature vector X = (x1, x2, ... x m ) is the input, θ0, θ1, …, θ m+1 is the parameter of the model, ∈ is the error term, and SA is the scene association value; In the process of training the relationship, the least square method is used to minimize the error between the predicted scene association value and the actual scene association value, thereby obtaining a relationship model between the trained scene association value and the scene recognition value: Where N is the number of training samples, SA i and SR i is the actual scene association value and scene recognition value of the i-th training sample, x ij is the j-th eigenvalue of the ith training sample.

8. A real-time recognition system for vehicle operating system operation scenarios, characterized in that: The system comprises: A data collection module, used for collecting system log data and preprocessing the system log data; A calculation module, used to calculate the actual scene recognition value according to a preset algorithm and the scene parameters; The scene recognition module is used to obtain the actual scene association value through the pre-trained relationship model between the scene association value and the scene recognition value, and the actual scene recognition value. The actual scene association value is the scene recognized by the system.

9. A vehicle-mounted device, characterized in that: The method comprises a processor or a calculator and a memory, wherein the memory is used to store a computer program, wherein the computer program comprises program instructions, and the processor or the calculator is configured to call the program instructions to execute the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor or a computer, the processor or the computer executes the method according to any one of claims 1 to 7.

Images