Security equipment control method, device, electronic device and computer-readable medium

By obtaining user permission information to generate device command configuration information and performing verification processing, the problems of cumbersome user operations and differences in interaction habits in security equipment control are solved, and the effect of simplifying operations and improving user experience is achieved.

CN118784461BActive Publication Date: 2025-08-15ADDX (BEIJING) TECH CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202410758814.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-06-13
Publication Date
2025-08-15
Estimated Expiration
2044-06-13

AI Technical Summary

Technical Problem

In the existing security equipment control methods, users need to perform multiple operations to complete complex configurations, and the differences in interaction habits of different users lead to a poor experience.

Method used

By obtaining user configuration permission information, generating device command configuration information and performing verification processing, displaying a configuration information interface for users to confirm, simplifying the operation process and adapting to the interactive habits of different users.

Benefits of technology

It simplifies user operation process, improves the security and user experience of security equipment configuration, adapts to the interactive habits of different users, and reduces cumbersome interface operations.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118784461B_ABST
    Figure CN118784461B_ABST
Patent Text Reader

Abstract

Embodiments of the present disclosure disclose a security device control method, apparatus, electronic device, and computer-readable medium. A specific implementation of the method includes: in response to detecting device configuration request information corresponding to a security device to be configured, obtaining user configuration permission information; determining configuration text information; determining preset prompt information as device prompt information; inputting the configuration text information and device prompt information into a device command configuration information generation model to obtain device command configuration information; verifying the device command configuration information to obtain a verification result; in response to determining that the verification result meets a preset verification condition, displaying a device configuration information interface; determining whether to generate confirmation information corresponding to the device configuration information interface; and in response to determining that the confirmation information corresponding to the device configuration information interface is generated, controlling the security device to be configured to execute at least one device operation corresponding to the device command configuration information. This implementation can simplify user operations.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of computer technology, and more particularly to a security equipment control method, apparatus, electronic device, and computer-readable medium. Background Art

[0002] With the rapid development of the Internet of Things (IoT), security devices (such as video surveillance equipment) are becoming increasingly common in smart homes. Currently, controlling security devices typically involves setting execution commands on the corresponding app interface via an associated terminal, and then controlling the security device to perform related operations based on the set execution commands.

[0003] However, the inventors found that when the above method is used to control security equipment, the following technical problems often occur: when setting execution commands on the corresponding APP application interface through the associated terminal, when the execution commands are more complicated, the user needs to perform multiple operations to complete the configuration, resulting in cumbersome configuration user operations.

[0004] In the process of adopting technical solutions to solve the above-mentioned technical problem 1, the following technical problem often arises: how does the user confirm the configured information? In response to the above-mentioned technical problem, the conventional solution is generally to display the configured information through the interface and to display corresponding confirmation controls for user interaction and confirmation. However, the above-mentioned conventional solution still has the following problem 2: different users have different interaction habits. For example, users with hand disabilities find it inconvenient to use confirmation controls for interaction, resulting in a poor user experience.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the inventive concept and therefore it may contain information that does not form the prior art that is already known in this country to a person of ordinary skill in the art. Summary of the Invention

[0006] The content of this disclosure is used to briefly introduce concepts that will be described in detail in the detailed description section below. The content of this disclosure is not intended to identify key features or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0007] Some embodiments of the present disclosure provide security equipment control methods, devices, electronic devices, and computer-readable media to solve the technical problems mentioned in the above background technology section.

[0008] In a first aspect, some embodiments of the present disclosure provide a security device control method, the method comprising: in response to detecting device configuration request information corresponding to a security device to be configured, obtaining user configuration permission information corresponding to a configuration user identifier, wherein the device configuration request information includes the security device identifier to be configured; in response to determining that the user configuration permission information satisfies a preset permission condition, determining configuration text information corresponding to the security device identifier to be configured; determining the preset prompt information corresponding to the security device identifier to be configured as device prompt information in a preset prompt information concentration; inputting the configuration text information and the device prompt information into a pre-trained device command configuration information generation model to obtain device command configuration information; performing verification processing on the device command configuration information to obtain a verification result; in response to determining that the verification result satisfies the preset verification condition, displaying a device configuration information interface corresponding to the device command configuration information; determining whether to generate confirmation information corresponding to the device configuration information interface; in response to determining that confirmation information corresponding to the device configuration information interface is generated, controlling the security device to be configured to perform at least one device operation corresponding to the device command configuration information.

[0009] In a second aspect, some embodiments of the present disclosure provide a security device control device, the device comprising: an acquisition unit, configured to, in response to detecting device configuration request information corresponding to the security device to be configured, acquire user configuration permission information corresponding to the configuration user identifier, wherein the above-mentioned device configuration request information includes the security device to be configured identifier; a first determination unit, configured to, in response to determining that the above-mentioned user configuration permission information meets a preset permission condition, determine the configuration text information corresponding to the above-mentioned security device identifier to be configured; a second determination unit, configured to determine the preset prompt information corresponding to the above-mentioned security device identifier to be configured as the device prompt information in the preset prompt information set; an input unit, configured to input the above-mentioned configuration text information into the device prompt information. This information and the above-mentioned device prompt information are input into a pre-trained device command configuration information generation model to obtain device command configuration information; the verification unit is configured to verify the above-mentioned device command configuration information to obtain a verification result; the display unit is configured to display the device configuration information interface corresponding to the above-mentioned device command configuration information in response to determining that the above-mentioned verification result meets the preset verification condition; the third determination unit is configured to determine whether to generate confirmation information corresponding to the above-mentioned device configuration information interface; the control unit is configured to control the above-mentioned security device to be configured to perform at least one device operation corresponding to the above-mentioned device command configuration information in response to determining that the confirmation information corresponding to the above-mentioned device configuration information interface is generated.

[0010] In a third aspect, some embodiments of the present disclosure provide an electronic device comprising: one or more processors; a storage device on which one or more programs are stored, and when the one or more programs are executed by one or more processors, the one or more processors implement the method described in any implementation of the first aspect above.

[0011] In a fourth aspect, some embodiments of the present disclosure provide a computer-readable medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the method described in any implementation of the first aspect is implemented.

[0012] The aforementioned embodiments of the present disclosure have the following beneficial effects: The security device control methods of some embodiments of the present disclosure can simplify user operations. Specifically, the cumbersome configuration user operation is caused by setting execution commands on the corresponding app interface through an associated terminal. When the execution commands are complex, the user needs to perform multiple operations to complete the configuration, resulting in cumbersome configuration operations. Based on this, the security device control methods of some embodiments of the present disclosure first obtain user configuration permission information corresponding to the configuration user identifier in response to detecting a device configuration request message corresponding to the security device to be configured. The device configuration request message includes the identity of the security device to be configured. Thus, when a user issues a request to configure the security device, it can determine whether the user has permission to configure the security device, thereby improving the security of the security device. Secondly, in response to determining that the user configuration permission information meets preset permission conditions, configuration text information corresponding to the identity of the security device to be configured is determined. Thus, if the identity information corresponding to the configuration user has permission to configure the security device, a textual description of the configuration user's security device configuration requirements can be obtained, thereby clarifying the configuration requirements of the configuration user. Then, the preset prompt information corresponding to the identifier of the security device to be configured in the preset prompt information set is determined as the device prompt information. This generates prompt information for configuring the security device, which can be used to generate commands for configuring the security device. The configuration text information and the device prompt information are then input into a pre-trained device command configuration information generation model to generate device command configuration information. This automatically generates commands for configuring the security device configured by the user, which can be used to control the security device to perform device operations. Next, in response to determining that the verification result meets the preset verification conditions, a device configuration information interface corresponding to the device command configuration information is displayed. This allows the configured user to intuitively display the configured information, allowing the user to confirm whether it is correct. Next, a determination is made as to whether confirmation information corresponding to the device configuration information interface is generated. This allows the user to confirm the displayed configuration information. Finally, in response to determining that confirmation information corresponding to the device configuration information interface is generated, the configured security device is controlled to perform at least one device operation corresponding to the device command configuration information. Consequently, when the user confirms the displayed configuration information, the security device can be controlled to perform the device operation requested by the user. Also, when controlling the security equipment to perform various equipment operations, the configuration user only needs to naturally express the configuration requirements for the security equipment through a piece of text, and then clarify the configuration user's needs through the intention recognition of the text. After that, combined with the prompt information of the security equipment configuration command, the configuration command of the security equipment is automatically generated and confirmed by the configuration user through the interface, so that the configuration user does not need to make settings through interface operations, thereby simplifying user operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The above and other features, advantages, and aspects of the various embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that components and elements are not necessarily drawn to scale.

[0014] Figure 1 is a flow chart of some embodiments of the security device control method according to the present disclosure;

[0015] Figure 2 is a schematic structural diagram of some embodiments of the security equipment control device according to the present disclosure;

[0016] Figure 3 It is a structural diagram of an electronic device suitable for implementing some embodiments of the present disclosure. DETAILED DESCRIPTION

[0017] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of protection of the present disclosure.

[0018] It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present disclosure may be combined with each other.

[0019] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0020] It should be noted that the modifications of "one" and "multiple" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, they should be understood as "one or more".

[0021] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0022] The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0023] Figure 1The process 100 of some embodiments of the security device control method according to the present disclosure is shown. The security device control method includes the following steps:

[0024] Step 101: in response to detecting device configuration request information corresponding to a security device to be configured, obtaining user configuration permission information corresponding to a configuration user identifier.

[0025] In some embodiments, an executing entity (e.g., a computing device) of a security device control method may, in response to detecting device configuration request information corresponding to a security device to be configured, obtain user configuration permission information corresponding to a configuration user identifier. The security device to be configured may be a security device awaiting configuration. The security device may be a security protection device. For example, the security device may be a video surveillance device or a household smoke sensor. The device configuration request information may indicate a request for configuration of the security device to be configured. The device configuration request information may include, but is not limited to, the identifier of the security device to be configured. The identifier of the security device to be configured may be a unique identifier of the security device to be configured. The device configuration request information may also include a configuration user identifier. The configuration user identifier may be a unique identifier of the configuration user. The configuration user may be a user who needs to configure the functions of the security device to be configured. The user configuration permission information may indicate whether the configuration user has permission to configure the security device to be configured. The user configuration permission information may include, but is not limited to, a configuration permission type. The configuration permission type may indicate whether the user has permission to configure the security device to be configured. The above-mentioned configuration permission type may be, but is not limited to, one of the following: authorized or unauthorized. In practice, the above-mentioned execution entity may, in response to detecting device configuration request information corresponding to the security device to be configured, obtain user configuration permission information corresponding to the configuration user identifier from the database via a wired connection or a wireless connection. It should be noted that the above-mentioned wireless connection method may include, but is not limited to, 3G / 4G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection, and other wireless connection methods currently known or to be developed in the future.

[0026] Step 102: In response to determining that the user configuration permission information meets the preset permission condition, determine the configuration text information corresponding to the security device identifier to be configured.

[0027] In some embodiments, the execution subject may determine the configuration text information corresponding to the security device identifier to be configured in response to determining that the user configuration permission information satisfies the preset permission conditions. The preset permission conditions may be that the configuration permission type included in the user configuration permission information represents the permission to configure the security device to be configured. The configuration text information may be a text representing the function input by the configuration user for configuring the security device. There is no limitation on the description method and number of words included in the configuration text information. For example, if the security device to be configured is a video surveillance device, the configuration text information may be "the device is turned on from 7 am to 7 pm every day, the alarm ring of the video surveillance is the first emergency ring, and the cached video files are cleared every week." In practice, the execution subject may determine the configuration text information corresponding to the security device identifier to be configured in various ways in response to determining that the user configuration permission information meets the preset permission conditions.

[0028] In some optional implementations of some embodiments, the execution entity may determine the configuration text information corresponding to the security device identifier to be configured through the following steps:

[0029] The first step is to display a device configuration interface. The device configuration interface may be an interface for configuring the functions of the security device. The device configuration interface may include, but is not limited to, a configuration text input box and a configuration confirmation control. The configuration text input box may be used for the user to enter text information. The configuration confirmation control may be used for the user to enter text information.

[0030] In the second step, in response to detecting a selection operation on the configuration confirmation control, the text information corresponding to the configuration text input box is determined as the configuration text information. The selection operation can be, but is not limited to, at least one of the following: click, slide, and hover.

[0031] In some other optional implementations of some embodiments, the execution entity may determine the configuration text information corresponding to the security device identifier to be configured through the following steps:

[0032] The first step is to control the associated sound collection device to perform a voice collection operation. The sound collection device may be a microphone array or a receiver. The voice collection operation may be an operation of collecting voice.

[0033] In the second step, in response to detecting the user voice information, pre-emphasize the user voice information to obtain first voice information. The user voice information may be a voice signal emitted by the configured user. In practice, the execution entity may filter the user voice information using a high-pass filter to obtain the first voice information in response to detecting the user voice information.

[0034] The third step is to perform frame processing on the first voice information to obtain a voice frame information sequence. In practice, the execution entity may perform frame processing on the first voice information according to a preset frame length to obtain a voice frame information sequence. The preset frame length may be a pre-set frame length. For example, the preset frame length may be 20 milliseconds.

[0035] The fourth step is to perform windowing processing on each voice frame information included in the voice frame information sequence to obtain an updated voice frame information sequence. In practice, the execution entity may perform windowing processing on each voice frame information included in the voice frame information sequence using a preset windowing function to obtain an updated voice frame information sequence. The preset windowing function may be a pre-set windowing function. For example, the preset windowing function may be a Hamming window function.

[0036] Step 5: Perform voiceprint recognition on the updated voice frame information sequence to obtain a voiceprint recognition result. The voiceprint recognition result can indicate whether the user voice information is produced by a user with configuration permission. In practice, the execution entity can perform voiceprint recognition on the updated voice frame information sequence to obtain a voiceprint recognition result in various ways.

[0037] In step 6, in response to determining that the voiceprint recognition result satisfies a preset voiceprint condition, voice recognition processing is performed on the updated voice frame information sequence to obtain voice text information. The preset voiceprint condition may be that the voiceprint recognition result indicates that the user voice information is a voice produced by a user with configuration permission.

[0038] Step 7: Determine the above voice text information as configuration text information.

[0039] In some optional implementations of some embodiments, the execution entity may perform voiceprint recognition processing on the updated voice frame information sequence through the following steps to obtain a voiceprint recognition result:

[0040] In the first step, feature extraction processing is performed on each updated voice frame information included in the above-mentioned updated voice frame information sequence to obtain voice feature information. The above-mentioned voice feature information includes a voice feature vector. In practice, the above-mentioned execution entity can perform feature extraction processing on each updated voice frame information included in the above-mentioned updated voice frame information sequence using a preset voice feature extraction algorithm to obtain voice feature information. The above-mentioned preset voice feature extraction algorithm can be a pre-set algorithm for extracting voice features. For example, the above-mentioned preset voice feature extraction algorithm can be a Mel Frequency Cepstral Coefficents (MFCC) algorithm.

[0041] The second step is to obtain a target user voice feature vector set corresponding to the security device identifier to be configured. The target user voice feature vectors in the target user voice feature vector set may be voice feature vectors of the target user. The target user may be a user with permission to configure the security device to be configured. In practice, the execution entity may obtain the target user voice feature vector set corresponding to the security device identifier to be configured from a database via a wired or wireless connection.

[0042] In a third step, for each target user speech feature vector included in the target user speech feature vector set, a feature similarity is generated based on the target user speech feature vector and the speech feature vector. In practice, for each target user speech feature vector included in the target user speech feature vector set, the execution entity may determine the feature similarity as the cosine similarity between the target user speech feature vector and the speech feature vector.

[0043] In a fourth step, in response to determining that any feature similarity included in the generated feature similarities satisfies a preset similarity condition, preset recognition success information is determined as the voiceprint recognition result information. The preset similarity condition may be that the feature similarity is greater than or equal to a preset similarity. The preset similarity may be a preset similarity indicating that two feature vectors are identical. The preset recognition success information may be a preset indication that the configuration user has configuration permission for the security device to be configured.

[0044] Thus, the identity of the user who sends the voice message can be verified first, thereby improving the security of configuring security equipment.

[0045] In some optional implementations of some embodiments, the execution entity may perform speech recognition processing on the updated speech frame information sequence to obtain speech text information through the following steps:

[0046] The first step is to transform each updated speech frame information included in the updated speech frame information sequence to obtain spectrogram information. In practice, the execution entity can transform each updated speech frame information included in the updated speech frame information sequence through fast Fourier transform and logarithmic transform to obtain spectrogram information.

[0047] In the second step, the above-mentioned spectrogram information is input into a pre-trained language type generation model to obtain the language type. The above-mentioned language type generation model can be a neural network that takes the spectrogram information as input and outputs the language type. The above-mentioned neural network can be an LSTM (Long Short-term Memory) network. The above-mentioned language type can represent the category to which the pronunciation characteristics of the speech belong. The above-mentioned language type can be, but is not limited to, one of the following: Cantonese, Sichuanese, Mandarin, and Henan dialect. The above-mentioned language type generation model includes an input layer, a first feature extraction layer, a second feature extraction layer, a third feature extraction layer, a fourth feature extraction layer, and an output layer. The above-mentioned input layer can be a network layer for shallow feature extraction. The above-mentioned input layer can be a convolutional layer with a convolution kernel size of 7×7. The above-mentioned first feature extraction layer, second feature extraction layer, third feature extraction layer, and fourth feature extraction layer can each include a residual module and a self-attention mechanism module. The above-mentioned residual module can include 3 convolutional layers. The first, second, third, and fourth feature extraction layers can each perform the following steps: First, the input feature information is input into the corresponding residual module to obtain a first feature vector. The first feature vector is a feature vector containing spatial and channel attention weights. Second, the input feature information is input into the corresponding self-attention mechanism module to obtain a second feature vector. The second feature vector can be a feature vector containing self-attention weights. Finally, the sum of the first and second feature vectors is determined as the output feature vector. The output feature vector can be the feature vector output by the corresponding feature extraction layer. The output layer can be a classifier that takes the feature vector as input and outputs the language type. The input layer is connected to the first feature extraction layer. The first feature extraction layer is connected to the second feature extraction layer. The second feature extraction layer is connected to the third feature extraction layer. The third feature extraction layer is connected to the fourth feature extraction layer. The fourth feature extraction layer is connected to the output layer.

[0048] In the third step, the preset speech-text information generation model corresponding to the above-mentioned language type included in the preset speech-text information generation model set is determined as the target speech-text information generation model. The preset speech-text information generation model included in the preset speech-text information generation model set corresponds to a dialect type. The above-mentioned dialect type can be, but is not limited to, at least one of the following: Cantonese, Sichuanese, Mandarin, and Henan dialect. The preset speech-text information generation model included in the preset speech-text information generation model set can be a pre-trained model that converts speech of the corresponding dialect type into text. The preset speech-text information generation model can be a neural network that takes speech information as input and speech-text information as output. The above-mentioned neural network can be an LSTM network. The above-mentioned speech-text information can be text representing the corresponding speech.

[0049] The fourth step is to input the user voice information into the target voice-to-text information generation model to obtain voice-to-text information.

[0050] Therefore, the language type of the voice information can be identified first, and then the voice recognition can be performed through the corresponding voice recognition model. Therefore, when different configuration users use different language types for description, the accuracy of voice recognition can be improved, and the accuracy of the configuration information can be improved.

[0051] Step 103: Determine the preset prompt information corresponding to the identifier of the security device to be configured in the preset prompt information set as the device prompt information.

[0052] In some embodiments, the execution entity may determine the preset prompt information in the preset prompt information set corresponding to the security device identifier to be configured as the device prompt information. The preset prompt information in the preset prompt information set may correspond to the security device identifier to be configured. The preset prompt information in the preset prompt information set may be information in a pre-set format for prompting the generation of configuration commands. For example, when the security device is an air purifier, the preset prompt information may be "A configuration instruction for the security device needs to be generated. The instruction needs to follow the following format: {"command":"setTo","target":"airConditioner","level":"23",timeSchedule":"19:00'}." For another example, when the security device is a video surveillance device, the preset prompt information may be "A configuration instruction for the security device needs to be generated. The instruction needs to follow the following format: {"command":"setTo","target":"camera","Siren sounds":"firstSiren sounds",timeSchedule":"7:00-19:00",clear":"every other week"}."

[0053] Step 104 : Input the configuration text information and the device prompt information into a pre-trained device command configuration information generation model to obtain the device command configuration information.

[0054] In some embodiments, the execution entity may input the configuration text information and the device prompt information into a pre-trained device command configuration information generation model to obtain the device command configuration information. The device command configuration information generation model may be a generative model that takes the configuration text information and the device prompt information as input and outputs the device command configuration information. For example, the generative model may be a GPT (Generative Pre-trained Transformer) model. The device command configuration information may be instruction code for a user to configure the operation of the security device.

[0055] Optionally, the device command configuration information generation model may be generated through the following training steps:

[0056] The first step is to obtain a sample, wherein the sample may include sample configuration text information and sample device prompt information.

[0057] In the second step, the sample configuration text information included in the sample is input into the input layer of the initial device command configuration information generation model to obtain preprocessed sample text information. The input layer can be used to preprocess the sample configuration text information to obtain preprocessed sample text information. The preprocessing can include, but is not limited to, at least one of the following: text cleaning and word cleaning.

[0058] The third step is to determine the initial number of inputs and perform the following input steps:

[0059] In the first input step, the pre-processed sample text information is input into the intent recognition model included in the initial device command configuration information generation model to obtain intent text information. The intent recognition model can be a generative model that takes text information as input and outputs intent text information. For example, the generative model can be a GPT model. The intent text information can be text that clearly expresses the user's requirements for configuring the security device. For example, if the configuration text information is "The device is on from 7:00 AM to 7:00 PM daily, the video surveillance alarm is the first emergency ring, and cached video files are cleared every week," the intent text information can be "Video surveillance device; on from 7:00 AM to 7:00 PM, the alarm is the first emergency ring, and cached video files are cleared every week." The initial input count can be the initial number of times the pre-processed sample text information is input into the intent recognition model included in the initial device command configuration information generation model. In practice, the execution entity can set a preset initial input count as the initial input count. The preset initial input count can be a pre-set initial input count. For example, the preset initial input count can be 0.

[0060] In the second input step, the initial input count is updated to obtain an updated input count as the initial input count. In practice, the execution entity may determine the sum of the initial input count and the preset increment count as the updated input count, which serves as the initial input count. The preset increment count may be a pre-set value that increases with each input. For example, the preset increment count may be 1.

[0061] In a fourth input step, in response to determining that the initial input number satisfies a preset number condition, the above input step is continued. The preset number condition may be that the initial input number is less than or equal to a preset number of inputs. The preset number of inputs may be a pre-set number of inputs. For example, the preset number of inputs may be 5.

[0062] In the fifth input step, in response to determining that the initial number of inputs does not meet the above-preset number condition, for each obtained intent text message, the sample configuration text message and the intended text message are concatenated to obtain concatenated text message. In practice, the execution entity may, in response to determining that the initial number of inputs does not meet the above-preset number condition, combine the sample configuration text message and the intended text message for each obtained intent text message to obtain concatenated text message. The concatenation method may be character concatenation.

[0063] In the third step, the obtained concatenated text information is input into an intent ranking model to obtain an intent text information sequence. The intent ranking model may be a BERT (Bidirectional Encoder Representations from Transformers) model that takes the concatenated text information as input and outputs a sequence of intent text information. The sequence of intent text information may be a sequence in which the intent text information is arranged in descending order of the scores of the corresponding concatenated text information. The intent ranking model may include a text input layer, a feature extraction layer, a score generation layer, and a sequence output layer. The text input layer may be used to encode the concatenated text information. The feature extraction layer may be used to extract features from the encoded concatenated text information to obtain a concatenated text feature vector. The score generation layer may generate a loss value corresponding to the concatenated text feature vector using a cross-entropy loss function, and determine a preset score corresponding to the loss value as a score. The preset score may be a pre-set score. The sequence output layer may sort the intent text information in descending order of the scores corresponding to the intent text information to obtain the intent text information sequence.

[0064] In the fourth step, the intended text information that meets a preset sequence number condition in the intended text information sequence is determined as the target intended text information, wherein the preset sequence number condition may be that the intended text information has a position of 1 in the intended text information sequence.

[0065] In the fifth step, the target intent text information and the sample device prompt information are input into the output layer of the initial device command configuration information generation model to obtain the device command configuration information corresponding to the sample. The output layer can be a generation model that takes the intent text information and device prompt information as input and outputs the device command configuration information. For example, the generation model can be a GPT model.

[0066] In step 6, the sample device command configuration information is compared with the device command configuration information corresponding to the sample to obtain a comparison result. Here, the comparison method can calculate the loss value through the cross entropy loss function.

[0067] Step 7: Based on the comparison results, determine whether the initial device command configuration information generation model has achieved a preset optimization goal. The optimization goal can be that the calculated loss value is less than a preset loss value. There is no limit on the setting of the preset loss value.

[0068] In step 8, in response to determining that the initial device command configuration information generation model does not achieve the above-mentioned optimization goal, the network parameters of the initial device command configuration information generation model are adjusted, and the adjusted initial device command configuration information generation model is used as the initial device command configuration information generation model, and the above-mentioned training steps are continued. As an example, the network parameters of the initial device command configuration information generation model can be adjusted using a back propagation algorithm (BP algorithm) and a gradient descent method (e.g., a stochastic mini-batch gradient descent algorithm).

[0069] Optionally, the above training step further includes:

[0070] In the ninth step, in response to determining that the initial device command configuration information generation model achieves the above-mentioned optimization goal, the initial device command configuration information generation model is determined as the trained device command configuration information generation model.

[0071] Step 105: Verify the device command configuration information to obtain a verification result.

[0072] In some embodiments, the execution entity may verify the device command configuration information to obtain a verification result. The verification result may indicate whether the device command configuration information is incorrect. In practice, the execution entity may verify the device command configuration information using a preset code analyzer to obtain a verification result. The preset code analyzer may be a pre-set code analysis tool for detecting code syntax errors. For example, the preset code analyzer may be SonarQube.

[0073] Step 106 : In response to determining that the verification result satisfies the preset verification condition, a device configuration information interface corresponding to the device command configuration information is displayed.

[0074] In some embodiments, the execution entity may, in response to determining that the verification result satisfies a preset verification condition, display a device configuration information interface corresponding to the device command configuration information. The preset verification condition may be that the verification result indicates that the device command configuration information is correct. The device configuration information interface may be an interface for displaying the functional configuration of the device.

[0075] Step 107: Determine whether confirmation information corresponding to the device configuration information interface is generated.

[0076] In some embodiments, the execution entity may determine whether to generate confirmation information corresponding to the device configuration information interface. The confirmation information may be information from the configuration user confirming that the device configuration information displayed on the device configuration information interface is correct. In practice, the execution entity may determine whether to generate confirmation information corresponding to the device configuration information interface in various ways.

[0077] To address the second technical issue mentioned above: different users have different interaction habits. For example, users with hand impairments may not be able to use confirmation controls to interact, resulting in a poor user experience. Combining the advantages of big data, the following solutions can be adopted:

[0078] Optionally, the execution entity may determine whether to generate confirmation information corresponding to the device configuration information interface by following the steps below:

[0079] The first step is to obtain a historical operation information sequence corresponding to the above-mentioned configuration user identifier. The historical operation information in the above-mentioned historical operation information sequence can characterize the interaction mode of the corresponding configuration user with the execution subject in the historical time period. The above-mentioned historical operation information sequence may include but is not limited to the operation type. The above-mentioned operation type can characterize the interaction mode of the configuration user and the execution subject. The above-mentioned operation type can be but is not limited to one of the following: control type, body gesture confirmation type, voice type. The above-mentioned control type can be a type of interaction through a control. The above-mentioned body gesture confirmation type can be a type of interaction through the user's body gesture. The above-mentioned voice type can be a type of interaction through the user's voice. In practice, the above-mentioned execution subject can obtain the historical operation information sequence corresponding to the above-mentioned configuration user identifier through a wired connection or a wireless connection.

[0080] In the second step, the historical operation information sequence is input into a pre-trained model for generating predicted operation information to obtain predicted operation information. The model for generating predicted operation information may be a neural network that takes the historical operation information sequence as input and outputs predicted operation information. The neural network may be an LSTM network. The predicted operation information may represent the predicted type of operation that the user will perform. The predicted operation information may include, but is not limited to, the predicted operation type. The predicted operation type may be the predicted operation type.

[0081] In the third step, in response to determining that the predicted operation type is a control type, an information confirmation control is displayed on the device configuration information interface. The information confirmation control can be used for the configuration user to confirm the information displayed on the device configuration information interface.

[0082] In the fourth step, in response to detecting a selection operation on the information confirmation control, determining to generate confirmation information corresponding to the device configuration information interface.

[0083] In a fifth step, in response to determining that the predicted operation type is a body gesture confirmation type, controlling an associated image acquisition device to acquire a sequence of images of the configured user's body gestures. The image acquisition device may be a camera. The sequence of images of the configured user's head gestures may include images of the configured user's body gestures. The body gestures may be hand gestures or head gestures.

[0084] The sixth step is to perform limb motion recognition processing on the above-mentioned configured user limb posture image sequence to obtain the limb motion type. The above-mentioned limb motion type can represent the action represented by the limb. For example, the above-mentioned limb motion type can be a hand gesture OK or a nod. In practice, the above-mentioned execution subject can perform limb motion recognition processing on the above-mentioned configured user limb posture image sequence through a preset limb motion recognition processing algorithm to obtain the limb motion type. The above-mentioned preset limb motion recognition processing algorithm can be a pre-set algorithm for recognizing limb motions. For example, the above-mentioned preset limb motion recognition processing algorithm can be a gesture recognition algorithm based on a convolutional neural network, or a head posture recognition algorithm based on a convolutional neural network.

[0085] In step 7, in response to determining that the above-mentioned body movement type meets the preset body movement type condition, determining to generate confirmation information corresponding to the above-mentioned device configuration information interface. The above-mentioned preset body movement type condition can be that the body movement represented by the body movement type is the same as the pre-set movement representing the user confirmation information.

[0086] In step 8, in response to determining that the predicted operation type is a voice confirmation type, controlling the associated sound collection device to collect sound to obtain first user voice information. The first user voice information may be a voice signal emitted by the user.

[0087] In step nine, voice recognition processing is performed on the first user's voice information to obtain a voice recognition result. The voice recognition result can ensure that the voice is a predetermined voice that indicates confirmation of the information. In practice, first, the execution entity may perform feature extraction processing on the first user's voice information using a predetermined voice feature extraction algorithm to obtain a first voice feature vector. The predetermined voice feature extraction algorithm may be a predetermined algorithm for extracting voice features. For example, the predetermined voice feature extraction algorithm may be a voice feature extraction algorithm based on a recurrent neural network. Next, the cosine similarity between the first voice feature vector and the predetermined confirmation voice feature vector is determined as the voice similarity. The predetermined confirmation voice feature vector may be a predetermined feature vector that indicates the voice is a confirmed voice. Then, in response to determining that the voice similarity satisfies a predetermined voice similarity condition, a predetermined recognition success message is determined as the voice recognition result. The predetermined voice similarity condition may be that the voice similarity is greater than a predetermined voice similarity. The predetermined voice similarity may be a predetermined similarity that indicates that the voices are identical. The predetermined recognition success message may be a predetermined message indicating that the voice uttered by the user is identical to a predetermined voice that indicates confirmation. Finally, in response to determining that the voice similarity does not meet the preset voice similarity condition, a preset recognition failure message is determined as the voice recognition result. The preset recognition failure message may be a preset signal indicating that the voice uttered by the user is different from a preset signal indicating confirmation.

[0088] In step 10, in response to determining that the voice recognition result satisfies a preset voice recognition result condition, determining to generate confirmation information corresponding to the device configuration information interface. The preset voice recognition result condition may be that the voice recognition result indicates that the voice uttered by the user is the same as a preset voice indicating confirmation.

[0089] The above technical solution and its related contents, as an inventive feature of the embodiments of the present disclosure, address the second problem mentioned in the background technology: "Different users have different interaction habits. For example, users with limited hands have difficulty using confirmation controls for interaction, resulting in a poor user experience." Factors contributing to a poor user experience are often as follows: Different users have different interaction habits. For example, users with limited hands have difficulty using confirmation controls for interaction, resulting in a poor user experience. Addressing these factors can improve the user experience. To achieve this, the security device control method of some embodiments of the present disclosure first obtains a historical operation information sequence corresponding to the configuration user identifier. This historical operation information sequence includes operation types. This allows the configuration user to determine the operation types used during a historical time period, which can be used to predict the interaction type used by the configuration user this time. Secondly, the historical operation information sequence is input into a pre-trained prediction operation information generation model to obtain predicted operation information. This predicted operation information includes the predicted operation type. This allows the configuration user to predict the interaction type intended for this time period, which can be used for interaction confirmation. Then, in response to determining that the predicted operation type is a control type, an information confirmation control is displayed on the device configuration information interface; in response to detecting a selection operation on the information confirmation control, confirmation information corresponding to the device configuration information interface is generated. Thus, when the predicted user intended interaction type is a control type, user confirmation can be provided through control interaction. Then, in response to determining that the predicted operation type is a gesture confirmation type, an associated image acquisition device is controlled to capture a sequence of images of the configured user's gestures; gesture recognition is performed on the sequence of gesture images to obtain a gesture type; and in response to determining that the gesture type meets a preset gesture type condition, confirmation information corresponding to the device configuration information interface is generated. Thus, when the predicted user intended interaction type is a gesture confirmation type, interaction confirmation can be performed by recognizing the gesture of the configured user. Finally, in response to determining that the predicted operation type is a voice type, an associated sound acquisition device is controlled to capture sound to obtain first user voice information; voice recognition is performed on the first user voice information to obtain a voice recognition result; and in response to determining that the voice recognition result meets a preset voice recognition result condition, confirmation information corresponding to the device configuration information interface is generated. Therefore, when the predicted user interaction type is voice interaction, the user can confirm it through voice interaction. This also improves the user experience because when the user confirms the configuration information, the predicted user interaction type can be used to provide the user with the corresponding interaction method for confirmation, thereby improving the user experience.

[0090] Step 108 : In response to the confirmation information of determining to generate the corresponding device configuration information interface, control the security device to be configured to execute at least one device operation corresponding to the device command configuration information.

[0091] In some embodiments, the execution entity may, in response to determining that a confirmation message corresponding to the device configuration information interface is generated, control the security device to be configured to perform at least one device operation corresponding to the device command configuration information. The device operation may include, but is not limited to, an opening operation, a closing operation, and an alarm operation.

[0092] As an example, when the above device command configuration information is "{"command":"setTo","target":"camera","Siren sounds":"first Siren sounds",timeSchedule”:"7:00-19:00”,clear”:"every other week”}", the security device to be configured "surveillance video device" performs the power-on operation at 7 o'clock in the morning to turn on the surveillance video device, and performs the power-off operation at 7 o'clock in the evening. When an alarm is required, the first emergency bell is used.

[0093] The aforementioned embodiments of the present disclosure have the following beneficial effects: The security device control methods of some embodiments of the present disclosure can simplify user operations. Specifically, the cumbersome configuration user operation is caused by setting execution commands on the corresponding app interface through an associated terminal. When the execution commands are complex, the user needs to perform multiple operations to complete the configuration, resulting in cumbersome configuration operations. Based on this, the security device control methods of some embodiments of the present disclosure first obtain user configuration permission information corresponding to the configuration user identifier in response to detecting a device configuration request message corresponding to the security device to be configured. The device configuration request message includes the identity of the security device to be configured. Thus, when a user issues a request to configure the security device, it can determine whether the user has permission to configure the security device, thereby improving the security of the security device. Secondly, in response to determining that the user configuration permission information meets preset permission conditions, configuration text information corresponding to the identity of the security device to be configured is determined. Thus, if the identity information corresponding to the configuration user has permission to configure the security device, a textual description of the configuration user's security device configuration requirements can be obtained, thereby clarifying the configuration requirements of the configuration user. Then, the preset prompt information corresponding to the identifier of the security device to be configured in the preset prompt information set is determined as the device prompt information. This generates prompt information for configuring the security device, which can be used to generate commands for configuring the security device. The configuration text information and the device prompt information are then input into a pre-trained device command configuration information generation model to generate device command configuration information. This automatically generates commands for configuring the security device configured by the user, which can be used to control the security device to perform device operations. Next, in response to determining that the verification result meets the preset verification conditions, a device configuration information interface corresponding to the device command configuration information is displayed. This allows the configured user to intuitively display the configured information, allowing the user to confirm whether it is correct. Next, a determination is made as to whether confirmation information corresponding to the device configuration information interface is generated. This allows the user to confirm the displayed configuration information. Finally, in response to determining that confirmation information corresponding to the device configuration information interface is generated, the configured security device is controlled to perform at least one device operation corresponding to the device command configuration information. Consequently, when the user confirms the displayed configuration information, the security device can be controlled to perform the device operation requested by the user. Also, when controlling the security equipment to perform various equipment operations, the configuration user only needs to naturally express the configuration requirements for the security equipment through a piece of text, and then clarify the configuration user's needs through the intention recognition of the text. After that, combined with the prompt information of the security equipment configuration command, the configuration command of the security equipment is automatically generated and confirmed by the configuration user through the interface, so that the configuration user does not need to make settings through interface operations, thereby simplifying user operations.

[0094] Further references Figure 2 As an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of a security equipment control device. These device embodiments are similar to Figure 1 Corresponding to the method embodiments shown, the device can be specifically applied to various electronic devices.

[0095] like Figure 2 As shown, the security device control apparatus 200 of some embodiments includes: an acquisition unit 201, a first determination unit 202, a second determination unit 203, an input unit 204, a verification unit 205, a display unit 206, a third determination unit 207, and a control unit 208. The acquisition unit 201 is configured to, in response to detecting device configuration request information corresponding to the security device to be configured, acquire user configuration permission information corresponding to the configuration user identifier, wherein the device configuration request information includes the security device to be configured identifier; the first determination unit 202 is configured to, in response to determining that the user configuration permission information meets a preset permission condition, determine configuration text information corresponding to the security device identifier to be configured; the second determination unit 203 is configured to determine the preset prompt information corresponding to the security device identifier to be configured as the device prompt information in the preset prompt information set; the input unit 204 is configured to input the configuration text information and the device prompt information into the preset prompt information. The device command configuration information generation model obtained by training is firstly used to obtain the device command configuration information; the verification unit 205 is configured to perform verification processing on the above-mentioned device command configuration information to obtain a verification result; the display unit 206 is configured to display the device configuration information interface corresponding to the above-mentioned device command configuration information in response to determining that the above-mentioned verification result meets the preset verification condition; the third determination unit 207 is configured to determine whether to generate confirmation information corresponding to the above-mentioned device configuration information interface; the control unit 208 is configured to control the above-mentioned security device to be configured to perform at least one device operation corresponding to the above-mentioned device command configuration information in response to determining that the confirmation information corresponding to the above-mentioned device configuration information interface is generated.

[0096] It is understood that the units described in the security equipment control device 200 are similar to those in the reference Figure 1 Therefore, the operations, features and beneficial effects described above for the method are also applicable to the device 200 and the units included therein, and will not be repeated here.

[0097] Reference below Figure 3, which shows a schematic structural diagram of an electronic device 300 suitable for implementing some embodiments of the present disclosure. The electronic devices in some embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 3 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0098] like Figure 3 As shown, the electronic device 300 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 into a random access memory (RAM) 303. Various programs and data required for the operation of the electronic device 300 are also stored in the RAM 303. The processing device 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0099] Typically, the following devices may be connected to the I / O interface 305: an input device 306 including, for example, a touch screen, a touchpad, 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 by wire to exchange data. Figure 3 The electronic device 300 is shown with various devices, but it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed instead. Figure 3 Each block shown in the figure may represent one device, or may represent multiple devices as needed.

[0100] In particular, according to some embodiments of the present disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, some embodiments of the present disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In some such embodiments, the computer program can be downloaded and installed from a network via 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-mentioned functions defined in the method of some embodiments of the present disclosure are performed.

[0101] It should be noted that the computer-readable medium described in some embodiments of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination of the above. More specific examples of computer-readable storage media 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 that can be used by or in conjunction with an instruction execution system, device, or device. In some embodiments of the present disclosure, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport 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 suitable medium, including but not limited to wires, optical cables, RF (radio frequency), etc., or any suitable combination thereof.

[0102] In some embodiments, the client and server can communicate using any currently known or future developed network protocol, such as HTTP (Hypertext Transfer Protocol), and can be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0103] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device. The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device: in response to detecting device configuration request information corresponding to the security device to be configured, obtains user configuration permission information corresponding to the configuration user identifier, wherein the device configuration request information includes the security device identifier to be configured; in response to determining that the user configuration permission information meets the preset permission condition, determines the configuration text information corresponding to the security device identifier to be configured; determines the preset prompt information corresponding to the security device identifier to be configured as the device prompt information in the preset prompt information set; inputs the configuration text information and the device prompt information into a pre-trained device command configuration information generation model to obtain device command configuration information; verifies the device command configuration information to obtain a verification result; in response to determining that the verification result meets the preset verification condition, displays a device configuration information interface corresponding to the device command configuration information; determines whether to generate confirmation information corresponding to the device configuration information interface; and in response to determining that confirmation information corresponding to the device configuration information interface is generated, controls the security device to be configured to perform at least one device operation corresponding to the device command configuration information.

[0104] Computer program code for performing the operations of some embodiments of the present disclosure may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, 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 cases involving 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 (e.g., through the Internet using an Internet service provider).

[0105] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0106] The units described in some embodiments of the present disclosure may be implemented in software or in hardware. The described units may also be provided in a processor. For example, they may be described as follows: a processor comprising an acquisition unit, a first determination unit, a second determination unit, an input unit, a verification unit, a display unit, a third determination unit, and a control unit. The names of these units do not, in some cases, constitute limitations on the units themselves. For example, the acquisition unit may also be described as a "unit that acquires user configuration permission information corresponding to a configuration user identifier in response to detecting device configuration request information corresponding to the security device to be configured."

[0107] The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, and without limitation, exemplary types of hardware logic components that may 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 the like.

[0108] The above description is only an illustration of some preferred embodiments of the present disclosure and the technical principles used. 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-mentioned technical features, but should also cover other technical solutions formed by any combination of the above-mentioned technical features or their equivalent features without departing from the above-mentioned inventive concept. For example, the above-mentioned features are replaced with (but not limited to) technical features with similar functions disclosed in the embodiments of the present disclosure.

Claims

1. A security equipment control method, comprising: In response to detecting device configuration request information corresponding to the security device to be configured, obtaining user configuration permission information corresponding to the configuration user identifier, wherein the device configuration request information includes the security device to be configured identifier; In response to determining that the user configuration permission information satisfies a preset permission condition, determining configuration text information corresponding to the identifier of the security device to be configured, wherein the configuration text information is text representing a function input by the configuration user for configuring the security device; Determine the preset prompt information corresponding to the identifier of the security device to be configured in the preset prompt information set as the device prompt information; Inputting the configuration text information and the device prompt information into a pre-trained device command configuration information generation model to obtain device command configuration information; Performing verification processing on the device command configuration information to obtain a verification result; In response to determining that the verification result satisfies a preset verification condition, displaying a device configuration information interface corresponding to the device command configuration information; Determining whether to generate confirmation information corresponding to the device configuration information interface; In response to determining that confirmation information corresponding to the device configuration information interface is generated, the security device to be configured is controlled to perform at least one device operation corresponding to the device command configuration information.

2. The method according to claim 1, wherein The determining of the configuration text information corresponding to the identifier of the security device to be configured includes: Displaying a device configuration interface, wherein the device configuration interface includes a configuration text input box and a configuration confirmation control, wherein the configuration text input box is used for the configuration user to input text information; In response to detecting a selection operation acting on the configuration confirmation control, the text information corresponding to the configuration text input box is determined as configuration text information.

3. The method according to claim 1, wherein The determining of the configuration text information corresponding to the identifier of the security device to be configured includes: Control the associated sound collection device to perform voice collection operations; In response to detecting user voice information, performing pre-emphasis processing on the user voice information to obtain first voice information; performing frame processing on the first voice information to obtain a voice frame information sequence; performing windowing processing on each voice frame information included in the voice frame information sequence to obtain an updated voice frame information sequence; Performing voiceprint recognition processing on the updated voice frame information sequence to obtain a voiceprint recognition result; In response to determining that the voiceprint recognition result meets the preset voiceprint condition, performing voice recognition processing on the updated voice frame information sequence to obtain voice text information; The voice text information is determined as configuration text information.

4. The method according to claim 3, wherein: The performing voiceprint recognition processing on the updated voice frame information sequence to obtain a voiceprint recognition result includes: performing feature extraction processing on each updated speech frame information included in the updated speech frame information sequence to obtain speech feature information, wherein the speech feature information includes a speech feature vector; Obtaining a target user voice feature vector set corresponding to the identifier of the security device to be configured, wherein the target user voice feature vector in the target user voice feature vector set is a voice feature vector of a target user, and the target user is a user who has permission to configure the security device to be configured; For each target user speech feature vector included in the target user speech feature vector set, generating a feature similarity based on the target user speech feature vector and the speech feature vector; In response to determining that any feature similarity included in the generated feature similarities satisfies a preset similarity condition, preset recognition success information is determined as voiceprint recognition result information.

5. The method according to claim 3, wherein The performing speech recognition processing on the updated speech frame information sequence to obtain speech text information includes: Performing transformation processing on each updated speech frame information included in the updated speech frame information sequence to obtain spectrogram information; Inputting the spectrogram information into a pre-trained language type generation model to obtain a language type, wherein the language type generation model includes an input layer, a first feature extraction layer, a second feature extraction layer, a third feature extraction layer, a fourth feature extraction layer and an output layer; Determining a preset speech-text information generation model corresponding to the language type included in the preset speech-text information generation model set as a target speech-text information generation model; The user voice information is input into the target voice-text information generation model to obtain voice-text information.

6. The method according to claim 1, wherein The device command configuration information generation model is generated through the following training steps: Acquire a sample, wherein the sample includes sample configuration text information, sample device prompt information, and sample device command configuration information; Inputting the sample configuration text information included in the sample into the input layer included in the initial device command configuration information generation model to obtain sample preprocessed text information; Determine the initial input times and perform the following input steps: Inputting the sample preprocessed text information into the intention recognition model included in the initial device command configuration information generation model to obtain intention text information; The initial input times are updated to obtain the updated input times as the initial input times; In response to determining that the initial input number meets the preset number condition, continuing to perform the input step; In response to determining that the number of initial inputs does not meet the preset number condition, for each obtained intention text information, splicing the sample configuration text information and the intention text information to obtain spliced text information; Inputting the obtained concatenated text information into an intention ranking model to obtain an intention text information sequence, wherein the intention ranking model includes an input layer, a feature extraction layer, and an output layer; Determining the intended text information that meets the preset sequence number condition in the intended text information sequence as the target intended text information; Inputting the target intent text information and the sample device prompt information into an output layer of an initial device command configuration information generation model to obtain device command configuration information corresponding to the sample; Comparing the sample device command configuration information with the device command configuration information corresponding to the sample to obtain a comparison result; Determining whether the initial device command configuration information generation model achieves a preset optimization goal based on the comparison result; In response to determining that the initial device command configuration information generation model does not achieve the optimization goal, adjust the network parameters of the initial device command configuration information generation model, use the adjusted initial device command configuration information generation model as the initial device command configuration information generation model, and continue to perform the training step.

7. The method according to claim 6, wherein: The training step further comprises: In response to determining that the initial device command configuration information generation model achieves the optimization goal, the initial device command configuration information generation model is determined as the trained device command configuration information generation model.

8. A security equipment control device, comprising: an acquiring unit configured to acquire user configuration permission information corresponding to a configuration user identifier in response to detecting device configuration request information corresponding to a security device to be configured, wherein the device configuration request information includes the identifier of the security device to be configured; A first determining unit is configured to, in response to determining that the user configuration permission information satisfies a preset permission condition, determine configuration text information corresponding to the identifier of the security device to be configured, wherein the configuration text information is text representing a function input by the configuration user for configuring the security device; The second determining unit is configured to determine the preset prompt information corresponding to the identifier of the security device to be configured in the preset prompt information set as the device prompt information; An input unit is configured to input the configuration text information and the device prompt information into a pre-trained device command configuration information generation model to obtain device command configuration information; a verification unit configured to verify the device command configuration information and obtain a verification result; a display unit configured to display a device configuration information interface corresponding to the device command configuration information in response to determining that the verification result satisfies a preset verification condition; a third determining unit, configured to determine whether to generate confirmation information corresponding to the device configuration information interface; The control unit is configured to control the security device to be configured to execute at least one device operation corresponding to the device command configuration information in response to determining to generate confirmation information corresponding to the device configuration information interface.

9. 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 7.

10. A computer-readable medium having a computer program stored thereon, wherein: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Citation Information

Patent Citations

  • Method and device for controlling intelligent equipment

    CN107748500A

  • Speech recognition processing method and electronic equipment

    CN117437912A