Door lock control method, device, equipment and medium based on intelligent door lock device

Abstract

Embodiments of the present disclosure disclose a door lock control method, device, equipment, and medium based on an intelligent door lock device. A specific implementation manner of the method includes: in response to detecting a visitor performing a preset action, controlling an image acquisition device to obtain a personnel image set for the visitor from multiple angles; generating initial personnel information according to the personnel image set; in response to determining that the initial personnel information does not exist in the target personnel information list, generating initial visit intention information corresponding to the visitor according to the personnel image set; generating visit risk information for the visitor according to the initial visit intention information; generating pre-set door lock control strategy information corresponding to the visit risk information; and in response to detecting that the door opening personnel to perform the door opening operation is a target category personnel, instructing the door opening personnel to act according to the door lock control strategy information. This implementation manner can safely and efficiently perform corresponding door opening operations for unfamiliar visitors.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of computer technologies, and particularly to a door lock control method, apparatus, device, and medium based on an intelligent door lock device. Background Art

[0002] Currently, an intelligent door lock refers to a lock improved on the basis of a traditional mechanical lock, which is more intelligent and simpler in terms of user security, identification, and management. Related applications of intelligent door locks have been particularly extensive. For the handling of visitors, the commonly adopted method is to use a camera device provided in the door lock device to project the outdoor situation for the target user to view, so that the target user can perform corresponding processing according to the category of the visitor.

[0003] However, the inventors have found that when using the above method, the following technical problems often exist:

[0004] First, it is necessary for the target person to manually determine the category of the visitor, which has the problems of low efficiency and ineffective security guarantee.

[0005] Second, the judgment of the personnel information in the personnel image set is too superficial, and the characteristics of the personnel are not considered from multiple aspects, resulting in inaccurate initial personnel information.

[0006] The above information disclosed in this background art section is only used to enhance the understanding of the background of the inventive concept, and thus, it may include information that does not form the prior art known to those of ordinary skill in the art in this country. Summary of the Invention

[0007] The content part of the present disclosure is used to briefly introduce the inventive concepts, which will be described in detail in the following detailed implementation part. The content part of the present disclosure is not intended to identify the key features or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0008] Some embodiments of the present disclosure propose a door lock control method, apparatus, device, and medium based on an intelligent door lock device to solve one or more of the technical problems mentioned in the above background art section.

[0009] In a first aspect, some embodiments of the present disclosure provide a door lock control method based on an intelligent door lock device, including: in response to detecting a visitor performing a preset action, controlling an image acquisition device to acquire a set of personnel images of the visitor from multiple angles, where the image acquisition device is an image acquisition device provided in the intelligent door lock device for acquiring outdoor images; generating initial personnel information corresponding to the visitor according to the set of personnel images; in response to determining that the initial personnel information does not exist in a target personnel information list, generating initial visit intention information corresponding to the visitor according to the set of personnel images; generating visit risk information for the visitor according to the initial visit intention information; generating pre-set door lock control policy information corresponding to the visit risk information; and in response to detecting that the door opener to perform a door opening operation is a target category of personnel, instructing the door opener to perform the door opening operation according to the door lock control policy information.

[0010] In a second aspect, some embodiments of the present disclosure provide a door lock control device based on an intelligent door lock device, including: a control unit configured to, in response to detecting a visitor performing a preset action, control an image acquisition device to acquire a set of personnel images of the visitor from multiple angles, where the image acquisition device is an image acquisition device provided in the intelligent door lock device for acquiring outdoor images; a first generation unit configured to generate initial personnel information corresponding to the visitor according to the set of personnel images; a second generation unit configured to, in response to determining that the initial personnel information does not exist in a target personnel information list, generate initial visit intention information corresponding to the visitor according to the set of personnel images; a third generation unit configured to generate visit risk information for the visitor according to the initial visit intention information; a fourth generation unit configured to generate pre-set door lock control policy information corresponding to the visit risk information; and an instruction unit configured to, in response to detecting that the door opener to perform a door opening operation is a target category of personnel, instruct the door opener to perform the door opening operation according to the door lock control policy information.

[0011] In a third aspect, some embodiments of the present disclosure provide an electronic device, including: one or more processors; a storage device having stored thereon one or more programs, which, when executed by the one or more processors, cause the one or more processors to implement the method described in any implementation manner of the first aspect.

[0012] In a fourth aspect, some embodiments of the present disclosure provide a computer-readable medium having stored thereon a computer program, where the program, when executed by a processor, implements the method described in any implementation manner of the first aspect.

[0013] The above embodiments of the present disclosure have the following beneficial effects: The door lock control method based on the intelligent door lock device according to some embodiments of the present disclosure can safely and efficiently perform corresponding door opening operations for unfamiliar visitors. Specifically, the reason for the lack of safety and efficiency in dealing with relevant unfamiliar visitors is that it is necessary for the target person to manually determine the category of the visitor, resulting in low efficiency and ineffective security guarantee. Based on this, in the door lock control method based on the intelligent door lock device according to some embodiments of the present disclosure, first, in response to detecting a visitor performing a preset action, the image acquisition device is controlled to obtain a set of personnel images of the above-mentioned visitor from multiple angles. Among them, the above-mentioned image acquisition device is an image acquisition device provided in the above-mentioned intelligent door lock device for acquiring outdoor images. Here, the image acquisition device is used to obtain a set of personnel images for subsequent determination of relatively accurate initial personnel information and execution of corresponding operations based on the personnel information. Then, based on the above-mentioned set of personnel images, the initial personnel information corresponding to the above-mentioned visitor can be accurately generated. Next, in response to determining that the above-mentioned initial personnel information does not exist in the target personnel information list, based on the above-mentioned set of personnel images, the initial visit intention information corresponding to the above-mentioned visitor can be accurately generated. Furthermore, based on the above-mentioned initial visit intention information, the visit risk information corresponding to the above-mentioned visitor can be accurately generated. Here, the generation of the initial personnel information, the initial visit intention information, and the visit risk information can help the target person determine the category of the visitor and the risk level of the visitor, so as to assist the subsequent door opener in performing corresponding operations. Further, the pre-set door lock control strategy information corresponding to the above-mentioned visit risk information is generated for subsequent assistance to the door opener to perform corresponding strategies while ensuring safety. Finally, in response to detecting that the door opener to perform the door opening operation is a target category person, the above-mentioned door opener is instructed to perform the door opening operation according to the above-mentioned door lock control strategy information. In summary, by determining the initial personnel information, the initial visit intention information, and the visit risk information of the visitor to generate the corresponding door lock control strategy information to assist the door opener in performing corresponding operations, not only the safety is guaranteed, but also the execution efficiency is greatly improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In combination with the accompanying drawings and with reference to the following specific embodiments, the above and other features, advantages, and aspects of the various embodiments of the present disclosure will become more apparent. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic and the elements and elements are not necessarily drawn to scale.

[0015] Figure 1 is a flowchart of some embodiments of the door lock control method based on the intelligent door lock device according to the present disclosure;

[0016] Figure 2 is a schematic structural diagram of some embodiments of a door lock control device based on an intelligent door lock device according to the present disclosure;

[0017] Figure 3 is a schematic structural diagram of an electronic device suitable for implementing some embodiments of the present disclosure. Detailed implementation manners

[0018] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although some embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. On the contrary, these embodiments are provided to more thoroughly and completely understand the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not used to limit the protection scope of the present disclosure.

[0019] In addition, it should be noted that only parts related to the relevant invention are shown in the drawings for the convenience of description. Without conflict, the embodiments in the present disclosure and the features in the embodiments can be combined with each other.

[0020] It should be noted that concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependent relationships.

[0021] It should be noted that the modifications of "one" and "multiple" mentioned in the present disclosure are illustrative rather than restrictive. Those skilled in the art should understand that unless otherwise clearly specified in the context, it should be understood as "one or more".

[0022] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only for illustrative purposes and are not used to limit the scope of these messages or information.

[0023] The present disclosure will be described in detail below with reference to the drawings and in conjunction with the embodiments.

[0024] Reference Figure 1 , shows a flow 100 of some embodiments of a door lock control method based on an intelligent door lock device according to the present disclosure. The door lock control method based on the intelligent door lock device includes the following steps:

[0025] Step 101, in response to detecting a visitor who performs a preset action, control an image acquisition device to obtain a set of personnel images of the above-mentioned visitor from multiple angles.

[0026] In some embodiments, in response to detecting a visitor performing a preset action, the execution subject of the above-mentioned door lock control method based on the intelligent door lock device may control the image acquisition device to acquire a set of personnel images of the above-mentioned visitor from multiple angles. Wherein, the above-mentioned image acquisition device is an image acquisition device provided in the above-mentioned intelligent door lock device for acquiring outdoor images. The preset action may be an action related to a visit. For example, the preset action may be a knocking action or a doorbell pressing action. The visitor may be a person for access. The image acquisition device may be a device for acquiring images. For example, the image acquisition device may be a camera device. The set of personnel images may be captured images of the visitor from various angles.

[0027] Step 102, generate initial personnel information corresponding to the above-mentioned visitor according to the above-mentioned set of personnel images.

[0028] In some embodiments, the above-mentioned execution subject may generate initial personnel information corresponding to the above-mentioned visitor according to the above-mentioned set of personnel images. The initial personnel information may be the personnel information initially judged for the visitor. In practice, the personnel information may include: personnel name, personnel clothing, and gender.

[0029] As an example, first, the above-mentioned execution subject may input each personnel image in the set of personnel images into a convolutional neural network model connected in series in multiple layers to generate personnel image feature information and obtain a set of personnel image feature information. Then, fuse the above-mentioned set of personnel image feature information to generate fused feature information. Next, input the fused feature information into a fully connected layer connected in series in multiple layers to output the initial personnel information.

[0030] In some optional implementation manners of some embodiments, generating the initial personnel information corresponding to the above-mentioned visitor according to the above-mentioned set of personnel images includes the following steps:

[0031] First step, determine the acquisition angle and acquisition time corresponding to each personnel image in the above-mentioned set of personnel images. Wherein, the acquisition angle may be the image shooting angle. The acquisition time may be the image shooting time. Wherein, the number of personnel images included in the set of personnel images is determined in advance. For example, the number of images may be 27.

[0032] Second step, sort the set of personnel images according to the acquisition angle in clockwise order and the acquisition time from early to late, according to the acquisition angle and acquisition time corresponding to each personnel image, to obtain a sequence of personnel images.

[0033] Step 3: Determine the image weight corresponding to each person image in the person image sequence according to the sequence position of each person image in the person image sequence. Among them, the image weight can characterize the importance degree of the person information of the visitor in the image. That is, each position in the person image sequence corresponds to a unique image weight.

[0034] Step 4: Perform the following information generation steps on each person image in the above person image sequence:

[0035] The first sub-step: Input the above person image into a convolutional neural network model connected in series in multiple layers to generate person image feature information. Among them, the convolutional neural network model connected in series in multiple layers can be a neural network model for extracting person image features. The person image feature information can characterize the feature information of the person image content.

[0036] The second sub-step: Input the person image feature information into a skin color information generation model to generate skin color information. Among them, the skin color information can characterize the skin color depth of the person corresponding to the person image. The skin color information can be a null value. When the skin color information is a null value, it means that the skin of the visitor in the image is not exposed. The skin color information can be numerical information. The larger the value, the darker the skin color.

[0037] The third sub-step: Input the person image feature information into a face recognition model to generate face information. Among them, the face information can include: face contour information, face key point information. The face recognition model can be a YOLO model. The face key point information can be the key point coordinates corresponding to each key point of the face.

[0038] The fourth sub-step: Input the person image feature information into a marker recognition model to generate marker information. Among them, the marker information can be the information of the marker worn or held by the person. For example, the marker can be glasses. In practice, the marker recognition model can be a YOLO model.

[0039] The fifth sub-step: Input the person image feature information into a body landmark information recognition model to generate height landmark information. Among them, the body landmark information can include: body height, body leg length, body arm length, and body weight. Among them, the body landmark information recognition model can be a residual network model connected in series in multiple layers.

[0040] The sixth sub-step: Package the person image feature information, skin color information, face information, marker information, and height landmark information to generate candidate person information.

[0041] Step 5: Multiply the candidate person information in the obtained candidate person information sequence by the corresponding image weight to generate a multiplication information sequence.

[0042] The sixth step is to add up the respective multiplication information in the multiplication information sequence to generate addition information as initial personnel information.

[0043] The above-mentioned relevant contents of "Step 1-Step 6", as one of the inventive points of the present disclosure, solve the second technical problem in the background technical problem, "the judgment of the personnel information of the personnel image set is too superficial, and the characteristics of the personnel are not considered from many aspects, resulting in the initial personnel information obtained being not accurate enough". Based on this, the present disclosure sets an image weight for each personnel image to ensure the importance of the characteristics of the personnel characteristic information included in each personnel image. In addition, by comprehensively determining the characteristic information of the visiting personnel from various aspects such as skin color information, marker information, facial information and height representation information, more abundant candidate personnel information can be obtained later. With the support of image weights, the information of each candidate personnel is fused to obtain more accurate initial personnel information.

[0044] Step 103 , in response to determining that the initial personnel information does not exist in the target personnel information list, generating initial visit intention information corresponding to the visitor according to the personnel image set.

[0045] In some embodiments, in response to determining that the above-mentioned initial personnel information does not exist in the target personnel information list, the above-mentioned execution entity may generate the initial visit intention information corresponding to the above-mentioned visitor based on the above-mentioned personnel image set. Among them, the personnel information in the target personnel information list may be personnel information that has been registered historically. In practice, the target personnel information list may be a personnel whitelist. The initial visit intention information may be the intention information of the visit intention preliminarily judged for the visitor. For example, the initial visit intention information may be "the visitor's intention is to deliver a courier."

[0046] Step 104: Generate visit danger information for the visitor based on the initial visit intention information.

[0047] In some embodiments, the execution subject may generate visit danger information for the visitor according to the initial visit intention information. The visit danger information may be the degree of danger of the visitor. Specifically, the visit danger information may include: a visit danger score. The larger the visit danger score, the more dangerous the visitor is.

[0048] As an example, the execution subject may determine the visit danger information corresponding to the initial visit intention information by querying the association table. Specifically, the association table may represent the association relationship between the visit intention information and the visit danger information.

[0049] In some alternative implementations of some embodiments, generating the visit risk information for the above-mentioned visiting person based on the above-mentioned initial visit intention information may include the following steps:

[0050] First, use a pre-trained fraud potential inquiry statement generation model to generate fraud potential inquiry statements for the above-mentioned initial visit intention information. Among them, the fraud potential inquiry statement generation model can be a neural network model for generating fraud potential inquiry statements. The fraud potential inquiry statement can be an inquiry statement that induces the visiting person to say something related to fraud. For example, the fraud potential inquiry statement can be "May I ask what you are here for?" The fraud potential inquiry statement generation model can be a generative and adversarial neural network model.

[0051] Second, control the outdoor voice playback device to play the fraud potential inquiry statements. Among them, the outdoor voice playback device can be a device set in the intelligent door lock device for voice playback outdoors.

[0052] Third, obtain the speech reply of the above-mentioned visiting person in response to the fraud potential inquiry statement.

[0053] Fourth, perform authenticity verification on the speech reply to obtain an authenticity verification result. Among them, the authenticity verification result can be a verification result indicating whether the speech reply is the real voice of the above-mentioned visiting person.

[0054] As an example, the above-mentioned execution subject can perform speech processing on the speech reply to obtain processed information. Then, input the processed information into the authenticity information classification model to generate authenticity information as the authenticity verification result. Among them, the authenticity information classification model can be a recurrent neural network model connected in series in multiple layers.

[0055] Fifth, in response to determining that the authenticity verification result indicates that the speech reply is the real voice of the above-mentioned visiting person, re-determine the person determination information corresponding to the above-mentioned visiting person according to the speech reply and the above-mentioned person image set.

[0056] As an example, first, the above-mentioned execution subject can generate candidate person determination information for the above-mentioned visiting person according to the speech reply. Then, perform person information fusion on the candidate person determination information and the initial person information, where the person determination information of the candidate person determination information is the main, and the initial person information is the secondary, to generate person determination information.

[0057] Sixth, in response to determining that there is no person determination information in the above-mentioned target person information list, generate the above-mentioned visit risk information through various methods according to the speech reply and the above-mentioned person image set.

[0058] Optionally, generating the above-mentioned visiting danger information based on the above-mentioned speech response and the above-mentioned set of personnel images may include the following steps:

[0059] First step, generate a first candidate visiting danger score for the above-mentioned set of personnel images. Among them, the first candidate visiting danger score can represent the personnel danger level of the personnel corresponding to the set of personnel images. The larger the first candidate visiting danger score, the higher the personnel danger level.

[0060] As an example, first, the above-mentioned execution entity can use a human body pose determination model to determine the human body pose corresponding to the set of personnel images. Then, determine the pose danger score corresponding to the human body pose. Next, determine the personnel wearing information corresponding to each personnel image in the above-mentioned set of personnel images. Then, determine the personnel wearing danger score corresponding to the personnel wearing information. Finally, perform a weighted summation process on the pose danger score and the personnel wearing score to generate the visiting danger information.

[0061] Second step, obtain at least one response statement in the above-mentioned speech response.

[0062] As an example, first, the above-mentioned execution entity can convert the speech response into a text form to generate an audio text. Then, perform a sentence splitting process on the audio text to obtain at least one response statement.

[0063] Third step, for at least one response statement, perform the following generation steps:

[0064] First sub-step, use a statement danger information generation model to determine at least one statement danger information corresponding to at least one response statement. Among them, the statement danger information includes: statement danger score and statement danger reason information. Among them, the statement danger information generation model can be a neural network model for generating statement danger information. The statement danger information can represent the danger level of the statement. The statement danger information generation model can be a neural network model based on a classification task. For example, the statement danger information generation model can be a composite model composed of a multi-layer cascaded convolutional neural network model and a multi-layer cascaded recurrent neural network model. The statement danger score can be a score representing that the statement can reflect that the visiting personnel is a dangerous person. The statement danger reason information can be the reason information representing the existence of risk factors in the statement.

[0065] Second sub-step, perform a weighted summation on at least one statement danger score and the above-mentioned first candidate visiting danger score to obtain a second candidate visiting danger score.

[0066] Third sub-step, generate predicted danger reason information according to at least one statement danger reason information.

[0067] As an example, the above-mentioned execution entity may summarize the various statement risk cause information in at least one statement risk cause information to generate a summarized cause, which is used as the predicted risk cause information.

[0068] As another example, the above-mentioned execution entity may determine the statement risk cause information with the highest statement risk score in at least one statement risk cause information as the predicted risk cause information.

[0069] The fourth sub-step, in response to determining that the second candidate visit risk score is in the first interval or the second interval, determines the second candidate visit risk score and the predicted risk cause information corresponding to the second candidate visit risk score as the visit risk information. Among them, the value corresponding to the second interval is greater than the value corresponding to the first interval. The value corresponding to the first interval represents a relatively low risk coefficient for the visiting person. The value corresponding to the second interval represents a relatively high risk coefficient for the visiting person.

[0070] Optionally, the step further includes:

[0071] The first step, in response to determining that the second candidate visit risk score is in the third interval, uses the above-mentioned fraud potential inquiry statement generation model to generate a fraud potential inquiry statement for the statement reply voice as the target fraud potential inquiry statement. Among them, the value corresponding to the third interval is greater than the value corresponding to the first interval. The value corresponding to the second interval is greater than the value corresponding to the third interval. The value corresponding to the third interval represents that the risk coefficient of the visiting person is uncertain.

[0072] As an example, first, the above-mentioned execution entity may generate a voice vector for the statement reply voice. Then, input the voice to the fraud potential inquiry statement generation model to generate the target fraud potential inquiry statement.

[0073] The second step, controls the outdoor voice playback device to play the above-mentioned target fraud potential inquiry statement.

[0074] The third step, obtains the statement reply voice of the visiting person in response to the target fraud potential inquiry statement as the target statement reply voice.

[0075] The fourth step, performs authenticity verification on the target statement reply voice to obtain an authenticity verification result as the target authenticity verification result. The implementation method will not be described in detail.

[0076] The fifth step, in response to determining that the target authenticity verification result indicates that the target statement reply voice is the real voice of the above-mentioned visiting person, re-determines the person determination information corresponding to the above-mentioned visiting person according to the target statement reply voice and the above-mentioned personnel image set as the target person determination information. For the specific implementation method, refer to the generation of the person determination information.

[0077] Step 6, in response to determining that the target person determination information does not exist in the above-mentioned target person information list, generate at least one response statement corresponding to the target statement reply voice as at least one target response statement.

[0078] Step 7, use at least one target response statement as at least one response statement and continue to execute the above-mentioned generation step.

[0079] Optionally, the authenticity verification of the above-mentioned statement reply voice to obtain the authenticity verification result may include the following steps:

[0080] Step 1, use the sound positioning device set in the above-mentioned intelligent door lock device to generate voice positioning information for the above-mentioned statement reply voice. The sound positioning device may be a device that realizes sound source positioning. For example, the sound positioning device may be a sound locator.

[0081] Step 2, according to the voice positioning information, execute the following processing steps:

[0082] The first sub-step, in response to determining that the voice positioning information is not the first target position of the above-mentioned visitor, randomly obtain an inquiry statement for the above-mentioned initial visit intention information from the corpus. The corpus stores sets of inquiry statements for each intention.

[0083] The second sub-step, control the above-mentioned outdoor voice playback device to play the inquiry statement.

[0084] The third sub-step, obtain the statement reply voice of the above-mentioned visitor in response to the inquiry statement as the inquiry statement reply voice.

[0085] The fourth sub-step, determine the voice positioning information for the above-mentioned inquiry statement reply voice as the target voice positioning information.

[0086] The fifth sub-step, in response to determining that the target voice positioning information is the first target position of the above-mentioned visitor and the number of executions corresponding to the above-mentioned processing step is less than the target value, generate an authenticity verification result indicating that the statement reply voice passes the authenticity verification. The first target position may be the mouth position of the visitor. The target value may be a preset value. For example, the target value may be 3.

[0087] Step 3, in response to determining that the target voice positioning information is not the first target position of the above-mentioned visitor, use the target voice positioning information as the voice positioning information and execute the above-mentioned processing step again.

[0088] Step 105, generate the pre-set door lock control strategy information corresponding to the above-mentioned visit danger information.

[0089] In some embodiments, the above-mentioned execution entity may generate pre-set door lock control policy information corresponding to the above-mentioned visiting danger information. Among them, the door lock control policy information may be the policy information of the door lock control policy. The door lock control policy may be a policy for controlling and processing an intelligent door lock. For example, the door lock control policy may be an operation of setting the intelligent door lock device to the highest security level.

[0090] As an example, the above-mentioned execution entity may query, through the method of querying policy information, the door lock control policy information pre-set by the target person corresponding to the visiting danger information from the target relationship table.

[0091] Step 106, in response to detecting that the door-opening person for the to-be-executed door-opening operation is a target category person, instruct the above-mentioned door-opening person to execute the door-opening operation according to the above-mentioned door lock control policy information.

[0092] In some embodiments, in response to detecting that the door-opening person for the to-be-executed door-opening operation is a target category person, the above-mentioned execution entity may instruct the above-mentioned door-opening person to execute the door-opening operation according to the above-mentioned door lock control policy information.

[0093] As an example, the above-mentioned execution entity may instruct the above-mentioned door-opening person to execute the door-opening operation according to the door lock control policy corresponding to the above-mentioned door lock control policy information.

[0094] In some optional implementation manners of some embodiments, after step 106, the steps further include:

[0095] In response to detecting that the door-opening person for the to-be-executed door-opening operation is not a target category person, the above-mentioned execution entity may control the outdoor detection information processing device located at the second target position and connected to the above-mentioned intelligent door lock device to display the above-mentioned visiting danger information and the real-time picture of the above-mentioned visiting person outdoors, and control the outdoor detection information processing device to play the speech information for the above-mentioned visiting danger information and the door-opening operation. Among them, the second target position may be a position near the door indoors. The outdoor detection information processing device may be a device for processing outdoor detection information. The outdoor detection information may include: outdoor detection information outside the door.

[0096] In some optional implementation manners of some embodiments, the above-mentioned instructing the above-mentioned door-opening person to execute the door-opening operation according to the above-mentioned door lock control policy information may include the following steps:

[0097] The first step is to instruct the above-mentioned door-opening person to view the corresponding display content of the above-mentioned outdoor detection information processing device.

[0098] Second, in response to detecting a confirmation message from the above-mentioned door-opening person indicating that the displayed content on the above-mentioned outdoor detection information processing device is correct, instruct the above-mentioned door-opening person to click on the above-mentioned door-opening control. The door-opening control can be a control associated with the intelligent door lock device for opening the door.

[0099] Third, in response to determining that the control click information for the above-mentioned door-opening person has been received, play a door-opening statement indicating that the above-mentioned door-opening person should perform a door-opening operation.

[0100] The above-mentioned various embodiments of the present disclosure have the following beneficial effects: The door lock control method based on the intelligent door lock device in some embodiments of the present disclosure can safely and efficiently perform corresponding door-opening operations for unfamiliar visiting personnel. Specifically, the reason for the lack of safety and efficiency in dealing with relevant unfamiliar visiting personnel is that the target person needs to manually determine the category of the visiting person, resulting in low efficiency and ineffective security guarantee. Based on this, in some embodiments of the door lock control method based on the intelligent door lock device of the present disclosure, first, in response to detecting a visiting person performing a preset action, control the image acquisition device to obtain a set of personnel images of the above-mentioned visiting person from multiple angles. Among them, the above-mentioned image acquisition device is an image acquisition device provided in the above-mentioned intelligent door lock device for acquiring outdoor images. Here, the image acquisition device is used to obtain a set of personnel images for subsequent determination of relatively accurate initial personnel information to perform corresponding operations based on the personnel information. Then, based on the above-mentioned set of personnel images, the initial personnel information corresponding to the above-mentioned visiting person can be accurately generated. Next, in response to determining that the above-mentioned initial personnel information does not exist in the target personnel information list, based on the above-mentioned set of personnel images, the initial visiting intention information corresponding to the above-mentioned visiting person can be accurately generated. Furthermore, based on the above-mentioned initial visiting intention information, the visiting risk information corresponding to the above-mentioned visiting person can be accurately generated. Here, the generation of the initial personnel information, the initial visiting intention information, and the visiting risk information can help the target person determine the category of the visiting person and the risk level of the visiting person, so as to assist the door-opening person in performing corresponding operations subsequently. Further, generate the pre-set door lock control strategy information corresponding to the above-mentioned visiting risk information for subsequent assistance to the door-opening person to perform corresponding strategies on the premise of ensuring safety. Finally, in response to detecting that the door-opening person to perform the door-opening operation is a target category person, instruct the above-mentioned door-opening person to perform the door-opening operation according to the above-mentioned door lock control strategy information. In summary, by determining the initial personnel information, the initial visiting intention information, and the visiting risk information of the visiting person to generate the corresponding door lock control strategy information to assist the door-opening person in performing corresponding operations, not only can safety be guaranteed, but also the execution efficiency can be greatly improved.

[0101] For further reference Figure 2, as an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of a door lock control device based on an intelligent door lock device. These device embodiments correspond to Figure 1 the method embodiments shown, and the door lock control device can be specifically applied to various electronic devices.

[0102] As Figure 2 shown, a door lock control device 200 includes: a control unit 201, a first generation unit 202, a second generation unit 203, a third generation unit 204, a fourth generation unit 205, and an indication unit 206. Among them, the control unit 201 is configured to, in response to detecting a visitor who performs a preset action, control an image acquisition device to acquire a set of personnel images of the above-mentioned visitor from multiple angles, where the image acquisition device is an image acquisition device provided in the above-mentioned intelligent door lock device and used to acquire outdoor images; the first generation unit 202 is configured to generate initial personnel information corresponding to the above-mentioned visitor according to the above-mentioned set of personnel images; the second generation unit 203 is configured to, in response to determining that the above-mentioned initial personnel information does not exist in the target personnel information list, generate initial visit intention information corresponding to the above-mentioned visitor according to the above-mentioned set of personnel images; the third generation unit 204 is configured to generate visit risk information for the above-mentioned visitor according to the above-mentioned initial visit intention information; the fourth generation unit 205 is configured to generate pre-set door lock control policy information corresponding to the above-mentioned visit risk information; the indication unit 206 is configured to, in response to detecting that the door opening person to perform a door opening operation is a target category person, instruct the above-mentioned door opening person to perform a door opening operation according to the above-mentioned door lock control policy information.

[0103] It can be understood that the various units described in the image segmentation device 200 correspond to the respective steps in the method described with reference to Figure 1 Therefore, the operations, features, and beneficial effects described above for the method also apply to the image segmentation device 200 and the units included therein, and will not be repeated here.

[0104] Next, refer to Figure 3 , which shows a schematic structural diagram of an electronic device (for example, an electronic device) 300 suitable for implementing some embodiments of the present disclosure. Figure 3 The electronic device shown is only an example and should not bring any limitations to the functions and usage scopes of the embodiments of the present disclosure.

[0105] As Figure 3As shown, the electronic device 300 may include a processing device (such as a central processing unit, a graphics processing unit, etc.) 301, which may perform various appropriate actions and processes according to a program stored in the read-only memory (ROM) 302 or a program loaded from the storage device 308 into the random access memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the electronic device 300 are also stored. The processing device 301, the ROM 302, and the RAM 303 are connected to each other through a bus 304. The input / output (I / O) interface 305 is also connected to the bus 304.

[0106] Generally, the following devices may be connected to the I / O interface 305: an input device 306 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 308 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 309. The communication device 309 may allow the electronic device 300 to communicate with other devices wirelessly or wiredly to exchange data. Although Figure 3 an electronic device 300 with various devices is shown, it should be understood that it is not required to implement or have all the shown devices. Instead, more or fewer devices may be implemented or had. Figure 3 Each block shown in may represent a device or, as needed, multiple devices.

[0107] Specifically, according to some embodiments of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, some embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program codes for performing the methods shown in the flowcharts. In such some embodiments, the computer program may be downloaded and installed from a network through the communication device 309, or installed from the storage device 308, or installed from the ROM 302. When the computer program is executed by the processing device 301, the above functions defined in the methods of some embodiments of the present disclosure are executed.

[0108] It should be noted that, in some embodiments of the present disclosure, the above-mentioned computer-readable medium may be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In some embodiments of the present disclosure, the computer-readable storage medium may be any tangible medium that contains or stores a program, which can be used by or in conjunction with an instruction execution system, apparatus, or device. In some embodiments of the present disclosure, the computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium may also be any computer-readable medium other than the computer-readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0109] In some embodiments, the client and the server may communicate using any currently known or future-developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include local area networks ("LANs"), wide area networks ("WANs"), the Internet (e.g., the Internet), and end-to-end networks (e.g., ad hoc end-to-end networks), as well as any currently known or future-developed network.

[0110] The above computer-readable medium may be included in the above electronic device; or it may exist separately and not be assembled into the electronic device. The above computer-readable medium carries one or more programs. When the above one or more programs are executed by the electronic device, the electronic device is caused to: in response to detecting a visiting person performing a preset action, control an image acquisition device to acquire a set of personnel images of the visiting person from multiple angles, where the image acquisition device is an image acquisition device provided in the above intelligent door lock device and used for acquiring outdoor images; generate initial personnel information corresponding to the visiting person according to the set of personnel images; in response to determining that the initial personnel information does not exist in a target personnel information list, generate initial visiting intention information corresponding to the visiting person according to the set of personnel images; generate visiting risk information for the visiting person according to the initial visiting intention information; generate pre-set door lock control strategy information corresponding to the visiting risk information; and in response to detecting that the door-opening person for a door-opening operation to be performed is a target category person, instruct the door-opening person to perform the door-opening operation according to the door lock control strategy information.

[0111] Computer program code for performing the operations of some embodiments of the present disclosure may be written in one or more programming languages or combinations thereof. The above programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, executed as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (for example, by using an Internet service provider to connect through the Internet).

[0112] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a portion of code that contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions noted in the blocks may occur in a different order than noted in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, or they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system that performs the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0113] The units described in some embodiments of the present disclosure can be implemented in software or in hardware. The described units can also be provided in a processor. For example, it can be described as: a processor includes a control unit, a first generation unit, a second generation unit, a third generation unit, a fourth generation unit, and an indication unit. Among them, the names of these units do not constitute a limitation to the unit itself in some cases. For example, the first generation unit can also be described as "the unit that generates the initial personnel information corresponding to the above-mentioned visiting personnel according to the above-mentioned personnel image set".

[0114] The functions described above can be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that can be used include: Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), Systems on Chip (SOCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0115] The above description is only some preferred embodiments of the present disclosure and an explanation of the applied technical principles. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by the specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above inventive concept. For example, the technical solutions formed by mutually replacing the above features with the (but not limited to) technical features having similar functions disclosed in the embodiments of the present disclosure.

Claims

1. A door lock control method based on an intelligent door lock device, comprising: In response to detecting a visitor who performs a preset action, controlling an image acquisition device to acquire a set of images of the visitor at multiple angles, wherein the image acquisition device is an image acquisition device provided in the smart door lock device and used to acquire outdoor images; Generating initial personnel information corresponding to the visiting personnel according to the personnel image set; In response to determining that the initial personnel information does not exist in the target personnel information list, generating initial visit intention information corresponding to the visitor according to the personnel image set; Generate visit danger information for the visitor based on the initial visit intention information, wherein the generating of visit danger information for the visitor based on the initial visit intention information includes: using a pre-trained fraud potential inquiry sentence generation model to generate a fraud potential inquiry sentence for the initial visit intention information; controlling an outdoor voice playback device to play the fraud potential inquiry sentence; obtaining a sentence reply voice for the fraud potential inquiry sentence replied by the visitor; performing an authenticity verification on the sentence reply voice to obtain an authenticity verification result; in response to determining that the authenticity verification result indicates that the sentence reply voice is the real voice of the visitor, re-determine the person determination information corresponding to the visitor based on the sentence reply voice and the person image set; in response to determining that the person determination information does not exist in the target person information list, generate the visit danger information based on the sentence reply voice and the person image set; Generate pre-set door lock control strategy information corresponding to the visitor danger information; In response to detecting that the door-opening person to be opened is a person of the target category, the door-opening person is instructed to perform the door-opening operation according to the door lock control strategy information.

2. The method according to claim 1, wherein: The step of generating the visitor danger information according to the sentence reply voice and the personnel image set includes: generating a first candidate visitor risk score for the set of person images; Acquire at least one reply sentence in the sentence reply speech; For at least one reply sentence, perform the following generation steps: Determine at least one sentence danger information corresponding to at least one reply sentence by using a sentence danger information generation model, wherein the sentence danger information includes: a sentence danger score and sentence danger cause information; Taking a weighted sum of at least one sentence risk score and the first candidate visit risk score to obtain a second candidate visit risk score; generating predicted danger cause information based on at least one sentence danger cause information; In response to determining that the second candidate visit risk score is in the first interval or the second interval, the second candidate visit risk score and the predicted risk cause information corresponding to the second candidate visit risk score are determined as visit risk information, wherein the value corresponding to the second interval is greater than the value corresponding to the first interval.

3. The method according to claim 2, wherein: The method further comprises: In response to determining that the second candidate visit risk score is in the third interval, using the fraud potential inquiry sentence generation model, generating a fraud potential inquiry sentence for the sentence reply speech as a target fraud potential inquiry sentence, wherein the value corresponding to the third interval is greater than the value corresponding to the first interval, and the value corresponding to the second interval is greater than the value corresponding to the third interval; Controlling an outdoor voice playback device to play the target fraud potential inquiry statement; Acquire the sentence reply voice of the visitor in response to the target fraud potential inquiry sentence as the target sentence reply voice; Performing authenticity verification on the target sentence reply speech to obtain an authenticity verification result as the target authenticity verification result; In response to determining that the target authenticity verification result indicates that the target sentence reply voice is the real voice of the visitor, according to the target sentence reply voice and the person image set, the person determination information corresponding to the visitor is determined again as the target person determination information; In response to determining that the target person determination information does not exist in the target person information list, generating at least one reply sentence corresponding to the target sentence reply voice as at least one target reply sentence; The generation step is continued by taking at least one target reply sentence as at least one reply sentence.

4. The method according to claim 1, wherein: The authenticity verification of the sentence reply voice is performed to obtain an authenticity verification result, including: Using the sound positioning device provided in the smart door lock device, generating voice positioning information for the sentence reply voice; Based on the voice localization information, the following processing steps are performed: In response to determining that the voice positioning information is not the first target location of the visitor, randomly acquiring a query sentence for the initial visit intention information from a corpus; Controlling the outdoor voice playing device to play the inquiry statement; Acquire a sentence reply voice to the inquiry sentence replied by the visitor as the inquiry sentence reply voice; Determining speech localization information of the speech replying to the inquiry sentence as target speech localization information; In response to determining that the target voice positioning information is the first target position of the visitor and the number of executions corresponding to the processing step is less than the target value, generating an authenticity verification result representing that the sentence reply voice passes the authenticity verification; In response to determining that the target voice positioning information is not the first target position of the visitor, the target voice positioning information is used as the voice positioning information and the processing step is performed again.

5. The method according to claim 1, wherein: The method further comprises: In response to detecting that the person who is to perform the door opening operation is not a person of the target category, the outdoor detection information processing device connected to the smart door lock device and located at the second target position is controlled to display the visitor danger information and a real-time image of the visitor outdoors, and the outdoor detection information processing device is controlled to play speech information for the visitor danger information and the door opening operation.

6. The method according to claim 5, wherein: The instructing the door opener to perform the door opening operation according to the door lock control strategy information includes: Instructing the door-opening person to view corresponding display content of the outdoor detection information processing device; In response to detecting that the person opening the door clicks on the outdoor detection information processing device to confirm that the displayed content is correct, instructing the person opening the door to click on a door opening control; In response to determining that control click information for the door opener is received, a door opening statement representing instructions to the door opener to perform a door opening operation is played.

7. A door lock control device based on an intelligent door lock device, comprising: A control unit, configured to, in response to detecting a visitor performing a preset action, control an image acquisition device to acquire a set of images of the visitor at multiple angles, wherein the image acquisition device is an image acquisition device provided in the smart door lock device and used to acquire outdoor images; A first generating unit is configured to generate initial personnel information corresponding to the visiting person according to the personnel image set; A second generating unit is configured to generate initial visit intention information corresponding to the visitor according to the person image set in response to determining that the initial person information does not exist in the target person information list; The third generating unit is configured to generate visit danger information for the visitor according to the initial visit intention information, wherein the generating of the visit danger information for the visitor according to the initial visit intention information includes: using a pre-trained fraud potential inquiry sentence generation model to generate a fraud potential inquiry sentence for the initial visit intention information; controlling an outdoor voice playback device to play the fraud potential inquiry sentence; obtaining a sentence reply voice for the fraud potential inquiry sentence replied by the visitor; performing an authenticity verification on the sentence reply voice to obtain an authenticity verification result; in response to determining that the authenticity verification result indicates that the sentence reply voice is the real voice of the visitor, re-determining the person determination information corresponding to the visitor according to the sentence reply voice and the person image set; in response to determining that the person determination information does not exist in the target person information list, generating the visit danger information according to the sentence reply voice and the person image set; A fourth generating unit is configured to generate preset door lock control strategy information corresponding to the visitor danger information; The indication unit is configured to, in response to detecting that the door-opening person to be opened is a person of the target category, indicate the door-opening person to perform the door-opening operation according to the door lock control strategy information.

8. An electronic device comprising: one or more processors; a storage device having one or more programs stored thereon, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 6.

9. A computer readable medium having a computer program stored thereon, wherein: When the program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images