Alarm information processing method and device, equipment and medium

Abstract

The invention discloses an alarm information processing method and device, equipment and a medium, which are used for realizing more accurate and rapid processing of alarm information. The method comprises the following steps: acquiring alarm record information from a target on-duty host; acquiring a video stream corresponding to the alarm record information and monitoring information reported by Internet of Things equipment corresponding to the alarm record information from the target guarding host; determining a fusion analysis result corresponding to the alarm record information; wherein the fusion analysis result is obtained based on a first analysis result and a second analysis result, the first analysis result is a detection result obtained by detecting the video stream, and the second analysis result is an analysis result obtained by analyzing the monitoring information; and matching a fusion analysis result corresponding to the alarm record information with a preset guard processing rule, and executing a corresponding processing operation according to a matching result.

Description

Technical Field

[0001] The present application relates to the field of information technology, and in particular to an alarm information processing method, device, equipment and medium. Background Art

[0002] RPA (Robotic Process Automation) is the abbreviation of Robotic Process Automation, which is a business process automation technology based on software robots and artificial intelligence. RPA uses automation software as a virtual workforce to interact with existing systems according to pre-set programs and complete expected tasks. These tasks can include recognition, triggering, communication, text generation, etc., and can automatically execute repetitive business processes.

[0003] The operating principle of RPA is mainly to capture and simulate the human-computer interaction behaviors such as keyboard and mouse operations in daily work through software robots. These software robots use the user interface (UI) to capture data and simulate human operation of applications. They can recognize, trigger responses, and communicate with other systems to perform various repetitive tasks. Summary of the invention

[0004] The embodiments of the present application provide an alarm information processing method, apparatus, device and medium to achieve more accurate and rapid handling of alarm information, greatly reduce manual processing workload and improve work efficiency.

[0005] On the RPA on-call host side, an alarm information processing method provided in an embodiment of the present application includes:

[0006] Obtain alarm record information from the target on-duty host;

[0007] Acquire a video stream corresponding to the alarm record information and monitoring information reported by an IoT device corresponding to the alarm record information from the target on-duty host; and determine a fusion analysis result corresponding to the alarm record information; wherein the fusion analysis result is obtained based on a first analysis result and a second analysis result, the first analysis result is a detection result obtained by detecting the video stream, and the second analysis result is an analysis result obtained by analyzing the monitoring information;

[0008] The fusion analysis result corresponding to the alarm record information is matched with the preset on-duty handling rules, and the corresponding handling operation is performed according to the matching result.

[0009] Through the method provided in the embodiment of the present application, the alarm record information is obtained from the target on-duty host, and then the video stream corresponding to the alarm record information and the monitoring information reported by the IoT device corresponding to the alarm record information can be further obtained from the target on-duty host; and the fusion analysis result corresponding to the alarm record information is determined; wherein the fusion analysis result is obtained based on the first analysis result and the second analysis result, the first analysis result is the detection result obtained by detecting the video stream, and the second analysis result is the analysis result obtained by analyzing the monitoring information; finally, the fusion analysis result corresponding to the alarm record information can be matched with the preset on-duty disposal rule, and the corresponding disposal operation is performed according to the matching result, so the embodiment of the present application can realize automatic processing of the alarm information through multi-dimensional fusion analysis of the IoT device data and video data associated with the alarm information, greatly reducing the manual processing amount. It can be seen that the embodiment of the present application can not only improve the accuracy of the alarm information disposal, avoid the occurrence of alarm situations such as misjudgment and false alarm, but also greatly improve the work efficiency of the alarm information disposal, and improve the security of the on-duty in the relevant application scenarios.

[0010] In some embodiments, obtaining alarm record information from the target on-duty host includes:

[0011] The optical character recognition (OCR) technology is used to identify the on-duty client interface in the mirror desktop screen of the target on-duty host to obtain alarm record information.

[0012] In some embodiments, determining the fusion analysis result corresponding to the alarm record information includes:

[0013] Sending the video stream and the monitoring information to a preset multi-dimensional analysis server;

[0014] Receiving a fusion analysis result corresponding to the alarm record information sent by the multidimensional analysis server;

[0015] Among them, the fusion analysis result is obtained by the multidimensional analysis server based on the first analysis result and the second analysis result, the first analysis result is the detection result obtained by the video intelligent analysis module in the multidimensional analysis server to detect the video stream, and the second analysis result is the analysis result obtained by the Internet of Things data analysis module in the multidimensional analysis server to analyze the monitoring information.

[0016] Accordingly, on the server side, an alarm information processing method provided by an embodiment of the present application includes:

[0017] Obtaining a video stream corresponding to the alarm record information sent by a Robotic Process Automation (RPA) on-duty host, and monitoring information reported by an IoT device corresponding to the alarm record information; wherein the alarm record information is obtained by the RPA on-duty host from a target on-duty host;

[0018] Determine a fusion analysis result corresponding to the alarm record information, and send it to the RPA on-duty host; wherein the fusion analysis result is obtained based on a first analysis result and a second analysis result, the first analysis result is a detection result obtained by detecting the video stream, and the second analysis result is an analysis result obtained by analyzing the monitoring information.

[0019] In some embodiments, analyzing the monitoring information includes:

[0020] Based on the monitoring information reported by the IoT device corresponding to the alarm record information, determine the monitoring information within a time period of a preset length corresponding to the monitoring information at the i-th moment; wherein the monitoring information at the i-th moment is the monitoring information at any moment reported by the IoT device corresponding to the alarm record information;

[0021] By fitting the monitoring information in the time period, a first fitting curve is obtained, and based on the first fitting curve, a first fitting residual of the monitoring information at the i-th moment in the time period is determined;

[0022] Eliminate the monitoring information at the i-th moment in the time period, and fit the remaining monitoring information in the time period to obtain a second fitting curve, and determine a second fitting residual of the monitoring information at the i-th moment in the time period based on the second fitting curve;

[0023] A third fitting curve is obtained by fitting the prediction alarm information within the time period, and a third fitting residual of the monitoring information at the i-th moment in the time period is determined based on the third fitting curve; wherein the prediction alarm information is the prediction alarm information output by the neural network model by inputting the monitoring information within the time period into a preset neural network model;

[0024] Based on the first fitting residual, the second fitting residual, and the third fitting residual, determining the authenticity parameter of the monitoring information at the i-th moment as the alarm information;

[0025] Determining a parameter of a true contribution degree of the monitoring information at the i-th moment to the time period based on the first fitting residual and the second fitting residual;

[0026] Based on the authenticity parameter and the real contribution degree parameter, finally determining the authenticity degree parameter of the monitoring information at the i-th moment as the alarm information;

[0027] When the authenticity parameter is greater than or equal to a preset threshold, the monitoring information at the i-th moment is determined to be true alarm information.

[0028] In some embodiments, determining the actual contribution degree parameter of the monitoring information at the i-th moment to the time period based on the first fitting residual and the second fitting residual includes:

[0029] Determining an initial true contribution degree parameter of the monitoring information at the i-th moment to the time period based on the first fitting residual and the second fitting residual;

[0030] The initial true contribution degree parameter is normalized to finally obtain the true contribution degree parameter of the monitoring information at the i-th moment to the time period.

[0031] On the RPA on-call host side, an alarm information processing device provided in an embodiment of the present application includes:

[0032] An alarm record acquisition unit, used to acquire alarm record information from a target on-duty host;

[0033] A fusion analysis result acquisition unit is used to acquire, from the target on-duty host, a video stream corresponding to the alarm record information and monitoring information reported by an IoT device corresponding to the alarm record information; and determine a fusion analysis result corresponding to the alarm record information; wherein the fusion analysis result is obtained based on a first analysis result and a second analysis result, the first analysis result being a detection result obtained by detecting the video stream, and the second analysis result being an analysis result obtained by analyzing the monitoring information;

[0034] The processing rule matching unit is used to match the fusion analysis result corresponding to the alarm record information with the preset on-duty processing rule, and perform corresponding processing operations according to the matching result.

[0035] Accordingly, on the server side, an alarm information processing device provided by an embodiment of the present application includes:

[0036] An alarm information acquisition unit, used to acquire a video stream corresponding to the alarm record information sent by a Robotic Process Automation (RPA) on-duty host, and monitoring information reported by an IoT device corresponding to the alarm record information; wherein the alarm record information is acquired by the RPA on-duty host from a target on-duty host;

[0037] A fusion analysis result determination unit is used to determine a fusion analysis result corresponding to the alarm record information and send it to the RPA on-duty host; wherein the fusion analysis result is obtained based on a first analysis result and a second analysis result, the first analysis result is a detection result obtained by detecting the video stream, and the second analysis result is an analysis result obtained by analyzing the monitoring information.

[0038] Another embodiment of the present application provides an electronic device, which includes a memory and a processor, wherein the memory is used to store program instructions, and the processor is used to call the program instructions stored in the memory and execute any of the above methods according to the obtained program.

[0039] Another embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable the computer to execute any of the above methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0041] Figure 1 A schematic diagram of the overall process of an alarm information processing method on the RPA on-duty host side provided in an embodiment of the present application;

[0042] Figure 2 A schematic diagram of a specific process of determining a fusion analysis result corresponding to alarm record information on the RPA on-duty host side provided in an embodiment of the present application;

[0043] Figure 3 A schematic diagram of the overall process of an alarm information processing method on the server side provided in an embodiment of the present application;

[0044] Figure 4 A schematic diagram of a specific process of analyzing monitoring information on the server side provided in an embodiment of the present application;

[0045] Figure 5 A schematic diagram of a specific process for determining a parameter of the actual contribution degree of monitoring information at the i-th moment to a time period of a preset length based on a first fitting residual and a second fitting residual provided in an embodiment of the present application;

[0046] Figure 6A schematic diagram of a specific processing flow of an alarm information processing system including a target on-duty host, an RPA on-duty host, a multi-dimensional analysis server, and a voice intercom device provided in an embodiment of the present application;

[0047] Figure 7 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application;

[0048] Figure 8 A structural diagram of an alarm information processing device on the RPA on-duty host side provided in an embodiment of the present application;

[0049] Fig. 9 A schematic diagram of the structure of an alarm information processing device on the server side provided in an embodiment of the present application;

[0050] Fig.10 A schematic diagram of the specific structure of the fusion analysis result determination unit provided in an embodiment of the present application. DETAILED DESCRIPTION

[0051] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0052] The embodiments of the present application provide an alarm information processing method, apparatus, device and medium to achieve more accurate and rapid handling of alarm information, greatly reduce manual processing workload and improve work efficiency.

[0053] Among them, the method and the device, equipment, and medium are based on the same application concept. Since the principles of solving problems by the method and the device, equipment, and medium are similar, the implementation of the device, equipment, medium, and method can refer to each other, and the repeated parts will not be repeated.

[0054] The terms "first", "second", etc. (if any) in the specification and claims of the embodiments of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described herein can be implemented in an order other than the content illustrated or described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0055] The following examples and embodiments are to be understood as illustrative examples only. Although this specification may refer to "one", "an" or "some" examples or embodiments in several places, this does not mean that each such reference relates to the same example or embodiment, nor does it mean that the feature applies only to a single example or embodiment. Individual features of different embodiments may also be combined to provide other embodiments. In addition, terms such as "including" and "comprising" should be understood as not limiting the described embodiments to only those features that have been mentioned; such examples and embodiments may also include features, structures, units, modules, etc. that are not specifically mentioned.

[0056] The following is a detailed description of each embodiment of the present application in conjunction with the accompanying drawings. It should be noted that the display order of the embodiments of the present application only represents the order of the embodiments, and does not represent the advantages and disadvantages of the technical solutions provided by the embodiments.

[0057] The advantage of RPA is that it can automate the deployment of business processes on the original business system without any modification to the original system. It is a non-invasive technology. Moreover, RPA software robots never rest and never make mistakes. Their cost of use is much lower than that of human employees. Therefore, it can reduce operating costs while improving compliance and security.

[0058] RPA has a wide range of applications, mainly including financial accounting, human resources, procurement, supply chain management, etc., such as expense reimbursement, document review, personnel onboarding, certification, order verification and other processes. With the increasing maturity of artificial intelligence technology, the development of RPA has reached the fourth stage, namely AI+RPA. At this stage, artificial intelligence and robotic process automation are effectively combined to make intelligent decisions in complex scenarios, making RPA more functional, more applicable, and more intelligent. Although RPA technology has developed rapidly in various industries, the application of RPA technology in the field of remote banking in smart finance is still in its infancy.

[0059] At present, the remote duty of bank branches mainly relies on the real-time images of the on-site points monitored manually. According to the basic principle of "prevention first, timely handling, and safety guarantee" for handling abnormal events of self-service banks and ATMs, various events are discovered and handled to achieve 7x24 hours of remote duty. This method not only has high labor costs, but also low efficiency. Due to low wages, the duty personnel are not very motivated to handle alarms, and the safety risk management of bank branches is not guaranteed.

[0060] The technical solution provided in the embodiment of the present application can be applied in the field of bank duty, for example, to realize remote bank duty based on RPA. Under the premise of meeting the requirements of bank information security regulations, the original system functions are not modified, and the duty alarm data is obtained in a non-invasive manner. The IoT device data and video data associated with the alarm are analyzed in a multi-dimensional fusion manner, and the alarm information is automatically processed by the RPA duty host for review and verification, which can greatly reduce the amount of manual processing.

[0061] See also Figure 1 On the RPA on-call host side, an alarm information processing method provided by an embodiment of the present application includes:

[0062] S101, obtaining alarm record information from the target on-duty host;

[0063] Wherein, the target on-duty host is, for example, a bank on-duty host. Of course, in practical applications, different target on-duty hosts can be set according to the needs of different application scenarios.

[0064] In some embodiments, a wireless adapter can be used to establish a remote keyboard and mouse operation communication link between the target on-duty host and the RPA on-duty host. The keyboard and mouse operation refers to the RPA on-duty host sending operation instructions to the target on-duty host through wireless communication to remotely operate the on-duty client interface of the target on-duty host, that is, remotely operate the target on-duty host through the RPA on-duty host.

[0065] S102, obtaining from the target on-duty host a video stream corresponding to the alarm record information, and monitoring information reported by the IoT device corresponding to the alarm record information; and determining a fusion analysis result corresponding to the alarm record information; wherein the fusion analysis result is obtained based on a first analysis result and a second analysis result, the first analysis result being a detection result obtained by detecting the video stream, and the second analysis result being an analysis result obtained by analyzing the monitoring information;

[0066] The IoT device may be, for example, a door magnetic device, and the monitoring information reported by the device may be information related to door magnetic separation, etc.

[0067] The first analysis result, for example, is a detection of a multi-person event;

[0068] The second analysis result is, for example, detection of a door magnetic separation event;

[0069] Therefore, the fusion analysis result may be, for example, an event in which multiple people enter the cabin.

[0070] In some embodiments, the RPA on-call host can obtain the mirrored desktop video stream of the target on-call host through a High Definition Multimedia Interface (HDMI) bypass (including a splitter, a capture card, etc.) of the target on-call host.

[0071] S103: Match the fusion analysis result corresponding to the alarm record information with the preset on-duty handling rule, and perform corresponding handling operations according to the matching result.

[0072] In the embodiment of the present application, the on-duty handling rules for various situations can be preset in the RPA on-duty host according to the actual manual on-duty process in combination with the specific application scenario, so that the corresponding handling operations can be performed according to the matching results.

[0073] For example, if the fusion analysis result is that multiple people enter the cabin, then the on-duty handling rule that matches it is, for example, a handling rule that executes a preset voice call. In other words, the corresponding handling operation is executed according to the matching result, for example, a voice is played through a player set near the protection cabin, "Hello, only one person can handle business in the protection cabin, other people please wait outside the protection cabin."

[0074] In some embodiments, obtaining alarm record information from the target on-duty host includes:

[0075] The on-duty client interface in the mirror desktop screen of the target on-duty host is recognized by using optical character recognition (OCR) technology to obtain alarm record information.

[0076] In some embodiments, the RPA on-duty host can further play the video stream, thereby identifying the video screen through OCR technology and obtaining alarm-related information.

[0077] In some embodiments, see Figure 2 , the determining of the fusion analysis result corresponding to the alarm record information includes:

[0078] S201, sending the video stream corresponding to the alarm record information and the monitoring information reported by the IoT device corresponding to the alarm record information to a preset multi-dimensional analysis server;

[0079] S202, receiving a fusion analysis result corresponding to the alarm record information sent by the multidimensional analysis server;

[0080] Among them, the fusion analysis result is obtained by the multidimensional analysis server based on the first analysis result and the second analysis result, the first analysis result is the detection result obtained by the video intelligent analysis module in the multidimensional analysis server to detect the video stream, and the second analysis result is the analysis result obtained by the Internet of Things data analysis module in the multidimensional analysis server to analyze the monitoring information.

[0081] The multi-dimensional analysis server may be pre-configured with a video intelligent analysis module, an Internet of Things data analysis module and a fusion module, which are respectively used to obtain the first analysis result, the second analysis result and the fusion analysis result.

[0082] It should be noted that, in the embodiment of the present application, the fusion analysis result corresponding to the alarm record information can be determined by the multidimensional analysis server connected to the RPA on-duty host. In addition, in the embodiment of the present application, the fusion analysis result corresponding to the alarm record information can also be determined by the RPA on-duty host itself. The specific determination method is the same as that of the multidimensional analysis server, and will not be described in detail.

[0083] Correspondingly, on the server side, see Figure 3 , an alarm information processing method provided in an embodiment of the present application includes:

[0084] S301, obtaining a video stream corresponding to alarm record information sent by a robot process automation (RPA) on-duty host, and monitoring information reported by an IoT device corresponding to the alarm record information; wherein the alarm record information is obtained by the RPA on-duty host from a target on-duty host;

[0085] S302. Determine a fusion analysis result corresponding to the alarm record information, and send it to the RPA on-duty host; wherein the fusion analysis result is obtained based on a first analysis result and a second analysis result, the first analysis result is a detection result obtained by detecting the video stream, and the second analysis result is an analysis result obtained by analyzing the monitoring information.

[0086] In some embodiments, see Figure 4 , analyzing the monitoring information, including:

[0087] S401, based on the monitoring information reported by the IoT device corresponding to the alarm record information, determining the monitoring information within a time period of a preset length corresponding to the monitoring information at the i-th moment;

[0088] The monitoring information at the i-th moment is the monitoring information at any moment reported by the IoT device corresponding to the alarm record information;

[0089] The time period of preset length corresponding to the monitoring information at the i-th moment may also be referred to as a local interval regarding the monitoring information at the i-th moment, that is, the local interval includes monitoring information at multiple moments, including the monitoring information at the i-th moment. In some embodiments, the monitoring information at the i-th moment may be in the middle position of the local interval, or of course, may be in other positions.

[0090] For example, the period of reporting monitoring information by the door magnetic device is 3 seconds, and the 10 monitoring information before and after the monitoring information at the i-th moment can be taken to form a local interval of the monitoring information at the i-th moment.

[0091] S402, obtaining a first fitting curve by fitting the monitoring information in the time period, and determining a first fitting residual of the monitoring information at the i-th moment in the time period based on the first fitting curve;

[0092] The fitting described in the embodiments of the present application can be performed by, for example, using a moving average method.

[0093] Among them, the first fitting residual of the monitoring information at the i-th moment in the time period is, for example, expressed as

[0094] S403, removing the monitoring information at the i-th moment in the time period, and fitting the remaining monitoring information in the time period to obtain a second fitting curve, and determining a second fitting residual of the monitoring information at the i-th moment in the time period based on the second fitting curve;

[0095] Among them, the second fitting residual of the monitoring information at the i-th moment in the time period is, for example, expressed as

[0096] S404, obtaining a third fitting curve by fitting the prediction alarm information in the time period, and determining a third fitting residual of the monitoring information at the i-th moment in the time period based on the third fitting curve; wherein the prediction alarm information is the prediction alarm information output by inputting the monitoring information in the time period into a preset neural network model;

[0097] Among them, the third fitting residual of the monitoring information at the i-th moment in the time period is, for example, expressed as

[0098] S405: determining, based on the first fitting residual, the second fitting residual, and the third fitting residual, the authenticity parameter of the monitoring information at the i-th moment as alarm information;

[0099] The monitoring information at the i-th moment is used as the authenticity parameter of the alarm information, for example, represented by P i, then, for example, P i The following formula can be used for calculation:

[0100]

[0101] Wherein, norm represents the normalization function, a, b, c are the weights of the first fitting residual, the second fitting residual, and the third fitting residual, respectively, all of which are preset values ​​and satisfy a+b+c=1, for example: a=0.5, b=0.3, c=0.2, and the specific values ​​of a, b, and c can be determined according to actual needs. n represents the number of monitoring information in the time period.

[0102] Authenticity parameter P i The smaller it is, the smaller the difference between the first fitting residual, the second fitting residual, and the third fitting residual is, which means that the authenticity of the monitoring information at the i-th moment is higher.

[0103] S406: determining a parameter of a real contribution degree of the monitoring information at the i-th moment to the time period based on the first fitting residual and the second fitting residual;

[0104] S407, based on the authenticity parameter and the real contribution degree parameter, finally determining the authenticity degree parameter of the monitoring information at the i-th moment as the alarm information;

[0105] S408: When the authenticity parameter is greater than or equal to a preset threshold, the monitoring information at the i-th moment is determined as true alarm information.

[0106] It can be determined whether the authenticity parameter of the finally determined monitoring information at the i-th moment as the alarm information is greater than or equal to the preset threshold α. If so, the monitoring information at the i-th moment is regarded as the real alarm information; otherwise, it is regarded as the unreal alarm information and can be ignored. The preset threshold α can be, for example, 0.85, which is determined according to actual needs.

[0107] In some embodiments, see Figure 5 , based on the first fitting residual and the second fitting residual, determining a parameter of the actual contribution degree of the monitoring information at the i-th moment to the time period, including:

[0108] S501, determining an initial true contribution degree parameter of the monitoring information at the i-th moment to the time period based on the first fitting residual and the second fitting residual;

[0109] The initial real contribution parameter of the monitoring information at the i-th moment to the time period is expressed as D i ;

[0110] Then, for example, D can be calculated using the following formula 2: i :

[0111]

[0112] S502: Normalize the initial true contribution degree parameter to finally obtain the true contribution degree parameter of the monitoring information at the i-th moment to the time period.

[0113] The actual contribution parameter of the monitoring information at the i-th moment to the time period is expressed as D′ i ;

[0114] Then, for example, D′ can be calculated using the following formula 3: i :

[0115]

[0116] in, represents the sum of the parameters of the real contribution of the monitoring information at each moment in the time period to the time period, and n represents the number of monitoring information in the time period. In other words, D′ i is the normalized parameter of the actual contribution degree of the monitoring information at the i-th moment to the time period.

[0117] In some embodiments, the above step S406 can be calculated using the above formula 2, or can be calculated using the above formula 2 and formula 3. That is, the real contribution degree parameter used in step S407 can be D i , or D′ i .

[0118] In some embodiments, the monitoring information at the i-th moment finally determined in step S407 is used as the authenticity parameter of the alarm information, for example, represented by R i , then R i The following formula 4 can be used for calculation:

[0119]

[0120] Among them, P j Indicates the authenticity parameter of the monitoring information at the jth moment in the time period as the alarm information, D' j represents the normalized parameter of the actual contribution degree of the monitoring information at the jth moment to the time period, n represents the number of monitoring information in the time period, and norm represents the normalization function.

[0121] The following uses the bank duty as an example to illustrate the specific processing flow of the alarm information processing system including the bank duty host, RPA duty host, multi-dimensional analysis server, and voice intercom equipment. Figure 6 , the alarm information processing method of the whole system includes:

[0122] S601, open the on-call client;

[0123] That is, the RPA on-call host opens the on-call client on the bank on-call host through remote control;

[0124] S602, identifying the on-call client interface in the mirror desktop screen of the bank on-call host, and obtaining alarm record information;

[0125] In the embodiment of the present application, the RPA on-duty host can obtain the alarm record information on the bank on-duty host one by one and perform subsequent processing.

[0126] S603, sending a video stream corresponding to the alarm record information, and monitoring information reported by the IoT device corresponding to the alarm record information;

[0127] That is, the bank's on-duty host sends the video stream corresponding to the alarm record information and the monitoring information reported by the IoT device corresponding to the alarm record information to the RPA on-duty host under the control of the RPA on-duty host.

[0128] S604: Sending a video stream corresponding to the alarm record information and monitoring information reported by the IoT device corresponding to the alarm record information;

[0129] That is, after the RPA duty host obtains the video stream corresponding to the alarm record information and the monitoring information reported by the IoT device corresponding to the alarm record information from the bank duty host, it sends the video stream corresponding to the alarm record information and the monitoring information reported by the IoT device corresponding to the alarm record information to the multidimensional analysis server.

[0130] S605: Detect the video stream to obtain a first analysis result, and analyze the monitoring information to obtain a second analysis result;

[0131] That is to say, through the RPA duty host, the duty desktop of the bank duty host is remotely operated to play the video associated with the alarm record, and the video stream (the video stream can be a part of the entire desktop mirror video stream) is connected to the video intelligent analysis module of the multidimensional analysis server for behavior detection, and the event detection result output by the video intelligent analysis module is obtained, that is, the first analysis result.

[0132] In addition, through the RPA duty host, the bank duty host is remotely operated to obtain the monitoring information reported by the IoT device associated with the alarm record, and send it to the IoT (Internet of Things) data analysis module of the multi-dimensional analysis server, so as to obtain the analysis result output by the IoT data analysis module, that is, the second analysis result.

[0133] In an embodiment of the present application, on the multidimensional analysis server side, before analyzing IoT data (ie, monitoring information reported by IoT devices), for example, it may also include: data collection and data processing processes.

[0134] The data collection, for example, includes collecting the following data:

[0135] Static data, such as device type, specifications, capabilities, and manufacturers.

[0136] Dynamic data, such as the device’s own status, device monitoring information, etc.

[0137] Historical data, such as past monitoring information records and fault records.

[0138] Environmental data, such as temperature, humidity, voltage, etc.

[0139] The data processing includes, for example, data cleaning, feature engineering, and model selection.

[0140] The data cleaning is used to process missing values ​​and remove abnormal data. For example, for historical monitoring information, a denoising algorithm is first used to obtain the monitoring information at each reporting time after denoising.

[0141] The feature engineering is based on the application scenarios of IoT devices and the construction of features based on historical data. For example, when the door magnetic sensor opens / closes the door, its signal shows a certain regularity. Therefore, the distribution of historical alarm information in each interval is obtained, and the correlation of the monitoring information in each interval is obtained based on the distribution. Based on the correlation, the alarm authenticity of the collected data in each interval can be obtained. Specifically, for example, by analyzing the historical event data of the door magnetic, the following information can be obtained: the duration of the door opening or closing, the frequency of the door magnetic state change, the door magnetic state sequence and other information.

[0142] The model selection uses data analysis and statistical methods to establish an appropriate neural network model, the neural network model inputs monitoring information and outputs prediction alarm information, for example, the monitoring information reported by the door magnetic device is input into a preset neural network model, and the prediction alarm information is output through the preset neural network model. For the prediction alarm information of the door magnetic device, for example, a long short-term memory network (LSTM) can be used, which is a special recurrent neural network (RNN) that is particularly good at processing sequence data and capturing long-term dependencies.

[0143] S606, fusing the first analysis result with the second analysis result to obtain a fused analysis result;

[0144] S607, sending the fusion analysis result corresponding to the alarm record information;

[0145] That is to say, in the embodiment of the present application, the first analysis result and the second analysis result can be fused through the multidimensional analysis server to obtain a fused analysis result, and then fed back to the RPA on-duty host.

[0146] S608, matching the fusion analysis result corresponding to the alarm record information with the preset on-duty handling rule;

[0147] For example, when two people enter the ATM protection cabin at the same time, the IoT event of door magnet separation will be triggered, and the video intelligent analysis module will detect a multi-person event. The combination of the two will trigger a multi-person entry alarm and match the on-duty handling rules. For example, according to the bank's on-duty handling process specifications, manual intervention is required, that is, the on-duty personnel calls the voice panel in the protection cabin through the IP voice terminal and speaks the standard words to the customer - "Hello, only one person can handle business in the protection cabin, other people please wait outside the protection cabin". Therefore, when it is determined that a multi-person entry event has occurred, the RPA on-duty host will automatically play the voice corresponding to the multi-person entry event "Hello, only one person can handle business in the protection cabin, other people please wait outside the protection cabin" to make a call, and can also record the handling operation results. For another example, if the above-mentioned video intelligent analysis module detects that a person falls to the ground, the final matched preset voice can be "Hello, do you need help?" The other processing methods are similar and will not be repeated.

[0148] S609, triggering the voice intercom device to play a preset voice;

[0149] S610, saving a processing record for the alarm record information, and generating a processing report for the alarm record information;

[0150] S611: Control recording of processing operations for the alarm record information.

[0151] That is, the RPA on-duty host converts the processing operation results into keyboard and mouse operation instructions, and sends them to the bank's on-duty host for recording through wireless communication.

[0152] In addition, the embodiment of the present application can also detect and analyze tailgating events, emergency alarm events, answering intercom events, etc. through the RPA on-duty host, and perform corresponding disposal operations, which will not be described in detail.

[0153] It can be seen that the embodiment of the present application realizes remote bank monitoring in a non-invasive manner through the RPA monitoring host. In addition, through multi-dimensional data fusion analysis, it reduces the false alarm of alarm information, reduces a large amount of manual processing, and improves the accuracy and efficiency of alarm information processing.

[0154] The following is an introduction to the equipment or device provided in the embodiments of the present application, in which the explanations or examples of technical features that are the same or corresponding to those described in the above method will not be repeated later.

[0155] An electronic device provided in an embodiment of the present application may be, for example, an RPA on-call host or a server. Figure 7 , the electronic device includes, for example: a processor 600 and a memory 620;

[0156] If the electronic device is used as the RPA on-duty host, then:

[0157] The processor 600 is used to read the program in the memory 620 and execute the following process:

[0158] Obtain alarm record information from the target on-duty host;

[0159] Acquire a video stream corresponding to the alarm record information and monitoring information reported by an IoT device corresponding to the alarm record information from the target on-duty host; and determine a fusion analysis result corresponding to the alarm record information; wherein the fusion analysis result is obtained based on a first analysis result and a second analysis result, the first analysis result is a detection result obtained by detecting the video stream, and the second analysis result is an analysis result obtained by analyzing the monitoring information;

[0160] The fusion analysis result corresponding to the alarm record information is matched with the preset on-duty handling rules, and the corresponding handling operation is performed according to the matching result.

[0161] In some embodiments, obtaining alarm record information from the target on-duty host includes:

[0162] The optical character recognition (OCR) technology is used to identify the on-duty client interface in the mirror desktop screen of the target on-duty host to obtain alarm record information.

[0163] In some embodiments, determining the fusion analysis result corresponding to the alarm record information includes:

[0164] Sending the video stream and the monitoring information to a preset multi-dimensional analysis server;

[0165] Receiving a fusion analysis result corresponding to the alarm record information sent by the multidimensional analysis server;

[0166] Among them, the fusion analysis result is obtained by the multidimensional analysis server based on the first analysis result and the second analysis result, the first analysis result is the detection result obtained by the video intelligent analysis module in the multidimensional analysis server to detect the video stream, and the second analysis result is the analysis result obtained by the Internet of Things data analysis module in the multidimensional analysis server to analyze the monitoring information.

[0167] If the electronic device is used as a multi-dimensional analysis server, then:

[0168] The processor 600 is used to read the program in the memory 620 and execute the following process:

[0169] Obtaining a video stream corresponding to the alarm record information sent by a Robotic Process Automation (RPA) on-duty host, and monitoring information reported by an IoT device corresponding to the alarm record information; wherein the alarm record information is obtained by the RPA on-duty host from a target on-duty host;

[0170] Determine a fusion analysis result corresponding to the alarm record information, and send it to the RPA on-duty host; wherein the fusion analysis result is obtained based on a first analysis result and a second analysis result, the first analysis result is a detection result obtained by detecting the video stream, and the second analysis result is an analysis result obtained by analyzing the monitoring information.

[0171] In some embodiments, analyzing the monitoring information includes:

[0172] Based on the monitoring information reported by the IoT device corresponding to the alarm record information, determine the monitoring information within a time period of a preset length corresponding to the monitoring information at the i-th moment; wherein the monitoring information at the i-th moment is the monitoring information at any moment reported by the IoT device corresponding to the alarm record information;

[0173] By fitting the monitoring information in the time period, a first fitting curve is obtained, and based on the first fitting curve, a first fitting residual of the monitoring information at the i-th moment in the time period is determined;

[0174] Eliminate the monitoring information at the i-th moment in the time period, and fit the remaining monitoring information in the time period to obtain a second fitting curve, and determine a second fitting residual of the monitoring information at the i-th moment in the time period based on the second fitting curve;

[0175] A third fitting curve is obtained by fitting the prediction alarm information within the time period, and a third fitting residual of the monitoring information at the i-th moment in the time period is determined based on the third fitting curve; wherein the prediction alarm information is the prediction alarm information output by the neural network model by inputting the monitoring information within the time period into a preset neural network model;

[0176] Based on the first fitting residual, the second fitting residual, and the third fitting residual, determining the authenticity parameter of the monitoring information at the i-th moment as the alarm information;

[0177] Determining a parameter of a true contribution degree of the monitoring information at the i-th moment to the time period based on the first fitting residual and the second fitting residual;

[0178] Based on the authenticity parameter and the real contribution degree parameter, finally determining the authenticity degree parameter of the monitoring information at the i-th moment as the alarm information;

[0179] When the authenticity parameter is greater than or equal to a preset threshold, the monitoring information at the i-th moment is determined to be true alarm information.

[0180] In some embodiments, determining the actual contribution degree parameter of the monitoring information at the i-th moment to the time period based on the first fitting residual and the second fitting residual includes:

[0181] Determining an initial true contribution degree parameter of the monitoring information at the i-th moment to the time period based on the first fitting residual and the second fitting residual;

[0182] The initial true contribution degree parameter is normalized to finally obtain the true contribution degree parameter of the monitoring information at the i-th moment to the time period.

[0183] The transceiver 610 is configured to receive and send data under the control of the processor 600 .

[0184] Among them, Figure 7In the embodiment, the bus architecture may include any number of interconnected buses and bridges, specifically one or more processors represented by processor 600 and various circuits of memory represented by memory 620 are linked together. The bus architecture may also link together various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface. The transceiver 610 may be a plurality of components, namely, a transmitter and a receiver, providing a unit for communicating with various other devices on a transmission medium, including wireless channels, wired channels, optical cables, and other transmission media. For different user devices, the user interface 630 may also be an interface capable of externally and internally connecting required devices, and the connected devices include but are not limited to a keypad, a display, a speaker, a microphone, a joystick, and the like.

[0185] The processor 600 is responsible for managing the bus architecture and general processing, and the memory 620 can store data used by the processor 600 when performing operations.

[0186] In some embodiments, the processor 600 may be a CPU (central processing unit), an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array) or a CPLD (Complex Programmable Logic Device), and the processor may also adopt a multi-core architecture.

[0187] The processor calls the computer program stored in the memory to execute any of the methods provided in the embodiments of the present application according to the obtained executable instructions. The processor and the memory can also be arranged physically separately.

[0188] It should be noted here that the above-mentioned device provided in the embodiment of the present application can implement all the method steps implemented in the above-mentioned method embodiment, and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as those in the method embodiment will not be described in detail here.

[0189] See also Figure 8 On the RPA on-call host side, an alarm information processing device provided in an embodiment of the present application may be, for example, the RPA on-call host itself or a device in the RPA on-call host. An alarm information processing device provided in an embodiment of the present application includes:

[0190] The alarm record acquisition unit 11 is used to obtain the alarm record information from the target on-duty host;

[0191] The fusion analysis result acquisition unit 12 is used to obtain the video stream corresponding to the alarm record information and the monitoring information reported by the Internet of Things device corresponding to the alarm record information from the target on-duty host; and determine the fusion analysis result corresponding to the alarm record information; wherein the fusion analysis result is obtained based on the first analysis result and the second analysis result, the first analysis result is the detection result obtained by detecting the video stream, and the second analysis result is the analysis result obtained by analyzing the monitoring information;

[0192] The handling rule matching unit 13 is used to match the fusion analysis result corresponding to the alarm record information with the preset on-duty handling rule, and perform corresponding handling operations according to the matching result.

[0193] In some embodiments, obtaining alarm record information from the target on-duty host includes:

[0194] The optical character recognition (OCR) technology is used to identify the on-duty client interface in the mirror desktop screen of the target on-duty host to obtain alarm record information.

[0195] In some embodiments, determining the fusion analysis result corresponding to the alarm record information includes:

[0196] Sending the video stream and the monitoring information to a preset multi-dimensional analysis server;

[0197] Receiving a fusion analysis result corresponding to the alarm record information sent by the multidimensional analysis server;

[0198] Among them, the fusion analysis result is obtained by the multidimensional analysis server based on the first analysis result and the second analysis result, the first analysis result is the detection result obtained by the video intelligent analysis module in the multidimensional analysis server to detect the video stream, and the second analysis result is the analysis result obtained by the Internet of Things data analysis module in the multidimensional analysis server to analyze the monitoring information.

[0199] Correspondingly, on the server side, see Fig. 9 The embodiment of the present application provides an alarm information processing device, which may be, for example, the multidimensional analysis server itself, or a part of the multidimensional analysis server. The embodiment of the present application provides an alarm information processing device, including:

[0200] The alarm information acquisition unit 21 is used to acquire the video stream corresponding to the alarm record information sent by the Robotic Process Automation (RPA) on-duty host, and the monitoring information reported by the IoT device corresponding to the alarm record information; wherein the alarm record information is acquired by the RPA on-duty host from the target on-duty host;

[0201] The fusion analysis result determination unit 22 is used to determine the fusion analysis result corresponding to the alarm record information and send it to the RPA on-duty host; wherein the fusion analysis result is obtained based on the first analysis result and the second analysis result, the first analysis result is the detection result obtained by detecting the video stream, and the second analysis result is the analysis result obtained by analyzing the monitoring information.

[0202] In some embodiments, the fusion analysis result determination unit 22, see Fig.10 ,include:

[0203] A video intelligent analysis module 31, configured to detect the video stream corresponding to the alarm record information, and obtain the detection result as the first analysis result;

[0204] The Internet of Things data analysis module 32 is used to analyze the monitoring information reported by the Internet of Things device corresponding to the alarm record information, and the obtained analysis result is used as the second analysis result;

[0205] The fusion module 33 fuses the first analysis result and the second analysis result to obtain a fused analysis result.

[0206] In some embodiments, the IoT data analysis module 32 analyzes the monitoring information, including:

[0207] Based on the monitoring information reported by the IoT device corresponding to the alarm record information, determine the monitoring information within a time period of a preset length corresponding to the monitoring information at the i-th moment; wherein the monitoring information at the i-th moment is the monitoring information at any moment reported by the IoT device corresponding to the alarm record information;

[0208] By fitting the monitoring information in the time period, a first fitting curve is obtained, and based on the first fitting curve, a first fitting residual of the monitoring information at the i-th moment in the time period is determined;

[0209] Eliminate the monitoring information at the i-th moment in the time period, and fit the remaining monitoring information in the time period to obtain a second fitting curve, and determine a second fitting residual of the monitoring information at the i-th moment in the time period based on the second fitting curve;

[0210] A third fitting curve is obtained by fitting the prediction alarm information within the time period, and a third fitting residual of the monitoring information at the i-th moment in the time period is determined based on the third fitting curve; wherein the prediction alarm information is the prediction alarm information output by the neural network model by inputting the monitoring information within the time period into a preset neural network model;

[0211] Based on the first fitting residual, the second fitting residual, and the third fitting residual, determining the authenticity parameter of the monitoring information at the i-th moment as the alarm information;

[0212] Determining a parameter of a true contribution degree of the monitoring information at the i-th moment to the time period based on the first fitting residual and the second fitting residual;

[0213] Based on the authenticity parameter and the real contribution degree parameter, finally determining the authenticity degree parameter of the monitoring information at the i-th moment as the alarm information;

[0214] When the authenticity parameter is greater than or equal to a preset threshold, the monitoring information at the i-th moment is determined to be true alarm information.

[0215] In some embodiments, determining the actual contribution degree parameter of the monitoring information at the i-th moment to the time period based on the first fitting residual and the second fitting residual includes:

[0216] Determining an initial true contribution degree parameter of the monitoring information at the i-th moment to the time period based on the first fitting residual and the second fitting residual;

[0217] The initial true contribution degree parameter is normalized to finally obtain the true contribution degree parameter of the monitoring information at the i-th moment to the time period.

[0218] It should be noted that the division of units in the embodiments of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation. In addition, each functional unit in each embodiment of the present application may be integrated into a processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0219] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) or a processor (processor) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (RandomAccess Memory, RAM), disk or optical disk and other media that can store program code.

[0220] Any of the devices or apparatuses provided in the embodiments of the present application may specifically be a desktop computer, a portable computer, a smart phone, a tablet computer, a personal digital assistant (PDA), etc. It may include a central processing unit (CPU), a memory, an input / output device, etc. The input device may include a keyboard, a mouse, a touch screen, etc. The output device may include a display device, such as a liquid crystal display (LCD), a cathode ray tube (CRT), etc.

[0221] The memory may include a read-only memory (ROM) and a random access memory (RAM), and provides the processor with program instructions and data stored in the memory. In an embodiment of the present application, the memory may be used to store the program of any of the methods provided in the embodiments of the present application.

[0222] The processor calls the program instructions stored in the memory, and the processor is used to execute any of the methods provided in the embodiments of the present application according to the obtained program instructions.

[0223] The present application embodiment also provides a computer program product or computer program, which includes a computer instruction, which is stored in a computer-readable storage medium. The processor of the computer device reads the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction so that the computer device executes any of the methods described in the above embodiments. The program product can use any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, - but not limited to - an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of readable storage media (non-exhaustive list) include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0224] The embodiment of the present application provides a computer-readable storage medium for storing computer program instructions used by the apparatus provided in the embodiment of the present application, which includes a program for executing any of the methods provided in the embodiment of the present application. The computer-readable storage medium may be a non-transitory computer-readable medium.

[0225] The computer-readable storage medium can be any available medium or data storage device that can be accessed by a computer, including but not limited to magnetic storage (such as floppy disks, hard disks, magnetic tapes, magneto-optical disks (MO), etc.), optical storage (such as CD, DVD, BD, HVD, etc.), and semiconductor storage (such as ROM, EPROM, EEPROM, non-volatile memory (NANDFLASH), solid-state drive (SSD)), etc.

[0226] It should be understood that:

[0227] The access technology through which entities in the communication network transmit traffic can be any suitable current or future technology, such as WLAN (Wireless Local Access Network), WiMAX (Worldwide Interoperability for Microwave Access), LTE, LTE-A, 5G, Bluetooth, infrared, etc.; in addition, the embodiments can also apply wired technology, for example, IP-based access technology, such as a wired network or a fixed line.

[0228] Embodiments suitable for being implemented as software code or a portion thereof and running using a processor or processing functionality are independent of the software code and may be specified using any known or future developed programming language, such as a high-level programming language such as objective-C, C, C++, C#, Java, Python, Javascript, other scripting languages, etc., or a low-level programming language such as machine language or assembler.

[0229] The implementation of the embodiments is hardware independent and may be implemented using any known or future developed hardware technology or any mixture thereof, such as a microprocessor or CPU (central processing unit), MOS (metal oxide semiconductor), CMOS (complementary MOS), BiMOS (bipolar MOS), BiCMOS (bipolar CMOS), ECL (emitter coupled logic) and / or TTL (transistor-transistor logic).

[0230] Embodiments may be implemented as separate devices, apparatuses, units, components, or functions, or in a distributed manner, for example, one or more processors or processing functions may be used or shared in a process, or one or more processing segments or processing portions may be used and shared in a process, wherein one physical processor or more than one physical processor may be used to implement one or more processing portions dedicated to a specific process as described.

[0231] The device may be implemented by a semiconductor chip, a chipset, or a (hardware) module including such a chip or chipset.

[0232] The embodiments may also be implemented as any combination of hardware and software, such as ASIC (Application Specific IC (Integrated Circuit)) components, FPGA (Field Programmable Gate Array) or CPLD (Complex Programmable Logic Device) components or DSP (Digital Signal Processor) components.

[0233] The embodiments may also be implemented as a computer program product including a computer usable medium having computer readable program code embodied therein, the computer readable program code being adapted to perform the processes as described in the embodiments, wherein the computer usable medium may be a non-transitory medium.

[0234] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) that contain computer-usable program code.

[0235] The present application is 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 generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. 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.

[0236] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate 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 A function specified in one or more boxes.

[0237] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0238] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A method for processing alarm information, characterized in that: The method comprises: Obtain alarm record information from the target on-duty host; Acquire a video stream corresponding to the alarm record information and monitoring information reported by an IoT device corresponding to the alarm record information from the target on-duty host; and determine a fusion analysis result corresponding to the alarm record information; wherein the fusion analysis result is obtained based on a first analysis result and a second analysis result, the first analysis result is a detection result obtained by detecting the video stream, and the second analysis result is an analysis result obtained by analyzing the monitoring information; The fusion analysis result corresponding to the alarm record information is matched with the preset on-duty handling rules, and the corresponding handling operation is performed according to the matching result.

2. The method according to claim 1, characterized in that: The step of obtaining alarm record information from the target on-duty host includes: The optical character recognition (OCR) technology is used to identify the on-duty client interface in the mirror desktop screen of the target on-duty host to obtain alarm record information.

3. The method according to claim 1, characterized in that The determining of the fusion analysis result corresponding to the alarm record information includes: Sending the video stream and the monitoring information to a preset multi-dimensional analysis server; Receiving a fusion analysis result corresponding to the alarm record information sent by the multidimensional analysis server; Among them, the fusion analysis result is obtained by the multidimensional analysis server based on the first analysis result and the second analysis result, the first analysis result is the detection result obtained by the video intelligent analysis module in the multidimensional analysis server to detect the video stream, and the second analysis result is the analysis result obtained by the Internet of Things data analysis module in the multidimensional analysis server to analyze the monitoring information.

4. A method for processing alarm information, characterized in that: The method comprises: Obtaining a video stream corresponding to the alarm record information sent by a Robotic Process Automation (RPA) on-duty host, and monitoring information reported by an IoT device corresponding to the alarm record information; wherein the alarm record information is obtained by the RPA on-duty host from a target on-duty host; Determine a fusion analysis result corresponding to the alarm record information, and send it to the RPA on-duty host; wherein the fusion analysis result is obtained based on a first analysis result and a second analysis result, the first analysis result is a detection result obtained by detecting the video stream, and the second analysis result is an analysis result obtained by analyzing the monitoring information.

5. The method according to claim 4, characterized in that Analyzing the monitoring information includes: Based on the monitoring information reported by the IoT device corresponding to the alarm record information, determine the monitoring information within a time period of a preset length corresponding to the monitoring information at the i-th moment; wherein the monitoring information at the i-th moment is the monitoring information at any moment reported by the IoT device corresponding to the alarm record information; By fitting the monitoring information in the time period, a first fitting curve is obtained, and based on the first fitting curve, a first fitting residual of the monitoring information at the i-th moment in the time period is determined; Eliminate the monitoring information at the i-th moment in the time period, and fit the remaining monitoring information in the time period to obtain a second fitting curve, and determine a second fitting residual of the monitoring information at the i-th moment in the time period based on the second fitting curve; A third fitting curve is obtained by fitting the prediction alarm information within the time period, and a third fitting residual of the monitoring information at the i-th moment in the time period is determined based on the third fitting curve; wherein the prediction alarm information is the prediction alarm information output by the neural network model by inputting the monitoring information within the time period into a preset neural network model; Based on the first fitting residual, the second fitting residual, and the third fitting residual, determining the authenticity parameter of the monitoring information at the i-th moment as the alarm information; Determining a parameter of a true contribution degree of the monitoring information at the i-th moment to the time period based on the first fitting residual and the second fitting residual; Based on the authenticity parameter and the real contribution degree parameter, finally determining the authenticity degree parameter of the monitoring information at the i-th moment as the alarm information; When the authenticity parameter is greater than or equal to a preset threshold, the monitoring information at the i-th moment is determined to be true alarm information.

6. The method according to claim 5, characterized in that Determining a parameter of a true contribution degree of the monitoring information at the i-th moment to the time period based on the first fitting residual and the second fitting residual includes: Determining an initial true contribution degree parameter of the monitoring information at the i-th moment to the time period based on the first fitting residual and the second fitting residual; The initial true contribution degree parameter is normalized to finally obtain the true contribution degree parameter of the monitoring information at the i-th moment to the time period.

7. An alarm information processing device, characterized in that: The device comprises: An alarm record acquisition unit, used to acquire alarm record information from a target on-duty host; A fusion analysis result acquisition unit is used to acquire, from the target on-duty host, a video stream corresponding to the alarm record information and monitoring information reported by an IoT device corresponding to the alarm record information; and determine a fusion analysis result corresponding to the alarm record information; wherein the fusion analysis result is obtained based on a first analysis result and a second analysis result, the first analysis result being a detection result obtained by detecting the video stream, and the second analysis result being an analysis result obtained by analyzing the monitoring information; The processing rule matching unit is used to match the fusion analysis result corresponding to the alarm record information with the preset on-duty processing rule, and perform corresponding processing operations according to the matching result.

8. An alarm information processing device, characterized in that: The device comprises: An alarm information acquisition unit, used to acquire a video stream corresponding to the alarm record information sent by a Robotic Process Automation (RPA) on-duty host, and monitoring information reported by an IoT device corresponding to the alarm record information; wherein the alarm record information is acquired by the RPA on-duty host from a target on-duty host; A fusion analysis result determination unit is used to determine a fusion analysis result corresponding to the alarm record information and send it to the RPA on-duty host; wherein the fusion analysis result is obtained based on a first analysis result and a second analysis result, the first analysis result is a detection result obtained by detecting the video stream, and the second analysis result is an analysis result obtained by analyzing the monitoring information.

9. An electronic device, characterized in that: include: A memory for storing program instructions; A processor, configured to call the program instructions stored in the memory, and execute the method according to any one of claims 1 to 6 according to the obtained program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable the computer to execute the method according to any one of claims 1 to 6.

Images