An intrusion monitoring method, device, equipment and storage medium

Abstract

The application discloses an intrusion monitoring method and device, equipment and a storage medium, and relates to the technical field of intelligent monitoring, and comprises the following steps: image acquisition is performed on a current target place, and face information in the collected image is extracted to obtain to-be-detected face information; it is judged whether the to-be-detected face information is current face information which has not been saved; if the to-be-detected face information is current face information which has not been saved, historical face information extracted in a neighboring historical time period is acquired, and it is judged whether the historical face information exists in a preset safe face information record table to obtain a corresponding judgment result; and it is determined whether an intrusion alarm operation is triggered for the current target place based on the judgment result. The application identifies face information of surrounding personnel, judges whether safe personnel exist around the face information to determine whether an alarm operation is triggered, and effectively realizes intrusion monitoring of untrusted personnel by means of an intelligent home device.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent monitoring, and in particular to an intrusion monitoring method, device, equipment and storage medium. BACKGROUND

[0002] With the continuous development of science and technology, artificial intelligence has gradually entered people's lives, and more and more smart homes have appeared and provided many conveniences for people. Smart home is a platform based on residence, which uses integrated wiring technology, network communication technology, security protection technology, automatic control technology, audio and video technology to integrate facilities related to home life, build an efficient residential facility and home affairs management system, and improve the safety, convenience, comfort, artistry and environmentally friendly energy-saving living environment of the home.

[0003] With the continuous improvement of people's safety awareness, many smart homes are equipped with monitoring devices to ensure the safety of the residence. For example, many existing smart speakers already have a camera that can rotate according to sound and have powerful computing power to achieve face recognition locally. However, the monitoring effect of the monitoring device is relatively poor, and how to improve the monitoring effect is a problem to be solved at present. SUMMARY

[0004] Therefore, the purpose of the present application is to provide an intrusion monitoring method, device, equipment and storage medium, which can effectively detect the intrusion of untrusted personnel through smart home devices and improve the security effect. The specific scheme is as follows:

[0005] In a first aspect, the present application discloses an intrusion monitoring method applied to a smart home device, comprising:

[0006] Image collection is performed on a current target place, and face information in the collected image is extracted to obtain to-be-detected face information;

[0007] It is judged whether the to-be-detected face information is current unrecorded face information;

[0008] If the to-be-detected face information is current unrecorded face information, historical face information extracted in a neighboring historical time period is obtained, and it is judged whether the historical face information exists in a preset safe face information record table to obtain a corresponding judgment result;

[0009] Based on the judgment result, it is determined whether to trigger an intrusion alarm operation for the current target place.

[0010] Optionally, the judgment of whether the to-be-detected face information is current unrecorded face information comprises:

[0011] obtain a temporary face information record table, the temporary face information record table being used to save face information extracted in a target time period and meeting a preset saving condition, the target time period being a time period corresponding to a time point of capturing the image;

[0012] determine whether the to-be-detected face information exists in the temporary face information record table and the preset security face information record table, and if the to-be-detected face information does not exist in the temporary face information record table and the preset security face information record table, determine that the to-be-detected face information is current face information that is not saved.

[0013] Optionally, after the determination of whether the to-be-detected face information exists in the temporary face information record table and the preset security face information record table, the method further comprises:

[0014] if the to-be-detected face information exists in any of the temporary face information record table and the preset security face information record table, determine that the to-be-detected face information meets a first saving condition, and save the to-be-detected face information to the temporary face information record table.

[0015] Optionally, after the determination of whether the historical face information exists in the preset security face information record table, the method further comprises:

[0016] if the historical face information exists in the preset security face information record table, determine that the to-be-detected face information meets a second saving condition, and save the to-be-detected face information to the temporary face information record table.

[0017] Optionally, the method further comprises:

[0018] determine whether a current time point is an end time point of the target time period;

[0019] if the current time point is the end time point of the target time period, update a weight of face information in the preset security face information record table based on the temporary face information record table, and remove face information with a weight less than a preset weight threshold from the preset security face information record table.

[0020] Optionally, the updating of the weight of the face information in the preset security face information record table based on the temporary face information record table comprises:

[0021] delete face information with a number of occurrences less than a preset number threshold from the temporary face information record table to obtain a first adjusted record table;

[0022] perform a deduplication process on the face information in the first adjusted record table to obtain a second adjusted record table;

[0023] Determine whether the facial information in the second adjusted record table exists in the preset secure facial information record table. If it does, then perform weight increase processing on the corresponding facial information in the preset secure facial information record table according to the preset weight increase rule.

[0024] Optionally, after performing weighting processing on the corresponding face information in the preset secure face information record table according to the preset weighting rule, the method further includes:

[0025] If it is detected that the duration for which any face information in the current preset secure face information record table has not undergone the weight increase processing is not less than a preset number of time periods, then the corresponding face information in the preset secure face information record table will undergo weight reduction processing according to the preset weight reduction rule.

[0026] Optionally, determining whether to trigger an intrusion alarm operation for the current target location based on the judgment result includes:

[0027] If the historical face information is not found in the preset secure face information record table, an alarm message containing the image corresponding to the face information to be detected is generated, and the alarm message is sent to the preset user terminal so that the preset user terminal can return the corresponding alarm processing instruction according to the alarm message.

[0028] If the alarm processing instruction is the first alarm processing instruction, then the local preset alarm device is controlled to trigger the corresponding alarm;

[0029] If the alarm processing instruction is the second alarm processing instruction, then the face information to be detected is added to the preset secure face information record table.

[0030] Optionally, adding the face information to be detected to the preset secure face information record table includes:

[0031] The face information to be detected is added to the preset secure face information record table, and a preset permission identifier is configured for the face information to be detected added to the preset secure face information record table, so as to prevent the background from automatically deleting the face information to be detected added to the preset secure face information record table based on the preset permission identifier;

[0032] Alternatively, the face information to be detected can be added to the preset secure face information record table, and an initial weight can be configured for the face information to be detected added to the preset secure face information record table through a preset weight configuration interface.

[0033] Secondly, this application discloses an intrusion monitoring device for use in smart home devices, comprising:

[0034] The image acquisition module is used to acquire images of the current target location;

[0035] The information acquisition module is used to extract facial information from the acquired images to obtain the facial information to be detected;

[0036] The first judgment module is used to determine whether the face information to be detected is face information that has not been saved at present;

[0037] The second judgment module is used to obtain historical face information extracted in adjacent historical time periods if the face information to be detected is face information that has not been saved at present, and to determine whether the historical face information exists in the preset safe face information record table, so as to obtain the corresponding judgment result.

[0038] The alarm triggering module is used to determine whether to trigger an intrusion alarm operation for the current target location based on the judgment result.

[0039] Thirdly, this application discloses an electronic device, including:

[0040] Memory, used to store computer programs;

[0041] A processor for executing the computer program to implement the aforementioned intrusion monitoring method.

[0042] Fourthly, this application discloses a computer-readable storage medium for storing a computer program, which, when executed by a processor, implements the aforementioned intrusion monitoring method.

[0043] As can be seen, this application uses smart home devices to capture images of the current target location and extracts facial information from the captured images to obtain the facial information to be detected. Then, it determines whether the facial information to be detected is currently unsaved. If the facial information to be detected is unsaved, it acquires historical facial information extracted from adjacent historical time periods and determines whether the historical facial information exists in a preset secure facial information record table to obtain a corresponding judgment result. Finally, based on the judgment result, it determines whether to trigger an intrusion alarm operation for the current target location. Therefore, this application determines whether to trigger an alarm operation by judging whether the facial information appearing in the current target location is currently unsaved, then determining whether there are security personnel around the facial information. In this way, it can determine whether there are security personnel accompanying the unsaved person while simultaneously identifying the unsaved person, avoiding the situation where an alarm is triggered simply by recognizing a stranger. This makes the intrusion monitoring process more intelligent and effectively improves the security effect of intrusion monitoring. Attached Figure Description

[0044] To more clearly illustrate the technical solutions in the embodiments of the present 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 only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0045] Figure 1 This is a flowchart of an intrusion monitoring method disclosed in this application;

[0046] Figure 2 This is a flowchart of a specific intrusion monitoring method disclosed in this application;

[0047] Figure 3 This is a flowchart of a specific intrusion monitoring method disclosed in this application;

[0048] Figure 4 This is a flowchart of a specific intrusion monitoring method disclosed in this application;

[0049] Figure 5 This is a flowchart of a specific intrusion monitoring method disclosed in this application;

[0050] Figure 6 This is a schematic diagram of the structure of an intrusion monitoring device disclosed in this application;

[0051] Figure 7 This is a structural diagram of an electronic device disclosed in this application. Detailed Implementation

[0052] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0053] As people become increasingly security-conscious, many smart homes are equipped with surveillance devices to ensure home security. For example, many existing smart speakers now have cameras that rotate based on sound and possess powerful computing capabilities, enabling local facial recognition. However, the monitoring effectiveness of current surveillance equipment is relatively poor, and how to improve monitoring performance remains a problem to be solved.

[0054] For this reason, see Figure 1 As shown in the figure, this application discloses an intrusion monitoring method applied to smart home devices, including:

[0055] Step S11: Acquire images of the current target location and extract facial information from the acquired images to obtain the facial information to be detected.

[0056] In this embodiment, an image of the current target location is captured by a camera device on a smart home device, and facial information is extracted from the captured image using facial recognition technology to obtain the facial information to be detected. It is understood that the facial information includes, but is not limited to, facial encoding information generated by extracting facial feature information using facial recognition technology and matching the facial feature information, image time information, and facial images. Furthermore, the facial encoding information can be generated in real-time based on the facial feature information, or several encoding information can be generated in advance. When new facial feature information is extracted, one of the pre-generated encoding information is selected to match the new facial feature information. It is understood that one facial feature information corresponds to only one facial encoding information. It should be noted that the camera device on the smart home device can also rotate according to the direction of the sound source to adjust the camera position, so as to determine the position of the object to be identified based on the sound and acquire the facial information of the object to be identified. In this way, by using facial recognition technology to collect facial information in real time and matching the corresponding facial code information, the facial information of people appearing in the current target location can be quickly obtained. And by rotating the camera according to the direction of the sound source to collect the image, the situation of missed collection can be effectively prevented.

[0057] In this embodiment, smart home devices include, but are not limited to, smart speakers, smart screens, smart trash cans, robot vacuum cleaners, and other types of smart home appliances.

[0058] Step S12: Determine whether the face information to be detected is face information that has not been saved at present.

[0059] In this embodiment, after acquiring images and extracting the face information to be detected using a camera device, the system determines whether the face information to be detected is a face information that has not been saved, based on the face information data recorded in the system's backend. It can be understood that by comparing whether there is matching encoding information in the face information data recorded in the system's backend with the face encoding information of the face information to be detected, it is determined whether the face information to be detected is a face information that has not been recorded and saved in the current system backend, so as to determine whether to proceed to the next step based on the detection result. It should be noted that in one special case, if the currently identified facial information was previously recorded and saved by the system in the background during monitoring, but has not been identified again for a long period, the system automatically deletes the background data of that facial information. When the facial information is identified again, it will still be considered an unsaved facial, requiring further steps to be performed. In another special case, if the currently identified facial information has already been identified once within a certain time period and has not been trusted and saved to the system's background data, when the facial information is identified again within the same time period, it will still be judged as an unsaved facial to prevent harm to the user's personal and property safety. In this way, by first determining whether the facial information to be detected is an unsaved facial by checking the background recorded data, automatic identification and accurate judgment of whether the facial information belongs to an untrusted person can be achieved, avoiding manual intervention and effectively improving the efficiency and effectiveness of intrusion detection.

[0060] Step S13: If the face information to be detected is face information that has not been saved at present, then obtain the historical face information extracted in the adjacent historical time period, and determine whether the historical face information exists in the preset secure face information record table, so as to obtain the corresponding judgment result.

[0061] In this embodiment, if the facial information to be detected is determined to be an unsaved facial information based on the facial information data recorded in the system background, then historical facial information extracted within adjacent historical time periods is obtained, and it is determined whether the historical facial information exists in the preset secure facial information record table, in order to determine whether there are security personnel accompanying the person to be identified, and obtain the corresponding judgment result. It should be noted that, as shown in Table 1 below, the preset secure facial information record table is a data table that records the facial information of all security personnel, including but not limited to facial encoding information, weight value, last weighting time, whether it is a permanent member, etc., wherein the facial encoding information is information reflecting the facial features of the person to be identified, the weight value can be understood as the trust level of the facial information, the higher the weight value, the higher the trust level of the corresponding facial information, the last weighting time is the time when the weight value corresponding to the facial information was last increased, and whether it is a permanent member can be set by the user. If the user sets a certain facial encoding information as a permanent member, the system will not automatically delete the facial encoding information. Furthermore, the preset secure facial information record table can be updated by user input or based on historical data recorded in the system backend.

[0062] Table 1

[0063] Face encoding information Weight value Last weighting time Whether a permanent member 011202323232 280 2020 / 07 / 08 N 067677676655 1000 2020 / 07 / 05 Y

[0064] As shown in Table 1, for example, the face code information corresponding to a certain security personnel in the preset security face information record table is 011202323232, the weight value is 280, and the last weighting time is July 8, 2020.

[0065] In this embodiment, the adjacent historical time period is a preset time period forward or backward based on the image time information in the collected facial information. Users can set the preset time period themselves using the preset time setting interface on the smart home device. For example, if the user sets the preset time to 5 minutes, when the detected facial information is not currently saved, the system will retrieve historical facial information extracted within the previous 5 minutes of the image time information. In this way, by comparing whether historical facial information within the historical time period exists in the preset safe facial information record table, it can determine whether safe facial information exists around the detected facial information. This allows for automatic determination of whether a safe person is accompanying the target, avoiding triggering an alarm system upon detecting a facial information not currently saved in the system. This prevents situations where an alarm is triggered when a user's relatives or friends visit for the first time or when a repairman comes to perform repairs, avoiding resource waste and memory occupation. This enables the system to automatically recognize and learn facial information.

[0066] Step S14: Based on the judgment result, determine whether to trigger an intrusion alarm operation for the current target location.

[0067] In this embodiment, if the historical face information is not found in the preset secure face information record table, it is determined that no security personnel are accompanying the target object, and an intrusion alarm operation will be triggered for the current target location. The intrusion alarm operation includes, but is not limited to, directly triggering a voice alarm system or sending information indicating an intrusion to the user, so that the user can determine whether to trigger the alarm system based on the information. In this way, by judging whether to trigger an intrusion alarm operation based on information feedback, automatic intrusion monitoring and alarm operations can be achieved, effectively improving security.

[0068] In this embodiment, when the user does not interact with the smart home device, the smart home device can rotate the camera to patrol the current target location, so as to realize real-time monitoring of whether there are untrustworthy persons around the target location. This can effectively improve the monitoring effect, prevent missed detections that could lead to the user's safety and property being harmed, and improve the security effect.

[0069] As can be seen, this application uses smart home devices to capture images of the current target location and extracts facial information from the captured images to obtain the facial information to be detected. Then, it determines whether the facial information to be detected is currently unsaved. If the facial information to be detected is currently unsaved, it acquires historical facial information extracted from adjacent historical time periods and determines whether the historical facial information exists in a preset secure facial information record table to obtain a corresponding judgment result. Finally, based on the judgment result, it determines whether to trigger an intrusion alarm operation for the current target location. Therefore, this application determines whether to trigger an alarm operation by judging whether the facial information appearing in the current target location is currently unsaved, then determining whether there are security personnel around the facial information. In this way, it can determine whether there are security personnel accompanying the unsaved person while simultaneously identifying the unsaved person, avoiding the situation where an alarm is triggered simply by identifying an untrusted person. This makes the intrusion monitoring process more intelligent and effectively improves the security effect of intrusion monitoring.

[0070] Based on the above embodiments, the general process of the intrusion monitoring method is as follows. The process of determining whether the face information is currently not saved based on system background data will be described in detail below. See [link to documentation]. Figure 2 As shown in the figure, this application discloses a specific intrusion monitoring method applied to smart home devices, including:

[0071] Step S21: Acquire images of the current target location and extract facial information from the acquired images to obtain the facial information to be detected.

[0072] Step S22: Obtain a temporary face information record table; the temporary face information record table is used to save face information extracted within a target time period that meets the preset saving conditions, the target time period being the time period corresponding to the acquisition time of the image.

[0073] In this embodiment, after acquiring the face information to be detected, a temporary face information record table needs to be obtained, which records face information extracted within a target time period that meets preset storage conditions. This table is used to determine whether the face information to be detected is currently not saved, based on the temporary face information record table and the preset security personnel information record table. The temporary face information record table is used to save face information extracted within a target time period that meets preset storage conditions. The target time period is the time period corresponding to the acquisition time of the image. It should be further noted that, as shown in Table 2 below, the data recorded in the temporary face information record table includes, but is not limited to, face encoding information, time information, and whether an alarm is triggered. The time information is the moment when the face encoding information is recorded in the temporary face information record table, and whether an alarm is triggered refers to whether an alarm operation is triggered when the current face encoding information is detected.

[0074] Table 2

[0075] Face encoding information Time information Whether to trigger an alarm 011202323232 08:34:45 N 067677676655 09:12:11 N

[0076] As shown in Table 2, for example, the face code information detected in the current target scene is 011202323232. The time information of recording the detection information in the table is 8:34:45. No alarm operation was triggered when the face code information was detected.

[0077] Furthermore, meeting the preset storage conditions means that the face encoding information of the face to be detected exists in the face information data recorded in the system background, or that the face information of a security person matching the preset secure face information record table exists in the vicinity of the face information to be detected within an adjacent time period. The target time period can be the system default or set by the user based on a preset interface. It should be noted that after one target time period, the temporary face information record table needs to be integrated and cleared according to preset rules so that new face information can be recorded in the next target time period. For example, if the target time period is 24 hours, the temporary face information record table will record all face information detected between 00:00 AM and 00:00 AM the next day that meets the preset storage conditions, and at 00:00 AM the next day, the data recorded in the current temporary face information record table will be integrated and cleared. This timely organization of the records in the temporary face information record table improves the effectiveness of intrusion detection, and timely clearing of infrequently seen face information such as visiting relatives or delivery personnel reduces memory usage.

[0078] Step S23: Determine whether the face information to be detected exists in the temporary face information record table and the preset secure face information record table. If the face information to be detected does not exist in either table, then determine that the face information to be detected is currently unsaved face information.

[0079] In this embodiment, after obtaining the temporary face information record table, it is determined whether the face information to be detected exists in the temporary face information record table and the preset secure face information record table. If the face information to be detected does not exist in either the temporary face information record table or the preset secure face information record table, then the face information to be detected is determined to be face information that has not been saved at present.

[0080] In this embodiment, after determining whether the face information to be detected exists in the temporary face information record table and the preset secure face information record table, the method may further include: if the face information to be detected exists in either the temporary face information record table or the preset secure face information record table, then the face information to be detected is determined to meet the first storage condition, and the face information to be detected is saved to the temporary face information record table. That is, when the face encoding information in the face information to be detected exists in either the temporary face information record table or the preset secure face information record table, the face information to be detected is determined to meet the first storage condition, and the face information to be detected is saved to the temporary face information record table to record the number of times the face information to be detected appears, and to update the preset secure face information record table based on preset rules. In this way, by detecting facial information in real time and recording it in the temporary facial information record table, and by judging whether the facial information to be detected belongs to an untrusted person based on the temporary facial information record table and the preset secure facial information record table, the process of automatic recording and detection is realized. By recording temporary facial information and secure facial information in two separate tables, intrusion monitoring can be carried out more clearly through data tables, thereby improving the efficiency and effectiveness of monitoring.

[0081] Step S24: If the face information to be detected is face information that has not been saved at present, then obtain the historical face information extracted in the adjacent historical time period, and determine whether the historical face information exists in the preset secure face information record table, so as to obtain the corresponding judgment result.

[0082] In this embodiment, after determining whether the historical face information exists in the preset secure face information record table, the method may further include: if the historical face information exists in the preset secure face information record table, then the face information to be detected is determined to meet the second storage condition, and the face information to be detected is saved to the temporary face information record table. That is, if the historical face information in the temporary face information record table exists in the preset secure face information record table within an adjacent historical time period, then it is determined that a security person is accompanying the person to be identified, the face information to be detected meets the second storage condition, and the face information to be detected is saved to the temporary face information record table.

[0083] Step S25: Based on the judgment result, determine whether to trigger an intrusion alarm operation for the current target location.

[0084] The specific processes of steps S21, S24 to S25 can be found in the relevant content disclosed in the foregoing embodiments, and will not be repeated here.

[0085] As can be seen, this embodiment determines whether the face information to be detected exists in the temporary face information record table and the preset secure face information record table, and then determines whether the face information to be detected is currently not saved. Furthermore, when the face information to be detected meets preset conditions, it is saved to the temporary face information record table. In this way, dividing the face information data stored in the system backend into a temporary face information record table and a preset secure face information record table allows for a clearer recording of historical face information as belonging to uncommon or familiar secure individuals. This facilitates a clearer determination of whether the person to be detected is untrusted during intrusion monitoring, improving the efficiency and effectiveness of intrusion monitoring and ensuring the personal and property safety of users.

[0086] As can be seen from the above embodiments, the system utilizes a temporary face information recording table and a preset secure face information recording table to record and determine the face information to be detected. The process of triggering the alarm operation will be described in detail below. See [link to documentation]. Figure 3 As shown in the figure, this application discloses a specific intrusion monitoring method applied to smart home devices, including:

[0087] Step S31: Acquire images of the current target location and extract facial information from the acquired images to obtain the facial information to be detected.

[0088] Step S32: Determine whether the face information to be detected is face information that has not been saved at present.

[0089] Step S33: If the face information to be detected is face information that has not been saved at present, then obtain the historical face information extracted in the adjacent historical time period, and determine whether the historical face information exists in the preset secure face information record table, so as to obtain the corresponding judgment result.

[0090] Step S34: If the historical face information does not exist in the preset secure face information record table, an alarm message containing the image corresponding to the face information to be detected is generated, and the alarm message is sent to the preset user terminal so that the preset user terminal can return the corresponding alarm processing instruction according to the alarm message.

[0091] In this embodiment, if the face information to be detected is not currently saved, and the historical face information does not exist in the preset secure face information record table, then an alarm message containing the image corresponding to the face information to be detected is generated, and the alarm message is sent to a preset user terminal so that the preset user terminal can return the corresponding alarm handling instruction based on the alarm message. It should be further noted that the preset user terminal can be a pre-bound smartphone, smart tablet, or other mobile device so that the user can view the alarm message promptly. In this way, by feeding back the alarm message to the preset user terminal so that the user can determine the alarm handling instruction based on the image containing the face information to be detected, it avoids directly triggering an alarm when someone the user knows arrives at the target location. Furthermore, the addition of a human-computer interaction process makes the automatic intrusion monitoring process controllable, improving the effectiveness of intrusion monitoring.

[0092] Step S35: If the alarm processing instruction is the first alarm processing instruction, then control the locally preset alarm device to trigger the corresponding alarm.

[0093] In this embodiment, if the alarm processing instruction returned by the preset user terminal is a first alarm processing instruction, then the locally preset alarm device is controlled to trigger the corresponding alarm. It is understood that the alarm device can be an alarm device inherent in the smart home device itself, or an external alarm device connected to the smart home device. It should be noted that triggering the corresponding alarm can be a voice alarm, and the content of the voice alarm can be set by the user. In this way, the alarm device can warn the person to be identified, preventing further harm to the user's personal safety and property.

[0094] Step S36: If the alarm processing instruction is the second alarm processing instruction, then add the face information to be detected to the preset secure face information record table.

[0095] In this embodiment, if the alarm processing instruction returned by the preset user terminal is the second alarm processing instruction, the face information to be detected is added to the preset secure face information record table. In this way, the system can be informed that the face information to be detected is a face information recognized by the user, so there is no need to trigger an alarm. The face information to be detected is also recorded in the preset security information record table to prevent alarm information from being fed back again when the face information to be detected is detected next time.

[0096] In a first specific implementation, adding the face information to be detected to the preset secure face information record table may include: adding the face information to be detected to the preset secure face information record table, and configuring a preset permission identifier for the face information added to the preset secure face information record table. This preset permission identifier prevents the background system from automatically deleting the face information added to the preset secure face information record table, effectively permanently saving the face information to be detected in the preset secure face information record table. This prevents the system background from issuing an alarm when it detects the face information again. The preset permission identifier is the "whether it is a permanent member" field in the preset secure face information record table. If a preset permission identifier needs to be configured for the face information to be detected, the data in the "whether it is a permanent member" field corresponding to the face information to be detected in the preset secure face information record table can be changed from N to Y. This effectively avoids duplicate alarms and improves the effectiveness of intrusion monitoring.

[0097] In a second specific implementation, adding the face information to be detected to the preset secure face information record table may include: adding the face information to be detected to the preset secure face information record table, and configuring an initial weight for the face information added to the preset secure face information record table through a preset weight configuration interface. That is, after the user informs the system to store the face information to be detected in the preset secure face information record table, an initial weight can be configured for the face information to be detected, so that the system can update the data in the preset secure face information record table according to preset rules. It is understood that when the weight corresponding to the stored face information to be detected is less than a preset value, the system can delete the face information to be detected according to preset rules. In this way, face information of people who need to enter and exit the target location multiple times within a certain period can be stored, avoiding repeated judgment of the face information by the user, reducing manual intervention by the user, and improving the effectiveness of intrusion monitoring.

[0098] The specific processes of steps S31 to S33 can be found in the relevant content disclosed in the foregoing embodiments, and will not be repeated here.

[0099] As can be seen, this embodiment sends alarm information containing the image corresponding to the face information to be detected to the user, so that the user can determine the alarm handling instruction based on the alarm information. If the alarm handling instruction is a first alarm handling instruction, the local preset alarm device is controlled to trigger the corresponding alarm. If the alarm handling instruction is a second alarm handling instruction, the face information to be detected is added to the preset secure face information record table. The user can also set the weight and permission identifier of the face information to be detected in the preset secure face information record table. In this way, determining whether to trigger an alarm through manual intervention improves the controllability of automatic intrusion monitoring, and allows for customized settings based on user choices. This provides convenience to users while achieving automatic intrusion monitoring, effectively improving security.

[0100] refer to Figure 4 As shown, this application discloses a specific intrusion monitoring method with the following process: First, images of the current target location are captured, and facial information is obtained from the captured images to obtain the facial information to be detected. Then, it is determined whether the facial information to be detected exists in a temporary facial information record table and a preset secure facial information record table. If it exists, the facial information to be detected is saved to the temporary facial information record table, and the surrounding environment of the current target location is monitored. If it does not exist, it is determined whether historical facial information extracted in adjacent historical time periods exists in the preset secure facial information record table. If it exists, the facial information to be detected is saved to the temporary facial information record table, and the surrounding environment is monitored. If it does not exist, an alarm message is sent to the user. The user determines whether they recognize the facial information to be detected based on the alarm message. If the user recognizes the facial information to be detected, the facial information to be detected is added to the preset secure facial information record table. If the user does not recognize the facial information to be detected, an alarm device in the current target scene is triggered.

[0101] Based on the above embodiments, the specific implementation process of triggering the alarm operation in the intrusion monitoring method is as follows. The intrusion monitoring method includes an update operation on the secure face information record table. The following will describe in detail the operations of increasing and decreasing the weights of the secure face information record table. See [link to documentation]. Figure 5 As shown in the figure, this application discloses a specific intrusion monitoring method applied to smart home devices, including:

[0102] Step S41: Determine whether the current time is the end time of the target time period.

[0103] In this embodiment, based on step S22, it is known that when the target time period ends, the data in the temporary information record table needs to be integrated. Therefore, it is necessary to determine whether the current time is the end time of the target time period.

[0104] Step S42: If the current time is the end time of the target time period, delete face information that appears less than a preset threshold number of times from the temporary face information record table to obtain the first adjusted record table.

[0105] In this embodiment, when the current time is the end time of the target time period, face information appearing less than a preset threshold number is deleted from the temporary face information record table, resulting in a first adjusted record table. The preset threshold number can be a system default setting or a user-defined setting based on a preset interface. For example, if the user sets the preset threshold number to 3, face information appearing less than 3 times in the temporary face information record table is deleted at the end of the target time period, resulting in the first adjusted record table. This way, by deleting face information appearing less than the preset threshold number, some unimportant face information, such as that of delivery drivers and couriers, can be promptly removed, facilitating the system's automatic learning of security personnel's face information and real-time intrusion monitoring.

[0106] Step S43: Perform deduplication on the face information in the first adjusted record table to obtain the second adjusted record table.

[0107] In this embodiment, after obtaining the first adjusted record table, the facial information in the first adjusted record table is deduplicated to obtain a second adjusted record table, which is then used to update the preset secure facial information record table. In this way, the system can record individuals who appear multiple times within a target time period and temporarily designate them as secure individuals. This prevents the system from needing to manually identify individuals the next time they appear, as the information in the temporary facial information record table may be cleared, thus avoiding the need for user verification when the individual reappears. This achieves an automatic learning process for the system.

[0108] Step S44: Determine whether the face information in the second adjusted record table exists in the preset secure face information record table. If so, perform weight increase processing on the corresponding face information in the preset secure face information record table according to the preset weight increase rule.

[0109] In this embodiment, after obtaining the second adjusted record table, it is determined whether the facial information in the second adjusted record table exists in the preset secure facial information record table. If it does, the corresponding facial information in the preset secure facial information record table is weighted according to the preset weight increase rule. If not, the facial information is added to the preset secure facial information record table, and the facial information in the preset secure facial information record table is weighted according to the preset weight increase rule. The weight increase rule includes, but is not limited to, a weight increase value, which can be set by the user. For example, if the user sets the weight increase rule to increase by 10 each time, and the weight value of a certain facial information in the preset secure facial information record table is 500, when the facial information exists in the second adjusted record table, the weight value of the facial information is increased by 10, that is, the current weight value of the facial information is 510, and the last weighted time of the facial information is updated to the current time. In this way, by increasing the weight value in the preset secure facial information record table, the deletion due to excessively low weight can be prevented.

[0110] Step S45: If it is detected that the duration for which any face information in the current preset secure face information record table has not undergone the weight increase processing is not less than a preset number of time periods, then the corresponding face information in the preset secure face information record table is weighted according to the preset weight reduction rule.

[0111] In this embodiment, if it is detected that the duration for which any face information in the current preset secure face information record table has not undergone the weight increase processing is not less than a preset number of time periods, that is, the time difference between the last weighting time and the current time is greater than or equal to the preset number of time periods, then the corresponding face information in the preset secure face information record table is weighted according to the preset weight reduction rule. The weight reduction rule includes, but is not limited to, the weight increase value, and the weight reduction value and the preset number can be set by the user. For example, if the user sets the weight reduction rule to decrease by 10 each time, the preset number is 7, and the weight value of a certain face information in the preset secure face information record table is 500, and the last weighting time is 2022 / 05 / 20, when it is detected on 2022 / 5 / 28 that the duration for which the face information has not undergone the weight increase processing is greater than 7, then the weight value of the face information is reduced by 10, that is, the current weight value of the face information is 490. In this way, by updating the preset secure face information record table through weight reduction operations, the process of automatically learning face information is realized.

[0112] Step S46: Remove face information whose weight is less than the preset weight threshold from the preset secure face information record table.

[0113] In this embodiment, after completing the weight increase and weight decrease operations, face information with a weight less than a preset weight threshold in the preset secure face information record table is removed. This preset weight threshold can be set by the user. For example, if the user sets the preset weight threshold to 50, and the weight value of a certain face information in the preset secure face information record table is 40, then that face information is removed from the preset secure face information record table. This allows for the timely removal of face information from infrequently seen individuals, such as occasionally visiting relatives and friends, reducing memory usage and improving the effectiveness of intrusion monitoring.

[0114] As can be seen, in this embodiment, by deleting and deduplicating the temporary face information record table, an adjusted record table is obtained. Based on the adjusted record table and preset weight increase and decrease rules, the preset secure face information record table is subjected to weight increase and weight decrease operations, respectively, so as to update the temporary face information record table and the preset secure face information record table in a timely manner. In this way, the system can automatically learn face information during the update process, making the intrusion monitoring process more intelligent and improving the effectiveness of intrusion monitoring.

[0115] refer to Figure 6 The present application also discloses an intrusion monitoring device for use in smart home devices, comprising:

[0116] Image acquisition module 11 is used to acquire images of the current target location;

[0117] The information acquisition module 12 is used to extract facial information from the acquired images to obtain the facial information to be detected;

[0118] The first judgment module 13 is used to determine whether the face information to be detected is face information that has not been saved at present;

[0119] The second judgment module 14 is used to obtain historical face information extracted in adjacent historical time periods if the face information to be detected is face information that has not been saved at present, and to determine whether the historical face information exists in the preset safe face information record table, so as to obtain the corresponding judgment result.

[0120] The alarm triggering module 15 is used to determine whether to trigger an intrusion alarm operation for the current target location based on the judgment result.

[0121] As can be seen, this application uses smart home devices to capture images of the current target location and extracts facial information from the captured images to obtain the facial information to be detected. Then, it determines whether the facial information to be detected is currently unsaved. If the facial information to be detected is currently unsaved, it acquires historical facial information extracted from adjacent historical time periods and determines whether the historical facial information exists in a preset secure facial information record table to obtain a corresponding judgment result. Finally, based on the judgment result, it determines whether to trigger an intrusion alarm operation for the current target location. Therefore, this application determines whether to trigger an alarm operation by judging whether the facial information appearing in the current target location is currently unsaved, then determining whether there are security personnel around the facial information. In this way, it can determine whether there are security personnel accompanying the unsaved person while simultaneously identifying the unsaved person, avoiding the situation where an alarm is triggered simply by identifying an untrusted person. This makes the intrusion monitoring process more intelligent and effectively improves the security effect of intrusion monitoring.

[0122] In some specific embodiments, the first determining module 13 may specifically include:

[0123] A record table acquisition unit is used to acquire a temporary face information record table; the temporary face information record table is used to store face information extracted within a target time period that meets preset storage conditions, and the target time period is the time period corresponding to the acquisition time of the image;

[0124] The face information determination unit is used to determine whether the face information to be detected exists in the temporary face information record table and the preset secure face information record table. If the face information to be detected does not exist in either table, the face information to be detected is determined to be face information that has not been saved at present.

[0125] In some specific embodiments, the intrusion monitoring device may further include:

[0126] The first information storage module is used to determine that the face information to be detected meets the first storage condition if the face information to be detected exists in either the temporary face information record table or the preset secure face information record table, and to save the face information to be detected to the temporary face information record table.

[0127] In some specific embodiments, the intrusion monitoring device may further include:

[0128] The second information storage module is used to determine that the face information to be detected meets the second storage condition if the historical face information exists in the preset secure face information record table, and to save the face information to be detected to the temporary face information record table.

[0129] In some specific embodiments, the intrusion monitoring device may further include:

[0130] The time determination module is used to determine whether the current time is the end time of the target time period;

[0131] The weight update module is used to update the weights of face information in the preset secure face information record table based on the temporary face information record table if the current time is the end time of the target time period, and to remove face information in the preset secure face information record table whose weight is less than the preset weight threshold.

[0132] In some specific embodiments, the weight update module may specifically include:

[0133] The information deletion unit is used to delete face information that appears less than a preset threshold number of times from the temporary face information record table to obtain the first adjusted record table;

[0134] The record table deduplication unit is used to deduplicate the face information in the first adjusted record table to obtain the second adjusted record table.

[0135] The weighting unit is used to determine whether the face information in the second adjusted record table exists in the preset secure face information record table. If it does, the corresponding face information in the preset secure face information record table is weighted according to the preset weighting rule.

[0136] In some specific embodiments, the intrusion monitoring device may further include:

[0137] The weight reduction unit is used to perform weight reduction processing on the corresponding face information in the preset secure face information record table according to the preset weight reduction rule if the duration for which any face information in the current preset secure face information record table has not undergone the weight increase processing is not less than a preset number of time periods.

[0138] In some specific embodiments, the alarm triggering module 15 may specifically include:

[0139] The information sending submodule is used to generate alarm information containing the image corresponding to the face information to be detected if the historical face information does not exist in the preset secure face information record table, and send the alarm information to the preset user terminal so that the preset user terminal can return the corresponding alarm processing instruction according to the alarm information;

[0140] The alarm triggering submodule is used to control the locally preset alarm device to trigger the corresponding alarm if the alarm processing instruction is the first alarm processing instruction.

[0141] The face information adding submodule is used to add the face information to be detected to the preset secure face information record table if the alarm processing instruction is the second alarm processing instruction.

[0142] In some specific embodiments, the face information adding submodule may specifically include:

[0143] The permission identifier configuration unit is used to add the face information to be detected to the preset secure face information record table, and configure a preset permission identifier for the face information to be detected added to the preset secure face information record table, so as to prohibit the background from automatically deleting the face information to be detected added to the preset secure face information record table based on the preset permission identifier;

[0144] An initial weight configuration unit is used to add the face information to be detected to the preset secure face information record table, and to configure an initial weight for the face information to be detected added to the preset secure face information record table through a preset weight configuration interface.

[0145] Furthermore, embodiments of this application also disclose an electronic device, Figure 7 This is a structural diagram of an electronic device 20 according to an exemplary embodiment. The content of the diagram should not be construed as limiting the scope of this application.

[0146] Figure 7 This is a schematic diagram of the structure of an electronic device 20 provided in an embodiment of this application. Specifically, the electronic device 20 may include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 stores a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the intrusion monitoring method disclosed in any of the foregoing embodiments. Furthermore, the electronic device 20 in this embodiment may specifically be an electronic computer.

[0147] In this embodiment, the power supply 23 is used to provide operating voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and external devices, and the communication protocol it follows can be any communication protocol applicable to the technical solution of this application, and is not specifically limited here; the input / output interface 25 is used to acquire external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs, and is not specifically limited here.

[0148] In addition, the memory 22, as a carrier for resource storage, can be a read-only memory, random access memory, disk or optical disk, etc. The resources stored thereon can include operating system 221, computer program 222, etc., and the storage method can be temporary storage or permanent storage.

[0149] The operating system 221 is used to manage and control the various hardware devices on the electronic device 20 and the computer program 222, which may be Windows Server, Netware, Unix, Linux, etc. In addition to including a computer program capable of performing the intrusion monitoring method executed by the electronic device 20 as disclosed in any of the foregoing embodiments, the computer program 222 may further include a computer program capable of performing other specific tasks.

[0150] Furthermore, this application also discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, it implements the aforementioned disclosed intrusion monitoring method. Specific steps of this method can be found in the corresponding content disclosed in the foregoing embodiments, and will not be repeated here.

[0151] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to the method section.

[0152] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0153] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0154] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0155] The technical solutions provided in this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. An intrusion monitoring method, characterized in that, Applied to smart home devices, including: The camera device is used to capture images of the current target location and extract facial information from the captured images to obtain the facial information to be detected; the camera device has a rotation function according to the direction of the sound source. Determine whether the face information to be detected is face information that has not been saved at present; If the face information to be detected is face information that has not been saved, then historical face information extracted in the adjacent historical time period is obtained, and then it is determined whether the historical face information exists in the preset secure face information record table, and whether there are security personnel accompanying the target object corresponding to the face information to be detected, and the corresponding judgment result is obtained; the adjacent historical time period is a preset time period forward or backward based on the image time information in the face information to be detected. Based on the judgment result, it is determined whether to trigger an intrusion alarm operation for the current target location. After the target time period has elapsed, the temporary face information record table is integrated and cleared according to preset rules so as to record new face information in the next target time period. The temporary face information record table is used to save face information extracted within the target time period that meets the preset saving conditions. The target time period is the time period corresponding to the acquisition time of the image. The step of determining whether to trigger an intrusion alarm operation for the current target location based on the judgment result further includes: When the user does not interact with the smart home device, the camera device will patrol the current target location to monitor in real time whether there are any untrusted persons around the target location.

2. The intrusion monitoring method according to claim 1, characterized in that, The step of determining whether the face information to be detected is face information that has not been saved at present includes: Obtain a temporary facial information record form; Determine whether the face information to be detected exists in the temporary face information record table and the preset secure face information record table. If the face information to be detected does not exist in either table, then the face information to be detected is determined to be face information that has not been saved at present.

3. The intrusion monitoring method according to claim 2, characterized in that, After determining whether the face information to be detected exists in the temporary face information record table and the preset secure face information record table, the method further includes: If the face information to be detected exists in either the temporary face information record table or the preset secure face information record table, then the face information to be detected is determined to meet the first storage condition, and the face information to be detected is saved to the temporary face information record table.

4. The intrusion monitoring method according to claim 2, characterized in that, After determining whether the historical face information exists in the preset secure face information record table, the method further includes: If the historical face information exists in the preset secure face information record table, then the face information to be detected is determined to meet the second storage condition, and the face information to be detected is saved to the temporary face information record table.

5. The intrusion monitoring method according to claim 2, characterized in that, Also includes: Determine whether the current moment is the end moment of the target time period; If the current time is the end time of the target time period, the weights of the face information in the preset secure face information record table are updated based on the temporary face information record table, and face information with a weight less than a preset weight threshold in the preset secure face information record table is removed.

6. The intrusion monitoring method according to claim 5, characterized in that, The step of updating the weights of facial information in the preset secure facial information record table based on the temporary facial information record table includes: Delete facial information that appears less than a preset threshold number of times from the temporary facial information record table to obtain the first adjusted record table; The facial information in the first adjusted record table is deduplicated to obtain the second adjusted record table; Determine whether the facial information in the second adjusted record table exists in the preset secure facial information record table. If it does, then perform weight increase processing on the corresponding facial information in the preset secure facial information record table according to the preset weight increase rule.

7. The intrusion monitoring method according to claim 6, characterized in that, After performing weighting processing on the corresponding face information in the preset secure face information record table according to the preset weighting rule, the method further includes: If it is detected that the duration for which any face information in the current preset secure face information record table has not undergone the weight increase processing is not less than a preset number of time periods, then the corresponding face information in the preset secure face information record table will undergo weight reduction processing according to the preset weight reduction rule.

8. The intrusion monitoring method according to any one of claims 1 to 7, characterized in that, The step of determining whether to trigger an intrusion alarm operation for the current target location based on the judgment result includes: If the historical face information is not found in the preset secure face information record table, an alarm message containing the image corresponding to the face information to be detected is generated, and the alarm message is sent to the preset user terminal so that the preset user terminal can return the corresponding alarm processing instruction according to the alarm message. If the alarm processing instruction is the first alarm processing instruction, then the local preset alarm device is controlled to trigger the corresponding alarm; If the alarm processing instruction is the second alarm processing instruction, then the face information to be detected is added to the preset secure face information record table.

9. The intrusion monitoring method according to claim 8, characterized in that, Adding the face information to be detected to the preset secure face information record table includes: The face information to be detected is added to the preset secure face information record table, and a preset permission identifier is configured for the face information to be detected added to the preset secure face information record table, so as to prevent the background from automatically deleting the face information to be detected added to the preset secure face information record table based on the preset permission identifier; Alternatively, the face information to be detected can be added to the preset secure face information record table, and an initial weight can be configured for the face information to be detected added to the preset secure face information record table through a preset weight configuration interface.

10. An intrusion monitoring device, characterized in that, Applied to smart home devices, including: An image acquisition module is used to acquire images of the current target location using a camera device; the camera device has a rotation function based on the direction of the sound source. The information acquisition module is used to extract facial information from the acquired images to obtain the facial information to be detected; The first judgment module is used to determine whether the face information to be detected is face information that has not been saved at present; The second judgment module is used to, if the face information to be detected is face information that has not been saved at present, obtain historical face information extracted in the adjacent historical time period, then determine whether the historical face information exists in the preset secure face information record table, and determine whether there are security personnel accompanying the target object corresponding to the face information to be detected, and obtain the corresponding judgment result; the adjacent historical time period is a preset time period forward or backward based on the image time information in the face information to be detected; The alarm triggering module is used to determine whether to trigger an intrusion alarm operation for the current target location based on the judgment result, and after the target time period has elapsed, to integrate and clear the temporary face information record table according to preset rules, so as to record new face information in the next target time period; the temporary face information record table is used to store face information extracted within the target time period that meets the preset storage conditions, and the target time period is the time period corresponding to the acquisition time of the image; Specifically, the device is used to patrol the current target location through the camera device when the user is not interacting with the smart home device, so as to monitor in real time whether there are any untrusted persons around the target location.

11. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor for executing the computer program to implement the intrusion monitoring method as described in any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that, Used to store a computer program, which, when executed by a processor, implements the intrusion monitoring method as described in any one of claims 1 to 9.

Images