Vehicle unlocking and locking control method, device, equipment, medium and vehicle

Abstract

The invention relates to a vehicle unlocking and locking control method, device and equipment, a medium and a vehicle. The vehicle unlocking and locking control method comprises the steps that the signal strength of a Bluetooth signal sent by a target Bluetooth key is obtained; the signal intensity, the vehicle body data of the target vehicle and the position information of the target vehicle are input into a trained judgment model, so that the trained judgment model carries out judgment processing to obtain a corresponding judgment result, and the judgment result is used for representing an unlocking and locking intention of the Bluetooth signal; wherein the judgment model stores the corresponding relation among the signal intensity, the vehicle body data, the position information and the unlocking and locking intention; and controlling a target vehicle lock of the target vehicle to perform unlocking and locking operation according to the unlocking and locking intention, wherein the unlocking and locking operation is used for enabling the target vehicle lock to be in an unlocking and locking state corresponding to the unlocking and locking intention. According to the embodiment of the invention, the judgment precision can be improved, and wrong unlocking and locking operations can be avoided.

Description

Technical Field

[0001] The present disclosure relates to the field of vehicle control technology, and in particular to a vehicle unlocking control method, device, equipment, medium and vehicle. Background Art

[0002] By comparing the received signal strength indication (RSSI) of the Bluetooth node calibrated at the specified position of the vehicle body with the RSSI of the Bluetooth signal actually received and sent by the Bluetooth key, the distance position between the Bluetooth key and the vehicle body is determined, and it is judged that the distance position is within the target area of ​​the pre-defined area, and the unlocking / locking operation is performed based on the unlocking / locking command action pre-specified in the target area.

[0003] However, the RSSI of the Bluetooth signal sent by the Bluetooth key received by the Bluetooth node is unstable, that is, the distance position determined by comparing the RSSI of the actual received Bluetooth signal with the RSSI calibrated at the specified position is inaccurate, and control is only performed through a pre-demarcated area, which may result in large errors and lead to erroneous unlocking operations. Summary of the invention

[0004] In order to solve the above technical problems, the present disclosure provides a vehicle unlocking control method, device, equipment, medium and vehicle.

[0005] In a first aspect, the present disclosure provides a vehicle unlocking control method, comprising:

[0006] Get the signal strength of the Bluetooth signal emitted by the target Bluetooth key;

[0007] Inputting the signal strength, the body data of the target vehicle and the location information of the target vehicle into a trained decision model, so that the trained decision model performs decision processing to obtain a corresponding decision result, and the decision result is used to characterize the unlocking intention of the Bluetooth signal; wherein the decision model saves the corresponding relationship between the signal strength, the body data, the location information and the unlocking intention;

[0008] The target vehicle lock of the target vehicle is controlled to perform an unlocking operation according to the unlocking intention, and the unlocking operation is used to put the target vehicle lock in an unlocking state corresponding to the unlocking intention.

[0009] In a second aspect, the present disclosure provides a vehicle unlocking control device, comprising:

[0010] A first acquisition module, used to acquire the signal strength of the Bluetooth signal emitted by the target Bluetooth key;

[0011] A first processing module is used to input the signal strength, the body data of the target vehicle and the location information of the target vehicle into a trained decision model, so that the trained decision model performs decision processing to obtain a corresponding decision result, and the decision result is used to characterize the unlocking intention of the Bluetooth signal; wherein the decision model saves the corresponding relationship between the signal strength, the body data, the location information and the unlocking intention;

[0012] The vehicle control module is used to control the target vehicle lock of the target vehicle to perform an unlocking operation according to the unlocking intention, and the unlocking operation is used to put the target vehicle lock in an unlocking state corresponding to the unlocking intention.

[0013] In a third aspect, the present disclosure provides a vehicle unlocking control device, comprising:

[0014] processor;

[0015] A memory for storing executable instructions;

[0016] The processor is used to read executable instructions from the memory and execute the executable instructions to implement the vehicle unlocking control method of the first aspect.

[0017] In a fourth aspect, the present disclosure provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the processor implements the vehicle unlocking control method of the first aspect.

[0018] In a fifth aspect, the present disclosure provides a vehicle, comprising the vehicle unlocking control device as described above.

[0019] Compared with the prior art, the technical solution provided by the embodiments of the present disclosure has the following advantages:

[0020] The vehicle unlocking control method, device, equipment, medium and vehicle of the embodiment of the present disclosure can obtain the signal strength of the Bluetooth signal emitted by the target Bluetooth key, and then input the signal strength, the body data and the position information of the target vehicle into the trained decision model, so that the trained decision model performs decision processing to obtain the corresponding decision result, and the decision result is used to characterize the unlocking intention of the Bluetooth signal, wherein the decision model saves the corresponding relationship between the signal strength, the body data, the position information and the unlocking intention, and finally controls the target vehicle lock of the target vehicle to perform an unlocking operation according to the unlocking intention, and the unlocking operation is used to put the target vehicle lock in an unlocking state corresponding to the unlocking intention. Therefore, compared with the prior art that only judges the distance and position by the strength of the Bluetooth signal, a large error will occur. In the present disclosure, multiple data such as signal strength, body data and position information can be combined for decision processing to obtain an accurate decision result, thereby improving the decision accuracy and avoiding the operation of erroneous unlocking. In addition, the unlocking operation based on the trained decision model of the present disclosure is more intelligent and efficient. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale.

[0022] Figure 1 A schematic flow chart of a vehicle unlocking control method provided by an embodiment of the present disclosure;

[0023] Figure 2 A schematic diagram of an unlocking state provided by an embodiment of the present disclosure;

[0024] Figure 3 A flowchart of a model training method provided in an embodiment of the present disclosure;

[0025] Figure 4 A schematic diagram of the structure of a vehicle unlocking control device provided by an embodiment of the present disclosure;

[0026] Figure 5 A schematic structural diagram of a vehicle unlocking control device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0027] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0028] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0029] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0030] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0031] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0032] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0033] In order to solve the above problems, the embodiments of the present disclosure provide a vehicle unlocking control method, device, equipment, medium and vehicle. Figures 1 to 3 The vehicle unlocking control method provided by the embodiment of the present disclosure is described in detail.

[0034] Figure 1 A flow chart of a vehicle unlocking control method provided by an embodiment of the present disclosure is shown.

[0035] In the disclosed embodiment, the vehicle unlocking control method may be executed by a processor of an electronic device having a vehicle unlocking control function. Specifically, the electronic device may include but is not limited to a mobile terminal such as a mobile phone, an in-vehicle device, a vehicle controller, a tablet computer, a wearable device, etc.

[0036] like Figure 1 As shown, the vehicle unlocking control method may include the following steps.

[0037] S110: Acquire the signal strength of the Bluetooth signal emitted by the target Bluetooth key.

[0038] In the embodiment of the present disclosure, the electronic device can obtain the signal strength of the Bluetooth signal emitted by the target Bluetooth key.

[0039] Optionally, the target Bluetooth key may be a key for controlling a Bluetooth connection with the vehicle.

[0040] Optionally, the signal strength may be the signal strength of a Bluetooth signal emitted by a target Bluetooth key.

[0041] Specifically, the target Bluetooth key can be connected to the vehicle via Bluetooth, the target Bluetooth key can send a Bluetooth signal to the vehicle, and the electronic device can receive the Bluetooth signal and determine the corresponding signal strength.

[0042] S120, inputting the signal strength, the body data and the location information of the target vehicle into the trained decision model, so that the trained decision model performs decision processing to obtain a corresponding decision result, and the decision result is used to characterize the unlocking intention of the Bluetooth signal; wherein the decision model saves the corresponding relationship between the signal strength, the body data, the location information and the unlocking intention.

[0043] In the disclosed embodiment, the electronic device may input the signal strength, body data and location information of the target vehicle into a trained decision model, so that the trained decision model performs decision processing to obtain a corresponding decision result.

[0044] Optionally, the target vehicle may be a vehicle connected to a target Bluetooth key.

[0045] Optionally, the vehicle body data may be data representing the state of the target vehicle itself. For example, the vehicle body data may be data representing the state of the target vehicle being charged, the state of the target vehicle being repaired, etc., which is not limited here.

[0046] Optionally, the position information may be positioning position information characterizing the target vehicle. For example, the position information may be acquired through a global positioning system (GPS).

[0047] Optionally, the decision process may be a process of deciding whether to release the locking control.

[0048] Optionally, the judgment result may be a characterization of an unlocking control result. The judgment result is used to characterize the unlocking intention of the Bluetooth signal. For example, the judgment result may be a characterization that after receiving the Bluetooth signal, the intention of the Bluetooth signal is an unlocking intention or a locking intention.

[0049] The decision model stores the corresponding relationship between the signal strength, the vehicle body data, the location information and the unlocking intention.

[0050] Specifically, the electronic device can input the acquired signal strength, body data and location information of the target vehicle into a trained decision model. The trained decision model can perform decision processing on the signal strength, body data and location information to obtain a corresponding decision result.

[0051] S130. Controlling a target vehicle lock of the target vehicle to perform an unlocking operation according to the unlocking intention, where the unlocking operation is used to put the target vehicle lock in an unlocking state corresponding to the unlocking intention.

[0052] In the disclosed embodiment, the electronic device may control the target vehicle lock of the target vehicle to perform an unlocking operation according to the unlocking intention.

[0053] Optionally, the target vehicle lock may be a vehicle lock that can be controlled by the target vehicle. For example, the target vehicle lock may include at least one of a door lock, a trunk lock, etc., which is not limited here.

[0054] Optionally, the unlocking operation may be an operation of unlocking or locking the target vehicle lock.

[0055] Specifically, after obtaining the judgment result, the electronic device can control the target vehicle lock of the target vehicle to perform an unlocking operation according to the unlocking intention represented by the judgment result. For example, when the unlocking intention is to unlock the target vehicle lock, the electronic device can control the target vehicle lock to perform an unlocking operation; when the unlocking intention is to lock the target vehicle lock, the electronic device can control the target vehicle lock to perform a locking operation.

[0056] Therefore, in the embodiment of the present disclosure, the signal strength of the Bluetooth signal emitted by the target Bluetooth key can be obtained, and then the signal strength, the body data and the position information of the target vehicle are input into the trained decision model, so that the trained decision model performs decision processing to obtain a corresponding decision result, and the decision result is used to characterize the unlocking intention of the Bluetooth signal, and finally the target vehicle lock of the target vehicle is controlled to perform an unlocking operation according to the unlocking intention, and the unlocking operation is used to put the target vehicle lock in an unlocked state corresponding to the unlocking intention. Therefore, the signal strength, the body data and the position information can be combined for decision processing to obtain a corresponding decision result, thereby improving the decision accuracy and avoiding erroneous unlocking operations.

[0057] Optionally, after the signal strength, body data and location information of the target vehicle are input into a trained decision model, the vehicle unlocking control method may further include: performing field feature conversion on the original data of the signal strength, the body data and the location information respectively through a feature conversion layer in the trained decision model to obtain a plurality of unified input feature data corresponding to the signal strength, the body data and the location information.

[0058] Optionally, the feature conversion layer may be a processing layer that converts raw data into suitable processed data.

[0059] Optionally, the feature data may be data obtained after feature conversion.

[0060] Optionally, the field feature conversion may be an algorithm for performing data conversion through a feature conversion algorithm. For example, the feature conversion algorithm may be a logarithmic transformation algorithm, a reciprocal transformation algorithm, a square root translation algorithm, etc., which are not limited here.

[0061] Optionally, the plurality of input feature data have a unified feature form.

[0062] Specifically, after obtaining the signal strength, vehicle body data and location information, the electronic device can perform field feature conversion on the original data of the signal strength, vehicle body data and location information based on the feature conversion layer in the trained decision model, that is, convert the signal strength, vehicle body data and location information into data with a unified feature form, and output corresponding multiple feature data with a unified feature form.

[0063] Furthermore, S120 may specifically include: based on the intention recognition layer in the trained decision model, performing data mapping processing on the multiple unified input feature data to determine the corresponding decision result.

[0064] Optionally, the intent recognition layer may be an algorithm that encodes and decodes data through a converter algorithm. For example, the converter algorithm may be a transformer algorithm.

[0065] Optionally, the encoding process may be to convert and encode the data according to a preset rule.

[0066] Optionally, the decoding process may be decoding and processing the encoded data.

[0067] Optionally, the data mapping process may be to determine a corresponding decision result according to a preset mapping relationship.

[0068] Specifically, the electronic device can perform data mapping processing on multiple unified input feature data through the intention recognition layer in the trained decision model, that is, determine the decision results corresponding to the multiple unified input feature data according to the preset mapping relationship.

[0069] Therefore, in the model decision input, not only the Bluetooth signal strength is considered, but also the vehicle body data and location information are introduced to achieve scene-related decisions and improve decision accuracy.

[0070] Optionally, the training process of training the decision model includes: obtaining a training sample set; wherein, for any sample in the training sample set, the sample includes: historical signal strength, historical vehicle body data and historical location information, and a corresponding first state label, wherein the first state label is used to characterize the labeled unlocked state corresponding to the sample; inputting the sample into the original decision model to obtain a predicted unlocked state output by the original decision model; based on the first state label and the predicted unlocked state, training the original decision model to obtain the trained decision model.

[0071] In an embodiment of the present disclosure, the electronic device may obtain a training sample set.

[0072] Optionally, the training sample set may be a sample set used for model training, wherein the training sample set may include multiple samples.

[0073] Optionally, the sample may include historical signal strength, historical vehicle body data and historical location information, and a corresponding first state label.

[0074] Optionally, the historical signal strength may represent the strength of a Bluetooth signal between a target Bluetooth key and a target vehicle within a historical time period.

[0075] Optionally, the historical vehicle body data may be a signal representing the state of the target vehicle itself within a historical time period.

[0076] Optionally, the historical position information may be positioning position information representing the target vehicle within a historical time period.

[0077] Optionally, the first state label may be used to characterize a label unlock state corresponding to the sample.

[0078] Specifically, the electronic device may obtain a training sample set, and any sample in the training sample set may include historical signal strength, historical vehicle body data and historical location information, and a corresponding first state label.

[0079] Furthermore, the electronic device may mark the historical signal strength, the historical vehicle body data and the historical location information, and the corresponding unlocking result status with an unlocking status to obtain a corresponding first status label.

[0080] Optionally, the unlocked state label may be used to mark the unlocked state.

[0081] Specifically, the electronic device can mark the unlocking status of the historical signal strength, historical vehicle body data and historical location information, as well as the corresponding unlocking result status, that is, instead of marking the specific time, it marks the time sequence transition of the status (such as: locked status -> unlocking instruction -> unlocked status) to obtain the first status label.

[0082] As a result, there is no need for manual labeling and data collection, and historical data can be used for automatic labeling to improve labeling speed and accuracy.

[0083] Figure 2 A schematic diagram of an unlocking state marking provided by an embodiment of the present disclosure is shown.

[0084] like Figure 2 As shown, the upper part is the state timing transition from the locked state to the unlocked state for the target vehicle, and the unlocking time period is marked by the shortest unlocking time and the longest unlocking time. The lower part is the state timing transition from the unlocked state to the locked state for the target vehicle, and the locking time period is marked by the shortest locking time and the longest locking time.

[0085] Optionally, the vehicle unlocking control method may also include: inputting the sample into the original decision model to obtain the predicted unlocking state output by the original decision model; training the original decision model based on the first state label and the predicted unlocking state to obtain the trained decision model.

[0086] In the embodiment of the present disclosure, the electronic device may: input the sample into the original decision model to obtain the predicted unlocking state output by the original decision model.

[0087] Optionally, the predicted unlocking state may be a result obtained by processing through an original decision model.

[0088] Specifically, the electronic device may input the sample into the original decision model, thereby obtaining the predicted unlocking state output by the original decision model.

[0089] Furthermore, the electronic device may train the original decision model based on the first state label and the predicted unlocking state to obtain the trained decision model.

[0090] Specifically, the electronic device can train the original decision model according to the first state label and the predicted unlocked state, such as performing loss calculation on the original decision model according to the first state label and the predicted unlocked state, such as the loss calculation can be calculated through a connection temporal classification loss function (CTC loss), so as to obtain the trained decision model.

[0091] Figure 3 A flow chart of a model training method provided by an embodiment of the present disclosure is shown.

[0092] like Figure 3 As shown, the electronic device can first obtain a training sample set, wherein any sample in the training sample set includes historical signal strength, historical vehicle body data and historical location information, and a corresponding first state label, and the historical signal strength, historical vehicle body data and historical location information are marked with an unlocked state to obtain the first state label, and then the acquired historical signal strength, historical vehicle body data and historical location information are converted into field features and converted into unified input feature data, and then the model is trained through the encoder and converter (Transformer) in the intent recognition layer to obtain the original decision model, and finally the loss of the original decision model is calculated according to the first state label, that is, it is calculated through the connection temporal classification loss function (CTC loss), and the parameters of the original decision model are adjusted based on the loss to obtain the trained decision model.

[0093] Optionally, after S120, the vehicle unlocking control method may further include: determining whether the current time satisfies a preset model adjustment condition, wherein the preset model adjustment condition includes that the number of times the model outputs a judgment result is greater than a preset number threshold and / or the time the model is used is greater than a preset time threshold; if so, determining the second state label corresponding to each interaction data in the time period corresponding to the current time to the time when the model was last adjusted; determining the target accuracy rate corresponding to the judgment model based on the second state label corresponding to each interaction data and the judgment result of each interaction data output by the judgment model; wherein the interaction data includes signal strength, vehicle body data and vehicle location information; when the target accuracy rate is lower than the preset threshold, performing incremental training on the trained judgment model through each interaction data to obtain an updated judgment model.

[0094] In an embodiment of the present disclosure, the electronic device may determine whether the current time satisfies a preset model adjustment condition.

[0095] Optionally, the preset model adjustment condition may include that the number of times the model outputs a judgment result is greater than a preset number threshold and / or the time the model is used is greater than a preset time threshold.

[0096] Optionally, the preset number threshold may be a pre-set threshold.

[0097] Optionally, the preset time threshold may be a pre-set threshold.

[0098] Specifically, the electronic device can determine whether the current time meets the preset model adjustment conditions, such as whether the current time satisfies the number of times the model outputs the judgment result is greater than the preset number threshold, and / or whether the current time satisfies the time the model is used is greater than the preset time threshold.

[0099] Further, after the electronic device determines the current time, if the current time satisfies the preset model adjustment condition, it determines the second state label corresponding to each interaction data within the time period corresponding to the current time to the time when the model was last adjusted;

[0100] Optionally, the interaction data may be data of interaction between the Bluetooth key and the vehicle, wherein the interaction data includes signal strength, vehicle body data and vehicle location information.

[0101] Optionally, the second state tag may be used to represent an unlock state corresponding to the interaction data.

[0102] Specifically, if the current time satisfies the preset model adjustment condition, the electronic device can determine the second state label corresponding to each interaction data within the time period corresponding to the current time to the time when the model was last adjusted.

[0103] Furthermore, the electronic device may output a judgment result of each interaction data according to the second state label corresponding to each interaction data and the judgment model, and determine a target accuracy rate corresponding to the judgment model.

[0104] Specifically, the electronic device can determine the second state label corresponding to each interaction data, and output the judgment result of each interaction data through the judgment model, and compare the second state label with the judgment result to determine the target accuracy corresponding to the judgment model.

[0105] Furthermore, after determining the target accuracy, the electronic device performs incremental training on the trained decision model through each interaction data to obtain an updated decision model when the target accuracy is lower than a preset threshold.

[0106] Optionally, the preset threshold may be a pre-set threshold, for example, the preset threshold may be 80%, 70%, etc., which is not limited here.

[0107] Optionally, the incremental training may be online model training for a trained decision model.

[0108] Specifically, after determining the target accuracy, the electronic device can determine whether the target accuracy is lower than a preset threshold. If the target accuracy is lower than the preset threshold, the trained decision model is incrementally trained through each interaction data to obtain an updated decision model.

[0109] Therefore, the trained decision model is trained through online learning, so that the decision result is more in line with the user's personalized behavior and the decision accuracy is improved.

[0110] Optionally, the process of obtaining the second state label corresponding to each interaction data may include: for each interaction data, if no unblocking exception feedback input by the user is received within a preset time length after the judgment model outputs the judgment result of the interaction data, then the judgment result of the user output by the judgment model is determined as the second state label corresponding to the interaction data; if an unblocking exception feedback input by the user is received within a preset time length after the judgment model outputs the judgment result of the interaction data, then the target judgment result carried in the unblocking exception feedback is determined as the second state label corresponding to the interaction data; wherein, the target judgment result is different from the judgment result output by the judgment model for the interaction data.

[0111] In some embodiments of the present disclosure, for each interaction data, if no unlocking exception feedback input by the user is received within a preset time length after the judgment model outputs the judgment result of the interaction data, the electronic device can determine the judgment result of the user output by the judgment model as the second state label corresponding to the interaction data.

[0112] Optionally, the unlocking abnormality feedback may be a user feeding back to the electronic device that the determination result is abnormal.

[0113] Specifically, for each interaction data, if the electronic device does not receive the unlocking exception feedback input by the user within a preset time length after the judgment model outputs the judgment result of the interaction data, the judgment result of the user output by the judgment model can be determined as the second state label corresponding to the interaction data.

[0114] In other embodiments of the present disclosure, if an unblocking exception feedback input by a user is received within a preset time length after the judgment model outputs the judgment result of the interaction data, the target judgment result carried in the unblocking exception feedback is determined as the second state label corresponding to the interaction data.

[0115] Specifically, for each interaction data, if the electronic device receives an unblocking exception feedback input by the user within a preset time length after the judgment model outputs the judgment result of the interaction data, the target judgment result carried in the unblocking exception feedback can be determined as the second state label corresponding to the interaction data.

[0116] Optionally, the target judgment result is different from the judgment result of the interaction data output by the judgment model.

[0117] Figure 4 A schematic structural diagram of a vehicle unlocking control device provided in an embodiment of the present disclosure is shown.

[0118] In some embodiments of the present disclosure, Figure 4 The vehicle unlocking control device shown can be arranged in an electronic device. Specifically, the electronic device can include but is not limited to mobile terminals such as mobile phones, vehicle-mounted devices, vehicle controllers, tablet computers, wearable devices, etc.

[0119] like Figure 4 As shown, the vehicle unlocking control device 400 may include a first acquisition module 410 , a first processing module 420 and a vehicle control module 430 .

[0120] The first acquisition module 410 may be used to acquire the signal strength of the Bluetooth signal emitted by the target Bluetooth key.

[0121] The first processing module 420 can be used to input the signal strength, the body data of the target vehicle and the location information of the target vehicle into a trained decision model, so that the trained decision model performs decision processing to obtain a corresponding decision result, and the decision result is used to characterize the unlocking intention of the Bluetooth signal; wherein the decision model saves the correspondence between the signal strength, the body data, the location information and the unlocking intention.

[0122] The vehicle control module 430 may be configured to control a target vehicle lock of the target vehicle to perform an unlocking operation according to the unlocking intention, wherein the unlocking operation is configured to place the target vehicle lock in an unlocking state corresponding to the unlocking intention.

[0123] Therefore, in the embodiment of the present disclosure, the signal strength of the Bluetooth signal emitted by the target Bluetooth key can be obtained, and then the signal strength, the body data and the position information of the target vehicle are input into the trained decision model, so that the trained decision model performs decision processing to obtain the corresponding decision result, and the decision result is used to characterize the unlocking intention of the Bluetooth signal, wherein the decision model saves the correspondence between the signal strength, the body data, the position information and the unlocking intention, and finally controls the target vehicle lock of the target vehicle to perform an unlocking operation according to the unlocking intention, and the unlocking operation is used to put the target vehicle lock in an unlocked state corresponding to the unlocking intention. Therefore, compared with the prior art in which the distance position is judged only by the strength of the Bluetooth signal, a large error will occur. In the present disclosure, multiple data such as signal strength, body data and position information can be combined for decision processing to obtain an accurate decision result, thereby improving the decision accuracy and avoiding erroneous unlocking operations.

[0124] In some embodiments of the present disclosure, the first processing module 420 may specifically include a first processing unit and a second processing unit.

[0125] The first processing unit can be used to perform field feature conversion on the original data of the signal strength, the vehicle body data and the location information based on the feature conversion layer in the trained decision model, so as to obtain multiple unified input feature data corresponding to the signal strength, the vehicle body data and the location information.

[0126] The second processing unit can be used to perform data mapping processing on the multiple unified input feature data based on the intention recognition layer in the trained decision model to determine the corresponding decision results.

[0127] In some embodiments of the present disclosure, the vehicle unlocking control device 400 may further include a second acquisition module, a second processing module and a first training module.

[0128] The second acquisition module can be used to obtain a training sample set. For any sample in the training sample set, the sample includes: historical signal strength, historical vehicle body data and historical location information, and a corresponding first state label, wherein the first state label is used to characterize the labeled unlock state corresponding to the sample.

[0129] The second processing module may be used to input the sample into an original decision model to obtain a predicted unlocking state output by the original decision model.

[0130] The first training module can be used to train the original decision model based on the first state label and the predicted unlocking state to obtain the trained decision model.

[0131] In some embodiments of the present disclosure, the vehicle unlocking control device 400 may further include a first determination module, a second determination module, a third determination module and a second training module.

[0132] The first determination module can be used to input the signal strength, the body data of the target vehicle and the location information of the target vehicle into a trained decision model so that the trained decision model performs decision processing and obtains the corresponding decision result, and then determine whether the current time meets the preset model adjustment conditions, wherein the preset model adjustment conditions include that the number of times the model outputs the decision result is greater than a preset number threshold and / or the time the model is used is greater than a preset time threshold.

[0133] The second determination module can be used to determine the second state label corresponding to each interaction data within the time period corresponding to the current time to the time when the model was last adjusted.

[0134] The third determination module can be used to determine the target accuracy corresponding to the judgment model based on the second state label corresponding to each interaction data and the judgment result of each interaction data output by the judgment model; wherein the interaction data includes signal strength, vehicle body data and vehicle location information.

[0135] The second training module can be used to perform incremental training on the trained decision model through each interaction data when the target accuracy is lower than a preset threshold, so as to obtain an updated decision model.

[0136] In some embodiments of the present disclosure, the vehicle unlocking control device 400 may further include a fourth determination module and a fifth determination module.

[0137] The fourth determination module can be used for each interaction data. If no unlocking exception feedback input by the user is received within a preset time length after the judgment model outputs the judgment result of the interaction data, the judgment result of the user output by the judgment model will be determined as the second state label corresponding to the interaction data.

[0138] The fifth determination module can be used to determine the target judgment result carried in the unblocking exception feedback as the second state label corresponding to the interaction data if a user-input unblocking exception feedback is received within a preset time length after the judgment model outputs the judgment result of the interaction data; wherein the target judgment result is different from the judgment result of the interaction data output by the judgment model.

[0139] It should be noted that Figure 4 The vehicle unlocking control device 400 shown can execute Figures 1 to 3 The various steps in the method embodiment shown in the figure are implemented Figures 1 to 3 The various processes and effects in the method embodiment shown are not described in detail here.

[0140] Figure 5 A schematic structural diagram of a vehicle unlocking control device provided by an embodiment of the present disclosure is shown.

[0141] In some embodiments of the present disclosure, Figure 5 The vehicle unlocking control device shown may be an intelligent electronic device that a user wants to control the vehicle unlocking. The intelligent electronic screen device may include a first device and a second device having a vehicle unlocking control function. Specifically, the electronic device may include but is not limited to mobile terminals such as mobile phones, vehicle-mounted devices, vehicle controllers, tablet computers, wearable devices, smart home devices, and the like.

[0142] like Figure 5 As shown, the vehicle unlocking control device may include a processor 501 and a memory 502 storing computer program instructions.

[0143] Specifically, the processor 501 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0144] The memory 502 may include a large capacity memory for information or instructions. By way of example and not limitation, the memory 502 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a tape, or a universal serial bus (USB) drive or a combination of two or more of these. Where appropriate, the memory 502 may include a removable or non-removable (or fixed) medium. Where appropriate, the memory 502 may be inside or outside the integrated gateway device. In a particular embodiment, the memory 502 is a non-volatile solid-state memory. In a particular embodiment, the memory 502 includes a read-only memory (ROM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (Electrically Erasable Programmable ROM, EEPROM), an electrically rewritable ROM (EAROM) or a flash memory, or a combination of two or more of these.

[0145] The processor 501 reads and executes the computer program instructions stored in the memory 502 to perform the steps of the vehicle unlocking control method provided in the embodiment of the present disclosure.

[0146] In one example, the vehicle unlocking control device may further include a transceiver 503 and a bus 504. Figure 5 As shown, the processor 501, the memory 502 and the transceiver 503 are connected via a bus 504 and communicate with each other.

[0147] The bus 504 includes hardware, software, or both. For example, but not limitation, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industrial Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a MicroChannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses or a combination of two or more of these. Where appropriate, the bus 504 may include one or more buses. Although embodiments of the present application describe and illustrate a particular bus, the present application contemplates any suitable bus or interconnect.

[0148] The embodiment of the present disclosure further provides a computer-readable storage medium, which may store a computer program. When the computer program is executed by a processor, the processor implements the vehicle unlocking control method provided by the embodiment of the present disclosure.

[0149] The storage medium may include, for example, a memory 502 of computer program instructions, and the instructions may be executed by the processor 501 of the vehicle unlocking control device to complete the vehicle unlocking control method provided by the embodiment of the present disclosure. Alternatively, the storage medium may be a non-temporary computer-readable storage medium, for example, a non-temporary computer-readable storage medium may be a ROM, a random access memory (RAM), a compact disc read-only memory (CD-ROM), a magnetic tape, a floppy disk, an optical data storage device, etc.

[0150] The embodiment of the present disclosure also provides a vehicle, which includes the vehicle unlocking control device as described above. It is understandable that the vehicle may also include: a processor, a memory, and a computer program. The computer program is stored in the memory and is configured to be executed by the processor to implement the vehicle unlocking control method provided by the embodiment of the present disclosure. The processor and the memory are already in Figure 3 The parts described in the illustrated embodiment are not repeated here.

[0151] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the term "comprising" is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0152] The above are only specific embodiments of the present disclosure, so that those skilled in the art can understand or implement the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to these embodiments herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A vehicle unlocking control method, characterized in that: include: Get the signal strength of the Bluetooth signal emitted by the target Bluetooth key; Inputting the signal strength, the body data of the target vehicle and the location information of the target vehicle into a trained decision model, so that the trained decision model performs decision processing to obtain a corresponding decision result, and the decision result is used to characterize the unlocking intention of the Bluetooth signal; wherein the decision model saves the corresponding relationship between the signal strength, the body data, the location information and the unlocking intention; The target vehicle lock of the target vehicle is controlled to perform an unlocking operation according to the unlocking intention, and the unlocking operation is used to put the target vehicle lock in an unlocking state corresponding to the unlocking intention.

2. The method according to claim 1, characterized in that The signal strength, the body data of the target vehicle and the position information of the target vehicle are input into the trained decision model so that the trained decision model performs decision processing to obtain the corresponding decision result, which includes: Based on the feature conversion layer in the trained decision model, field feature conversion is performed on the original data of the signal strength, the vehicle body data and the location information respectively to obtain a plurality of unified input feature data corresponding to the signal strength, the vehicle body data and the location information; Based on the intention recognition layer in the trained decision model, data mapping processing is performed on the multiple unified input feature data to determine the corresponding decision results.

3. The method according to claim 2, characterized in that The process of training the decision model includes: Obtain a training sample set; Wherein, for any sample in the training sample set, the sample includes: historical signal strength, historical vehicle body data and historical location information, and a corresponding first state label, wherein the first state label is used to characterize the labeled unlocked state corresponding to the sample; The sample is input into the original decision model to obtain the predicted unlocking state output by the original decision model; based on the first state label and the predicted unlocking state, the original decision model is trained to obtain the trained decision model.

4. The method according to claim 1, characterized in that After inputting the signal strength, the body data of the target vehicle and the position information of the target vehicle into the trained decision model so that the trained decision model performs decision processing and obtains the corresponding decision result, the method further includes: Determine whether the current time satisfies a preset model adjustment condition, wherein the preset model adjustment condition includes that the number of times the model outputs a judgment result is greater than a preset number threshold and / or the time the model is used is greater than a preset time threshold; If yes, then determine the second state label corresponding to each interaction data in the time period from the current time to the time when the model was last adjusted; wherein the interaction data includes signal strength, vehicle body data and vehicle location information; Determine the target accuracy rate corresponding to the decision model according to the second state label corresponding to each interaction data and the decision result of each interaction data output by the decision model; When the target accuracy is lower than a preset threshold, the trained decision model is incrementally trained through each interaction data to obtain an updated decision model.

5. The method according to claim 4, characterized in that The process of obtaining the second state label corresponding to each interaction data includes: For each interaction data, if no unlocking abnormal feedback input by the user is received within a preset time length after the decision model outputs the decision result of the interaction data, the decision result of the user output by the decision model is determined as the second state label corresponding to the interaction data; If an unblocking exception feedback input by the user is received within a preset time length after the judgment model outputs the judgment result of the interaction data, the target judgment result carried in the unblocking exception feedback is determined as the second state label corresponding to the interaction data; wherein the target judgment result is different from the judgment result output by the judgment model for the interaction data.

6. A vehicle unlocking control device, characterized in that: include: A first acquisition module, used to acquire the signal strength of the Bluetooth signal emitted by the target Bluetooth key; A first processing module is used to input the signal strength, the body data of the target vehicle and the location information of the target vehicle into a trained decision model, so that the trained decision model performs decision processing to obtain a corresponding decision result, and the decision result is used to characterize the unlocking intention of the Bluetooth signal; wherein the decision model saves the corresponding relationship between the signal strength, the body data, the location information and the unlocking intention; The vehicle control module is used to control the target vehicle lock of the target vehicle to perform an unlocking operation according to the unlocking intention, and the unlocking operation is used to put the target vehicle lock in an unlocking state corresponding to the unlocking intention.

7. A vehicle unlocking control device, characterized in that: include: processor; A memory for storing executable instructions; The processor is used to read the executable instructions from the memory and execute the executable instructions to implement the vehicle unlocking control method described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the processor implements the vehicle unlocking control method according to any one of claims 1 to 5.

9. A vehicle, characterized in that: It includes the vehicle unlocking control device according to claim 6, the vehicle unlocking control apparatus according to claim 7, or the computer-readable storage medium according to claim 8.

Images