Video monitoring streaming media decision method, device and equipment and storage medium

Abstract

The application provides a video monitoring streaming media decision method, device and equipment and a storage medium, and relates to the technical field of video monitoring. The method comprises the following steps: acquiring an enabling stream decision factor corresponding to each video monitoring device in at least one video monitoring device; determining an enabling stream probability of each video monitoring device based on each enabling stream decision factor; and determining a streaming media decision result corresponding to the at least one video monitoring device based on each enabling stream probability, wherein the streaming media decision result is used to represent whether each video monitoring device is pre-enabled to stream, and the streaming media decision result carries a corresponding pre-enabled stream prediction sequence in the case that the streaming media decision result represents that each video monitoring device is pre-enabled to stream. The application can shorten the enabling stream waiting time and improve the user experience.

Description

Technical Field

[0001] This invention relates to the field of video surveillance technology, and in particular to a video surveillance streaming media decision-making method, apparatus, device, and storage medium. Background Technology

[0002] With the rapid development of IoT technology, video surveillance equipment has significantly shortened the distance between people, eliminating geographical limitations. With this equipment installed, users can view people and events they are interested in anytime, anywhere. The specific process is as follows: After the user opens the app and logs in, the app obtains a list of devices, performs a hole-punching login, and then, after the user selects a device, the app requests a stream from that device. The device then sends the stream back to the app, which decodes and plays it upon receiving it. However, the success rate of the app's hole-punching login is low, and even after successful hole punching, the streaming startup speed is slow, resulting in a long waiting time.

[0003] In existing technologies, such as Figure 1 As shown, by having the user open the app, log in to their account, obtain the device list, and select a device, the app requests a stream from the streaming media server, thus avoiding the problem of app login failures due to homing attacks. The specific process is as follows: the signaling server initiates a stream for the selected device, the device sends the stream to the streaming media server, the streaming media server forwards the video stream to the app, and the app decodes and plays the received video stream. However, the above solution only solves the problem of app login failures due to homing attacks; it does not solve the problem of long stream initiation waiting times. Therefore, how to shorten the stream initiation waiting time for video surveillance devices is a pressing issue that needs to be addressed. Summary of the Invention

[0004] This invention provides a video surveillance streaming media decision-making method, apparatus, device, and storage medium to address the shortcomings of existing technologies in terms of long streaming start-up waiting times for video surveillance equipment, thereby shortening the streaming start-up waiting time and improving the user experience.

[0005] This invention provides a video surveillance streaming media decision-making method, comprising:

[0006] Obtain the starting decision factor corresponding to each of the video surveillance devices in at least one video surveillance device;

[0007] Based on each of the aforementioned start-up decision factors, the start-up probability of each of the aforementioned video surveillance devices is determined;

[0008] Based on the streaming start probability, a streaming media decision result is determined for each of the at least one video surveillance devices. The streaming media decision result is used to characterize whether each of the video surveillance devices has started streaming in advance. When the streaming media decision result characterizes that each of the video surveillance devices has started streaming in advance, the streaming media decision result carries the corresponding pre-start streaming prediction order.

[0009] According to the video surveillance streaming media decision-making method provided by the present invention, determining the streaming probability of each video surveillance device based on each of the streaming decision factors includes:

[0010] Under the condition that the first preset condition is met, the probability of starting the video surveillance device is determined to be 1;

[0011] If the first preset condition is not met, for each video surveillance device, determine the probability of occurrence corresponding to the start-up decision factor; based on the start-up decision factor and the corresponding probability of occurrence, determine the start-up probability of the video surveillance device.

[0012] The first preset conditions include:

[0013] A preset alarm in the aforementioned start-up decision factor is triggered; or,

[0014] The number of devices corresponding to the at least one video surveillance device is one.

[0015] According to the video surveillance streaming media decision-making method provided by the present invention, determining the occurrence probability corresponding to the streaming start decision factor includes:

[0016] Obtain historical flow data;

[0017] Based on the historical start-up data, the preset occurrence probability corresponding to the start-up decision factor is determined;

[0018] If the video surveillance equipment does not meet the second preset condition, the probability of occurrence corresponding to the start-up decision factor will be determined to be 0.

[0019] When the power-on of the video surveillance device meets the second preset condition, the preset occurrence probability is determined as the occurrence probability corresponding to the power-on decision factor.

[0020] According to the video surveillance streaming media decision-making method provided by the present invention, the streaming decision factor includes an alarm factor and a user habit factor; the preset occurrence probability includes a first preset occurrence probability corresponding to the user habit factor and a second preset occurrence probability corresponding to the alarm factor; the occurrence probability includes the habit occurrence probability corresponding to the user habit factor and the alarm occurrence probability corresponding to the alarm factor.

[0021] When the power-on condition of the video surveillance device is met, determining the second preset probability of occurrence as the probability of occurrence corresponding to the power-on decision factor includes:

[0022] If the start-up of the video surveillance device meets the second preset condition that the start-up of the video surveillance device is in line with the user's habitual location and / or time, the first preset occurrence probability is determined as the habit occurrence probability corresponding to the user habit factor;

[0023] And / or,

[0024] When the power-on condition of the video surveillance device meets the second preset condition and the video surveillance device generates alarm information, the second preset occurrence probability is determined as the alarm occurrence probability corresponding to the alarm factor.

[0025] According to the video surveillance streaming media decision-making method provided by the present invention, the streaming decision factor further includes the number of devices corresponding to the at least one video surveillance device;

[0026] The step of determining the activation probability of the video surveillance device based on the activation decision factor and the corresponding occurrence probability includes:

[0027] Upon receiving alarm information corresponding to the video surveillance device, the target alarm type is determined based on the alarm information;

[0028] Based on the target alarm type and the historical start-up data, determine the alarm weight corresponding to the alarm factor;

[0029] Based on the historical user data, determine the habit weights corresponding to the user habit factors;

[0030] The first initiation probability is determined based on a preset constant, the alarm occurrence probability and alarm weight corresponding to the alarm factor, and the habit occurrence probability and habit weight corresponding to the user habit factor.

[0031] The device weights corresponding to the video surveillance devices are determined based on the number of devices.

[0032] The starting probability of the video surveillance device is determined based on the first starting probability and the device weight.

[0033] According to the video surveillance streaming media decision-making method provided by the present invention, determining the streaming media decision result corresponding to the at least one video surveillance device based on each of the streaming initiation probabilities includes:

[0034] Each of the stated start-up probabilities is compared with a preset start-up threshold to determine the start-up decision result;

[0035] Sort the current activation probabilities in descending order to determine the current activation priority ranking result corresponding to the at least one video surveillance device;

[0036] Based on the streaming priority ranking result and the streaming decision result, the streaming media decision result corresponding to the at least one video surveillance device is determined.

[0037] According to the video surveillance streaming media decision-making method provided by the present invention, the method further includes:

[0038] Obtain abnormal flow start data;

[0039] If the abnormal start-up data differs from the start-up priority ranking result, based on the abnormal start-up data, the abnormal factor corresponding to the video surveillance device is determined from the start-up decision factors; the abnormal occurrence probability corresponding to the abnormal factor is updated, and based on the abnormal occurrence probability, the start-up probability of the video surveillance device is updated.

[0040] If the abnormal start-up data differs from the start-up decision result, the start-up preset threshold is updated based on the abnormal start-up data.

[0041] The present invention also provides a video surveillance streaming media decision-making device, comprising:

[0042] The acquisition module is used to acquire the starting decision factor corresponding to each of the video surveillance devices in at least one video surveillance device;

[0043] The first determining module is used to determine the activation probability of each video surveillance device based on each of the activation decision factors.

[0044] The second determining module is used to determine the streaming media decision result corresponding to the at least one video surveillance device based on each of the streaming start probabilities. The streaming media decision result is used to characterize whether each of the video surveillance devices has started streaming in advance. When the streaming media decision result characterizes that each of the video surveillance devices has started streaming in advance, the streaming media decision result carries the corresponding pre-start prediction order.

[0045] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the video surveillance streaming media decision-making method as described above.

[0046] The present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the video surveillance streaming media decision-making method as described above.

[0047] The video surveillance streaming media decision-making method, apparatus, device, and storage medium provided by this invention determine the streaming probability of each video surveillance device based on the streaming decision factor corresponding to each video surveillance device, and determine the streaming media decision result corresponding to all video surveillance devices based on each streaming probability, that is, determine whether each video surveillance device should be pre-started. If each video surveillance device is pre-started, the pre-start prediction order of each video surveillance device is further determined, and the video surveillance devices are pre-started according to the pre-start prediction order, so that after the user triggers, the live broadcast of the corresponding video surveillance device can be directly opened, which greatly shortens the streaming waiting time and improves the user experience. Attached Figure Description

[0048] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0049] Figure 1 This is a schematic diagram of the power-on process for video surveillance equipment provided by existing technology;

[0050] Figure 2 This is one of the flowcharts illustrating the video surveillance streaming media decision-making method provided in this embodiment of the invention;

[0051] Figure 3 This is the second flowchart illustrating the video surveillance streaming media decision-making method provided in this embodiment of the invention;

[0052] Figure 4 This is a schematic diagram of the power-on process of the video surveillance equipment provided in this embodiment of the invention;

[0053] Figure 5 This is a schematic diagram of the structure of the video surveillance streaming media decision-making device provided in an embodiment of the present invention;

[0054] Figure 6 This is a schematic diagram of the structure of the electronic device provided in an embodiment of the present invention. Detailed Implementation

[0055] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0056] To address the issue of long startup waiting times for video surveillance equipment in existing technologies, this invention provides a video surveillance streaming media decision-making method. Figure 2 This is one of the flowcharts illustrating the video surveillance streaming media decision-making method provided in this embodiment of the invention, such as... Figure 2 As shown, the method includes:

[0057] Step 210: Obtain the starting decision factor corresponding to each video surveillance device in at least one video surveillance device.

[0058] Specifically, the corresponding start-up decision factors can be obtained through the configuration files of each video surveillance device. These start-up decision factors are factors that affect whether each video surveillance device starts up and the order in which it starts up.

[0059] It should be noted that "start streaming" is used to indicate that after identifying a target video surveillance device and having the target video surveillance device enabled, a request is made to the target video surveillance device for the video stream captured by the target video surveillance device. The target video surveillance device can be any one of at least one video surveillance device.

[0060] Optionally, the video surveillance device is a network camera (IP camera, IPC), which can transmit the captured video stream to the terminal via a network. Network cameras may include dome cameras, wired bullet cameras, high-speed PTZ cameras, and wireless cameras, etc., and this embodiment of the invention does not impose any limitations on this.

[0061] Optionally, the triggering decision factor may include: alarm factors, user habit factors, and the number of devices corresponding to at least one video surveillance device. Example:

[0062] 1) Alarm factors can include: After device B triggers an alarm such as an audio alarm, fall alarm, human detection alarm, motion alarm, video loss alarm, or network fluctuation alarm, the user can enable live streaming on device B. Audio alarms can include crying alarms, pet sound alarms, motor vehicle alarms, and non-motor vehicle alarms. Furthermore, after device B triggers a preset alarm such as a doorbell alarm, the streaming media server needs to pull the video stream from device B and forward it to the app on the terminal, allowing the user to enable live streaming on device B.

[0063] 2) User habit factors can be: the user's habit of turning on device C at location S and time T.

[0064] 3) The number of devices can be: if a user has only one video surveillance device, the user can only turn on the live feed of that video surveillance device; if a user has at least two video surveillance devices, the user can turn on the live feed of any one of the video surveillance devices.

[0065] Step 220: Determine the activation probability of each video surveillance device based on each of the activation decision factors.

[0066] Specifically, after determining each start-up decision factor, the start-up probability of each video surveillance device can be further determined. This facilitates determining whether each video surveillance device should be pre-started based on the start-up probability, and the corresponding pre-start-up prediction order when pre-start-up is determined. This allows the streaming media to be directly notified to start up after the user logs in, shortening the start-up waiting time and improving the user experience.

[0067] Furthermore, Figure 3 This is a second flowchart illustrating the video surveillance streaming media decision-making method provided in this embodiment of the invention, as shown below. Figure 3 As shown, determining the activation probability of each video surveillance device based on each activation decision factor includes:

[0068] Under the condition that the first preset condition is met, the probability of starting the video surveillance device is determined to be 1;

[0069] If the first preset condition is not met, for each video surveillance device, determine the probability of occurrence corresponding to the start-up decision factor; based on the start-up decision factor and the corresponding probability of occurrence, determine the start-up probability of the video surveillance device.

[0070] The first preset conditions include:

[0071] A preset alarm in the aforementioned start-up decision factor is triggered; or,

[0072] The number of devices corresponding to the at least one video surveillance device is one.

[0073] Specifically, such as Figure 3 As shown, if a preset alarm occurs on a video surveillance device, such as a doorbell alarm on device B, the probability of device B immediately starting live streaming is 1. That is, the probability of the streaming media server pulling the stream from device B and forwarding the video stream to the app is 1. If no preset alarm occurs on the video surveillance device, the number of video surveillance devices is further determined. If there is only one device, the probability of starting live streaming for that video surveillance device is always 1, regardless of the type of alarm or the user's habits. If there are at least two devices, the probability of the occurrence of the live streaming decision factor is further determined, and based on this probability and the live streaming decision factor, the probability of starting live streaming for each video surveillance device is further determined.

[0074] Furthermore, determining the occurrence probability corresponding to the initiation decision factor includes:

[0075] Obtain historical flow data;

[0076] Based on the historical start-up data, the preset occurrence probability corresponding to the start-up decision factor is determined;

[0077] If the video surveillance equipment does not meet the second preset condition, the probability of occurrence corresponding to the start-up decision factor will be determined to be 0.

[0078] When the power-on of the video surveillance device meets the second preset condition, the preset occurrence probability is determined as the occurrence probability corresponding to the power-on decision factor.

[0079] Specifically, determining the probability of occurrence corresponding to the flow initiation decision factor requires first acquiring historical flow initiation data. This historical data can include operation data from multiple users initiating live streaming to the video surveillance equipment within a preset time period. By analyzing this historical data, we can analyze the occurrence of different alarm types on the video surveillance equipment and the instances of users initiating live streaming according to their habits. This allows us to determine the preset probability of occurrence corresponding to the flow initiation decision factor; that is, the preset probability of occurrence is determined based on the proportion of users initiating live streaming to the video surveillance equipment under different circumstances. Furthermore, depending on whether the video surveillance equipment meets the second preset condition, we can further determine whether the probability of occurrence corresponding to the flow initiation decision factor is 0 or the preset probability.

[0080] It should be noted that, since the aforementioned streaming decision factors include alarm factors and user habit factors, the aforementioned preset occurrence probabilities include a first preset occurrence probability corresponding to the user habit factor and a second preset occurrence probability corresponding to the alarm factor. The occurrence probabilities of the aforementioned streaming decision factors include the habit occurrence probability corresponding to the user habit factor and the alarm occurrence probability corresponding to the alarm factor. Specifically, the alarm occurrence probability is the probability that the user will immediately start streaming to the video surveillance device after an alarm is triggered. The habit occurrence probability is the probability that the user will start streaming to the video surveillance device at their preferred location and time based on their own habits.

[0081] Optionally, when determining the preset occurrence probability corresponding to the start-up decision factor, it can be determined based on all historical start-up data or a portion of historical start-up data.

[0082] Optionally, when selecting historical data for multiple users, users can be randomly selected.

[0083] For example, taking historical feed start data including the operation data of 100 randomly selected users over 5 days as an example, and randomly selecting a portion of the historical feed start data of 10 users over 5 days, this portion of historical feed start data contains data where users start streaming to the video surveillance device at locations and times that do not conform to their usual habits, and where they do not start streaming after the video surveillance device alarms. That is, there is data where users start streaming without alarms and without any pattern. Therefore, to ensure the accuracy of the feed start probability, a preset constant can be set based on the proportion of data where users start streaming without alarms and without any pattern in this portion of historical feed start data. For example, if the proportion of data where users start streaming without alarms and without any pattern in this portion of historical feed start data is 20%, then the preset constant is set to 0.2. Then, in this portion of historical feed start data, the proportion of data where users start streaming to the video surveillance device and enable live streaming after an alarm occurs is 50%, and the proportion of data where users start streaming to the video surveillance device and enable live streaming at specific locations and / or times according to their habits is 50%. Therefore, the first preset probability of occurrence corresponding to the user habit factor is... The second preset occurrence probability corresponding to the alarm factor is

[0084] It should be noted that, because this part of the historical streaming data contains overlapping data of users starting streaming and enabling live streaming to the video surveillance device at specific locations and / or times according to their habits, and also starting streaming and enabling live streaming to the video surveillance device after an alarm is triggered, the sum of the proportion of data where users start streaming and enable live streaming to the video surveillance device after an alarm is triggered and the proportion of data where users start streaming and enable live streaming to the video surveillance device at specific locations and / or times according to their habits can be less than 100% or greater than or equal to 100%.

[0085] Furthermore, the aforementioned second preset condition includes: the video surveillance device's streaming start conforming to the user's habitual location and / or time, or the video surveillance device generating alarm information. Wherein, the video surveillance device's streaming start conforming to the user's habitual location and / or time corresponds to a user habit factor, and the video surveillance device generating alarm information corresponds to an alarm factor. When the video surveillance device's streaming start does not meet all of the aforementioned second preset conditions, it can be determined that the probability of habit occurrence corresponding to the user habit factor is 0, and the probability of alarm occurrence corresponding to the alarm factor is 0.

[0086] Furthermore, when the power-on of the video surveillance device meets the second preset condition, determining the second preset occurrence probability as the occurrence probability corresponding to the power-on decision factor includes:

[0087] If the start-up of the video surveillance device meets the second preset condition that the start-up of the video surveillance device is in line with the user's habitual location and / or time, the first preset occurrence probability is determined as the habit occurrence probability corresponding to the user habit factor;

[0088] And / or,

[0089] When the power-on condition of the video surveillance device meets the second preset condition and the video surveillance device generates alarm information, the second preset occurrence probability is determined as the alarm occurrence probability corresponding to the alarm factor.

[0090] Specifically, if the video surveillance device's startup coincides with the user's preferred location and / or time, but does not meet the user's preferred location and / or time, the first preset occurrence probability can be determined as the user's preferred occurrence probability, and the alarm occurrence probability corresponding to the alarm factor can be determined as 0. If the video surveillance device's startup meets the user's preferred location and / or time, but does not meet the user's preferred location and / or time, the second preset occurrence probability can be determined as the alarm occurrence probability corresponding to the alarm factor, and the user's preferred occurrence probability corresponding to the user's preferred factor can be determined as 0. If the video surveillance device's startup meets both the user's preferred location and / or time, and also meets the user's preferred location and / or time, the first preset occurrence probability can be determined as the user's preferred occurrence probability, and the second preset occurrence probability can be determined as the alarm occurrence probability corresponding to the alarm factor.

[0091] For example, taking a second preset occurrence probability of 0.4 corresponding to the alarm factor as an example, if an alarm message is received, indicating that the video surveillance device has triggered an alarm and generated an alarm message, then the second preset occurrence probability corresponding to the alarm factor is determined as the alarm occurrence probability corresponding to the alarm factor, that is, the alarm occurrence probability is 0.4. If no alarm message is received, indicating that the video surveillance device has not triggered an alarm, then the alarm occurrence probability corresponding to the alarm factor is 0.

[0092] For example, with a first preset probability of occurrence of 0.4 corresponding to the user habit factor, among the user's multiple video surveillance devices, for each video surveillance device, if the start-up of the video surveillance device conforms to the user's habitual location and / or time, that is, based on the historical start-up data of the video surveillance device, it is determined that the video surveillance device frequently starts up at locations that conform to the user's habitual location, and / or the video surveillance device frequently starts up at times that conform to the user's habitual time, then the second preset probability of occurrence of the habit is determined as the probability of occurrence of the habit corresponding to the user habit factor of the video surveillance device, that is, the probability of occurrence of the habit is 0.4. Conversely, if the start-up of the video surveillance device does not conform to either the user's habitual location or the user's habitual time, then the probability of occurrence of the habit corresponding to the user habit factor of the video surveillance device is determined to be 0.

[0093] Furthermore, determining the start-up probability of the video surveillance device based on the start-up decision factor and the corresponding occurrence probability includes:

[0094] Upon receiving alarm information corresponding to the video surveillance device, the target alarm type is determined based on the alarm information;

[0095] Based on the target alarm type and the historical start-up data, determine the alarm weight corresponding to the alarm factor;

[0096] Based on the historical user data, determine the habit weights corresponding to the user habit factors;

[0097] The first initiation probability is determined based on a preset constant, the alarm occurrence probability and alarm weight corresponding to the alarm factor, and the habit occurrence probability and habit weight corresponding to the user habit factor.

[0098] The starting decision factor also includes the number of devices corresponding to the at least one video surveillance device.

[0099] The device weights corresponding to the video surveillance devices are determined based on the number of devices.

[0100] The starting probability of the video surveillance device is determined based on the first starting probability and the device weight.

[0101] Specifically, after acquiring historical alarm data, the initial alarm weights corresponding to different alarm types in the alarm factor can be determined based on the data proportions of different alarm types in the historical alarm data. When the video surveillance equipment receives alarm information, the target alarm type is determined based on the alarm information. Then, by traversing the different alarm types corresponding to the initial alarm weight, the alarm weight corresponding to the target alarm type is determined.

[0102] Taking the historical data on live streaming, which includes the operation data of 100 randomly selected users within a day, and assuming that all of this data reflects received alarm information, analysis of all operation data reveals the following: 1) After alarms such as crying alarms, pet sound alarms, and fall alarms occurred, 80% of the data showed users immediately activating live streaming to the video surveillance device, while 20% showed users activating live streaming at other times. Therefore, the alarm types corresponding to crying alarms, pet sound alarms, and fall alarms are classified as Category I alarms. 2) After alarms such as human body alarms, motor vehicle alarms, and non-motor vehicle alarms occurred, some users activated live streaming to the video surveillance device immediately or at other times, while others did not. Therefore, the alarm types corresponding to human body alarms, motor vehicle alarms, and non-motor vehicle alarms are classified as Category II alarms. 3) After motion alarms, video loss alarms, and network fluctuation alarms occur, there is no data showing that the user initiated live streaming to the video surveillance device immediately. There are instances where the user initiated live streaming to the video surveillance device at a later time, and instances where the user did not initiate live streaming at all. Therefore, the alarm types corresponding to motion alarms, video loss alarms, and network fluctuation alarms are classified into three categories. Category I alarms have a higher priority than Category II alarms, and Category II alarms have a higher priority than Category III alarms. Based on the above alarm types, the weight range and initial alarm weight corresponding to different alarm types can be further determined as shown in Table 1. The initial alarm weight is determined based on the average of the upper and lower limits of the weight range.

[0103] Table 1. Weight range and initial alarm weight for different alarm types.

[0104]

[0105] It should be noted that the aforementioned "first moment" refers to a short interval between the moment when the user starts streaming to the video surveillance device and the moment when the alarm occurs, while the aforementioned "non-first moment" refers to a longer interval between the moment when the user starts streaming to the video surveillance device and the moment when the alarm occurs.

[0106] Secondly, based on the data proportions corresponding to the locations and times of user habits in the historical data, the initial habit weights corresponding to the locations and times that conform to user habits in the user habit factors are determined. Then, based on the locations or times that conform to user habits of the video surveillance equipment, the habit weights corresponding to the user habit factors are further determined.

[0107] Table 2: Statistics of different users starting live games at the same location

[0108] user Day 1 Day 2 Day 3 Day 4 Day 5 The proportion of traffic starting at the same location User 1 Location A Location A / Location A Location A 80％ User 2 Location B Location B Location B Location B Location B 100％ User 3 Location C / / Location C / 40％ User 4 Location D / Location D / Location D 60％ User 5 Location E Location E Location E Location E / 80％ User 6 Location F / Location F / / 40％ User 7 / Location G / Location G Location G 60％ User 8 Location H Location H / / / 40％ User 9 Location I Location I / / Location I 60％ User 10 Location J / Location J / / 40％

[0109] Taking the historical data of live streaming as an example, which includes the operation data of 10 randomly selected users within 5 days, and whose operation data all conform to the user's habitual location or time, the analysis of the live streaming time and location in all operation data shows that, as shown in Table 2, the average proportion of data from users 1 to 10 who started live streaming to the video surveillance device from the same location is 60%. Therefore, the initial habit weight corresponding to the location that conforms to the user's habit is determined to be 0.6. Similarly, it can be determined that the average proportion of data from the same time that started live streaming to the video surveillance device is 40%, so the initial habit weight corresponding to the time that conforms to the user's habit is determined to be 0.4.

[0110] Secondly, based on the number of video surveillance devices corresponding to the user, the device weight corresponding to that video surveillance device is determined. When the number of devices is 1, the probability of selecting that video surveillance device is 1. When the number of devices is N, under the same conditions, the probability of the user selecting each video surveillance device is 1 / N. Therefore, based on the number of devices, the device weight corresponding to that video surveillance device can be further determined to be 1 or 1 / N.

[0111] After determining the preset constant, the probability of habit occurrence, the probability of alarm occurrence, the habit weight, and the alarm weight, the first start-up probability can be determined according to equation (1). Then, using equation (2), the start-up probability of the video surveillance device can be determined based on the product of the first start-up probability and the device weight. Equation (1) is:

[0112] P1 = P c +P a *w a +P b *w b

[0113] Where P1 represents the first initiation probability, P c P represents a preset constant. b P represents the probability of habit formation. a Let P represent the probability of an alarm occurring, and P0 represent the probability of an alarm occurring. c +P a +P b =1, w b w represents the custom weight. a This indicates the alarm weight.

[0114] Equation (2) is:

[0115] P t =P1*w s

[0116] Among them, P tw represents the probability of starting a current flow for this video surveillance device. s This indicates the device weight.

[0117] Optionally, the aforementioned historical user start data can be all historical user start data, or it can be a portion of historical user start data randomly selected from all historical user start data. For example, if all historical user start data includes the operation data of 100 randomly selected users within 5 days, then the aforementioned historical user start data can be the operation data of 100 randomly selected users on any day.

[0118] Step 230: Based on each of the streaming start probabilities, determine the streaming media decision result corresponding to the at least one video surveillance device. The streaming media decision result is used to characterize whether each of the video surveillance devices has pre-started streaming, and when the streaming media decision result characterizes that each of the video surveillance devices has pre-started streaming, the streaming media decision result carries the corresponding pre-start prediction order.

[0119] Specifically, after determining the activation probability of each video surveillance device, it can be determined whether each video surveillance device should be pre-activated based on the magnitude of the activation probability. If the video surveillance device is determined to be pre-activated, the pre-activation prediction order of each video surveillance device is further determined based on the ranking result of the activation probability. That is, in the case of each video surveillance device being pre-activated, the streaming media decision result also carries the pre-activation prediction order of each video surveillance device being pre-activated.

[0120] Furthermore, determining the streaming media decision result corresponding to the at least one video surveillance device based on each of the aforementioned streaming probabilities includes:

[0121] Each of the stated start-up probabilities is compared with a preset start-up threshold to determine the start-up decision result;

[0122] Sort the current activation probabilities in descending order to determine the current activation priority ranking result corresponding to the at least one video surveillance device;

[0123] Based on the streaming priority ranking result and the streaming decision result, the streaming media decision result corresponding to the at least one video surveillance device is determined.

[0124] Specifically, after determining the activation probability for each video surveillance device, these probabilities can be sorted in descending order to obtain the activation priority ranking result for each device. This priority ranking result determines the activation order of each device; the higher the activation probability, the earlier it is activated. Simultaneously, to ensure the prediction accuracy of the streaming media decision results, each activation probability can be compared with a preset activation threshold to obtain an activation decision result. This result determines whether the video surveillance device needs to be pre-activated. If the activation probability is greater than the preset threshold, the device is pre-activated; otherwise, it is not. Based on the intersection of the activation decision result and the activation priority ranking result, the streaming media decision result for at least one video surveillance device can be further determined.

[0125] For example, considering different scenarios for users A, B, C, and D, and assuming a preset streaming threshold of 0.1, for simplicity, all devices described below are video surveillance devices. The process for determining the streaming media decision result is as follows:

[0126] 1) User A has only one device. Regardless of whether the preset constant, the probability of habit occurrence, the probability of alarm occurrence, the habit weight, and the alarm weight change, the probability of starting traffic for device A1, PRA1, is always 1. That is, PRA1 = 1 and PRA1 > 0.1. Therefore, the user will always actively click on device A1, that is, the user will start traffic for device A1 in advance when logging into the APP.

[0127] 2) User B has 2 devices. Device B1 has a preset alarm, so the probability of device B1 starting a stream is PRB1 = 1. Device B2 has no alarm, but it matches the user's habit of clicking on device B2 at a specific location and time to watch the live stream. As mentioned above, the preset constant is 0.2, the alarm probability is 0, the habit occurrence probability is 0.4, the initial habit weight corresponding to the location that matches the user's habit is 0.6, and the initial habit weight corresponding to the time that matches the user's habit is 0.4. User B has two devices, so the device weight is 1 / 2. According to equations (1) and (2), the probability of device B2 starting a stream is PRB2 = (0.2 + 0 + (0.6 + 0.4) * 0.4) * (1 / 2) = 0.3. Since PRB1>PRB2>0.1, the determined streaming decision is that both device B1 and device B2 will be pre-started with streaming, and the streaming order is to start streaming on device B1 first, and then start streaming on device B2.

[0128] 3) User C has 3 devices. Device C1 triggered a crying alarm, and the location matched the user's habitual location. That is, in the past, user C only habitually clicked on device C1 at a specific location to watch the live stream. Therefore, the probability of device C1 starting the stream is PRC1 = (0.2 + 0.8 * 0.4 + 0.6 * 0.4) * (1 / 3) = 0.253. Device C2 did not trigger an alarm, but the time matched the user's habitual location. Therefore, the probability of device C2 starting the stream is PRC2 = (0.2 + 0.4 * 0.4) * (1 / 3) = 0.12. Device C3 did not trigger an alarm, nor did it match the user's habitual location and time. Therefore, the probability of device C3 starting the stream is PRC3 = (0.2) * (1 / 3) = 0.067. Since PRC1>PRC2>0.1>PRC3, the determined streaming media decision is to pre-start streaming for devices C1 and C2, with the startup order being to start streaming for device C1 first, then for device C2, and not to pre-start streaming for device C3.

[0129] 4) User D has 4 devices. None of the devices have alarmed and none of them are in the user's usual location and time. The probability of starting streaming for devices D1, D2, D3 and D4 is PRD1 = PRD2 = PRD3 = PRD4 = (0.2) * (1 / 4) = 0.04. Since PRD1 = PRD2 = PRD3 = PRD4 < 0.1, the determined streaming decision is not to start streaming for devices D1, D2, D3 and D4 in advance.

[0130] Furthermore, such as Figure 3 As shown, the method further includes:

[0131] Obtain abnormal flow start data;

[0132] If the abnormal start-up data differs from the start-up priority ranking result, based on the abnormal start-up data, the abnormal factor corresponding to the video surveillance device is determined from the start-up decision factors; the abnormal occurrence probability corresponding to the abnormal factor is updated, and based on the abnormal occurrence probability, the start-up probability of the video surveillance device is updated.

[0133] And / or,

[0134] If the abnormal start-up data differs from the start-up decision result, the start-up preset threshold is updated based on the abnormal start-up data.

[0135] Specifically, after the signaling server obtains the streaming media decision result and initiates streaming based on the streaming media decision result and the user trigger result, it can obtain the user trigger result as feedback data, and extract abnormal streaming start data that differs from the streaming media decision result from the feedback data, so as to optimize based on the abnormal streaming start data. Among these:

[0136] If the abnormal start-up data differs from the start-up priority ranking result, i.e., the start-up order of the devices is different, the abnormal start-up data can be further analyzed to determine the abnormal factors causing the different start-up order of the devices. Based on the abnormal start-up data, the probability of occurrence of the abnormal factors is updated, and then the start-up probability of the video surveillance devices is updated. For example, if user E has two devices, and device E1 triggers a crying alarm, but the location and time do not match the user's usual habits, then the start-up probability of device E1 is PRE1 = (0.2 + 0.8 * 0.4) * (1 / 2) = 0.26; device E2 does not trigger an alarm, but the location and time match the user's usual habits, then the start-up probability of device E2 is PRE2 = (0.2 + (0.6 + 0.4) * 0.4) * (1 / 2) = 0.3. Since PRE2 > PRE1 > 0.1, the streaming media decision result can be determined to pre-start both devices E1 and E2, with the start-up order being to start device E2 first, and then start device E1. However, in actual use, the user first activated the live stream on device E1, and then activated the live stream on device E2, causing the user's triggering result to differ from the streaming media decision result. Therefore, the abnormal streaming data corresponding to this user's triggering result was analyzed, determining that the user was more concerned with alarm factors than habit factors. Thus, the abnormal factors were identified as alarm factors and habit factors. Subsequently, the probability of alarm occurrence was gradually increased, while the probability of habit occurrence was gradually decreased. After each increase in alarm occurrence probability and decrease in habit occurrence probability, the streaming probability PRE1 of device E1 and the streaming probability PRE2 of device E2 were determined, and it was judged whether the streaming probability PRE1 of device E1 was greater than the streaming probability PRE2 of device E2. If the streaming probability PRE1 of device E1 was greater than the streaming probability PRE2 of device E2, the alarm occurrence probability was updated to the increased alarm occurrence probability, and the habit occurrence probability was updated to the decreased habit occurrence probability. If the current activation probability PRE1 of device E1 is less than or equal to the current activation probability PRE2 of device E2, then the alarm occurrence probability continues to increase, while the alarm occurrence probability continues to decrease, until the current activation probability PRE1 of device E1 is greater than the current activation probability PRE2 of device E2, at which point the iteration stops.For example, taking a step of 0.025 as an example, update the alarm occurrence probability to 0.425 and the habit occurrence probability to 0.375. After the update, the start flow probability PRE1 of device E1 = (0.2 + 0.8 * 0.425) * (1 / 2) = 0.27, and the start flow probability PRE2 of device E2 = (0.2 + (0.6 + 0.4) * 0.375) * (1 / 2) = 0.2875. Since PRE1 < PRE2, continue to update the alarm occurrence probability to 0.45 and the habit occurrence probability to 0.35. After the update, the start flow probability PRE1 of device E1 = (0.2 + 0.8 * 0.45) * (1 / 2) = 0.28, and the start flow probability PRE2 of device E2 = (0.2 + (0.6 + 0.4) * 0.35) * (1 / 2) = 0.275. At this time, PRE1 > PRE2 > 0.1, making the optimized streaming media decision result the same as the user trigger result in the abnormal start flow data. Therefore, update the alarm occurrence probability to 0.45 and the habit occurrence probability to 0.35.

[0137] It should be noted that since the above-mentioned abnormal factors are alarm factors and habit factors, the increase in the alarm occurrence probability is equal to the decrease in the habit occurrence probability. However, the increases in two consecutive increases may be equal or unequal, and this embodiment of the invention does not impose any restrictions on this. Furthermore, if the two devices of user E do not conform to the user's habitual location and / or time, and no alarm occurs, then a preset constant can be updated. Based on the increase or decrease of the preset constant, the alarm occurrence probability and the habit occurrence probability can be updated respectively according to the ratio of the alarm occurrence probability to the habit occurrence probability, ensuring that the sum of the preset constant, the alarm occurrence probability, and the habit occurrence probability is 1. For example, with a preset constant of 0.2, an alarm occurrence probability and a habit occurrence probability of 0.4, and a preset streaming threshold of 0.06, if a user has 4 devices, none of which trigger alarms, and none of them occur at locations and / or times consistent with the user's habits, then the streaming probability for each device is 0.2*(1 / 4) = 0.05. Since 0.05 < 0.06, the predetermined streaming decision is that none of the devices will be pre-activated. However, in actual use, the user activates live streaming on three of the devices, causing the user's triggering result to differ from the streaming decision result. Therefore, the preset constant is increased by 0.05 in increments of 0.05 each time. The new activation probability for each device is then calculated as 0.25 * (1 / 4) = 0.0625. Since 0.0625 > 0.06, the preset constant is updated to 0.25 while maintaining the original activation probability. Simultaneously, because the preset constant increases by 0.05, and the ratio of habit occurrence probability to alarm occurrence probability is 1:1, to ensure the sum of the preset constant, alarm occurrence probability, and habit occurrence probability is 1, both the habit occurrence probability and alarm occurrence probability need to be reduced by 0.025, i.e., both are reduced to 0.375. After updating the preset constant, habit occurrence probability, and alarm occurrence probability, the streaming media decision result is updated to pre-activate streaming for each device, with equal activation probabilities for each device, ensuring the optimized streaming media decision result matches the actual user-triggered result.

[0138] Furthermore, the preset threshold for starting streaming can be updated to ensure that the optimized streaming decision result matches the actual user-triggered result. Specifically, if abnormal streaming data differs from the streaming decision result—that is, if the streaming probability of a device is less than or equal to the preset threshold, then streaming will not be pre-started for that device. However, in actual use, if a user starts streaming for a device with a streaming probability less than or equal to the preset threshold, the preset threshold can be updated, thereby optimizing the streaming decision result. For example, user F has 5 devices. Only device F1 triggers a motion alarm, while the other devices do not trigger alarms, and the alarms do not occur at the user's preferred location and time. Therefore, the probability of starting streaming for device F1 is PRF1 = (0.2 + 0.2 * 0.4) * (1 / 5) = 0.06. The probability of starting streaming for devices F2 through F5 is PRF2 = PRF3 = PRF4 = PRF5 = (0.2 * 1) * (1 / 5) = 0.04. Since 0.1 > PRF1 > PRF2 = PRF3 = PRF4 = PRF5, the determined streaming decision is not to start streaming for any device prematurely. However, in actual use, the user turns on live streaming for device F1. Therefore, the preset threshold for starting streaming can be updated to a value greater than 0.04 and less than 0.06. For example, the preset threshold for starting streaming can be updated to 0.05. After updating the preset threshold for starting streaming, since PRF1>0.05>PRF2=PRF3=PRF4=PRF5, it can be determined that the streaming media decision result is to start streaming only on device F1 and not on other devices.

[0139] Furthermore, Figure 4 This is a schematic diagram of the power-on process of the video surveillance equipment provided in an embodiment of the present invention, such as... Figure 4 As shown, the execution entity of the video surveillance streaming media decision-making method provided in this embodiment of the invention is a streaming media decision server. After the streaming media decision result is predetermined and the signaling server detects the user's login account, the streaming media decision server can send the streaming media decision result to the signaling server. After obtaining the streaming media decision result, the signaling server pre-starts streaming to each video surveillance device according to the streaming media decision result. Then, it sends the streaming start address corresponding to the streaming media server to the user's client and sends the streaming start result to the streaming media server. After the video surveillance device starts streaming, it sends a video stream to the streaming media server, so that when the user triggers the streaming video surveillance device, the live broadcast can be started directly, which greatly shortens the streaming start waiting time. In addition, after the user triggers, the signaling server provides feedback on the user's trigger effect to optimize the occurrence probability corresponding to the streaming start decision factor.

[0140] The video surveillance streaming decision-making method provided in this embodiment of the invention determines the streaming probability of each video surveillance device based on the streaming decision factor corresponding to each video surveillance device, and determines the streaming decision result corresponding to all video surveillance devices based on each streaming probability, that is, determines whether each video surveillance device should be pre-started. If each video surveillance device is pre-started, the pre-start prediction order of each video surveillance device is further determined, and the video surveillance devices are pre-started according to the pre-start prediction order, so that after the user triggers, the live broadcast of the corresponding video surveillance device can be directly opened, which greatly shortens the streaming waiting time and improves the user experience.

[0141] The video surveillance streaming media decision-making device provided by the present invention is described below. The video surveillance streaming media decision-making device described below can be referred to in correspondence with the video surveillance streaming media decision-making method described above.

[0142] This invention also provides a video surveillance streaming media decision-making device. Figure 5 This is a schematic diagram of the structure of the video surveillance streaming media decision-making device provided in an embodiment of the present invention, as shown below. Figure 5 As shown, the video surveillance streaming media decision-making device 500 includes: an acquisition module 510, a first determination module 520, and a second determination module 530, wherein:

[0143] The acquisition module 510 is used to acquire the starting decision factor corresponding to each of the video surveillance devices in at least one video surveillance device;

[0144] The first determining module 520 is used to determine the starting probability of each video surveillance device based on each of the starting decision factors.

[0145] The second determining module 530 is used to determine the streaming media decision result corresponding to the at least one video surveillance device based on each of the streaming start probabilities. The streaming media decision result is used to characterize whether each of the video surveillance devices has started streaming in advance. When the streaming media decision result characterizes that each of the video surveillance devices has started streaming in advance, the streaming media decision result carries the corresponding pre-start prediction order.

[0146] The video surveillance streaming media decision-making device provided in this embodiment of the invention determines the activation probability of each video surveillance device based on the activation decision factor corresponding to each video surveillance device, and determines the streaming media decision result corresponding to all video surveillance devices based on each activation probability, that is, determines whether each video surveillance device should be pre-activated. If each video surveillance device is pre-activated, the device further determines the pre-activation prediction order of each video surveillance device, and pre-activates the video surveillance devices according to the pre-activation prediction order, so that after the user triggers, the live broadcast of the corresponding video surveillance device can be directly opened, which greatly shortens the activation waiting time and improves the user experience.

[0147] Optionally, the first determining module 520 is specifically used for:

[0148] Under the condition that the first preset condition is met, the probability of starting the video surveillance device is determined to be 1;

[0149] If the first preset condition is not met, for each video surveillance device, determine the probability of occurrence corresponding to the start-up decision factor; based on the start-up decision factor and the corresponding probability of occurrence, determine the start-up probability of the video surveillance device.

[0150] The first preset conditions include:

[0151] A preset alarm in the aforementioned start-up decision factor is triggered; or,

[0152] The number of devices corresponding to the at least one video surveillance device is one.

[0153] Optionally, the first determining module 520 is specifically used for:

[0154] Obtain historical flow data;

[0155] Based on the historical start-up data, the preset occurrence probability corresponding to the start-up decision factor is determined;

[0156] If the video surveillance equipment does not meet the second preset condition, the probability of occurrence corresponding to the start-up decision factor will be determined to be 0.

[0157] When the power-on of the video surveillance device meets the second preset condition, the preset occurrence probability is determined as the occurrence probability corresponding to the power-on decision factor.

[0158] Optionally, the traffic initiation decision factor includes an alarm factor and a user habit factor; the preset occurrence probability includes a first preset occurrence probability corresponding to the user habit factor and a second preset occurrence probability corresponding to the alarm factor; the occurrence probability includes the habit occurrence probability corresponding to the user habit factor and the alarm occurrence probability corresponding to the alarm factor.

[0159] Optionally, the first determining module 520 is specifically used for:

[0160] If the start-up of the video surveillance device meets the second preset condition that the start-up of the video surveillance device is in line with the user's habitual location and / or time, the first preset occurrence probability is determined as the habit occurrence probability corresponding to the user habit factor;

[0161] And / or,

[0162] When the power-on condition of the video surveillance device meets the second preset condition and the video surveillance device generates alarm information, the second preset occurrence probability is determined as the alarm occurrence probability corresponding to the alarm factor.

[0163] Optionally, the starting decision factor may also include the number of devices corresponding to the at least one video surveillance device.

[0164] Optionally, the first determining module 520 is specifically used for:

[0165] Upon receiving alarm information corresponding to the video surveillance device, the target alarm type is determined based on the alarm information;

[0166] Based on the target alarm type and the historical start-up data, determine the alarm weight corresponding to the alarm factor;

[0167] Based on the historical user data, determine the habit weights corresponding to the user habit factors;

[0168] The first initiation probability is determined based on a preset constant, the alarm occurrence probability and alarm weight corresponding to the alarm factor, and the habit occurrence probability and habit weight corresponding to the user habit factor.

[0169] The device weights corresponding to the video surveillance devices are determined based on the number of devices.

[0170] The starting probability of the video surveillance device is determined based on the first starting probability and the device weight.

[0171] Optionally, the second determining module 530 is specifically used for:

[0172] Each of the stated start-up probabilities is compared with a preset start-up threshold to determine the start-up decision result;

[0173] Sort the current activation probabilities in descending order to determine the current activation priority ranking result corresponding to the at least one video surveillance device;

[0174] Based on the streaming priority ranking result and the streaming decision result, the streaming media decision result corresponding to the at least one video surveillance device is determined.

[0175] Optionally, the video surveillance streaming decision-making device 500 also includes an update module, which is specifically used for:

[0176] Obtain abnormal flow start data;

[0177] If the abnormal start-up data differs from the start-up priority ranking result, based on the abnormal start-up data, the abnormal factor corresponding to the video surveillance device is determined from the start-up decision factors; the abnormal occurrence probability corresponding to the abnormal factor is updated, and based on the abnormal occurrence probability, the start-up probability of the video surveillance device is updated.

[0178] And / or,

[0179] If the abnormal start-up data differs from the start-up decision result, the start-up preset threshold is updated based on the abnormal start-up data.

[0180] Figure 6 This is a schematic diagram of the structure of the electronic device provided in the embodiment of the present invention, such as... Figure 6 As shown, the electronic device may include: a processor 610, a communications interface 620, a memory 630, and a communication bus 640, wherein the processor 610, the communications interface 620, and the memory 630 communicate with each other via the communication bus 640. The processor 610 can call logical instructions in the memory 630 to execute a video surveillance streaming media decision-making method, which includes:

[0181] Obtain the starting decision factor corresponding to each of the video surveillance devices in at least one video surveillance device;

[0182] Based on each of the aforementioned start-up decision factors, the start-up probability of each of the aforementioned video surveillance devices is determined;

[0183] Based on the streaming start probability, a streaming media decision result is determined for each of the at least one video surveillance devices. The streaming media decision result is used to characterize whether each of the video surveillance devices has started streaming in advance. When the streaming media decision result characterizes that each of the video surveillance devices has started streaming in advance, the streaming media decision result carries the corresponding pre-start streaming prediction order.

[0184] Furthermore, the logical instructions in the aforementioned memory 630 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or a 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.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. 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.

[0185] On the other hand, the present invention also provides a computer program product, the computer program product comprising a computer program that can be stored on a computer-readable storage medium, wherein when the computer program is executed by a processor, the computer is able to execute the video surveillance streaming media decision-making method provided by the above methods, the method comprising:

[0186] Obtain the starting decision factor corresponding to each of the video surveillance devices in at least one video surveillance device;

[0187] Based on each of the aforementioned start-up decision factors, the start-up probability of each of the aforementioned video surveillance devices is determined;

[0188] Based on the streaming start probability, a streaming media decision result is determined for each of the at least one video surveillance devices. The streaming media decision result is used to characterize whether each of the video surveillance devices has started streaming in advance. When the streaming media decision result characterizes that each of the video surveillance devices has started streaming in advance, the streaming media decision result carries the corresponding pre-start streaming prediction order.

[0189] In another aspect, the present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to perform the video surveillance streaming media decision-making method provided by the methods described above, the method comprising:

[0190] Obtain the starting decision factor corresponding to each of the video surveillance devices in at least one video surveillance device;

[0191] Based on each of the aforementioned start-up decision factors, the start-up probability of each of the aforementioned video surveillance devices is determined;

[0192] Based on the streaming start probability, a streaming media decision result is determined for each of the at least one video surveillance devices. The streaming media decision result is used to characterize whether each of the video surveillance devices has started streaming in advance. When the streaming media decision result characterizes that each of the video surveillance devices has started streaming in advance, the streaming media decision result carries the corresponding pre-start streaming prediction order.

[0193] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0194] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0195] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A video surveillance streaming media decision-making method, characterized in that, include: Obtain the starting decision factor corresponding to each of the video surveillance devices in at least one video surveillance device; The start-up decision factors include alarm factors, user habit factors, and the number of devices corresponding to the at least one video surveillance device. Based on each of the aforementioned start-up decision factors, the start-up probability of each of the aforementioned video surveillance devices is determined; Based on each of the aforementioned streaming start probabilities, a streaming media decision result is determined for each of the at least one video surveillance devices. The streaming media decision result is used to characterize whether each of the video surveillance devices has pre-started streaming. In the case where the streaming media decision result characterizes that each of the video surveillance devices has pre-started streaming, the streaming media decision result carries the corresponding pre-start prediction order. The determination of the activation probability of each video surveillance device based on each of the activation decision factors includes: Under the condition that the first preset condition is met, the probability of starting the video surveillance device is determined to be 1; If the first preset condition is not met, for each video surveillance device, determine the probability of occurrence corresponding to the start-up decision factor; based on the start-up decision factor and the corresponding probability of occurrence, determine the start-up probability of the video surveillance device. The first preset conditions include: A preset alarm in the aforementioned start-up decision factor is triggered; or, The number of devices corresponding to the at least one video surveillance device is one.

2. The video surveillance streaming media decision-making method according to claim 1, characterized in that, Determining the occurrence probability corresponding to the initiation decision factor includes: Obtain historical flow start data; Based on the historical start-up data, the preset occurrence probability corresponding to the start-up decision factor is determined; If the video surveillance equipment does not meet the second preset condition, the probability of occurrence corresponding to the start-up decision factor will be determined to be 0. When the power-on of the video surveillance device meets the second preset condition, the preset occurrence probability is determined as the occurrence probability corresponding to the power-on decision factor.

3. The video surveillance streaming media decision-making method according to claim 2, characterized in that, The preset occurrence probability includes a first preset occurrence probability corresponding to the user habit factor and a second preset occurrence probability corresponding to the alarm factor; the occurrence probability includes the habit occurrence probability corresponding to the user habit factor and the alarm occurrence probability corresponding to the alarm factor. When the power-on condition of the video surveillance device is met, determining the second preset probability of occurrence as the probability of occurrence corresponding to the power-on decision factor includes: If the start-up of the video surveillance device meets the second preset condition that the start-up of the video surveillance device is in line with the user's habitual location and / or time, the first preset occurrence probability is determined as the habit occurrence probability corresponding to the user habit factor; And / or, When the power-on condition of the video surveillance device meets the second preset condition and the video surveillance device generates alarm information, the second preset occurrence probability is determined as the alarm occurrence probability corresponding to the alarm factor.

4. The video surveillance streaming media decision-making method according to claim 3, characterized in that, The step of determining the activation probability of the video surveillance device based on the activation decision factor and the corresponding occurrence probability includes: Upon receiving alarm information corresponding to the video surveillance device, the target alarm type is determined based on the alarm information; Based on the target alarm type and the historical start-up data, determine the alarm weight corresponding to the alarm factor; Based on the historical user data, determine the habit weights corresponding to the user habit factors; The first initiation probability is determined based on a preset constant, the alarm occurrence probability and alarm weight corresponding to the alarm factor, and the habit occurrence probability and habit weight corresponding to the user habit factor. The device weights corresponding to the video surveillance devices are determined based on the number of devices. The starting probability of the video surveillance device is determined based on the first starting probability and the device weight.

5. The video surveillance streaming media decision-making method according to any one of claims 1-4, characterized in that, The determination of the streaming media decision result corresponding to the at least one video surveillance device based on each of the aforementioned streaming start probabilities includes: Each of the stated start-up probabilities is compared with a preset start-up threshold to determine the start-up decision result; Sort the current activation probabilities in descending order to determine the current activation priority ranking result corresponding to the at least one video surveillance device; Based on the streaming priority ranking result and the streaming decision result, the streaming media decision result corresponding to the at least one video surveillance device is determined.

6. The video surveillance streaming media decision-making method according to claim 5, characterized in that, The method further includes: Obtain abnormal flow start data; If the abnormal start-up data differs from the start-up priority ranking result, based on the abnormal start-up data, the abnormal factor corresponding to the video surveillance device is determined from the start-up decision factors; the abnormal occurrence probability corresponding to the abnormal factor is updated, and based on the abnormal occurrence probability, the start-up probability of the video surveillance device is updated. And / or, If the abnormal start-up data differs from the start-up decision result, the start-up preset threshold is updated based on the abnormal start-up data.

7. A video surveillance streaming media decision-making device, characterized in that, include: The acquisition module is used to acquire the starting decision factors corresponding to each of the video surveillance devices in at least one video surveillance device; the starting decision factors include alarm factors, user habit factors and the number of devices corresponding to the at least one video surveillance device. The first determining module is used to determine the activation probability of each video surveillance device based on each of the activation decision factors. The second determining module is used to determine the streaming media decision result corresponding to the at least one video surveillance device based on each of the streaming start probabilities. The streaming media decision result is used to characterize whether each of the video surveillance devices has started streaming in advance. When the streaming media decision result characterizes that each of the video surveillance devices has started streaming in advance, the streaming media decision result carries the corresponding pre-start prediction order. The first determining module is specifically used for: determining the starting probability of the video surveillance device to be 1 when the first preset condition is met; and determining the occurrence probability corresponding to the starting decision factor for each video surveillance device when the first preset condition is not met. Based on the aforementioned start-up decision factor and its corresponding occurrence probability, the start-up probability of the video surveillance device is determined. The first preset condition includes: the occurrence of a preset alarm in the start-up decision factor; Alternatively, the number of devices corresponding to the at least one video surveillance device is one.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the video surveillance streaming media decision-making method as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the video surveillance streaming media decision-making method as described in any one of claims 1-6.

Images