Object recognition method, electronic device, and storage medium

Abstract

This application discloses an object recognition method, an electronic device, and a storage medium. The method includes dividing object click data within a preset time window based on a preset time interval to generate multiple click data sequences; performing data statistics on the click data sequences to obtain multi-dimensional features corresponding to each click data sequence; performing cluster analysis on the multi-dimensional features corresponding to each click data sequence to obtain candidate object sets with similar behavioral patterns for each click data sequence; and determining the target object set based on the intersection of the candidate object sets. This not only improves object recognition efficiency but also considers the click timing during object recognition, thereby helping to avoid missed detections and improving the accuracy of object recognition.

Description

Technical Field

[0001] This application relates to the field of object recognition technology, specifically to an object recognition method, electronic device, and storage medium. Background Technology

[0002] Currently, the aim is to identify potential collaborative malicious groups by analyzing the spatial distribution similarity of user click behavior.

[0003] However, current solutions typically compare the spatial distribution features of click locations between pairs of users, which requires a large amount of computation, has low recognition efficiency, and relies on a single data dimension for object recognition, making it easy to miss certain cases. Summary of the Invention

[0004] This application provides an object recognition method, electronic device, and storage medium, which not only improves object recognition efficiency but also considers click timing during object recognition, thereby helping to avoid missed detections and improve the accuracy of object recognition.

[0005] On one hand, embodiments of this application provide an object recognition method, the method comprising: Based on a preset time interval, the object click data within a preset time window is divided to generate multiple click data sequences; Data statistics are performed on the click data sequence to obtain the multi-dimensional features corresponding to the click data sequence; Cluster analysis is performed on the multi-dimensional features corresponding to each click data sequence to obtain a set of candidate objects with similar behavioral patterns for each click data sequence. The target object set is determined based on the intersection of the various candidate object sets.

[0006] On the other hand, embodiments of this application provide an electronic device, which includes a processor and a memory. The memory stores a computer program, and the processor executes the object recognition method as described in any of the above embodiments by calling the computer program stored in the memory.

[0007] On the other hand, embodiments of this application provide a computer-readable storage medium storing a computer program adapted for loading by a processor to execute the object recognition method as described in any of the above embodiments.

[0008] The object recognition method, electronic device, and storage medium provided in this application divide object click data over a period of time (i.e., a preset time window) into multiple click data sequences within time periods with short-term spatiotemporal correlation. Click data from each time period is used to generate a click data sequence, taking into account the click timing, which helps improve the accuracy of object recognition.

[0009] Then, data statistics are performed on each click data sequence to obtain the multi-dimensional features corresponding to each click data sequence. Subsequently, cluster analysis is performed in parallel on the multi-dimensional features of each click data sequence to identify the set of candidate objects with similar behavioral patterns in each click data sequence.

[0010] Finally, the target object set can be obtained based on the intersection of the candidate object sets corresponding to each click data sequence. This not only helps to improve the recognition efficiency, but also further improves the accuracy of object recognition by utilizing the intersection of candidate objects from different click data sequences with temporal correlation. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 This is a schematic diagram of an object recognition system provided in an embodiment of this application.

[0013] Figure 2 This is a first flowchart illustrating the object recognition method provided in an embodiment of this application.

[0014] Figure 3 This is a second flowchart illustrating the object recognition method provided in an embodiment of this application.

[0015] Figure 4 This is a schematic diagram of a scenario for the object recognition method provided in the embodiments of this application.

[0016] Figure 5 This is a schematic diagram of the structure of the object recognition device provided in the embodiments of this application.

[0017] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0018] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0019] This application provides an object identification method, apparatus, storage medium, device, and program product. Specifically, the object identification method of this application can be executed by an electronic device, which can be a terminal or server, etc.

[0020] The terminal can be a smartphone, tablet, laptop, smart TV, wearable smart device, smart vehicle terminal, etc. The terminal can also include a client, which can be a game client, browser client, instant messaging client, or mini-program, etc.

[0021] A server can be a standalone physical server, a server cluster or distributed system consisting of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms.

[0022] It should be noted that in the embodiments of this application, the executing entity of the object identification method can be a terminal device or a server, and the embodiments of this application do not limit the type of executing entity.

[0023] It is understood that in the specific implementation of this application, user object data, context data and other related data are involved. When the embodiments of this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0024] For example, in conjunction with the above description, Figure 1 This application illustrates an object recognition system 1000 for implementing an object recognition method, as provided in an embodiment of this application. The object recognition system 1000 may include at least one terminal 1001, at least one server 1002, at least one database 1003, and a network. The terminal 1001 can be connected to different servers via the network. The terminal can be any device with computing hardware capable of supporting and executing software application tools corresponding to the game.

[0025] Furthermore, when the object recognition system 1000 includes multiple terminals, multiple servers, and multiple networks, different terminals can connect to each other through different networks and different servers. The network can be a wireless network or a wired network; for example, wireless networks include wireless local area networks (WLAN), local area networks (LAN), cellular networks, 2G networks, 3G networks, 4G networks, 5G networks, etc. Additionally, different terminals can also connect to other terminals or to servers using their own Bluetooth networks or hotspot networks. Furthermore, the system 100 can include multiple databases coupled to different servers, and can continuously store game-related information in the databases while different users are playing multi-user games online.

[0026] It should be noted that, Figure 1 The schematic diagram of the object recognition system shown is merely an example. The object recognition system 1000 described in this application embodiment is intended to more clearly illustrate the technical solutions of this application embodiment and does not constitute a limitation on the technical solutions provided in this application embodiment. As those skilled in the art will know, with the evolution of object recognition systems and the emergence of new business scenarios, the technical solutions provided in this application embodiment are also applicable to similar technical problems.

[0027] The technical solution of this application will be described in detail below through specific embodiments. It should be noted that the following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments.

[0028] Please see Figure 2 It should be noted that the steps shown may be executed in a logical order different from that shown in the flowchart of this method. The object identification method of this application may include the following steps: Step 011: Based on a preset time interval, divide the object click data within the preset time window to generate multiple click data sequences.

[0029] The preset time interval is an empirical value and can be set based on actual needs. For example, the preset time interval can be 1 minute, 2 minutes, etc.

[0030] The preset time window is also an empirical value and can be set according to actual needs. The preset time window represents the cycle for object recognition; an object detection is performed once per preset time window. In other words, the smaller the preset time window, the higher the frequency of object recognition. For example, preset time windows could be 1 hour or 2 hours.

[0031] Among them, object click data refers to data related to objects (such as users) clicking or touching on the screen space of electronic devices.

[0032] For example, object click data may include at least one of the following: click coordinates, click timestamp, object identifier, device identifier, IP address, and screen resolution.

[0033] Among them, the click coordinates are the precise numerical values ​​of the operation point in the interface coordinate system when a user performs a click / touch operation on the visual interface of an electronic device (mobile phone, computer, tablet, etc.), and are the core parameters describing the user's click location. The click timestamp is an absolute time identifier generated by the system at the instant the user completes the click / touch operation, used to accurately record the time point of the operation, and is the core benchmark for behavioral timing analysis. The object identifier is the user's unique identifier (ID), and is the core basis for distinguishing different objects. The device identifier is an identifier string used to uniquely identify the physical device used by the user's operation, and is the core basis for distinguishing different devices.

[0034] After obtaining the object click data of each object collected within the preset time window, the object click data of each object collected within the preset time window can be divided according to the preset time interval to obtain a click data sequence with short-term spatiotemporal correlation. Each click data sequence corresponds to a preset time interval.

[0035] Please combine Figure 3 In one optional embodiment, step 011 includes: Step 0111: Divide the preset time window into multiple sub-time windows based on a preset time interval; Step 0112: Based on the object click data whose click timestamps are located within each sub-time window, generate each click data sequence, where each click data sequence corresponds to a sub-time window.

[0036] When dividing data according to a preset time interval, the preset time window can be divided into multiple sub-time windows based on the preset time interval. Then, based on the click data of objects whose click timestamps are located in each sub-time window, the click data sequence corresponding to each sub-time window can be generated.

[0037] In this way, the user's long-term (corresponding to the preset time window) click behavior data is processed into time-series slices of fixed duration (corresponding to the preset time interval) to generate a sequence of behavior segments (corresponding to the click data sequence) with short-term spatiotemporal correlation, thereby capturing the temporal pattern of the click behavior of each object, which is beneficial to improving the accuracy of object recognition.

[0038] Step 012: Perform data statistics on the click data sequence to obtain the multi-dimensional features corresponding to the click data sequence.

[0039] Among them, multi-dimensional features include features of multiple different dimensions to fully extract useful information from the click data sequence.

[0040] In one alternative embodiment, the multi-dimensional features include basic statistical features, spatial distribution features, click timing features, and address clustering features.

[0041] The basic statistical features include mathematical statistical features related to click operations, such as the total number of clicks and click frequency. Spatial distribution features include the distribution of click operations at different locations on the screen, such as the distribution of click coordinates. Click temporal features include the temporal characteristics of click operations, such as the time interval between adjacent click timestamps and changes in click speed. Address clustering features include the number of objects associated with each IP address and device, such as the number of objects clustered under the same IP address and the number of objects using the same device.

[0042] In this way, by using multi-dimensional features, we can analyze whether user click behavior is abnormal from different dimensions, thereby improving the accuracy of object recognition.

[0043] In one optional embodiment, the basic statistical features include at least one of the following: total number of clicks, click frequency, percentage of click coordinates located in the target area, and number of repeated clicks; The total number of clicks is the total number of clicks on objects in the click data sequence; the click frequency is the ratio of the total number of clicks to the preset time interval.

[0044] The proportion of click coordinates located in the target area (such as the area where interactive elements are located in the visualization interface) can be determined based on the ratio of the number of object click data whose click coordinates are located in the target area to the total number of object click data in the click data sequence. It's understandable that in many application interfaces, core interactive elements are usually concentrated in a certain area of ​​the screen or a visual focal point; this area is the target area. Simulated clicks driven by AI or scripts tend to directly and efficiently locate and click these known target areas, resulting in click events being highly concentrated in the target area of ​​the screen. Real user actions, however, are exploratory, random, and error-tolerant. For example, users might swipe the screen, touch an edge to return, or click on a blank area to return. Therefore, the proportion of real user clicks appearing in the target area is significantly lower than that of simulated clicks.

[0045] The number of repeated clicks is determined by counting the number of clicks on objects corresponding to the same click coordinates.

[0046] It is understandable that when normal objects click on a visual interface, the number of clicks, frequency, and click locations are relatively random. However, abnormal objects are objects with specific purposes, such as using AI or script-driven simulated clicks to perform repetitive operations like order brushing. This makes the total number of clicks, frequency, and click locations within the same time period of abnormal objects more regular and highly similar.

[0047] Therefore, by using total number of clicks, click frequency, percentage of click coordinates located in the target area, and number of repeated clicks, object identification can be accurately performed from the perspective of mathematical statistical features.

[0048] In one optional embodiment, the spatial distribution characteristics include at least one of the following: a first statistical value of the click coordinates at a first coordinate on a first coordinate axis, a second statistical value of the click coordinates at a second coordinate on a second coordinate on a second coordinate axis, click coverage area, and click concentration. The first statistical value characterizes the distribution concentration of each click coordinate along the first coordinate axis. The second statistical value characterizes the distribution concentration of each click coordinate along the second coordinate axis, where the first coordinate axis is the X-axis and the second axis is the Y-axis perpendicular to the X-axis. The click coverage area is determined based on the largest first and second coordinate values ​​among all click coordinates. The click concentration is determined based on the average distance from each click coordinate to the center coordinate, where the center coordinate is the coordinate corresponding to the center position of each click coordinate.

[0049] It's understandable that when a normal object is clicked on a visual interface, the spatial distribution of the click locations is relatively random. However, the spatial distribution of click locations for abnormal objects is more regular and exhibits a high degree of similarity.

[0050] Therefore, by using spatial distribution features, object identification can be accurately performed based on the spatial distribution of click locations.

[0051] In one optional embodiment, the click timing features include at least one of the following: a third statistical value corresponding to the click interval, a fourth statistical value corresponding to the click speed, the maximum duration of no click operation, and the number of click interval abrupt changes.

[0052] The third statistical value is determined based on the statistical value (such as mean and / or variance) of the click interval between two adjacent click operations. For example, if the same object is in a click data sequence, the statistical value of the click interval between two adjacent click operations is used to characterize whether the object clicks regularly at equal intervals or irregularly.

[0053] The fourth statistical value is determined based on the statistical value (such as the standard deviation) of the number of clicks within each first preset duration within a preset time interval. It is also used to characterize whether the number of clicks on an object within each first preset duration is consistent in a regular manner. For example, if the preset time interval is 1 minute and the first preset duration is 1 second, then the fourth statistical value for each object is obtained by counting the number of clicks on each object in each second in the click data sequence.

[0054] It is understandable that the click sequence of abnormal objects is generally quite regular. By analyzing the click sequence characteristics of each object, we can more accurately determine a set of abnormal objects that are similar and have regular click sequences from the perspective of click sequence.

[0055] In one optional embodiment, the address clustering features include IP address (Internet Protocol Address) clustering features and device fingerprint clustering features; Among them, the IP address clustering characteristics include at least one of the following: the number of objects associated with the same IP address, the binding duration of the IP address and the object, and the IP address value.

[0056] It's understandable that abnormal objects often use proxy IP pools in batches, and these IP addresses are often numerically consecutive or belong to the same C-class segment (i.e., the first three segments are the same). Therefore, by analyzing the number of objects associated with the same IP address, the duration of the binding between the IP address and the object, and the numerical value of the IP address, objects can be accurately identified from the IP dimension.

[0057] Among them, the device fingerprint clustering feature includes the number of objects associated with the same device fingerprint.

[0058] It is understandable that abnormal objects are identified by sharing a common device. Therefore, by counting the number of objects associated with the same device fingerprint, the device used by the abnormal object can be accurately identified, thus enabling accurate object identification from a device perspective.

[0059] Step 013: Perform cluster analysis on the multi-dimensional features corresponding to each click data sequence to obtain a set of candidate objects with similar behavioral patterns for each click data sequence.

[0060] Cluster analysis is the process of identifying objects with similar characteristics and forming clusters.

[0061] It is understandable that the click behavior patterns of different normal objects vary considerably, while abnormal objects generally act in groups, and their click behavior patterns are regular and highly similar. Therefore, by performing cluster analysis on the multi-dimensional features corresponding to each click data sequence, we can accurately identify the set of candidate objects with similar behavior patterns corresponding to each click data sequence (such as a set of objects that may contain abnormal objects).

[0062] In an optional embodiment, step 013 includes: Step 0131: Perform feature processing on the multi-dimensional features of each object to generate multi-dimensional feature vectors corresponding to each object. Step 0132: Based on the preset hierarchical density clustering algorithm, perform parallel clustering analysis on the multi-dimensional feature vectors of each click data sequence to obtain cluster feature clusters; Step 0133: Generate a set of candidate objects based on the object identifiers corresponding to each multi-dimensional feature vector in the cluster feature cluster.

[0063] Hierarchical density clustering is a type of clustering method that combines the hierarchical partitioning characteristics of hierarchical clustering with the core idea of ​​density clustering (based on density connectivity and noise resistance). It overcomes the shortcomings of traditional hierarchical clustering in being sensitive to noise and traditional density clustering (such as DBSCAN) in being unable to generate hierarchical structures. A typical example is the HDBSCAN (Hierarchical DBSCAN) algorithm.

[0064] It is understandable that, in order to facilitate data processing, after obtaining the multi-dimensional features of each object, feature processing can be performed on the multi-dimensional features to generate multi-dimensional feature vectors corresponding to the multi-dimensional features, which represent the features of each dimension in vector form.

[0065] Generally, the click behavior patterns of normal objects are discrete, and the corresponding multi-dimensional feature vectors are usually relatively isolated, making it difficult to form clusters. In contrast, the click behavior patterns of abnormal objects are highly similar, thus making clustering easier. Therefore, the number of feature vectors in each cluster is used to determine whether a cluster is a high-density cluster. If the proportion of feature vectors in a cluster to the total number of feature vectors in the corresponding click data sequence is greater than a preset proportion, the cluster is determined to be a high-density cluster. This high-density cluster is then identified as a cluster feature cluster, and isolated multi-dimensional feature vectors and low-density clusters are filtered out.

[0066] Therefore, by using hierarchical density clustering algorithms to perform parallel clustering analysis on the multi-dimensional feature vectors of each click data sequence, not only can cluster feature clusters be obtained, which are highly likely to be clusters formed by abnormal objects, but also the efficiency of object recognition can be improved because the clustering analysis of each click data sequence is executed in parallel.

[0067] Finally, based on the object identifiers corresponding to each multi-dimensional feature vector in the cluster feature cluster, a candidate object set is generated, thereby obtaining a candidate object set that may contain abnormal objects.

[0068] Step 014: Determine the target object set based on the intersection of the candidate object sets.

[0069] It's understandable that abnormal objects are typically clicked repeatedly over extended periods. This means that abnormal objects usually appear in the candidate object sets corresponding to various click data sequences within a preset time window. Therefore, if an object exists in all candidate object sets, it's highly likely to be an abnormal object. By finding the intersection of these candidate object sets, the target object set formed by each abnormal object can be determined more accurately.

[0070] In one alternative embodiment, the intersection of object identifiers in multiple candidate object sets can be determined first; based on the object identifiers within the intersection, a target object set can be generated.

[0071] Thus, by comprehensively determining the final set of target objects through the cluster analysis results of the divided click data sequences, the accuracy of identifying abnormal objects can be improved.

[0072] The object recognition method of this application divides object click data over a period of time (i.e., a preset time window) into multiple click data sequences within time periods with short-term spatiotemporal correlation. Click data from each time period is used to generate a click data sequence, taking into account the click time sequence, which helps to improve the accuracy of object recognition.

[0073] Then, data statistics are performed on each click data sequence to obtain the multi-dimensional features corresponding to each click data sequence. Next, cluster analysis is performed in parallel on the multi-dimensional features of each click data sequence to identify a set of candidate objects with similar behavioral patterns within each click data sequence. Finally, the target object set is obtained based on the intersection of the candidate object sets corresponding to each click data sequence. This not only improves recognition efficiency but also further enhances the accuracy of object recognition by utilizing the intersection of candidate objects from different click data sequences with temporal correlations.

[0074] Please see Figure 4 In some embodiments, a click coordinate distribution map corresponding to the target object set is generated, and the click coordinate distribution map is generated based on the click coordinates of each click operation of the target object set within a preset time window.

[0075] After obtaining the target object set, to facilitate users in verifying the accuracy of the object recognition results, a click coordinate distribution map corresponding to the target object set can be generated. This map displays the coordinate points corresponding to each click operation within a preset time window for the target object set (e.g., ...). Figure 4 (This refers to the distribution of various coordinate points). Users can use the degree of concentration of coordinate points to help confirm whether the object recognition results are accurate.

[0076] In some embodiments, object click data is preprocessed to remove at least one of invalid data, duplicate data, and abnormal data.

[0077] Invalid data refers to data that is useless for object recognition. For example, data with coordinates outside the screen resolution range or timestamps from the future are obviously erroneous and will not only be useless for object recognition but may even affect the accuracy of object recognition. This may include invalid click data where the click coordinates are outside the screen coordinate range and / or the click timestamp is outside the preset time window.

[0078] Among them, duplicate data includes data of repeated clicks on the same object within a second preset time period (the second preset time period is generally short, such as 1 millisecond, 2 milliseconds, etc., and repeated clicks are generally not possible within the second preset time period), to avoid accidental triggering.

[0079] Abnormal data includes abnormal click data of objects whose click count falls within a preset range within a preset time window (such as very few clicks (less than the minimum value of the preset range) or very many clicks (greater than the maximum value of the preset range)). Extreme abnormal data is removed.

[0080] All of the above technical solutions can be combined in any way to form optional embodiments of this application, and will not be described in detail here.

[0081] In summary, the object recognition method of this application has the following technical effects: (1) The object click data within the preset time window is evenly divided into 60 isochronous segments according to the natural time dimension (such as the preset time interval), which are the click data sequences. This design can ensure that the click behavior within a single segment has "short-term spatiotemporal correlation" (avoiding behavior discretization across long time dimensions), while supporting parallel computing of multiple segments, which greatly improves the overall object recognition efficiency.

[0082] (2) For user click data within a single time segment, construct a multi-dimensional feature vector that integrates basic statistical features, spatial distribution features, click time sequence features and address clustering features.

[0083] (3) Within a single time segment, a density clustering algorithm (i.e., hierarchical density clustering algorithm) without pre-setting the number of clusters is used to analyze multi-dimensional feature vectors in order to identify a set of abnormal objects with highly similar behavior patterns.

[0084] (4) Aggregate and deduplicate the clustering results (i.e., each set of candidate objects) across multiple consecutive time segments (i.e., take the intersection) to output a stable and persistent set of target objects.

[0085] To facilitate better implementation of the object recognition method of this application, this application also provides an object recognition device. Please refer to... Figure 5 , Figure 5 A schematic diagram of the structure of an object recognition device provided in an embodiment of this application. The object recognition device 200 may include: The data segmentation module 201 is used to segment object click data within a preset time window based on a preset time interval, so as to generate multiple click data sequences. The data statistics module 202 is used to perform data statistics on the click data sequence in order to obtain the multi-dimensional features corresponding to the click data sequence; Clustering analysis module 203 is used to perform clustering analysis on the multi-dimensional features corresponding to each click data sequence to obtain a set of candidate objects with similar behavioral patterns corresponding to each click data sequence. The determination module 204 is used to determine the target object set based on the intersection of the candidate object sets.

[0086] Each module or unit in the aforementioned object recognition device can be implemented entirely or partially through software, hardware, or a combination thereof. Each unit can be embedded in or independent of the processor in the electronic device in hardware form, or stored in the memory of the electronic device in software form, so that the processor can call and execute the operations corresponding to each unit.

[0087] The object identification device 200 can be integrated into a terminal or server that has storage and a processor and thus computing power, or the object identification device 200 can be the terminal or server.

[0088] Optionally, this application also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0089] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device may be a terminal or a server. Figure 6 As shown, the electronic device 300 includes a processor 301 with one or more processing cores, a memory 302 with one or more computer-readable storage media, and a computer program stored in the memory 302 and executable on the processor. The processor 301 and the memory 302 are electrically connected. Those skilled in the art will understand that the electronic device structure shown in the figures does not constitute a limitation on the electronic device, and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0090] The processor 301 is the control center of the electronic device 300. It connects various parts of the electronic device 300 through various interfaces and lines. By running or loading software programs and / or modules stored in the memory 302, and calling data stored in the memory 302, it executes various functions of the electronic device 300 and processes data, thereby performing overall processing of the electronic device 300.

[0091] Optional, such as Figure 6 As shown, the electronic device 300 also includes: a display screen 303, a radio frequency circuit 304, an audio circuit 305, an input unit 306, and a power supply 307. The processor 301 is electrically connected to the display screen 303, the radio frequency circuit 304, the audio circuit 305, the input unit 306, and the power supply 307. Those skilled in the art will understand that... Figure 6 The electronic device structure shown does not constitute a limitation on the electronic device and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0092] The display screen 303 can be used to display a graphical user interface (GUI) and receive operation commands generated by the user interacting with the GUI. The display screen 303 may include a display panel and a touch panel. The display panel can be used to display information input by the user or information provided to the user, as well as various graphical user interfaces of the electronic device. These graphical user interfaces can be composed of graphics, text, icons, video, and any combination thereof. The touch panel can be used to collect touch operations performed by the user on or near it (such as operations performed by the user using a finger, stylus, or any suitable object or accessory on or near the touch panel), generate corresponding operation commands, and execute the corresponding program. Optionally, the touch panel may include a touch detection device and a touch controller. The touch detection device detects the user's touch location and the signal generated by the touch operation, and transmits the signal to the touch controller. The touch controller receives touch information from the touch detection device, converts it into touch point coordinates, sends it to the processor 301, and can receive and execute commands from the processor 301. The touch panel can cover the display panel. When the touch panel detects a touch operation on or near it, it transmits the information to the processor 301 to determine the type of touch event. Subsequently, the processor 301 provides corresponding visual output on the display panel according to the type of touch event. In this embodiment, the touch panel and the display panel can be integrated into the display screen 303 to achieve input and output functions. However, in some embodiments, the touch panel and the display screen 303 can be implemented as two independent components to achieve input and output functions. That is, the display screen 303 can also be used as part of the input unit 306 to achieve input functions.

[0093] The radio frequency circuit 304 can be used to transmit and receive radio frequency signals to establish wireless communication with network devices or other electronic devices, and to transmit and receive signals with network devices or other electronic devices.

[0094] Audio circuitry 305 can be used to provide an audio interface between a user and an electronic device via a speaker and a microphone. Audio circuitry 305 converts received audio data into electrical signals, transmits them to the speaker, and the speaker converts them into sound signals for output. Conversely, the microphone converts collected sound signals into electrical signals, which are then received by audio circuitry 305, converted back into audio data, and then processed by processor 301 before being transmitted via radio frequency circuitry 304 to, for example, another electronic device, or output to memory 302 for further processing. Audio circuitry 305 may also include an earphone jack to facilitate communication between peripheral headphones and electronic devices.

[0095] The input unit 306 can be used to receive input numbers, characters, or object feature information (such as fingerprints, irises, facial information, etc.), and to generate keyboard, mouse, joystick, optical, or trackball signal inputs related to user settings and function control.

[0096] Power supply 307 is used to supply power to various components of electronic device 300. Optionally, power supply 307 can be logically connected to processor 301 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. Power supply 307 may also include one or more DC or AC power supplies, recharging systems, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0097] although Figure 6 As not shown in the diagram, the electronic device 300 may also include a camera, sensor, wireless fidelity module, Bluetooth module, etc., which will not be described in detail here.

[0098] This application also provides a computer-readable storage medium for storing a computer program. This computer-readable storage medium can be applied to an electronic device, and the computer program causes the electronic device to execute the corresponding process in the object recognition method of the embodiments of this application; for the sake of brevity, further details are omitted here.

[0099] This application also provides a computer program product including computer instructions stored in a computer-readable storage medium. The processor of an electronic device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the electronic device to perform the corresponding process in the object recognition method of this application embodiment. For simplicity, further details are omitted here.

[0100] It should be understood that the processor in this application may be an integrated circuit chip with signal processing capabilities. In implementation, the steps of the above method embodiments can be completed by integrated logic circuits in the processor's hardware or by instructions in software form. The processor described above can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules can be located in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. This storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method.

[0101] It is understood that the memory in the embodiments of this application can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDR SDRAM), Enhanced Synchronous DRAM (ESDRAM), Synchlink DRAM (SLDRAM), and Direct Rambus RAM (DR RAM). It should be noted that the memory used in the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0102] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0103] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0104] In the embodiments of this application, the terms "module" or "unit" refer to a computer program or part of a computer program that has a predetermined function and works with other related parts to achieve a predetermined goal, and can be implemented wholly or partially using software, hardware (such as processing circuitry or memory), or a combination thereof. Similarly, a processor (or multiple processors or memory) can be used to implement one or more modules or units. Furthermore, each module or unit can be part of an overall module or unit that includes the functionality of that module or unit.

[0105] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0106] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0107] In addition, the functional units in this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0108] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause an electronic device (which may be a personal computer or a server) to execute all or part of the steps of the methods in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0109] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. An object recognition method, characterized in that, include: Based on a preset time interval, the object click data within a preset time window is divided to generate multiple click data sequences; Data statistics are performed on the click data sequence to obtain the multi-dimensional features corresponding to the click data sequence; Cluster analysis is performed on the multi-dimensional features corresponding to each click data sequence to obtain a set of candidate objects with similar behavioral patterns for each click data sequence. The target object set is determined based on the intersection of the various candidate object sets.

2. The object recognition method according to claim 1, characterized in that, The step involves dividing the object click data within a preset time window based on a preset time interval to generate multiple click data sequences, including: The preset time window is divided into multiple sub-time windows based on the preset time interval; Based on the object click data whose click timestamps are located within each of the sub-time windows, each click data sequence is generated, wherein each click data sequence corresponds to one of the sub-time windows.

3. The object recognition method according to claim 1, characterized in that, The multi-dimensional features include at least one of basic statistical features, spatial distribution features, click time sequence features, and address clustering features; The basic statistical features include mathematical statistical features related to click operations; the spatial distribution features include the distribution features of click operations at different locations on the screen; the click timing features include the timing features of click operations; and the address clustering features include the number of objects associated with each IP address and device.

4. The object recognition method according to claim 3, characterized in that, The basic statistical features include at least one of the following: total number of clicks, click frequency, percentage of click coordinates located in the target area, and number of repeated clicks; The spatial distribution characteristics include at least one of the following: a first statistical value of the first coordinate of the click coordinate on the first coordinate axis, a second statistical value of the second coordinate of the click coordinate on the second coordinate axis, click coverage area, and click concentration. Wherein, the first statistical value is used to characterize the distribution concentration of each click coordinate on the first coordinate axis, the second statistical value is used to characterize the distribution concentration of each click coordinate on the second coordinate axis, the click coverage area is determined based on the largest first coordinate value and the largest second coordinate value among each click coordinate, the click concentration is determined based on the average distance of each click coordinate to the center coordinate, and the center coordinate is the coordinate corresponding to the center position of each click coordinate; The click timing features include at least one of the following: a third statistical value corresponding to the click interval, a fourth statistical value corresponding to the click speed, the maximum duration of no click operation, and the number of click interval abrupt changes. The third statistical value is determined based on the statistical value of the click interval between two adjacent click operations, and the fourth statistical value is determined based on the statistical value of the number of clicks within each first preset duration within the preset time interval. The address clustering features include IP address clustering features and device fingerprint clustering features; The IP address clustering feature includes at least one of the following: the number of objects associated with the same IP address, the binding duration of the IP address and the object, and the IP address value; the device fingerprint clustering feature includes the number of objects associated with the same device fingerprint.

5. The object recognition method according to claim 1, characterized in that, The step of performing cluster analysis on the multi-dimensional features corresponding to each click data sequence to obtain a set of candidate objects with similar behavioral patterns for each click data sequence includes: The multi-dimensional features of each object are processed to generate multi-dimensional feature vectors corresponding to each object. Based on a preset hierarchical density clustering algorithm, clustering analysis is performed in parallel on each of the multi-dimensional feature vectors of each click data sequence to obtain cluster feature clusters. The candidate object set is generated based on the object identifiers corresponding to each of the multi-dimensional feature vectors in the clustered feature clusters.

6. The object recognition method according to claim 1, characterized in that, Also includes: The object click data is preprocessed to remove at least one of invalid data, duplicate data, and abnormal data; The invalid data includes invalid click data where the click coordinates are outside the screen coordinate range and / or the click timestamp is outside the preset time window; the duplicate data includes repeated click data of the same object within a second preset time period; and the abnormal data includes abnormal click data of objects whose number of clicks exceeds a preset number range within the preset time window.

7. The object recognition method according to claim 1, characterized in that, Determining the target object set based on the intersection of the various candidate object sets includes: Determine the intersection of object identifiers in multiple candidate object sets; The target object set is generated based on the object identifiers within the intersection.

8. An object recognition device, characterized in that, include: The data segmentation module is used to segment object click data within a preset time window based on a preset time interval, so as to generate multiple click data sequences; The data statistics module is used to perform data statistics on the click data sequence to obtain the multi-dimensional features corresponding to the click data sequence; The clustering analysis module is used to perform clustering analysis on the multi-dimensional features corresponding to each click data sequence to obtain a set of candidate objects with similar behavior patterns for each click data sequence. The determination module is used to determine the target object set based on the intersection of the various candidate object sets.

9. An electronic device, characterized in that, The electronic device includes a processor and a memory, the memory storing a computer program, and the processor executing the object recognition method according to any one of claims 1-7 by calling the computer program stored in the memory.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program adapted for loading by a processor to perform the object recognition method as described in any one of claims 1-7.

Images