A control strategy determination method, device, storage medium and vehicle

Abstract

The application discloses a control strategy determination method and device, a storage medium and a vehicle, relates to the field of vehicle-mounted human-computer interaction, and comprises the following steps: determining a task type of a task to be executed and determining an execution condition corresponding to the task type according to a request of a user for a vehicle; collecting current multi-dimensional information of the vehicle, splitting the request, determining at least one atomic action node, and responding to the multi-dimensional information satisfying the execution condition; calculating an execution risk of each atomic action node, determining a total risk of the task, and determining a control strategy corresponding to the total risk of the task. Through the application, the request can be blocked by a deterministic bottom line to prevent an unallowed task, the driving safety is ensured, the efficiency of control strategy determination is improved, the probability of misexecution caused by misrecognition of an intention, expiration of state data, risk accumulation of a complex task and state drift of the vehicle is reduced, and the interactive load in the driving process is controlled.

Description

Technical Field

[0001] This invention relates to the field of vehicle-mounted human-machine interaction, and more particularly to a control strategy determination method, a control strategy determination device, a storage medium, and a vehicle. Background Technology

[0002] With the development of large language models, vehicle networking, and smart cockpit technologies, in-vehicle voice assistants are evolving from recognizing fixed commands to AI agents capable of accessing knowledge bases, third-party services, and vehicle control interfaces. These AI agents can break down natural language requests into multiple sub-tasks and sequentially invoke vehicle status queries, navigation, air conditioning, entertainment, diagnostics, or after-sales interfaces.

[0003] Unlike ordinary consumer electronic devices, vehicle states are constantly changing, and some operations can affect driving safety, vehicle energy status, or critical electronic control units. Various technical solutions have been proposed in related technologies, such as collecting voice commands, performing semantic analysis, and controlling the vehicle to execute corresponding functions; generating scripts based on custom scenarios; issuing and executing combined commands after voice requests meet trigger conditions; or using alignment models to determine whether information and interaction commands are aligned and to determine the response strategy.

[0004] However, the technical solutions in related technologies rely solely on the intent recognition results to directly call the interface, which poses significant risks. Summary of the Invention

[0005] The purpose of this invention is to provide a control strategy determination method, a control strategy determination device, an electronic device, a storage medium, and a vehicle, at least to solve the technical problem that relying solely on intent recognition results to directly call interfaces leads to significant execution risks.

[0006] This invention provides the following solution:

[0007] According to one aspect of the present invention, a method for determining a control strategy is provided, comprising:

[0008] Based on the user's request for the vehicle, determine the task type to be executed, and determine the execution conditions corresponding to the task type;

[0009] Collect the current multi-dimensional information of the vehicle, and in response to the multi-dimensional information satisfying the execution conditions, split the request and determine at least one atomic action node;

[0010] Calculate the execution risk of each atomic action node to determine the overall task risk;

[0011] Determine the control strategy corresponding to the overall risk of the task.

[0012] Preferably, the calculation of the execution risk of each atomic action node to determine the overall task risk includes:

[0013] Determine the sequential execution relationship between the atomic action nodes;

[0014] According to the aforementioned execution order, the calculation order of each atomic action node is determined, and the execution risk of each atomic action node is assessed based on the calculation order.

[0015] Among all the execution risks, the maximum value of the execution risks is selected as the overall task risk.

[0016] Preferably, the execution risk of the atomic action nodes based on the calculation order includes:

[0017] For each atomic action node, determine the underlying risk of the atomic action node and determine the unresolved risk of at least one preceding node on which the execution of the atomic action node depends;

[0018] The risk propagation coefficient is determined based on the degree to which the preceding node eliminates the uneliminated risk.

[0019] Based on the risk propagation coefficient and the unresolved risk, determine the propagation risk from the preceding node to the atomic action node;

[0020] Calculate the sum of the basic risk and all propagation risks to determine the execution risk of the atomic action node.

[0021] Preferably, determining the control strategy corresponding to the overall risk of the task includes:

[0022] Obtain at least one pre-defined risk zone;

[0023] Based on the multi-dimensional information, the range of each risk interval is adjusted, and the adjusted risk area is compared with the overall task risk to determine the first risk interval where the overall task risk is located;

[0024] The control result corresponding to the first risk interval is determined as the control strategy requested.

[0025] Preferably, adjusting the range of each risk interval based on the multi-dimensional information includes:

[0026] Based on the aforementioned multi-dimensional information, vehicle motion risks and environmental risks are determined;

[0027] The first degree of influence of vehicle speed on the risk range is determined based on the vehicle motion risk, and the second degree of influence of the environment on the risk range is determined based on the environmental risk.

[0028] Obtain the basic execution threshold, the minimum execution threshold, and the pre-set risk threshold used to divide the risk interval;

[0029] The risk threshold is adjusted based on the vehicle motion risk, the environmental risk, the first degree of impact, the second degree of impact, the basic execution threshold, and the minimum execution threshold;

[0030] Based on the adjusted risk threshold, the range of each risk interval is adjusted.

[0031] Preferably, after determining the control strategy corresponding to the overall risk of the task, the method further includes:

[0032] In response to the control policy being executed, the first critical state at the security determination moment is read to form a one-time token corresponding to the control policy;

[0033] Before executing the control strategy at the vehicle control interface, the second critical state at the current moment is reread;

[0034] If the absolute value of the difference between the first critical state and the second critical state is less than or equal to the set state drift tolerance vector, and the one-time token verification passes, the control strategy is executed.

[0035] Preferably, the verification of the one-time token includes:

[0036] When the one-time token meets all preset conditions, the one-time token passes the verification.

[0037] The preset conditions include:

[0038] The one-time token was unused and the signature was valid;

[0039] The time difference between reading the second critical state and the first critical state exceeds the validity period;

[0040] The vehicle identification number of the current vehicle is the same as the vehicle identification number included in the one-time token;

[0041] The unique identifier of the control policy is the same as the event identifier included in the one-time token;

[0042] The re-collected multi-dimensional information satisfies the execution conditions;

[0043] The overall risk of the recalculation task did not exceed the maximum risk threshold of the risk range in which the control strategy is located.

[0044] According to a second aspect of the present invention, a control strategy determination apparatus is provided, comprising:

[0045] The execution condition determination module is used to determine the task type of the task to be executed based on the user's request for the vehicle, and to determine the execution conditions corresponding to the task type.

[0046] An atomic node determination module is used to collect the current multi-dimensional information of the vehicle, and in response to the multi-dimensional information satisfying the execution conditions, to split the request and determine at least one atomic action node.

[0047] The task risk determination module is used to calculate the execution risk of each atomic action node and determine the overall task risk.

[0048] The control strategy determination module is used to determine the control strategy corresponding to the overall risk of the task.

[0049] According to three aspects of the present invention, an electronic device is provided, comprising: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus;

[0050] The memory stores a computer program, which, when executed by the processor, enables the steps of determining the processor control strategy.

[0051] According to four aspects of the present invention, a computer-readable storage medium is provided, comprising: storing a computer program executable by an electronic device, wherein when the computer program is run on the electronic device, the steps of an electronic device control strategy determination method are performed.

[0052] According to five aspects of the present invention, a vehicle is provided, comprising:

[0053] Electronic equipment used to implement the steps of a control strategy determination method;

[0054] The processor runs a program, and when the program runs, it executes the steps of a control strategy determination method based on data output from the electronic device.

[0055] A storage medium used to store a program that, when running, executes steps to determine a control strategy based on data output from an electronic device.

[0056] The above solution achieves the following beneficial technical effects:

[0057] This invention determines the task type to be performed based on the user's request for a vehicle, and determines the corresponding execution conditions for the task type, enabling personalized settings of execution conditions and scenario expansion capabilities.

[0058] This invention determines whether the vehicle's multi-dimensional information meets the requirements by executing conditions, and, under the premise that the execution conditions are met, breaks down the request into atomic actions. This enables the blocking of disallowed tasks by deterministic bottom lines, ensuring driving safety while improving the efficiency of control strategy determination.

[0059] This invention determines the overall task risk by calculating the execution risk of each atomic action node. It can consider the risks of multi-dimensional nodes, reduce the probability of mis-identification of intent, expired state data, accumulation of risks in complex tasks, and mis-execution caused by vehicle state drift, and control the interactive load during driving. Attached Figure Description

[0060] Figure 1 This is a flowchart of a control strategy determination method provided by one or more embodiments of the present invention.

[0061] Figure 2 This is a task execution flowchart provided in a specific embodiment of the present invention.

[0062] Figure 3 This is a structural diagram of a control strategy determination device provided in one or more embodiments of the present invention.

[0063] Figure 4 This is a block diagram of an electronic device structure for a control strategy determination method provided in one or more embodiments of the present invention. Detailed Implementation

[0064] The technical solution of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0065] Figure 1 This is a flowchart of a control strategy determination method provided by one or more embodiments of the present invention.

[0066] like Figure 1 The control strategy determination method shown includes:

[0067] Step S1: Based on the user's request for the vehicle, determine the task type to be executed and the corresponding execution conditions for the task type.

[0068] Users can input their vehicle requests in various ways, including multimodal input methods such as voice, text, or touch.

[0069] Task types include, for example, clearing fault codes, remote start, air conditioning control, or window control.

[0070] Among them, the execution conditions for clearing fault codes can be vehicle speed of 0, engine speed of 0, parking brake effective, vehicle electrical / power status (ACC) in the specified state, remote communication terminal (TBOX) online, vehicle model support, and key data age ≤ 2 seconds, etc.

[0071] The conditions for remote start can be that the vehicle is locked, the gear is in P / N position, the engine is not running, the anti-theft authentication is passed, the door and hood status meet the requirements, and the status age is ≤2 seconds.

[0072] The execution conditions for air conditioning control can include vehicle online status, energy status meeting thresholds, target temperature within allowable range, and interface health.

[0073] The conditions for controlling the windows can be a vehicle speed of ≤60km / h and the absence of severe weather such as heavy rain or sandstorms.

[0074] Step S2: Collect the current multi-dimensional information of the vehicle. In response to the multi-dimensional information meeting the execution conditions, split the request and determine at least one atomic action node.

[0075] Based on the task types and corresponding execution conditions determined in the above embodiments, the collected multi-dimensional information of the vehicle is judged. For example, an execution condition set Hq={h1, h2, ..., hn} is configured for task type q. The multi-dimensional information is judged according to each execution condition in the execution condition set, and the corresponding result 0 or 1 is output, where 0 indicates prohibition and 1 indicates permission to execute. The judgment result Gq=∏hk of all output execution conditions is determined. If any execution condition is 0, then Gq=0, and the system prohibits the generation of the corresponding vehicle control command. If any execution condition is not met, a missing condition can be output, or multi-dimensional information can be re-collected, etc. Permission to execute can be either direct permission or secondary confirmation.

[0076] The set of execution conditions can be versioned by vehicle model, configuration, control interface version, and regulatory region.

[0077] If the multi-dimensional information satisfies all the defined execution conditions, the user's request is broken down to determine at least one atomic action node. Examples include intent confirmation, status reading, object confirmation, vehicle control, and result verification.

[0078] Step S3: Calculate the execution risk of each atomic action node to determine the overall task risk.

[0079] Each atomic action node includes a pre-set basic risk and a propagation risk from its predecessor nodes. By combining the basic risk and the propagation risk, the execution risk of each atomic action node is determined, thereby determining the overall task risk.

[0080] Step S4: Determine the control strategy corresponding to the overall risk of the task.

[0081] Furthermore, by comparing the overall risk of the task with a pre-set risk range, the corresponding control strategy is determined.

[0082] Specifically, at least one pre-divided risk interval is obtained, which can be determined by a pre-determined risk threshold.

[0083] Based on multi-dimensional information, the range of each risk interval is adjusted, and the adjusted risk area is compared with the overall task risk to determine the first risk interval where the overall task risk lies. The control result corresponding to the first risk interval is determined as the requested control strategy.

[0084] In this embodiment, vehicle motion risk and environmental risk can be determined based on multi-dimensional information. Then, the first degree of influence of vehicle speed on the risk range can be determined based on vehicle motion risk, and the second degree of influence of the environment on the risk range can be determined based on environmental risk.

[0085] Generally, a basic execution threshold can be set first, which is the minimum execution threshold allowed by the system. Then, based on vehicle movement risk, environmental risk, primary impact level, secondary impact level, the basic execution threshold, and the minimum execution threshold, the risk threshold can be adjusted to achieve adjustment of the risk range. The adjustment of the risk threshold can be performed according to the following formula:

[0086] T= max (Tmin, T0-kM×M-kE×E)

[0087] Where T represents the risk threshold, Tmin represents the minimum execution threshold, T0 represents the basic execution threshold, kM represents the first degree of impact, kE represents the second degree of impact, M represents vehicle motion risk, and E represents environmental risk.

[0088] For example, the preset risk thresholds include T1, T2, T3, and T4. The risk range is less than T1, and the corresponding control strategy is P0; the risk range is greater than or equal to T1 and less than T2, and the corresponding control strategy is P1; the risk range is greater than or equal to T2 and less than T3, and the corresponding control strategy is P2; the risk range is greater than or equal to T3 and less than T4, and the corresponding control strategy is P3; the risk range is less than T4, and the corresponding control strategy is P4.

[0089] By adjusting the risk thresholds using the above formulas, we obtain T1', T2', T3', and T4', with the corresponding risk intervals adjusted to be less than T1', greater than or equal to T1' and less than T2', greater than or equal to T2' and less than T3', greater than or equal to T3' and less than T4', and less than T4'.

[0090] Among them, the control result corresponding to P0 is direct execution, and typical processing includes, for example, low-risk queries or explicit and reversible comfort control.

[0091] The control result corresponding to P1 is to execute after simplifying the interaction. Typical processing includes shortening voice output while driving, disabling long texts, and automatic navigation.

[0092] The control result corresponding to P2 is executed after secondary confirmation. Typical processing includes, for example, restating the object, parameters and effects, and receiving explicit confirmation.

[0093] The control result corresponding to P3 is either downgrade or delay. Typical processing methods include, for example, converting it to a suggestion, adding it to the pending execution queue, and re-verifying it after stopping.

[0094] If P4 and multi-dimensional information do not meet any execution condition (G=0), the corresponding control result is to prohibit execution. Typical processing is, for example, to specify the specific blocking conditions and not to generate vehicle control messages.

[0095] The implementation method for calculating the execution risk of each atomic action node and determining the overall task risk is as follows.

[0096] The execution sequence of atomic action nodes is determined, and the computation order of each atomic action node is determined according to this sequence. The execution risk of each atomic action node is then assessed based on this computation order. The execution sequence can be represented using a risk graph, directed acyclic graph, state machine, behavior tree, or weighted Petri net, which can express the dependencies between atomic actions and the propagation of risks.

[0097] Furthermore, for each atomic action node, a pre-defined basic risk, ranging from 0 to 1, is identified, along with unresolved risks, also ranging from 0 to 1, from the at least one preceding node upon which the execution of the atomic action node depends. Examples include motion state risk, operational consequence risk, data trust risk, interaction load risk, semantic uncertainty risk, and environmental risk.

[0098] Among these, unresolved risks can be determined using multi-dimensional information about the vehicle. For example, motion state risk can be determined using vehicle speed, gear position, engine speed, parking brake, and lateral and longitudinal acceleration to reflect whether the vehicle is stationary, at low speed, or in motion. Operational consequence risk can be determined using the controlled object, safety impact, reversibility, failure consequences, and compensation capabilities to differentiate between query, comfort control, and critical control. Data trust risk can be determined using data age, number of data sources, inter-source deviation, communication quality, and interface health to prevent expired or conflicting states from entering the control chain. Interaction load risk can be determined using vehicle speed, road complexity, driver fatigue, output length, and interaction rounds to control visual and cognitive occupancy during driving. Semantic uncertainty risk can be determined using intent confidence, slot completeness, referential ambiguity, and the degree of contextual cross-domain interaction to constrain vehicle operations caused by misunderstandings. Environmental risk can be determined using weather, road grade, traffic density, hazardous road sections, and location trustworthiness to dynamically tighten thresholds according to the environment.

[0099] Furthermore, based on the degree to which preceding nodes eliminate unresolved risks, the risk propagation coefficient is determined to range from 0 to 1. Based on the risk propagation coefficient and the unresolved risks, the propagation risk from preceding nodes to atomic action nodes is determined. The risk propagation coefficient is a weight determined according to the degree of elimination. The sum of the basic risk and all propagated risks is calculated to determine the execution risk of the atomic action node.

[0100] The formula for calculating the execution risk of atomic action nodes is as follows:

[0101] ri=min(1, bi + Σ(aji × rj))

[0102] In the formula, ri represents the execution risk of the atomic action node, bi represents the basic risk, aji represents the risk propagation coefficient, and rj represents the unresolved risk. ri has a maximum value of 1; if greater than 1, it takes the value 1.

[0103] Finally, among all execution risks, the maximum value of the execution risk is selected as the overall task risk R, i.e., R = max(ri).

[0104] Among these methods, the execution risk of atomic action nodes can also be calculated using deterministic formulas, Bayesian networks, fuzzy inference, or machine learning models trained with security constraints.

[0105] This embodiment blocks prohibited tasks through an unbypassable hard security gating system, and then constructs a task risk map for complex tasks that pass the gating system and performs risk propagation calculations, forming a two-layer control system that combines deterministic bottom lines with probabilistic decision-making.

[0106] By breaking down user requests into atomic action nodes, basic risks, input credibility, reversibility, and failure consequences are set for each node, and risks are propagated along action-dependent edges. Uncertainties in preceding recognition or state reading are passed to subsequent vehicle control nodes, rather than being statically scored only once for the entire instruction. Calculating atomic action nodes ensures that preceding risks, such as speech recognition uncertainty and outdated state data, are propagated to vehicle control actions. For tasks with multiple parallel branches, the system calculates each branch separately and uses the highest risk at the vehicle control node as the overall risk. This avoids complex multiplication and ensures that any high-risk control action is not averaged out by other low-risk actions.

[0107] In this embodiment, after determining the control strategy corresponding to the overall risk of the task, if the control strategy is to execute, the token module reads the key state snapshot S0 at the security determination time t0, generates a state digest (S0), and forms a one-time token. The one-time token includes at least the vehicle identifier (VIN), task identifier (TaskID), atomic action identifier, state digest, gating rule version, risk model version, generation time t0, validity period (TTL), random number (nonce), allowed action set (Aallow), state drift tolerance vector (Δ), and signature value. The one-time token can be issued on the vehicle, in the cloud, or in a trusted execution environment. The signature method can be a message authentication code, asymmetric signature, or a trusted credential generated by a hardware security module.

[0108] The token structure is: Token = SignK[VIN||TaskID||ActionID||Digest(S0)||GateVer||RiskVer||t0||TTL||nonce||Aallow||Δ||]. The token can only be used for a specified vehicle, task, and action, and is invalidated after one use.

[0109] Before executing the control strategy at the vehicle control interface, the second critical state S1 at the current moment is reread. If the absolute value of the difference between the first and second critical states is less than or equal to the set state drift tolerance vector (i.e., |S1-S0|≤Δ), and the one-time token verification passes, the control strategy is executed. The state drift tolerance vector can be a vector with a fixed threshold configured according to the task type, or it can be generated in real time based on vehicle dynamics and sensor accuracy.

[0110] A one-time token passes verification if all preset conditions are met. The preset conditions include:

[0111] The one-time token was unused and the signature is valid.

[0112] The time difference between reading the second critical state and the first critical state exceeds the validity period;

[0113] The vehicle identification number of the current vehicle is the same as the vehicle identification number included in the one-time token;

[0114] The unique identifier of the control policy is the same as the event identifier included in the one-time token;

[0115] The newly collected multi-dimensional information meets the execution conditions;

[0116] The overall risk of the recalculation task did not exceed the maximum risk threshold of the risk range where the control strategy is located.

[0117] In this embodiment, the execution result confirmation can be accomplished through CAN signals, Ethernet services, diagnostic responses, actuator feedback, or multi-source state fusion.

[0118] This embodiment generates a one-time task status lock token between the security judgment and the actual vehicle execution; before execution, the status of key vehicles is re-collected, and the signature, validity period, vehicle and task binding relationship, state drift tolerance, hard gating result and dynamic risk threshold of the one-time token are verified twice to solve the time difference risk that the judgment is safe but the status has changed during execution.

[0119] For example, Figure 2 This is a task execution flowchart provided in a specific embodiment of the present invention. Referring to the flowchart in Figure 2, a user makes a voice request to open the car window during a heavy rainstorm. The vehicle is traveling at 110 km / h on the highway, the rain sensor determines that it is raining heavily outside, the windshield wipers are in high speed mode, the navigation road type is highway, and the user voice inputs "open the car window". The system recognizes this as a vehicle body opening and closing control task and breaks the task down into seven nodes: identifying the control object, confirming the target window, reading the vehicle's motion status, reading the external environment, determining the window opening range, executing the window opening control, and verifying the execution result.

[0120] Hard safety gating: When the vehicle speed exceeds the preset high-speed threshold, there is heavy rain outside, the road type is high-speed, or the driver's interactive load is high, the system prohibits large window opening; if the vehicle model allows for a very small defrosting gap, the allowed action set only includes "window opening not exceeding the preset safe opening degree".

[0121] Risk propagation: Environmental risks (E) from heavy rain, high-speed motion risks (M), and voice object ambiguity (C) will propagate to the vehicle control action node, significantly increasing the risk level (R). Even if the user's intent is clear, environmental and motion risks will still cause the strategy to enter P3 or P4.

[0122] Dynamic Strategy: If the user does not specify which window to open, the system will not display a complex list, but will only ask a short voice message: "Currently, there is heavy rain on the highway, and it is not recommended to open the window; would you like to turn on the defroster or ventilation instead?" If the user insists on opening the window, the system will enter a prohibition or downgrade strategy and will not generate a message to control the window to be opened significantly.

[0123] State Lock Token: A token is generated only when the policy allows for a very small window opening. The token is bound to the vehicle speed range, rainfall level, road type, target window, and maximum opening. If the vehicle speed increases, the rainfall level rises, or the target window changes before execution, the token becomes invalid.

[0124] Closed-loop execution: If a very small window opening is performed, the system reads the window position feedback; if the actual opening exceeds the token limit, a stop or rollback control is immediately sent and the anomaly is recorded.

[0125] Figure 3 This is a structural diagram of a control strategy determination device provided in one or more embodiments of the present invention.

[0126] like Figure 3 The control strategy determination device shown includes: an execution condition determination module, an atomic node determination module, a task risk determination module, and a control strategy determination module.

[0127] The execution condition determination module is used to determine the task type of the task to be executed based on the user's request for the vehicle, and to determine the execution conditions corresponding to the task type.

[0128] The atomic node determination module is used to collect the current multi-dimensional information of the vehicle. In response to the multi-dimensional information meeting the execution conditions, the request is split and at least one atomic action node is determined.

[0129] The task risk determination module is used to calculate the execution risk of each atomic action node and determine the overall task risk.

[0130] The control strategy determination module is used to determine the control strategy corresponding to the overall risk of the task.

[0131] The task risk determination module is used to determine the sequential execution relationship between atomic action nodes; according to the sequential execution relationship, it determines the calculation order of each atomic action node, and calculates the execution risk of each atomic action node in turn based on the calculation order; among all execution risks, the maximum value of the execution risk is selected as the overall task risk.

[0132] The task risk determination module is used to determine the basic risk of each atomic action node, and to determine the unresolved risk of at least one preceding node on which the execution of the atomic action node depends; to determine the risk propagation coefficient based on the degree to which the preceding node eliminates the unresolved risk; to determine the propagation risk from the preceding node to the atomic action node based on the risk propagation coefficient and the unresolved risk; and to determine the execution risk of the atomic action node by calculating the sum of the basic risk and all propagation risks.

[0133] The control strategy determination module is used to obtain at least one pre-divided risk interval; adjust the range of each risk interval according to multi-dimensional information, and compare the adjusted risk area with the overall risk of the task to determine the first risk interval where the overall risk of the task is located; and determine the control result corresponding to the first risk interval as the requested control strategy.

[0134] The control strategy determination module is used to determine vehicle motion risk and environmental risk based on multi-dimensional information; determine the first degree of influence of vehicle speed on the risk range based on vehicle motion risk, and determine the second degree of influence of the environment on the risk range based on environmental risk; obtain the basic execution threshold, the minimum execution threshold, and the pre-set risk threshold used to divide the risk range; adjust the risk thresholds based on vehicle motion risk, environmental risk, the first degree of influence, the second degree of influence, the basic execution threshold, and the minimum execution threshold; and adjust the range of each risk range based on the adjusted risk thresholds.

[0135] The control strategy determination module is also used to read the first critical state at the time of safety determination in response to the execution of the control strategy, and form a one-time token corresponding to the control strategy; before the vehicle control interface executes the control strategy, it rereads the second critical state at the current time; if the absolute value of the difference between the first critical state and the second critical state is less than or equal to the set state drift tolerance vector, and the one-time token passes the verification, the control strategy is executed.

[0136] When a one-time token meets all the preset conditions, the one-time token passes the verification.

[0137] The preset conditions include:

[0138] The one-time token was unused and the signature is valid.

[0139] The time difference between reading the second critical state and the first critical state exceeds the validity period;

[0140] The vehicle identification number of the current vehicle is the same as the vehicle identification number included in the one-time token;

[0141] The unique identifier of the control policy is the same as the event identifier included in the one-time token;

[0142] The newly collected multi-dimensional information meets the execution conditions;

[0143] The overall risk of the recalculation task did not exceed the maximum risk threshold of the risk range where the control strategy is located.

[0144] Figure 4 This is a block diagram of an electronic device structure for a control strategy determination method provided in one or more embodiments of the present invention.

[0145] like Figure 4As shown, the present invention provides an electronic device, including: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus;

[0146] The memory stores a computer program, which, when executed by a processor, causes the processor to perform steps of a control strategy determination method.

[0147] The present invention also provides a computer-readable storage medium storing a computer program executable by an electronic device, which, when run on the electronic device, causes the electronic device to perform the steps of a control strategy determination method.

[0148] The present invention also provides a vehicle, comprising:

[0149] Electronic equipment for implementing steps of a method based on a control strategy;

[0150] The processor, which runs programs, determines the steps of the control strategy method by outputting data from electronic devices during program execution.

[0151] A storage medium used to store a program, which, during runtime, determines the steps of a method for controlling data output from an electronic device.

[0152] The communication bus mentioned in the above electronic devices can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used to represent it in the diagram, but this does not mean that there is only one bus or one type of bus.

[0153] The electronic device comprises a hardware layer, an operating system layer running on top of the hardware layer, and an application layer running on the operating system. The hardware layer includes hardware such as a central processing unit (CPU), a memory management unit (MMU), and memory. The operating system can be any one or more computer operating systems that control the electronic device through processes, such as Linux, Unix, Android, iOS, or Windows. Furthermore, in this embodiment of the invention, the electronic device can be a smartphone, tablet computer, or other handheld device, or a desktop computer, portable computer, or other electronic device; there is no particular limitation in this embodiment.

[0154] In this embodiment of the invention, the executing entity for electronic device control can be an electronic device itself, or a functional module within an electronic device capable of calling and executing a program. The electronic device can obtain the firmware corresponding to the storage medium. This firmware is provided by the supplier, and different storage media may have the same or different firmware; no limitation is made here. After obtaining the firmware corresponding to the storage medium, the electronic device can write this firmware into the storage medium; specifically, it burns the firmware corresponding to the storage medium into the storage medium. The process of burning the firmware into the storage medium can be implemented using existing technology, and will not be elaborated upon in this embodiment of the invention.

[0155] Electronic devices can also obtain reset commands corresponding to the storage media. The reset commands corresponding to the storage media are provided by the supplier. The reset commands corresponding to different storage media can be the same or different, and no restrictions are imposed here.

[0156] At this time, the storage medium of the electronic device is a storage medium on which the corresponding firmware has been written. The electronic device can respond to the reset command corresponding to the storage medium on which the corresponding firmware has been written, thereby resetting the storage medium on which the corresponding firmware has been written according to the reset command. The process of resetting the storage medium according to the reset command can be implemented by existing technology and will not be described in detail in this embodiment of the invention.

[0157] For ease of description, the above apparatus is described by dividing it into various units and modules according to their functions. Of course, in implementing this invention, the functions of each unit and module can be implemented in one or more software and / or hardware.

[0158] It will be understood by those skilled in the art that, unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. It should also be understood that terms such as those defined in general dictionaries should be understood to have the meaning consistent with their meaning in the context of the prior art, and should not be interpreted in an idealized or overly formal sense unless specifically defined.

[0159] For the sake of simplicity, the method embodiments are described as a series of actions. However, those skilled in the art should understand that the embodiments of the present invention are not limited to the described order of actions, because according to the embodiments of the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions involved are not necessarily essential to the embodiments of the present invention.

[0160] As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that the present invention can be implemented by means of software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments of the present invention.

[0161] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for determining a control strategy, characterized in that, include: Based on the user's request for the vehicle, determine the task type to be executed, and determine the execution conditions corresponding to the task type; Collect the current multi-dimensional information of the vehicle, and in response to the multi-dimensional information satisfying the execution conditions, split the request and determine at least one atomic action node; Calculate the execution risk of each atomic action node to determine the overall task risk; Determine the control strategy corresponding to the overall risk of the task.

2. The control strategy determination method according to claim 1, characterized in that, The calculation of the execution risk of each atomic action node to determine the overall task risk includes: Determine the sequential execution relationship between the atomic action nodes; According to the aforementioned execution order, the calculation order of each atomic action node is determined, and the execution risk of each atomic action node is assessed based on the calculation order. Among all the execution risks, the maximum value of the execution risks is selected as the overall task risk.

3. The control strategy determination method according to claim 2, characterized in that, The execution risks of the atomic action nodes based on the calculation order include: For each atomic action node, determine the underlying risk of the atomic action node and determine the unresolved risk of at least one preceding node on which the execution of the atomic action node depends; The risk propagation coefficient is determined based on the degree to which the preceding node eliminates the uneliminated risk. Based on the risk propagation coefficient and the unresolved risk, determine the propagation risk from the preceding node to the atomic action node; Calculate the sum of the basic risk and all propagation risks to determine the execution risk of the atomic action node.

4. The control strategy determination method according to claim 1, characterized in that, The determination of the control strategy corresponding to the overall risk of the task includes: Obtain at least one pre-defined risk zone; Based on the multi-dimensional information, the range of each risk interval is adjusted, and the adjusted risk area is compared with the overall task risk to determine the first risk interval where the overall task risk is located; The control result corresponding to the first risk interval is determined as the control strategy requested.

5. The control strategy determination method according to claim 4, characterized in that, The step of adjusting the range of each risk interval based on the multi-dimensional information includes: Based on the aforementioned multi-dimensional information, vehicle motion risks and environmental risks are determined; The first degree of influence of vehicle speed on the risk range is determined based on the vehicle motion risk, and the second degree of influence of the environment on the risk range is determined based on the environmental risk. Obtain the basic execution threshold, the minimum execution threshold, and the pre-set risk threshold used to divide the risk interval; The risk threshold is adjusted based on the vehicle motion risk, the environmental risk, the first degree of impact, the second degree of impact, the basic execution threshold, and the minimum execution threshold; Based on the adjusted risk threshold, the range of each risk interval is adjusted.

6. The control strategy determination method according to claim 1, characterized in that, After determining the control strategy corresponding to the overall risk of the task, the method further includes: In response to the control policy being executed, the first critical state at the security determination moment is read to form a one-time token corresponding to the control policy; Before executing the control strategy at the vehicle control interface, the second critical state at the current moment is reread; If the absolute value of the difference between the first critical state and the second critical state is less than or equal to the set state drift tolerance vector, and the one-time token verification passes, the control strategy is executed.

7. The control strategy determination method according to claim 6, characterized in that, The verification of the one-time token includes: When the one-time token meets all preset conditions, the one-time token passes the verification. The preset conditions include: The one-time token was unused and the signature was valid; The time difference between reading the second critical state and the first critical state exceeds the validity period; The vehicle identification number of the current vehicle is the same as the vehicle identification number included in the one-time token; The unique identifier of the control policy is the same as the event identifier included in the one-time token; The re-collected multi-dimensional information satisfies the execution conditions; The overall risk of the recalculation task did not exceed the maximum risk threshold of the risk range in which the control strategy is located.

8. A control strategy determination device, characterized in that, The method described using any one of claims 1-7 includes: The execution condition determination module is used to determine the task type of the task to be executed based on the user's request for the vehicle, and to determine the execution conditions corresponding to the task type. An atomic node determination module is used to collect the current multi-dimensional information of the vehicle, and in response to the multi-dimensional information satisfying the execution conditions, to split the request and determine at least one atomic action node. The task risk determination module is used to calculate the execution risk of each atomic action node and determine the overall task risk. The control strategy determination module is used to determine the control strategy corresponding to the overall risk of the task.

9. A computer-readable storage medium, characterized in that, The device stores a computer program executable by an electronic device, which, when run on the electronic device, causes the electronic device to perform the steps of the control strategy determination method as described in any one of claims 1 to 7.

10. A vehicle, characterized in that, include: An electronic device for implementing the steps of the control strategy determination method as described in any one of claims 1 to 7; A processor that runs a program that, when the program is running, performs the steps of the control strategy determination method as described in any one of claims 1 to 7 from data output by the electronic device. A storage medium for storing a program that, when running, performs the steps of the control strategy determination method as described in any one of claims 1 to 7 on data output from an electronic device.

Images