WO2024255614A1 - 复杂事件处理方法、电子设备、存储介质及车辆 - Google Patents

复杂事件处理方法、电子设备、存储介质及车辆 Download PDF

Info

Publication number
WO2024255614A1
WO2024255614A1 PCT/CN2024/096657 CN2024096657W WO2024255614A1 WO 2024255614 A1 WO2024255614 A1 WO 2024255614A1 CN 2024096657 W CN2024096657 W CN 2024096657W WO 2024255614 A1 WO2024255614 A1 WO 2024255614A1
Authority
WO
WIPO (PCT)
Prior art keywords
event
complex
combined
complex event
processing method
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2024/096657
Other languages
English (en)
French (fr)
Inventor
聂松洋
李明骏
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
NIO Technology Anhui Co Ltd
Original Assignee
NIO Technology Anhui Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by NIO Technology Anhui Co Ltd filed Critical NIO Technology Anhui Co Ltd
Publication of WO2024255614A1 publication Critical patent/WO2024255614A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/54—Interprogram communication
    • G06F9/542—Event management; Broadcasting; Multicasting; Notifications
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/02—Knowledge representation; Symbolic representation
    • G06N5/022—Knowledge engineering; Knowledge acquisition
    • G06N5/025—Extracting rules from data

Definitions

  • the present invention relates to the field of data processing, and specifically provides a complex event processing method, electronic equipment, storage medium and vehicle.
  • Complex event processing is the main technique for extracting information.
  • Complex event processing is a data processing technique based on a set of predefined rules that dictate how a data stream should be processed and what new event streams should be generated as output.
  • Events can be many independent events of interest or complex events that correspond to specific situations or patterns of the business.
  • the present invention provides a complex event processing method, an electronic device, a storage medium and a vehicle.
  • the present invention provides a complex event processing method, the method comprising: monitoring original perception events; obtaining complex events based on the original perception events; matching the complex events with preset rules in a rule library; and determining a processing result of the complex event based on the matching result.
  • the method before monitoring the original perception event, the method also includes: obtaining preset rules; storing the preset rules in a rule library; wherein the preset rules include at least an event window, a start event, an end event, context information and perception judgment logic.
  • the original perception event includes a first original perception event and a second original perception event
  • the complex event includes a first combined event and a second combined event
  • obtaining the complex event based on the original perception event includes: filtering or combining the first original perception event to obtain the first combined event; within the event window, filtering or combining the second original perception event that occurs continuously to obtain a second combined event.
  • matching the complex event with the preset rules in the rule base includes: when the first combined event is obtained, activating a non-deterministic state machine, obtaining a first state of the non-deterministic state machine, and matching the rule corresponding to the first combined event in the preset rules based on the first state; when the second combined event is obtained, obtaining a second state of the non-deterministic state machine, and matching the rule corresponding to the second combined event in the preset rules based on the second state.
  • determining the processing result of the complex event based on the matching result includes: updating context information based on the rules corresponding to the first combined event and the rules corresponding to the second combined event; and obtaining the processing result of the complex event based on the updated context information and the perception judgment logic in the rule base.
  • the first combination event includes at least one of the main driver's door opening, the front passenger door opening, the rear left door opening, and the rear right door opening;
  • the second combination event includes at least one of the main driver's door closing, the front passenger door closing, the rear left door closing, and the rear right door closing;
  • the method also includes: when the first combination event is obtained, recording the number of people in the first car; when the second combination event is obtained, recording the number of people in the second car.
  • the processing result of the complex event is determined according to the matching result.
  • the result includes: updating context information based on the rule corresponding to the first combination event, the rule corresponding to the second combination event, and the combination of the number of people in the first car and the number of people in the second car; determining the difference in the number of people based on the updated context information; judging whether the difference in the number of people is greater than a preset threshold; if so, determining that the processing result of the complex event is that a single person is boarding the car; if not, determining that the processing result of the complex event is that multiple people are boarding the car.
  • an electronic device comprising at least one processor and at least one storage device, wherein the storage device is suitable for storing a plurality of program codes, wherein the program codes are suitable for being loaded and run by the processor to execute any one of the complex event processing methods described above.
  • a computer-readable storage medium wherein a plurality of program codes are stored in the computer-readable storage medium, wherein the program codes are suitable for being loaded and run by a processor to execute any of the complex event processing methods described above.
  • a vehicle comprising a vehicle body, at least one processor and at least one storage device, wherein the storage device is suitable for storing multiple program codes, and characterized in that the program code is suitable for being loaded and run by the processor to execute any of the complex event processing methods described above.
  • the complex event processing method of the present invention includes monitoring the original perception event; obtaining the complex event based on the original perception event; matching the complex event with the preset rules in the rule library; and determining the processing result of the complex event according to the matching result. In this way, any complex event can be processed based on the original perception event, thereby expanding the event capability library of the system that understands me, reducing the development cost, and improving the processing efficiency of complex events.
  • FIG1 is a schematic flow chart of main steps of a complex event processing method according to an embodiment of the present invention.
  • FIG2 is a schematic diagram of a process of acquiring complex events based on original sensed events in one embodiment
  • FIG3 is a schematic diagram of a process of matching a complex event with a preset rule in a rule base in one embodiment
  • FIG4 is a schematic diagram of a process of determining a processing result of a complex event according to a matching result in one embodiment
  • FIG5 is a schematic diagram of a complete process of complex event processing in one embodiment
  • FIG. 6 is a schematic structural diagram of an electronic device in an embodiment.
  • module and “processor” may include hardware, software or a combination of the two.
  • a module may include hardware circuits, various suitable sensors, communication ports, and memories, and may also include software parts, such as program codes, or a combination of software and hardware.
  • the processor may be a central processing unit, a microprocessor, an image processor, a digital signal processor, or any other suitable processor.
  • the processor has data and/or signal processing functions.
  • the processor may be implemented in software, hardware, or a combination of the two.
  • Non-temporary computer-readable storage media include any suitable medium that can store program codes, such as a magnetic disk, a hard disk, an optical disk, a flash memory, a read-only memory, a random access memory, and the like.
  • a and/or B means all possible combinations of A and B, such as only A, only B, or A and B.
  • the term "at least one A or B” or “at least one of A and B” has a similar meaning to “A and/or B", and may include only A, only B, or A and B.
  • the singular terms “one” and “the” may also include plural forms.
  • the present application provides a complex event processing method, electronic device, storage medium and vehicle, including monitoring original perception events; obtaining complex events based on original perception events; matching complex events with preset rules in a rule library; determining complex events based on matching results.
  • any complex event can be processed based on the original perception event, thereby expanding the event capability library of the system that understands me, reducing development costs, and improving the processing efficiency of complex events.
  • FIG. 1 is a schematic flow chart of main steps of a complex event processing method according to an embodiment of the present invention.
  • the complex event processing method in the embodiment of the present invention mainly includes the following steps S100 to S400 .
  • Step S100 monitor original perception events.
  • Step S200 Acquire a complex event based on the original perceived event.
  • Step S300 Match the complex event with the preset rules in the rule base.
  • Step S400 determining the processing result of the complex event according to the matching result.
  • any complex event can be processed based on the original perception event, thereby expanding the event capability library of the system that understands me, reducing the development cost, and improving the processing efficiency of complex events.
  • the method before monitoring the original perception event, the method also includes: obtaining preset rules; storing the preset rules in a rule library; wherein the preset rules include at least an event window, a start event, an end event, context information and perception judgment logic.
  • the vehicle may include an engine module that understands me.
  • An event engine is built in the engine module.
  • the preset rules are registered in the event engine.
  • the preset rules are described as follows. First, the event window (span) is defined as 60s, indicating that the maximum duration of the event is 60s; then the start event (begin), middle event (middle, there may be no middle event), end event (end) and event triggering logic of the combined event are defined. It needs to be executed strictly in the sequence of the start event, middle event and end event. The above process can successfully implement the construction of complex events. Next, it is necessary to define how to throw events.
  • Throwing events is the process of obtaining the processing results of complex events.
  • Each thrown event needs to have a perception judgment logic. Only after the perception judgment logic is passed, can it be thrown. You can get the actual thrown event.
  • the current number of people in the vehicle can be used as an example of the context information, but is not limited thereto.
  • the following rule can be used as an example of the preset rule, but is not limited thereto.
  • Pre-loading preset rules into the rule base provides basic support for the rapid and efficient processing of each subsequent complex event.
  • the raw perception event is an unprocessed event generated from the cockpit system and is an atomic event that cannot be decomposed.
  • the original event sensing module may sense the original sensing event in the cockpit.
  • at least one of the main driver's door opening, the co-driver's door opening, the rear left door opening, the rear right door opening, the main driver's door closing, the co-driver's door closing, the rear left door closing, and the rear right door closing may be used as an example of the original sensing event, but is not limited thereto.
  • step S100 is a further description of step S100
  • step S200 is a further description of step S200 .
  • the original perception event includes a first original perception event and a second original perception event.
  • the types of the initial perception event and the second original perception event are different.
  • a complex event is an event that describes a series of events that occur according to pre-written preset rules.
  • the complex event includes a first combined event and a second combined event.
  • step S200 can be implemented through the following steps S201 to S202 .
  • Step S201 Filter or combine the first original perception events to obtain the first combined events.
  • first original events are filtered or combined to obtain a first combined event.
  • the first original event may include any one of the main driver's door opening, the co-driver's door opening, the rear left door opening, and the rear right door opening, and the combination of these original events constitutes the first combined event.
  • Other invalid events in the vehicle door opening process may also be filtered.
  • Step S202 within the event window, filtering or combining the second original perception events that occur continuously to obtain a second combined event.
  • the second original event that is different from the first original event type and occurs continuously is combined or filtered to obtain the second combined event.
  • the second original event may include any one of the main driver's door closing, the co-driver's door closing, the rear left door closing, and the rear right door closing, and the combination of these original events constitutes the second combined event.
  • Other invalid events in the door closing process may also be filtered.
  • step S200 is a further description of step S200
  • step S300 is a further description of step S300 .
  • step S300 can be implemented through the following steps S301 to S302 .
  • Step S301 when the first combination event is obtained, a non-deterministic state machine is activated to obtain a first state of the non-deterministic state machine, and a rule corresponding to the first combination event in the preset rules is matched based on the first state.
  • Nondeterministic Finite Automata refers to a finite state machine that can have multiple possible next states for each state and input symbol pair.
  • NFA can be used to implement the rule matching logic configured for a complex event processing rule.
  • the specific implementation process can be as follows: For the rule matching logic configured, the rule matching logic can be parsed and compiled to obtain a series of state vertices and edges of state transfer between these vertices, so that these vertices and edges can be used to construct the NFA corresponding to the complex event processing rules.
  • the non-deterministic state machine NFA when the first combination event is obtained, the non-deterministic state machine NFA is activated, the first state of the non-deterministic state machine is set to start, and the rule corresponding to the first combination event in the preset rules is matched based on the first state.
  • the rule corresponding to the first combination event in the preset rules may be a rule for obtaining the number of people currently in the car after the door is opened.
  • Step S302 when the second combination event is obtained, a second state of the non-deterministic state machine is obtained, and a rule corresponding to the second combination event in the preset rules is matched based on the second state.
  • the second state of the non-deterministic state machine is set to end, and a rule corresponding to the second combined event in the preset rules is matched based on the second state.
  • the rule corresponding to the second combined event in the preset rules may be a rule for obtaining the number of people currently in the car after the door is closed.
  • step S300 is a further description of step S300
  • step S400 is a further description of step S400 .
  • the first combination event includes at least one of the main driver's door opening, the front passenger door opening, the rear left door opening, and the rear right door opening;
  • the second combination event includes at least one of the main driver's door closing, the front passenger door closing, the rear left door closing, and the rear right door closing;
  • the method also includes: when the first combination event is obtained, recording the number of people in the first car; when the second combination event is obtained, recording the number of people in the second car.
  • the number of people currently in the car (the first number of people in the car) is recorded, and after the door closing event occurs, the number of people currently in the car (the second number of people in the car) is recorded.
  • step S400 can be implemented through the following steps S401 to S402 .
  • Step S401 updating context information based on the rule corresponding to the first combined event and the rule corresponding to the second combined event.
  • the context information is updated according to the rule corresponding to the first combined event and the rule corresponding to the second combined event in combination with the actual collected data.
  • Step S402 Obtaining a processing result of the complex event based on the updated context information and the perception judgment logic in the rule base.
  • step S400 can be used as a specific example of the above step S400, but is not limited thereto.
  • determining the processing result of the complex event based on the matching result includes: updating context information based on the rule corresponding to the first combined event, the rule corresponding to the second combined event, and the combination of the first number of people in the car and the second number of people in the car; determining the number difference based on the updated context information; judging whether the number difference is greater than a preset threshold; if so, determining that the processing result of the complex event is a single person boarding the car; if not, determining that the processing result of the complex event is multiple people boarding the car.
  • the context variables are updated according to the recorded or collected number of people in the first car and the number of people in the second car, in combination with the rules corresponding to the first combination event and the rules corresponding to the second combination event.
  • the number of people in the first car is assigned to the starting number
  • the number of people in the second car is assigned to the ending number.
  • the difference in the number of people is calculated based on the starting number and the ending number, and combined with the perception judgment logic in the rule base, it is determined whether the difference in the number of people is equal to 1 or greater than 1. If the difference in the number of people is equal to 1, it is determined that only one person is on the car. If the difference in the number of people is greater than 1, it is determined that multiple people are on the car.
  • An event engine is built in the Understand Me Engine module.
  • the preset rules (combined event list rules) are registered in the event engine.
  • the event rules define event windows (span), start events (begin), middle events (middle), end events (end), perception judgment logic, emission events (emitevent), etc.
  • Each combined event rule will build a non-deterministic state machine (NFA).
  • NFA non-deterministic state machine
  • the start event occurs, a rule's NFA will be triggered and set to the initial state. If the middle events continue to occur, the current NFA will query whether there is an edge corresponding to the current middle event and enter the next state along this edge. If an end event occurs within the current window duration, the NFA will enter the end state and inform the event engine that an event match has occurred. At this time, the perception judgment logic will be entered. Different perception judgments may emit different combined events.
  • the Understand Me Engine will then trigger the Understand Me story based on this combined event.
  • the original door is judged and opened, and uniformly mapped to the door opening event (open_door).
  • the number of people in the car (the starting number) is recorded.
  • the NFA will be activated, and the NFA state will be set to start.
  • the start (start) rule will be matched in the current NFA.
  • the current NFA matches the rule, it enters the process, updates the context variables in the rule, and calculates the difference between the end number of people and the start number of people.
  • the event emission logic is entered, and the logic is judged according to different perceptions. If the judgment is true, a specified event is thrown, such as whether one person or multiple people are boarding the bus.
  • the present invention implements all or part of the processes in the method of the above embodiment, and can also be completed by instructing the relevant hardware through a computer program
  • the computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor.
  • the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form.
  • the computer-readable storage medium may include: any entity or device, medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory, random access memory, electric carrier signal, telecommunication signal and software distribution medium that can carry the computer program code.
  • computer-readable storage medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction.
  • computer-readable storage media do not include electric carrier signals and telecommunication signals.
  • the present invention also provides an electronic device.
  • the electronic device includes at least one processor 61 and at least one storage device 62, the storage device 62 can be configured to store a program for executing the complex event processing method of the above method embodiment, and the processor 61 can be configured to execute the program in the storage device.
  • Program including but not limited to the program for executing the complex event processing method of the above method embodiment.
  • the electronic device may be a control device device including various devices.
  • the electronic device may include multiple storage devices and multiple processors.
  • the program for executing the complex event processing method of the above method embodiment may be divided into multiple subprograms, each of which may be loaded and run by a processor to execute different steps of the complex event processing method of the above method embodiment.
  • each subprogram may be stored in different storage devices, and each processor may be configured to execute programs in one or more storage devices to jointly implement the complex event processing method of the above method embodiment, that is, each processor executes different steps of the complex event processing method of the above method embodiment, to jointly implement the complex event processing method of the above method embodiment.
  • the above-mentioned multiple processors may be processors deployed on the same device.
  • the above-mentioned electronic device may be a high-performance device composed of multiple processors, and the above-mentioned multiple processors may be processors configured on the high-performance device.
  • the above-mentioned multiple processors may also be processors deployed on different devices.
  • the above-mentioned electronic device may be a server cluster, and the above-mentioned multiple processors may be processors on different servers in the server cluster.
  • the present invention also provides a computer-readable storage medium.
  • the computer-readable storage medium can be configured to store a program for executing the complex event processing method of the above method embodiment, and the program can be loaded and run by a processor to implement the above complex event processing method.
  • the computer-readable storage medium can be a storage device formed by various electronic devices.
  • the computer-readable storage medium in the embodiment of the present invention is a non-temporary computer-readable storage medium.
  • the present invention also provides a vehicle, comprising a vehicle body, at least one processor and at least one storage device, wherein the storage device is suitable for storing multiple program codes, and the program codes are suitable for being loaded and run by the processor to execute the complex event processing method of the aforementioned embodiment.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • Computing Systems (AREA)
  • Evolutionary Computation (AREA)
  • Mathematical Physics (AREA)
  • Data Mining & Analysis (AREA)
  • Artificial Intelligence (AREA)
  • Multimedia (AREA)
  • Traffic Control Systems (AREA)

Abstract

本发明涉及数据处理领域，具体提供一种复杂事件处理方法、电子设备、存储介质及车辆，旨在解决现有复杂事件方法的处理效率较低的技术问题。为此目的，本发明的复杂事件处理方法，包括监听原始感知事件；基于原始感知事件获取复杂事件；将复杂事件与规则库中的预设规则进行匹配；根据匹配结果确定复杂事件的处理结果。如此，能够基于原始感知事件实现任何复杂事件的处理，降低了开发成本，提高了复杂事件的处理效率。

Description

复杂事件处理方法、电子设备、存储介质及车辆
本申请要求2023年06月15日提交的、发明名称为“复杂事件处理方法、电子设备、存储介质及车辆”的中国专利申请CN202310709776.X的优先权，上述中国专利申请的全部内容通过引用并入本申请中。
技术领域
本发明涉及数据处理领域，具体提供一种复杂事件处理方法、电子设备、存储介质及车辆。
背景技术
目前，在懂我引擎(KnowMe Engine)中，很重要的一个组成部分就是事件(Event)，所有懂我的故事(Story)都是由事件来触发的，有一些事件是座舱内的原始感知事件，如主驾驶车门打开、副驾驶车门打开等。
复杂事件处理是提取信息的主要技术。复杂事件处理是一种基于一组预定义规则的数据处理技术，这些规则规定应该如何处理数据流，以及应该生成哪些新的事件流作为输出。事件可以是许多感兴趣的独立事件或复杂事件，它们对应于业务的特定情况或模式。
然而，现有的复杂事件处理方法均是通过开发人员基于产品的定义文档，针对每个逻辑定义事件，都进行代码开发、性能测试、产品验证等，测试流程长且成本高，导致复杂事件处理效率较低。
相应地，本领域需要一种新的方案来解决上述问题。
发明内容
为了克服上述缺陷，提出了本发明，以提供解决或至少部分地解决上述技术问题。本发明提供了一种复杂事件处理方法、电子设备、存储介质及车辆。
在第一方面，本发明提供一种复杂事件处理方法，所述方法包括：监听原始感知事件；基于所述原始感知事件获取复杂事件；将所述复杂事件与规则库中的预设规则进行匹配；根据匹配结果确定所述复杂事件的处理结果。
在一个实施方式中，在所述监听原始感知事件之前，所述方法还包括：获取预设规则；将所述预设规则存储至规则库中；其中所述预设规则至少包括事件窗口、开始事件、结束事件、上下文信息和感知判断逻辑。
在一个实施方式中，所述原始感知事件包括第一原始感知事件和第二原始感知事件，所述复杂事件包括第一组合事件和第二组合事件；所述基于所述原始感知事件获取复杂事件，包括：对所述第一原始感知事件进行过滤或组合，获得所述第一组合事件；在事件窗口内，对持续发生的所述第二原始感知事件进行过滤或组合，获得第二组合事件。
在一个实施方式中，所述将所述复杂事件与规则库中的预设规则进行匹配，包括：在获得所述第一组合事件的情况下，激活非确定性状态机，获得所述非确定性状态机的第一状态，基于所述第一状态匹配所述预设规则中第一组合事件对应的规则；在获得所述第二组合事件的情况下，获得所述非确定性状态机的第二状态，基于所述第二状态匹配所述预设规则中第二组合事件对应的规则。
在一个实施方式中，所述根据匹配结果确定所述复杂事件的处理结果，包括：基于所述第一组合事件对应的规则和所述第二组合事件对应的规则更新上下文信息；基于更新后的所述上下文信息和所述规则库中的感知判断逻辑获得所述复杂事件的处理结果。
在一个实施方式中，所述第一组合事件包括主驾驶车门打开、副驾驶车门打开、后排左侧车门打开和后排右侧车门打开中的至少一种；所述第二组合事件包括主驾驶车门关闭、副驾驶车门关闭、后排左侧车门关闭和后排右侧车门关闭中的至少一种；所述方法还包括：在获得所述第一组合事件的情况下，记录第一车内人数；在获得所述第二组合事件的情况下，记录第二车内人数。
在一个实施方式中，所述根据匹配结果确定所述复杂事件的处理结 果，包括：基于所述第一组合事件对应的规则、所述第二组合事件对应的规则、结合所述第一车内人数和所述第二车内人数更新上下文信息；基于更新后的所述上下文信息确定人数差；判断所述人数差是否大于预设阈值；若是，则确定所述复杂事件的处理结果为单人上车；若否，则确定所述复杂事件的处理结果为多人上车。
在第二方面，提供一种电子设备，该电子设备包括至少一个处理器和至少一个存储装置，所述存储装置适于存储多条程序代码，所述程序代码适于由所述处理器加载并运行以执行前述任一项所述的复杂事件处理方法。
在第三方面，提供一种计算机可读存储介质，该计算机可读存储介质其中存储有多条程序代码，所述程序代码适于由处理器加载并运行以执行前述任一项所述的复杂事件处理方法。
在第四方面，提供一种车辆，所述车辆包括车辆本体、至少一个处理器和至少一个存储装置，其中所述存储装置适于存储多条程序代码，其特征在于，所述程序代码适于由所述处理器加载并运行以执行前述任一项所述的复杂事件处理方法。
本发明上述一个或多个技术方案，至少具有如下一种或多种有益效果：
本发明中的复杂事件处理方法，包括监听原始感知事件；基于原始感知事件获取复杂事件；将复杂事件与规则库中的预设规则进行匹配；根据匹配结果确定复杂事件的处理结果。如此，能够基于原始感知事件实现任何复杂事件的处理，从而扩大了懂我系统的事件能力库，降低了开发成本，提高了复杂事件的处理效率。
附图说明
参照附图，本发明的公开内容将变得更易理解。本领域技术人员容易理解的是：这些附图仅仅用于说明的目的，而并非意在对本发明的保护范围组成限制。此外，图中类似的数字用以表示类似的部件，其中：
图1是根据本发明的一个实施例的复杂事件处理方法的主要步骤流程示意图；
图2是一个实施例中基于原始感知事件获取复杂事件的流程示意图；
图3是一个实施例中将复杂事件与规则库中的预设规则进行匹配的流程示意图；
图4是一个实施例中根据匹配结果确定复杂事件的处理结果的流程示意图；
图5是一个实施例中复杂事件处理的完整流程示意图；
图6是一个实施例中电子设备的结构示意图。
具体实施方式
下面参照附图来描述本发明的一些实施方式。本领域技术人员应当理解的是，这些实施方式仅仅用于解释本发明的技术原理，并非旨在限制本发明的保护范围。
在本发明的描述中，“模块”、“处理器”可以包括硬件、软件或者两者的组合。一个模块可以包括硬件电路，各种合适的感应器，通信端口，存储器，也可以包括软件部分，比如程序代码，也可以是软件和硬件的组合。处理器可以是中央处理器、微处理器、图像处理器、数字信号处理器或者其他任何合适的处理器。处理器具有数据和/或信号处理功能。处理器可以以软件方式实现、硬件方式实现或者二者结合方式实现。非暂时性的计算机可读存储介质包括任何合适的可存储程序代码的介质，比如磁碟、硬盘、光碟、闪存、只读存储器、随机存取存储器等等。术语“A和/或B”表示所有可能的A与B的组合，比如只是A、只是B或者A和B。术语“至少一个A或B”或者“A和B中的至少一个”含义与“A和/或B”类似，可以包括只是A、只是B或者A和B。单数形式的术语“一个”、“这个”也可以包含复数形式。
目前传统的复杂事件处理方法均是通过开发人员基于产品的定义文档，针对每个逻辑定义事件都进行代码开发、性能测试、产品验证等，测试流程长且成本高，导致复杂事件处理效率较低。
为此，本申请提供了一种复杂事件处理方法、电子设备、存储介质及车辆，包括监听原始感知事件；基于原始感知事件获取复杂事件；将复杂事件与规则库中的预设规则进行匹配；根据匹配结果确定复杂事件 的处理结果。如此，能够基于原始感知事件实现任何复杂事件的处理，从而扩大了懂我系统的事件能力库，降低了开发成本，提高了复杂事件的处理效率。
参阅附图1，图1是根据本发明的一个实施例的复杂事件处理方法的主要步骤流程示意图。
如图1所示，本发明实施例中的复杂事件处理方法主要包括下列步骤S100-步骤S400。
步骤S100：监听原始感知事件。
步骤S200：基于所述原始感知事件获取复杂事件。
步骤S300：将所述复杂事件与规则库中的预设规则进行匹配。
步骤S400：根据匹配结果确定所述复杂事件的处理结果。
基于上述步骤S100-步骤S400，包括监听原始感知事件；基于原始感知事件获取复杂事件；将复杂事件与规则库中的预设规则进行匹配；根据匹配结果确定复杂事件的处理结果。如此，能够基于原始感知事件实现任何复杂事件的处理，从而扩大了懂我系统的事件能力库，降低了开发成本，提高了复杂事件的处理效率。
在一个具体实施方式中，在所述监听原始感知事件之前，所述方法还包括：获取预设规则；将所述预设规则存储至规则库中；其中所述预设规则至少包括事件窗口、开始事件、结束事件、上下文信息和感知判断逻辑。
具体来说，车辆可以包括一个懂我引擎模块，懂我引擎模块中构建了一个事件引擎，启动时将预设规则注册到事件引擎中，预设规则描述如下，首先定义事件窗口(span)为60s，表明该事件最长持续时间为60s；然后定义组合事件的开始事件(begin)、中间事件(middle，中间事件可以没有)、结束事件(end)和事件触发的逻辑。需要严格按照开始事件、中间事件、结束事件的时序来执行。上述流程可以成功实现复杂事件的构造，接下来需要定义如何抛出事件，在这一步，首先定义需要计算的上下文变量(上下文信息)并存储，最后再定义抛出事件(emits)，抛出事件就是对复杂事件的处理结果的获取过程，其中每个抛出事件需要有感知(perception)判断逻辑，只有感知判断逻辑判断通过后，才 可以获得真正的抛出事件。
当前车内人数可以作为所述上下文信息的一个示例，但不限于此。
下述规则可以作为所述预设规则的一个示例，但不限于此。
1 span:60s
2 begin:
3    event:open_door
4     context:start_number＝context.getPersonNumber()
5  end:
6     event:close_all_door
7     context:end_number＝context.getPersonNumber()
8  process:
9  context:diff_number＝end_number-start_number
10  emits:
11    -perception:diff_number＝＝1
12      event:single_person_boarding
13    -perception:diff_number＞1
14      event:multi_person_boarding
预先将预设规则加载至规则库中，为后续每个复杂事件的快速且高效处理提供了基础支撑。
下面分别对上述步骤S100至步骤S400作进一步说明。
原始感知事件为从座舱系统产生并未被处理的事件且不可被分解的原子事件。
针对步骤S100，具体可以通过原始事件感知模块感知座舱内的原始感知事件。在一个具体实施例中，主驾驶车门打开、副驾驶车门打开、后排左侧车门打开、后排右侧车门打开、主驾驶车门关闭、副驾驶车门关闭、后排左侧车门关闭、后排右侧车门关闭中的至少一种可以作为所述原始感知事件的一个示例，但不限于此。
以上是对步骤S100的进一步说明，下面继续对步骤S200作进一步说明。
原始感知事件包括第一原始感知事件和第二原始感知事件，第一原 始感知事件和第二原始感知事件的类型不同。
复杂事件是描述一系列事件按照预先编写的预设规则发生的事件，复杂事件包括第一组合事件和第二组合事件。
具体如图2所示，上述步骤S200可通过下述步骤S201至步骤S202实现。
步骤S201：对所述第一原始感知事件进行过滤或组合，获得所述第一组合事件。
具体来说，对一个或多个第一原始事件进行过滤或者组合，即可得到第一组合事件。示例性地，第一原始事件可以包括主驾驶车门打开、副驾驶车门打开、后排左侧车门打开和后排右侧车门打开中的任意一种，这些原始事件的组合构成了第一组合事件。也可以对车辆开门过程中的其它无效事件进行过滤。
步骤S202：在事件窗口内，对持续发生的所述第二原始感知事件进行过滤或组合，获得第二组合事件。
在预设规则设置的事件窗口内，对持续发生的不同于第一原始事件类型的第二原始事件进行组合或者过滤，即可获得第二组合事件。示例性地，第二原始事件可以包括主驾驶车门关闭、副驾驶车门关闭、后排左侧车门关闭和后排右侧车门关闭中的任意一种，这些原始事件的组合构成了第二组合事件。也可以对关门过程中的其它无效事件进行过滤。
以上是对步骤S200的进一步说明，下面继续对步骤S300作进一步说明。
具体如图3所示，上述步骤S300可通过下述步骤S301至步骤S302实现。
步骤S301：在获得所述第一组合事件的情况下，激活非确定性状态机，获得所述非确定性状态机的第一状态，基于所述第一状态匹配所述预设规则中第一组合事件对应的规则。
非确定性状态机(Nondeterministic Finite Automata，NFA)是指对每个状态和输入符号对可以有多个可能的下一个状态的有限状态自动机。另外，NFA可以用于实现针对一个复杂事件处理规则所配置的规则匹配逻辑，其实现过程具体可以为：对于针对一个复杂事件处理规则所配 置的规则匹配逻辑来说，可以将该规则匹配逻辑进行解析编译处理，以得到一系列状态顶点以及这些顶点之间状态转移的边，以使这些顶点以及边可以被用于构建复杂事件处理规则所对应的NFA。
具体来说，在获得第一组合事件的情况下，激活非确定性状态机NFA，将非确定性状态机的第一状态设置为开始，并基于第一状态匹配到预设规则中第一组合事件对应的规则。
例如，以开车门事件作为第一组合事件来说，匹配到预设规则中第一组合事件对应的规则可以是获取车门开启后当前车内人数的规则。
步骤S302：在获得所述第二组合事件的情况下，获得所述非确定性状态机的第二状态，基于所述第二状态匹配所述预设规则中第二组合事件对应的规则。
具体来说，在获得第二组合事件的情况下，将非确定性状态机的第二状态设置为结束，并基于第二状态匹配预设规则中第二组合事件对应的规则。
例如，以关车门事件作为第二组合事件来说，匹配到预设规则中第二组合事件对应的规则可以是获取车门关闭后当前车内人数的规则。
以上是对步骤S300的进一步说明，下面继续对步骤S400作进一步说明。
在一个实施例中，所述第一组合事件包括主驾驶车门打开、副驾驶车门打开、后排左侧车门打开和后排右侧车门打开中的至少一种；所述第二组合事件包括主驾驶车门关闭、副驾驶车门关闭、后排左侧车门关闭和后排右侧车门关闭中的至少一种；所述方法还包括：在获得所述第一组合事件的情况下，记录第一车内人数；在获得所述第二组合事件的情况下，记录第二车内人数。
具体来说，在开车门事件发生后，记录当前车内人数(第一车内人数)，以及在关车门事件发生后，记录当前车内人数(第二车内人数)。
具体如图4所示，上述步骤S400可通过下述步骤S401至步骤S402实现。
步骤S401：基于所述第一组合事件对应的规则和所述第二组合事件对应的规则更新上下文信息。
具体地，结合实际采集数据、根据第一组合事件对应的规则和第二组合事件对应的规则更新上下文信息。
步骤S402：基于更新后的所述上下文信息和所述规则库中的感知判断逻辑获得所述复杂事件的处理结果。
具体地，下述实施例可以作为上述步骤S400的一个具体示例，但不限于此。
在一个实施方式中，所述根据匹配结果确定所述复杂事件的处理结果，包括：基于所述第一组合事件对应的规则、所述第二组合事件对应的规则、结合所述第一车内人数和所述第二车内人数更新上下文信息；基于更新后的所述上下文信息确定人数差；判断所述人数差是否大于预设阈值；若是，则确定所述复杂事件的处理结果为单人上车；若否，则确定所述复杂事件的处理结果为多人上车。
具体来说，根据记录或者采集的第一车内人数和第二车内人数、结合第一组合事件对应的规则、第二组合事件对应的规则更新上下文变量，例如将第一车内人数赋值给开始人数，将第二车内人数赋值给结束人数，并根据开始人数和结束人数计算人数差，结合规则库中的感知判断逻辑，判断人数差等于1还是大于1，若人数差等于1，则确定为单人上车，若人数差大于1，则确定为多人上车。
在懂我引擎模块内构建了一个事件引擎，启动时将预设规则(组合事件列表规则)注册到事件引擎中，事件规则里面定义事件窗口(span)、开始事件(begin)、中间事件(middle)、结束事件(end)、感知(perception)判断逻辑、发射事件(emitevent)等。每一个组合事件规则会构建一个非确定性状态机(NFA)，当开始事件发生时，会触发一个规则的NFA，并设置为初始状态，后续如果继续发生中间事件，当前的NFA会查询是否有与当前中间事件相对应的边，并沿着这一个边进入下一个状态，如果在当前窗口时长内，发生一次结束事件，NFA会进入结束状态，并告知事件引擎当前发生了一次事件匹配，此时会进入感知判断逻辑，不同的感知判断可能会发射出不同的组合事件，后续懂我引擎会基于此组合事件进行懂我故事的触发。
在一个具体实施例中，如图5所示，车门打开事件发生后，首先会 判断并将原始车门打开，统一映射为开车门事件(open_door)，同时记录当前车内人数(开始人数)，此时会激活NFA，将NFA状态设置为start，当前NFA中会匹配到开始(start)的规则。
在事件窗口(60s)内，如果继续发生了单一车门关闭事件，同时将此事映射为全部车门关闭事件(close_all_door)，此时当前NFA中会匹配到结束(end)的规则，此时记录当前车内人数(结束人数)。
当前NFA匹配到规则后，进入流程(process)，更新规则内上下文变量，计算结束人数和开始人数的人数差。
最后进入事件发射逻辑，根据不同的感知(perception)判断逻辑，如果判断为ture则抛出指定事件，例如单人上车还是多人上车。
需要指出的是，尽管上述实施例中将各个步骤按照特定的先后顺序进行了描述，但是本领域技术人员可以理解，为了实现本发明的效果，不同的步骤之间并非必须按照这样的顺序执行，其可以同时(并行)执行或以其他顺序执行，这些变化都在本发明的保护范围之内。
本领域技术人员能够理解的是，本发明实现上述一实施例的方法中的全部或部分流程，也可以通过计算机程序来指令相关的硬件来完成，所述的计算机程序可存储于一计算机可读存储介质中，该计算机程序在被处理器执行时，可实现上述各个方法实施例的步骤。其中，所述计算机程序包括计算机程序代码，所述计算机程序代码可以为源代码形式、对象代码形式、可执行文件或某些中间形式等。所述计算机可读存储介质可以包括：能够携带所述计算机程序代码的任何实体或装置、介质、U盘、移动硬盘、磁碟、光盘、计算机存储器、只读存储器、随机存取存储器、电载波信号、电信信号以及软件分发介质等。需要说明的是，所述计算机可读存储介质包含的内容可以根据司法管辖区内立法和专利实践的要求进行适当的增减，例如在某些司法管辖区，根据立法和专利实践，计算机可读存储介质不包括电载波信号和电信信号。
进一步，本发明还提供了一种电子设备。在根据本发明的一个电子设备实施例中，如图6所示，电子设备包括至少一个处理器61和至少一个存储装置62，存储装置62可以被配置成存储执行上述方法实施例的复杂事件处理方法的程序，处理器61可以被配置成用于执行存储装置中的 程序，该程序包括但不限于执行上述方法实施例的复杂事件处理方法的程序。为了便于说明，仅示出了与本发明实施例相关的部分，具体技术细节未揭示的，请参照本发明实施例方法部分。
在本发明实施例中电子设备可以是包括各种设备形成的控制装置设备。在一些可能的实施方式中，电子设备可以包括多个存储装置和多个处理器。而执行上述方法实施例的复杂事件处理方法的程序可以被分割成多段子程序，每段子程序分别可以由处理器加载并运行以执行上述方法实施例的复杂事件处理方法的不同步骤。具体地，每段子程序可以分别存储在不同的存储装置中，每个处理器可以被配置成用于执行一个或多个存储装置中的程序，以共同实现上述方法实施例的复杂事件处理方法，即每个处理器分别执行上述方法实施例的复杂事件处理方法的不同步骤，来共同实现上述方法实施例的复杂事件处理方法。
上述多个处理器可以是部署于同一个设备上的处理器，例如上述电子设备可以是由多个处理器组成的高性能设备，上述多个处理器可以是该高性能设备上配置的处理器。此外，上述多个处理器也可以是部署于不同设备上的处理器，例如上述电子设备可以是服务器集群，上述多个处理器可以是服务器集群中不同服务器上的处理器。
进一步，本发明还提供了一种计算机可读存储介质。在根据本发明的一个计算机可读存储介质实施例中，计算机可读存储介质可以被配置成存储执行上述方法实施例的复杂事件处理方法的程序，该程序可以由处理器加载并运行以实现上述复杂事件处理方法。为了便于说明，仅示出了与本发明实施例相关的部分，具体技术细节未揭示的，请参照本发明实施例方法部分。该计算机可读存储介质可以是包括各种电子设备形成的存储装置设备，可选的，本发明实施例中计算机可读存储介质是非暂时性的计算机可读存储介质。
进一步，本发明还提供了一种车辆，所述车辆包括车辆本体、至少一个处理器和至少一个存储装置，其中所述存储装置适于存储多条程序代码，所述程序代码适于由所述处理器加载并运行以执行前述实施例的复杂事件处理方法。
至此，已经结合附图所示的优选实施方式描述了本发明的技术方案， 但是，本领域技术人员容易理解的是，本发明的保护范围显然不局限于这些具体实施方式。在不偏离本发明的原理的前提下，本领域技术人员可以对相关技术特征作出等同的更改或替换，这些更改或替换之后的技术方案都将落入本发明的保护范围之内。

Claims (10)

  1. 一种复杂事件处理方法，其特征在于，所述方法包括：
    监听原始感知事件；
    基于所述原始感知事件获取复杂事件；
    将所述复杂事件与规则库中的预设规则进行匹配；
    根据匹配结果确定所述复杂事件的处理结果。
  2. 根据权利要求1所述的复杂事件处理方法，其特征在于，在所述监听原始感知事件之前，所述方法还包括：
    获取预设规则；
    将所述预设规则存储至规则库中；
    其中所述预设规则至少包括事件窗口、开始事件、结束事件、上下文信息和感知判断逻辑。
  3. 根据权利要求1所述的复杂事件处理方法，其特征在于，所述原始感知事件包括第一原始感知事件和第二原始感知事件，所述复杂事件包括第一组合事件和第二组合事件；
    所述基于所述原始感知事件获取复杂事件，包括：
    对所述第一原始感知事件进行过滤或组合，获得所述第一组合事件；
    在事件窗口内，对持续发生的所述第二原始感知事件进行过滤或组合，获得所述第二组合事件。
  4. 根据权利要求3所述的复杂事件处理方法，其特征在于，所述将所述复杂事件与规则库中的预设规则进行匹配，包括：
    在获得所述第一组合事件的情况下，激活非确定性状态机，获得所述非确定性状态机的第一状态，基于所述第一状态匹配所述预设规则中第一组合事件对应的规则；
    在获得所述第二组合事件的情况下，获得所述非确定性状态机的第二状态，基于所述第二状态匹配所述预设规则中第二组合事件对应的规 则。
  5. 根据权利要求4所述的复杂事件处理方法，其特征在于，所述根据匹配结果确定所述复杂事件的处理结果，包括：
    基于所述第一组合事件对应的规则和所述第二组合事件对应的规则更新上下文信息；
    基于更新后的所述上下文信息和所述规则库中的感知判断逻辑获得所述复杂事件的处理结果。
  6. 根据权利要求4所述的复杂事件处理方法，其特征在于，所述第一组合事件包括主驾驶车门打开、副驾驶车门打开、后排左侧车门打开和后排右侧车门打开中的至少一种；所述第二组合事件包括主驾驶车门关闭、副驾驶车门关闭、后排左侧车门关闭和后排右侧车门关闭中的至少一种；
    所述方法还包括：
    在获得所述第一组合事件的情况下，记录第一车内人数；
    在获得所述第二组合事件的情况下，记录第二车内人数。
  7. 根据权利要求6所述的复杂事件处理方法，其特征在于，所述根据匹配结果确定所述复杂事件的处理结果，包括：
    基于所述第一组合事件对应的规则、所述第二组合事件对应的规则、结合所述第一车内人数和所述第二车内人数更新上下文信息；
    基于更新后的所述上下文信息确定人数差；
    判断所述人数差是否大于预设阈值；
    若是，则确定所述复杂事件的处理结果为单人上车；
    若否，则确定所述复杂事件的处理结果为多人上车。
  8. 一种电子设备，包括至少一个处理器和至少一个存储装置，所述存储装置适于存储多条程序代码，其特征在于，所述程序代码适于由所述处理器加载并运行以执行权利要求1至7中任一项所述的复杂事件处 理方法。
  9. 一种计算机可读存储介质，其中存储有多条程序代码，其特征在于，所述程序代码适于由处理器加载并运行以执行权利要求1至7中任一项所述的复杂事件处理方法。
  10. 一种车辆，其特征在于，所述车辆包括车辆本体、至少一个处理器和至少一个存储装置，其中所述存储装置适于存储多条程序代码，其特征在于，所述程序代码适于由所述处理器加载并运行以执行权利要求1至7中任一项所述的复杂事件处理方法。
PCT/CN2024/096657 2023-06-15 2024-05-31 复杂事件处理方法、电子设备、存储介质及车辆 Ceased WO2024255614A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202310709776.X 2023-06-15
CN202310709776.XA CN116450381B (zh) 2023-06-15 2023-06-15 复杂事件处理方法、电子设备、存储介质及车辆

Publications (1)

Publication Number Publication Date
WO2024255614A1 true WO2024255614A1 (zh) 2024-12-19

Family

ID=87122286

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2024/096657 Ceased WO2024255614A1 (zh) 2023-06-15 2024-05-31 复杂事件处理方法、电子设备、存储介质及车辆

Country Status (2)

Country Link
CN (1) CN116450381B (zh)
WO (1) WO2024255614A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116450381B (zh) * 2023-06-15 2023-09-08 蔚来汽车科技(安徽)有限公司 复杂事件处理方法、电子设备、存储介质及车辆

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080109824A1 (en) * 2006-11-08 2008-05-08 Institute For Information Industry Method and system for complex event processing
US20110060496A1 (en) * 2009-08-11 2011-03-10 Certusview Technologies, Llc Systems and methods for complex event processing of vehicle information and image information relating to a vehicle
US20140195465A1 (en) * 2013-01-05 2014-07-10 Microsoft Corporation Monitor-mine-manage cycle
KR20210023273A (ko) * 2019-08-22 2021-03-04 아이브스 주식회사 터널 상황 판단 장치 및 그 방법
CN114880134A (zh) * 2022-03-31 2022-08-09 中国农业大学 基于复杂事件处理的家居自动控制方法和装置
CN115544120A (zh) * 2022-10-20 2022-12-30 重庆长安汽车股份有限公司 多传感器的事件生成系统、方法、电子设备及存储介质
CN115909564A (zh) * 2022-12-23 2023-04-04 北京百度网讯科技有限公司 自动驾驶车辆的控制方法、系统、装置和电子设备
CN116450381A (zh) * 2023-06-15 2023-07-18 蔚来汽车科技(安徽)有限公司 复杂事件处理方法、电子设备、存储介质及车辆

Family Cites Families (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8646025B2 (en) * 2005-12-21 2014-02-04 Mcafee, Inc. Automated local exception rule generation system, method and computer program product
JP2012118928A (ja) * 2010-12-03 2012-06-21 Nec Corp イベント処理装置、イベント処理方法およびイベント処理プログラム
US9286354B2 (en) * 2011-08-15 2016-03-15 Software Ag Systems and/or methods for forecasting future behavior of event streams in complex event processing (CEP) environments
US9135826B2 (en) * 2012-12-26 2015-09-15 Sap Se Complex event processing for moving objects
EP3239686B1 (en) * 2016-04-26 2024-09-18 Walter Steven Rosenbaum Method for determining driving characteristics of a vehicle
CN112026686B (zh) * 2019-06-04 2022-04-12 上海汽车集团股份有限公司 一种自动调节车辆座椅位置的方法及装置
CN110466509A (zh) * 2019-08-23 2019-11-19 威马智慧出行科技（上海）有限公司 自动泊车模式选择方法、电子设备及汽车
CN112668843A (zh) * 2020-12-16 2021-04-16 中国汽车技术研究中心有限公司 车险理赔风险管控方法及系统、电子设备、介质
CN113240909B (zh) * 2021-06-17 2022-11-29 阿波罗智联(北京)科技有限公司 车辆监测方法、设备、云控平台和车路协同系统
CN113665440A (zh) * 2021-08-31 2021-11-19 东风汽车集团股份有限公司 一种自适应式乘坐空间调节系统及调节方法
CN113835570B (zh) * 2021-09-16 2024-04-12 阿波罗智联(北京)科技有限公司 车辆中显示屏的控制方法、装置、设备、存储介质及程序

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080109824A1 (en) * 2006-11-08 2008-05-08 Institute For Information Industry Method and system for complex event processing
US20110060496A1 (en) * 2009-08-11 2011-03-10 Certusview Technologies, Llc Systems and methods for complex event processing of vehicle information and image information relating to a vehicle
US20140195465A1 (en) * 2013-01-05 2014-07-10 Microsoft Corporation Monitor-mine-manage cycle
KR20210023273A (ko) * 2019-08-22 2021-03-04 아이브스 주식회사 터널 상황 판단 장치 및 그 방법
CN114880134A (zh) * 2022-03-31 2022-08-09 中国农业大学 基于复杂事件处理的家居自动控制方法和装置
CN115544120A (zh) * 2022-10-20 2022-12-30 重庆长安汽车股份有限公司 多传感器的事件生成系统、方法、电子设备及存储介质
CN115909564A (zh) * 2022-12-23 2023-04-04 北京百度网讯科技有限公司 自动驾驶车辆的控制方法、系统、装置和电子设备
CN116450381A (zh) * 2023-06-15 2023-07-18 蔚来汽车科技(安徽)有限公司 复杂事件处理方法、电子设备、存储介质及车辆

Also Published As

Publication number Publication date
CN116450381A (zh) 2023-07-18
CN116450381B (zh) 2023-09-08

Similar Documents

Publication Publication Date Title
CN114373189B (zh) 一种行为检测方法、装置、终端设备及存储介质
CN114879630B (zh) 车辆故障诊断方法、装置、设备及可读存储介质
CN111177417A (zh) 基于网络安全知识图谱的安全事件关联方法、系统、介质
EP3776367A1 (en) Detecting data anomalies on a data interface using machine learning
CN114972827B (zh) 资产识别方法、装置、设备及计算机可读存储介质
US20120054163A1 (en) Policy conflict classifier
WO2024255614A1 (zh) 复杂事件处理方法、电子设备、存储介质及车辆
CN107368582B (zh) 一种sql语句检测方法及系统
RU2527738C1 (ru) Способ обезвреживания вредоносных программ, блокирующих работу пк, с использованием отдельного устройства для активации пользователем процедуры противодействия вредоносному программному обеспечению
CN112329014B (zh) 一种病毒识别防御方法、装置、存储介质及设备
DE112008003075T5 (de) Systeme und Verfahren zum Aktualisieren von Einrichtung- bzw Geräte-Software
JP7273875B2 (ja) 判定装置、移動体、判定方法及びプログラム
CN108491213A (zh) 软件持续集成方法、软件持续集成装置及电子设备
WO2022155376A1 (en) Root cause analysis tool for alarms
Hajamydeen et al. A detailed description on unsupervised heterogeneous anomaly based intrusion detection framework
CN103810222A (zh) 样本文件的处理方法及装置
TWI553502B (zh) 用於應用程式層之防火牆裝置的保護方法與其電腦系統
US20210012037A1 (en) Proofing against tampering with a computer
WO2023088523A1 (de) Verfahren zur erkennung von auf eine manipulation hindeutenden anomalien während eines sicheren startvorgangs einer softwaregesteuerten vorrichtung
EP4589908A1 (en) Intrusion detection method, apparatus and system
CN113312201A (zh) 一种异常进程的处置方法及相关装置
CN113141369A (zh) 基于人工智能的防火墙策略管理方法及相关设备
CN113705961B (zh) 基于车辆动力总成功能的风险等级评估分解方法及装置
KR20140105391A (ko) 자동차 제어 유닛의 운영 체제 내 스택 메모리를 모니터링하는 방법
CN115034397B (zh) 行为安全基线状态管控方法、装置、设备和存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 24822566

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE