CN117422294A

CN117422294A - Method, device, equipment and storage medium for determining power deficiency factor

Info

Publication number: CN117422294A
Application number: CN202311237872.5A
Authority: CN
Inventors: 李钰林; 蔡佳佳; 王茂林; 易纲; 贺刚
Original assignee: Chongqing Changan Automobile Co Ltd
Current assignee: Chongqing Changan Automobile Co Ltd
Priority date: 2023-09-22
Filing date: 2023-09-22
Publication date: 2024-01-19

Abstract

The application relates to a method, a device, equipment and a storage medium for determining a power loss factor, and relates to the technical field of vehicle detection. The method comprises the following steps: a first time series and a plurality of second time series are acquired, wherein the first time series comprises the power deficiency probability of the vehicle in different time, and the second time series comprises the influence factors of the power deficiency of the vehicle in different time. And carrying out causal relation detection on the first time sequence and each second time sequence to obtain at least one target time sequence, wherein the target time sequence is a second time sequence which passes the causal relation detection with the first time sequence in the plurality of second time sequences. And determining the power deficiency factor corresponding to each target time sequence according to each target time sequence in the at least one target time sequence so as to determine at least one power deficiency factor. Therefore, the influence factors of the vehicle power shortage are determined through causal relation inspection, and the accuracy of judging the cause of the battery power shortage is improved.

Description

Method, device, equipment and storage medium for determining power deficiency factor

Technical Field

The application relates to the technical field of vehicle detection, in particular to a method, a device, equipment and a storage medium for determining a power loss factor.

Background

With the rapid development of automobile technology, the number of automobiles is increasing, and various faults of automobiles are attracting more and more attention. For example, a vehicle battery is a relatively common problem. The power shortage of the storage battery can be caused by the faults of the storage battery, and also can be caused by the improper behaviors of a driver, so that the power shortage reason of the storage battery can be timely determined, and the risk of continuing power shortage can be reduced.

At present, the method for judging the cause of the battery deficiency is to detach the battery with the deficiency from the vehicle for detection, inquire the vehicle service condition of a driver and comprehensively judge the cause of the battery with the deficiency. However, the driving habits fed back by the driver may deviate, and if the staff is not specialized in the battery, the accuracy of determining the cause of the battery deficiency may be lowered.

Disclosure of Invention

The application provides a method, a device, equipment and a storage medium for determining a power shortage factor, which are used for at least solving the technical problem of accuracy reduction of determining the power shortage reason of a storage battery in the related technology. The technical scheme of the application is as follows:

according to a first aspect to which the present application relates, there is provided a method of determining a deficiency factor, the method comprising: a first time sequence and a plurality of second time sequences are acquired, wherein the first time sequence comprises the power deficiency probability of the vehicle in different time, the second time sequence comprises the influence factors of the power deficiency of the vehicle in different time, and one second time sequence corresponds to one influence factor. And carrying out causal relation detection on the first time sequence and each second time sequence to obtain at least one target time sequence, wherein the target time sequence is a second time sequence which passes the causal relation detection with the first time sequence in the plurality of second time sequences. And determining the power deficiency factor corresponding to each target time sequence according to each target time sequence in the at least one target time sequence so as to determine at least one power deficiency factor.

According to the technical means, the influence factors of the vehicle power shortage are determined according to causal relation inspection, accuracy of judging the cause of the battery power shortage is improved, early warning efficiency of the battery power shortage can be improved, potential vehicle power shortage risks can be found and exposed in advance, so that staff or drivers can respond in time, and the power shortage risks are reduced.

In one possible embodiment, vehicle information of a vehicle and state information of the vehicle are acquired. The "acquiring the first time series and the plurality of second time series" includes: the method comprises the steps of preprocessing vehicle information of vehicles and state information of the vehicles to obtain a third time sequence and a plurality of fourth time sequences, wherein the third time sequence comprises power deficiency probabilities of the vehicles in different times, fluctuation values of the power deficiency probabilities of the vehicles in different times are larger than a preset fluctuation threshold, the fourth time sequence comprises influence factors of the power deficiency of the vehicles in different times, and fluctuation values of the influence factors of the power deficiency of the vehicles in different times are larger than the preset fluctuation threshold. And performing stationarity processing on the third time sequence to obtain a first time sequence. And carrying out stationarity processing on each fourth time sequence to obtain a second time sequence corresponding to each fourth time sequence so as to obtain a plurality of second time sequences.

According to the technical means, the collected data is preprocessed, the time sequence tends to be stable, the requirement of causality examination is met, and the calculated amount can be reduced.

In one possible embodiment, the vehicle information includes at least one of: vehicle basic information, vehicle alarm information, vehicle maintenance information, vehicle complaint information and vehicle rescue information; the status information includes: battery state information and travel state information.

According to the technical means, the reference information adopted in the method is large in quantity, and the accuracy of determining the cause of the power deficiency of the storage battery can be improved.

In one possible embodiment, the pretreatment comprises at least one of: data deduplication processing, time sequence alignment processing, null value filling processing, exception clearing processing and format unification processing.

According to the technical means, the data are preprocessed, the information with lower reference value can be removed, the accuracy of determining the power shortage reason of the storage battery is improved, the quality of a data mining mode can be improved, and the time required by actual mining is reduced.

In one possible implementation, the performing the causal relationship check on the first time series and each second time series to obtain at least one target time series includes: for each second time series, determining whether the first time series and the second time series pass a causal relationship check according to the target operation, and taking the second time series which passes the causal relationship check with the first time series as the target time series. The target operations include: and determining a first error according to the first time sequence and the autoregressive equation, wherein the first error is an error for predicting the power deficiency probability. And determining a second error according to the first time sequence, the second time sequence and the joint regression equation, wherein the second error is an error for predicting the power deficiency probability under the action of the influence factors. According to the first error, the second error and the F-test method, it is determined whether the first time series and the second time series pass a causal relationship test.

According to the technical means, after the first error and the second error corresponding to the first time sequence are detected by calculating the first error and the second error corresponding to the second time sequence, whether the first time sequence and the second time sequence meet the causality detection or not is determined according to the first error and the second error, and therefore accuracy of the causality detection can be improved.

In one possible implementation, the method for determining the deficiency factor includes: based on the vehicle information and at least one power loss factor of the vehicle, constructing an representation of the vehicle, the representation of the vehicle being used to reflect a power loss cause of the vehicle.

According to the technical means, the image of the vehicle is constructed based on the vehicle information of the vehicle and at least one power shortage factor, and the power shortage reason of the vehicle is reflected through the image, so that a worker can conveniently and intuitively determine the power shortage reason of the vehicle. And the related side of the power shortage can be rapidly positioned from the dimension of massive vehicle-end data through the data mining application method mode, so that the time cost and the labor cost of large data mining can be reduced.

According to a second aspect provided by the present application, there is provided a device for determining a deficiency factor, the device comprising: an acquisition unit and a processing unit.

The system comprises an acquisition unit, a control unit and a control unit, wherein the acquisition unit is used for acquiring a first time sequence and a plurality of second time sequences, the first time sequence comprises the power deficiency probability of the vehicle in different time, the second time sequence comprises the influence factors of the power deficiency of the vehicle in different time, and one second time sequence corresponds to one influence factor. And the processing unit is used for carrying out causal relation detection on the first time sequence and each second time sequence to obtain at least one target time sequence, wherein the target time sequence is a second time sequence which passes the causal relation detection with the first time sequence in the plurality of second time sequences. The processing unit is further configured to determine, according to each target time sequence in the at least one target time sequence, a power loss factor corresponding to each target time sequence, so as to determine at least one power loss factor.

In one possible embodiment, the acquiring unit is further configured to acquire vehicle information of the vehicle and status information of the vehicle. The processing unit is further configured to pre-process vehicle information of the vehicle and state information of the vehicle to obtain a third time sequence and a plurality of fourth time sequences, where the third time sequence includes a power loss probability of the vehicle in different time periods, a fluctuation value of the power loss probability of the vehicle in different time periods is greater than a preset fluctuation threshold, the fourth time sequence includes an influence factor of the power loss of the vehicle in different time periods, and a fluctuation value of the influence factor of the power loss of the vehicle in different time periods is greater than the preset fluctuation threshold. The processing unit is further configured to perform stationarity processing on the third time sequence to obtain a first time sequence. The processing unit is further configured to perform stationarity processing on each fourth time sequence to obtain a second time sequence corresponding to each fourth time sequence, so as to obtain a plurality of second time sequences.

In a possible implementation manner, the processing unit is specifically configured to determine, for each second time sequence, whether the first time sequence and the second time sequence pass a causal relationship test according to a target operation, and take, as the target time sequence, the second time sequence that passes the causal relationship test with the first time sequence. The target operations include: the processing unit is specifically configured to determine a first error according to the first time sequence and the autoregressive equation, where the first error is an error for predicting the power loss probability. The processing unit is specifically configured to determine a second error according to the first time sequence, the second time sequence, and the joint regression equation, where the second error is an error that predicts the power loss probability under the influence of the influence factor. The processing unit is specifically configured to determine whether the first time sequence and the second time sequence pass the causal relationship test according to the first error, the second error, and the F test method.

In a possible implementation manner, the processing unit is further configured to construct an image of the vehicle based on the vehicle information of the vehicle and at least one power loss factor, where the image of the vehicle is used to reflect a power loss cause of the vehicle.

According to a third aspect provided by the present application, there is provided an electronic device comprising: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to execute instructions to implement the method of the first aspect and any of its possible embodiments described above.

According to a fourth aspect provided herein, there is provided a computer readable storage medium, which when executed by a processor of an electronic device, enables the electronic device to perform the method of any one of the above-mentioned first aspects and any one of its possible embodiments.

According to a fifth aspect provided herein, there is provided a computer program product comprising computer instructions which, when run on an electronic device, cause the electronic device to perform the method of the first aspect and any of its possible embodiments.

Therefore, the technical characteristics of the application have the following beneficial effects:

(1) And determining the influence factors of the vehicle deficiency according to the causal relationship test, improving the accuracy of judging the cause of the battery deficiency, improving the early warning efficiency of the battery deficiency, and finding and exposing the potential vehicle deficiency risk in advance so as to facilitate the timely response of staff or drivers and reduce the deficiency risk.

(2) The acquired data is preprocessed, and the information with lower reference value is removed, so that the calculated amount can be reduced, and the accuracy of determining the power deficiency reason of the storage battery is improved. And the time sequence can be enabled to be stable, and the requirement of causality examination is met.

(3) Based on the vehicle information and at least one power shortage factor of the vehicle, an image of the vehicle is constructed, and the power shortage reason of the vehicle is reflected through the image, so that a worker can conveniently and intuitively determine the reason for the power shortage of the vehicle.

It should be noted that, the technical effects caused by any implementation manner of the second aspect to the fifth aspect may refer to the technical effects caused by the corresponding implementation manner in the first aspect, which are not described herein.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application and do not constitute an undue limitation on the application.

FIG. 1 is a schematic diagram of an architecture of a system for determining a deficiency factor, according to an example embodiment;

FIG. 2 is a flow chart illustrating a method of determining a deficiency factor in accordance with an exemplary embodiment;

FIG. 3 is a flow chart illustrating a method of determining a deficiency factor in accordance with an exemplary embodiment;

FIG. 4 is a flow chart illustrating a method of determining a deficiency factor in accordance with an exemplary embodiment;

FIG. 5 is a block diagram illustrating a device for determining a deficiency factor in accordance with an exemplary embodiment;

fig. 6 is a block diagram of an electronic device, according to an example embodiment.

Detailed Description

In order to enable those skilled in the art to better understand the technical solutions of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.

It should be noted that the terms "first," "second," and the like in the description and claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that embodiments of the present application described herein may be implemented in sequences other than those illustrated or otherwise described herein. The implementations described in the following exemplary examples are not representative of all implementations consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present application as detailed in the accompanying claims.

Before describing the method for determining the deficiency factor in the embodiment of the present application in detail, the implementation environment and application field Jing Jinhang of the embodiment of the present application will be described.

The power shortage of the storage battery can be caused by the faults of the storage battery, and also can be caused by the improper behaviors of a driver, so that the power shortage reason of the storage battery can be timely determined, and the risk of continuing power shortage can be reduced. At present, the method for judging the cause of the battery deficiency is to detach the battery with the deficiency from the vehicle for detection, inquire the vehicle service condition of a driver and comprehensively judge the cause of the battery with the deficiency. However, the driving habits fed back by the driver may deviate, and if the staff is not specialized in the battery, the accuracy of determining the cause of the battery deficiency may be lowered.

In order to solve the above-mentioned problems, an embodiment of the present application provides a method for determining a deficiency factor, including: the target server may obtain a first time series and a plurality of second time series, the first time series including a power loss probability of the vehicle at different times, the second time series including an impact factor of the power loss of the vehicle at different times, one of the second time series corresponding to one of the impact factors. The target server may perform a causal relationship check on the first time sequence and each second time sequence to obtain at least one target time sequence, where the target time sequence is a second time sequence that passes the causal relationship check with the first time sequence in the plurality of second time sequences. The target server may determine a power loss factor corresponding to each target time sequence according to each target time sequence in the at least one target time sequence, so as to determine the at least one power loss factor. Therefore, the target server can determine the influence factors of the vehicle power shortage according to the causal relation test, and accuracy of judging the cause of the battery power shortage is improved. And moreover, the early warning efficiency of the battery power deficiency can be improved, and the potential vehicle power deficiency risk can be found and exposed in advance, so that the staff can solve the problem in time, and the power deficiency risk is reduced.

The following describes an implementation environment of an embodiment of the present application.

Fig. 1 is a schematic architecture diagram of a system for determining a deficiency factor according to an exemplary embodiment, and as shown in fig. 1, the communication system includes: a target server 101, and an in-vehicle communication system 102. The target server 101 performs wired/wireless communication with the in-vehicle communication system 102.

Wherein the target server 101 may communicate with the in-vehicle communication system 102. For example, the target server 101 may receive vehicle information and status information from the in-vehicle communication system 102. Also, the target server 101 may process the vehicle information and the state information.

The target server may be a single physical target server, or may be a target server cluster formed by a plurality of target servers. Alternatively, the target server cluster may also be a distributed cluster. Alternatively, the target server may be a cloud target server. The embodiment of the application does not limit the specific implementation manner of the target server.

The in-vehicle communication system 102 may store vehicle information of the vehicle. The in-vehicle communication system 102 may receive status information of the vehicle detected by each of the plurality of vehicle detection systems. The in-vehicle communication system 102 may transmit vehicle information of the vehicle and a state of the vehicle to the target server 101.

For easy understanding, the method for determining the deficiency factor provided in the present application is specifically described below with reference to the accompanying drawings. Fig. 2 is a flow chart illustrating a method of determining a deficiency factor according to an exemplary embodiment, as shown in fig. 2, the method comprising the steps of:

s201, the target server acquires a first time sequence and a plurality of second time sequences.

Wherein the first time series comprises the power loss probability of the vehicle at different times and the second time series comprises the influence factor of the power loss of the vehicle at different times.

In one possible design, the first time series may be represented by y (a 1, a2, …, an). Wherein y is used for representing vehicle identification, n is used for representing the number of time stamps in different time, the value range of the power shortage probability a is [0,1],0 is used for representing that the power shortage probability of the vehicle is 0, and 1 is used for representing that the vehicle actually lacks power. The second time series may be represented by x (b 1, b2, …, bn). Where x is used to represent the impact factor, n is used to represent the number of time stamps in different time stamps, and b is used to represent the value of the impact factor at different time stamps.

Illustratively, the first time series may be y1 (0,0.21,0.25,0.24,0.26,0.54,0, …,1, 0.99), the first time series including a probability of power loss during the day for vehicle number y1, at 0.1 second intervals. The second time series may be x1 (25.5,25.6,25.5,25.8,26.5,27.5, …,27.9,30.0) being the ambient temperature of the same day as the y1 vehicle, with a time interval of 0.1 seconds.

In the embodiment of the present application, the influence factor is not limited. For example, the influencing factor may be ambient temperature. For another example, the impact factor may be a vehicle speed. For another example, the impact factor may be a door opening. For another example, the influencing factor may be a window opening. For another example, the influencing factor may be the fuel consumption. As another example, the influencing factor may be the battery temperature.

In one possible implementation, the target server may receive a first input instruction, the first input instruction being for indicating to input the first time series and the plurality of second time series. In response to the first input instruction, the target server may acquire a first time series and a plurality of second time series.

S202, the target server performs causal relation detection on the first time sequence and each second time sequence to obtain at least one target time sequence.

The target time sequence is a second time sequence which passes the causal relation test with the first time sequence in the plurality of second time sequences.

It should be noted that, in the embodiment of the present application, the causal relationship test may be a gland causal relationship test. The glabrous cause and effect relationship test is used to test whether one set of time series (e.g., time series a) is the cause of glabrous in another set of time series (e.g., time series B). If time series a is the gland cause of time series B, it is explained that a is the influencing factor of B. If the time series a includes the variable X and the time series B includes the variable B, and if the prediction effect of the historical information based on the variable X and the variable Y on the variable Y is better than the prediction effect of the historical information based on the variable Y alone, the variable X is considered as the cause of the glaring of the variable Y, that is, the glaring causal relationship exists between the variable X and the variable Y, and the change of the variable X can explain the change of the variable Y.

In one possible implementation, for each second time series, the target server may determine whether the first time series and the second time series pass a causal relationship check. If the first time series and the second time series pass the causal relationship test, the target server may use the second time series as a target time series to determine at least one target time series.

S203, the target server determines the power deficiency factor corresponding to each target time sequence according to each target time sequence in at least one target time sequence so as to determine at least one power deficiency factor.

In one possible implementation, for each target time series, the target server may determine an impact factor corresponding to the target time series. The target server may take the target time series correspondence affecting factor as a power loss factor to determine at least one power loss factor.

It will be appreciated that the target server may obtain a first time series including the power loss probability of the vehicle at different times and a plurality of second time series including the influence factor of the power loss of the vehicle at different times, one of the second time series corresponding to one of the influence factors. The target server may perform a causal relationship check on the first time sequence and each second time sequence to obtain at least one target time sequence, where the target time sequence is a second time sequence that passes the causal relationship check with the first time sequence in the plurality of second time sequences. The target server may determine a power loss factor corresponding to each target time sequence according to each target time sequence in the at least one target time sequence, so as to determine the at least one power loss factor. Therefore, the target server can determine the influence factors of the vehicle power shortage according to the causal relation test, and accuracy of judging the cause of the battery power shortage is improved. And moreover, the early warning efficiency of the battery power deficiency can be improved, and the potential vehicle power deficiency risk can be found and exposed in advance, so that the staff can solve the problem in time, and the power deficiency risk is reduced.

In some embodiments, to acquire the first time series and the plurality of second time series, as shown in fig. 3, the target server may perform the following steps before acquiring the first time series and the plurality of second time series:

s301, the target server acquires vehicle information of the vehicle and state information of the vehicle.

Wherein the vehicle information includes at least one of: vehicle basic information, vehicle alarm information, vehicle maintenance information, vehicle complaint information and vehicle rescue information. The status information includes: battery state information and travel state information.

It should be noted that, in the embodiment of the present application, the vehicle basic information may include: the vehicle-mounted terminal device unique identification code (vehicle terminal equipment unique identification code, TUID) of the vehicle, the vehicle identification code (vehicle identification code, VIN) of the vehicle, the train code, the train name, the real-name authentication time, the configuration name, the configuration code, the dealer address, the dealer telephone. The vehicle warning information may include: vehicle VIN code, alarm starting time, alarm ending time, train, alarm position, alarm type, alarm reason, alarm wake-up time, electric quantity when alarm and voltage when alarm. The vehicle maintenance information may include: vehicle VIN code, production date, maintenance audit date, stock length, product name, vehicle nature, customer issue code (customer concern code, CCC) code, CCC name. The vehicle complaint information may include: vehicle VIN code, complaint time, CCC name, dealer, complaint content. The vehicle rescue information may include: vehicle VIN code, rescue time, user type, vehicle brand, train, repair order number, repair order content, order handling dealer name, order handling dealer contact phone. The battery state information may include: the battery usage information (e.g., maximum value, minimum value, start value, end value of the percentage of remaining charge (SOC) of the battery in the preset period, maximum value, minimum value, start value, end value of the functional state (state of function, SOF) of the battery in the preset period), and the battery performance information (e.g., power-on time, power-off time, power-on charge, power-off charge, charge amount of the vehicle in the preset period) in the preset period. The driving state information may include: power on/off state, ambient temperature, vehicle speed, fuel consumption, door opening, window opening, etc.

In one possible implementation, a vehicle is deployed with an on-board communication system. The in-vehicle communication system may transmit the status information of the vehicle to the target server. The target server may receive status information from the in-vehicle communication system.

In one possible design, the vehicle is deployed with a plurality of vehicle detection systems for detecting the state of the vehicle within a preset period of time to obtain the state information of the vehicle. Each of the plurality of vehicle detection systems may send vehicle status information to the vehicle communication system via a controller area network (controller area network, CAN) signal or via a tag length value (tag, length, value, TLV) format.

For example, the plurality of vehicle detection systems may include: temperature sensor, battery sensor, automobile body controller, transmitter control module, instrument. The temperature sensor can detect the environment temperature of the vehicle, the storage battery sensor can detect the battery state, the vehicle body controller can detect the power state, the vehicle door state, the vehicle window state and the like of the vehicle, the engine control module can detect the engine state of the vehicle, and the instrument can detect the driving mileage and the vehicle speed of the vehicle.

In the embodiment of the application, the target server may acquire the vehicle information of the vehicle from the vehicle management department. The servers deployed by the vehicle management department may each send vehicle information of the vehicle to the target server. The target server may receive vehicle information for the vehicle.

For example, the vehicle management may include: automobile sales service (automobile sales servicshop, 4S) store, dealer, repair shop.

In another possible implementation, the target server may receive a second input instruction for inputting vehicle information of the vehicle and status information of the vehicle. In response to the second input instruction, the target server may acquire vehicle information of the vehicle and state information of the vehicle.

In this embodiment of the present application, the target server may collect the original CAN signal, the buried point data, and the TLV data at the vehicle end in real time, and may also synchronize the data of vehicle maintenance, rescue information, official portal feedback, complaint data, charging of a third party platform, insurance, etc. at a 4S shop, a dealer, a repair shop, etc. offline.

In some embodiments, the target server obtains a first time series and a plurality of second time series (S201), comprising: S302-S304.

S302, the target server preprocesses vehicle information of the vehicle and state information of the vehicle to obtain a third time sequence and a plurality of fourth time sequences.

The third time sequence comprises the power deficiency probability of the vehicle in different time, and the fluctuation value of the power deficiency probability of the vehicle in different time is larger than a preset fluctuation threshold; the fourth time sequence comprises influence factors of the vehicle power shortage in different time, and the fluctuation value of the influence factors of the vehicle power shortage in different time is larger than a preset fluctuation threshold.

It should be noted that, in the embodiment of the present application, the power loss probabilities of the vehicles in different times may form a first curve, and the fluctuation values of the power loss probabilities of the vehicles in different times are used to indicate the fluctuation degree of the first curve. The influence factors of the vehicle loss of electricity in different times can form a second curve, and fluctuation values of the influence factors of the vehicle loss of electricity in different times are used for indicating the fluctuation degree of the second curve. The larger the fluctuation value is, the larger the fluctuation degree of the curve is; the smaller the fluctuation value, the smaller the fluctuation degree of the curve. In one possible design, the preprocessing may include at least one of: data deduplication processing, null value filling processing, time sequence alignment processing, exception clearing processing and format unification processing.

In the embodiment of the present application, the situation that the target server may have abnormal communication in acquiring the vehicle information of the vehicle and the state information of the vehicle may cause repeated acquisition of part of the data or a part of the data is empty. Therefore, the target server can preprocess the data, improve the quality of the data mining mode and reduce the time required by actual mining.

Specifically, the target server may perform data deduplication processing on the data that is partially uploaded repeatedly or is conducted repeatedly abnormally according to the vehicle VIN code, the timestamp, and the CAN message identifier (CAN identification, CAN) as main attributes, so as to obtain information after the data deduplication processing, and ensure that only one piece of data exists in the same CAN with the same timestamp. The target server can perform null value filling processing on the information subjected to the data de-duplication processing, sort the information subjected to the data de-duplication processing according to the time stamp, and search a first non-null value for filling before null value orientation to obtain the information subjected to the null value filling processing. The target server can perform time sequence alignment processing on the information subjected to the null value filling processing based on the time stamps, so that the time stamp intervals are unified to be 0.1 second, and the information subjected to the time sequence alignment processing is obtained. And then, the target server can perform exception clearing processing on the information after the time sequence alignment processing, and delete the information exceeding the preset effective value threshold value in the information after the time sequence alignment processing to obtain the information after the exception clearing processing. The target server can adjust the information after the exception clear processing into a unified data format.

In the embodiment of the application, after the target server performs preprocessing on the vehicle information of the vehicle and the state information of the vehicle, the target server may store the vehicle information and the state information in the data warehouse according to the date partition. The target server may determine the power loss probability of the vehicle at different times according to the vehicle information of the vehicle and the state information of the vehicle, so as to obtain the first time sequence.

In one possible design, the target server may input vehicle information of the vehicle and state information of the vehicle into the trained power loss prediction model to obtain power loss probabilities of the vehicle in different times, so as to obtain the first time sequence.

S303, the target server performs stability processing on the third time sequence to obtain a first time sequence.

In one possible implementation, the target server may perform trending and averaging processing on the third time sequence to obtain a processed third time sequence. The target server may perform a unit root check on the processed third time series.

It should be noted that, in the embodiment of the present application, the time sequence required by the glaring causal relationship is a stable time sequence, the stable time sequence does not contain a variation trend, and a plurality of sections of data in the sequence are taken to calculate variances, so that the obtained variances have no obvious difference. The target server may subtract a best fit line from the third time series such that the overall trend is not significantly increased or decreased. The target server may perform a de-averaging process on the trended time series, causing the time series to fluctuate around the y=0 axis. In this way, the time series can be made smooth, and the calculation amount can be reduced after the averaging process.

In one possible design, if the processed third time series fails the unit root test, the target server may first-order differential the processed third time series until the processed third time series passes the unit root test.

In another possible design, the target server may determine the processed third time series as the first time series if the processed third time series passes the unit root test.

S304, the target server performs stationarity processing on each fourth time sequence to obtain a second time sequence corresponding to each fourth time sequence, so as to obtain a plurality of second time sequences.

In one possible implementation, for each fourth time sequence, the target server may perform a trending process and a averaging process on the fourth time sequence, to obtain a processed fourth time sequence. The target server may perform a unit root check on the processed fourth time series.

In one possible design, if the processed fourth time series fails the unit root test, the target server may first differential the processed fourth time series until the processed fourth time series passes the unit root test.

In another possible design, the target server may determine the processed fourth time series as the second time series if the processed fourth time series passes the root-by-root test.

It is understood that the target server may acquire vehicle information of the vehicle and status information of the vehicle. The target server can preprocess vehicle information of the vehicle and state information of the vehicle to obtain a third time sequence and a plurality of fourth time sequences, wherein the third time sequence comprises the power shortage probability of the vehicle in different time, the fluctuation value of the power shortage probability of the vehicle in different time is larger than a preset fluctuation threshold, the fourth time sequence comprises the influence factors of the power shortage of the vehicle in different time, and the fluctuation value of the influence factors of the power shortage of the vehicle in different time is larger than the preset fluctuation threshold. And then, the target server can perform stationarity processing on the third time sequence to obtain a first time sequence. The target server may perform stationarity processing on each fourth time sequence to obtain a second time sequence corresponding to each fourth time sequence, so as to obtain a plurality of second time sequences. In this way, the target server can smooth the time series, meet the requirements of causal relationship verification, and reduce the amount of computation.

In some embodiments, after the target server performs preprocessing on the vehicle information of the vehicle and the state information of the vehicle, the target server may further construct a vehicle basic information model, a vehicle state query model, and a vehicle history query model according to the preprocessed vehicle information of the vehicle and the state information of the vehicle. The target server may construct a shallow representation of the vehicle based on the vehicle base information model, the vehicle status query model, and the vehicle history query model.

In an embodiment of the present application, the vehicle basic information model may include: vehicle TUID, vehicle VIN, train code, train name, real name authentication time, configuration name, configuration code, dealer address, dealer phone. The vehicle state query model may include: the method includes the steps of providing information of different time intervals of single use in a preset period (total number of times of use in the preset period, time length of use in the preset period is less than Zhong Cishu, time length of use in the preset period is ten minutes to thirty minutes, time length of use in the preset period is greater than thirty minutes), recording information of incapability of starting of the vehicle in the preset period (date, SOC maximum value, SOC minimum value, SOC start value, SOC end value, SOF maximum value, SOF minimum value, SOF start value, SOF end value), network signal information of a vehicle end in the preset period (date, time length of non-dormancy, time length of abnormal wake-up, time length of wake-up, time length of electric quantity distribution), recording information of full 10 days of vehicle parking in the preset period (VIN code, vehicle system, parking start time, time length of parking end time, time length of parking), alarm information in the preset period (time length of non-dormancy, time length of abnormal wake-up, time length of electric quantity at alarm time, voltage at alarm time, abnormal start time, abnormal release time), battery performance information (last time, last time of parking, last time of discharge, last time, power up, power consumption, preset charge amount, alarm time, reason of the alarm time). The vehicle history query model may include: alert information (VIN code, abnormal start time, abnormal end time, train, event address, alert type, alert cause, no sleep time, abnormal wake time, specific cause, power, voltage, configuration, dealer address), maintenance information (VIN code, production date to month, production date to time stamp, maintenance date to month, maintenance audit date, library age, product name, vehicle nature, CCC code, CCC name), complaint information (VIN code, number, train code, complaint time, CCC name, dealer, problem summary/brief), rescue information (VIN code, creation time, user type, vehicle brand, train, job ticket number, job ticket content, job ticket process dealer name, job ticket process dealer contact phone).

It can be understood that the target server can perform data extraction on relevant vehicle data according to the vehicle basic information model, the vehicle state query model and the vehicle history query model, and establish a vehicle portrait dimension model to obtain a shallow portrait result of the electric power shortage vehicle, so that staff can intuitively identify electric power shortage information of the vehicle.

In some embodiments, to improve the accuracy of the causal relationship check, the target server performs the causal relationship check on the first time series and each of the second time series to obtain at least one target time series (S202), including: for each second time series, the target server may determine whether the first time series and the second time series pass a causal relationship check according to the target operation, and regard the second time series that passes the causal relationship check with the first time series as the target time series.

In the embodiment of the present application, as shown in fig. 4, the target operation includes:

s401, the target server determines a first error according to the first time sequence and the autoregressive equation.

The first error is an error for predicting the power shortage probability.

In one possible implementation, the target server may calculate the first time series of hysteresis orders by the red-pool information criterion (akaike information criterion, AIC).

In one possible design, the hysteresis order of the first time series may be represented by equation one.

Wherein, lag ₁ For representing the hysteresis order of the first time series, RSS for representing the sum of residuals after fitting the first time series, and n for representing the total number of data of the first time series.

In the embodiment of the present application, a lag that minimizes AIC is found in the range of 1 to n ₁ Lag to minimize AIC ₁ I.e. the hysteresis order of the first time series. The sum of residuals after the first time series fit may be represented by equation two.

Wherein RSS ₁ For representing the sum of residuals after the first time series fitting, n for representing the total number of data of the first time series,for representing the average value of the first time series, y _i For representing the ith data in the first time series.

In the embodiment of the present application, the target server may construct an autoregressive equation according to the hysteresis order of the first time sequence. The target server may determine a plurality of first sub-errors based on the first time series and the autoregressive equation.

In one possible design, the autoregressive equation may be represented by equation three.

Wherein Y is _t For representing the t-th data, delta, in a first time series ₀ For representing constant terms calculated by fitting in autoregressive equations, lag ₁ For representing the hysteresis order of the first time series, y _t-k Hysteresis sequence value, beta, for representing target variable _k Equation coefficient epsilon used for representing fitting calculation in autoregressive equation _t For representing a first sub-error corresponding to the t-th data.

The target server may then determine a first error from the plurality of first sub-errors.

In one possible design, the first error may be represented by equation four.

Wherein P1 is used for representing a first error, n is used for representing the total number of data of the first time sequence, and lag ₁ For representing the hysteresis order, epsilon of a first time series _l For representing a first sub-error of the plurality of first sub-errors,for representing an average of the first plurality of sub-errors.

S402, the target server determines a second error according to the first time sequence, the second time sequence and the joint regression equation.

The second error is an error for predicting the power deficiency probability under the effect of the influence factors.

In one possible implementation, the target server may calculate the hysteresis order of the second time series by AIC.

In one possible design, the hysteresis order of the second time series may be represented by equation five.

Wherein, lag ₂ For representing the hysteresis order of the second time series, RSS ₂ For representing the sum of residuals after the second time series fitting, and m for representing the total number of data of the second time series.

In the embodiment of the present application, a lag that minimizes AIC is found in the range of 1 to m ₂ Lag to minimize AIC ₂ I.e. the hysteresis order of the second time series. The sum of residuals after the second time series fitting may be represented by equation six.

Wherein RSS ₂ For representing the sum of the residuals after fitting, n for representing the total number of data of the second time series,for representing the average value, x, of the second time series _j For representing the j-th data in the second time series.

In the embodiment of the present application, the target server may construct a joint regression equation according to the hysteresis order of the first time sequence and the hysteresis order of the second time sequence.

In one possible design, the joint regression equation may be represented by equation seven.

Wherein Y is _t For representing the t-th data, delta, in a first time series ₀ For representing constant terms, lag, calculated by fitting in a joint regression equation ₁ For representing the hysteresis order of the first time series, y _t-k Hysteresis sequence value, beta, for representing target variable _k Equation coefficient epsilon used for representing fitting calculation in autoregressive equation _t And the second sub-error is used for representing the corresponding t-th data.

The target server may then determine a second error based on the plurality of second sub-errors.

In one possible design, the second error may be represented by equation eight.

Wherein P2 is used for representing a second error, n is used for representing the total number of data of the first time sequence, lag ₁ For representing the hysteresis order, epsilon of a first time series _l ^′ For representing a first one of the plurality of second sub-errors,for representing an average of the plurality of second sub-errors.

In some embodiments, after the target server obtains the first plurality of sub-errors and the second plurality of sub-errors, the target server may determine whether the first plurality of sub-errors obey a normal distribution for the first plurality of sub-errors Du Erbin white test (Durbin-Watson test). The target server may also perform a consistency check on the plurality of first sub-errors to determine whether the plurality of first sub-errors meets a preset error threshold.

Similarly, the target server may determine whether the plurality of second sub-errors obey a normal distribution for a plurality of second sub-errors Du Erbin white test (Durbin-Watson test). The target server may also perform a consistency check on the plurality of second sub-errors to determine whether the plurality of second sub-errors meets a preset error threshold.

In one possible design, if the first plurality of sub-errors or the second plurality of sub-errors do not follow a normal distribution, or the first plurality of sub-errors or the second plurality of sub-errors do not meet a predetermined error threshold, the target server needs to regress the first time series and the second plurality of time series.

In another possible design, if the first plurality of sub-errors or the second plurality of sub-errors obey a normal distribution, and the first plurality of sub-errors or the second plurality of sub-errors satisfy the preset error threshold, the target server may execute S403.

It should be noted that, in the embodiment of the present application, since the error compliance with the normal distribution is a prerequisite for solving the regression problem using the least square method, it is necessary to check whether the plurality of first sub-errors are compliant with the normal distribution by the Du Erbin white-channel test (Durbin-Watson test) method and to check whether the plurality of second sub-errors are compliant with the normal distribution by the Du Erbin white-channel test method. If the first plurality of sub-errors or the second plurality of sub-errors do not follow a normal distribution, the preconditions for using the least squares method are not satisfied, nor is the basis for the graininess causality check. In this way, the accuracy of the gland cause and effect relationship test can be improved.

S403, the target server determines whether the first time sequence and the second time sequence pass the causal relationship test according to the first error, the second error and the F test method.

In one possible implementation, after the target server obtains the first error and the second error, the target server may perform an F-check on the first error and the second error to determine whether the first time series and the second time series pass a causal relationship check.

In the embodiment of the present application, the F-test can be expressed by formula nine.

Wherein P1 is used to represent a first error, P2 is used to represent a second error, lag ₁ For representing the hysteresis order of the first time series, n for representing the total number of data of the first time series.

In one possible design, the target server may set the original assumption that the first time series and the second time series are not glaring causal, and if the F value is greater than the significance threshold, the target server may accept the original assumption and determine that the first time series and the second time series do not pass the causal relationship check.

For example, if the impact factor corresponding to the second time series is ambient temperature. Assume the original assumption H0: the ambient temperature is not a gladhand causality of vehicle loss of power, i.e. the second error is greater than the first error. If the significance threshold is 0.05, if the F value is greater than 0.05, the probability that the environmental temperature is not the Grandiary cause and effect relationship of the vehicle power shortage is high, the original assumption H0 is accepted, and the environmental temperature is not the Grandiary cause and effect relationship of the vehicle power shortage is proved.

In another possible design, the target server may set the original hypothesis that the first time series and the second time series are glaring causal, and if the F value is less than or equal to the significance threshold, the target server may reject the original hypothesis, and determine that the first time series and the second time series pass the causal relationship test.

For example, if the impact factor corresponding to the second time series is ambient temperature. Assume the original assumption H0: the ambient temperature is not a gladhand causality of vehicle loss of power, i.e., the second error is less than or equal to the first error. If the significance threshold is 0.05, if the F value is less than or equal to 0.05, the probability that the environmental temperature is not the Grangel causal relationship of the vehicle power deficiency is small, the original assumption H0 is refused, and the environmental temperature is proved to be the Grangel causal relationship of the vehicle power deficiency.

It will be appreciated that for each second time series, the target server may determine whether the first time series and the second time series pass the causal relationship check based on the target operation, and take the second time series that passes the causal relationship check with the first time series as the target time series. The target operations include: the target server may determine a first error according to the first time series and the autoregressive equation, the first error being an error that predicts the power loss probability. The target server may determine a second error according to the first time sequence, the second time sequence, and the joint regression equation, where the second error is an error that predicts the power loss probability under the influence of the influence factor. The target server may determine whether the first time series and the second time series pass the causal relationship check based on the first error, the second error, and the F-check method. Therefore, by calculating the first error corresponding to the first time sequence and the second error corresponding to the second time sequence, after the first error and the second error are detected, whether the first time sequence and the second time sequence meet the causality detection or not is determined according to the first error and the second error, and the accuracy of the causality detection can be improved. And the real-time and offline data of the vehicle are monitored and shared through cloud service, so that the requirements of different business parties and all parties in the field of electricity deficiency are met, the risk factors based on the time sequence are traced back through the correlation analysis method of the Granges causal relationship of the time sequence analysis method, the networking and intellectualization of the intelligent network-connected vehicle electricity deficiency information are enhanced, and the information value is improved.

In some embodiments, to facilitate the staff member to determine the cause of the vehicle power loss, the method for determining the power loss factor further comprises: the target server may construct a representation of the vehicle based on the vehicle information of the vehicle and the at least one power loss factor, the representation of the vehicle being used to reflect a power loss cause of the vehicle.

It should be noted that, in the embodiment of the present application, the target server may complete the deep image of the vehicle with insufficient power through the vehicle VIN code, the vehicle code, the production date and other dimension feature data.

It can be appreciated that the target server can construct an image of the vehicle based on the vehicle information and at least one power loss factor of the vehicle, and the power loss cause of the vehicle can be reflected by the image of the vehicle, so that a worker can intuitively determine the cause of the power loss of the vehicle. And the related side of the power shortage can be rapidly positioned from the dimension of massive vehicle-end data through the data mining application method mode, so that the time cost and the labor cost of large data mining can be reduced.

The foregoing description of the solution provided in the embodiments of the present application has been mainly presented in terms of a method. In order to achieve the above functions, the determining means or device of the deficiency factor comprises corresponding hardware structures and/or software modules for performing the respective functions. Those of skill in the art will readily appreciate that the elements and algorithm steps of the examples described in connection with the embodiments disclosed herein may be implemented as hardware or combinations of hardware and computer software. Whether a function is implemented as hardware or computer software driven hardware depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

In the embodiment of the present application, according to the above method, the functional module may be divided by an exemplary apparatus or device for determining a deficiency factor, for example, the apparatus or device for determining a deficiency factor may include each functional module corresponding to each functional division, or two or more functions may be integrated into one processing module. The integrated modules may be implemented in hardware or in software functional modules. It should be noted that, in the embodiment of the present application, the division of the modules is schematic, which is merely a logic function division, and other division manners may be implemented in actual implementation.

Fig. 5 is a block diagram illustrating a device for determining a deficiency factor according to an exemplary embodiment. Referring to fig. 5, the means for determining the deficiency factor is used to perform the methods shown in fig. 2, 3 and 4. The device for determining the power deficiency factor comprises: an acquisition unit 501 and a processing unit 502.

The obtaining unit 501 is configured to obtain a first time sequence and a plurality of second time sequences, where the first time sequence includes a power loss probability of the vehicle in different times, the second time sequence includes an influence factor of the power loss of the vehicle in different times, and one second time sequence corresponds to one influence factor. The processing unit 502 is configured to perform a causal relationship test on the first time sequence and each second time sequence to obtain at least one target time sequence, where the target time sequence is a second time sequence that passes the causal relationship test with the first time sequence in the plurality of second time sequences. The processing unit 502 is further configured to determine, according to each target time sequence in the at least one target time sequence, a power loss factor corresponding to each target time sequence, so as to determine at least one power loss factor.

In a possible embodiment, the acquiring unit 501 is further configured to acquire vehicle information of a vehicle and status information of the vehicle. The processing unit 502 is further configured to pre-process vehicle information of the vehicle and state information of the vehicle to obtain a third time sequence and a plurality of fourth time sequences, where the third time sequence includes a power loss probability of the vehicle in different time periods, a fluctuation value of the power loss probability of the vehicle in different time periods is greater than a preset fluctuation threshold, the fourth time sequence includes an influence factor of the power loss of the vehicle in different time periods, and a fluctuation value of the influence factor of the power loss of the vehicle in different time periods is greater than the preset fluctuation threshold. The processing unit 502 is further configured to perform stationarity processing on the third time sequence to obtain a first time sequence. The processing unit 502 is further configured to perform stationarity processing on each fourth time sequence to obtain a second time sequence corresponding to each fourth time sequence, so as to obtain a plurality of second time sequences.

In a possible implementation manner, the processing unit 502 is specifically configured to determine, for each second time sequence, whether the first time sequence and the second time sequence pass the causal relationship test according to the target operation, and take, as the target time sequence, the second time sequence that passes the causal relationship test with the first time sequence. The target operations include: the processing unit 502 is specifically configured to determine a first error according to the first time sequence and the autoregressive equation, where the first error is an error for predicting the power loss probability. The processing unit 502 is specifically configured to determine a second error according to the first time sequence, the second time sequence, and the joint regression equation, where the second error is an error that predicts the power loss probability under the influence of the influence factor. The processing unit 502 is specifically configured to determine whether the first time sequence and the second time sequence pass the causal relationship test according to the first error, the second error, and the F test method.

In a possible implementation manner, the processing unit 502 is further configured to construct an image of the vehicle based on the vehicle information of the vehicle and at least one power loss factor, where the image of the vehicle is used to reflect a power loss cause of the vehicle.

The specific manner in which the individual units perform the operations in relation to the apparatus of the above embodiments has been described in detail in relation to the embodiments of the method and will not be described in detail here.

Fig. 6 is a block diagram of an electronic device, according to an example embodiment. As shown in fig. 6, electronic device 600 includes, but is not limited to: a processor 601 and a memory 602.

The memory 602 is used for storing executable instructions of the processor 601. It will be appreciated that the processor 601 is configured to execute instructions to implement the method of determining the power loss factor in the above embodiment.

It should be noted that the electronic device structure shown in fig. 6 is not limited to the electronic device, and the electronic device may include more or less components than those shown in fig. 6, or may combine some components, or may have different arrangements of components, as will be appreciated by those skilled in the art.

The processor 601 is a control center of the electronic device, connects various parts of the entire electronic device using various interfaces and lines, and performs various functions of the electronic device and processes data by running or executing software programs and/or modules stored in the memory 602, and calling data stored in the memory 602, thereby performing overall monitoring of the electronic device. The processor 601 may include one or more processing units. Alternatively, the processor 601 may integrate an application processor that primarily handles operating systems, user interfaces, applications, etc., and a modem processor that primarily handles wireless communications. It will be appreciated that the modem processor described above may not be integrated into the processor 601.

The memory 602 may be used to store software programs as well as various data. The memory 602 may include primarily a program storage area and a data storage area, wherein the program storage area may store an operating system, application programs (such as a processing unit) required for at least one functional module, and the like. In addition, the memory 602 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage device.

In an exemplary embodiment, a computer readable storage medium is also provided, e.g. a memory 602, comprising instructions executable by the processor 601 of the electronic device 600 to implement the method of determining a power deficit factor in the above embodiments.

In actual implementation, the functions of the acquisition unit 501 and the processing unit 502 in fig. 5 may be implemented by the processor 601 in fig. 6 calling a computer program stored in the memory 602. For specific implementation, reference may be made to the description of the method for determining the deficiency factor in the above embodiment, which is not repeated here.

Alternatively, the computer readable storage medium may be a non-transitory computer readable storage medium, for example, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.

In an exemplary embodiment, the present application also provides a computer program product comprising one or more instructions executable by a processor of an electronic device to perform the method of determining a deficiency factor in the above-described embodiments.

It should be noted that, when the instructions in the computer readable storage medium or one or more instructions in the computer program product are executed by the processor of the electronic device, the respective processes of the above embodiment of the method for determining the deficiency factor are implemented, and the same technical effects as those of the above embodiment of the method for determining the deficiency factor can be achieved, and for avoiding repetition, a detailed description is omitted here.

From the foregoing description of the embodiments, it will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of functional modules is illustrated, and in practical application, the above-described functional allocation may be implemented by different functional modules according to needs, i.e. the internal structure of the apparatus is divided into different functional modules to implement all or part of the functions described above.

In the several embodiments provided in this application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of modules or units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another apparatus, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.

The units described as separate parts may or may not be physically separate, and the parts shown as units may be one physical unit or a plurality of physical units, may be located in one place, or may be distributed in a plurality of different places. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.

The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a readable storage medium. Based on such understanding, the technical solution of the embodiments of the present application may be essentially or a part contributing to the prior art or all or part of the technical solution may be embodied in the form of a software product stored in a storage medium, including several instructions to cause a device (may be a single-chip microcomputer, a chip or the like) or a processor (processor) to perform all or part of the steps of the methods of the embodiments of the present application. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk, etc.

The foregoing is merely a specific embodiment of the present application, but the protection scope of the present application is not limited thereto, and any changes or substitutions within the technical scope of the present disclosure should be covered in the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A method of determining a deficiency factor, the method comprising:

acquiring a first time sequence and a plurality of second time sequences, wherein the first time sequence comprises the power deficiency probability of vehicles in different times, the second time sequence comprises the influence factors of the power deficiency of the vehicles in the different times, and one second time sequence corresponds to one influence factor;

performing causal relation detection on the first time sequence and each second time sequence to obtain at least one target time sequence, wherein the target time sequence is the second time sequence which passes the causal relation detection with the first time sequence in the second time sequences;

and determining a power deficiency factor corresponding to each target time sequence according to each target time sequence in the at least one target time sequence so as to determine at least one power deficiency factor.

2. The method of claim 1, wherein prior to acquiring the first time series and the plurality of second time series, the method further comprises:

acquiring vehicle information of the vehicle and state information of the vehicle;

the acquiring the first time series and the plurality of second time series includes:

preprocessing the vehicle information of the vehicle and the state information of the vehicle to obtain a third time sequence and a plurality of fourth time sequences, wherein the third time sequence comprises the power shortage probability of the vehicle in different time, the fluctuation value of the power shortage probability of the vehicle in different time is larger than a preset fluctuation threshold value, the fourth time sequence comprises the influence factors of the power shortage of the vehicle in different time, and the fluctuation value of the influence factors of the power shortage of the vehicle in different time is larger than the preset fluctuation threshold value;

performing stationarity processing on the third time sequence to obtain the first time sequence;

and carrying out stationarity processing on each fourth time sequence to obtain the second time sequence corresponding to each fourth time sequence so as to obtain a plurality of second time sequences.

3. The method of claim 2, wherein the vehicle information includes at least one of: vehicle basic information, vehicle alarm information, vehicle maintenance information, vehicle complaint information and vehicle rescue information; the status information includes: battery state information and travel state information.

4. The method of claim 2, wherein the pre-processing comprises at least one of: data deduplication processing, time sequence alignment processing, null value filling processing, exception clearing processing and format unification processing.

5. The method according to any one of claims 1-4, wherein said performing a causal relationship check on said first time series and each of said second time series results in at least one target time series, comprising:

for each of the second time series, determining whether the first time series and the second time series pass the causal relationship check according to a target operation, and regarding a second time series that passes the causal relationship check with the first time series as the target time series; the target operation includes:

determining a first error according to the first time sequence and an autoregressive equation, wherein the first error is an error for predicting the power deficiency probability;

Determining a second error according to the first time sequence, the second time sequence and a joint regression equation, wherein the second error is an error for predicting the power deficiency probability under the action of the influence factor;

determining whether the first time series and the second time series pass the causal relationship check according to the first error, the second error, and an F-check method.

6. The method according to any one of claims 2-4, further comprising:

constructing an representation of the vehicle based on vehicle information of the vehicle and at least one of the power deficit factors, the representation of the vehicle being used to reflect a cause of the power deficit of the vehicle.

7. A device for determining a deficiency factor, the device comprising:

an acquisition unit configured to acquire a first time series and a plurality of second time series, where the first time series includes a power loss probability of a vehicle in different times, the second time series includes an influence factor of the power loss of the vehicle in the different times, and one of the second time series corresponds to one of the influence factors;

the processing unit is used for carrying out causal relation detection on the first time sequence and each second time sequence to obtain at least one target time sequence, wherein the target time sequence is the second time sequence which passes the causal relation detection with the first time sequence in the plurality of second time sequences;

The processing unit is further configured to determine, according to each target time sequence in the at least one target time sequence, a power loss factor corresponding to each target time sequence, so as to determine at least one power loss factor.

8. The apparatus of claim 7, wherein the device comprises a plurality of sensors,

the acquisition unit is further used for acquiring vehicle information of the vehicle and state information of the vehicle;

the processing unit is further configured to pre-process vehicle information of the vehicle and state information of the vehicle to obtain a third time sequence and a plurality of fourth time sequences, where the third time sequence includes power loss probabilities of the vehicle in different times, and fluctuation values of the power loss probabilities of the vehicle in the different times are greater than a preset fluctuation threshold, and the fourth time sequence includes influence factors of the power loss of the vehicle in the different times, and fluctuation values of the influence factors of the power loss of the vehicle in the different times are greater than the preset fluctuation threshold;

the processing unit is further configured to perform stationarity processing on the third time sequence to obtain the first time sequence;

the processing unit is further configured to perform stationarity processing on each fourth time sequence to obtain the second time sequence corresponding to each fourth time sequence, so as to obtain the plurality of second time sequences.

9. The apparatus of claim 8, wherein the vehicle information comprises at least one of: vehicle basic information, vehicle alarm information, vehicle maintenance information, vehicle complaint information and vehicle rescue information; the status information includes: battery state information and travel state information.

10. The apparatus of claim 8, wherein the preprocessing comprises at least one of: data deduplication processing, time sequence alignment processing, null value filling processing, exception clearing processing and format unification processing.

11. The device according to any one of claims 7 to 10, wherein,

the processing unit is specifically configured to determine, for each of the second time sequences, whether the first time sequence and the second time sequence pass the causal relationship test according to a target operation, and take, as the target time sequence, a second time sequence that passes the causal relationship test with the first time sequence; the target operation includes:

the processing unit is specifically configured to determine a first error according to the first time sequence and an autoregressive equation, where the first error is an error for predicting the power loss probability;

The processing unit is specifically configured to determine a second error according to the first time sequence, the second time sequence, and a joint regression equation, where the second error is an error that predicts the power loss probability under the effect of the influence factor;

the processing unit is specifically configured to determine whether the first time sequence and the second time sequence pass the causal relationship check according to the first error, the second error, and an F-check method.

12. The device according to any one of claims 8-10, wherein,

the processing unit is further used for constructing an image of the vehicle based on vehicle information of the vehicle and at least one of the power shortage factors, and the image of the vehicle is used for reflecting the power shortage reason of the vehicle.

13. An electronic device, comprising: a processor; a memory for storing the processor-executable instructions; wherein the processor is configured to execute the instructions to implement the method of any one of claims 1 to 6.

14. A computer readable storage medium, characterized in that, when computer-executable instructions stored in the computer readable storage medium are executed by a processor of an electronic device, the electronic device is capable of performing the method of any one of claims 1 to 6.