CN111209979A

CN111209979A - Method and device for monitoring vehicle voltage and electronic equipment

Info

Publication number: CN111209979A
Application number: CN202010314425.5A
Authority: CN
Inventors: 韦仕伟; 赵勇; 林剑峰
Original assignee: Mobai Beijing Information Technology Co Ltd
Current assignee: Mobai Beijing Information Technology Co Ltd
Priority date: 2020-04-21
Filing date: 2020-04-21
Publication date: 2020-05-29

Abstract

The invention discloses a method and a device for monitoring vehicle voltage and electronic equipment, wherein the method comprises the following steps: obtaining a vector value of a target vehicle to a set feature vector according to historical data of the target vehicle in the last first set days, wherein the feature vector comprises at least one feature influencing vehicle voltage; according to the vector value and a preset low-voltage identification model, identifying whether the target vehicle is in a low-voltage state within a second set number of days in the future, wherein the low-voltage state is a state that the vehicle voltage is lower than or equal to a set low-voltage threshold value, and the low-voltage identification model reflects a mapping relation between the feature vector and an identification result of whether the low-voltage state is in the second set number of days in the future; and performing a setting process on the target vehicle when the low power state may occur.

Description

Method and device for monitoring vehicle voltage and electronic equipment

Technical Field

The invention relates to the technical field of vehicle monitoring, in particular to a method for monitoring vehicle voltage, a device for monitoring vehicle voltage and electronic equipment.

Background

At present, the shared vehicle trip becomes a emerging trip mode in a city, and the trip demand of urban people can be effectively solved.

The electronic control system of the shared vehicle is powered by a battery to realize the functions of lock-open control, positioning, communication with a server and the like, if the power supply voltage of the battery of the shared vehicle is lower than a lower limit value capable of maintaining normal operation of the vehicle, the shared vehicle may not provide stable service for users, and the vehicle may be lost under severe conditions, so that most of the current operation strategies perform low-power intervention when the latest reported voltage value of the vehicle is found to be close to the lower limit value. In practice, since the shared vehicles have the capability of charging the battery, for example, some vehicles may convert mechanical energy of riding of the user into electric energy to charge the battery, some vehicles may be charged by a solar panel, and the like, for a vehicle whose current voltage is already close to the lower limit value, even if a so-called low-power intervention is not performed, a low-power problem in which the supply voltage of the battery is lower than the lower limit value may not occur in the future. Therefore, when the latest reported voltage value of the vehicle is found to be close to the lower limit value, the low-power intervention mode is carried out, the operation efficiency of the vehicle is influenced, and the operation and maintenance cost is increased. In view of the above problem, it is necessary to provide a method for effectively predicting whether the vehicle will have a low-power problem in the next few days, so as to reduce unnecessary low-power intervention.

Disclosure of Invention

It is an object of embodiments of the present invention to provide a new solution for monitoring a vehicle voltage.

According to a first aspect of the present invention, there is provided a method of monitoring vehicle voltage, the method comprising:

obtaining a vector value of a target vehicle to a set feature vector according to historical data of the target vehicle in the last first set days, wherein the feature vector comprises at least one feature influencing vehicle voltage;

according to the vector value and a preset low-voltage identification model, identifying whether the target vehicle is in a low-voltage state within a second set number of days in the future, wherein the low-voltage state is a state that the vehicle voltage is lower than or equal to a set low-voltage threshold value, and the low-voltage identification model reflects a mapping relation between the feature vector and an identification result of whether the low-voltage state is in the second set number of days in the future;

and performing setting processing on the target vehicle when the low power state may occur.

Optionally, the method further comprises: setting the characteristic vector to comprise a first characteristic group and a second characteristic group, wherein the first characteristic group comprises vehicle voltage actual values of the monitored vehicle in each day in the last first set days, and the second characteristic group comprises vehicle voltage predicted values of the monitored vehicle in each day in the second set days in the future;

the obtaining, according to the history data, a vector value of the target vehicle for a set feature vector includes:

acquiring the actual value of the vehicle voltage of each day in the historical data, and taking the actual value as the value of the target vehicle to the first characteristic group;

according to the actual vehicle voltage value of each day in the historical data, obtaining the predicted vehicle voltage value of each day of the target vehicle in the second set number of days in the future, and taking the predicted vehicle voltage value as the value of the target vehicle to the second characteristic group;

and obtaining the vector value according to the value of the target vehicle to the first characteristic group and the value of the target vehicle to the second characteristic group.

Optionally, the method further comprises: setting the feature vector comprises at least one feature group of:

a first set of characteristics including actual vehicle voltage values for the monitored vehicle for each day on a first set of recent days;

a second feature set comprising vehicle voltage predictions for each day of a second set number of days in the future for the monitored vehicle;

third characteristic group: at least one of a city where the monitored vehicle is located and a weather condition of the city in the last first set number of days each day;

fourth characteristic group: at least one of the model of the monitored vehicle, the number of times of unlocking the monitored vehicle within the latest first set number of days, and the failure state of the monitored vehicle within the latest first set number of days;

a fifth set of characteristics, during a first, most recent set of days, of voltage characteristics of the monitored vehicle over a first sliding window of at least one length of time, the voltage characteristics including at least one of a vehicle voltage minimum, a vehicle voltage maximum, a vehicle voltage mean, and a vehicle voltage variance;

a sixth set of characteristics, the number of orders placed by the monitored vehicle in a second sliding window of at least one length of time during the last first set number of days;

a seventh set of characteristics, the number of times the monitored vehicle has experienced said low power condition under a third sliding window of at least one length of time during a first set of recent days;

and the time length of any sliding window is less than or equal to the first set number of days.

Optionally, the method further comprises:

acquiring the setting content of the feature vector;

and updating the feature vector according to the setting content.

Optionally, the method further comprises:

acquiring setting contents for at least one of the first set number of days and the second set number of days;

and updating the corresponding set days according to the set content.

Optionally, the method further comprises the step of screening the target vehicle, comprising:

screening vehicles with the vehicle voltage actual value reported latest in the current day being less than or equal to the set first low-voltage threshold value from the released vehicles as target vehicles;

wherein the first low pressure threshold is higher than the low pressure threshold.

Optionally, the setting process of the target vehicle includes at least one of:

a first item to set the target vehicle as a vehicle requiring vehicle voltage to be monitored again for a second set number of days in the future;

a second item of setting a riding incentive for the target vehicle in a case where the target vehicle is a first vehicle type, wherein the first vehicle type is a vehicle type charged by converting mechanical energy generated using a corresponding vehicle into electric energy;

setting an incentive for cleaning a solar panel for the target vehicle in the case that the target vehicle is of a second vehicle type, wherein the second vehicle type is a vehicle type charged through the solar panel;

and fourthly, sending the information of the target vehicle to an account number of an operation and maintenance person for low-power intervention.

Optionally, the method further comprises the step of obtaining the low pressure identification model, comprising:

acquiring historical data of a sample vehicle in a first set number of days before a reference date as first historical data, and acquiring historical data of the sample vehicle in a second set number of days after the reference date as second historical data;

obtaining vector values of corresponding sample vehicles for the feature vectors according to the first historical data;

according to the second historical data, obtaining an actual classification result of whether the corresponding sample vehicle has a low power state within a second set number of days after the reference date;

generating a training sample according to the matched vector value and the actual classification result;

and training to obtain the low-pressure recognition model according to the training sample.

Optionally, the obtaining the low pressure identification model further comprises:

selecting the reference date;

selecting, as the sample vehicle, a vehicle that satisfies a set condition among the dropped vehicles based on the reference date, wherein the set condition includes at least one of:

a first item that the vehicle state on the reference date is a healthy state;

a second term, wherein the actual value of the vehicle voltage reported last on the reference date is less than or equal to a second low-voltage threshold, wherein the second low-voltage threshold is higher than the low-voltage threshold;

third, the low power intervention is not performed from the first day in the first set number of days before the reference date to the last day period in the second set number of days after the reference date.

According to a second aspect of the present invention, there is also provided an apparatus for monitoring a voltage of a vehicle, comprising:

the characteristic extraction module is used for obtaining a vector value of a target vehicle to a set characteristic vector according to the historical data of the target vehicle in the last first set days, wherein the characteristic vector comprises at least one characteristic influencing the voltage of the vehicle;

the identification module is used for identifying whether the target vehicle is in a low-power state within a second set number of days in the future or not according to the vector value and a preset low-voltage identification model, wherein the low-power state is a state that the vehicle voltage is lower than or equal to a set low-voltage threshold value, and the low-voltage identification model reflects the mapping relation between the feature vector and an identification result of whether the low-power state is in the second set number of days in the future or not; and the number of the first and second groups,

and the low-voltage processing module is used for performing setting processing on the target vehicle under the condition that the low-power state can occur.

According to a third aspect of the present invention, there is also provided an electronic device comprising the apparatus according to the second aspect of the present invention; or,

the electronic device includes: a memory for storing executable instructions; a processor configured to execute the electronic device according to the control of the instruction to perform the method according to the first aspect of the present invention.

The method has the advantages that whether the target vehicle has the low-power problem in a future period of time can be predicted according to the historical data of the target vehicle in the recent period of time and the low-voltage recognition model obtained through pre-training, and necessary low-power intervention is performed on the target vehicle under the condition that the low-power problem occurs in the future period of time, so that unnecessary low-power intervention is effectively reduced, the operation efficiency of the vehicle is improved, and the operation and maintenance cost is reduced.

Other features of the present invention and advantages thereof will become apparent from the following detailed description of exemplary embodiments thereof, which proceeds with reference to the accompanying drawings.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description, serve to explain the principles of the invention.

FIG. 1 is a functional block diagram showing a hardware configuration of a shared vehicle system that may be used to implement a method of monitoring vehicle voltage according to one embodiment;

FIG. 2 is a schematic flow diagram of a method of monitoring vehicle voltage according to one embodiment;

FIG. 3 is a schematic time line diagram of acquiring historical data of a vehicle according to one embodiment;

FIG. 4 is a functional block diagram of an apparatus to monitor vehicle voltage according to one embodiment;

FIG. 5 is a hardware architecture diagram of an electronic device according to one embodiment.

Detailed Description

Various exemplary embodiments of the present invention will now be described in detail with reference to the accompanying drawings. It should be noted that: the relative arrangement of the components and steps, the numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present invention unless specifically stated otherwise.

The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the invention, its application, or uses.

Techniques, methods, and apparatus known to those of ordinary skill in the relevant art may not be discussed in detail but are intended to be part of the specification where appropriate.

In all examples shown and discussed herein, any particular value should be construed as merely illustrative, and not limiting. Thus, other examples of the exemplary embodiments may have different values.

It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, further discussion thereof is not required in subsequent figures.

< hardware configuration >

FIG. 1 is a block diagram of a hardware configuration of a shared vehicle system 100 that may be used to implement a method of monitoring vehicle voltage according to one embodiment.

As shown in fig. 1, the shared vehicle system 100 includes a server 1000, a mobile terminal 2000, and a vehicle 3000.

The mobile terminal 2000 is a user terminal used by a user, communication connections can be established between the mobile terminal 2000 and the server 1000, and between the server 1000 and the vehicle 3000 through the network 4000, and the network 4000 on which the vehicle 3000 and the server 1000, and the mobile terminal 2000 and the server 1000 communicate may be the same or different, which is not limited herein.

In the shared vehicle system 100, the server 1000 is used to provide all functions necessary to support vehicle use; the mobile terminal 2000 may be a mobile phone on which a vehicle use application is installed, and the vehicle use application may help a user to implement a function of using the vehicle 3000.

In the shared vehicle system 100, a user may use the mobile terminal 2000 to send an unlocking request for unlocking the vehicle 3000 to the server 1000 by scanning a two-dimensional code of the vehicle 3000 or inputting a code of the vehicle 3000, after receiving the unlocking request, the server 1000 sends an unlocking command to the vehicle 3000 when both the user and the vehicle are authenticated to meet a use condition, and the vehicle 3000 performs an unlocking operation according to the unlocking command, at this time, the user may use the vehicle 3000. After the use is finished, the user performs a lock closing operation on the vehicle 3000, the vehicle 3000 reports the successful lock closing information to the server 1000, and the server 1000 starts an order settlement process according to the successful lock closing information.

In the shared vehicle system 100, the vehicle 3000 may report a vehicle voltage, which is also an output voltage of the battery, to the server. The vehicle 3000 may be configured to report the vehicle voltage to the server 1000 periodically, for example, every set time every day. The vehicle may also be configured to carry the vehicle voltage and the like when reporting the locking success information, which is not limited herein.

The server 1000 provides a service point for processes, databases, and communications facilities. The server 1000 may be a unitary server or a distributed server across multiple computers or computer data centers. The server may be of various types, such as, but not limited to, a web server, a news server, a mail server, a message server, an advertisement server, a file server, an application server, an interaction server, a database server, or a proxy server. In some embodiments, each server may include hardware, software, or embedded logic components or a combination of two or more such components for performing the appropriate functions supported or implemented by the server. For example, a server, such as a blade server, a cloud server, etc., or may be a server group consisting of a plurality of servers, which may include one or more of the above types of servers, etc.

In one embodiment, as shown in fig. 1, the server 1000 may include a processor 1100, a memory 1200, an interface device 1300, a communication device 1400, a display device 1500, an input device 1600.

The processor 1100 is used to execute computer programs. The computer program may be written in an instruction set of an architecture such as x86, Arm, RISC, MIPS, SSE, etc. The memory 1200 includes, for example, a ROM (read only memory), a RAM (random access memory), a nonvolatile memory such as a hard disk, and the like. The interface device 1300 includes, for example, various bus interfaces such as a serial bus interface (including a USB interface), a parallel bus interface, and the like. Communication device 1400 is capable of wired or wireless communication, for example. The display device 1500 is, for example, a liquid crystal display, an LED display touch panel, or the like. The input device 1600 may include, for example, a touch screen, a keyboard, and the like.

In this embodiment, the memory 1200 of the server 1000 is used to store instructions for controlling the processor 1100 to operate to perform a method of monitoring vehicle voltage according to any of the embodiments. The skilled person can design the instructions according to the disclosed solution. How the instructions control the operation of the processor is well known in the art and will not be described in detail herein.

Although a plurality of devices of the server 1000 are shown in fig. 1, the present invention may only relate to some of the devices, for example, the server 1000 only relates to the memory 1200, the processor 1100, the communication device 1400, and the like.

In this embodiment, the mobile terminal 2000 is, for example, a mobile phone, a laptop, a tablet computer, a palmtop computer, a wearable device, and the like.

As shown in fig. 1, the mobile terminal 2000 may include a processor 2100, a memory 2200, an interface device 2300, a communication device 2400, a display device 2500, an input device 2600, a speaker 2700, a microphone 2800, and the like.

The processor 2100 may be a mobile version processor. The memory 2200 includes, for example, a ROM (read only memory), a RAM (random access memory), a nonvolatile memory such as a hard disk, and the like. The interface device 2300 includes, for example, a USB interface, a headphone interface, and the like. The communication device 2400 can perform wired or wireless communication, for example, the communication device 2400 may include a short-range communication device, such as any device that performs short-range wireless communication based on a short-range wireless communication protocol, such as a Hilink protocol, WiFi (IEEE 802.11 protocol), Mesh, bluetooth, ZigBee, Thread, Z-Wave, NFC, UWB, LiFi, and the like, and the communication device 2400 may also include a remote communication device, such as any device that performs WLAN, GPRS, 2G/3G/4G/5G remote communication. The display device 2500 is, for example, a liquid crystal display panel, a touch panel, or the like. The input device 2600 may include, for example, a touch screen, a keyboard, and the like. The mobile terminal 2000 may output audio information through the speaker 2700, and collect audio information through the microphone 2800, and the like.

In this embodiment, the memory 2200 of the mobile terminal 2000 is configured to store instructions for controlling the processor 2100 to operate to perform a method of using the shared vehicle 3000, for example, including at least: acquiring an identity of a vehicle 3000, forming an unlocking request for a specific vehicle, and sending the unlocking request to a server; and bill settlement and the like according to the charge settlement notice sent by the server. The skilled person can design the instructions according to the disclosed solution. How the instructions control the operation of the processor is well known in the art and will not be described in detail herein.

Although a plurality of devices of the mobile terminal 2000 are illustrated in fig. 1, the present invention may relate only to some of the devices, for example, the mobile terminal 2000 may relate only to the memory 2200 and the processor 2100, the communication device 2400, and the display device 2500.

The vehicle 3000 may be a bicycle shown in fig. 1, and may be in various forms such as a tricycle, an electric bicycle, a motorcycle, and a four-wheel passenger car, which are not limited herein.

As shown in fig. 1, vehicle 3000 may include a processor 3100, a memory 3200, interface devices 3300, communication devices 3400, output devices 3500, input devices 3600, and so forth. The processor 3100 may be a microprocessor MCU or the like. The memory 3200 includes, for example, a ROM (read only memory), a RAM (random access memory), a nonvolatile memory such as a hard disk, and the like. The interface 3300 includes, for example, a USB interface, a headphone interface, and the like. The communication device 3400 is capable of wired or wireless communication, for example, and also capable of short-range and long-range communication, for example. The output device 3500 may be, for example, a device that outputs a signal, may be a display device such as a liquid crystal display screen or a touch panel, or may be a speaker or the like that outputs voice information or the like. The input device 3600 may include, for example, a touch screen, various sensors, and the like.

Although a plurality of devices of the vehicle 3000 are shown in fig. 1, the present invention may only relate to some of the devices, and may also relate to other devices not shown in fig. 1, which is not limited herein.

In this embodiment, memory 3200 of vehicle 3000 is used to store instructions that control processor 3100 to operate to perform information interactions with server 1000. The skilled person can design the instructions according to the disclosed solution. How the instructions control the operation of the processor is well known in the art and will not be described in detail herein.

It should be understood that although fig. 1 shows only one server 1000, mobile terminal 2000, vehicle 3000, there is no intention to limit the respective numbers, and multiple servers 1000, multiple mobile terminals 2000, multiple vehicles 3000 may be included in the system 100.

In addition, the system 100 may further include a service terminal used by the operation and maintenance personnel, the service terminal is in communication connection with the server 1000, and the service terminal may have a hardware structure the same as or similar to that of the mobile terminal in fig. 1, and details are not described here.

< method examples >

Fig. 2 is a schematic flow diagram of a method for monitoring a vehicle voltage according to an embodiment of the present invention, which may be implemented by a server, for example, the server 1000 in fig. 1, where the vehicle voltage is an output voltage of a vehicle battery, that is, a supply voltage of the vehicle battery.

According to fig. 2, the method of the present embodiment may include the following steps:

step S2100, obtaining a vector value of the target vehicle to a set feature vector according to historical data of the target vehicle in the last first set days, wherein the feature vector comprises at least one feature influencing vehicle voltage.

The method of the embodiment is to predict whether the target vehicle will have a low power state in the second set number of days in the future through the historical data of the target vehicle in the last first set number of days, wherein the low power state is a state that the vehicle voltage is less than or equal to the set low voltage threshold value.

In this embodiment, for example, the following may be set: if the target vehicle is in the low power state on any of the second set number of days in the future, the monitored vehicle is deemed to be in the low power state on the second set number of days in the future.

In the present embodiment, the first set number of days and/or the second set number of days may be expressed in time units such as "week" and "month", for example, the first set number of days is three weeks, and the second set number of days is one week, and the present invention is not limited thereto.

The low voltage threshold may be set according to actual needs, for example, may be set based on a minimum voltage requirement that can satisfy normal use of the vehicle, and the like.

The first set number of days may be set and adjusted according to the accuracy of the predicted result, the control requirement for the predicted data throughput, and the like. In consideration of the above two aspects, the first set number of days may be set to 15 to 30 days, for example, the first set number of days is 20 days.

In this embodiment, the last first set number of days may include the current day on which the method of this embodiment is performed. In order to ensure the integrity of the historical data of the target vehicle on each of the first set number of days, the latest first set number of days may not include the current day, in which case, the second set number of days in the future may include the current day or may not include the current day, which is not limited herein.

As shown in fig. 3, for example, the current day is a date T, the latest first set number of days n may be a number from [ (T-n), T ], and the future second set number of days m may be a number from [ (T +1), (T + m) ], and the like.

The historical data comprises at least one of the model of the target vehicle, the city where the target vehicle is located, the daily weather condition of the city where the target vehicle is located, the daily order number, the daily unlocking times, the last reported vehicle voltage actual value and the daily fault record. The actual value of the vehicle voltage is the vehicle voltage value reported by the target vehicle at the last time every day.

The feature vector includes at least one set of features affecting the vehicle voltage, each set of features including at least one feature. The target vehicle as a monitored vehicle may determine values of the target vehicle for all the features in the feature vector according to the features included in the feature vector, and form a vector value of the target vehicle for the feature vector, that is, the vector value of the target vehicle for the feature vector is formed by values of the target vehicle for the features in the at least one feature group.

In one embodiment, the feature vector may include a first feature set including vehicle voltage actual values reported last day by the monitored vehicle for each day of the last first set number of days by the monitored vehicle.

The values of the target vehicle for the first characteristic group are arranged according to the time sequence, so that a vehicle voltage sequence reflecting the change situation of the vehicle voltage of the target vehicle advancing along with time is formed, a curve reflecting the mapping relation between the vehicle voltage of the target vehicle and the time (date) can be fitted according to the vehicle voltage sequence, and a function corresponding to the curve can be used as a vehicle voltage prediction function and used for calculating the predicted value of the vehicle voltage of the target vehicle in each day in the second set days in the future. Since whether the target vehicle will be in a low-power state within the second set number of days in the future can be known through the predicted vehicle voltage values, the setting of the feature vector to include the first feature group is beneficial to accurately predicting whether the target vehicle will be in a low-power state within the second set number of days in the future.

In this embodiment, in order to fit a more accurate vehicle voltage prediction function in the shortest possible time according to the vehicle voltage sequence of the target vehicle, a time sequence prediction model of any structure may be used for the fitting, that is, an optimal solution of model parameters of a selected time sequence prediction model is determined according to the target voltage sequence, and the time sequence prediction model with the model parameters valued as the optimal solution is used as the vehicle voltage prediction functionNumber of

Wherein, t is the date,

for the predicted value of the vehicle voltage of the target vehicle on the date t, the optimal solution is such that the vehicle voltage prediction function is passed

The calculated predicted vehicle voltage value of the target vehicle on each day in the first set number of days in the past satisfies the set convergence condition compared with the average error of the corresponding actual vehicle voltage values in the vehicle voltage sequence.

In one embodiment, since one time series can be fit by a plurality of time series with different characteristics, one time series can be decomposed into a plurality of characteristic terms, and then fit is carried out, for example, the vehicle voltage series can be decomposed into a trend term, a period term, a holiday term and a residual term, wherein the trend term represents the variation trend of the time series on a non-periodic basis; the period item can take days, weeks, quarters or years and the like as a period unit; the holiday item represents whether festivals and holidays exist on the current day; the remaining terms, also referred to as error terms, follow a normal distribution. In this way, the model structure of the selected time sequence prediction model can be represented as the sum of the function expressions of the items, and the undetermined parameters in the function expressions are the model parameters of the time sequence prediction model.

In one embodiment, it may be further provided that the feature vector comprises a second feature set comprising predicted values of vehicle voltage for the monitored vehicle for each day in a second set number of days in the future. In this embodiment, since the predicted values of the vehicle voltage can represent the high-order time series characteristics of the monitored vehicle on the vehicle voltage, even when the vehicle voltage time series change of the target vehicle has strong randomness and the set first set number of days is short and only a short vehicle voltage time series can be obtained, the predicted values of the vehicle voltage are added to predict whether the target vehicle will have a low-power state within the second set number of days in the future, and the prediction accuracy that meets the use requirement can be obtained.

In one embodiment, the feature vector may further include a third feature group, and the third feature group may include: at least one of the city in which the monitored vehicle is located and the weather condition of the city in the last first set number of days. Because the temperature and the illumination conditions of different cities have larger differences, and the temperature, the illumination and the weather conditions such as cloudy, sunny, rainy and snowy affect the voltage of the vehicle, the setting of the feature vector to include the third feature group is beneficial to accurately predicting whether the target vehicle can be in a low-power state within the second set number of days in the future.

In one embodiment, it may be further provided that the feature vector includes a fourth feature group including features reflecting vehicle information, and the fourth feature group may include: at least one of a model of the monitored vehicle, a number of times the monitored vehicle was unlocked on a last first set number of days, and a failure state of the monitored vehicle on a last first set number of days. The fault condition may include whether a charging fault exists, which may be determined from fault and repair records for the monitored vehicle. In this embodiment, since different vehicle models have different self-charging modes and the usage conditions of the vehicle determine the consumption of the battery power, the basic information and the usage information of the vehicle can greatly influence the voltage of the vehicle, and setting the feature vector to include the fourth feature group is beneficial to accurately predicting whether the target vehicle will have a low-power state within the second set number of days in the future.

In one embodiment, the feature vector may further include a fifth feature group, and the fifth feature group may include: and in the last first set number of days, the voltage characteristics of the monitored vehicle under the first sliding window of at least one time length comprise at least one of the minimum value of the vehicle voltage actual value, the maximum value of the vehicle voltage actual value, the mean value of the vehicle voltage actual value and the variance of the vehicle voltage actual value.

The fifth feature group embodies a time-series change of the voltage feature by which robustness of a recognition result of recognizing whether or not the target vehicle will exhibit a low-power state, which will be present or not, within a second set number of days in the future through the low-voltage recognition model can be improved. The first sliding window of the at least one time length may be set as required, and may include, for example, three days, seven days, fourteen days, and the like, which is not limited herein, but the time length of any first sliding window should be less than or equal to the first set number of days.

Taking the first sliding window with the time length of three days as an example, when obtaining the values of the target vehicle for the fifth feature group, for example, the values may be slid on the vehicle voltage sequence with the first set number of days being 20 days to sequentially determine the voltage features on the 1 st to 3 rd days, the voltage features on the 2 nd to 4 th days, the voltage features on the 3 rd to 5 th days, and so on until determining the voltage features on the 18 th to 20 th days.

In one embodiment, the feature vector may further include a sixth feature group, and the sixth feature group may include: and in the last first set number of days, the monitored vehicle places the order number in a second sliding window of at least one time length.

The sixth feature group reflects a time-series change in the order number, and by this time-series change, it is possible to improve the robustness of the recognition result of whether or not the low-power state will occur in the second set number of days in the future of the recognition of the target vehicle by the low-voltage recognition model. The second sliding window of the at least one time length may be set as required, and may include, for example, three days, seven days, fourteen days, and the like, which is not limited herein, but the time length of any second sliding window should be less than or equal to the first set number of days.

Taking the second sliding window with the time length of three days as an example, when obtaining the value of the target vehicle for the sixth feature group, the order quantity of the target vehicle in each day in the first set number of days may be obtained first to form an order quantity sequence, and then the second sliding window with the time length of three days is used to slide on the order quantity sequence to sequentially determine the order quantity from day 1 to day 3, the order quantity from day 2 to day 4, the order quantity from day 3 to day 5, and so on until determining the order quantity from day 18 to day 20.

In one embodiment, it may be further provided that the feature vector includes a seventh feature group, and the seventh feature group may include: the number of times the monitored vehicle has a low power condition within a third sliding window of at least one length of time during the last first set number of days.

The seventh feature group represents a time-series change of the low-power state, and by this time-series change, it is possible to improve the robustness of the recognition result of recognizing whether or not the low-power state will occur in the second set number of days in the future by the low-voltage recognition model. The third sliding window of at least one time length may be set according to the length of the first set number of days, and may be, for example, three days, seven days, fourteen days, or the like, or may be equal to the first set number of days, which is not limited herein, but the time length of any third sliding window should be less than or equal to the first set number of days.

Taking the third sliding window with the time length being the first set number of days as an example, when the value of the target vehicle for the seventh feature group is obtained, the actual value of the vehicle voltage in the vehicle voltage sequence of the target vehicle may be compared with the set low voltage threshold, so as to obtain the number of times that the target vehicle has a low power state in the third sliding window.

In one embodiment, the operation and maintenance personnel may be allowed to set or adjust the feature group and the features in the feature group included in the feature vector as needed, so as to improve the flexibility and the application range of the method for implementing the embodiment. In this embodiment, the method may further include: acquiring the setting content of the feature vector; and updating the feature vector according to the setting content.

In this embodiment, the operation and maintenance personnel can input the setting content through their own service terminal, and the service terminal sends the setting content to the server to update the feature vector. The updating may include at least one of adding a new feature to the feature vector, deleting an existing feature, and replacing an existing feature.

On one side of the service terminal, the service terminal can provide a setting interface in response to the operation of setting the feature vector by the operation and maintenance personnel, the setting interface can provide a setting interface corresponding to each feature group and a setting interface for adding or deleting the feature groups, and the operation and maintenance personnel can input the setting content through the setting interfaces, wherein the setting interface can also load and display the current feature group and the features contained in each feature group so that the operation and maintenance personnel can complete the setting by referring to the current content of the feature vector.

In one embodiment, the operation and maintenance personnel may also be allowed to set or adjust the first set number of days and/or the second set number of days as needed to improve the flexibility and applicability of the method of the embodiment. In this embodiment, the method may further include: acquiring the setting content of the set days; and updating the corresponding set days according to the set content.

And step S2200, identifying whether the target vehicle is in a low power state within the second set number of days in the future according to the vector value obtained in the step S2100 and a preset low voltage identification model.

In this embodiment, the low-voltage recognition model is obtained by pre-training and is pre-stored locally to execute the method of this embodiment. The low voltage identification model reflects a mapping relationship between the feature vector and an identification result of whether a low power state will occur within a second set number of days in the future, and the identification result can be represented by a probability value.

The input of the low-voltage identification model is a vector value of the target vehicle for the feature vector, and the output can be a probability value representing whether the target vehicle is in a low-power state in the second set number of days in the future, if the probability value is higher than or equal to the set value, the target vehicle is indicated to be in the low-power state in the second set number of days in the future, otherwise, the target vehicle is indicated not to be in the low-power state in the second set number of days in the future.

In step S2300, if the low power state is present, the setting process is performed on the target vehicle.

In this embodiment, if the low power state is identified as occurring, it indicates that the target vehicle has a very high probability of occurring the low power state within the second set number of days in the future, and is in a state in which low power intervention is necessary, and at this time, the target vehicle may be subjected to low power intervention.

In one embodiment, the setting process of the target vehicle in the step S2300 may include at least one of:

first, the target vehicle is set as a vehicle that needs to be monitored for the vehicle voltage again for a second set number of days in the future.

By setting the target vehicle which will be in a low-power state in the second set number of days in the future as the target vehicle which needs to be monitored again for the vehicle voltage in these days, the key vehicle can be continuously monitored, and if the target vehicle is found to be no longer the vehicle which will be in a low-power state in the second set number of days in the future in the continuous monitoring, no further low-voltage intervention is needed.

In the second item, in the case where the model of the target vehicle is a first model, the target vehicle is set with a riding incentive, where the first model is a model that is charged by converting mechanical energy generated by using the corresponding vehicle into electrical energy, that is, for a vehicle whose model is a first model, the battery of the vehicle can be charged by using the vehicle by the user, thereby avoiding low power of the vehicle.

By setting the riding incentive for the target vehicle, the purpose of encouraging the user to use the target vehicle is achieved, and the purpose of charging the battery of the target vehicle by riding the target vehicle can be further achieved.

For example, the cycling stimulus may include: setting the target vehicle as a red packet vehicle; for another example, the usage stimulus may also include: the vehicle use coupon and the like can be obtained when the target vehicle reaches the set mileage, which is not limited herein.

Third, in the case where the model of the target vehicle is a second model, which is a model charged by a solar cell panel, an incentive to clean the solar cell panel is set for the target vehicle.

By setting the incentive for the target vehicle, when the solar cell panel of the target vehicle is shielded by a shielding object such as advertising paper or covered by dust or the like, the user can assist in cleaning the solar cell panel, for example, assist in removing the shielding object or dust or the like, thereby achieving the purpose of charging the battery of the target vehicle as soon as possible.

And fourthly, sending the information of the target vehicle to an account number of the operation and maintenance personnel for low-power intervention.

The information of the target vehicle may include a code of the target vehicle, a current location of the target vehicle, and the like.

The operation and maintenance personnel can check the vehicle needing low-electricity intervention by logging in the account through the service terminal, and thus, the operation and maintenance personnel can find the vehicle to conduct low-electricity intervention, for example, the solar cell panel is shielded, the target vehicle is conveyed to an area where sunlight is not shielded, the target vehicle is conveyed to the nearest garage to be charged, maintained and the like.

In this embodiment, if it is determined through the recognition in step S2200 that the target vehicle does not exhibit the low power state, it indicates that the target vehicle may be in the normal use state in the second set number of days in the future without performing the low power intervention processing.

As can be seen from the above steps S2100 to S2300, in the method of this embodiment, it can be accurately identified whether the target vehicle will have a low power state in the second set number of days in the future through the historical data of the target vehicle in the last first set number of days and the preset low voltage identification model, and the setting process is performed only when the low power state will occur, so as to ensure that the low power intervention for the target vehicle is necessary, thereby avoiding the unnecessary low power intervention, improving the operating efficiency of the vehicle, and reducing the operation and maintenance cost.

In one embodiment, the method may further comprise the step of screening the target vehicle as the monitored vehicle. In this embodiment, screening the target vehicle may include: and screening the vehicles with the vehicle voltage actual value which is reported latest in the current day and is less than or equal to the set first low-voltage threshold value from all the vehicles as the target vehicle.

In this embodiment, the first low voltage threshold is greater than the low voltage threshold, and when the latest vehicle voltage actual value of the vehicle is less than or equal to the first low voltage threshold, it indicates that the vehicle may have a low power state in the second set number of days in the future and needs to be monitored, and when the latest vehicle voltage actual value of the vehicle is greater than the first low voltage threshold, it indicates that the vehicle may have a low power state in the second set number of days in the future and may not temporarily perform low voltage monitoring. Therefore, the method screens the target vehicles needing to be monitored every day, can effectively reduce the number of the monitored vehicles, and does not influence the monitoring effect.

In another embodiment, all released vehicles or all healthy vehicles in the released vehicles may also be used as target vehicles that need to be subjected to voltage monitoring on the current day, which is not limited herein.

In one embodiment, the method may further comprise: detecting a set event; and in the case where an arbitrary setting event is detected, performing an operation of screening the target vehicle to further perform an operation of identifying whether or not a low-power state of the target vehicle will occur within a second set number of days in the future.

The setting event may include, for example: and when the set monitoring time is up, receiving an external trigger, and at least one item of vehicles with the vehicle voltage actual value less than or equal to the first low-voltage threshold value appears in the current day.

In one embodiment, the method may further include the step of obtaining a low voltage identification model identifying whether the target vehicle will exhibit a low power condition for a second set number of days in the future. In this embodiment, obtaining the low-voltage identification model may include the following steps S2011 to S2015:

in step S2011, history data of the sample vehicle in a first set number of days before the reference date is acquired as first history data, and history data of the sample vehicle in a second set number of days after the reference date is acquired as second history data.

In the low pressure recognition according to the low pressure recognition model, if neither the first set number of days nor the second set number of days includes the current day, the "before reference date" and the "after reference date" herein are understood as not including the reference date, if the first set number of days includes the current day, the "before reference date" herein is understood as including the reference date, and if the second set number of days includes the current day, the "after reference date" herein is understood as including the reference date.

In this embodiment, different sample vehicles may have the same reference date or different reference dates, which is not limited herein.

In order to facilitate screening of sample vehicles and data cleaning, in one embodiment, a reference date may be selected, that is, all sample vehicles have the same reference date, and vehicles satisfying a set condition are screened from all vehicles as sample vehicles.

The setting condition may include, for example, at least one of: a first item that the vehicle state on the reference date is a healthy state; the second term is that the actual value of the vehicle voltage reported last on the reference date is less than or equal to the second low-voltage threshold value; and a third term in which the low-power intervention is not performed from the first day in the first set number of days before the reference date to the last day period in the second set number of days after the reference date.

The second low pressure threshold is higher than the low pressure threshold. The second low pressure threshold may be the same value as the first low pressure threshold.

In this embodiment, the vehicle with the vehicle state as the healthy state may be screened according to at least one item of the vehicle log information, whether the vehicle is in the operating state, whether the vehicle is ridden within the set time period, and the like.

In this embodiment, the vehicle with the vehicle state as the healthy state may also be screened through a preset state check model for identifying the vehicle state, which is not limited herein.

Step S2012, obtaining a vector value of the corresponding sample vehicle with respect to the feature vector according to the first history data.

And step S2013, according to the second historical data, obtaining an actual classification result of whether the corresponding sample vehicle has a low power state within the second set number of days in succession.

And step S2014, generating a training sample according to the matched vector value and the actual classification result.

Step S2015, training to obtain the low-pressure recognition model according to the training sample.

In step S2015, an optimal solution of the model parameters of the selected classification model may be obtained through training according to the training sample, and the classification model with the model parameters being the optimal solution is used as the low-pressure recognition model.

The classification model selected may be, for example, LightGBM, GBDT, XGBoost, etc., without limitation.

Taking LightGBM as an example, the mapping function of the low-voltage identification model is obtained through the LightGBM addition model

(i.e. obtained after training T rounds

) The process of (a) may be as follows, wherein, X is the above-mentioned feature vector,

for the prediction classification result corresponding to the feature vector X:

step 1), initialization

To obtain

Wherein

is a mapping function obtained by the training of the T-th round, and the value of T is 1-T, therefore,

i.e. the mapping function that is finally obtained

_。

Step 2), calculating a loss function

The value of the negative gradient of (a) in the t-th round is taken as the estimation of the residual error of the t-th round

：

Formula (1);

wherein,

and M is the number of sample vehicles,

to average the losses at the t-th round,

as an actual classification result of the m-th sample vehicle,

for mapping functions obtained from the (t-1) th round of training

The predicted classification result of the m-th sample vehicle obtained, i.e. according to the mapping function

And predicting whether the m sample vehicle can generate a prediction classification result of a low power state within the second set number of days in the future.

Step 3), learning the t tree according to the formula (2);

formula (2);

wherein,

as a function of the t-th round of regression trees,

for the parameters of the t-th round of the regression tree, the functional relationship of the regression tree for each round may be the same, except that the parameter values are different,

to make it possible to

When the value of (A) takes a minimum value

The value is obtained.

Step 4), determining the weight of the t tree according to the formula (3)

：

Formula (3);

wherein,

to make it possible to

When the value of (A) takes a minimum value

The value is obtained.

Step 5), updating the model:

equation (4).

Finally obtaining the target through T-round iteration

I.e. to obtain a mapping function

。

The training process of other classification models XGBoost and the like is similar to that of the above classification model LightGBM, and is not described herein again.

According to the embodiment, the low-pressure identification model is obtained by training the classification model, so that the operation of obtaining the low-pressure identification model can be simplified, and the low-pressure identification model obtained by training has higher identification accuracy.

In one embodiment, a method of obtaining a status check model for screening healthy vehicles may include:

in step S3100, the server 1000 acquires a vector value of the delivered vehicle with respect to a set feature vector reflecting the vehicle health state.

In this embodiment, a feature vector for describing the health status of the vehicle, that is, a status feature vector, may be selected in advance, for example, according to the content that each vehicle in the database of the server 1000 must include.

The state feature vector may be comprised of at least one feature that is relevant to determining the state of health of the vehicle, and the corresponding state of health of the vehicle may be determined from the feature vector.

In one example, the vehicle data may be processed according to some existing processing means to obtain features describing the vehicle data relevant to determining the vehicle health status, thereby forming a feature vector. For example, feature processing such as feature discretization, feature cleaning, feature selection, and feature normalization is performed on the vehicle data to extract vehicle parameter features, interaction features between the vehicle and the user, parking position features of the vehicle, and the like, thereby constituting a feature vector.

In one example, the set feature vector reflecting the vehicle health state may include at least one of vehicle parameter features, interaction features between the vehicle and the user, and parking location features of the vehicle.

The vehicle parameter characteristics can include vehicle static parameter characteristics and vehicle dynamic parameter characteristics, and the vehicle static parameter characteristics can include a vehicle number, a vehicle lock electricity quantity and voltage and a decay rate thereof, a vehicle type, a vehicle historical maintenance frequency, a pseudo-healthy vehicle state, a vehicle last riding time, a vehicle first delivery date, a vehicle last delivery date, vehicle lock hardware, a vehicle firmware version and the like. The vehicle dynamic parameter characteristics may include a total number of rides per day, a total number of rides per three days, a total number of rides per seven days, a total number of rides per fourteen days, a short number of rides per day, a short number of rides per three days, a short number of rides per seven days, a short number of rides per fourteen days, and the like.

The interactive features between the vehicle and the user may include at least one of a number of times the user rides the vehicle, a number of times the user sweeps a code for a non-riding vehicle, and a manual input of vehicle information by the user.

The parking position characteristics of the vehicle can be the ratio of the vehicle turnover rate to the area turnover rate, the electronic fence where the vehicle is located, the fence type of the electronic fence where the vehicle is located, and the like.

The above electronic fence is an area which is defined according to a plan and allows parking or disallows parking, and many electronic fences are set based on the need of parking management for different areas, such as cities, administrative areas of cities, streets, grids and the like.

The fence types may be classified as a parking prohibition fence or a parking fence according to the fence attributes, or may be classified as a subway entrance fence, a bus stop fence, a street fence, and the like according to the geographic location attributes, which is not limited herein.

In step S3200, the server 1000 obtains a check result indicating whether the corresponding vehicle is a healthy vehicle according to the vector value and a preset state check model, where the state check model reflects a mapping relationship between the state feature vector and a vehicle health state.

Taking the vehicle health status including a healthy status and an unhealthy status as an example, the function value may be a true value corresponding to the vehicle being in a healthy status, that is, the vehicle belongs to a healthy vehicle, and a false value corresponding to the vehicle being in an unhealthy status, that is, the vehicle belongs to a faulty vehicle; the function value may be a true value corresponding to the vehicle being in the unhealthy state, and the function value may be a false value corresponding to the vehicle being in the healthy state, as long as whether the vehicle is a healthy vehicle can be distinguished according to the function value, which is not limited herein.

In this embodiment, according to step S3100, after the vector value of the feature vector of the released vehicle is obtained, the vector value may be input to the state check model, so as to obtain the vehicle health state of the corresponding vehicle.

In step S4300, the server 1000 screens the released vehicles for healthy vehicles according to the inspection result.

In this embodiment, the method shown in fig. 2 is implemented for screening healthy vehicles that can be used by a user, and the accuracy of the probability that any vehicle type is selected for use in various vehicle usage scenarios can be effectively improved.

In this embodiment, the method for training the state checking model may include: obtaining a vehicle with an accurate vehicle health state as a training sample; and training the model parameters of the state inspection model according to the vector values of the training samples relative to the characteristic vectors and the vehicle health states of the training samples, so as to obtain the state inspection model.

< apparatus embodiment >

In the present embodiment, there is also provided an apparatus for monitoring a vehicle voltage, and as shown in fig. 4, the apparatus 4000 may include a feature extraction module 4100, an identification module 4200, and a low voltage processing module 4300.

The feature extraction module 4100 is configured to obtain a vector value of a target vehicle for a set feature vector according to historical data of the target vehicle in a last first set number of days, where the feature vector includes at least one feature affecting a vehicle voltage.

The identification module 4200 is configured to identify whether a low power state of the target vehicle occurs within a second set number of days in the future according to the vector value and a preset low voltage identification model, where the low power state is a state where a vehicle voltage is lower than or equal to a low voltage threshold.

The low voltage processing module 4300 is configured to perform setting processing on the target vehicle when the low power state may occur.

In one embodiment, the apparatus 4000 may further comprise a feature setting module, which may be configured to: setting the characteristic vector to comprise a first characteristic group and a second characteristic group, wherein the first characteristic group comprises vehicle voltage actual values of the monitored vehicle in each day in the last first set days, and the second characteristic group comprises vehicle voltage predicted values of the monitored vehicle in each day in the second set days in the future.

In this embodiment, the feature extraction module 4100, when obtaining the vector value of the target vehicle for the set feature vector according to the history data, may be configured to: acquiring the actual value of the vehicle voltage of each day in the historical data, and taking the actual value as the value of the target vehicle to the first characteristic group; according to the actual vehicle voltage value of each day in the historical data, obtaining the predicted vehicle voltage value of each day of the target vehicle in the second set number of days in the future, and taking the predicted vehicle voltage value as the value of the target vehicle to the second characteristic group; and obtaining the vector value according to the value of the target vehicle to the first characteristic group and the value of the target vehicle to the second characteristic group.

In an embodiment, the apparatus 4000 may further include a feature setting module, and the feature setting module may be configured to set the feature vector to include at least one of the following feature groups:

In one embodiment, the apparatus 4000 may further comprise a feature setting module, which may be configured to: acquiring the setting content of the feature vector; and updating the feature vector according to the setting content.

In one embodiment, the apparatus 4000 may further include a parameter setting module, which may be configured to: acquiring setting contents for at least one of the first set number of days and the second set number of days; and updating the corresponding set days according to the setting content.

In one embodiment, the apparatus 4000 may further include a vehicle screening module, which may be used to screen the target vehicle. This vehicle screening module can be used to when screening the target vehicle: screening vehicles with the vehicle voltage actual value reported latest in the current day being less than or equal to the set secondary low-voltage threshold value from the released vehicles as target vehicles; wherein the secondary low pressure threshold is higher than the low pressure threshold.

In one embodiment, the low voltage processing module 4300, in performing the setup process for the target vehicle, may perform at least one of:

In one embodiment, the apparatus 4000 may further include a model generation module that may be used to obtain the low pressure identification model. The model generation module, when obtaining the low pressure identification model, may be configured to: acquiring historical data of a sample vehicle in a first set number of days before a reference date as first historical data, and acquiring historical data of the sample vehicle in a second set number of days after the reference date as second historical data; obtaining vector values of corresponding sample vehicles for the feature vectors according to the first historical data; according to the second historical data, obtaining an actual classification result of whether the corresponding sample vehicle has a low power state within a second set number of days after the reference date; generating a training sample according to the matched vector value and the actual classification result; and training to obtain the low-pressure recognition model according to the training sample.

In one embodiment, the model generation module, when obtaining the low pressure identification model, may be further configured to: selecting the reference date; and screening, as the sample vehicle, a vehicle that satisfies a set condition among the dropped vehicles based on the reference date, wherein the set condition includes at least one of:

a first item that the vehicle state on the reference date is a healthy state;

a second term, in which the actual value of the vehicle voltage last reported on the reference date is less than or equal to a secondary low-voltage threshold, wherein the secondary low-voltage threshold is higher than the low-voltage threshold;

< apparatus embodiment >

In the present embodiment, there is also provided an electronic device, which may include the apparatus 4000 for monitoring a vehicle voltage according to any embodiment of the present invention, for implementing the method for monitoring a vehicle voltage according to any embodiment of the present invention.

As shown in fig. 5, the electronic device 5000 may further include a processor 5200 and a memory 5100, the memory 5100 being configured to store executable instructions; the processor 5200 is configured to operate the electronic device to perform a method of monitoring a vehicle voltage according to any embodiment of the present invention according to the commanded control.

The various modules of the above apparatus 4000 may be implemented by the processor 5200 executing the instructions to perform a method of monitoring a vehicle voltage according to any embodiment of the present invention.

The electronic device 5000 may be a server, or may be other types of devices, such as a terminal device, and the like, but is not limited thereto, and for example, the electronic device 5000 is the server 1000 in fig. 1, and the like.

The present invention may be a system, method and/or computer program product. The computer program product may include a computer-readable storage medium having computer-readable program instructions embodied therewith for causing a processor to implement various aspects of the present invention.

The computer readable storage medium may be a tangible device that can hold and store the instructions for use by the instruction execution device. The computer readable storage medium may be, for example, but not limited to, an electronic memory device, a magnetic memory device, an optical memory device, an electromagnetic memory device, a semiconductor memory device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a Static Random Access Memory (SRAM), a portable compact disc read-only memory (CD-ROM), a Digital Versatile Disc (DVD), a memory stick, a floppy disk, a mechanical coding device, such as punch cards or in-groove projection structures having instructions stored thereon, and any suitable combination of the foregoing. Computer-readable storage media as used herein is not to be construed as transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission medium (e.g., optical pulses through a fiber optic cable), or electrical signals transmitted through electrical wires.

The computer-readable program instructions described herein may be downloaded from a computer-readable storage medium to a respective computing/processing device, or to an external computer or external storage device via a network, such as the internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers and/or edge servers. The network adapter card or network interface in each computing/processing device receives computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in the respective computing/processing device.

The computer program instructions for carrying out operations of the present invention may be assembler instructions, Instruction Set Architecture (ISA) instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer-readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider). In some embodiments, aspects of the present invention are implemented by personalizing an electronic circuit, such as a programmable logic circuit, a Field Programmable Gate Array (FPGA), or a Programmable Logic Array (PLA), with state information of computer-readable program instructions, which can execute the computer-readable program instructions.

Aspects of the present invention are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer-readable program instructions.

These computer-readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks. These computer-readable program instructions may also be stored in a computer-readable storage medium that can direct a computer, programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer-readable medium storing the instructions comprises an article of manufacture including instructions which implement the function/act specified in the flowchart and/or block diagram block or blocks.

The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer, other programmable apparatus or other devices implement the functions/acts specified in the flowchart and/or block diagram block or blocks.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions. It is well known to those skilled in the art that implementation by hardware, by software, and by a combination of software and hardware are equivalent.

Having described embodiments of the present invention, the foregoing description is intended to be exemplary, not exhaustive, and not limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen in order to best explain the principles of the embodiments, the practical application, or improvements made to the technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein. The scope of the invention is defined by the appended claims.

Claims

1. A method of monitoring vehicle voltage, comprising:

2. The method of claim 1, further comprising: setting the characteristic vector to comprise a first characteristic group and a second characteristic group, wherein the first characteristic group comprises vehicle voltage actual values of the monitored vehicle in each day in the last first set days, and the second characteristic group comprises vehicle voltage predicted values of the monitored vehicle in each day in the second set days in the future;

3. The method of claim 1, the setting the feature vector comprising at least one of the following sets of features:

4. The method of claim 1, wherein the method further comprises:

acquiring the setting content of the feature vector;

and updating the feature vector according to the setting content.

5. The method of claim 1, wherein the method further comprises the step of screening the target vehicle, comprising:

6. The method of claim 1, wherein the configuring the target vehicle comprises at least one of:

7. The method of any one of claims 1 to 6, wherein the method further comprises the step of obtaining the low pressure identification model, comprising:

8. The method of claim 7, wherein the obtaining the low pressure identification model further comprises:

selecting the reference date;

a first item that the vehicle state on the reference date is a healthy state;

9. An apparatus for monitoring vehicle voltage, comprising:

10. An electronic device comprising the apparatus of claim 9; or,

the electronic device includes:

a memory for storing executable instructions;

a processor configured to execute the electronic device to perform the method according to the control of the instruction, wherein the method is as claimed in any one of claims 1 to 8.