CN-121999549-A - Vehicle unlocking method, device, equipment, computer readable storage medium and computer program product

CN121999549ACN 121999549 ACN121999549 ACN 121999549ACN-121999549-A

Abstract

The application provides a vehicle unlocking method, a device, equipment, a computer readable storage medium and a computer program product, wherein the method comprises the steps that the vehicle unlocking device obtains a plurality of groups of RSSIs and a plurality of groups of differential signals corresponding to the plurality of groups of RSSIs, each group of RSSIs in the plurality of groups of RSSIs is a signal sent by user equipment, an unlocking recognition result or a locking recognition result is determined according to the plurality of groups of RSSIs and the plurality of groups of differential signals by utilizing an unlocking AI model and an unlocking logic judgment rule, the unlocking AI model is a model obtained by training a plurality of groups of sample RSSIs and a plurality of groups of sample differential signals corresponding to the plurality of groups of sample RSSIs when historical unlocking is successful, and corresponding unlocking operation or locking operation is executed according to the unlocking recognition result or the locking recognition result. According to the application, the accuracy of unlocking the vehicle can be improved.

Inventors

LI ZHIWEI
LI JUAN
ZHU YIFEI

Assignees

北京罗克维尔斯科技有限公司

Dates

Publication Date: 20260508
Application Date: 20241105

Claims (15)

1.A vehicle unlatching method, the method comprising: acquiring a plurality of groups of RSSIs and a plurality of groups of differential signals corresponding to the plurality of groups of RSSIs, wherein each group of RSSI in the plurality of groups of RSSIs is a signal sent by user equipment; Determining an unlocking recognition result or a locking recognition result according to the multiple groups of RSSIs and the multiple groups of differential signals by using an unlocking AI model and an unlocking logic judgment rule, wherein the unlocking AI model is a model obtained by training multiple groups of sample RSSIs and multiple groups of sample differential signals corresponding to the multiple groups of sample RSSIs when historical unlocking is successful; And executing corresponding unlocking operation or locking operation according to the unlocking identification result or the locking identification result.
2. The method of claim 1, wherein determining a latch identification result from the plurality of sets of RSSI and the plurality of sets of differential signals using a latch-up AI model and a latch-up logic decision rule comprises: Determining a first blocking identification result according to the plurality of sets of RSSIs and the plurality of sets of differential signals by using a blocking AI model in the unblocking AI model; Determining a second locking recognition result according to the unlocking logic judgment rule and the multiple groups of RSSIs; and determining the locking recognition result according to the first locking recognition result and the second locking recognition result.
3. The method of claim 2, wherein said determining a second lockout identification result based on said unlocking logic decision rule and said plurality of sets of RSSI comprises: Acquiring a locking logic judgment threshold value from the unlocking logic judgment rule; Determining comparison results of the multiple groups of RSSIs and the locking logic judgment threshold value respectively; And determining the second locking recognition result according to the comparison result.
4. The method of claim 2, wherein the determining the latch identification result based on the first latch identification result and the second latch identification result comprises: and determining the lock as the lock identification result under the condition that the first lock identification result and the second lock identification result both identify the lock.
5. The method of claim 4, wherein the determining a latch as the latch identification result if both the first latch identification result and the second latch identification result identify a latch, comprises: when the second locking recognition result is locking, the first locking state machine is adjusted to be in a setting state; when the first locking identification result is locking, a second locking state machine is adjusted to be in a setting state; and under the condition that the first locking state machine and the second locking state machine are both in a set state, locking is used as the locking identification result.
6. The method of claim 5, wherein after performing the corresponding latch operation according to the latch identification result, the method further comprises: Adjusting the states of the first locking state machine and the second locking state machine to a non-setting state when any door in the target vehicle is in an open state; Or when the vehicle controller of the target vehicle is switched from the sleep state to the wake state, the states of the first locking state machine and the second locking state machine are adjusted to be non-setting states; or under the condition that the target vehicle executes and completes corresponding locking operation, the states of the first locking state machine and the second locking state machine are adjusted to be non-setting states.
7. The method of claim 1, wherein determining an unlock recognition result from the plurality of sets of RSSI and the plurality of sets of differential signals using an unlock AI model and an unlock logic decision rule comprises: inputting the multiple groups of RSSIs and the multiple groups of differential signals into an unlocking AI model in the unlocking AI models to obtain a first unlocking identification result; determining a second unlocking recognition result according to the unlocking logic judgment rule and the multiple groups of RSSIs; and determining the first unlocking recognition result as the unlocking recognition result when the first unlocking recognition result is unlocking, or determining the second unlocking recognition result as the unlocking recognition result when the second unlocking recognition result is unlocking.
8. The method of claim 7, wherein the method further comprises: determining a position area where the user equipment is located according to the multiple groups of RSSIs; Determining the first unlocking recognition result as the unlocking recognition result when the position area is not the tail area of the target vehicle and the first unlocking recognition result is unlocking, or determining the second unlocking recognition result as the unlocking recognition result when the position area is not the tail area of the target vehicle and the second unlocking recognition result is unlocking; And determining the second unlocking recognition result as the unlocking recognition result under the condition that the position area is the tail area of the target vehicle.
9. The method of claim 1, wherein prior to determining an unlock recognition result or a lock recognition result from the plurality of sets of RSSI and the plurality of sets of differential signals using the unlock AI model and the unlock logic decision rule, the method further comprises: acquiring a plurality of groups of sample RSSIs and a plurality of groups of sample differential signals corresponding to the plurality of groups of sample RSSIs and sample unlocking operation results corresponding to the plurality of groups of sample RSSIs and the plurality of groups of sample differential signals when historical unlocking is performed; Training an initial unlocking AI model according to the RSSIs of the multiple groups of samples, the differential signals of the multiple groups of samples and the sample unlocking operation result to obtain the unlocking AI model, wherein an initial unlocking model in the initial unlocking AI model comprises an initial convolutional neural network and an initial circulating neural network, and an initial locking model in the initial unlocking AI model comprises the initial convolutional neural network and the initial circulating neural network.
10. The method of claim 9, wherein training an initial unblocking AI model based on the plurality of sets of sample RSSI, the plurality of sets of sample differential signals, and the sample unblocking operation results to obtain the unblocking AI model comprises: Inputting the multiple groups of sample RSSIs and the multiple groups of sample differential signals into an initial unlocking AI model to obtain an output unlocking identification result; Determining binary cross entropy loss of the initial unlocking AI model according to the output unlocking identification result and the sample unlocking operation result; Under the condition that the binary cross entropy loss is greater than or equal to a preset loss threshold value, continuously training an initial unlocking AI model by using the RSSI of the plurality of groups of samples, the differential signals of the plurality of groups of samples and the sample unlocking operation result to obtain a training model; and under the condition that the corresponding binary training cross entropy loss of the training model is smaller than or equal to the preset loss threshold value, taking the training model as the deblocking AI model.
11. The method according to claim 1, wherein the method further comprises: Performing a lockout operation in the event that a communication link between the user device and the target vehicle is broken; Or executing locking operation under the condition that the values of the plurality of groups of RSSIs are smaller than or equal to a preset threshold value.
12. A vehicle unlatching apparatus, characterized in that the apparatus comprises: The system comprises an acquisition unit, a detection unit and a control unit, wherein the acquisition unit is used for acquiring a plurality of groups of RSSIs and a plurality of groups of differential signals corresponding to the plurality of groups of RSSIs; The determining unit is used for determining an unlocking recognition result or a locking recognition result according to the multiple groups of RSSIs and the multiple groups of differential signals by utilizing an unlocking AI model and an unlocking logic judgment rule, wherein the unlocking AI model is a model obtained by training multiple groups of sample RSSIs and multiple groups of sample differential signals corresponding to the multiple groups of sample RSSIs when historical unlocking is successful; And the execution unit is used for executing corresponding unlocking operation or locking operation according to the unlocking identification result or locking identification result.
13. A vehicle unlatching apparatus, characterized in that the apparatus comprises: a memory for storing computer executable instructions; A processor for implementing the method of any one of claims 1 to 9 when executing computer-executable instructions stored in the memory.
14. A computer readable storage medium storing computer executable instructions which when executed by a processor implement the method of any one of claims 1 to 11.
15. A computer program product comprising computer-executable instructions or a computer program, which, when executed by a processor, implements the method of any one of claims 1 to 11.

Description

Vehicle unlocking method, device, equipment, computer readable storage medium and computer program product Technical Field The present application relates to the field of automobile control technology, and in particular, to a vehicle unlocking method, device, apparatus, computer readable storage medium and computer program product. Background Under the background of continuous progress of automobile intellectualization, more and more vehicles adopt keyless entry function, and convenience is provided for users to unlock the vehicles or lock the vehicles. Typically, a bluetooth key is used to perform an unlocking or locking function for the vehicle. In the related art, a bluetooth key determines whether to unlock or lock based on a judgment of a logic rule, that is, a signal strength threshold is set, a received signal strength Indication (RECEIVED SIGNAL STRENGTH Indication, RSSI) of a user's device received by a bluetooth module in a vehicle is compared with the set signal strength threshold, and whether to unlock or lock is determined according to a comparison result. Since such unlocking or locking is easily affected by environments, device differences and usage patterns, the accuracy of the determination result of unlocking or locking is insufficient. For example, when the vehicle is in a locked state and the user's equipment is placed in a user bag or is blocked by the user's body, the intensity of the RSSI signal received by the Bluetooth module in the vehicle is reduced, so that the vehicle deviates from calibration data, and unlocking fails. Disclosure of Invention The embodiment of the application provides a vehicle unlocking method, device, equipment, a computer readable storage medium and a computer program product, which can improve the accuracy of vehicle unlocking. The technical scheme of the embodiment of the application is realized as follows: the embodiment of the application provides a vehicle unlocking method, which comprises the following steps: acquiring a plurality of groups of RSSIs and a plurality of groups of differential signals corresponding to the plurality of groups of RSSIs, wherein each group of RSSI in the plurality of groups of RSSIs is a signal sent by user equipment; Determining an unlocking recognition result or a locking recognition result according to the multiple groups of RSSIs and the multiple groups of differential signals by using an unlocking AI model and an unlocking logic judgment rule, wherein the unlocking AI model is a model obtained by training multiple groups of sample RSSIs and multiple groups of sample differential signals corresponding to the multiple groups of sample RSSIs when historical unlocking is successful; And executing corresponding unlocking operation or locking operation according to the unlocking identification result or the locking identification result. In the above solution, the determining, by using the unblocking AI model and the unblocking logic decision rule, a blocking identification result according to the plurality of sets of RSSI and the plurality of sets of differential signals includes: Determining a first blocking identification result according to the plurality of sets of RSSIs and the plurality of sets of differential signals by using a blocking AI model in the unblocking AI model; Determining a second locking recognition result according to the unlocking logic judgment rule and the multiple groups of RSSIs; and determining the locking recognition result according to the first locking recognition result and the second locking recognition result. In the above solution, the determining, according to the unlocking logic determining rule and the multiple sets of RSSI, a second locking identification result includes: Acquiring a locking logic judgment threshold value from the unlocking logic judgment rule; Determining comparison results of the multiple groups of RSSIs and the locking logic judgment threshold value respectively; And determining the second locking recognition result according to the comparison result. In the above aspect, the determining the latch identification result according to the first latch identification result and the second latch identification result includes: and determining the lock as the lock identification result under the condition that the first lock identification result and the second lock identification result both identify the lock. In the above aspect, the determining, when the first latch identification result and the second latch identification result each identify a latch, the latch as the latch identification result includes: when the second locking recognition result is locking, the first locking state machine is adjusted to be in a setting state; when the first locking identification result is locking, a second locking state machine is adjusted to be in a setting state; and under the condition that the first locking state machine and the second locking state machine are both in a set state