Data flow-based tire pressure risk detection method, device, equipment and medium

Abstract

The application discloses a tire pressure risk detection method and device based on a data stream, equipment, and a medium, and relates to the technical field of computers. The method comprises the following steps: receiving a tire pressure data stream transmitted in a real-time streaming mode, wherein the tire pressure data stream comprises data collected and uploaded by a target vehicle in real time and continuously, and the target vehicle comprises a target tire; determining tire pressure difference value data of the target tire based on the tire pressure data stream, wherein the tire pressure difference value data is used to indicate a tire pressure change condition of the target tire; accumulating the number of times of obtaining the tire pressure difference value data in the case that the tire pressure difference value data is less than a preset difference threshold; and sending tire risk data in the case that the number of times of obtaining reaches a first quantity threshold, wherein the tire risk data is used to indicate that the tire pressure of the target tire changes continuously and there is a risk of tire burst. The method can feed back tire burst early warning to the user earlier by detecting the case that the tire pressure changes continuously, so that the vehicle can reduce the possibility of tire burst.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer, in particular to a tire pressure risk detection method and device based on data stream, equipment and medium. BACKGROUND

[0002] The tire pressure detection of a vehicle is one of the keys to ensure the safe operation of the vehicle. During the operation of the vehicle, the vehicle detects the tire pressure through the sensor installed on the wheel.

[0003] In the related art, the tire pressure monitoring system (TPMS) is usually used to realize the early warning of tire burst risk. The tire pressure monitoring system will issue an alarm when the tire pressure is lower than or higher than the preset threshold, reminding the driver to pay attention to the abnormal state of the tire pressure.

[0004] However, the above-mentioned method only distinguishes whether the tire pressure is in an abnormal state by setting one threshold, and the alarm after exceeding the threshold may cause the alarm to be not timely. SUMMARY

[0005] The present application provides a tire pressure risk detection method and device based on data stream, equipment and medium. The technical solution is as follows:

[0006] On the one hand, a tire pressure risk detection method based on data stream is provided, which comprises:

[0007] Receiving a tire pressure data stream transmitted in real-time streaming mode, the tire pressure data stream being data collected and uploaded by a target vehicle in real time and continuously, the target vehicle comprising a target tire;

[0008] Determining tire pressure difference data of the target tire based on the tire pressure data stream, the tire pressure difference data being used to indicate the tire pressure change of the target tire;

[0009] In the case that the tire pressure difference data is less than a preset difference threshold, accumulating the acquisition times of the tire pressure difference data;

[0010] In the case that the acquisition times reach a first quantity threshold, sending tire risk data, the tire risk data being used to indicate that the tire pressure of the target tire changes continuously and there is a tire burst risk.

[0011] On the other hand, a tire pressure risk detection device based on data stream is provided, which comprises:

[0012] A big data module is configured to receive a tire pressure data stream transmitted in real-time streaming mode, the tire pressure data stream being data collected and uploaded by a target vehicle in real-time and continuously, the target vehicle comprising a target tire;

[0013] The flow processing module is configured to determine tire pressure difference value data of the target tire based on the tire pressure data stream, the tire pressure difference value data being used to indicate a tire pressure change condition of the target tire; in a case where the tire pressure difference value data is less than a preset difference threshold, accumulate a number of times of acquisition of the tire pressure difference value data; and in a case where the number of times of acquisition reaches a first quantity threshold, send tire risk data, the tire risk data being used to indicate that the tire pressure of the target tire is continuously changing and there is a risk of tire burst.

[0014] In another aspect, a computer device is provided, the computer device comprising a processor and a memory, the memory having stored therein at least one instruction, at least one program, a code set or an instruction set, the at least one instruction, the at least one program, the code set or the instruction set being loaded and executed by the processor to implement the data stream-based tire pressure risk detection method according to any one of the above embodiments of the present application.

[0015] In another aspect, a computer-readable storage medium is provided, the storage medium having stored therein at least one instruction, at least one program, a code set or an instruction set, the at least one instruction, the at least one program, the code set or the instruction set being loaded and executed by a processor to implement the data stream-based tire pressure risk detection method according to any one of the above embodiments of the present application.

[0016] In another aspect, a computer program product or computer program is provided, the computer program product or computer program comprising computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions to cause the computer device to perform the data stream-based tire pressure risk detection method according to any one of the above embodiments.

[0017] The technical solutions provided by the present application at least have the following beneficial effects:

[0018] The tire pressure data stream of the vehicle is received in real time through real-time streaming, the difference between the tire pressure in the tire pressure data stream is continuously detected, a preset difference threshold is taken as a judgment limit, the number of times that the difference between the tire pressure is less than the preset difference threshold is continuously counted, and when the accumulated number of times indicates that the tire pressure of the target tire is continuously changing, a tire risk data is sent to alarm the tire burst risk. That is, through real-time streaming, the tire pressure of the vehicle tire can be obtained in real time, and the difference between the tire pressure can be continuously monitored. When the tire pressure is continuously reduced or continuously increased according to the difference, the vehicle is fed back with tire risk data, so as to indicate to the user through the tire risk data that the tire pressure of the tire is continuously reduced or continuously increased, and the tire burst warning is performed. Since the data transmission efficiency of the real-time streaming mode is high, real-time tire pressure monitoring can be realized, so that the tire pressure risk data can be provided in time. Moreover, the detection is for the case that the tire pressure is continuously changed, so compared with the detection mode of directly setting a threshold, the tire burst warning can be fed back to the user earlier, so that the vehicle reduces the possibility of tire burst. BRIEF DESCRIPTION OF DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. 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.

[0020] Figure 1 is a structural block diagram of a computer system provided by an exemplary embodiment of the present application;

[0021] Figure 2 is a flow chart of a tire pressure risk detection method based on data stream provided by an exemplary embodiment of the present application;

[0022] Figure 3 is a flow chart of a tire pressure risk detection method based on data stream provided by an exemplary embodiment of the present application;

[0023] Figure 4 is a flow chart of a tire pressure continuous reduction risk identification provided by an exemplary embodiment of the present application;

[0024] Figure 5 is a flow chart of configuration through a configuration page provided by an exemplary embodiment of the present application;

[0025] Figure 6 is a structural block diagram of a tire pressure risk detection device based on data stream provided by an exemplary embodiment of the present application;

[0026] Figure 7is a structure block diagram of a data flow-based tire pressure risk detection device provided by an example embodiment of the present application.

[0027] Figure 8 is a structure diagram of a server provided by an example embodiment of the present application. DETAILED DESCRIPTION

[0028] For the purpose, technical solutions and advantages of the present application to be clearer, the embodiments of the present application will be described in further detail below with reference to the drawings.

[0029] First, the terms involved in the embodiments of the present application are briefly introduced.

[0030] Internet of Vehicle (IoV): refers to connecting vehicles with the Internet through wireless communication technology, realizing data exchange and communication between vehicles, between vehicles and infrastructure, and between vehicles and users. Internet of Vehicles technology enables vehicles to interact with the external environment in real time, providing drivers and passengers with more intelligent, more convenient and safer driving experience. Internet of Vehicles technology is changing the automotive industry and driving mode, providing users with more intelligent, more convenient and safer travel experience, while also bringing new business opportunities and challenges for automobile manufacturers and service providers.

[0031] Data flow: refers to a series of continuous data elements generated in time sequence. In the field of computer science, data flow is often used to describe the transmission, processing and analysis process of dynamic data. Data flow can be continuous, real-time generated, or discrete, batch generated, depending on the specific application scenario and data source.

[0032] Stream processing: a data processing method designed for real-time data streams, which can process and analyze data in real time as data is continuously generated. Unlike batch processing, stream processing is a continuous and continuous data processing process, data is processed immediately without waiting for all data to arrive before processing. Stream processing has the following characteristics and advantages: real-time, low latency, continuity, dynamics, real-time decision-making and high throughput.

[0033] Flink computing architecture: an open source stream processing framework for large-scale real-time data processing and analysis. It provides high-performance, high-reliability and high-scalability stream data processing capabilities, supporting complex event-driven applications and batch processing jobs.

[0034] In the embodiments of the present application, the detection of the health status of the tire pressure of the vehicle is realized through the Internet of Vehicles system, so as to discover and prevent vehicle failures in time.

[0035] Figure 1A structural block diagram of a computer system provided by an example embodiment of the present application is shown. The computer system 100 includes a vehicle terminal 120 and a server 140.

[0036] The vehicle terminal 120 is a device installed on a vehicle for realizing connection and data exchange between the vehicle and an external system (such as a vehicle network, the Internet, a mobile communication network, etc.). The vehicle terminal 120 usually contains various sensors, communication modules and computing units, and is capable of monitoring the state, position and driving information of the vehicle in real time, and transmitting these data to the vehicle network or external system, while also being capable of receiving external instructions or data and performing corresponding operations or feedback according to the instructions.

[0037] In the embodiments of the present application, various sensors are also installed in the vehicle, such as an engine speed sensor, a temperature sensor, a tire pressure sensor, a speed sensor, a fuel tank sensor, a collision sensor, etc. The sensors installed on the vehicle transmit the detected data to the vehicle terminal 120 through wireless communication or wired communication.

[0038] The vehicle terminal 120 is connected to the server 140 through the Internet of Vehicles.

[0039] Those skilled in the art can know that the number of the above-mentioned devices can be more or less. For example, the above-mentioned devices can be only one, or the above-mentioned devices can be dozens or hundreds, or more. The number and type of devices are not limited in the embodiments of the present application.

[0040] The server 140 includes at least one of a server, multiple servers, a cloud computing platform and a virtualization center. The server 140 is used to provide background services for application programs supporting a three-dimensional virtual environment. Optionally, the server 140 undertakes the main computing work, and the vehicle terminal 120 undertakes the secondary computing work; or the server 140 undertakes the secondary computing work, and the vehicle terminal 120 undertakes the main computing work; or the server 140 and the vehicle terminal 120 adopt a distributed computing architecture for collaborative computing.

[0041] It is worth noting that the above-mentioned server 140 can be implemented as a physical server or a cloud server in the cloud. The cloud technology refers to a kind of hosting technology that unifies a series of resources such as hardware, software and network in a wide area network or a local area network to realize data calculation, storage, processing and sharing. The cloud technology is a general term for network technology, information technology, integration technology, management platform technology, application technology, etc. based on cloud computing business model application, which can form a resource pool, and be used on demand, flexibly and conveniently.

[0042] Illustratively, the vehicle terminal 120 continuously acquires the tire pressure data from the tire pressure sensor in real time, and transmits the tire pressure data to the server 140 in the form of a data stream through the Internet of Vehicles in a real-time streaming manner. After receiving the tire pressure data stream transmitted in the real-time streaming manner, the server 140 determines the tire pressure difference value data of the target tire based on the tire pressure data stream, the tire pressure difference value data is used to indicate the tire pressure change of the target tire, in the case that the tire pressure difference value data is less than a preset difference threshold, the acquisition number of the tire pressure difference value data is accumulated, in the case that the acquisition number reaches a first number threshold, the tire risk data is sent to the vehicle terminal 120, the tire risk data is used to indicate that the tire pressure of the target tire continuously changes and there is a risk of tire burst. After receiving the tire risk data, the vehicle terminal 120 prompts the user that there is a risk of tire burst of the target tire.

[0043] In some embodiments, the above-mentioned detection process of the tire pressure continuous change can also be completed by the vehicle terminal 120, which is not limited here.

[0044] In some embodiments, the above-mentioned server 140 can also be implemented as a node in a blockchain system.

[0045] In combination with the above-mentioned name introduction and application scenario, the data stream-based tire pressure risk detection method provided by the present application is described, which is taken as an example of being applied to the server, as shown in Figure 2 The method includes the following steps 210 to 240.

[0046] Step 210, receiving a tire pressure data stream transmitted in a real-time streaming manner.

[0047] In the embodiments of the present application, the above-mentioned tire pressure data stream includes data continuously collected and uploaded by a target vehicle in real time, wherein the target vehicle includes a target tire.

[0048] Illustratively, the above-mentioned real-time streaming manner is a way of real-time data transmission and processing, which is used to process the data stream generated in real time.

[0049] Optionally, the above-mentioned target vehicle can be implemented as a motor vehicle or a non-motor vehicle, i.e., the target vehicle is a vehicle configured with at least one tire.

[0050] In some embodiments, the target vehicle is loaded with a vehicle terminal, which is an electronic device in the target vehicle for providing functions and services, and the vehicle terminal can connect to the Internet through the Internet of Vehicles, realizing data exchange and communication between vehicles, between vehicles and infrastructure, and between vehicles and users.

[0051] Illustratively, the target tire is internally installed with a tire pressure sensor for monitoring the air pressure inside the tire.

[0052] In some embodiments, the vehicle terminal receives the tire pressure values continuously output by the tire pressure sensor, encapsulates the received tire pressure values, vehicle identification, tire identification and time stamp into first tire pressure data, forms the tire pressure data stream when transmitting the first tire pressure data in real-time streaming manner, and sends the tire pressure data stream to the backend server through the Internet of Vehicles. The vehicle identification is used to uniquely identify the target vehicle, the tire identification is used to uniquely identify the target tire corresponding to the tire pressure value, and the time stamp is used to indicate the time when the tire pressure value is collected.

[0053] In step 220, the tire pressure difference value data of the target tire is determined based on the tire pressure data stream.

[0054] In the embodiments of the present application, the tire pressure difference value data is used to indicate the tire pressure change of the target tire, that is, the tire pressure difference value data indicates the change of the tire pressure through the difference between the continuous tire pressure values.

[0055] Illustratively, the tire pressure data stream includes a plurality of first tire pressure data, and the first tire pressure data includes the vehicle identification of the collection vehicle, the tire identification of the collection tire, the tire pressure value, and the time stamp of the collection of the tire pressure value.

[0056] In some embodiments, the server receives a plurality of first tire pressure data uploaded by vehicles in the tire pressure data stream, that is, the server can simultaneously receive the first tire pressure data sent by a plurality of vehicles. Illustratively, the server determines at least two target tire pressure data corresponding to the target tire of the target vehicle from the plurality of first tire pressure data based on the vehicle identification of the collection vehicle and the tire identification of the collection tire, determines the difference between adjacent tire pressure values according to the time stamp in the at least two target tire pressure data, and obtains the tire pressure difference value data of the target tire.

[0057] In some embodiments, in order to improve the accuracy of the tire pressure difference value data, the server can perform data preprocessing on the tire pressure data stream after receiving the tire pressure data stream, that is, perform data preprocessing on the plurality of first tire pressure data to obtain second tire pressure data, and in the case that the number of second tire pressure data reaches a second quantity threshold, determine at least two target tire pressure data corresponding to the target tire of the target vehicle from the second tire pressure data based on the vehicle identification of the collection vehicle and the tire identification of the collection tire.

[0058] Optionally, the data preprocessing includes at least one of the following processing methods: outlier screening, missing value supplement / screening, duplicate value deduplication, data format adjustment, etc.

[0059] The outlier screening refers to the process of identifying and removing the first tire pressure data that deviates significantly from the overall mode of the tire pressure data stream during data preprocessing. The outliers usually refer to those tire pressure data with abnormally high or abnormally low values relative to the remaining first tire pressure data in the tire pressure data stream.

[0060] Optionally, the outlier screening method can be implemented as a Z-score method based on mean and standard deviation. Illustratively, the mean (μ) and standard deviation (σ) of the tire pressure data stream are calculated, for each first tire pressure data, the deviation from the mean is calculated and divided by the standard deviation to obtain the Z-score, and according to a set threshold value (e.g., 2 or 3), the first tire pressure data whose Z-score exceeds the threshold value is identified. If the Z-score is greater than the threshold value, the first tire pressure data is considered as an outlier. Wherein, since the tire pressure data stream is continuously received without boundary, when calculating the mean and standard deviation of the tire pressure data stream, a preset data amount threshold value can be set, i.e., the server performs outlier screening on the first tire pressure data after receiving the first tire pressure data meeting the above-mentioned preset data amount threshold value.

[0061] The missing value supplement / screening is a step of filling or replacing missing numerical values in the data processing process to ensure the integrity and availability of the data set. The missing value identification includes first tire pressure data missing identification and sub-data missing identification. Wherein, the first tire pressure data missing identification is implemented by determining whether the sequence of the first tire pressure data is complete according to the time stamp indicated by the first tire pressure data, so as to determine whether there is missing first tire pressure data; the sub-data missing identification is implemented by identifying a single first tire pressure data to determine whether it includes complete data composition, i.e., whether its data composition includes vehicle identification, tire identification, time stamp and tire pressure value.

[0062] In some embodiments, when there is a case of missing first tire pressure data, the missing value supplement is performed. Illustratively, the server determines the missing vehicle identification and tire identification corresponding to the time stamp, sends a request message for missing value supplement to the vehicle identification corresponding vehicle terminal through the Internet of Vehicles according to the vehicle identification and tire identification, and the vehicle terminal acquires the corresponding missing tire pressure data from the terminal storage space after receiving the above-mentioned request message, and sends the missing tire pressure data to the server through the Internet of Vehicles.

[0063] In some embodiments, when there is sub-data missing, the first tire pressure data with sub-data missing can be screened out.

[0064] The repeated value deduplication is used to identify and remove repeated records in the tire pressure data stream to ensure the accuracy and consistency of the data. Illustratively, the server screens the repeated first tire pressure data according to the vehicle identification, tire identification and time stamp in the first tire pressure data, i.e., when the vehicle identification, tire identification and time stamp of two first tire pressure data are all the same, the two are combined into one first tire pressure data.

[0065] Data format adjustment generally involves arranging tire pressure data into a form suitable for analysis, visualization, or modeling. Optionally, the data format adjustment includes rearranging data, converting data types, merging data sets, etc.

[0066] In embodiments of the present application, determining the difference between adjacent tire pressure values according to the timestamps in the at least two target tire pressure data is implemented as follows: determining at least two target tire pressure data {Cid, Tid, Time i , Stress i}, where Cid is used to indicate the vehicle identification of the target vehicle, Tid is used to indicate the tire identification of the target tire, Time i is used to indicate the timestamp, Stress i is used to indicate the tire pressure value, i is a positive integer, determining the order of the at least two target tire pressure data according to Time i , calculating the difference between Stress i and Stress i+1 corresponding to Time i and Time i+1 respectively to obtain tire pressure difference data Stress i+1 -Stress i . Wherein, when the above tire pressure difference data Stress i+1 -Stress i is positive, it means that the tire pressure is rising, and when the above Stress i+1 -Stress i is negative, it means that the tire pressure is falling. In some embodiments, since both the rising and falling of the tire pressure represent changes in the tire pressure, the absolute value can be taken, i.e., the tire pressure difference data is |Stress i+1 -Stress i |.

[0067] It is worth noting that when there is tire pressure difference data, it means that there is a difference between Stress i and Stress i+1 that is not zero.

[0068] Step 230, in the case where the tire pressure difference data is less than a preset difference threshold, accumulating the number of times of obtaining the tire pressure difference data.

[0069] In embodiments of the present application, when the tire pressure difference data is less than the preset difference threshold, the number of times of obtaining the tire pressure difference data is accumulated, thereby realizing the detection of the small amplitude change of the tire pressure. That is, when |Stress i+1 -Stress i | < k, n + 1, where k is a preset difference threshold, for example 1 bar, and n is the number of times of obtaining.

[0070] In some embodiments, the acquisition times corresponding to the target vehicle are reset when the ith tire pressure difference value corresponding to the target vehicle in the tire pressure data stream is greater than or equal to the preset difference threshold. That is, when the ith tire pressure difference value in the tire pressure difference value data belonging to the target vehicle is greater than or equal to the preset difference threshold, the variable corresponding to the acquisition times is reset.

[0071] At step 240, the tire risk data is sent when the acquisition times reach the first quantity threshold.

[0072] The tire risk data is used to indicate that the tire pressure of the target tire is continuously changing and there is a risk of tire burst. That is, when the acquisition times reach the first quantity threshold, it means that the tire pressure of the target tire is continuously decreasing, and therefore, the server reminds the user that the target tire of the target vehicle currently has a continuous tire pressure change by feeding back the tire risk data to the target vehicle, prompting the user that the target tire may have a certain risk of tire burst, so that the user can pay attention to the tire pressure problem of the target tire in time, to perform tire burst event warning and early handle the tire pressure problem of the target tire to reduce the occurrence of tire burst event. In one example, the first quantity threshold can be implemented as 4 times.

[0073] In some embodiments, when the tire pressure difference value is greater than or equal to the preset difference threshold, it means that the tire pressure of the target tire is changing rapidly, which means that the risk of tire burst of the target tire is very large, and therefore, in this case, the server directly sends the tire pressure warning information to the vehicle terminal, the tire pressure warning information is used to indicate that the target tire has a strong risk of tire burst.

[0074] Illustratively, the tire burst risk indicated in the tire risk data corresponds to a first risk degree, and the tire burst risk indicated in the tire pressure warning information corresponds to a second risk degree, wherein the second risk degree is greater than the first risk degree.

[0075] In some embodiments, the tire pressure sequence with the risk of tire burst can be predicted by a pre-trained risk detection model to determine the cause of the continuous tire pressure change. Illustratively, when the acquisition times reach the first quantity threshold, the tire pressure sequence of the target tire is acquired, the tire pressure sequence is the tire pressure value of the target tire participating in the continuous tire pressure change detection and the time stamp corresponding to the tire pressure value, the tire pressure sequence is input into the pre-trained risk detection model to obtain a risk prediction result, the risk prediction result is used to indicate the cause of the continuous tire pressure change, the tire risk data is generated according to the risk prompt information and the risk prediction result, the risk prompt information is used to prompt that the tire pressure of the target tire is continuously changing, and the tire risk data is sent to the target vehicle.

[0076] That is, the reason for the continuous decrease in tire pressure is first predicted by the pre-trained risk detection model, and the prediction result is fed back to the target vehicle, so that the user can quickly make a judgment and perform relevant maintenance, thereby reducing the risk caused by the continuous decrease in tire pressure.

[0077] Optionally, the risk detection model can be implemented by a neural network model such as a convolutional neural network (CNN), a feedforward neural network (FNN), a residual network (ResNet), a transformer, etc., which is not specifically limited here.

[0078] In summary, the tire pressure data stream of the vehicle is received in real time through the real-time streaming mode, the difference between the tire pressures in the tire pressure data stream is continuously detected, the preset difference threshold is used as the judgment limit, the number of times that the difference between the tire pressures is less than the preset difference threshold is continuously counted, and when the cumulative number of times indicates that the tire pressure of the target tire is continuously changing, the tire risk data is sent to alarm the tire burst risk. That is, through the real-time streaming mode, the tire pressure of the vehicle tire can be obtained in real time, and the difference between the tire pressures can be continuously monitored. When it is known from the difference that the tire pressure is continuously decreasing or continuously increasing, the tire risk data is fed back to the vehicle to indicate to the user that the tire pressure of the tire is continuously decreasing or continuously increasing through the tire risk data, and a tire burst warning is performed. Since the data transmission efficiency of the real-time streaming mode is high, real-time tire pressure monitoring can be achieved, so that tire pressure risk data can be provided in a timely manner. Moreover, the detection is for the case where the tire pressure is continuously changing, so compared with the detection method of directly setting a threshold, the tire burst warning can be fed back to the user earlier, so that the vehicle can reduce the possibility of tire burst.

[0079] In the embodiments of the present application, a plurality of functional modules are included in the server to implement the tire pressure risk detection process based on data stream, wherein the plurality of functional modules include a big data module, a message queue, and a stream processing module. Please refer to Figure 3 which shows a flowchart of the tire pressure risk detection method based on data stream provided by one exemplary embodiment of the present application, which includes the following steps 310-350.

[0080] Step 310: receiving, by the big data module, the tire pressure data stream sent by the target vehicle through the Internet of Vehicles.

[0081] In the embodiments of the present application, a sub-server cluster corresponding to a big data module is configured in the server environment, and the big data module is the basis and foundation of big data storage and calculation. The big data module is a functional module responsible for data input and output, and is mainly used to provide data input for the stream processing module, that is, to provide the first tire pressure data reported by the vehicle in real time.

[0082] Illustratively, the big data module is also used to store the operation processing result of the stream processing module to a database and / or a search engine library, for example, a Mysql database and Elasticsearch.

[0083] The data input and output processing of the server is realized by an independent big data module, and at least the following features exist: decoupling, separating the input / output of the first tire pressure data from the stream processing module, reducing the coupling between modules, and improving the robustness and maintainability of the entire system.

[0084] In step 320, the tire pressure data stream received by the big data module is cached through the message queue.

[0085] Illustratively, the big data module and the stream processing module communicate and cache data through the message queue, that is, the big data module sends the first tire pressure data in the received tire pressure data stream to the message queue, and the message queue caches the first tire pressure data.

[0086] By caching the tire pressure data stream through the message queue, the amount of data received by the stream processing module can be controlled, thereby realizing flow control and preventing the stream processing module from being overloaded in the case of high-concurrency tire pressure data stream.

[0087] Optionally, the message queue can be implemented as at least one of Kafka, RabbitMQ, RocketMQ, ActiveMQ, Redis, etc.

[0088] In step 330, when the stream processing module is in the module-on state, the stream processing module determines the tire pressure difference value data of the target tire based on the tire pressure data stream.

[0089] In the embodiments of the present application, a sub-server corresponding to the stream processing module is configured in the server environment, and the stream processing module is a module that realizes the calculation function of the tire pressure continuous decline risk identification algorithm. In some embodiments, the stream processing module can be implemented as a Flink computing architecture, which is an open source stream processing framework for large-scale real-time data processing and analysis, and provides high-performance, high-reliability and high-scalability stream data processing capabilities, and supports complex event-driven applications and batch processing jobs.

[0090] Illustratively, when the stream processing module is in the module open state, the stream processing module reads the first tire pressure data in the tire pressure data stream from the message queue.

[0091] In some embodiments, in order to improve the accuracy of the tire pressure difference value data, after receiving the tire pressure data stream, the stream processing module can perform data preprocessing on the tire pressure data stream, that is, perform data preprocessing on the plurality of first tire pressure data to obtain second tire pressure data, and in a case where the number of second tire pressure data reaches a second number threshold, determine at least two target tire pressure data corresponding to the target tire of the target vehicle from the second tire pressure data based on the vehicle identifier of the collection vehicle and the tire identifier of the collection tire.

[0092] Optionally, the above data preprocessing includes at least one of the following processing modes: outlier screening, missing value supplement / screening, duplicate value deduplication, data format adjustment, and empty row screening.

[0093] Illustratively, the tire pressure data stream includes a plurality of first tire pressure data, and the first tire pressure data includes a vehicle identifier of a collection vehicle, a tire identifier of a collection tire, a tire pressure value, and a timestamp of the tire pressure value collection. The stream processing module determines at least two target tire pressure data corresponding to the target tire of the target vehicle from the plurality of first tire pressure data based on the vehicle identifier of the collection vehicle and the tire identifier of the collection tire, determines the difference between adjacent tire pressure values according to the timestamps in the at least two target tire pressure data, and obtains the tire pressure difference value data of the target tire.

[0094] Step 340, through the stream processing module, in a case where the tire pressure difference value data is less than a preset difference value threshold, the number of times of obtaining the tire pressure difference value data is accumulated.

[0095] In the embodiments of the present application, when the tire pressure difference value data is less than the preset difference value threshold, the stream processing module accumulates the number of times of obtaining the tire pressure difference value data, thereby detecting the case of small amplitude change of the tire pressure.

[0096] Step 350, in a case where the number of times of obtaining reaches a first number threshold, the big data module sends tire risk data to the target vehicle.

[0097] The above tire risk data is used to indicate that the tire pressure of the target tire is continuously changing and there is a risk of tire burst.

[0098] In the embodiments of the present application, when the number of times of obtaining accumulated by the stream processing module reaches the first number threshold, the tire risk data is generated, the tire risk data includes the vehicle identifier of the target vehicle, the stream processing module sends the generated tire risk data to the big data module, and the big data module sends the above tire risk data to the target vehicle corresponding to the vehicle identifier according to the vehicle identifier indicated by the tire risk data.

[0099] In some embodiments, when the tire pressure difference value data is greater than or equal to the preset difference threshold value, it indicates that the tire pressure of the target tire is changing rapidly, and it indicates that the current target tire has a high risk of tire burst. Therefore, in this case, the flow processing module sends tire pressure warning information to the big data module, the tire pressure warning information is used to indicate that the target tire has a strong risk of tire burst, and the tire pressure warning information includes the vehicle identifier of the target vehicle. The big data module receives the tire pressure warning information according to the vehicle identifier indicated by the tire pressure warning information, and sends the tire pressure warning information to the target vehicle corresponding to the vehicle identifier.

[0100] In one example, please refer to Figure 4 which shows a vehicle tire pressure continuous decline risk identification flowchart provided by an exemplary embodiment of the present application. After receiving the tire pressure data stream, the big data platform 410 sends the tire pressure data stream to the message queue 420, the message queue 420 buffers the first tire pressure data in the tire pressure data stream, and the flow processing module 430 reads the first tire pressure data from the message queue 420 and performs the following steps: S431, tire pressure difference value data calculation; S432, determining whether the tire pressure difference value data is less than 1 bar, if yes, performing S433, if no, performing S434; S433, counting n+1; S434, resetting the count; S435, determining whether n is greater than or equal to 4, if yes, performing S436, if no, performing S431; S436, outputting tire risk data.

[0101] In the embodiments of the present application, the tire pressure continuous decline risk identification algorithm is implemented by the flow processing module. Since the algorithm is implemented in the server, the vehicle only needs to upload the tire pressure data stream to the server and does not need to perform specific data processing. Therefore, the power consumption of the vehicle is low when implementing the tire pressure continuous decline warning, that is, the tire pressure continuous decline warning is implemented by consuming very low power.

[0102] In some embodiments, the server is further connected with a control terminal for controlling the cluster of sub-servers in the server. Illustratively, after sending the tire risk data to the target vehicle, the target vehicle is added as a candidate vehicle in a running log, and vehicle information of the target vehicle and tire risk data corresponding to the target vehicle are added in the running log. The running log is used to record information of a plurality of candidate vehicles. The control terminal sends a risk vehicle acquisition request for requesting to acquire associated information of the candidate vehicle with a tire pressure change risk. The running log is queried based on the risk vehicle acquisition request to obtain vehicle information of the plurality of candidate vehicles. Position information of a current location of each of the plurality of candidate vehicles is collected. A risk visualization map is generated based on the position information. The risk visualization map is used to indicate a distribution of the candidate vehicles in a map. The vehicle information of the plurality of candidate vehicles and the risk visualization map are sent to the control terminal. The control terminal generates an assistance plan based on the vehicle information of the plurality of candidate vehicles and the risk visualization map. The assistance plan is used to provide tire change assistance to the candidate vehicles.

[0103] Optionally, the vehicle information includes vehicle identification (such as a vehicle identification number (vin code)), position information, vehicle battery remaining capacity, mileage, tire pressure change information, and other related information.

[0104] Illustratively, after receiving the vehicle information of the plurality of candidate vehicles and the risk visualization map, a developer can troubleshoot vehicles with safety hazards based on the data. In some embodiments, the control terminal can further generate an assistance plan based on the vehicle information of the plurality of candidate vehicles and the risk visualization map.

[0105] Optionally, the assistance plan includes at least one of assistance route planning, assistance demand, and assistance priority of the candidate vehicles. The assistance route planning is a best path planned for each candidate vehicle in need of assistance to reach a route in the shortest time and safest way. The assistance demand is a maintenance service type required by the candidate vehicle, such as replacing a tire, inflating a tire, etc. The assistance priority is a priority ranking between the plurality of candidate vehicles according to a risk degree, and those candidate vehicles in a high risk are given priority.

[0106] In summary, the tire pressure data stream of the vehicle is received in real time through the real-time streaming mode, the difference between the tire pressure in the tire pressure data stream is continuously detected, the preset difference threshold is taken as the judgment limit, the number of times that the difference between the tire pressure is less than the preset difference threshold is continuously counted, and when the accumulated number of times indicates that the tire pressure of the target tire is continuously changing, the tire risk data is sent to alarm the tire burst risk. That is, through the real-time streaming mode, the tire pressure of the vehicle tire can be obtained in real time, and the difference between the tire pressure can be continuously monitored. When the tire pressure is continuously reduced or continuously increased according to the difference, the vehicle is fed back with the tire risk data, so as to indicate to the user through the tire risk data that the tire pressure of the tire is continuously reduced or continuously increased, and the tire burst warning is performed. Since the data transmission efficiency of the real-time streaming mode is high, real-time tire pressure monitoring can be realized, so that the tire pressure risk data can be provided in time, and since the detection is performed on the condition that the tire pressure is continuously changed, compared with the detection mode of directly setting the threshold, the tire burst warning can be fed back to the user earlier, so that the vehicle reduces the possibility of tire burst.

[0107] In some optional embodiments, the server further comprises a remote access and cluster control module, which is configured to provide remote access function to the stream processing module and control function to the sub-server cluster.

[0108] Optionally, the remote access and cluster control module provides an interface for remotely logging in the sub-server cluster using a related protocol, and can submit commands to the sub-server cluster and execute the commands, and obtain the execution results. The sub-server cluster includes the sub-servers corresponding to the big data module, the message queue and the stream processing module. In an example, the sub-server cluster can be a server cluster managed and scheduled by a Yet Another Resource Negotiator (YARN) manager.

[0109] Optionally, the remote access and cluster control module provides the functions of uploading and downloading file resources. The file resources are stored in a Hadoop Distributed FileSystem (HDFS) in the server. In some embodiments, the file resources include cached data of the tire pressure data stream, cached data of the tire pressure difference data, cached data of the tire risk data, etc.

[0110] Optionally, the remote access and cluster control module provides functions of starting / closing the sub-server cluster, submitting a Flink job task to the cluster and executing, wherein the Flink job task is used to indicate the algorithm content of the tire pressure continuous decline risk identification algorithm, the preset difference threshold value in the tire pressure continuous decline risk identification algorithm, the numerical setting of the first quantity threshold value, the module opening and closing of the stream processing module, etc.

[0111] Optionally, the remote access and cluster control module provides functions of opening a configuration page to view the running state of the cluster job and the storage state of the cluster file resource. Illustratively, the developer can connect the remote access and cluster control module through the provided configuration page to realize the above functions.

[0112] In some embodiments, the configuration page provides at least one of the following functions: 1, binding menu bar events, button events to jump to the server operation page; 2, providing form components for filling in address, port number, username, password information, calling library functions to remotely log in the server; 3, uploading Flink task jar package to the server and executing 4, providing button components, binding HDFS file resource operations; 5, providing button components, binding YARN cluster start-stop operations; 6, providing button components, binding configuration page opening operations.

[0113] In one example, please refer to Figure 5 which shows a flowchart of configuration through a configuration page provided by an exemplary embodiment of the present application, which includes: S501, logging into the system; S502, adding data source input and data source output of the stream processing module in the configuration interface; S503, configuring the start parameters of the tire pressure risk identification task, starting the tire pressure risk identification task in the stream processing module; S504, the tire pressure risk identification task is executed and completed, returning the data number and running log; S505, displaying the data display interface; S506, exporting vehicle information; S507, investigating and checking the vehicle with safety hazards; S508, exiting the system.

[0114] Among them, the data display interface is used to display the data generated in the process of implementing the tire pressure continuous decline risk identification algorithm by the stream processing module. In some embodiments, the data display interface is displayed by a control terminal, which is a terminal operated by a developer. Optionally, the control terminal can be realized as at least one of a desktop computer, a smart phone, a tablet computer, etc.

[0115] The developer can export vehicle information through the data display interface, and optionally, the vehicle information includes the vin code, location information, vehicle battery remaining capacity, mileage, tire pressure continuous change information, etc. related information of the vehicle for which the tire pressure risk identification is performed.

[0116] Illustratively, the developer can screen the vehicle with safety risks according to the vehicle information described above. In some embodiments, a data screening function is provided in the data display interface, and the developer can screen the vehicle according to at least one of the vehicle information described above through the data screening function, so as to determine the vehicle with safety risks.

[0117] It should be noted that, before collecting the relevant data of the user and in the process of collecting the relevant data of the user, a prompt interface, a pop-up window or output voice prompt information can be displayed, which is used to prompt the user that the relevant data of the user is currently being collected, so that the application only starts to perform the related steps of obtaining the relevant data of the user after obtaining the confirmation operation of the user to the prompt interface or the pop-up window, otherwise (i.e. without obtaining the confirmation operation of the user to the prompt interface or the pop-up window), ending the related steps of obtaining the relevant data of the user, that is, not obtaining the relevant data of the user. In other words, all the user data collected by the application is collected under the condition that the user agrees and authorizes, and the collection, use and processing of the relevant user data need to comply with the relevant laws, regulations and standards of the country and region.

[0118] Please refer to Figure 6 which shows a structure block diagram of a data flow based tire pressure risk detection device provided by an exemplary embodiment of the application, the device includes the following modules:

[0119] The big data module 610 is configured to receive a tire pressure data stream transmitted in a real-time streaming manner, the tire pressure data stream being data collected and uploaded by a target vehicle in real time and continuously, and the target vehicle including a target tire.

[0120] The stream processing module 620 is configured to determine tire pressure difference value data of the target tire based on the tire pressure data stream, the tire pressure difference value data being used to indicate a tire pressure change of the target tire; in a case where the tire pressure difference value data is less than a preset difference threshold value, accumulate a number of times of acquisition of the tire pressure difference value data; and in a case where the number of times of acquisition reaches a first number threshold value, send tire risk data, the tire risk data being used to indicate that the tire pressure of the target tire is continuously changing and there is a risk of tire burst.

[0121] In some optional embodiments, the tire pressure data stream includes a plurality of first tire pressure data, and the first tire pressure data includes a vehicle identifier of a collecting vehicle, a tire identifier of a collecting tire, a tire pressure value and a timestamp of the tire pressure value.

[0122] The stream processing module 620 is further configured to determine, based on the vehicle identifier of the collection vehicle and the tire identifier of the collection tire, at least two target tire pressure data corresponding to the target tire of the target vehicle from the plurality of first tire pressure data; and determine, according to time stamps in the at least two target tire pressure data, a difference value between adjacent tire pressure values to obtain tire pressure difference value data of the target tire.

[0123] In some optional embodiments, the stream processing module 620 is further configured to perform data preprocessing on the plurality of first tire pressure data to obtain second tire pressure data, wherein the data preprocessing includes at least one of outlier exclusion, missing value supplementation, duplicate value deduplication, and data format adjustment; and in a case where a quantity of the second tire pressure data reaches a second quantity threshold, determine, based on the vehicle identifier of the collection vehicle and the tire identifier of the collection tire, at least two target tire pressure data corresponding to the target tire of the target vehicle from the second tire pressure data.

[0124] In some optional embodiments, the stream processing module 620 is further configured to reset the acquisition frequency corresponding to the target vehicle in a case where the i th tire pressure difference value data corresponding to the target vehicle in the tire pressure data stream is greater than or equal to the preset difference value threshold.

[0125] The big data module 610 is further configured to receive the tire pressure data stream sent by the target vehicle through the Internet of Vehicles.

[0126] As shown in Figure 7 The apparatus further includes:

[0127] The message queue module 630 is configured to cache the tire pressure data stream received by the big data module.

[0128] The stream processing module 620 is further configured to determine, by the stream processing module, the tire pressure difference value data of the target tire based on the tire pressure data stream in a case where the stream processing module is in a module-on state.

[0129] In some optional embodiments, the apparatus further includes:

[0130] The model processing module 640 is configured to, in a case where the acquisition frequency reaches a first quantity threshold, acquire a tire pressure sequence of the target tire, the tire pressure sequence being a tire pressure value participating in tire pressure continuous change detection and a time stamp corresponding to the tire pressure value; input the tire pressure sequence into a pre-trained risk detection model to obtain a risk prediction result, the risk prediction result being used to indicate a reason for tire pressure continuous change; and generate the tire risk data according to risk prompt information and the risk prediction result, the risk prompt information being used to prompt that the tire pressure of the target tire is continuously changing.

[0131] The big data module 610 is further configured to send the tire risk data to the target vehicle.

[0132] In some optional embodiments, the stream processing module 620 is further configured to add, in a running log, the target vehicle as a candidate vehicle, vehicle information of the target vehicle, and tire risk data corresponding to the target vehicle, the running log being used to record information of a plurality of candidate vehicles.

[0133] The big data module 610 is further configured to receive a risk vehicle acquisition request sent by a control terminal, the risk vehicle acquisition request being used to request to acquire associated information of the candidate vehicle that has a tire pressure continuous change risk.

[0134] The stream processing module 620 is further configured to query the running log based on the risk vehicle acquisition request to obtain vehicle information of the plurality of candidate vehicles, respectively collect position information of current positions of the plurality of candidate vehicles, and generate a risk visualization map based on the position information, the risk visualization map being used to indicate distribution of the candidate vehicles in a map.

[0135] The big data module 610 is further configured to send the vehicle information of the plurality of candidate vehicles and the risk visualization map to the control terminal, and the control terminal is configured to generate an aid plan according to the vehicle information of the plurality of candidate vehicles and the risk visualization map, the aid plan being used to provide a tire burst aid for the candidate vehicles.

[0136] It should be noted that the data stream-based tire pressure risk detection apparatus provided in the above embodiments is only used as an example for the division of the above functional modules, and in actual applications, the above functions can be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the above-described functions. In addition, the data stream-based tire pressure risk detection apparatus and the data stream-based tire pressure risk detection method provided in the above embodiments belong to the same concept, and the specific implementation process is detailed in the method embodiments, which will not be repeated here.

[0137] Figure 8 A structure schematic diagram of a server provided in an example embodiment of the present application is shown. Specifically, it includes the following structures.

[0138] The server 800 includes a central processing unit (CPU) 801, a system memory 804, including a random access memory (RAM) 802 and a read-only memory (ROM) 803, and a system bus 805 that couples the system memory 804 to the central processing unit 801. The server 800 also includes a mass storage device 806 for storing an operating system 813, application programs 814, and other program modules 815.

[0139] The mass storage device 806 connects to the central processing unit 801 through a mass storage controller (not shown) connected to the system bus 805. The mass storage device 806 and its associated computer-readable media provide nonvolatile storage for the server 800. That is, the mass storage device 806 can include a computer-readable medium (not shown) such as a hard disk or a compact disc read-only memory (CD-ROM) drive.

[0140] Without loss of generality, computer-readable media can include computer storage media and communication media. Computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Computer storage media includes RAM, ROM, erasable programmable read only memory (EPROM), electrically erasable programmable read only memory (EEPROM), flash memory or other solid state memory technology, CD-ROM, digital versatile disks (DVD), or other optical storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices. Computer storage media would not, however, include communication media including wired or wireless signaling media that communicate program code in a modulated data signal. The system memory 804 and mass storage device 806 described above can collectively be referred to as memory.

[0141] According to various embodiments of the present application, the server 800 can also run over a network connection to a remote computer in a network such as the Internet. That is, the server 800 can be connected to a network 812 through a network interface unit 811 connected to the system bus 805, or can use the network interface unit 811 to connect to other types of networks or remote computer systems (not shown).

[0142] The memory further includes one or more programs stored therein, which are configured to be executed by the CPU.

[0143] Embodiments of the present application further provide a computer device including a processor and a memory having at least one instruction, at least one program, a code set or an instruction set stored therein, the at least one instruction, at least one program, code set or instruction set being loaded and executed by the processor to implement the data flow based tire pressure risk detection method provided by any of the above method embodiments. Alternatively, the computer device can be a terminal or a server.

[0144] Embodiments of the present application further provide a computer readable storage medium having at least one instruction, at least one program, a code set or an instruction set stored thereon, the at least one instruction, at least one program, code set or instruction set being loaded and executed by the processor to implement the data flow based tire pressure risk detection method provided by any of the above method embodiments.

[0145] Embodiments of the present application further provide a computer program product or computer program including computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer readable storage medium, and the processor executes the computer instructions to cause the computer device to perform the data flow based tire pressure risk detection method described in any of the above embodiments.

[0146] Alternatively, the computer readable storage medium can include a read only memory (ROM), a random access memory (RAM), a solid state disk (SSD) or an optical disk. The random access memory can include a resistance random access memory (ReRAM) and a dynamic random access memory (DRAM). The above-mentioned serial numbers of the embodiments of the present application are only for description, and do not represent the advantages or disadvantages of the embodiments.

[0147] Those skilled in the art can understand that all or part of the steps of the above-mentioned embodiments can be completed by hardware, or by programs instructing relevant hardware to complete, and the programs can be stored in a computer readable storage medium. The storage medium mentioned above can be a read only memory, a magnetic disk or an optical disk.

[0148] The above merely provides the optional embodiments of the present application, and is not intended to limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A data stream based tire pressure risk detection method, characterized in that, The method comprises: receiving a tire pressure data stream transmitted in real-time streaming mode, the tire pressure data stream comprising data collected and uploaded by a target vehicle in real time and continuously, the target vehicle comprising a target tire; determining tire pressure difference data of the target tire based on the tire pressure data stream, the tire pressure difference data being used to indicate a tire pressure change condition of the target tire; in a case where the tire pressure difference data is less than a preset difference threshold, accumulating a number of times of acquisition of the tire pressure difference data; in a case where the number of times of acquisition reaches a first quantity threshold, acquiring a tire pressure sequence of the target tire, the tire pressure sequence being a tire pressure value of the target tire participating in tire pressure continuous change detection and a time stamp corresponding to the tire pressure value; inputting the tire pressure sequence into a pre-trained risk detection model to obtain a risk prediction result, the risk prediction result being used to indicate a reason for tire pressure continuous change; generating tire risk data according to risk prompt information and the risk prediction result, the risk prompt information being used to prompt that the tire pressure of the target tire has a continuous change condition; sending the tire risk data to the target vehicle, the tire risk data being used to indicate that the tire pressure of the target tire has a continuous change and has a risk of tire burst; in a running log, taking the target vehicle as a candidate vehicle, adding vehicle information of the target vehicle and tire risk data corresponding to the target vehicle, the running log being used to record information of a plurality of candidate vehicles; receiving a risk vehicle acquisition request sent by a control terminal, the risk vehicle acquisition request being used to request acquisition of associated information of the candidate vehicle having a risk of tire pressure continuous change; querying the running log based on the risk vehicle acquisition request to obtain vehicle information of the plurality of candidate vehicles; respectively collecting location information of a current location of the plurality of candidate vehicles; generating a risk visualization map based on the location information, the risk visualization map being used to indicate a distribution condition of the candidate vehicles in a map; sending the vehicle information of the plurality of candidate vehicles and the risk visualization map to the control terminal; wherein the control terminal is used to generate an assistance plan according to the vehicle information of the plurality of candidate vehicles and the risk visualization map, the assistance plan being used to provide tire burst assistance to the candidate vehicles.

2. The method of claim 1, wherein, The tire pressure data stream comprises a plurality of first tire pressure data, the first tire pressure data comprising vehicle identification of a collection vehicle, tire identification of a collection tire, a tire pressure value and a time stamp of collection of the tire pressure value; The method comprises: determining at least two target tire pressure data corresponding to the target tire of the target vehicle from the plurality of first tire pressure data based on the vehicle identification of the collection vehicle and the tire identification of the collection tire; determining a difference value between adjacent tire pressure values according to the time stamps in the at least two target tire pressure data to obtain tire pressure difference data of the target tire.

3. The method of claim 2, wherein, The determining of the at least two target tire pressure data corresponding to the target tire of the target vehicle from the plurality of first tire pressure data based on the vehicle identifier of the collection vehicle and the tire identifier of the collection tire comprises: The data preprocessing of the plurality of first tire pressure data comprises at least one of outlier screening, missing value supplement, duplicate value deduplication, and data format adjustment. In a case where the number of the second tire pressure data reaches a second number threshold, the at least two target tire pressure data corresponding to the target tire of the target vehicle are determined from the second tire pressure data based on the vehicle identifier of the collection vehicle and the tire identifier of the collection tire.

4. The method according to any one of claims 1 to 3, characterized in that, The accumulating of the acquisition number of the tire pressure difference value data in a case where the tire pressure difference value data is less than a preset difference threshold further comprises: In a case where the i-th tire pressure difference value data corresponding to the target vehicle in the tire pressure data stream is greater than or equal to the preset difference threshold, the acquisition number corresponding to the target vehicle is reset.

5. The method according to any one of claims 1 to 3, characterized in that, The receiving of the tire pressure data stream transmitted in a real-time streaming manner comprises: The tire pressure data stream transmitted by the target vehicle through the Internet of Vehicles is received by a big data module; The tire pressure data stream received by the big data module is data cached by a message queue; The determining of the tire pressure difference value data of the target tire based on the tire pressure data stream comprises: In a case where a stream processing module is turned on, the tire pressure difference value data of the target tire is determined by the stream processing module based on the tire pressure data stream.

6. A data stream based tire pressure risk detection apparatus, characterized by, The device comprises: a big data module configured to receive a tire pressure data stream transmitted in a real-time streaming manner, the tire pressure data stream being data collected and uploaded by a target vehicle in real time and continuously, the target vehicle comprising a target tire; a stream processing module configured to determine tire pressure difference value data of the target tire based on the tire pressure data stream, the tire pressure difference value data being used to indicate a tire pressure change of the target tire; and accumulate an acquisition number of the tire pressure difference value data in a case where the tire pressure difference value data is less than a preset difference threshold; a model processing module configured to, in a case where the acquisition number reaches a first number threshold, acquire a tire pressure sequence of the target tire, the tire pressure sequence being a tire pressure value of the target tire participating in tire pressure continuous change detection and a timestamp corresponding to the tire pressure value; input the tire pressure sequence into a pre-trained risk detection model to obtain a risk prediction result, the risk prediction result being used to indicate a reason for tire pressure continuous change; and generate tire risk data according to risk prompt information and the risk prediction result, the risk prompt information being used to prompt that the tire pressure of the target tire is continuously changing; the big data module is further configured to send the tire risk data to the target vehicle, the tire risk data being used to indicate that the tire pressure of the target tire is continuously changing and there is a risk of tire burst; and The flow processing module is further configured to add, in a running log, the target vehicle as a candidate vehicle, vehicle information of the target vehicle, and tire risk data corresponding to the target vehicle, and the running log is used to record information of a plurality of candidate vehicles; The big data module is further configured to receive a risk vehicle acquisition request sent by a control terminal, the risk vehicle acquisition request being used to request to acquire associated information of the candidate vehicle that has a tire pressure continuous change risk; The flow processing module is further configured to query the running log based on the risk vehicle acquisition request to obtain vehicle information of the plurality of candidate vehicles, respectively collect position information of current positions of the plurality of candidate vehicles, and generate a risk visualization map based on the position information, the risk visualization map being used to indicate a distribution of the candidate vehicles in a map; The big data module is further configured to send, to the control terminal, the vehicle information of the plurality of candidate vehicles and the risk visualization map, and the control terminal is configured to generate an assistance plan based on the vehicle information of the plurality of candidate vehicles and the risk visualization map, and the assistance plan is used to provide a tire burst assistance for the candidate vehicles.

7. A computer device, comprising: The computer device includes a processor and a memory, and the memory stores at least one program, the at least one program is loaded and executed by the processor to implement the data flow-based tire pressure risk detection method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer readable storage medium stores at least one program code, and the program code is loaded and executed by the processor to implement the data flow-based tire pressure risk detection method according to any one of claims 1 to 5.

Images