Mining monitoring intelligent recommendation method and device

Abstract

The invention provides a mining monitoring intelligent recommendation method and device. The method comprises the following steps: acquiring a video pushing rule base; obtaining multiple paths of monitoring videos, and performing risk prediction on the multiple paths of monitoring videos based on an artificial intelligence AI large model to obtain prediction results of the multiple paths of monitoring videos; based on the prediction result, determining at least one path of to-be-pushed monitoring video from the plurality of paths of monitoring videos, the to-be-pushed monitoring video satisfying at least one pushing rule in a video pushing rule base; and according to the first monitoring device corresponding to the to-be-pushed monitoring video, pushing the monitoring video of the first monitoring device to the terminal device. Therefore, according to the scheme, accurate pushing of the monitoring video can be realized, so that the monitoring value is improved, the monitoring efficiency is further improved, and the safety of coal mine production is promoted.

Description

Technical Field

[0001] The present application relates to the field of intelligent mining technology, and in particular to a method and device for intelligent mine monitoring recommendation. Background Art

[0002] The explosive growth of underground coal mine surveillance cameras has generated a massive amount of video information in real-time. However, this information is largely useless and only becomes meaningful when a specific event of interest occurs. Current video surveillance systems, both artificial intelligence (AI) and non-AI, simply display camera footage indiscriminately, failing to accurately push targeted video footage. Summary of the Invention

[0003] The purpose of this application is to solve one of the technical problems in the related art at least to a certain extent.

[0004] To this end, the first purpose of this application is to propose a monitoring intelligent recommendation method for mines to achieve intelligent push of monitoring videos, thereby improving the value and efficiency of monitoring.

[0005] The second purpose of this application is to provide a monitoring intelligent recommendation device for mines.

[0006] To achieve the above-mentioned purpose, the first embodiment of the present application proposes a monitoring intelligent recommendation method for mines, including: obtaining a video push rule library; obtaining multiple monitoring videos, and performing risk prediction on the multiple monitoring videos based on an artificial intelligence AI model to obtain prediction results of the multiple monitoring videos; based on the prediction results, determining at least one monitoring video to be pushed from the multiple monitoring videos, wherein the monitoring video to be pushed satisfies at least one push rule in the video push rule library; according to the first monitoring device corresponding to the monitoring video to be pushed, pushing the monitoring video of the first monitoring device to the terminal device.

[0007] To achieve the above-mentioned purpose, the second embodiment of the present application proposes a monitoring intelligent recommendation device for mines, including: an acquisition module for acquiring a video push rule library; a prediction module for acquiring multiple monitoring videos, and performing risk prediction on the multiple monitoring videos based on an artificial intelligence AI model to obtain prediction results of the multiple monitoring videos; a determination module for determining at least one monitoring video to be pushed from the multiple monitoring videos based on the prediction results, wherein the monitoring video to be pushed satisfies at least one push rule in the video push rule library; a push module for pushing the monitoring video of the first monitoring device corresponding to the monitoring video to be pushed to the terminal device.

[0008] The intelligent monitoring recommendation method and device provided in this application obtains a video push rule library and, based on the prediction results of multiple monitoring videos, determines at least one monitoring video to be pushed from multiple monitoring videos. Furthermore, based on the first monitoring device corresponding to the monitoring video to be pushed, the monitoring video of the first monitoring device is pushed to the terminal device, thereby realizing intelligent push of monitoring videos. By determining a monitoring video that meets at least one push rule in the video push rule library as the monitoring video to be pushed, accurate push of monitoring videos can be realized, thereby increasing the value of monitoring, further improving the efficiency of monitoring, and promoting the safety of coal mine production.

[0009] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0011] Figure 1 A flowchart of an intelligent mine monitoring recommendation method provided in an embodiment of the present application;

[0012] Figure 2 A flowchart of another intelligent mine monitoring recommendation method provided in an embodiment of the present application;

[0013] Figure 3 This is a structural diagram of a mining monitoring intelligent recommendation device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0014] The following describes in detail embodiments of the present application. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0015] The following describes the intelligent recommendation method and device for monitoring mines according to the embodiments of the present application with reference to the accompanying drawings.

[0016] Figure 1 This is a flow chart of a mine monitoring intelligent recommendation method provided by an embodiment of the present application. Figure 1 As shown, the monitoring intelligent recommendation method for mines in the embodiment of the present application includes but is not limited to the following steps:

[0017] S101, obtaining a video push rule library.

[0018] It should be noted that the execution subject of the intelligent mine monitoring recommendation method provided in the embodiment of the present application is an electronic device, which can be a terminal device. Optionally, the terminal device can be a mobile electronic device or a non-mobile electronic device. Exemplarily, the mobile electronic device can be a mobile phone, a tablet computer, a laptop computer, a PDA, an in-vehicle electronic device, a wearable device, an ultra-mobile personal computer (UMPC), a netbook or a personal digital assistant (PDA), etc., and the non-mobile electronic device can be a personal computer (PC), a television, etc. The embodiment of the present application does not make any specific limitations.

[0019] In an embodiment of the present application, the video push rule library is configured according to different push rules to obtain a video push rule library, so that the video push rule library contains a variety of different types of push rules, thereby improving the accuracy of video push.

[0020] Optionally, the video push rule library is configured, including the following possible implementations:

[0021] Method 1: According to the coal mine production process, summarize the general rules of coal mines and configure the general rules into the video push rule library.

[0022] In some embodiments, a large artificial intelligence (AI) model can be used to summarize general rules for coal mines based on the coal mine production process.

[0023] Alternatively, information related to coal mine production can be obtained from online platforms to understand the coal mine's production process. This process can then be summarized and analyzed using the AI model to obtain general rules for coal mines. Furthermore, a video push rule library can be configured based on these general rules.

[0024] Optionally, general rules can be related to the operations of coal mine production personnel or the coal mine's environmental information. For example, general rules can include: personnel being present at any monitoring point for a long time; monitoring equipment being offline for a long time, displaying distorted images, or having its angle adjusted; large water puddles in key areas of the coal mine; foreign objects being present at any monitoring point for a long time; and personnel violating operational regulations.

[0025] Method 2: Determine the push rules corresponding to different types of algorithm alarm conditions and configure the push rules into the video push rule library.

[0026] It is understandable that multiple monitoring videos of a coal mine can be collected based on multiple monitoring devices, and the multiple monitoring videos can be detected and analyzed based on different types of algorithms to detect and analyze abnormal situations in the monitoring videos.

[0027] Algorithm alarm conditions refer to the conditions that trigger an alarm. For example, for a persistent, non-instantaneous algorithmic alarm, if the alarm is occurring and its duration reaches the set time threshold, the corresponding surveillance video will be pushed. In other words, the non-instantaneous algorithmic alarm condition is when the alarm is occurring and its duration reaches the set time threshold.

[0028] In some embodiments, by obtaining different types of algorithm alarm conditions and configuring the video push rule library according to the algorithm alarm conditions, optionally, corresponding push rules can be generated according to different types of algorithm alarm conditions and configured into the video push rule library.

[0029] Method 3: Determine user preference rules and configure the user preference rules into the video push rule library.

[0030] In some embodiments, the video push rule library can be personalized to enable accurate push of surveillance videos. Optionally, the user interacts with the AI big model so that the AI big model determines user preference rules based on the interaction information.

[0031] In some embodiments, preference information can be input into a terminal device, and the terminal device interacts with the AI big model, using the preference information as interaction information, so that the AI big model determines user preference rules from the interaction information.

[0032] In other words, user preference rules can be determined by obtaining interaction information between the terminal device and the AI large model and based on this interaction information. Alternatively, the user can interact with the AI large model through the terminal device by text input or by voice input.

[0033] Furthermore, the video push rule base may be configured according to the user preference rules. By configuring the user preference rules in the video push rule base, the configuration of the video push rule base is achieved.

[0034] In some embodiments, in order to ensure the timeliness of push rules in the video push rule library, invalid push rules can be deleted from the video push rule library to implement regular cleaning of the video push rule library and avoid conflicts in the push rules.

[0035] Optionally, by performing validity detection on the push rules in the video push rule library, invalid rules are obtained from the push rules in the video push rule library, and the invalid rules are cleared regularly to ensure the validity of the push rules.

[0036] That is, by performing a validity check on the push rules in the video push rule library, a validity check result can be determined, which indicates whether the push rule is valid. If the push rule is not valid, the push rule is determined to be an invalid rule, so that the invalid rule can be cleaned up regularly.

[0037] S102, obtain multiple surveillance videos, and perform risk prediction on the multiple surveillance videos based on the artificial intelligence (AI) big model to obtain prediction results for the multiple surveillance videos.

[0038] In some embodiments, real-time data collection can be performed underground in a coal mine based on multiple monitoring devices to obtain multi-channel monitoring videos corresponding to multiple monitoring devices, and a large AI model can be used to perform risk prediction on the multi-channel monitoring videos to analyze the multi-channel monitoring videos and obtain prediction results for the multi-channel monitoring videos.

[0039] Optionally, the prediction result of each monitoring video may include whether there is a risk event in the monitoring video, and the risk level of the risk event.

[0040] In some embodiments, by inputting multiple surveillance videos into the AI big model, the AI big model can predict whether there are risk events in the multiple surveillance videos, and when there are risk events, predict the risk level of the risk events, thereby obtaining the prediction results of the multiple surveillance videos.

[0041] S103: Based on the prediction result, determine at least one surveillance video to be pushed from the multiple surveillance videos, where the surveillance video to be pushed satisfies at least one push rule in the video push rule library.

[0042] In some embodiments, the prediction result is matched with the push rules in the video push rule library to determine whether the prediction result satisfies at least one push rule in the video push rule library, and when at least one push rule in the video push rule library is satisfied, the surveillance video corresponding to the prediction result is determined as the surveillance video to be pushed.

[0043] For example, assume that there are surveillance video A, surveillance video B and surveillance video C, and their corresponding prediction results are: prediction result A, prediction result B and prediction result C. If prediction result A meets push rule 1 and push rule 2 in the video push rule library, surveillance video A is determined to be the surveillance video to be pushed; if prediction result B meets push rule 3 in the video push rule library, surveillance video B is determined to be the surveillance video to be pushed; if prediction result C does not meet the push rules, surveillance video C will not be pushed.

[0044] S104: Push the surveillance video of the first surveillance device to the terminal device according to the first surveillance device corresponding to the surveillance video to be pushed.

[0045] In some embodiments, after determining at least one monitoring video to be pushed, the first monitoring device corresponding to the at least one monitoring video to be pushed is determined, that is, the first monitoring device collects video underground in the coal mine to obtain the monitoring video.

[0046] In some embodiments, since there is at least one first monitoring device, the first monitoring devices may be sorted so as to push the monitoring videos of the first monitoring devices to the terminal device in sequence.

[0047] In some embodiments, the first monitoring devices may be ranked based on their own priorities to determine a push order, and the surveillance videos of the first monitoring devices may be pushed to the terminal device in the ranked push order. The first monitoring devices may also be ranked based on the predicted risk level of the videos to be pushed to determine a push order, and the surveillance videos of the first monitoring devices may be pushed to the terminal device in the ranked push order.

[0048] In the intelligent monitoring recommendation method for mines provided in the embodiment of the present application, by obtaining a video push rule library and determining at least one monitoring video to be pushed from the multiple monitoring videos based on the prediction results of the multiple monitoring videos. Furthermore, based on the first monitoring device corresponding to the monitoring video to be pushed, the monitoring video of the first monitoring device is pushed to the terminal device, thereby realizing intelligent push of the monitoring video. By determining the monitoring video that meets at least one push rule in the video push rule library as the monitoring video to be pushed, it is possible to achieve accurate push of the monitoring video, thereby increasing the value of monitoring, further improving the efficiency of monitoring, and promoting the safety of coal mine production.

[0049] Figure 2 This is a flow chart of a mine monitoring intelligent recommendation method provided by an embodiment of the present application. Figure 2 As shown, the monitoring intelligent recommendation method for mines in the embodiment of the present application includes but is not limited to the following steps:

[0050] S201, obtaining a video push rule library.

[0051] In the embodiment of the present application, the implementation method of step S201 can be implemented by any method in the various embodiments of the present application, which is not limited here and will not be repeated.

[0052] S202, obtain multiple surveillance videos, and perform risk prediction on the multiple surveillance videos based on the artificial intelligence (AI) big model to obtain prediction results for the multiple surveillance videos.

[0053] In the embodiment of the present application, the implementation method of step S202 can be implemented by any method in the various embodiments of the present application, which is not limited here and will not be repeated.

[0054] S203: Based on the prediction result, determine at least one surveillance video to be pushed from the multiple surveillance videos, where the surveillance video to be pushed satisfies at least one push rule in the video push rule library.

[0055] In the embodiment of the present application, the implementation method of step S203 can be implemented by using any method in the various embodiments of the present application, which is not limited here and will not be repeated.

[0056] S204: Generate a device push list based on the device identification of the first monitoring device.

[0057] In some embodiments, if at least one monitoring video to be pushed determined based on the prediction results corresponds to at least one first monitoring device, a device push list can be generated based on the at least one first monitoring device to push the monitoring video of the first monitoring device according to the device push list.

[0058] Optionally, the device identification of the first monitoring device is obtained, and a device push list including the device identification is generated according to the device identification.

[0059] Optionally, the device identifier may be a unique identification code of the first monitoring device, which is not specifically limited in the embodiment of the present application.

[0060] S205: Push sorting is performed on the first monitoring device in the device push list.

[0061] In some embodiments, in order to clarify the push order, the first monitoring device can be pushed in a sorted order so that the monitoring videos of the first monitoring device are pushed sequentially according to the order of the first monitoring device in the device push list.

[0062] In some embodiments, the device identifiers in the device push list may be sorted according to the priority of the first monitoring device or the predicted result of the monitoring video to be pushed.

[0063] Optionally, a first monitoring device with the highest priority may be determined according to the priority of the first monitoring device, and the device identifier of the first monitoring device may be sorted to the first position in the device push list.

[0064] That is to say, the higher the priority of the first monitoring device, the higher its position in the device push list.

[0065] For example, assume that there are surveillance videos 1, 2, and 3 to be pushed, and their corresponding first monitoring device identifiers are identifier 1, identifier 2, and identifier 3, respectively. The priorities of the first monitoring devices are priority 1, priority 2, and priority 3, respectively. If priority 1 is greater than priority 3, which is greater than priority 2, then the order of push notifications in the device push list is identifier 1, identifier 3, and identifier 2.

[0066] Optionally, the risk level of the surveillance video to be pushed can be determined based on the prediction results of the surveillance video to be pushed, by determining the surveillance video to be pushed with the highest risk level, and sorting the device identifier of the first surveillance device corresponding to the surveillance video to be pushed to the first position in the device push list.

[0067] That is to say, the higher the risk level of the surveillance video to be pushed, the higher the position of the corresponding first surveillance device in the device push list.

[0068] For example, assume that there are surveillance videos 1, 2, and 3 to be pushed, and their corresponding first monitoring device identifiers are identifier 1, identifier 2, and identifier 3, respectively, and their corresponding risk levels are level 1, level 2, and level 3, respectively. If level 2 is greater than level 1, which is greater than level 3, then the order of push notifications in the device push list is identifier 2, identifier 1, and identifier 3.

[0069] S206: Push the monitoring video of the first monitoring device to the terminal device according to the push order.

[0070] In some embodiments, the monitoring video of the first monitoring device can be pushed to the terminal device in sequence according to the push order. The push order of the first monitoring device can be determined based on the device identifier of the first monitoring device in the push order, so that the monitoring video of the first monitoring device is pushed to the terminal device according to the push order.

[0071] In some embodiments, in order to improve the intelligence of monitoring, before pushing the monitoring video of the first monitoring device to the terminal device, the subsequent monitoring video of the first monitoring device can also be tracked and analyzed to determine from the first monitoring device a second monitoring device whose subsequent monitoring video no longer meets the push rules in the video push rule library, and cancel the push to the second monitoring device.

[0072] That is, the first monitoring device that does not meet the push rule is determined to be the second monitoring device, and the push notification is revoked for the second monitoring device. Optionally, when the push notification is revoked for the second monitoring device, the device identifier of the second monitoring device is deleted from the device push list, and the monitoring video is pushed according to the push order of the device push list after deletion.

[0073] For example, the device identifiers in the device push list are identifier 2, identifier 1, and identifier 3, where the first monitoring device corresponding to identifier 1 is the second monitoring device that does not meet the push rules. In this case, identifier 1 is deleted from the device push list, so that when pushing the monitoring video, the monitoring video of the first monitoring device is pushed to the terminal device in the push order of identifier 2 and identifier 3.

[0074] In the intelligent recommendation method for monitoring mines provided in the embodiment of the present application, the device push list of the first monitoring device is determined, and the first monitoring device in the device push list is pushed in a push order, so that the monitoring video of the first monitoring device is pushed to the terminal device according to the push order, thereby reducing the redundancy of the monitoring video, improving the efficiency of information processing, and further improving the monitoring efficiency.

[0075] Corresponding to the intelligent monitoring recommendation methods for mines proposed in the above-mentioned embodiments, an embodiment of the present application further proposes an intelligent monitoring recommendation device for mines. Since the intelligent monitoring recommendation device for mines proposed in the embodiment of the present application corresponds to the intelligent monitoring recommendation methods for mines proposed in the above-mentioned embodiments, the implementation methods of the above-mentioned intelligent monitoring recommendation methods for mines are also applicable to the intelligent monitoring recommendation device for mines proposed in the embodiment of the present application, and will not be described in detail in the following embodiments.

[0076] In order to implement the above embodiment, the present application also proposes a monitoring intelligent recommendation device for mines.

[0077] Figure 3 This is a structural diagram of a monitoring intelligent recommendation device for mines provided in an embodiment of the present application.

[0078] like Figure 3 As shown, the monitoring intelligent recommendation device 300 for the mine includes:

[0079] Acquisition module 301, used to obtain a video push rule library;

[0080] Prediction module 302 is used to obtain multiple surveillance videos and perform risk prediction on the multiple surveillance videos based on the artificial intelligence (AI) model to obtain prediction results for the multiple surveillance videos;

[0081] A determination module 303 is configured to determine, based on the prediction result, at least one surveillance video to be pushed from the multiple surveillance videos, wherein the surveillance video to be pushed satisfies at least one push rule in the video push rule library;

[0082] The push module 304 is configured to push the monitoring video of the first monitoring device to the terminal device according to the first monitoring device corresponding to the monitoring video to be pushed.

[0083] In a possible implementation of an embodiment of the present application, the acquisition module 301 is also used to: obtain the production process of the coal mine; summarize and analyze the production process based on the AI big model to obtain the general rules of the coal mine; and configure the video push rule library based on the general rules.

[0084] In a possible implementation of the embodiment of the present application, the acquisition module 301 is further used to: acquire different types of algorithm alarm conditions, and configure the video push rule library according to the algorithm alarm conditions.

[0085] In a possible implementation of an embodiment of the present application, the acquisition module 301 is also used to: obtain interaction information between the terminal device and the AI large model, and determine user preference rules based on the interaction information; and configure the video push rule library according to the user preference rules.

[0086] In a possible implementation of the embodiment of the present application, the acquisition module 301 is further used to: perform validity detection on the push rules in the video push rule library to obtain invalid rules from the push rules in the video push rule library, and perform periodic cleaning of the invalid rules.

[0087] In a possible implementation of an embodiment of the present application, the push module 304 is also used to: generate a device push list based on the device identification of the first monitoring device; push sort the first monitoring device in the device push list; and push the monitoring video of the first monitoring device to the terminal device according to the push sort.

[0088] In a possible implementation of the embodiment of the present application, the push module 304 is further configured to: sort the device identifiers in the device push list according to the priority of the first monitoring device or the predicted result of the monitoring video to be pushed.

[0089] In a possible implementation of an embodiment of the present application, the push module 304 is also used to: track and analyze subsequent monitoring videos of the first monitoring device; determine from the first monitoring device that the subsequent monitoring video no longer meets the push rules in the video push rule library of the second monitoring device, and cancel the push to the second monitoring device.

[0090] In a possible implementation of the embodiment of the present application, the push module 304 is further configured to: when it is determined to cancel the push to the second monitoring device, delete the device identifier of the second monitoring device from the device push list.

[0091] In the intelligent monitoring recommendation device for mines provided in the embodiment of the present application, by obtaining a video push rule library and determining at least one monitoring video to be pushed from the multiple monitoring videos based on the prediction results of the multiple monitoring videos. Furthermore, based on the first monitoring device corresponding to the monitoring video to be pushed, the monitoring video of the first monitoring device is pushed to the terminal device, thereby realizing intelligent push of monitoring videos. By determining a monitoring video that satisfies at least one push rule in the video push rule library as the monitoring video to be pushed, accurate push of monitoring videos can be realized, thereby increasing the value of monitoring, further improving the efficiency of monitoring, and promoting the safety of coal mine production.

[0092] It should be noted that the aforementioned explanation of the embodiment of the intelligent monitoring recommendation method for mines is also applicable to the intelligent monitoring recommendation device for mines in this embodiment, and will not be repeated here.

[0093] The collection, storage, use, processing, transmission, provision and application of user personal information involved in this application are in compliance with relevant laws and regulations and do not violate public order and good morals.

[0094] It is important to note that personal information collected from users should be used for legitimate and reasonable purposes and should not be shared or sold beyond these legitimate uses. Furthermore, such collection / sharing should be conducted only after receiving the user's informed consent, including but not limited to notifying the user to read the user agreement / user notice and sign an agreement / authorization that includes the relevant user information before using the feature. Furthermore, any necessary steps must be taken to safeguard and secure access to such personal information and ensure that others with access to personal information comply with its privacy policy and procedures.

[0095] This application contemplates providing implementation options for users to selectively block the use or access of personal information data. Specifically, this application contemplates providing hardware and / or software to prevent or block access to such personal information data. Risks can be minimized by limiting data collection and deleting data once it is no longer needed. Furthermore, where applicable, such personal information can be de-identified to protect user privacy.

[0096] In the descriptions of the foregoing embodiments, the reference terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" mean that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they are mutually inconsistent.

[0097] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of such features. Throughout the description of this application, "plurality" means at least two, for example, two, three, etc., unless otherwise specifically defined.

[0098] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may be performed out of the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present application belong.

[0099] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and programmable read-only memory (EPROM or flash memory), fiber optic devices, and a portable compact disc read-only memory (CDROM). Furthermore, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing it in another suitable manner if necessary, and then storing it in a computer memory.

[0100] It should be understood that various parts of the present application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used to implement: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0101] Those skilled in the art will understand that all or part of the steps in the method of the above embodiment can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0102] In addition, the functional units in the various embodiments of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into a module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0103] The storage medium mentioned above may be a read-only memory, a magnetic disk, or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application. Persons skilled in the art may make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.

Claims

1. A monitoring intelligent recommendation method for mines, characterized in that: The method comprises: Get the video push rule library; Acquire multiple surveillance videos, and perform risk prediction on the multiple surveillance videos based on an artificial intelligence (AI) model to obtain prediction results for the multiple surveillance videos; Based on the prediction result, determining at least one surveillance video to be pushed from the multiple surveillance videos, wherein the surveillance video to be pushed satisfies at least one push rule in the video push rule library; According to the first monitoring device corresponding to the monitoring video to be pushed, the monitoring video of the first monitoring device is pushed to the terminal device.

2. The method according to claim 1, characterized in that The method further comprises: Obtain the production process of coal mines; Summarize and analyze the production process based on the AI big model to obtain universal rules for the coal mine; Based on the general rules, the video push rule library is configured.

3. The method according to claim 1 or 2, characterized in that The method further comprises: Different types of algorithm alarm conditions are obtained, and the video push rule library is configured according to the algorithm alarm conditions.

4. The method according to claim 3, characterized in that The method further comprises: Obtaining interaction information between the terminal device and the AI large model, and determining user preference rules based on the interaction information; The video push rule library is configured according to the user preference rule.

5. The method according to claim 1, wherein The method further comprises: The push rules in the video push rule library are tested for validity, so as to obtain invalid rules from the push rules in the video push rule library, and the invalid rules are cleaned up regularly.

6. The method according to claim 1, 2 or 5, characterized in that: The step of pushing the monitoring video of the first monitoring device corresponding to the monitoring video to be pushed to the terminal device includes: generating a device push list based on the device identification of the first monitoring device; Push sorting for the first monitoring device in the device push list; According to the push order, the monitoring video of the first monitoring device is pushed to the terminal device.

7. The method according to claim 6, characterized in that The pushing order of the first monitoring device in the device push list includes: The device identifiers in the device push list are sorted according to the priority of the first monitoring device or the prediction result of the monitoring video to be pushed.

8. The method according to claim 6, characterized in that Before pushing the monitoring video of the first monitoring device to the terminal device, the method further includes: Tracking and analyzing subsequent surveillance videos of the first monitoring device; From the first monitoring device, it is determined that the subsequent monitoring video no longer meets the push rule in the video push rule library of the second monitoring device, and the push is revoked for the second monitoring device.

9. The method according to claim 8, characterized in that The method further comprises: When it is determined to cancel the push notification to the second monitoring device, the device identification of the second monitoring device is deleted from the device push list.

10. A monitoring intelligent recommendation device for mines, characterized in that: The device comprises: Acquisition module, used to obtain the video push rule library; A prediction module is used to obtain multiple surveillance videos and perform risk prediction on the multiple surveillance videos based on an artificial intelligence (AI) model to obtain prediction results for the multiple surveillance videos; a determination module, configured to determine, based on the prediction result, at least one surveillance video to be pushed from the multiple surveillance videos, wherein the surveillance video to be pushed satisfies at least one push rule in the video push rule library; The push module is used to push the monitoring video of the first monitoring device corresponding to the monitoring video to be pushed to the terminal device.

Images