Fault classification method, device and equipment for video monitoring point

Abstract

The embodiment of the application discloses a video monitoring point fault classification method and a video monitoring fault classification device, and is used for the video monitoring fault classification device to obtain a fault category of a target video monitoring point with high accuracy. The method comprises the following steps: collecting target fault information of a target video monitoring point; performing normalization processing on the target fault information to obtain a target key weight and a target fault keyword; inputting the target key weight and the target fault keyword into a target fault diagnosis model to obtain a keyword hit weight; and determining a fault category of the target video monitoring point according to the keyword hit weight.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the technical field of communication, in particular to a video monitoring point fault classification method, device, equipment and computer readable storage medium. BACKGROUND

[0002] At present, there are many reasons for the failure of a video monitoring point, such as camera hardware failure, parameter configuration failure, and network failure, etc., which will cause user complaints.

[0003] In the prior art, there are two methods for diagnosing the failure of a video monitoring point. One is to monitor the running parameters of the front end of the camera, and to determine the category of the failure of the video monitoring point according to the running parameters. The other is to evaluate the external cause of the failure of the video monitoring point according to the captured image, that is, to determine the category of the failure of the video monitoring point according to the image. No matter which method is used, it is based on the monitoring of the hardware of the video monitoring point to determine the category of the failure of the video monitoring point. However, the accuracy of the category of the failure of the video monitoring point obtained by these methods is low. SUMMARY

[0004] In view of the above problems, embodiments of the present application provide a video monitoring point fault classification method, device, equipment and computer readable storage medium, so that a video monitoring fault classification device can obtain a higher accuracy of the category of the failure of a target video monitoring point.

[0005] In a first aspect of the embodiments of the present application, a video monitoring point fault classification method is provided, which can include:

[0006] Collecting target failure information of a target video monitoring point;

[0007] Normalizing the target failure information to obtain a target key weight and a target failure keyword;

[0008] Inputting the target key weight and the target failure keyword into a target failure diagnosis model to obtain a keyword hit weight;

[0009] Determining the category of the failure of the target video monitoring point according to the keyword hit weight.

[0010] Optionally, the target failure information of the target video monitoring point includes the point name, the point Internet Protocol (IP), the point gateway, the front-end manufacturer, the access protocol, the front-end account / password, the encoding method, the dedicated line bandwidth, the connectivity result with the platform gateway, the fault platform, the fault phenomenon, the fault description, and the interconnection encoding of the target video monitoring point.

[0011] Optionally, the target fault information is normalized to obtain a target key weight and a target fault keyword, including: obtaining a first connectivity result of the point IP and the point gateway, a second connectivity result of the point gateway and the platform gateway, and a third connectivity result of the platform gateway and the point IP through ping measurement; obtaining the target key weight according to the first connectivity result, the second connectivity result and the third connectivity result; obtaining the target fault keyword according to the fault phenomenon and the fault description; wherein the target fault keyword includes at least one of the following: black screen, lag, unable to log in, real-time unable to watch, jitter, video loss, and transcoding failure.

[0012] Optionally, when the number of target fault keywords is 1, the target key weight and the target fault keyword are input into the target fault diagnosis model to obtain a keyword hit weight, including: obtaining a fault keyword classification weight of the target fault keyword in the point IP, the point gateway and the platform gateway of the target video monitoring point according to the target fault keyword; obtaining the keyword hit weight according to a first formula; wherein the first formula is W = H + ω; W represents the keyword hit weight, H represents the target key weight, and ω represents the fault keyword classification weight.

[0013] Optionally, when the number of target fault keywords is 1, the target key weight and the target fault keyword are input into the target fault diagnosis model to obtain a keyword hit weight, including:

[0014] According to the target fault keyword, obtain a fault keyword classification weight of the target fault keyword in the point IP, the point gateway and the platform gateway of the target video monitoring point;

[0015] Obtain a first probability coefficient corresponding to the point IP, a second probability coefficient corresponding to the point gateway, and a third probability coefficient corresponding to the platform gateway in the platform gateway;

[0016] According to the first probability coefficient, the second probability coefficient and the third probability coefficient, obtain a three-dimensional probability matrix;

[0017] According to a second formula, obtain a keyword hit weight;

[0018] Wherein, the second formula is W = H + ω + W0; W represents the keyword hit weight, H represents the target key weight, ω represents the fault keyword classification weight, and W0 represents the three-dimensional probability matrix.

[0019] Optionally, when the number of the target fault keywords is greater than 1, the number of the fault keyword classification weights corresponds to the target fault keywords; the target keyword weight and the target fault keyword are input into the target fault diagnosis model to obtain a keyword hit weight, which includes:

[0020] According to the target fault keyword, fault keyword classification weights of the target fault keyword in the point IP of the target video monitoring point, the point gateway and the platform gateway are obtained;

[0021] According to the third formula, the keyword hit weight is obtained;

[0022] The third formula is W = H + ω'; W represents the keyword hit weight, H represents the target keyword weight, and ω' represents the sum of the fault keyword classification weights. Optionally, the method further includes: outputting the fault category of the target video monitoring point.

[0023] In a second aspect, the embodiment of the present application provides a video monitoring fault classification device, which can include:

[0024] The acquisition module is configured to collect fault information of a target video monitoring point;

[0025] The processing module is configured to normalize the fault information to obtain a target keyword weight and a target fault keyword, and input the target keyword weight and the target fault keyword into a target fault diagnosis model to obtain a keyword hit weight;

[0026] The determination module is configured to determine a fault category of the target video monitoring point according to the keyword hit weight.

[0027] Optionally, the fault information of the target video monitoring point includes: a point name, a point Internet Protocol (IP), a point gateway, a front-end manufacturer, an access protocol, a front-end account / password, an encoding method, a dedicated line bandwidth, a connection result with a platform gateway, a fault platform, a fault phenomenon, a fault description, and an interconnection encoding.

[0028] Optionally, the processing module is specifically configured to obtain a first connection result of the point IP and the point gateway, a second connection result of the point gateway and the platform gateway, and a third connection result of the platform gateway and the point IP through a ping test; obtain a target keyword weight according to the first connection result, the second connection result and the third connection result; obtain a target fault keyword according to the fault phenomenon and the fault description; the target fault keyword includes at least one of the following: black screen, lag, unable to log in, real-time unable to watch, jitter, video loss, and transcoding failure.

[0029] Optionally, the processing module is specifically configured to, when the number of the target fault keywords is 1, obtain, according to the target fault keyword, a fault keyword classification weight of the target fault keyword in a point IP of the target video monitoring point, a point gateway and the platform gateway; obtain a keyword hit weight according to a first formula; wherein the first formula is W = H + ω; W represents the keyword hit weight, H represents the target keyword weight, and ω represents the fault keyword classification weight.

[0030] Optionally, the processing module is specifically configured to obtain a first probability coefficient corresponding to the point IP, a second probability coefficient corresponding to the point gateway, and a third probability coefficient corresponding to the platform gateway; obtain a three-dimensional probability matrix according to the first probability coefficient, the second probability coefficient and the third probability coefficient; obtain a keyword hit weight according to a second formula; wherein the second formula is W = H + ω + W0; W represents the keyword hit weight, H represents the target keyword weight, ω represents the fault keyword classification weight, and W0 represents the three-dimensional probability matrix.

[0031] Optionally, when the number of the target fault keywords is greater than 1, the number of the fault keyword classification weights corresponds to the target fault keywords, and the first formula is W = H + ω; W represents the keyword hit weight, H represents the target keyword weight, and ω represents the sum of the fault keyword classification weights.

[0032] Optionally, the processing module is further configured to output a fault category of the target video monitoring point.

[0033] In a third aspect, an embodiment of the present application provides a video monitoring fault classification device, which comprises a processor, a memory, a communication interface and a communication bus, the processor, the memory and the communication interface complete communication with each other through the communication bus.

[0034] The memory is used to store at least one executable instruction, and the executable instruction makes the processor execute the operations of the video monitoring fault classification method.

[0035] In a fourth aspect, an embodiment of the present application provides a computer readable storage medium, the storage medium stores at least one executable instruction, and the executable instruction makes the electronic device execute the operations corresponding to the video monitoring fault classification method when the electronic device runs.

[0036] In another aspect, an embodiment of the present application discloses a computer program product, when the computer program product runs on a computer, the computer executes any one of the methods disclosed in the first aspect of the present application.

[0037] In a further aspect, the application discloses an application publishing platform for publishing a computer program product, wherein the computer program product, when running on a computer, enables the computer to execute any of the methods disclosed in the first aspect of the application.

[0038] From the above technical solutions, the embodiments of the application have the following advantages:

[0039] In the embodiments of the application, target fault information of a target video monitoring point is collected; the target fault information is normalized to obtain target key weights and target fault keywords; the target key weights and the target fault keywords are input into a target fault diagnosis model to obtain keyword hit weights; and a fault category of the target video monitoring point is determined according to the keyword hit weights. That is, the video monitoring fault classification device can determine the fault category of the target video monitoring point according to the target fault information of the target video monitoring point and the target fault diagnosis model. In this way, the video monitoring fault classification device can obtain the fault category of the target video monitoring point with high accuracy.

[0040] The above description is only a summary of the technical solutions of the embodiments of the application, in order to more clearly understand the technical means of the embodiments of the application, the embodiments of the application can be implemented according to the content of the specification, and in order to make the above and other purposes, characteristics and advantages of the embodiments of the application more obvious and easy to understand, the specific embodiments of the application are described below. BRIEF DESCRIPTION OF DRAWINGS

[0041] The accompanying drawings are only used to show the embodiments and are not considered as limiting the application. Moreover, the same reference signs are used to represent the same components throughout the drawings. In the drawings:

[0042] Figure 1 An embodiment of a fault classification method for a video monitoring point in the embodiments of the application is shown in the figure;

[0043] Figure 2 Another embodiment of a fault classification method for a video monitoring point in the embodiments of the application is shown in the figure;

[0044] Figure 3 An embodiment of a video monitoring fault classification device in the embodiments of the application is shown in the figure;

[0045] Figure 4 An embodiment of a video monitoring fault classification device in the embodiments of the application is shown in the figure. DETAILED DESCRIPTION

[0046] Exemplary embodiments of the present application will be described herein below with reference to the accompanying drawings. While exemplary embodiments of the present application are shown in the drawings, it is understood that the present application can be embodied in various forms and should not be limited by the embodiments set forth herein.

[0047] It can be understood that the electronic device involved in the embodiments of the present application can include any of the following video monitoring fault classification devices.

[0048] It should be noted that the execution subject of the embodiments of the present application can be a video monitoring fault classification device, or an electronic device. The technical solutions of the present application will be further described below taking the electronic device as an example.

[0049] As shown in Figure 1 FIG. 1 is a schematic diagram of an embodiment of a fault classification method for a video monitoring point in the embodiments of the present application, which can include the following steps:

[0050] Step 101: Collect target fault information of a target video monitoring point.

[0051] It should be noted that the target fault information of the target video monitoring point can include key information of the target video monitoring point and fault data of the target video monitoring point. The key information of the target video monitoring point can include a point name, a point Internet Protocol (IP), a point gateway, a front-end manufacturer, an access protocol, a front-end account / password, an encoding method, a dedicated line bandwidth, a connection result with a platform gateway, and an interconnection encoding. The fault data of the target video monitoring point can include a fault platform, a fault phenomenon, and a fault description.

[0052] In particular, each target video monitoring point has corresponding target fault information. The target fault information corresponding to different target video monitoring points can be the same or different, which is not specifically limited here.

[0053] For example, the platform gateway can be 10.13.0.132.

[0054] Optionally, the electronic device collecting the target fault information of the target video monitoring point can include, but is not limited to, the following implementation manners:

[0055] Implementation manner 1: The electronic device automatically triggers the electronic device to collect the target fault information of the target video monitoring point at the beginning.

[0056] In this way, the electronic device can collect the target fault information in a timely manner.

[0057] Implementation manner 2: The electronic device collects the target fault information of the target video monitoring point after a preset time period.

[0058] It should be noted that the preset time length is an interval composed of a first preset time threshold and a second preset time threshold, and the first preset time threshold is less than the second preset time threshold. Wherein, the preset time length can be set before the electronic device leaves the factory, or can be determined by the relevant unit according to the demand, which is not limited here.

[0059] It can be understood that when the electronic device is powered on, the target fault information of the target video monitoring point can be collected after a preset time length from the time of powering on. That is, the electronic device has a certain delay function to accurately collect the target fault information.

[0060] Implementation mode 3: the electronic device periodically collects the target fault information of the target video monitoring point.

[0061] For example, the electronic device collects the target fault information of the target video monitoring point at 17:00 every Friday. In this way, the electronic device can continuously collect the target fault information and collect the target fault information in time.

[0062] It should be noted that the implementation mode 1 and the implementation mode 2 of the step 101 can be combined to form a new implementation mode. The new implementation mode is also within the scope of protection of the present application, which will not be described in detail here.

[0063] Optionally, after step 101, the method can further include: the electronic device forms a fault table of the target video monitoring point from the target fault information and stores it, providing convenience for subsequent work.

[0064] Step 102: normalizing the target fault information to obtain target key weight and target fault keyword.

[0065] Optionally, the electronic device normalizing the target fault information to obtain the target key weight and the target fault keyword can include: the electronic device obtains the first connection result of the point IP and the point gateway, the second connection result of the point gateway and the platform gateway, and the third connection result of the platform gateway and the point IP through ping measurement; the electronic device obtains the target key weight according to the first connection result, the second connection result and the third connection result; the electronic device obtains the target fault keyword according to the fault phenomenon and the fault description.

[0066] Wherein, the target fault keyword includes at least one of the following: black screen, lag, unable to log in, real-time unable to watch, jitter, video loss, and transcoding failure.

[0067] It should be noted that the ping test is a network diagnostic tool. In the process of the ping test, the platform server interworks with the video monitoring point dedicated line, and after the electronic device responds to the user's guarantee request, the electronic device will automatically ping the connection relationship between the point IP, the point gateway and the platform gateway, and form the corresponding connection result.

[0068] It can be understood that the first connection result represents that the point IP and the point gateway are in a connected state, or in a disconnected state; the second connection result represents that the point gateway and the platform gateway are in a connected state, or in a disconnected state; and the third connection result represents that the platform gateway and the point IP are in a connected state, or in a disconnected state.

[0069] It should be noted that the target key weight can be a three-dimensional key weight matrix composed of the first connection result, the second connection result and the third connection result. In this three-dimensional key weight matrix, if connected, 1 is used to represent, and if disconnected, 0 is used to represent.

[0070] For example, if the first connection result represents that the point IP and the point gateway are in a connected state, the second connection result represents that the point gateway and the platform gateway are in a disconnected state, and the third connection result represents that the platform gateway and the point IP are in a connected state, then the target key weight H = [1, 0, 1].

[0071] Optionally, the electronic device obtains the target fault key word according to the fault phenomenon and the fault description, which can include: the electronic device obtains the target fault key word according to the fault phenomenon and the fault description through fuzzy matching.

[0072] It should be noted that fuzzy matching means that the electronic device can match to a certain extent according to the fault phenomenon and the fault description. That is, the electronic device can match the fault key word regardless of its position in the fuzzy matching process. In this way, the content matched by the electronic device is more extensive.

[0073] Step 103: input the target key weight and the target fault key word into the target fault diagnosis model to obtain a keyword hit weight.

[0074] Optionally, when the number of target fault key words is 1, the electronic device inputs the target key weight and the target fault key word into the target fault diagnosis model to obtain a keyword hit weight, which can include: the electronic device obtains the fault key word classification weight of the target fault key word in the point IP, the point gateway and the platform gateway of the target video monitoring point according to the target fault key word; and the electronic device obtains the keyword hit weight according to the first formula.

[0075] The first formula is W=H+ω, wherein W represents the keyword hit weight, H represents the target keyword weight, and ω represents the fault keyword classification weight.

[0076] For example, assuming that H=[1, 0, 1], the target fault keyword is transcoding failure, and the fault keyword classification weight ω of the transcoding failure in the point IP of the target video monitoring point, the point gateway, and the platform gateway is [a1, b1, c1]=[0.2, 0.2, 0.6], then the keyword hit weight W=H+ω=[1, 0, 1]+[0.2, 0.2, 0.6]=[1.2, 0.2, 1.6]. In this way, the electronic device can obtain that the platform gateway of the target video monitoring point has the fault of transcoding failure.

[0077] Optionally, when the number of the target fault keywords is one, the electronic device inputs the target keyword weight and the target fault keyword into the target fault diagnosis model to obtain the keyword hit weight, including: the electronic device obtains the fault keyword classification weight of the target fault keyword in the point IP of the target video monitoring point, the point gateway, and the platform gateway according to the target fault keyword; obtains the first probability coefficient corresponding to the point IP, the second probability coefficient corresponding to the point gateway, and the third probability coefficient corresponding to the platform gateway; the electronic device obtains a three-dimensional probability matrix according to the first probability coefficient, the second probability coefficient, and the third probability coefficient; and the electronic device obtains the keyword hit weight according to a second formula.

[0078] The second formula is W=H+ω+W0, wherein W represents the keyword hit weight, H represents the target keyword weight, ω represents the fault keyword classification weight, and W0 represents the three-dimensional probability matrix.

[0079] In particular, the electronic device can set the initialized three-dimensional probability matrix W0=[W a , W b , W c ]=[0, 0, 0] before leaving the factory.

[0080] Optionally, the electronic device obtains a first probability coefficient corresponding to the point IP, a second probability coefficient corresponding to the point gateway, and a third probability coefficient corresponding to the platform gateway; and the electronic device obtains a three-dimensional probability matrix according to the first probability coefficient, the second probability coefficient, and the third probability coefficient, which can include: the electronic device determines whether the front-end manufacturer and the access protocol in the fault information match, if yes, the electronic device obtains the first probability coefficient corresponding to the point IP, if not, the electronic device obtains the first probability coefficient corresponding to the point IP, and adds a first constant to the first probability coefficient to obtain a first target probability coefficient; the electronic device obtains the second probability coefficient corresponding to the point gateway; the electronic device determines whether the code rate and the special line bandwidth in the fault information match, if yes, the electronic device obtains the third probability coefficient corresponding to the platform gateway, if not, the electronic device obtains the third probability coefficient corresponding to the platform gateway, and adds a second constant to the third probability coefficient to obtain a second target probability coefficient; and the electronic device obtains a three-dimensional probability matrix according to the first target probability coefficient, the second probability coefficient, and the second target probability coefficient.

[0081] It should be noted that the first constant and the second constant can be the same or different, which is not limited here.

[0082] For example, assuming that the first constant x = 0.2 and the second constant y = 0.2. Then, the three-dimensional probability matrix W0 = [W a +x, W b , W c +y] = [0.2, 0, 0.2].

[0083] Assuming that H = [1, 0, 1], the target fault keyword is transcoding failure, and the fault keyword classification weight ω = [a1, b1, c1] = [0.2, 0.2, 0.6] in the point IP of the target video monitoring point, the point gateway, and the platform gateway, then the keyword hit weight W = H + ω + W0 = [1, 0, 1] + [0.2, 0.2, 0.6] + [0.2, 0, 0.2] = [1.4, 0.2, 1.8]. In this way, the electronic device can obtain that there is a transcoding failure in the platform gateway of the target video monitoring point.

[0084] Optionally, when the number of the target fault keywords is greater than 1, the number of the fault keyword classification weights corresponding to the target fault keywords is input into the target fault diagnosis model, the target keyword weight and the target fault keyword are obtained, and the keyword hit weight is obtained, including: according to the target fault keyword, the fault keyword classification weight of the target fault keyword in the point IP of the target video monitoring point, the point gateway and the platform gateway is obtained; according to the third formula, the keyword hit weight is obtained; wherein the third formula is W = H + ω'; W represents the keyword hit weight, H represents the target keyword weight, and ω' represents the sum of the fault keyword classification weights.

[0085] wherein, i is an integer greater than 1 and less than or equal to 11.

[0086] Step 104: determining the fault category of the target video monitoring point according to the keyword hit weight.

[0087] Optionally, the electronic device determines the fault category of the target video monitoring point according to the keyword hit weight, which can include: the electronic device determines the fault category of the target video monitoring point according to the keyword hit weight by using the hard clustering k-means algorithm.

[0088] Optionally, the electronic device determines the fault category of the target video monitoring point according to the keyword hit weight by using the hard clustering k-means algorithm, which can include: the electronic device constructs the three-dimensional coordinates of the point IP, the point gateway and the platform gateway, and determines the coordinate axis center of the three-dimensional coordinates as three cluster centers, i.e. the first cluster center, the second cluster center and the third cluster center; the electronic device places the keyword hit weight in the three-dimensional coordinates, calculates the distance between each keyword hit weight and the three cluster centers; it is judged that each keyword hit weight is respectively with the first cluster center, the second cluster center and the third cluster center, the shortest distance between the keyword hit weight and the distance center is determined as a cluster; in this way, at most three clusters can be formed; the electronic device analyzes each cluster to determine the fault category of the target video monitoring point.

[0089] In the embodiment of the present application, target fault information of a target video monitoring point is collected; the target fault information is normalized to obtain target key weights and target fault keywords; the target key weights and the target fault keywords are input into a target fault diagnosis model to obtain keyword hit weights; and the fault category of the target video monitoring point is determined according to the keyword hit weights. That is, the video monitoring fault classification device can determine the fault category of the target video monitoring point according to the target fault information of the target video monitoring point and the target fault diagnosis model. In this way, the electronic device can obtain the fault category of the target video monitoring point with high accuracy.

[0090] As shown in Figure 2 , it is another embodiment schematic diagram of the fault classification method of the video monitoring point in the embodiment of the present application, which can include:

[0091] Step 201: Collecting target fault information of a target video monitoring point.

[0092] Step 202: Normalizing the target fault information to obtain target key weights and target fault keywords.

[0093] Step 203: Inputting the target key weights and the target fault keywords into a target fault diagnosis model to obtain keyword hit weights.

[0094] Step 204: Determining the fault category of the target video monitoring point according to the keyword hit weights. It should be noted that steps 201-204 are similar to steps 101-104 shown in the embodiment of the present application, and will not be described here. Figure 1

[0095] Step 205: Outputting the fault category of the target video monitoring point.

[0096] Optionally, the electronic device outputs the fault category of the target video monitoring point, which can include but is not limited to the following implementation manners:

[0097] Implementation manner 1: The electronic device reports the fault category of the target video monitoring point in the form of voice.

[0098] For example, assuming that the fault category of the target video monitoring point is "data of the target video monitoring point is not connected", the electronic device reports "data of the target video monitoring point is not connected" in the form of voice.

[0099] Implementation manner 2: The electronic device displays the fault category of the target video monitoring point in the form of text / animation.

[0100] ​It can be understood that the electronic device reports the failure category in the form of voice or displays the failure category in the form of text / animation, so that the user can timely master the failure category of the target video monitoring point, and the user can take corresponding measures according to the failure category.

[0101] It should be noted that the implementation mode 1 and the implementation mode 2 of the step 205 can be combined with each other to form a new implementation mode. The new implementation mode is also within the protection scope of the present application, and will not be described in detail here.

[0102] In the embodiment of the present application, the target failure information of the target video monitoring point is collected, the target failure information is normalized to obtain target key weight and target failure keywords, the target key weight and the target failure keywords are input into a target failure diagnosis model to obtain keyword hit weight, the failure category of the target video monitoring point is determined according to the keyword hit weight, and the failure category of the target video monitoring point is output. That is, the video monitoring failure classification device can determine and output the failure category of the target video monitoring point according to the target failure information of the target video monitoring point and the target failure diagnosis model. In this way, the electronic device can not only obtain the failure category of the target video monitoring point with high accuracy, but also output the failure category, so that the user can timely master the failure category of the target video monitoring point.

[0103] As shown in FIG. 1, it is a schematic diagram of an embodiment of the video monitoring failure classification device in the embodiment of the present application, which can include an acquisition module 301, a processing module 302 and a determination module 303. Figure 3

[0104] The acquisition module 301 is configured to collect the failure information of the target video monitoring point.

[0105] The processing module 302 is configured to normalize the failure information to obtain target key weight and target failure keywords, and input the target key weight and the target failure keywords into a target failure diagnosis model to obtain keyword hit weight.

[0106] The determination module 303 is configured to determine the failure category of the target video monitoring point according to the keyword hit weight.

[0107] Optionally, in some embodiments of the present application, the failure information of the target video monitoring point includes the point name, the point IP, the point gateway, the front-end manufacturer, the access protocol, the front-end account / password, the encoding mode, the dedicated line bandwidth, the communication result with the platform gateway, the failure platform, the failure phenomenon, the failure description and the interconnection encoding of the target video monitoring point.

[0108] ​Optionally, in some embodiments of the application, the processing module 302 is specifically configured to obtain, by ping measurement, a first connectivity result of the point IP and the point gateway, a second connectivity result of the point gateway and the platform gateway, and a third connectivity result of the platform gateway and the point IP; obtain a target key weight according to the first connectivity result, the second connectivity result, and the third connectivity result; obtain a target fault keyword according to the fault phenomenon and the fault description; wherein the target fault keyword includes at least one of the following: black screen, lag, unable to log in, real-time unable to watch, jitter, video loss, and transcoding failure.

[0109] Optionally, in some embodiments of the application, when the number of target fault keywords is 1, the processing module 302 is specifically configured to obtain a fault keyword classification weight of the target fault keyword in the point IP, the point gateway, and the platform gateway of the target video monitoring point according to the target fault keyword; obtain a keyword hit weight according to a first formula; wherein the first formula is W = H + ω; W represents the keyword hit weight, H represents the target key weight, and ω represents the fault keyword classification weight.

[0110] Optionally, in some embodiments of the application, when the number of target fault keywords is 1, the processing module 302 is specifically configured to obtain a fault keyword classification weight of the target fault keyword in the point IP, the point gateway, and the platform gateway of the target video monitoring point according to the target fault keyword; obtain a first probability coefficient corresponding to the point IP, a second probability coefficient corresponding to the point gateway, and a third probability coefficient corresponding to the platform gateway; obtain a three-dimensional probability matrix according to the first probability coefficient, the second probability coefficient, and the third probability coefficient; obtain a keyword hit weight according to a second formula; wherein the second formula is W = H + ω + W0; W represents the keyword hit weight, H represents the target key weight, ω represents the fault keyword classification weight, and W0 represents the three-dimensional probability matrix.

[0111] Optionally, in some embodiments of the application, when the number of target fault keywords is greater than 1, the number of fault keyword classification weights corresponds to the target fault keywords, and the target key weight and the target fault keywords are input into the target fault diagnosis model to obtain a keyword hit weight, including: obtaining a fault keyword classification weight of the target fault keyword in the point IP, the point gateway, and the platform gateway of the target video monitoring point according to the target fault keyword; obtaining a keyword hit weight according to a third formula; wherein the first formula is W = H + ω'; W represents the keyword hit weight, H represents the target key weight, and ω' represents the sum of the fault keyword classification weights.

[0112] Optionally, in some embodiments of the present application, the processing module 302 is further configured to output the failure category of the target video monitoring point.

[0113] As shown in FIG. 1, which is a schematic diagram of an embodiment of the video monitoring failure classification device in the embodiment of the present application, the embodiment of the present application does not limit the specific implementation of the video monitoring failure classification device. Figure 4

[0114] As shown in FIG. 4, the video monitoring failure classification device can include a processor 402, a communication interface 404, a memory 406, and a communication bus 408. Figure 4

[0115] The processor 402, the communication interface 404, and the memory 406 can communicate with each other through the communication bus 408. The communication interface 404 is configured to communicate with network elements such as clients or other servers. The processor 402 is configured to execute the program 410, and specifically can execute the related steps in the above-mentioned embodiments of the video monitoring failure classification method.

[0116] Specifically, the program 410 can include program codes containing computer-executable instructions.

[0117] The processor 402 can be a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present application. The one or more processors included in the electronic device can be the same type of processor, such as one or more CPUs; or can be different types of processors, such as one or more CPUs and one or more ASICs.

[0118] The memory 406 is configured to store the program 410. The memory 406 can include a high-speed RAM memory, and can also include a non-volatile memory, such as at least one disk memory.

[0119] The program 410 specifically can be invoked by the processor 402 to enable the electronic device to execute the steps 101-104 shown in FIG. 1, Figure 1 Figure 2 the steps 201-205 shown in FIG. 2, and the functions of the modules 301-303 shown in FIG. 3. Figure 3

[0120] Optionally, the processor 402 has the following functions,

[0121] collecting target failure information of a target video monitoring point; ​​​​

[0122] The target fault information is normalized to obtain a target key weight and a target fault keyword;

[0123] The target key weight and the target fault keyword are input into the target fault diagnosis model to obtain a keyword hit weight;

[0124] According to the keyword hit weight, the fault category of the target video monitoring point is determined.

[0125] Optionally, the processor 402 further has the following functions: the fault information of the target video monitoring point includes the point name, the point IP, the point gateway, the front-end manufacturer, the access protocol, the front-end account / password, the encoding mode, the dedicated line bandwidth, the connectivity result with the platform gateway, the fault platform, the fault phenomenon, the fault description, and the interconnection encoding of the target video monitoring point.

[0126] Optionally, the processor 402 further has the following functions: the first connectivity result of the point IP and the point gateway, the second connectivity result of the point gateway and the platform gateway, and the third connectivity result of the platform gateway and the point IP are obtained through ping measurement; the target key weight is obtained according to the first connectivity result, the second connectivity result, and the third connectivity result; the target fault keyword is obtained according to the fault phenomenon and the fault description; the target fault keyword includes at least one of the following: black screen, lag, unable to log in, real-time unable to watch, jitter, video loss, and transcoding failure.

[0127] Optionally, the processor 402 further has the following functions: according to the target fault keyword, the fault keyword classification weight of the target fault keyword in the point IP, the point gateway, and the platform gateway of the target video monitoring point is obtained; the keyword hit weight is obtained according to the first formula; the first formula is W=H+ω; W represents the keyword hit weight, H represents the target key weight, and ω represents the fault keyword classification weight.

[0128] Optionally, the processor 402 further has the following functions: when the number of the target fault keywords is 1, obtaining, according to the target fault keyword, a fault keyword classification weight of the target fault keyword in a point IP of the target video monitoring point, a point gateway and a platform gateway; obtaining a first probability coefficient corresponding to the point IP, a second probability coefficient corresponding to the point gateway and a third probability coefficient corresponding to the platform gateway; obtaining a three-dimensional probability matrix according to the first probability coefficient, the second probability coefficient and the third probability coefficient; obtaining a keyword hit weight according to a second formula; wherein the second formula is W = H + ω + W0; W represents the keyword hit weight, H represents the target keyword weight, ω represents the fault keyword classification weight, and W0 represents the three-dimensional probability matrix.

[0129] Optionally, the processor 402 further has the following functions: when the number of the target fault keywords is greater than 1, the number of the fault keyword classification weights corresponds to the target fault keywords, obtaining, according to the target fault keywords, a fault keyword classification weight of the target fault keyword in a point IP of the target video monitoring point, a point gateway and a platform gateway; obtaining a keyword hit weight according to a third formula; wherein the third formula is W = H + ω'; W represents the keyword hit weight, H represents the target keyword weight, and ω' represents the sum of the fault keyword classification weights.

[0130] Optionally, the processor 402 further has the following functions: outputting a fault category of the target video monitoring point.

[0131] Optionally, the memory 406 has the following functions: for storing the processing process and the processing result of the processor 402.

[0132] The embodiment of the application provides a computer readable storage medium, the storage medium stores at least one executable instruction, the executable instruction runs on the electronic equipment, and the electronic equipment executes the video monitoring fault classification method in any method embodiment.

[0133] The embodiment of the application provides a computer program, the computer program can be called by a processor to make an electronic equipment execute a video monitoring fault classification method in any method embodiment.

[0134] The embodiment of the application provides a computer program product, the computer program product comprises a computer program stored on a computer readable storage medium, and the computer program comprises program instructions, when the program instructions run on a computer, the computer executes a video monitoring fault classification method in any method embodiment.

[0135] In the above-described embodiments, all or some of the elements can be implemented by software, hardware or firmware, or any combination thereof. When implemented by software, the above-described embodiments can be implemented in the form of a computer program product.

[0136] The algorithms and displays presented herein are not inherently related to any particular computer, virtual system, or other apparatus. Various general purpose systems can be used with programs in accordance with the teachings herein, or it can prove convenient to construct more specialized apparatus to perform the required method steps. The required structure for a variety of these systems will be apparent from the description above. In addition, the present embodiments are not described with reference to any particular programming language. It will be appreciated that a variety of programming languages can be used to implement the teachings of the present disclosure as described herein, and any references below to specific languages are provided for disclosure of enablement of the best mode of the invention.

[0137] In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the application can be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been described in detail in order to not obscure the understanding of this description.

[0138] Similarly, it is to be understood that the above description is intended to be illustrative and not restrictive. Many embodiments of the present application will be apparent to those of skill in the art upon reviewing the above description, and it is therefore contemplated that the claims should be construed to include all such embodiments of the present application and their equivalents.

[0139] Those of skill in the art would understand that information and signals can be represented using any of a variety of technologies and techniques. For example, data, instructions, commands, information, signals, bits, symbols, and chips that can be referenced throughout the above description can be represented by voltages, currents, electromagnetic waves, magnetic fields or particles, optical fields or particles, or any combination thereof.

[0140] It should be noted that the above-mentioned embodiments illustrate rather than limit the application, and that those skilled in the art will be able to design many alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word 'comprising' does not exclude the presence of elements or steps other than those listed in a claim. The word 'a' or 'an' preceding an element does not exclude the presence of a plurality of such elements. The application can be implemented by means of both hardware and software, and any combination thereof. In a unitary claim, several devices, apparatuses or means can be listed, comprising means for carrying out a certain task. The use of the term'means' in a claim is intended to refer to a combination of devices, apparatuses or means for carrying out a task. The word 'first','second', 'third', etc. do not imply any order. The use of these terms is to be construed as an indication of particular embodiments. Steps in the above-described embodiments, unless otherwise specified, are not to be construed as necessarily limiting the order in which the steps are performed.

Claims

1. A fault classification method for video surveillance points, characterized in that, include: Collect target fault information from the target video monitoring points; The target fault information is normalized to obtain target key weights and target fault keywords. Specifically, ping tests are used to obtain a first connectivity result (connected or disconnected) between the point IP and the point gateway, a second connectivity result (connected or disconnected) between the point gateway and the platform gateway, and a third connectivity result (connected or disconnected) between the platform gateway and the point IP. Based on the first, second, and third connectivity results, the target key weights are obtained. The target key weights are a three-dimensional key weight matrix composed of the first, second, and third connectivity results. Input the target key weight and the target fault keyword into the target fault diagnosis model to obtain the keyword hit weight; wherein, when the number of the target fault keyword is 1, based on the target fault keyword, obtain the fault keyword classification weight of the target fault keyword in the point IP, point gateway, and platform gateway of the target video surveillance point; obtain the first probability coefficient corresponding to the point IP, the second probability coefficient corresponding to the point gateway, and the third probability coefficient corresponding to the platform gateway; obtain the three-dimensional probability matrix based on the first probability coefficient, the second probability coefficient, and the third probability coefficient; obtain the keyword hit weight according to the second formula; wherein, the second formula is W=H+ω+W0; W represents the keyword hit weight, H represents the target key weight, ω represents the fault keyword classification weight, and W0 represents the three-dimensional probability matrix; The fault category of the target video surveillance point is determined based on the keyword hit weight.

2. The method according to claim 1, characterized in that, The fault information of the target video surveillance point includes: the point name, the point's Internet Protocol IP address, the point's gateway, the front-end manufacturer, the access protocol, the front-end account / password, the encoding method, the leased line bandwidth, the connection result with the platform gateway, the faulty platform, the fault phenomenon, the fault description, and the interconnection code.

3. The method according to claim 2, characterized in that, The step of normalizing the target fault information to obtain target key weights and target fault keywords includes: Based on the fault phenomena and fault descriptions, the target fault keywords are obtained; The target fault keywords include at least one of the following: black screen, lag, inability to go online, playback failure, crash, data disconnection, inability to log in, inability to watch in real time, jitter, lost recording, and transcoding failure.

4. The method according to any one of claims 1-3, characterized in that, When the number of target fault keywords is greater than 1, the number of fault keyword classification weights corresponds to the number of target fault keywords; The process of inputting the target key weights and the target fault keywords into the target fault diagnosis model to obtain keyword hit weights includes: Based on the target fault keywords, the fault keyword classification weights of the target fault keywords in the point IP of the target video surveillance point, the point gateway, and the platform gateway are obtained; Based on the third formula, the keyword hit weight is obtained; The third formula is W=H+ω'; W represents the keyword hit weight, H represents the target keyword weight, and ω' represents the sum of the classification weights of the faulty keywords.

5. The method according to claim 1, characterized in that, The method further includes: Output the fault category of the target video monitoring point.

6. A video surveillance fault classification device, characterized in that, include: The acquisition module is used to collect fault information from the target video surveillance point; The processing module is used to normalize the fault information to obtain target key weights and target fault keywords. Specifically, through ping testing, it obtains a first connectivity result (connected or disconnected) between the point IP and the point gateway, a second connectivity result (connected or disconnected) between the point gateway and the platform gateway, and a third connectivity result (connected or disconnected) between the platform gateway and the point IP. Based on the first, second, and third connectivity results, the target key weights are obtained. The target key weights are a three-dimensional key weight matrix composed of the first, second, and third connectivity results. The target key weights and target fault keywords are input into the target fault diagnosis model to obtain keyword names. The algorithm is as follows: When the number of target fault keywords is 1, the fault keyword classification weight of the target fault keyword in the IP address, gateway address, and platform gateway of the target video surveillance point is obtained based on the target fault keyword; a first probability coefficient corresponding to the IP address, a second probability coefficient corresponding to the gateway address, and a third probability coefficient corresponding to the platform gateway are obtained; a three-dimensional probability matrix is ​​obtained based on the first probability coefficient, the second probability coefficient, and the third probability coefficient; and the keyword hit weight is obtained according to a second formula; where the second formula is W=H+ω+W0; W represents the keyword hit weight, H represents the target key weight, ω represents the fault keyword classification weight, and W0 represents the three-dimensional probability matrix. The determination module is used to determine the fault category of the target video surveillance point based on the keyword hit weight.

7. A video surveillance fault classification device, characterized in that, include: The processor, memory, communication interface, and communication bus are provided, wherein the processor, memory, and communication interface communicate with each other via the communication bus. The memory is used to store at least one executable instruction, which causes the processor to perform an operation corresponding to the video surveillance fault classification method as described in any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The storage medium stores at least one executable instruction, which, when executed on the electronic device, causes the electronic device to perform the operation corresponding to the video surveillance fault classification method as described in any one of claims 1-5.

Images