Probability density-based data anomaly monitoring method and device and electronic equipment

Abstract

The application provides a data anomaly monitoring method and device based on probability density and electronic equipment. After obtaining the control operation information of the target vehicle in a historical time period, including the control operation amount of each day control operation and the control operation result of the corresponding control operation, and determining the to-be-monitored control operation, the cumulative probability corresponding to different control success times is determined based on the control operation amount of the to-be-monitored control operation in the control operation amount of each day control operation and the control operation result. The preset probability density algorithm is used to process the cumulative probability corresponding to different control success times and the corresponding control success times, and the control success times monitoring value corresponding to the to-be-monitored control operation is obtained. If the control success times of the to-be-monitored control operation obtained in the preset time period is less than the control success times monitoring value, it is determined that the to-be-monitored control operation of the target vehicle is abnormal. The method can inform the operation and maintenance personnel to solve the problem in time, and improve the operation experience of the user.

Description

Technical Field

[0001] The present application relates to the technical field of data processing, and in particular to a method, device and electronic device for monitoring data anomalies based on probability density. Background Art

[0002] Currently, users can remotely control the vehicle through a mobile phone app to perform routine control operations, such as opening and closing windows, unlocking doors, locking doors, etc.

[0003] However, due to reasons such as large concurrent usage, the success rate of vehicle control operations may easily become low at a certain moment, that is, abnormalities occur in the vehicle control operations. If the operation and maintenance personnel fail to detect the abnormality in time and provide maintenance, it will seriously affect the user's operating experience. Summary of the Invention

[0004] The purpose of the embodiments of the present application is to provide a data anomaly monitoring method, device and electronic equipment based on probability density, which can promptly detect whether there are any abnormal problems in vehicle control operations, thereby promptly informing operation and maintenance personnel to solve the problem, thereby improving the user's operating experience.

[0005] In a first aspect, a method for monitoring data anomalies based on probability density is provided, which may include:

[0006] Obtaining vehicle control operation information for a target vehicle within a historical time period, the vehicle control operation information including daily vehicle control operation volume and vehicle control operation results of the corresponding vehicle control operations within the historical time period; the vehicle control operation results including vehicle control success and vehicle control failure;

[0007] After any vehicle control operation is taken as the vehicle control operation to be monitored, based on the vehicle control operation amount to be monitored in the daily vehicle control operation amount and the corresponding vehicle control operation result, the cumulative probability Pn corresponding to different vehicle control success times is determined;

[0008] Using a preset probability density algorithm, the cumulative probability Pn corresponding to the different vehicle control success times and the corresponding vehicle control success times are processed to obtain a vehicle control success time monitoring value corresponding to the vehicle control operation to be monitored;

[0009] If the number of successful vehicle control operations of the target vehicle to be monitored obtained within a preset time period is less than the monitoring value of the number of successful vehicle control operations, it is determined that the target vehicle's target vehicle's successful vehicle control operation is abnormal.

[0010] In an optional embodiment, based on the daily vehicle control operation volume and the corresponding vehicle control operation results, determining the cumulative probability Pn corresponding to different vehicle control success times includes:

[0011] Based on the daily vehicle control operation volume of the vehicle control operation to be monitored, and according to whether the vehicle control operation to be monitored occurs every day, determining the different number of occurrences of the vehicle control operation to be monitored and Xm every day in the historical time period;

[0012] For any number and Xm, based on the vehicle control operation result, determine the total number of successful vehicle control times n corresponding to the number and Xm;

[0013] Based on the number and Xm, the intermediate cumulative probabilities corresponding to different numbers of successful vehicle control in the total number of successful vehicle control times n are calculated respectively;

[0014] Based on the intermediate cumulative probabilities corresponding to different vehicle control success times and the total number of vehicle control success times n, the cumulative probabilities Pn corresponding to different vehicle control success times are determined.

[0015] In an optional embodiment, a preset probability density algorithm is used to process the cumulative probabilities and corresponding vehicle control success times corresponding to the different vehicle control operation success times to obtain a vehicle control success time monitoring value corresponding to the vehicle control operation, including:

[0016] Using a preset probability density algorithm, the cumulative probabilities corresponding to the different vehicle control operation success times and the corresponding vehicle control success times are processed to obtain a target probability density function;

[0017] Based on the target probability density function, a monitoring value of the number of successful vehicle control operations corresponding to the to-be-monitored vehicle control operations that meet preset conditions is determined.

[0018] In an optional embodiment, determining a monitoring value of the number of successful vehicle control operations corresponding to the to-be-monitored vehicle control operation that meets a preset condition based on the target probability density function includes:

[0019] Based on the target probability density function, obtaining the target vehicle control success number when the probability density is 0;

[0020] If the probability density of the next vehicle control success number adjacent to the target vehicle control success number is non-zero, the target vehicle control success number is determined as the vehicle control success number monitoring value corresponding to the vehicle control operation to be monitored.

[0021] In an optional embodiment, the method further includes:

[0022] Obtaining an update request for the monitoring value of the number of successful vehicle control times, the update request including an updated historical time period;

[0023] The updated historical time period is used as a new historical time period, and the process returns to the step of obtaining vehicle control operation information for the target vehicle within the historical time period to obtain a new vehicle control success count monitoring value corresponding to the vehicle control operation to be monitored.

[0024] In an optional embodiment, after determining that the monitored vehicle control operation of the target vehicle is abnormal, the method further includes:

[0025] Send an alarm message to the operation and maintenance personnel; the alarm message includes the vehicle identification of the target vehicle and the abnormal information of the corresponding vehicle control operation to be monitored.

[0026] In a second aspect, a data anomaly monitoring device based on probability density is provided, which may include:

[0027] an acquisition unit, configured to acquire vehicle control operation information for a target vehicle within a historical time period, the vehicle control operation information including a daily vehicle control operation volume of various vehicle control operations within the historical time period and vehicle control operation results of the corresponding vehicle control operations; the vehicle control operation results including vehicle control success and vehicle control failure;

[0028] a determination unit configured to determine, after taking any vehicle control operation as a vehicle control operation to be monitored, a cumulative probability Pn corresponding to different vehicle control success times based on the vehicle control operation amount to be monitored in the daily vehicle control operation amount and the corresponding vehicle control operation result;

[0029] The acquisition unit is further configured to process the cumulative probabilities Pn and corresponding vehicle control success times corresponding to the different vehicle control success times using a preset probability density algorithm to obtain a vehicle control success time monitoring value corresponding to the vehicle control operation to be monitored;

[0030] The determining unit is further configured to determine that an abnormality occurs in the vehicle control operation to be monitored if the number of successful vehicle control operations of the vehicle control operation to be monitored obtained within a preset time period is less than the monitoring value of the number of successful vehicle control operations.

[0031] In a third aspect, an electronic device is provided, the electronic device including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus;

[0032] Memory for storing computer programs;

[0033] The processor is configured to implement any of the methods described in the first aspect above when executing a program stored in the memory.

[0034] In a fourth aspect, a computer-readable storage medium is provided, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, any of the methods described in the first aspect is implemented.

[0035] The data anomaly monitoring method based on probability density provided by the embodiment of the present application obtains the vehicle control operation information for the target vehicle within the historical time period. The vehicle control operation information includes the daily vehicle control operation volume of various vehicle control operations within the historical time period and the vehicle control operation results of the corresponding vehicle control operations; the vehicle control operation results include vehicle control success and vehicle control failure; after taking any vehicle control operation as the vehicle control operation to be monitored, based on the vehicle control operation volume of the vehicle control operation to be monitored in the daily vehicle control operation volume and the corresponding vehicle control operation results, the cumulative probabilities corresponding to different vehicle control success times are determined; using a preset probability density algorithm, the cumulative probabilities corresponding to different vehicle control success times and the corresponding vehicle control success times are processed to obtain the vehicle control success number monitoring value corresponding to the vehicle control operation to be monitored; if the vehicle control success number of the vehicle control operation to be monitored obtained within the preset time period is less than the vehicle control success number monitoring value, it is determined that the vehicle control operation to be monitored of the target vehicle is abnormal. The method can promptly determine that the vehicle control operation to be monitored is abnormal through the obtained vehicle control success number monitoring value, thereby promptly informing the operation and maintenance personnel to solve the problem, thereby improving the user's operating experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without creative work.

[0037] Figure 1 A flowchart of a data anomaly monitoring method based on probability density provided in an embodiment of the present application;

[0038] Figure 2 A schematic diagram of a curve of a target probability density function corresponding to a vehicle control operation to be monitored provided in an embodiment of the present application;

[0039] Figure 3 A schematic diagram of the structure of a data anomaly monitoring device based on probability density provided in an embodiment of the present application;

[0040] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0041] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0042] The data anomaly monitoring method based on probability density provided in the embodiment of the present application can be applied to a server that manages vehicle data. The server can be a physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms. The server can store the vehicle control operation information of each vehicle, and the vehicle control operation information may include the vehicle control operation time, vehicle control operation results, and vehicle control operation volume for any vehicle. The vehicle control operation results may include vehicle control success and vehicle control failure.

[0043] The server can obtain the vehicle control operation information for the target vehicle within the historical time period, and the vehicle control operation information includes the daily vehicle control operation volume and the vehicle control operation results of the corresponding vehicle control operations for various vehicle control operations within the historical time period; for any vehicle control operation, based on the daily vehicle control operation volume and the corresponding vehicle control operation results, the cumulative probabilities corresponding to different vehicle control success times are determined; using a preset probability density algorithm, the cumulative probabilities and corresponding vehicle control success times corresponding to different vehicle control success times are processed to obtain a vehicle control success number monitoring value corresponding to the vehicle control operation; thus, when the vehicle control success number of a certain vehicle control operation for the target vehicle obtained within the preset time period is less than the set vehicle control success number monitoring value, it can be quickly determined that the vehicle control operation of the target vehicle is abnormal, so that the maintenance personnel can be notified in time to perform maintenance, thereby improving the user's operating experience.

[0044] The preferred embodiments of the present application are described below in conjunction with the drawings in the specification. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present application and are not used to limit the present application. In addition, the embodiments and features in the embodiments of the present application can be combined with each other if there is no conflict.

[0045] Figure 1 The flowchart of a data anomaly monitoring method based on probability density is provided in the embodiment of the present application. Figure 1 As shown, the method may include:

[0046] Step S110: Acquire vehicle control operation information for the target vehicle within a historical time period.

[0047] The vehicle control operation information may include the daily vehicle control operation volume of various vehicle control operations within a historical period and the vehicle control operation results of the corresponding vehicle control operations, such as vehicle control success or vehicle control failure. The daily vehicle control operation volume refers to the sum of the number of vehicle control operations of various vehicle control operations in a day.

[0048] For example, taking the vehicle control operation as a window opening and closing operation, and the historical time period as 365 days, the vehicle control operation information may include the number of window opening and closing operation operations on the first day of 365 days is 5, the number of window opening and closing operation operations on the second day is 10, ..., the number of window opening and closing operation operations on the 365th day is 1, and the vehicle control operation results of whether the corresponding window opening and closing operation is successful.

[0049] Step S120: After any vehicle control operation is taken as the vehicle control operation to be monitored, the cumulative probabilities corresponding to different vehicle control success times are determined based on the vehicle control operation volume to be monitored in the daily vehicle control operation volume and the corresponding vehicle control operation results.

[0050] In a specific implementation, after any vehicle control operation is taken as a vehicle control operation to be monitored, based on the daily vehicle control operation volume of the vehicle control operation to be monitored and whether the vehicle control operation to be monitored occurs every day, the different number of vehicle control operations to be monitored and Xm that occur every day in the historical time period are determined;

[0051] Specifically, the daily vehicle control operation volume of various vehicle control operations is searched to determine whether a vehicle control operation to be monitored occurs each day within the historical time period, the vehicle control operation volume of the vehicle control operation to be monitored that occurs each day, the number of vehicle control operations, the vehicle control operation results, etc. The different number of occurrences of the vehicle control operation to be monitored is then counted each day, and the number of occurrences per day is summed up to obtain the total number of different occurrences of the vehicle control operation to be monitored, Xm, within the historical time period. Here, m represents the number of occurrences of the vehicle control operation to be monitored. For example, if m = 1, X1 represents the sum of the number of occurrences of the vehicle control operation to be monitored, which is 1 per day.

[0052] In an example, if the historical period is 5 days and the vehicle control operation to be monitored occurs every day, if the number of vehicle control operations to be monitored on the first day is 5; the number of vehicle control operations to be monitored on the second day is 10; the number of vehicle control operations to be monitored on the third day is 15; the number of vehicle control operations to be monitored on the fourth day is 20; and the number of vehicle control operations to be monitored on the fifth day is 25, then the different sums of times that can be obtained include:

[0053] X1=5, indicating that the number of times the vehicle control operation to be monitored occurs is 1 per day and X1 is 5 times, that is, it occurs once per day in the five-day historical period, and a total of 5 times in five days;

[0054] X2=5, indicating that the number of times the vehicle control operation to be monitored occurs is 2 times per day and X2 is 5 times, that is, it occurs 2 times per day in the five-day historical period, and a total of 5 times in five days;

[0055] X3=5, indicating that the number of times the vehicle control operation to be monitored occurs 3 times per day and X3 is 5 times, that is, it occurs 3 times per day in the five-day historical period, and a total of 5 times in five days;

[0056] …and so on…

[0057] X6=4, indicating that the number of times the monitored vehicle control operation occurs is 6 times per day, and X6 is 4 times. Because the number of monitored vehicle control operations on the first day is only 5 times, if the number of monitored vehicle control operations per day is required to be 6, it can only be satisfied from the second to the fifth day. That is, within the five-day historical period, there will be 6 times per day, and a total of 4 times in five days;

[0058] …and so on…

[0059] X10=4, indicating that the number of times the vehicle control operation to be monitored occurs is 10 times per day and X10 is 4 times, that is, the situation occurs 6 times per day in the five-day historical period, and a total of 4 times in five days;

[0060] X11=3, indicating that the number of times the monitored vehicle control operation occurs every day is 11 times, and X11 is 3 times. Because the number of monitored vehicle control operations on the first day is only 5 times, and the number of monitored vehicle control operations on the second day is only 10 times. If the number of monitored vehicle control operations on each day is required to be 11 times, it can only be satisfied from the third to the fifth day. That is, within the five-day historical period, there will be 11 times every day, and a total of 3 times in five days.

[0061] …and so on…

[0062] X25=1 indicates that the number of vehicle control operations to be monitored is 25 times per day and X25 is 1 time, that is, the situation occurs 25 times every day in the five-day historical period, and occurs once in total in five days.

[0063] Afterwards, for any number and Xm, based on the vehicle control operation result, the total number of successful vehicle control operations n corresponding to the number and Xm is determined; specifically, the vehicle control operation result of the vehicle control operation to be monitored corresponding to each number and Xm is obtained, so that the corresponding number of successful vehicle control operations of 1, 2, ..., n (0<n<=m) is obtained as Sm1, ..., Smn, where n is the total number of successful vehicle control operations.

[0064] Based on the number and Xm, the intermediate cumulative probabilities corresponding to different numbers of successful vehicle control operations in the total number of successful vehicle control operations n are calculated respectively; specifically, for the monitored vehicle control operations corresponding to the number and Xm, the number of successful vehicle control operations of 1 is Sm1, and the intermediate cumulative probability is Sm1 / Xm; the number of successful vehicle control operations of 2 is Sm2, and the intermediate cumulative probability is Sm2 / Xm; the number of successful vehicle control operations of 3 is Sm3, and the intermediate cumulative probability is Sm3 / Xm, ...,; the number of successful vehicle control operations of n is Smn, and the intermediate cumulative probability is Smn / Xm.

[0065] In an example, the intermediate cumulative probability is calculated for m=1, 2, and 10 as follows:

[0066] X1=5 means that the monitored vehicle control operation occurs once every day, and it occurs 5 times in five days, that is, m=5. If it occurs once every day, and the number of successful operations is 1 is S11, then the intermediate cumulative probability is S11 / X1;

[0067] X2=5 means that the monitored vehicle control operation occurs twice every day, and a total of 5 times in five days, that is, m=5. If it occurs twice every day, and the number of successful operations is S21, then the intermediate cumulative probability is S21 / X2. If it occurs twice every day, and the number of successful operations is S22, then the intermediate cumulative probability is S22 / X2.

[0068] X10=4 means that the monitored vehicle control operation occurs 6 times every day, and it occurs 4 times in five days, that is, m=4; if it occurs 6 times every day, and the number of successful operations is 1 is S61, then the intermediate cumulative probability is S61 / X6; if it occurs 6 times every day, and the number of successful operations is 2 is S62, then the intermediate cumulative probability is S62 / X6; if it occurs 6 times every day, and the number of successful operations is 3 is S63, then the intermediate cumulative probability is S63 / X6; if it occurs 6 times every day, and the number of successful operations is 4 is S64, then the intermediate cumulative probability is S64 / X6.

[0069] Furthermore, based on the intermediate cumulative probabilities corresponding to different vehicle control success times and the total number of vehicle control success times n, the cumulative probabilities Pn corresponding to different vehicle control success times are determined.

[0070] The cumulative probability Pn can be expressed as: Pn=(S11 / X1+S21 / X2+...+Smn / Xm)*1 / n.

[0071] Step S130: Using a preset probability density algorithm, the cumulative probabilities and corresponding vehicle control success times corresponding to different vehicle control success times are processed to obtain a vehicle control success time monitoring value corresponding to the vehicle control operation.

[0072] In the specific implementation, a preset probability density algorithm is used to process the cumulative probability Pn corresponding to different vehicle control operation success times and the corresponding vehicle control success times to obtain the target probability density function;

[0073] Based on the target probability density function, a monitoring value of the number of successful vehicle control operations corresponding to the vehicle control operation to be monitored that meets the preset conditions is determined. The step of determining the monitoring value of the number of successful vehicle control operations corresponding to the vehicle control operation to be monitored that meets the preset conditions may specifically include:

[0074] Method 1: To further guarantee the user's operational experience and ensure that the monitored vehicle control operation is successful, the target number of successful vehicle control attempts when the probability density is 0 can be obtained based on the target probability density function. If the probability density of the next successful vehicle control attempt adjacent to the target successful vehicle control attempt is non-zero, the target successful vehicle control attempt is determined as the monitoring value of the successful vehicle control attempt corresponding to the monitored vehicle control operation.

[0075] like Figure 2 As shown, Figure 2 Curve A in the figure is the target probability density function corresponding to the vehicle control operation to be monitored. The horizontal axis represents the number of successful vehicle control operations, where the total number of successful vehicle control operations n = 50, and the vertical axis represents the cumulative probability Pn corresponding to different numbers of successful vehicle control operations. The coordinates of point a in curve A are (38, 0), that is, the probability density of point a is 0, and the coordinates of point b adjacent to point a are (39, 0.025), that is, the probability density of point b is non-zero. Therefore, 38 corresponding to point a is the monitoring value of the number of successful vehicle control operations corresponding to the vehicle control operation to be monitored.

[0076] Method 2: Based on the target probability density function, the target number of successful vehicle control operations when the probability density is 0 is obtained; the average value of the target number of successful vehicle control operations and the number of successful vehicle control operations corresponding to the maximum probability density value is determined as the monitoring value of the number of successful vehicle control operations corresponding to the vehicle control operation to be monitored.

[0077] It should be noted that the above-mentioned method 1 is the preferred implementation method of the present application in actual application. Different implementation methods of the above-mentioned method 1 and method 2 can be selected according to different actual needs, and the present application does not limit them here.

[0078] Step S140: Determine whether the vehicle control operation to be monitored of the target vehicle is abnormal based on the number of successful vehicle control operations to be monitored and the monitoring value of the number of successful vehicle control operations to be monitored acquired within a preset time period.

[0079] If the number of successful vehicle control operations to be monitored obtained within the preset time period is not less than the monitoring value of the number of successful vehicle control operations, it is determined that the vehicle control operations to be monitored of the target vehicle are normal.

[0080] If the number of successful vehicle control operations of the to-be-monitored vehicle control operation obtained in the preset time period is less than the number of successful vehicle control operation monitoring value, it is determined that the to-be-monitored vehicle control operation of the target vehicle is abnormal.

[0081] It should be noted that the preset time period is a future time period of the historical time period, for example, the historical time period is January-December 2022, and the preset time period can be January-June 2023 or January-December 2023.

[0082] Further, after determining that the to-be-monitored vehicle control operation of the target vehicle is abnormal, an alarm information can be sent to the operation and maintenance personnel; the alarm information can include the vehicle identifier of the target vehicle and the abnormal information of the corresponding to-be-monitored vehicle control operation.

[0083] In some embodiments, as the use of the vehicle may change over time, i.e., the number of vehicle control operations of the to-be-monitored vehicle control operation of the target vehicle may change, in order to further ensure the success rate of the vehicle control operation, the update of the number of successful vehicle control operation monitoring value of any to-be-monitored vehicle control operation can be triggered periodically or according to actual needs to obtain a more accurate number of successful vehicle control operation monitoring value.

[0084] Specifically, the update request for the number of successful vehicle control operation monitoring value of the to-be-monitored vehicle control operation of the target vehicle input by the technician can be periodically received, and the update request can include an updated historical time period;

[0085] Then, the updated historical time period is taken as a new historical time period, and steps S110-S130 are returned to execute to obtain a new number of successful vehicle control operation monitoring value corresponding to the to-be-monitored vehicle control operation. Continuing the above example, if the historical time period is January-December 2022, the updated historical time period can be January-December 2023, and at this time the preset time period corresponding to the updated historical time period can be January-June 2024 or January-December 2024, i.e., the preset time period at this time is a future time period of the updated historical time period.

[0086] Corresponding to the above method, the embodiments of the present application also provide a data anomaly monitoring device based on probability density, as shown in Figure 3 The device comprises:

[0087] The acquisition unit 310 is configured to acquire vehicle control operation information of a target vehicle in a historical time period, wherein the vehicle control operation information comprises daily vehicle control operation amount of various vehicle control operations and vehicle control operation results of the corresponding vehicle control operations in the historical time period; the vehicle control operation results comprise successful vehicle control and failed vehicle control;

[0088] A determination unit 320 is configured to determine, after taking any vehicle control operation as a vehicle control operation to be monitored, a cumulative probability Pn corresponding to different vehicle control success times based on the vehicle control operation amount to be monitored in the daily vehicle control operation amount and the corresponding vehicle control operation result;

[0089] The acquisition unit 310 is further configured to process the cumulative probabilities Pn and corresponding vehicle control success times corresponding to the different vehicle control success times using a preset probability density algorithm to obtain a vehicle control success time monitoring value corresponding to the vehicle control operation to be monitored;

[0090] The determining unit 320 is further configured to determine that an abnormality occurs in the vehicle control operation to be monitored if the number of successful vehicle control operations of the vehicle control operation to be monitored obtained within a preset time period is less than the monitoring value of the number of successful vehicle control operations.

[0091] In some embodiments, the determining unit 320 is specifically configured to:

[0092] Based on the daily vehicle control operation volume of the vehicle control operation to be monitored, and according to whether the vehicle control operation to be monitored occurs every day, determining the different number of occurrences of the vehicle control operation to be monitored and Xm every day in the historical time period;

[0093] For any number and Xm, based on the vehicle control operation result, determine the total number of successful vehicle control times n corresponding to the number and Xm;

[0094] Based on the number and Xm, the intermediate cumulative probabilities corresponding to different numbers of successful vehicle control in the total number of successful vehicle control times n are calculated respectively;

[0095] Based on the intermediate cumulative probabilities corresponding to different vehicle control success times and the total number of vehicle control success times n, the cumulative probabilities Pn corresponding to different vehicle control success times are determined.

[0096] In some embodiments, the acquiring unit 310 is specifically configured to:

[0097] Using a preset probability density algorithm, the cumulative probabilities corresponding to the different vehicle control operation success times and the corresponding vehicle control success times are processed to obtain a target probability density function;

[0098] Based on the target probability density function, a monitoring value of the number of successful vehicle control operations corresponding to the to-be-monitored vehicle control operations that meet preset conditions is determined.

[0099] In some embodiments, the acquiring unit 310 is further configured to:

[0100] Based on the target probability density function, obtaining the target vehicle control success number when the probability density is 0;

[0101] If the probability density of the next vehicle control success number adjacent to the target vehicle control success number is non-zero, the target vehicle control success number is determined as the vehicle control success number monitoring value corresponding to the vehicle control operation to be monitored.

[0102] In some embodiments, the acquiring unit 310 is further configured to acquire an update request for the monitoring value of the number of successful vehicle control times, wherein the update request includes an updated historical time period;

[0103] The updated historical time period is used as a new historical time period, and the process returns to the step of obtaining vehicle control operation information for the target vehicle within the historical time period to obtain a new vehicle control success count monitoring value corresponding to the vehicle control operation to be monitored.

[0104] In some embodiments, the apparatus further includes a sending unit 330;

[0105] The sending unit 330 is used to send an alarm message to the operation and maintenance personnel after determining that the monitored vehicle control operation of the target vehicle is abnormal; the alarm message includes the vehicle identification of the target vehicle and the abnormal information of the corresponding monitored vehicle control operation.

[0106] The functions of each functional unit of the probability density-based data anomaly monitoring device provided in the above-mentioned embodiments of the present application can be realized through the above-mentioned method steps. Therefore, the specific working process and beneficial effects of each unit in the probability density-based data anomaly monitoring device provided in the embodiments of the present application will not be repeated here.

[0107] The present application also provides an electronic device, such as Figure 4 As shown, it includes a processor 410 , a communication interface 420 , a memory 430 and a communication bus 440 , wherein the processor 410 , the communication interface 420 , and the memory 430 communicate with each other via the communication bus 440 .

[0108] Memory 430, for storing computer programs;

[0109] The processor 410 is configured to execute the program stored in the memory 430 by performing the following steps:

[0110] Obtaining vehicle control operation information for a target vehicle within a historical time period, the vehicle control operation information including daily vehicle control operation volume and vehicle control operation results of the corresponding vehicle control operations within the historical time period; the vehicle control operation results including vehicle control success and vehicle control failure;

[0111] After any vehicle control operation is taken as the vehicle control operation to be monitored, based on the vehicle control operation amount to be monitored in the daily vehicle control operation amount and the corresponding vehicle control operation result, the cumulative probability Pn corresponding to different vehicle control success times is determined;

[0112] Using a preset probability density algorithm, the cumulative probability Pn corresponding to the different vehicle control success times and the corresponding vehicle control success times are processed to obtain a vehicle control success time monitoring value corresponding to the vehicle control operation to be monitored;

[0113] If the number of successful vehicle control operations of the target vehicle to be monitored obtained within a preset time period is less than the monitoring value of the number of successful vehicle control operations, it is determined that the target vehicle's target vehicle's successful vehicle control operation is abnormal.

[0114] The communication bus mentioned above can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. This communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is used in the figure, but this does not mean that there is only one bus or only one type of bus.

[0115] The communication interface is used for communication between the above electronic device and other devices.

[0116] The memory may include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage. Alternatively, the memory may be at least one storage device located away from the processor.

[0117] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, and discrete hardware components.

[0118] The implementation methods and beneficial effects of the various components of the electronic device in the above embodiments to solve the problems can be found in Figure 1 The various steps in the embodiment shown are implemented, therefore, the specific working process and beneficial effects of the electronic device provided by the embodiment of the present application are not repeated here.

[0119] In another embodiment provided in the present application, a computer-readable storage medium is also provided, which stores instructions. When the computer-readable storage medium is run on a computer, the computer executes the probability density-based data anomaly monitoring method described in any of the above embodiments.

[0120] In another embodiment provided by the present application, a computer program product including instructions is also provided, which, when executed on a computer, enables the computer to execute the data anomaly monitoring method based on probability density described in any of the above embodiments.

[0121] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the embodiments of the present application can be implemented in the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the embodiments of the present application can be implemented in the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0122] The embodiments of the present application are described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0123] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0124] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1a process or multiple processes and / or boxes Figure 1 The steps for the function specified in one or more boxes.

[0125] Although preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they become aware of the basic creative concepts. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention.

[0126] Obviously, those skilled in the art can make various changes and modifications to the embodiments of the present application without departing from the spirit and scope of the embodiments of the present application. Thus, if these modifications and variations of the embodiments of the present application fall within the scope of the claims and their equivalents, the embodiments of the present application are also intended to include these modifications and variations.

Claims

1. A data anomaly monitoring method based on probability density, characterized in that: The method comprises: Obtaining vehicle control operation information for a target vehicle within a historical time period, the vehicle control operation information including daily vehicle control operation volume and vehicle control operation results of the corresponding vehicle control operations within the historical time period; the vehicle control operation results including vehicle control success and vehicle control failure; After any vehicle control operation is taken as the vehicle control operation to be monitored, based on the daily vehicle control operation volume of the vehicle control operation to be monitored and according to whether the vehicle control operation to be monitored occurs each day, a different number of occurrences of the vehicle control operation to be monitored and a sum Xm are determined each day within the historical time period; for any number and Xm, based on the vehicle control operation result, a total number of successful vehicle control operations n corresponding to the number and Xm is determined; based on the number and Xm, intermediate cumulative probabilities corresponding to different successful vehicle control operations within the total number of successful vehicle control operations n are calculated; and cumulative probabilities Pn corresponding to different successful vehicle control operations are determined based on the intermediate cumulative probabilities corresponding to different successful vehicle control operations and the total number of successful vehicle control operations n. Using a preset probability density algorithm, the cumulative probability Pn corresponding to the different vehicle control success times and the corresponding vehicle control success times are processed to obtain a vehicle control success time monitoring value corresponding to the vehicle control operation to be monitored; If the number of successful vehicle control operations of the target vehicle to be monitored obtained within a preset time period is less than the monitoring value of the number of successful vehicle control operations, it is determined that the target vehicle's target vehicle's successful vehicle control operation is abnormal.

2. The method according to claim 1, wherein Using a preset probability density algorithm, the cumulative probabilities and corresponding vehicle control success times corresponding to the different vehicle control operation success times are processed to obtain a vehicle control success time monitoring value corresponding to the vehicle control operation, including: Using a preset probability density algorithm, the cumulative probabilities corresponding to the different vehicle control operation success times and the corresponding vehicle control success times are processed to obtain a target probability density function; Based on the target probability density function, a monitoring value of the number of successful vehicle control operations corresponding to the to-be-monitored vehicle control operations that meet preset conditions is determined.

3. The method according to claim 2, wherein Determining a vehicle control success count monitoring value corresponding to the vehicle control operation to be monitored that meets a preset condition based on the target probability density function includes: Based on the target probability density function, obtaining the target vehicle control success number when the probability density is 0; If the probability density of the next vehicle control success number adjacent to the target vehicle control success number is non-zero, the target vehicle control success number is determined as the vehicle control success number monitoring value corresponding to the vehicle control operation to be monitored.

4. The method according to claim 1, wherein The method further comprises: Obtaining an update request for the monitoring value of the number of successful vehicle control times, the update request including an updated historical time period; The updated historical time period is used as a new historical time period, and the process returns to the step of obtaining vehicle control operation information for the target vehicle within the historical time period to obtain a new vehicle control success count monitoring value corresponding to the vehicle control operation to be monitored.

5. The method according to claim 1, wherein After determining that the monitored vehicle control operation of the target vehicle is abnormal, the method further includes: Send an alarm message to the operation and maintenance personnel; the alarm message includes the vehicle identification of the target vehicle and the abnormal information of the corresponding vehicle control operation to be monitored.

6. A data anomaly monitoring device based on probability density, characterized in that: The device comprises: an acquisition unit, configured to acquire vehicle control operation information for a target vehicle within a historical time period, the vehicle control operation information including a daily vehicle control operation volume of various vehicle control operations within the historical time period and vehicle control operation results of the corresponding vehicle control operations; the vehicle control operation results including vehicle control success and vehicle control failure; a determination unit configured to, after taking any vehicle control operation as the vehicle control operation to be monitored, determine, based on the daily vehicle control operation volume of the vehicle control operation to be monitored and whether the vehicle control operation to be monitored occurs each day, a different number of occurrences of the vehicle control operation to be monitored and a sum Xm each day within the historical time period; determine, for any number and Xm, a total number of successful vehicle controls n corresponding to the number and Xm based on the vehicle control operation result; calculate, based on the number and Xm, intermediate cumulative probabilities corresponding to different successful vehicle control times within the total number of successful vehicle control times n; and determine cumulative probabilities Pn corresponding to different successful vehicle control times based on the intermediate cumulative probabilities corresponding to the different successful vehicle control times and the total number of successful vehicle control times n; The acquisition unit is further configured to process the cumulative probabilities Pn and corresponding vehicle control success times corresponding to the different vehicle control success times using a preset probability density algorithm to obtain a vehicle control success time monitoring value corresponding to the vehicle control operation to be monitored; The determining unit is further configured to determine that an abnormality occurs in the vehicle control operation to be monitored if the number of successful vehicle control operations of the vehicle control operation to be monitored obtained within a preset time period is less than the monitoring value of the number of successful vehicle control operations.

7. An electronic device, characterized in that: The electronic device includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; Memory for storing computer programs; A processor, configured to implement the method according to any one of claims 1 to 5 when executing a program stored in a memory.

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

Images