Key event reminding method and related device, storage medium

Abstract

The application discloses a key event reminding method and related equipment and a storage medium. The key event reminding method comprises the following steps: acquiring monitoring data collected in real time by each data collection device; analyzing and summarizing the monitoring data based on the collection time being located in a first sliding window to obtain key event information of a first time period in which the first sliding window is currently located; performing similarity comparison on each key event information based on the first time period being located in a second sliding window to obtain semantic similarity between different key events in a second time period in which the second sliding window is currently located; in response to the semantic similarity between different key events satisfying a filtering condition related to a similarity threshold, merging corresponding key events to obtain a key event set; and generating key event reminding information based on the key event set. The above scheme can reduce the number of repeated alarms and the repeated presentation of similar events.

Description

Technical Field

[0001] This application relates to the field of event management technology, and in particular to a method for alerting critical events and related equipment and storage media. Background Technology

[0002] The Internet of Things (IoT) is a network that enables all ordinary physical objects that can be independently addressed to interconnect, based on information carriers such as the Internet and traditional telecommunications networks.

[0003] With the widespread use of devices such as cameras and environmental sensors in the Internet of Things, a large number of alarms will be generated continuously on the device side. How to alleviate the generation of a large number of repeated alarms in a short period of time and reduce the recurrence of similar events is a current technical challenge. Summary of the Invention

[0004] This application provides at least one method for alerting critical events, as well as related devices and storage media, to alleviate the generation of a large number of repetitive alarms in a short period of time and reduce the recurrence of similar events.

[0005] The first aspect of this application provides a method for alerting critical events, comprising: acquiring monitoring data collected in real time by various data acquisition devices; analyzing and summarizing the monitoring data collected within a first sliding window to obtain critical event information for a first time period in which the first sliding window is currently located; wherein the critical event information includes descriptive information of the critical events, and the critical event information for the first time period is used for immediate push notification; performing similarity comparison on the critical event information for each critical event in a second sliding window in the first time period to obtain semantic similarity between different critical events in a second time period in which the second sliding window is currently located; wherein the second time period includes several first time periods; in response to the semantic similarity between different critical events satisfying a filtering condition related to a similarity threshold, merging the corresponding critical events to obtain a set of critical events; and generating critical event alert information based on the set of critical events.

[0006] Therefore, by analyzing and summarizing the monitoring data in the first sliding window, key event information is generated; and by comparing the similarity of the key event information in the second sliding window, the same or similar events are merged, thereby reducing the number of duplicate alarms and the repeated presentation of similar events.

[0007] The second aspect of this application provides an electronic device comprising a memory and a processor coupled to each other, the processor being used to execute program instructions stored in the memory to implement the critical event reminder method described in the first aspect above.

[0008] A third aspect of this application provides a computer-readable storage medium having program instructions stored thereon, which, when executed by a processor, implement the critical event alerting method described in the first aspect above.

[0009] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this application. Attached Figure Description

[0010] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with this application and, together with the specification, serve to explain the technical solutions of this application.

[0011] Figure 1 This is a flowchart illustrating the first embodiment of the critical event reminder method of this application;

[0012] Figure 2 This is a flowchart illustrating the second embodiment of the critical event reminder method of this application;

[0013] Figure 3 This is a flowchart illustrating the third embodiment of the critical event reminder method of this application;

[0014] Figure 4 This is a flowchart illustrating the fourth embodiment of the critical event reminder method of this application;

[0015] Figure 5 This is a flowchart illustrating the fifth embodiment of the critical event reminder method of this application;

[0016] Figure 6 This is a schematic diagram of the framework of an embodiment of the electronic device of this application;

[0017] Figure 7 This is a schematic diagram of a framework of an embodiment of the computer-readable storage medium of this application. Detailed Implementation

[0018] The embodiments of this application will now be described in detail with reference to the accompanying drawings.

[0019] In the following description, specific details such as particular system architectures, interfaces, and technologies are presented for illustrative purposes rather than for limiting purposes, in order to provide a thorough understanding of this application.

[0020] In this document, the term "and / or" merely describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " generally indicates that the preceding and following related objects have an "or" relationship. Furthermore, "many" in this document means two or more. Moreover, the term "at least one" in this document means any combination of at least two of any one or more of a plurality of objects. For example, including at least one of A, B, and C can mean including any one or more elements selected from the set consisting of A, B, and C. The term "several" indicates an indefinite quantity, which can be one, two, or more.

[0021] Please see Figure 1 The first aspect of this application provides a method for alerting critical events, including:

[0022] S110: Acquire the monitoring data collected in real time by each data acquisition device.

[0023] Data acquisition devices can collect multimodal data. For example, monitoring data may include image data, audio data, video data, text data, and other multimodal data. Exemplarily, a data acquisition device can be a camera, recording device, or sensing device. For instance, a data acquisition device can be an infrared sensor or other sensing device, which can output the collected data in text format. As another example, a data acquisition device can be a camera, thereby collecting image, audio, and video data as monitoring data. Furthermore, a data acquisition device can integrate a camera, recording device, and sensing device. This application does not limit the specific form of the data acquisition device or the specific form of the monitoring data.

[0024] The critical event alert method provided in this application can be applied to an Internet of Things (IoT) platform. The IoT platform may include data acquisition devices such as cameras, recording devices, and sensors to collect multimodal data. For example, the IoT platform may include a server and data acquisition devices. The data acquisition devices can be connected to the server via wired or wireless means, allowing the server to obtain monitoring data from the data acquisition devices.

[0025] In some embodiments, the monitoring data may also include timestamps, device identifiers, etc. Timestamps are used to identify the time the monitoring data was collected, and device identifiers can be used to indicate which data acquisition device collected the monitoring data.

[0026] S120: Based on the monitoring data collected within the first sliding window, analyze and summarize to obtain the key event information of the first time period in which the first sliding window is currently located. The key event information includes the description information of the key event, and the key event information of the first time period is used for real-time push.

[0027] For example, monitoring data can be analyzed and summarized by a multimodal model to obtain key event information. This application does not limit the model structure, type, etc.

[0028] In some embodiments, in addition to descriptive information, key event information may also include at least one of the following: event identifier, event level, event type, and start and end times of the first time period.

[0029] For example, different event identifiers can be generated for different key events, so that the event identifiers of key events can be used to indicate different key events.

[0030] Event levels can be represented by different scores to indicate the urgency, risk level, etc. of critical events. For example, an event level of 0 to 6 indicates a low-risk event, while an event level of 7 to 10 indicates a high-risk event.

[0031] The start and end times of the first time period in which a critical event occurs can be used to indicate the time period in which the critical event occurs, such as 9:00-9:01 or 9:01-9:02.

[0032] Event types can be determined by a multimodal model, such as personnel entering, vehicles passing by, equipment malfunctions, etc.

[0033] The first time period in which the first sliding window is located can be, for example, 1 minute, 2 minutes, 3 minutes, etc. This application does not limit the duration of the first time period. After obtaining the key event information of the first time period in which the first sliding window is currently located, the monitoring data in the next first time period in which the first sliding window is located can be analyzed and summarized. For example, assuming the first time period in which the first sliding window is located is 1 minute, the monitoring data collected between 9:00 and 9:01 can be analyzed and summarized first to obtain the key event information between 9:00 and 9:01; then the monitoring data collected between 9:01 and 9:02 can be analyzed and summarized to obtain the key event information between 9:01 and 9:02; then the monitoring data collected between 9:02 and 9:03 can be analyzed and summarized to obtain the key event information between 9:02 and 9:03, and so on.

[0034] For example, the descriptive information of a key event may include a natural language description of the key event, such as "a male deliveryman puts a package down at the door" or "a red car drives past the door." The descriptive information of the key event can be generated by a multimodal model.

[0035] Key event information from the first time period is used for immediate push notifications. For example, if an emergency is identified through analysis and summarization of monitoring data from each of the first time periods within the year, this key event can be immediately pushed out. This helps alleviate the problem of delayed emergency event notifications.

[0036] S130: Based on the information of each key event in the second sliding window in the first time period, perform similarity comparison to obtain the semantic similarity between different key events in the second time period in which the second sliding window is currently located. The second time period includes several first time periods.

[0037] For example, the second time period of the second sliding window can be 10 minutes, 20 minutes, 30 minutes, etc. This application does not limit the duration of the second time period, as long as it is longer than the duration of the first time period.

[0038] S140: In response to the semantic similarity between different key events satisfying the screening conditions related to the similarity threshold, the key events are merged to obtain a set of key events.

[0039] Filtering criteria related to similarity thresholds may include, for example, greater than the similarity threshold, greater than or equal to the similarity threshold, etc.

[0040] For example, the semantic similarity between different key events can be obtained by comparing the semantic similarity of the descriptive information of different key events.

[0041] For example, when the semantic similarity between different key events exceeds a similarity threshold, the corresponding key events are merged.

[0042] S150: Generate key event reminder information based on the set of key events.

[0043] Key event alerts generated based on a key event set are summary alerts for each key event within that set. In other words, key event alerts include a summary of the key events within the key event set.

[0044] Therefore, by analyzing and summarizing the monitoring data in the first sliding window, key event information is generated; and by comparing the similarity of the key event information in the second sliding window, the same or similar events are merged, thereby reducing the number of duplicate alarms and the repeated presentation of similar events.

[0045] In one implementation, the key event information also includes the time when the key event occurred.

[0046] Please refer to Figure 2 The generation of key event reminder information based on the key event set in S150 above may include:

[0047] S251: Generate key event reminder information based on the description information and occurrence time of key events within the key event set.

[0048] The key event alert information includes the frequency of key events and the time range of key events.

[0049] The occurrence time of a critical event refers to the specific point in time or time period during which the event is triggered, which can be determined by the timestamps in the monitoring data. The frequency of a critical event refers to the total number of times the event repeats within a specific time range, such as the cumulative number of times a vehicle passes by within a one-hour window. For example, a natural language summary can be generated based on a set of critical events using a multimodal large model. For instance, if the set of critical events includes five similar critical events, and these critical events represent vehicles passing by the entrance, then a natural language summary can be generated based on the timestamps corresponding to these critical events, such as "between 9:00 and 9:30, five vehicles passed by the entrance," and so on.

[0050] The above solution reduces duplicate alerts and the repetitive presentation of similar events by describing key events within a set of key events by their frequency and time range. By including frequency and time range in key event alerts, users can quickly grasp the overall situation without having to review each original event record, significantly improving information comprehension efficiency. For low-risk events, this summary alert effectively avoids information overload and reduces the cognitive burden on users.

[0051] In one implementation, please refer to Figure 3 The generation of key event reminder information based on the key event set in S150 above may include:

[0052] S351: Obtain the descriptive information of each key event in the key event set, and summarize the descriptive information based on this descriptive information to obtain the summary descriptive information.

[0053] S352: Use summary and description information as a reminder of key events.

[0054] Key event information in a key event set can include event type, timestamps, and multimodal content such as images, audio, or text. This key event information can be summarized using a multimodal model, for example, converting multiple similar images into a coherent natural language summary. For example, open-source models such as CLIP can be used for semantic fusion of images and text, or commercial APIs such as Google Cloud Vision can be used to extract key features and generate summaries. In some embodiments, when the description information contains multiple images of human figures triggering an alarm, common features can be extracted to generate a unified description such as "a male deliveryman placed a package at the door," or multiple video descriptions of passing vehicles can be summarized as "five cars passed through the door within 10 minutes," and so on.

[0055] The above solution reduces duplicate alerts and the repetitive presentation of similar events by describing key events within a set of key events by their frequency and time range. By including frequency and time range in key event alerts, users can quickly grasp the overall situation without having to review each original event record, significantly improving information comprehension efficiency. For low-risk events, this summary alert effectively avoids information overload and reduces the cognitive burden on users.

[0056] In one implementation, key event information may include the time of occurrence.

[0057] Please refer to Figure 4 The summary and description information in S352 above, which serves as a key event reminder, may include:

[0058] S3521: Based on the key event information, obtain the earliest appearing key event in the key event set, and take the earliest appearing key event as the main event of the key event set.

[0059] S3522: Update the description information of the main event to a summary description information, and use the summary description information as a key event reminder information.

[0060] Key event information can include the time of occurrence, which can be used to determine the chronological order of key events, thereby selecting the earliest occurrence as the master event when merging similar events.

[0061] By including the occurrence time in the key event information, the earliest event in the set of key events can be identified as the primary event. After updating the primary event description information to a summary description information, the key event alert information includes a comprehensive description of all similar events, reducing the number of duplicate alerts received by users and reducing the repeated presentation of similar events.

[0062] In one implementation, please refer to Figure 5 The methods also include:

[0063] S510: Obtain the importance level of critical events.

[0064] S520: Based on the importance level, take corresponding reminder strategies for critical events. The reminder strategies include immediately outputting reminder information and temporarily suspending the output of reminder information.

[0065] Importance levels can be generated by using a multimodal model to score events for safety. For example, this could be a numerical index ranging from 0 to 10, used to quantify the risk level of critical events. For instance, an importance level of 7 or higher can be defined as a high-risk event, and 0 to 6 as a low-risk event. Alerts for high-risk events can be immediately output to ensure timely handling of critical alarms, while alerts for low-risk events can be delayed and integrated into periodic summary reports.

[0066] By adopting a differentiated alert strategy based on importance levels, it is beneficial to alleviate the problem of alarm information overload in IoT scenarios. High-risk events are pushed in real time to prevent processing delays, while low-risk events are aggregated, summarized, and pushed periodically, which significantly reduces the number of redundant alarms received by users.

[0067] In one embodiment, similarity comparison is performed based on the information of each key event located in the second sliding window during the first time period. This can be achieved by converting the text of each key event information into semantic vectors, obtaining the cosine similarity or Euclidean distance between the semantic vectors corresponding to each key event information, and obtaining the semantic similarity between each key event based on the cosine similarity or Euclidean distance.

[0068] Key event information texts can be composed of natural language descriptions generated by multimodal models. Pre-trained text embedding models such as BERT can be used to encode the text into fixed-dimensional semantic vectors. Vector similarity calculation can be based on cosine similarity or Euclidean distance.

[0069] In some implementations, semantic similarity comparisons of key event information are also performed based on semantic models.

[0070] For example, vectorized similarity matching can be used to convert descriptive information into vector embeddings and calculate cosine similarity; model matching can be used to directly call a multimodal model to determine whether multiple key events describe similar events. The semantic similarity threshold can be set to, for example, 0.9 to determine the merging criteria.

[0071] By comparing semantic similarity based on a semantic model, the system can accurately identify multiple summaries describing the same event within a long time window, effectively eliminating semantic redundancy and preventing high-risk events from being interfered with by low-risk repetitive information. This technical feature significantly reduces alarm information redundancy, ensuring that high-risk events are pushed out instantly without delay, while aggregating low-risk events into periodic summaries, greatly reducing user information overload and improving the response efficiency and user experience of the alarm system.

[0072] Those skilled in the art will understand that, in the above-described method of the specific implementation, the order in which each step is written does not imply a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of each step should be determined by its function and possible internal logic.

[0073] Please see Figure 6 , Figure 6 This is a schematic diagram of an embodiment of the electronic device 60 of this application. The electronic device 60 includes a memory 61 and a processor 62 coupled to each other. The processor 62 is used to execute program instructions stored in the memory 61 to implement the steps in any of the above-described key event reminder method embodiments. In a specific implementation scenario, the electronic device 60 may include, but is not limited to, a microcomputer or a server. In addition, the electronic device 60 may also include mobile devices such as laptops and tablets, which are not limited here.

[0074] Specifically, processor 62 controls itself and memory 61 to implement the steps in any of the above-described key event reminder method embodiments. Processor 62 can also be referred to as a CPU (Central Processing Unit). Processor 62 may be an integrated circuit chip with signal processing capabilities. Processor 62 can also be a general-purpose processor, digital signal processor (DSP), application-specific integrated circuit (ASIC), field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. A general-purpose processor can be a microprocessor or any conventional processor. Furthermore, processor 62 can be implemented using integrated circuit chips.

[0075] Please see Figure 7 , Figure 7This is a schematic diagram of a framework of an embodiment of the computer-readable storage medium 70 of this application. The computer-readable storage medium 70 stores program instructions 701 that can be executed by a processor. The program instructions 701 are used to implement the steps in any of the above-described embodiments of the critical event reminder method.

[0076] In some embodiments, the functions or modules of the apparatus provided in this disclosure can be used to perform the methods described in the above method embodiments. The specific implementation can be referred to the description of the above method embodiments, and for the sake of brevity, it will not be repeated here.

[0077] The description of the various embodiments above tends to emphasize the differences between the various embodiments. The similarities or similarities between them can be referred to, and for the sake of brevity, they will not be repeated here.

[0078] In the several embodiments provided in this application, it should be understood that the disclosed methods and apparatus can be implemented in other ways. For example, the apparatus implementations described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection of devices or units may be electrical, mechanical, or other forms.

[0079] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0080] If the integrated unit is implemented as 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 this application, in essence, 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. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods of various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0081] If the technical solution of this application involves personal information, the product using this technical solution has clearly informed the user of the personal information processing rules and obtained the user's voluntary consent before processing the personal information. If the technical solution of this application involves sensitive personal information, the product using this technical solution has obtained the user's separate consent before processing the sensitive personal information, and also meets the requirement of "express consent". For example, at personal information collection devices such as cameras, clear and prominent signs are set up to inform users that they have entered the scope of personal information collection and that personal information will be collected. If an individual voluntarily enters the collection scope, it is deemed that they have agreed to the collection of their personal information; or on the personal information processing device, with clear signs / information informing users of the personal information processing rules, authorization is obtained from the individual through pop-up information or by asking the individual to upload their personal information; wherein, the personal information processing rules may include information such as the personal information processor, the purpose of personal information processing, the processing method, and the types of personal information processed.

Claims

1. A method for reminding users of critical events, characterized in that, include: Acquire monitoring data collected in real time by each data acquisition device; Based on the analysis and summary of monitoring data collected within the first sliding window, key event information of the first time period in which the first sliding window is currently located is obtained; wherein, the key event information includes descriptive information of the key events, and the key event information of the first time period is used for real-time push. Based on the key event information located within the second sliding window in the first time period, a similarity comparison is performed to obtain the semantic similarity between different key events within the second time period in which the second sliding window is currently located; wherein, the second time period includes several first time periods; In response to the semantic similarity between different key events satisfying the filtering conditions related to the similarity threshold, the key events are merged to obtain a set of key events; Generate key event reminder information based on the set of key events; The key event information includes the occurrence time of the key event. Generating key event reminder information based on the key event set includes: obtaining description information of each key event in the key event set; summarizing the description information of each key event to obtain summary description information; obtaining the earliest occurring key event in the key event set based on the key event information, and using the earliest occurring key event as the main event of the key event set; updating the description information of the main event to the summary description information, and using the summary description information as the key event reminder information.

2. The method according to claim 1, characterized in that, The key event information also includes the time when the key event occurred; The generation of key event reminder information based on the set of key events includes: Based on the description information and occurrence time of the key events within the set of key events, the key event reminder information is generated.

3. The method according to claim 1, characterized in that, The method further includes: Obtain the importance level of the key events; Based on the importance level, corresponding reminder strategies are adopted for the key events, and the reminder strategies include immediately outputting reminder information and temporarily delaying the output of reminder information.

4. The method according to claim 1, characterized in that, The monitoring data includes multimodal data.

5. The method according to claim 1, characterized in that, The step of performing similarity comparison based on the key event information located within the second sliding window in the first time period to obtain the semantic similarity between different key events within the second time period currently occupied by the second sliding window includes: Convert the text of each key event information into a semantic vector, and obtain the cosine similarity or Euclidean distance between the semantic vectors corresponding to each key event information. Based on the cosine similarity or Euclidean distance, the semantic similarity between each of the key events is obtained.

6. The method according to claim 1, characterized in that, The similarity comparison based on the key event information located within the second sliding window in the first time period includes: The semantic similarity of each key event information is compared based on a semantic model.

7. An electronic device, characterized in that, It includes a memory and a processor coupled to each other, the processor being used to execute program instructions stored in the memory to implement the critical event reminder method according to any one of claims 1 to 6.

8. A computer-readable storage medium having program instructions stored thereon, characterized in that, When the program instructions are executed by the processor, they implement the critical event reminder method according to any one of claims 1 to 6.

Images