A management method and system of a two-dimensional code smart doorplate system

Abstract

The present invention relates to the technical field of smart houseplates, and discloses a management method and system of a two-dimensional code smart houseplate system. The management method of the two-dimensional code smart houseplate system comprises the following steps: collecting historical visitor data and historical householder data; generating visitor features through historical visitor data, generating householder features through historical householder status data, and splicing and combining visitor features and householder features into comprehensive features; inputting the comprehensive features into an optimized processing strategy network, and the optimized processing strategy network outputs a processing strategy, wherein the processing strategy includes actions executed by the smart houseplate system; the smart houseplate system of the present invention can automatically process visitor requests according to the status and preferences of the householder, thereby shortening the waiting time of visitors and improving visitor processing efficiency. By automatically processing requests from low-risk visitors, the system can respond quickly and improve the overall experience of visitors and householders.

Description

Technical Field

[0001] The present invention relates to the field of smart house numbers, and more specifically, to a management method and system of a two-dimensional code smart house number system. Background Art

[0002] A smart community uses a QR code smart doorplate, which collects the basic information of the building, including the building number, unit number, floor distribution map, etc. In order to ensure the safety of the residents of the community, outsiders need to scan the QR code. After the homeowner receives the entry request and agrees, the outsiders can enter the building.

[0003] However, on weekends or after get off work, due to the increase in the number of visitors, the householder needs to frequently process entry requests, which brings inconvenience to the householder and may also cause visitors to wait too long. How to optimize the processing flow of visitor entry requests so that the householder can process these requests in the shortest time, while reducing the waiting time of visitors and maintaining the security of the system is an urgent problem that the current smart doorplate system needs to solve. Summary of the invention

[0004] The present invention provides a management method and system of a two-dimensional code smart house number system to solve the technical problems raised in the above-mentioned background technology.

[0005] The present invention provides a management method for a two-dimensional code smart doorplate system, comprising the following steps:

[0006] Step 101, collecting historical visitor data and historical householder data, the visitor data includes the number of visitors, visitor waiting time, visitor type and visitor history record, the householder data includes the busy status of the householder, whether the householder is at home, the householder's preferences and the householder's available time;

[0007] Step 102, generating visitor features through historical visitor data, generating householder features through historical householder status data, and combining visitor features and householder features into comprehensive features;

[0008] Step 103, input the comprehensive features into the optimization processing strategy network, and the optimization processing strategy network outputs the processing strategy. The processing strategy includes the actions performed by the smart doorplate system, including automatically sending entry requests to the homeowner, prompting the homeowner to process the request, automatically approving requests from low-risk visitors, prompting visitors to try again later, automatically sending emergency notifications to the property, and automatically approving visitors within a specific time period.

[0009] In a preferred embodiment, the method of combining visitor characteristics and household head characteristics into comprehensive characteristics is:

[0010]

[0011]

[0012] in, Represents comprehensive characteristics, represents vector concatenation, Indicates visitor characteristics, Indicates the characteristics of the household head, , , , They represent the first, second, i-th and n-th features in the comprehensive features respectively.

[0013] In a preferred embodiment, the optimization processing strategy network includes an attention layer, a hidden layer and an output layer, wherein the attention layer inputs the comprehensive features of the visitor features and the householder features, and then outputs the weighted features; the weighted features are input to the hidden layer, the hidden layer outputs the hidden features to the output layer, the output layer outputs the Q value of each optional processing strategy, and selects the processing strategy with the largest Q value as the output.

[0014] In a preferred embodiment, the calculation formula of the attention layer is:

[0015]

[0016]

[0017] in, represents the attention score of the i-th feature, Represents comprehensive features The i-th feature in represents the weight matrix of the attention layer, Represents the bias term of the attention layer;

[0018]

[0019] in, represents the weighted feature, represents the attention weight of the i-th feature, Represents comprehensive features The i-th feature in Indicates the length of the comprehensive feature;

[0020] The calculation formula for the hidden layer is:

[0021]

[0022] in, represents hidden features, represents the weighted feature, represents the weight matrix of the hidden layer, represents the bias term of the attention layer, ReLU activation function.

[0023] The calculation formula of the output layer is:

[0024]

[0025] in, Indicates the optional processing strategy for each value vector, represents hidden features, represents the weight matrix of the output layer, Represents the bias term of the output layer;

[0026] The calculation formula for selecting the best processing strategy is:

[0027]

[0028] in, represents the best processing strategy, represents the Q value of processing strategy a, Indicates the parameter to be maximized.

[0029] In a preferred embodiment, the state space includes the number of visitors, visitor waiting time, visitor type and visitor history, the busyness of the householder, whether the householder is at home, the householder's preferences and the householder's available time;

[0030] The action space includes automatically sending entry requests to the homeowner, prompting the homeowner to process the request, automatically approving requests from low-risk visitors, prompting visitors to try again later, automatically sending emergency notifications to the property, and automatically approving visitors within a specific time period.

[0031] In a preferred embodiment, the calculation formula of the reward function is:

[0032]

[0033] in, Represents the comprehensive reward value, Indicates the reward value obtained by reducing the visitor's waiting time. Indicates the reward value that the household owner gets for quickly processing the request. Indicates the reward value obtained by the householder for rejecting the entry request. Indicates the reward value obtained by ensuring safety.

[0034] In a preferred embodiment, the calculation formula for the reward value obtained by reducing the visitor waiting time is:

[0035]

[0036] in, Indicates the reward value obtained by reducing the visitor's waiting time. represents the coefficient of time reduction reward, Indicates the change in visitor waiting time;

[0037] The calculation formula for the reward value obtained by the household owner for quickly processing the request is:

[0038]

[0039] in, Indicates the reward value that the household owner gets for quickly processing the request. Indicates the basic reward coefficient for the householder to quickly process the request, Indicates the actual time it takes for the householder to process the request. represents the expected minimum processing time, Represents the attenuation coefficient.

[0040] In a preferred embodiment, the calculation formula for the reward value obtained by the householder for rejecting the entry request is:

[0041]

[0042] in, Indicates the reward value obtained by the householder for rejecting the entry request. represents the basic penalty coefficient for householder's rejection of entry request, represents the consistency index between the householder's preference and the agent's decision, ,when Completely agree, represents the consistency adjustment coefficient;

[0043] The calculation formula for the reward value obtained by ensuring safety is:

[0044]

[0045] in, Represents the reward value obtained by ensuring safety, represents the basic coefficient of security penalty, Represents the safety index, ,when The highest security. Represents the safety adjustment factor.

[0046] A QR code smart doorplate system, including the following modules:

[0047] Data collection module, used to collect historical visitor data and historical household head data;

[0048] A data preprocessing module is used to preprocess historical visitor data and historical household head data;

[0049] The feature generation module combines the pre-processed historical visitor data and historical household head data to generate comprehensive features;

[0050] The optimization processing strategy network is used to input comprehensive features and output processing strategies.

[0051] A storage medium storing non-temporary computer-readable instructions, which, when executed by a computer, can execute the steps in the management method of a QR code smart doorplate system as described above.

[0052] The beneficial effects of the present invention are as follows: the smart doorplate system of the present invention can automatically process visitor requests according to the status and preferences of the householder, thereby shortening the waiting time of visitors and improving visitor processing efficiency. By automatically processing requests from low-risk visitors, the system can respond quickly and improve the overall experience of visitors and householders. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 It is a flow chart of the management method of the two-dimensional code smart doorplate system of the present invention.

[0054] Figure 2 It is a block diagram of the two-dimensional code smart doorplate system of the present invention.

[0055] In the figure: 100, data acquisition module; 200, data preprocessing module; 300, feature generation module; 400, optimization processing strategy network. DETAILED DESCRIPTION

[0056] The subject matter described herein will now be discussed with reference to example embodiments. It should be understood that the discussion of these embodiments is only to enable those skilled in the art to better understand and implement the subject matter described herein, and the functions and arrangements of the elements discussed may be changed without departing from the scope of protection of the contents of this specification. Each example may omit, replace or add various processes or components as needed. In addition, the features described relative to some examples may also be combined in other examples.

[0057] like Figure 1 As shown, a management method of a two-dimensional code smart doorplate system includes the following steps:

[0058] Step 101, collecting historical visitor data and historical householder data, the visitor data includes the number of visitors, visitor waiting time, visitor type and visitor history record, the householder data includes the busy status of the householder, whether the householder is at home, the householder's preferences and the householder's available time;

[0059] Visitor waiting time is expressed as the average time all visitors waited (in minutes);

[0060] Visitor types include couriers, relatives and friends, and maintenance personnel;

[0061] Visitor history includes the number of previous entries and the number of rejections;

[0062] The busyness status of the household head can include busy and not busy, or can be divided into levels, for example, the busyness status can be divided into 5 levels, from low to high corresponding to increasingly busy;

[0063] Whether the household head is at home includes being at home and not at home, which can be represented by 0 (not at home) or 1 (at home);

[0064] Household owner preferences indicate the household owner's preferences for visitor entry requests, such as allowing automatic approval of certain types of visitors (such as couriers and delivery drivers);

[0065] The householder's available time indicates the time window during which the householder can process entry requests, such as 18:00-22:00;

[0066] How to obtain historical visitor data:

[0067] Visitor Registration System:

[0068] Source: Usually, visitors need to register when entering a building, and this information will be recorded in the visitor registration system.

[0069] Content: visitor's name, contact information, purpose of visit, visit time, etc.

[0070] Access control system records:

[0071] Source: Smart access control systems usually record the timestamps of visitors entering and leaving.

[0072] Content: Time when visitors enter and exit the building, access control usage records, etc.

[0073] User feedback:

[0074] Source: Collect user feedback on guest services through apps or online surveys.

[0075] Content: User satisfaction with visitor services, suggestions, etc.

[0076] Property Management Records:

[0077] Source: Property management companies may have records related to visitors, such as visitor violations, complaint records, etc.

[0078] Content: Visitor violation records, complaint records, etc.

[0079] Methods for obtaining historical household head data:

[0080] Application usage history:

[0081] Source: The application in the QR code smart doorplate system records the behavior of the householder, such as the time and frequency of handling visitor requests.

[0082] Content: The time it takes for the householder to process the request, the householder's preferences, etc.

[0083] Feedback from the householder:

[0084] Source: Collect feedback from householders on visitor services through apps or online surveys.

[0085] Content: Household owner’s satisfaction with visitor services, suggestions, etc.

[0086] Property Management Records:

[0087] Source: The property management company may have records related to the householder, such as the householder's preferences, special requests, etc.

[0088] Content: householder's preferences, special requirements, etc.

[0089] Household activity log:

[0090] Source: Smart devices (such as smart door locks) are used to record the activity time of the householder, such as the time of leaving home and returning home.

[0091] Content: the householder’s activity time, the householder’s status at home, etc.

[0092] The acquired historical visitor data and historical householder data are preprocessed by methods such as removing invalid data and filling missing values; the data are classified and labeled, such as marking the type of visitor, the status of the householder, etc.; the data are standardized to make the data comparable.

[0093] Step 102, generating visitor features through historical visitor data, generating householder features through historical householder status data, and combining visitor features and householder features into comprehensive features;

[0094]

[0095]

[0096] in, Represents comprehensive characteristics, represents vector concatenation, Indicates visitor characteristics, Indicates the characteristics of the household head, , , , Respectively represent the 1st, 2nd, i-th and n-th features in the comprehensive features;

[0097] Step 103, input the comprehensive features into the optimization processing strategy network, and the optimization processing strategy network outputs the processing strategy, which includes the actions performed by the smart doorplate system, including automatically sending an entry request to the householder, prompting the householder to process the request, automatically approving the request of a low-risk visitor, prompting the visitor to try again later, automatically sending an emergency notification to the property, and automatically approving visitors within a specific time period;

[0098] The optimization processing strategy network includes an attention layer, a hidden layer, and an output layer. The attention layer inputs the comprehensive features of the visitor features and the householder features, and then outputs the weighted features. The weighted features are input to the hidden layer, and the hidden layer outputs the hidden features to the output layer. The output layer outputs the Q value of each optional processing strategy, and selects the processing strategy with the largest Q value as the output.

[0099] The calculation formula of the attention layer is:

[0100]

[0101]

[0102] in, represents the attention score of the i-th feature, Represents comprehensive features The i-th feature in represents the weight matrix of the attention layer, Represents the bias term of the attention layer;

[0103]

[0104] in, represents the weighted feature, represents the attention weight of the i-th feature, Represents comprehensive features The i-th feature in Indicates the length of the comprehensive feature;

[0105] The calculation formula for the hidden layer is:

[0106]

[0107] in, represents hidden features, represents the weighted feature, represents the weight matrix of the hidden layer, represents the bias term of the attention layer, ReLU activation function.

[0108] The calculation formula of the output layer is:

[0109]

[0110] in, Indicates the optional processing strategy for each value vector, represents hidden features, represents the weight matrix of the output layer, Represents the bias term of the output layer;

[0111] The calculation formula for selecting the best processing strategy is:

[0112]

[0113] in, represents the best processing strategy, represents the Q value of processing strategy a, Indicates the parameter to be maximized;

[0114] It should be noted that before the smart door number system executes each action, it needs to update the visitor data and householder data to regenerate the processing strategy;

[0115] The training of the optimization processing policy network includes the following steps:

[0116] Step 1: Initialize all weights and bias items of the optimization processing strategy network and set the learning rate and training rounds ;

[0117] Step 2: Calculate the target Q value. For each training sample, calculate the target Q value based on the actual result and reward. , if action a leads to the final state ,but:

[0118]

[0119] in, Indicates the immediate reward obtained. represents the discount factor, Indicates in status The maximum Q value of all possible actions;

[0120] Step 3: For each training sample, calculate the loss function;

[0121] The loss function is calculated as:

[0122]

[0123] in, represents the predicted Q value of the optimization processing strategy network, represents the target Q value calculated based on the actual results and rewards, represents the mean square error loss;

[0124] Step 4: Use the gradient descent method to update the weights and bias terms to minimize the loss function. The update calculation formula is as follows:

[0125]

[0126] in, represents the old weights and biases, represents the updated weights and bias terms, represents the learning rate, Represents the loss function with respect to the parameter The gradient of

[0127] Step 5: Repeat steps 2 to 4 until the scheduled training rounds are completed. .

[0128] The reward function is calculated as:

[0129]

[0130] in, Represents the comprehensive reward value, Indicates the reward value obtained by reducing the visitor's waiting time. Indicates the reward value that the household owner gets for quickly processing the request. Indicates the reward value obtained by the householder for rejecting the entry request. Indicates the reward value obtained by ensuring safety;

[0131] The calculation formula for the bonus value obtained by reducing the visitor's waiting time is:

[0132]

[0133] in, Indicates the reward value obtained by reducing the visitor's waiting time. represents the coefficient of time reduction reward, Indicates the change in visitor waiting time;

[0134] The calculation formula for the reward value obtained by the household owner for quickly processing the request is:

[0135]

[0136] in, Indicates the reward value that the household owner gets for quickly processing the request. Indicates the basic reward coefficient for the householder to quickly process the request, Indicates the actual time it takes for the householder to process the request. represents the expected minimum processing time, represents the attenuation coefficient;

[0137] The calculation formula for the reward value obtained by the household owner for rejecting the entry request is:

[0138]

[0139] in, Indicates the reward value obtained by the householder for rejecting the entry request. represents the basic penalty coefficient for householder's rejection of entry request, represents the consistency index between the householder's preference and the agent's decision, ,when Completely agree, represents the consistency adjustment coefficient;

[0140] The calculation formula for the reward value obtained by ensuring safety is:

[0141]

[0142] in, Represents the reward value obtained by ensuring safety, represents the basic coefficient of security penalty, Represents the safety index, ,when The highest security. represents the safety adjustment factor;

[0143] The purpose of this design is to incentivize the agent to take actions that can reduce visitor waiting time, reduce the burden on homeowners and ensure system security.

[0144] The status space includes the number of visitors, visitor waiting time, visitor type and visitor history, the busyness of the householder, whether the householder is at home, the householder's preferences, and the householder's available time;

[0145] The action space includes :Automatically send access request to the householder, :Prompt the householder to process the request, : Automatically approve requests from low-risk visitors, : Prompt the visitor to try again later, : Automatically send emergency notifications to property and : Automatically approve visitors during a specific time period;

[0146] An action is defined as the next operation performed by the smart doorplate system. For example, when a visitor scans the QR code, the intelligent agent automatically sends an entry request to the homeowner; the intelligent agent prompts the homeowner to process the entry request through APP, SMS, etc.; for visitors who have already been recorded, the intelligent agent can directly approve their entry request without the need for confirmation from the homeowner; when the homeowner cannot process the request immediately, the intelligent agent can prompt the visitor to try again later; if the visitor waits too long or the homeowner does not respond for a long time, the intelligent agent can automatically send an emergency notification to the property, and the property will intervene to handle the matter; the intelligent agent can automatically approve visitor entry according to a pre-set time period, such as automatically approving visitor entry within a specific time range during the day without the need for confirmation from the homeowner.

[0147] In one embodiment of the present invention, some specific strategy examples are given:

[0148] When the householder is at home and not busy, the agent (smart house number system) will choose the action or , that is, automatically sending an entry request to the householder or prompting the householder to process the request; the reason is: when the householder is at home and not busy, the entry request can be processed faster, so the smart door number system tends to automatically send the request or prompt the householder to process it, so as to reduce the waiting time of visitors;

[0149] When the owner is home but busy, the agent may choose actions or , that is, prompting the homeowner to process the request or prompting the visitor to try again later, on the grounds that although the homeowner is at home, he may not be able to process the request immediately due to being busy. In this case, the intelligent body will choose to prompt the homeowner to process the request or prompt the visitor to try again later to ensure that the homeowner notices the existence of the request and avoid disturbing the homeowner;

[0150] When the owner is not at home, the agent may choose the action or , that is, automatically approving requests from low-risk visitors or automatically approving visitors within a specific time period. The reason is that if the householder is not at home, the agent needs to take measures to reduce the waiting time of visitors. For known low-risk visitors (such as couriers, frequent relatives and friends, etc.), the agent can directly approve their entry requests; for visitors within a specific time period, the agent can automatically approve the visitor's entry according to the preset time period;

[0151] When the number of visitors is large, the agent may choose action or The reason is that when there are a large number of visitors, the agent will give priority to reducing the waiting time of visitors. For known visitors, their entry requests can be automatically approved; for new visitors, the agent will automatically send an entry request to the householder;

[0152] When the visitor waits longer, the agent may choose to take action or , which means prompting the householder to process the request or automatically sending an emergency notification to the property management. The reason is that when the visitor waits for a long time, the intelligent body will try to speed up the processing process to reduce the visitor's waiting time. If the householder does not respond for a long time, the intelligent body will automatically send an emergency notification to the property management, and the property management will intervene to handle it;

[0153] Through the above scheme, the smart door number system of the present invention can select the optimal action according to the state space and the action space to reduce the waiting time of visitors, reduce the burden of the householder, and ensure the security of the system.

[0154] like Figure 2 As shown, a QR code smart doorplate system includes the following modules:

[0155] The data collection module 100 is used to collect historical visitor data and historical householder data;

[0156] A data preprocessing module 200 is used to preprocess historical visitor data and historical household head data;

[0157] Feature generation module 300, which combines the pre-processed historical visitor data and historical household head data to generate comprehensive features

[0158] The optimization processing strategy network 400 is used to input comprehensive features and output processing strategies.

[0159] A storage medium storing non-temporary computer-readable instructions, which, when executed by a computer, can execute the steps in the management method of a QR code smart doorplate system as described above.

[0160] The above describes an embodiment of the present embodiment, but the present embodiment is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present embodiment, ordinary technicians in this field can also make many forms, all of which are within the protection of the present embodiment.

Claims

1. A management method for a QR code smart doorplate system, characterized in that: The following steps are involved: Step 101, collecting historical visitor data and historical householder data, the visitor data includes the number of visitors, visitor waiting time, visitor type and visitor history record, the householder data includes the busy status of the householder, whether the householder is at home, the householder's preferences and the householder's available time; Step 102, generating visitor features through historical visitor data, generating householder features through historical householder status data, and combining visitor features and householder features into comprehensive features; Step 103, input the comprehensive features into the optimization processing strategy network, and the optimization processing strategy network outputs the processing strategy, which includes the actions performed by the smart doorplate system, including automatically sending an entry request to the householder, prompting the householder to process the request, automatically approving the request of a low-risk visitor, prompting the visitor to try again later, automatically sending an emergency notification to the property, and automatically approving visitors within a specific time period; The optimization processing strategy network includes an attention layer, a hidden layer, and an output layer. The attention layer inputs the comprehensive features of the visitor features and the householder features, and then outputs the weighted features. The weighted features are input to the hidden layer, and the hidden layer outputs the hidden features to the output layer. The output layer outputs the Q value of each optional processing strategy, and selects the processing strategy with the largest Q value as the output. The method of combining visitor characteristics and household head characteristics into comprehensive characteristics is: ； ； in, Represents comprehensive characteristics, represents vector concatenation, Indicates visitor characteristics, Indicates the characteristics of the household head, , , , Respectively represent the 1st, 2nd, i-th and n-th features in the comprehensive features; The calculation formula of the attention layer is: ； ； in, represents the attention score of the i-th feature, Represents comprehensive features The i-th feature in represents the weight matrix of the attention layer, Represents the bias term of the attention layer; ； in, represents the weighted feature, represents the attention weight of the i-th feature, Represents comprehensive features The i-th feature in Indicates the length of the comprehensive feature; The calculation formula for the hidden layer is: ； in, represents hidden features, represents the weighted feature, represents the weight matrix of the hidden layer, represents the bias term of the attention layer, ReLU activation function. The calculation formula of the output layer is: ； in, Indicates the optional processing strategy for each value vector, represents hidden features, represents the weight matrix of the output layer, Represents the bias term of the output layer; The calculation formula for selecting the best processing strategy is: ； in, represents the best processing strategy, represents the Q value of processing strategy a, Indicates the parameter to be maximized; The training of the optimization processing policy network includes the following steps: Step 1: Initialize all weights and bias items of the optimization processing strategy network and set the learning rate and training rounds ; Step 2: Calculate the target Q value. For each training sample, calculate the target Q value based on the actual result and reward. , if action a leads to the final state ,but: ； in, Indicates the immediate reward obtained. represents the discount factor, Indicates in status The maximum Q value of all possible actions; Step 3: For each training sample, calculate the loss function; The loss function is calculated as: ； in, represents the predicted Q value of the optimization processing strategy network, represents the target Q value calculated based on the actual results and rewards, represents the mean square error loss; Step 4: Use the gradient descent method to update the weights and bias terms to minimize the loss function. The update calculation formula is as follows: ； in, represents the old weights and biases, represents the updated weights and bias terms, represents the learning rate, Represents the loss function with respect to the parameter The gradient of Step 5: Repeat steps 2 to 4 until the scheduled training rounds are completed. ; The reward function is calculated as: ； in, Represents the comprehensive reward value, Indicates the reward value obtained by reducing the visitor's waiting time. Indicates the reward value that the household owner gets for quickly processing the request. Indicates the reward value obtained by the householder for rejecting the entry request. Indicates the reward value obtained by ensuring safety; The calculation formula for the bonus value obtained by reducing the visitor's waiting time is: ； in, Indicates the reward value obtained by reducing the visitor's waiting time. represents the coefficient of time reduction reward, Indicates the change in visitor waiting time; The calculation formula for the reward value obtained by the household owner for quickly processing the request is: ； in, Indicates the reward value that the household owner gets for quickly processing the request. Indicates the basic reward coefficient for the householder to quickly process the request, Indicates the actual time it takes for the householder to process the request. represents the expected minimum processing time, represents the attenuation coefficient; The calculation formula for the reward value obtained by the household owner for rejecting the entry request is: ； in, Indicates the reward value obtained by the householder for rejecting the entry request. represents the basic penalty coefficient for householder's rejection of entry request, represents the consistency index between the householder's preference and the agent's decision, ,when Completely agree, represents the consistency adjustment coefficient; The calculation formula for the reward value obtained by ensuring safety is: ； in, Represents the reward value obtained by ensuring safety, represents the basic coefficient of security penalty, Represents the safety index, ,when The highest security. Represents the safety adjustment factor.

2. A two-dimensional code smart house number system for executing the management method of a two-dimensional code smart house number system as claimed in claim 1, characterized in that: Includes the following modules: Data collection module, used to collect historical visitor data and historical household head data; A data preprocessing module is used to preprocess historical visitor data and historical household head data; The feature generation module combines the pre-processed historical visitor data and historical household head data to generate comprehensive features; The optimization processing strategy network is used to input comprehensive features and output processing strategies.

3. A storage medium storing non-transitory computer-readable instructions, characterized in that: When the non-temporary computer-readable instructions are executed by a computer, the steps in the management method of a QR code smart doorplate system as described in claim 1 can be executed.

Images