Anti-lost alarm method and device, terminal equipment and storage medium

Abstract

The invention relates to the field of intelligent article management, and provides an anti-lost alarm method and device, terminal equipment and a storage medium. Whether the wireless mouse is lost or not is judged by performing time sequence analysis on the time queue data of the position of the wireless mouse and the time queue data of the signal strength of the wireless mouse monitored by the receiving end, and whether an alarm signal needs to be sent or not is decided on the basis. In this way, whether the wireless mouse is in the lost state or not can be judged more accurately, and therefore the situation of misinformation and missed information can be reduced.

Description

Technical Field

[0001] The present application relates to the field of intelligent management of items, and more specifically, to an anti-loss alarm method, device, terminal equipment and storage medium. Background Art

[0002] The specific environment of places such as Internet cafes and e-sports hotels can easily lead to the loss of wireless peripheral products (such as wireless mice). For operators, the loss of wireless mice means additional cost expenditures for purchasing new equipment to maintain services. In order to effectively reduce losses and protect assets, an anti-loss alarm function is generally set for wireless mice. Traditional anti-loss alarm functions may rely on simple threshold settings, such as triggering an alarm when the signal strength is lower than a fixed value. This simple method is prone to false alarms (for example, the user moves the mouse to the other side of the room, but it is not actually lost) or missed alarms (the mouse is indeed lost, but the alarm is not triggered due to environmental factors).

[0003] Therefore, an optimized anti-lost alarm solution is needed. Summary of the invention

[0004] In view of the shortcomings of the prior art, the present application provides an anti-lost alarm method, device, terminal equipment and storage medium.

[0005] According to one aspect of the present application, there is provided an anti-lost alarm method, which includes:

[0006] Obtaining the time queue data of the wireless mouse position and the time queue data of the wireless mouse signal strength monitored by the receiving end;

[0007] Performing time series analysis on the time queue data of the wireless mouse position to obtain a time series change feature vector of the wireless mouse position;

[0008] Performing time series analysis on the time queue data of the wireless mouse signal strength monitored by the receiving end to obtain a time series feature vector of the wireless mouse signal strength;

[0009] Performing kernel feature fusion based on target domain association matching on the wireless mouse position time series change feature vector and the wireless mouse signal strength time series feature vector to obtain a wireless mouse monitoring time series feature vector;

[0010] Based on the information in the wireless mouse monitoring time series feature vector, it is determined whether an alarm signal needs to be issued.

[0011] According to another aspect of the present application, there is provided an anti-lost alarm device, comprising:

[0012] A wireless mouse monitoring related data acquisition module is used to obtain the time queue data of the wireless mouse position and the time queue data of the wireless mouse signal strength monitored by the receiving end;

[0013] A wireless mouse position time series data analysis module, used for performing time series analysis on the time queue data of the wireless mouse position to obtain a wireless mouse position time series change feature vector;

[0014] A wireless mouse signal strength time series data analysis module, used for performing time series analysis on the time queue data of the wireless mouse signal strength monitored by the receiving end to obtain a wireless mouse signal strength time series feature vector;

[0015] A wireless mouse monitoring feature fusion module, used for performing kernel feature fusion based on target domain association matching on the wireless mouse position time series change feature vector and the wireless mouse signal strength time series feature vector to obtain a wireless mouse monitoring time series feature vector;

[0016] The alarm result generating module is used to determine whether it is necessary to issue an alarm signal based on the information in the time series feature vector monitored by the wireless mouse.

[0017] According to another aspect of the present application, a terminal device is provided, comprising a memory and a processor coupled to the memory, wherein the processor is configured to execute the anti-loss alarm method as described above based on instructions stored in the memory.

[0018] According to another aspect of the present application, a computer-readable storage medium is provided, on which computer program instructions are stored, wherein the computer program instructions, when executed by a processor, implement the anti-lost alarm method as described above.

[0019] This application has significant technical effects due to the adoption of the above technical solutions:

[0020] The anti-lost alarm method, device, terminal device and storage medium provided by the present application adopt a data analysis method based on artificial intelligence, and judge whether the wireless mouse is lost by performing a time series analysis on the time queue data of the wireless mouse position and the time queue data of the wireless mouse signal strength monitored by the receiving end, and decide whether to send an alarm signal based on this. In this way, it is possible to more accurately judge whether the wireless mouse is in a lost state, thereby helping to reduce the occurrence of false alarms and missed alarms. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0022] Figure 1 Flow chart of the anti-lost alarm method according to an embodiment of the present application.

[0023] Figure 2 Schematic diagram of data flow of the anti-lost alarm method according to an embodiment of the present application.

[0024] Figure 3 Flow chart of step S2 in the anti-lost alarm method according to an embodiment of the present application.

[0025] Figure 4 is a block diagram of an anti-lost alarm device according to an embodiment of the present application.

[0026] Figure 5 A block diagram of a terminal device according to an embodiment of the present application. DETAILED DESCRIPTION

[0027] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0028] As mentioned in the above background technology, in places such as Internet cafes and e-sports hotels that frequently receive a large number of customers and have high equipment mobility, wireless peripheral products, especially wireless mice, face a higher risk of loss due to their portability and flexibility in use. The specific environment of these places, such as dense personnel flow, complex spatial layout, and various electronic equipment interference, have increased the difficulty of managing wireless mice. For operators, the frequent loss of wireless mice not only means the need to continuously invest in purchasing new equipment to maintain service quality and customer experience, but may also affect business operations and customer satisfaction due to equipment shortages, thus constituting a considerable amount of additional cost expenditure.

[0029] In order to effectively curb this loss and protect asset safety, operators generally tend to equip wireless mice with advanced anti-lost alarm functions. However, traditional anti-lost alarm mechanisms are often based on a relatively single threshold setting. For example, the system will automatically trigger an alarm only when the signal strength between the wireless mouse and the receiver drops below a preset fixed threshold. This relatively extensive alarm strategy exposes two major problems in actual applications: one is frequent false alarms, that is, when customers move the mouse to the other side of the room or temporarily away from the receiver during normal use, due to the natural attenuation of signal strength, the system may mistakenly determine that the device is lost, thereby causing unnecessary panic and interference; the second is the phenomenon of missed reports, that is, in some cases, even if the wireless mouse has been truly lost or illegally carried out of the designated area, due to interference from environmental factors (such as wireless signal shielding, the presence of interference sources, etc.), the alarm function may not respond in time, resulting in asset losses not being effectively prevented. Therefore, an optimized anti-lost alarm solution is expected.

[0030] In recent years, deep learning and neural networks have been widely used in computer vision, natural language processing, text signal processing and other fields. In addition, deep learning and neural networks have also shown a level close to or even beyond that of humans in image classification, object detection, semantic segmentation, text translation and other fields. The development of deep learning and neural networks provides new solutions and solutions for anti-lost alarm.

[0031] Figure 1 Flow chart of the anti-lost alarm method according to an embodiment of the present application. Figure 2 Schematic diagram of data flow of the anti-lost alarm method according to an embodiment of the present application. Figure 1 and Figure 2 As shown, according to the anti-lost alarm method of the embodiment of the present application, the method includes: S1, obtaining the time queue data of the wireless mouse position and the time queue data of the wireless mouse signal strength monitored by the receiving end; S2, performing a timing analysis on the time queue data of the wireless mouse position to obtain a wireless mouse position timing change feature vector; S3, performing a timing analysis on the time queue data of the wireless mouse signal strength monitored by the receiving end to obtain a wireless mouse signal strength timing feature vector; S4, performing kernel feature fusion based on target domain association matching on the wireless mouse position timing change feature vector and the wireless mouse signal strength timing feature vector to obtain a wireless mouse monitoring timing feature vector; S5, judging whether it is necessary to issue an alarm signal based on the information in the wireless mouse monitoring timing feature vector.

[0032] In step S1, the time queue data of the wireless mouse position and the time queue data of the wireless mouse signal strength monitored by the receiving end are obtained. It should be understood that the wireless mouse position data usually includes two-dimensional (such as x and y axis coordinates) or three-dimensional (x, y and z axis coordinates) position information. On a two-dimensional plane, the x and y coordinates can determine the specific position of the mouse on the desktop or the operating plane. If a three-dimensional space is considered, such as three-dimensional positioning in an e-sports hotel room, the z-axis coordinate can represent the height change of the mouse relative to the desktop. Through continuous position data points, the movement trajectory of the mouse can be inferred. This includes linear motion, curvilinear motion, reciprocating motion, etc. For example, by analyzing a series of position data, it can be known whether the mouse moves from the upper left corner of the display along the diagonal to the lower right corner, or performs circular motion in a small area. These motion trajectory information is very important for determining whether the mouse is used normally. The wireless mouse signal strength monitored by the receiving end specifically records the specific value of the wireless mouse signal strength recorded at each time point. Here, the receiving end specifically refers to a device that wirelessly communicates with the wireless mouse. In the environment of an Internet cafe or an e-sports hotel, it is usually a wireless receiver connected to a computer. Through the continuous wireless mouse signal strength value data, the fluctuation pattern of the mouse signal strength over time can be analyzed. In general, the time queue data of the wireless mouse position and the time queue data of the signal strength can verify each other. Under normal circumstances, when the mouse position gradually moves away from the receiving end (such as the user takes the mouse away from the use area), the signal strength should gradually weaken. On the contrary, if the position does not change significantly, but the signal strength suddenly drops sharply, it may be due to abnormal conditions such as obstacles or equipment failure. For example, when the position data shows that the mouse moves to the corner of the room in a short period of time, and the signal strength also drops to a lower level, this increases the possibility of judging that the mouse is lost. That is, by comprehensively analyzing the time queue data of the wireless mouse position and the time queue data of the wireless mouse signal strength monitored by the receiving end, it is possible to more accurately judge whether the wireless mouse is lost.

[0033] In step S2, the time series analysis of the time queue data of the wireless mouse position is performed to obtain a time series change feature vector of the wireless mouse position. Specifically, Figure 3 FIG. 1 is a flow chart of step S2 in the anti-lost alarm method according to an embodiment of the present application. Figure 3 As shown, the step S2 includes: S21, dividing the time queue data of the wireless mouse position to obtain time sub-queue data of multiple wireless mouse positions; S22, passing the time sub-queue data of the multiple wireless mouse positions through a short-term position change information capturer to obtain the wireless mouse position timing change feature vector.

[0034] In step S21, the time queue data of the wireless mouse position is segmented to obtain time sub-queue data of multiple wireless mouse positions. Accordingly, considering that the time queue data of the complete wireless mouse position contains a large number of data points, if all the position data are directly subjected to complex analysis, the amount of calculation and processing time will increase. In order to reduce the complexity of subsequent calculations and improve the efficiency of data processing, the time queue data of the wireless mouse position needs to be segmented. The segmented data subsets are relatively small, and operations such as feature extraction in each subset are faster, and by analyzing each subset, abnormal data points in the position data can be better identified and processed, thereby improving the accuracy of abnormal detection of the mouse position.

[0035] In step S22, the time sub-queue data of the multiple wireless mouse positions are passed through a short-term position change information capturer to obtain the wireless mouse position time series change feature vector. In particular, in the present application, the short-term position change information capturer specifically refers to a recurrent neural network model. It should be understood that the original wireless mouse position time sub-queue data contains a large amount of position information, which is often specific coordinate value data, and the data dimension is high and relatively complicated. In order to better utilize these data for subsequent analysis, such as determining whether the mouse is lost, it is necessary to encode and process them, and abstract the original data into a more representative feature vector. In this way, key information hidden in the data, such as the movement mode, speed change, and position stability of the mouse, can be extracted, so as to more efficiently perform loss judgment. Considering that the recurrent neural network model (RNN) is a neural network specifically used for processing sequence data, its basic structure includes an input layer, a hidden layer, and an output layer. Unlike traditional neural networks, RNN has a loop structure in the hidden layer, so that the output of the neuron can be fed back as the input of the next time step. This loop mechanism enables RNN to remember the historical information in the sequence, which is very effective for processing time series data (such as wireless mouse position time sub-queue data). The information extracted by RNN can be used to determine whether the mouse position remains stable over a certain period of time. In normal use scenarios, the mouse may be in a relatively stable position during certain operation phases (such as when the user temporarily leaves the computer). RNN can reflect this position stability through feature vectors. When the position suddenly becomes unstable and does not conform to normal usage patterns, this may indicate the risk of losing the mouse.

[0036] In step S3, the time queue data of the wireless mouse signal strength monitored by the receiving end is subjected to a time series analysis to obtain a wireless mouse signal strength time series feature vector. Specifically, in an embodiment of the present application, the step S3 includes: passing the time queue data of the wireless mouse signal strength monitored by the receiving end through a signal strength time series encoder to obtain the wireless mouse signal strength time series feature vector. It should be understood that the wireless mouse signal strength will dynamically change with various situations such as the usage scenario, environmental factors, and the relative position with the receiving end, and its change law in the time dimension contains key clues for judging whether the mouse is lost. For example, during normal use, the signal strength generally fluctuates within a relatively stable and reasonable range, and when the mouse begins to move away from the receiving end or encounters abnormal situations such as occlusion, the signal strength will show a specific change trend. Through time series analysis, these hidden information that changes with time can be excavated, so as to more accurately judge whether the mouse is in a lost state, rather than simply judging based on the signal strength at a certain moment. That is, when the mouse is within the normal use range and moves around the receiving end, although the signal strength will fluctuate to a certain extent, the overall change trend and fluctuation characteristics will conform to the normal mode under this environment. Once the mouse is lost, such as being taken out of the room or placed far away where the receiver cannot effectively receive the signal, the signal strength will often continue to drop until it falls below the normal communication threshold, and other obvious abnormal changes will occur. By analyzing these timing characteristics, reasonable judgment criteria can be set. When the change in signal strength deviates from the normal timing pattern to a certain extent, it can be determined that the mouse is at risk of being lost.

[0037] Specifically, the timing analysis method is to input the time queue of the wireless mouse signal strength monitored by the receiving end into the signal strength timing encoder. In particular, in the present application, the signal strength timing encoder refers to a convolutional neural network model including a fully connected layer and a one-dimensional convolutional layer. Those skilled in the art should know that the one-dimensional convolutional layer is good at capturing local features in the signal strength time queue data. By sliding the convolution kernel on the time dimension, it can detect the change pattern of signal strength in different time periods, such as identifying a small time area where the signal strength continuously decreases or a characteristic fragment of periodic fluctuations. These local features are an important basis for subsequent judgment of mouse loss, and can be automatically extracted from the original data through the convolution operation, without the need to manually design complex feature extraction rules, which greatly improves efficiency and accuracy. The fully connected layer can integrate the local features extracted by the one-dimensional convolutional layer, learn the relationship between these local features and how they reflect the change of signal strength as a whole. It can combine multiple local features to generate a more abstract and representative signal strength timing feature vector, describe the change law of signal strength over time from a more macro perspective, and provide comprehensive and comprehensive feature information for the final judgment of whether the mouse is lost.

[0038] In step S4, the wireless mouse position time series change feature vector and the wireless mouse signal strength time series feature vector are fused with kernel features based on target domain association matching to obtain a wireless mouse monitoring time series feature vector. It should be understood that the wireless mouse position time series change feature vector mainly reflects the position change trajectory of the mouse in space, the movement mode, and whether it exceeds the normal use range; the wireless mouse signal strength time series feature vector focuses on the change of the communication signal strength between the mouse and the receiving end over time, such as whether the signal is stably maintained in the normal range, gradually weakening trend or irregular fluctuations. In order to comprehensively consider the changes in the physical position and signal transmission of the mouse, so as to more comprehensively grasp the actual state of the mouse, avoid the one-sided problem when relying on a single feature vector for judgment, and provide a more sufficient basis for accurately judging whether the mouse is lost, it is necessary to fuse the wireless mouse position time series change feature vector and the wireless mouse signal strength time series feature vector in this application.

[0039] In particular, the wireless mouse position time series change feature vector and the wireless mouse signal strength time series feature vector are obtained by analyzing different types of observation data (one is position change and the other is signal strength), and they are distributed in different feature spaces. Each feature space has its own unique structure and characteristics, representing different types of information. When the two feature vectors from different feature spaces are directly fused, it is easy to ignore the complex relationship between the two features. For example, there is a complex interaction between position change and signal strength. For example, when the mouse is moved to a specific area, more interference may be encountered, affecting the signal strength. But this relationship is not always obvious and may be nonlinear. If the complex relationship between the two is not properly handled, the classifier may not be able to accurately understand which situations really need to be alarmed, which may lead to false alarms or missed alarms. Based on this, in the technical solution of the present application, the wireless mouse position time series change feature vector and the wireless mouse signal strength time series feature vector are fused based on the kernel feature of the target domain association matching to obtain the wireless mouse monitoring time series feature vector.

[0040] Specifically, in an embodiment of the present application, the wireless mouse position time series change feature vector and the wireless mouse signal strength time series feature vector are subjected to kernel feature fusion based on target domain association matching to obtain a wireless mouse monitoring time series feature vector, including: mapping the wireless mouse position time series change feature vector and the wireless mouse signal strength time series feature vector to an intrinsic decomposition space to obtain a wireless mouse position time series change intrinsic feature vector and a wireless mouse signal strength time series intrinsic feature vector; mapping the wireless mouse position time series change intrinsic feature vector and the wireless mouse signal strength time series intrinsic feature vector to an intrinsic decomposition space; The invention relates to a method for obtaining an intrinsic feature vector of a wireless mouse position after timing change modulation and an intrinsic feature vector of a wireless mouse signal strength after timing change modulation; constructing a wireless mouse monitoring fused fine-grained semantic information field between the intrinsic feature vector of a wireless mouse position after timing change modulation and the intrinsic feature vector of a wireless mouse signal strength after timing change modulation; and fusing the intrinsic feature vector of a wireless mouse position after timing change modulation and the intrinsic feature vector of a wireless mouse signal strength after timing change modulation based on the wireless mouse monitoring fused fine-grained semantic information field to obtain the wireless mouse monitoring timing feature vector.

[0041] More specifically, in an embodiment of the present application, a wireless mouse monitoring fusion fine-grained semantic information field is constructed between the intrinsic feature vector after the wireless mouse position timing change modulation and the intrinsic feature vector after the wireless mouse signal strength timing modulation, including: multiplying the transposed vectors of the intrinsic feature vector after the wireless mouse position timing change modulation and the intrinsic feature vector after the wireless mouse signal strength timing modulation, and then dividing by the scale of the intrinsic feature vector after the wireless mouse signal strength timing modulation to obtain a wireless mouse monitoring fusion fine-grained interaction matrix; performing convolution encoding on the wireless mouse monitoring fusion fine-grained matrix to obtain the wireless mouse monitoring fusion fine-grained semantic information field.

[0042] More specifically, in an embodiment of the present application, the wireless mouse monitoring fusion fine-grained semantic information field is used to fuse the wireless mouse position timing change modulated intrinsic feature vector and the wireless mouse signal strength timing modulated intrinsic feature vector to obtain the wireless mouse monitoring timing feature vector, including: multiplying the wireless mouse monitoring fusion fine-grained semantic information field by the wireless mouse position timing change modulated intrinsic feature vector to obtain the wireless mouse position timing change feature vector after information field mapping; multiplying the wireless mouse monitoring fusion fine-grained semantic information field by the wireless mouse signal strength timing modulated intrinsic feature vector to obtain the wireless mouse signal strength timing feature vector after information field mapping; weighted fusion of the wireless mouse position timing change feature vector after information field mapping and the wireless mouse signal strength timing feature vector after information field mapping to obtain the wireless mouse monitoring timing feature vector.

[0043] In the embodiment of the present application, specifically, the wireless mouse position time series change feature vector and the wireless mouse signal strength time series feature vector are subjected to kernel feature fusion based on target domain association matching to obtain the wireless mouse monitoring time series feature vector, including: processing the wireless mouse position time series change feature vector and the wireless mouse signal strength time series feature vector according to the following formula to obtain the wireless mouse monitoring time series feature vector; wherein the formula is:

[0044]

[0045] v c =αv kt +βv st

[0046] Wherein, V1 represents the time series change feature vector of the wireless mouse position, V2 represents the time series feature vector of the wireless mouse signal strength, PCA(·) represents the principal component analysis, U1 represents the sequence of the eigendecomposition vector of the time series change of the wireless mouse position, Λ1 represents the diagonal matrix of the time series change of the wireless mouse position, λ 11 and λ 1m They represent the eigenvalues ​​of the first and mth positions of the diagonal matrix of the wireless mouse position timing change, T represents the transpose of the vector, concat{·;·} represents the vector concatenation, and v 11 、v 12 、v 1m They represent the first, second and mth eigenvectors of the sequence of eigendecomposition vectors of the wireless mouse position time series change, V k represents the intrinsic eigenvector of the wireless mouse position time series change, U2 represents the sequence of the wireless mouse signal strength time series intrinsic decomposition vector, Λ2 represents the diagonal matrix of the wireless mouse position time series change, λ 21 and λ 2m They represent the eigenvalues ​​of the first and mth positions of the diagonal matrix of the wireless mouse signal strength time series, v 21 、v 22 、v 2m Respectively represent the first, second and mth eigenvectors of the sequence of the intrinsic decomposition vector of the wireless mouse signal strength time series, V s Represents the time series intrinsic eigenvector of wireless mouse signal strength, v i The ith eigenvalue of the intrinsic eigenvector representing the temporal change of the position of the wireless mouse, v j represents the jth eigenvalue of the time series intrinsic eigenvector of the wireless mouse signal strength, represents the square of the vector norm, exp represents the natural exponential function, V′ k Represents the intrinsic eigenvector after modulation of the wireless mouse position temporal change, V′ sRepresents the intrinsic eigenvector of the wireless mouse signal strength after time-series modulation, represents matrix multiplication, S represents the scale of the vector, M x represents the wireless mouse monitoring fusion fine-grained interaction matrix, Conv 3×3 (M x ) indicates that M x A convolutional encoding operation based on a convolution kernel of 3×3 is performed, Ω represents the fine-grained semantic information field of wireless mouse monitoring fusion, and v kt represents the characteristic vector of the time-series change of the wireless mouse position after information field mapping, v st represents the time series feature vector of wireless mouse signal strength after information field mapping, α and β represent weighted hyperparameters, and v c Represents the wireless mouse monitoring time series feature vector.

[0047] That is, in the technical solution of the present application, the wireless mouse position time series change feature vector and the wireless mouse signal strength time series feature vector are subjected to kernel feature fusion based on target domain association matching. The process first maps the wireless mouse position time series change feature vector and the wireless mouse signal strength time series feature vector to the intrinsic decomposition space to obtain the wireless mouse position time series change intrinsic feature vector and the wireless mouse signal strength time series intrinsic feature vector. Those of ordinary skill in the art should know that the process of mapping to the intrinsic decomposition space is a combination of dimensionality reduction and feature extraction. In a specific example, the intrinsic decomposition space is found by the eigenvalue decomposition technology of principal component analysis (PCA), and the intrinsic decomposition space mapping is performed. The wireless mouse position time series change intrinsic feature vector and the wireless mouse signal strength time series intrinsic feature vector after information field mapping not only represent the projection of the original feature vector in the new coordinate system, but also reflect the main direction of change of the data, which helps to avoid the "dimensionality disaster", that is, the problem that the sample density drops sharply as the number of features increases.

[0048] Next, after mapping the feature vector to the intrinsic decomposition space, it is necessary to perform inter-domain feature calibration on the wireless mouse position timing change intrinsic feature vector and the wireless mouse signal strength timing intrinsic feature vector to adjust the source domain feature vector to better match the data distribution of the target domain. This operation aims to capture and compensate for the systematic deviation between the two domains to reduce the hidden disturbance of the class expression of the local feature distribution of the wireless mouse position timing change intrinsic feature vector and the wireless mouse signal strength timing intrinsic feature vector to the overall class expression. After modulation, the wireless mouse position timing change modulated intrinsic feature vector and the wireless mouse signal strength timing modulated intrinsic feature vector can retain the source domain characteristics while being more in line with the actual needs of the target domain, thereby enhancing the model's understanding and application of the target domain data.

[0049] After completing the scale modulation of the feature vector, a wireless mouse monitoring fused fine-grained semantic information field is constructed between the intrinsic feature vector after the wireless mouse position time series change modulation and the intrinsic feature vector after the wireless mouse signal strength time series modulation. The wireless mouse monitoring fused fine-grained semantic information field is used to describe a more detailed relationship between feature vectors. The introduction of the wireless mouse monitoring fused fine-grained semantic information field enables the model to go beyond simple point-to-point comparison and consider more complex patterns and contextual information, thereby enhancing the model's sensitivity to subtle differences and improving the quality of feature representation. Finally, based on the wireless mouse monitoring fused fine-grained semantic information field, the intrinsic feature vector after the wireless mouse position time series change modulation and the intrinsic feature vector after the wireless mouse signal strength time series modulation are fused to obtain the wireless mouse monitoring time series feature vector.

[0050] In step S5, based on the information in the wireless mouse monitoring timing feature vector, determine whether it is necessary to issue an alarm signal. Specifically, in an embodiment of the present application, step S5 includes: passing the wireless mouse monitoring timing feature vector through an alarm classifier to obtain a classification result, and the classification result is used to indicate whether it is necessary to issue an alarm signal. It should be understood that the wireless mouse monitoring timing feature vector comprehensively reflects the various state changes of the mouse over a period of time. However, this comprehensive feature vector itself is only a form of data representation and cannot directly inform the operator whether the mouse is in a lost state. A mechanism is needed to convert it into an intuitive judgment result that can be used for decision-making, that is, whether to issue an alarm signal. Therefore, in the technical solution of the present application, it is necessary to pass the wireless mouse monitoring timing feature vector through an alarm classifier. The alarm classifier is essentially a model built based on machine learning or deep learning algorithms. Its main function is to receive the input feature vector (here, the wireless mouse monitoring time series feature vector), and then divide the input feature vector into different categories based on the patterns and rules learned internally, specifically divided into two categories: "need to send an alarm signal" and "no need to send an alarm signal", so as to achieve classification decisions on the input data to determine whether the wireless mouse is in a lost state. The classifier can be built based on traditional machine learning algorithms, such as support vector machines (SVMs), which divide different categories of data by finding an optimal hyperplane. In the training phase, a large number of time queue data of wireless mouse positions with labels (corresponding to whether they are lost) and time queue data of wireless mouse signal strength monitored by the receiving end are used for learning to find the hyperplane parameters that can maximize the distinction between the two types of samples that need alarms and those that do not need alarms. In the prediction phase, when a new wireless mouse monitoring time series feature vector is received, it is determined whether it belongs to the category that needs alarms based on which side of the hyperplane it is located on. The classifier can also be built based on a deep learning algorithm, such as a classifier of a neural network structure such as a multi-layer perceptron (MLP), which consists of an input layer, a hidden layer, and an output layer composed of multiple neurons. The input layer receives the time series feature vector of the wireless mouse monitoring, and the hidden layer performs nonlinear transformation and feature extraction on the input information. By passing through and learning the complex patterns in the training data layer by layer, the classification result is finally output in the output layer (for example, a probability value is output, close to 1 means that an alarm is required, and close to 0 means that an alarm is not required). The most direct role of the classification result is to decide whether to trigger an alarm signal. If the classification result indicates that an alarm signal needs to be issued, the corresponding alarm device can be activated immediately, such as popping up a prompt box in the Internet cafe management system to inform the staff that a wireless mouse is lost, so that it is convenient to take timely measures to find the mouse and reduce the loss caused by the loss.

[0051] In summary, the anti-lost alarm method based on the embodiment of the present application is explained, which uses an artificial intelligence-based data analysis method to determine whether the wireless mouse is lost by performing a time series analysis on the time queue data of the wireless mouse position and the time queue data of the wireless mouse signal strength monitored by the receiving end, and based on this, decide whether to send an alarm signal. In this way, it is possible to more accurately determine whether the wireless mouse is in a lost state, thereby helping to reduce the occurrence of false alarms and missed alarms.

[0052] Figure 4 FIG. 1 is a block diagram of an anti-lost alarm device according to an embodiment of the present application. Figure 4 As shown, according to the embodiment of the present application, the anti-lost alarm device 100 includes: a wireless mouse monitoring related data acquisition module 110, which is used to obtain the time queue data of the wireless mouse position and the time queue data of the wireless mouse signal strength monitored by the receiving end; a wireless mouse position timing data analysis module 120, which is used to perform timing analysis on the time queue data of the wireless mouse position to obtain the wireless mouse position timing change feature vector; a wireless mouse signal strength timing data analysis module 130, which is used to perform timing analysis on the time queue data of the wireless mouse signal strength monitored by the receiving end to obtain the wireless mouse signal strength timing feature vector; a wireless mouse monitoring feature fusion module 140, which is used to perform kernel feature fusion based on target domain association matching on the wireless mouse position timing change feature vector and the wireless mouse signal strength timing feature vector to obtain the wireless mouse monitoring timing feature vector; an alarm result generation module 150, which is used to determine whether an alarm signal needs to be issued based on the information in the wireless mouse monitoring timing feature vector.

[0053] Here, those skilled in the art will appreciate that the specific functions and operations of the various units and modules in the anti-lost alarm device 100 have been described in detail above. Figures 1 to 3 The anti-lost alarm method has been described in detail, and therefore, its repeated description will be omitted.

[0054] In summary, the anti-lost alarm device 100 according to the embodiment of the present application is explained, which uses an artificial intelligence-based data analysis method to determine whether the wireless mouse is lost by performing a time series analysis on the time queue data of the wireless mouse position and the time queue data of the wireless mouse signal strength monitored by the receiving end, and based on this, it is determined whether an alarm signal needs to be issued. In this way, it is possible to more accurately determine whether the wireless mouse is in a lost state, thereby helping to reduce the occurrence of false alarms and missed alarms.

[0055] Below, reference Figure 5 To describe the terminal device according to an embodiment of the present application. Figure 5 A block diagram of a terminal device according to an embodiment of the present application.

[0056] like Figure 5 As shown, the terminal device 10 includes one or more processors 11 and a memory 12. The processor 11 may be a central processing unit (CPU) or other forms of processing units with data processing capabilities and / or instruction execution capabilities, and may control other components in the terminal device 10 to perform desired functions. The memory 12 may include one or more computer program products, and the computer program products may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, a random access memory (RAM) and / or a cache memory (cache), etc. The non-volatile memory may include, for example, a read-only memory (ROM), a hard disk, a flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 11 may run the program instructions to implement the anti-lost alarm method of each embodiment of the present application described above and / or other desired functions. Various contents such as time queue data of the wireless mouse position and time queue data of the wireless mouse signal strength monitored by the receiving end may also be stored in the computer-readable storage medium.

[0057] In one example, the terminal device 10 may further include: an input device 13 and an output device 14, and these components are interconnected via a bus system and / or other forms of connection mechanisms (not shown).

[0058] The input device 13 may include, for example, a keyboard, a mouse, etc. The output device 14 may output various information to the outside, including the result of determining whether an alarm signal needs to be issued, etc. The output device 14 may include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto, etc.

[0059] Of course, to simplify, Figure 5 Only some of the components in the terminal device 10 related to the present application are shown, and components such as a bus, an input / output interface, etc. are omitted. In addition, according to specific application conditions, the terminal device 10 may also include any other appropriate components.

[0060] In the embodiment of the present application, a computer readable storage medium is also provided, and the computer readable storage medium can be a tangible device that can hold and store instructions used by an instruction execution device. The computer readable storage medium can be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the above. More specific examples (non-exhaustive list) of computer readable storage media include: portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), static random access memories (SRAM), portable compact disk read-only memories (CD-ROM), digital versatile disks (DVD), memory sticks, floppy disks, mechanical encoding devices, such as punch cards or protruding structures in grooves on which instructions are stored, and any suitable combination of the above. The computer readable storage medium used here is not interpreted as a transient signal itself, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagated by a waveguide or other transmission medium (e.g., a light pulse by an optical fiber cable), or an electrical signal transmitted by a wire.

[0061] The computer program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer program instructions from the network and forwards the computer program instructions for storage in a computer-readable storage medium in each computing / processing device.

[0062] The computer program instructions for performing the operation of the present application can be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. The computer program instructions can be executed completely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer, partially on the remote computer, or completely on the remote computer or server. In the case of a remote computer, the remote computer can 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 can be connected to an external computer (for example, using an Internet service provider to connect through the Internet). In some embodiments, by using the state information of the computer program instructions to personalize an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA) or a programmable logic array (PLA), the electronic circuit can execute the computer program instructions, thereby realizing various aspects of the present application.

[0063] Here, various aspects of the present application are described with reference to the flowchart and / or block diagram of the method, device (system) and terminal device according to the embodiment of the present application. It should be understood that each box of the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer or other programmable data processing device, so as to produce a machine so that these instructions, when executed by the processor of the computer or other programmable data processing device, produce a device for implementing the function / action specified in one or more boxes in the flowchart and / or block diagram. These computer program instructions can also be stored in a computer-readable storage medium, which enables the computer, programmable data processing device and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a product of manufacture, which includes instructions for implementing various aspects of the function / action specified in one or more boxes in the flowchart and / or block diagram. Computer program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operating steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

Claims

1. An anti-lost alarm method, characterized in that: include: Obtaining the time queue data of the wireless mouse position and the time queue data of the wireless mouse signal strength monitored by the receiving end; Performing time series analysis on the time queue data of the wireless mouse position to obtain a time series change feature vector of the wireless mouse position; Performing time series analysis on the time queue data of the wireless mouse signal strength monitored by the receiving end to obtain a time series feature vector of the wireless mouse signal strength; Performing kernel feature fusion based on target domain association matching on the wireless mouse position time series change feature vector and the wireless mouse signal strength time series feature vector to obtain a wireless mouse monitoring time series feature vector; Based on the information in the wireless mouse monitoring time series feature vector, it is determined whether an alarm signal needs to be issued.

2. The anti-lost alarm method according to claim 1, characterized in that: Performing time series analysis on the time queue data of the wireless mouse position to obtain a time series change feature vector of the wireless mouse position includes: Slicing the time queue data of the wireless mouse position to obtain time sub-queue data of multiple wireless mouse positions; The time sub-queue data of the multiple wireless mouse positions are passed through a short-term position change information capturer to obtain the wireless mouse position time series change feature vector.

3. The anti-lost alarm method according to claim 2, characterized in that: The time queue data of the wireless mouse signal strength monitored by the receiving end is subjected to time series analysis to obtain a wireless mouse signal strength time series feature vector, including: passing the time queue data of the wireless mouse signal strength monitored by the receiving end through a signal strength time series encoder to obtain the wireless mouse signal strength time series feature vector.

4. The anti-lost alarm method according to claim 3, characterized in that: The short-term position change information capturer is a recurrent neural network model, and the signal strength timing encoder is a convolutional neural network model including a fully connected layer and a one-dimensional convolutional layer.

5. The anti-lost alarm method according to claim 4, characterized in that: The wireless mouse position time series change feature vector and the wireless mouse signal strength time series feature vector are subjected to kernel feature fusion based on target domain association matching to obtain a wireless mouse monitoring time series feature vector, including: Mapping the wireless mouse position time series change feature vector and the wireless mouse signal strength time series feature vector to an intrinsic decomposition space to obtain a wireless mouse position time series change intrinsic feature vector and a wireless mouse signal strength time series intrinsic feature vector; Performing inter-domain feature calibration on the wireless mouse position timing change intrinsic feature vector and the wireless mouse signal strength timing intrinsic feature vector to obtain the wireless mouse position timing change modulated intrinsic feature vector and the wireless mouse signal strength timing modulated intrinsic feature vector; Constructing a wireless mouse monitoring fusion fine-grained semantic information field between the intrinsic feature vector after the wireless mouse position time series change modulation and the intrinsic feature vector after the wireless mouse signal strength time series modulation; Based on the wireless mouse monitoring fusion fine-grained semantic information field, the wireless mouse position temporal change modulated intrinsic feature vector and the wireless mouse signal strength temporal modulated intrinsic feature vector are fused to obtain the wireless mouse monitoring temporal feature vector.

6. The anti-lost alarm method according to claim 5, characterized in that: Constructing a wireless mouse monitoring fusion fine-grained semantic information field between the intrinsic feature vector after the wireless mouse position time series change modulation and the intrinsic feature vector after the wireless mouse signal strength time series modulation, including: After multiplying the transposed vector of the intrinsic feature vector after the wireless mouse position time series change modulation and the intrinsic feature vector after the wireless mouse signal strength time series modulation, the result is divided by the scale of the intrinsic feature vector after the wireless mouse signal strength time series modulation to obtain a wireless mouse monitoring fusion fine-grained interaction matrix; The wireless mouse monitoring fusion fine-grained matrix is ​​convolutionally encoded to obtain the wireless mouse monitoring fusion fine-grained semantic information field.

7. The anti-lost alarm method according to claim 6, characterized in that: Based on the information in the wireless mouse monitoring time series feature vector, determining whether an alarm signal needs to be issued includes: passing the wireless mouse monitoring time series feature vector through an alarm classifier to obtain a classification result, wherein the classification result is used to indicate whether an alarm signal needs to be issued.

8. An anti-lost alarm device, characterized in that: include: A wireless mouse monitoring related data acquisition module is used to obtain the time queue data of the wireless mouse position and the time queue data of the wireless mouse signal strength monitored by the receiving end; A wireless mouse position time series data analysis module, used for performing time series analysis on the time queue data of the wireless mouse position to obtain a wireless mouse position time series change feature vector; A wireless mouse signal strength time series data analysis module, used for performing time series analysis on the time queue data of the wireless mouse signal strength monitored by the receiving end to obtain a wireless mouse signal strength time series feature vector; A wireless mouse monitoring feature fusion module, used for performing kernel feature fusion based on target domain association matching on the wireless mouse position time series change feature vector and the wireless mouse signal strength time series feature vector to obtain a wireless mouse monitoring time series feature vector; The alarm result generating module is used to determine whether it is necessary to issue an alarm signal based on the information in the time series feature vector monitored by the wireless mouse.

9. A terminal device, comprising a memory and a processor coupled to the memory, characterized in that: The processor is configured to execute the anti-lost alarm method according to any one of claims 1 to 7 based on the instructions stored in the memory.

10. A computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by a processor, the anti-lost alarm method according to any one of claims 1 to 7 is implemented.

Images