Account behavior determination method and device, computer equipment, readable storage medium and program product

Abstract

The invention relates to an account behavior determination method and device, computer equipment, a computer readable storage medium and a computer program product, relates to the technical field of computers, and can improve the account behavior recognition accuracy. The method comprises the following steps: acquiring gateway interaction data corresponding to a gateway of a gateway deployment object and equipment position data of an equipment account; the gateway interaction data describes the interaction condition of the equipment account and the gateway; determining a gateway physical location of the gateway; according to the gateway physical location and the device location data, determining a first account behavior of the device account returning to or leaving the gateway deployment object, and according to the gateway interaction data, determining a second account behavior of the device account returning to or leaving the gateway deployment object; and according to the first account behavior and the second account behavior, determining a trusted account behavior of the device account for the gateway deployment object.

Description

Technical Field

[0001] The present application relates to the field of computer technologies, and in particular, to a method, apparatus, computer device, computer-readable storage medium, and computer program product for determining account behavior. Background Art

[0002] With the rapid development of Internet of Things and big data technologies, the amount of account behavior data generated has increased sharply, and the data types have also become increasingly rich.

[0003] In related technologies, account behavior can be analyzed based on data provided by a certain data source. However, the inventor has found in practice that the accuracy of the account behavior analysis results obtained in this way is relatively poor, and the accuracy of account behavior recognition still needs to be improved. Summary of the Invention

[0004] Based on this, in order to solve the above technical problems, it is necessary to provide a method, apparatus, computer device, computer-readable storage medium, and computer program product for determining account behavior.

[0005] In a first aspect, the present application provides a method for determining account behavior, including:

[0006] Obtaining gateway interaction data corresponding to the gateway of the gateway deployment object, and device location data of the device account; the gateway interaction data describes the interaction situation between the device account and the gateway;

[0007] Determining the physical location of the gateway;

[0008] Determining, according to the physical location of the gateway and the device location data, a first account behavior of the device account returning to or leaving the gateway deployment object, and determining, according to the gateway interaction data, a second account behavior of the device account returning to or leaving the gateway deployment object;

[0009] Determining a trusted account behavior of the device account with respect to the gateway deployment object according to the first account behavior and the second account behavior.

[0010] In one embodiment, the determining the physical location of the gateway includes:

[0011] Determining a device stay location according to the device location data; the device stay location is a location where the stay time and the number of stays meet a preset stay condition;

[0012] Determining a gateway interaction location of the device account according to the device location data and the gateway interaction data; the gateway interaction location is the location where the device account is located when the device account interacts with the gateway;

[0013] When the gateway interaction location matches the device staying location, determine the gateway physical location of the gateway according to the device staying location.

[0014] In one embodiment, determining the gateway physical location of the gateway includes:

[0015] Determine multiple gateway interaction locations of the device account according to the device location data and the gateway interaction data; the gateway interaction location is the location where the device account is located when the device account interacts with the gateway;

[0016] If the number of the multiple gateway interaction locations is greater than the number threshold and the locations among the multiple gateway interaction locations match, determine the gateway physical location of the gateway according to the multiple gateway interaction locations.

[0017] In one embodiment, determining the first account behavior of the device account to return to or leave the gateway deployment object according to the gateway physical location and the device location data includes:

[0018] Determine the distance change situation between the device account and the gateway physical location according to the gateway physical location and the device location data;

[0019] If it is determined according to the distance change situation that the device account leaves the gateway physical location and then returns to the gateway physical location after reaching a preset distance, determine the first account behavior of the device account to return to the gateway deployment object;

[0020] If it is determined according to the distance change situation that the device account leaves the gateway physical location and reaches a preset distance, determine the first account behavior of the device account to leave the gateway deployment object.

[0021] In one embodiment, determining the distance change situation between the device account and the gateway physical location according to the gateway physical location and the device location data includes:

[0022] When it is determined according to the gateway interaction data that the device account performs an online operation at the gateway, determine the online time corresponding to the online operation and the return time when the device account last returns to the gateway deployment object;

[0023] According to the device location data between the behavior occurrence time and the online time, and the gateway physical location, determine the first distance change situation between the device account and the gateway physical location; the first distance change situation is used to determine whether the device account has the first account behavior of returning to the gateway deployment object.

[0024] When it is determined according to the gateway interaction data that the device account performs a logout operation on the gateway, determine the logout time corresponding to the logout operation;

[0025] According to the device location data within a preset time after the logout time and the physical location of the gateway, determine the second distance change situation between the device account and the physical location of the gateway; the second distance change situation is used to determine whether the device account has a first account behavior of leaving the gateway deployment object.

[0026] In one embodiment, the determining the second account behavior of the device account returning to or leaving the gateway deployment object according to the gateway interaction data includes:

[0027] If it is determined according to the gateway interaction data that the device account performs a login operation on the gateway and the device account maintains the logged-in state for a preset time threshold, then determine the second account behavior of the device account returning to the gateway deployment object;

[0028] If it is determined according to the gateway interaction data that the device account performs a logout operation on the gateway and the device account maintains the logged-out state for a preset time threshold, then determine the second leaving behavior of the device account leaving the gateway deployment object.

[0029] In a second aspect, the present application further provides an account behavior determination device, including:

[0030] A multi-source data acquisition module, configured to acquire gateway interaction data corresponding to the gateway of the gateway deployment object and device location data of the device account; the gateway interaction data describes the interaction situation between the device account and the gateway;

[0031] A gateway location determination module, configured to determine the physical location of the gateway;

[0032] A behavior analysis module, configured to determine the first account behavior of the device account returning to or leaving the gateway deployment object according to the physical location of the gateway and the device location data, and determine the second account behavior of the device account returning to or leaving the gateway deployment object according to the gateway interaction data;

[0033] A trusted behavior determination module, configured to determine the trusted account behavior of the device account with respect to the gateway deployment object according to the first account behavior and the second account behavior.

[0034] In a third aspect, the present application further provides a computer device, including a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0035] Obtain the gateway interaction data corresponding to the gateway of the gateway deployment object, and the device location data of the device account; the gateway interaction data describes the interaction situation between the device account and the gateway;

[0036] Determine the gateway physical location of the gateway;

[0037] According to the gateway physical location and the device location data, determine the first account behavior of the device account to return to or leave the gateway deployment object, and, according to the gateway interaction data, determine the second account behavior of the device account to return to or leave the gateway deployment object;

[0038] According to the first account behavior and the second account behavior, determine the trusted account behavior of the device account for the gateway deployment object.

[0039] In a fourth aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0040] Obtain the gateway interaction data corresponding to the gateway of the gateway deployment object, and the device location data of the device account; the gateway interaction data describes the interaction situation between the device account and the gateway;

[0041] Determine the gateway physical location of the gateway;

[0042] According to the gateway physical location and the device location data, determine the first account behavior of the device account to return to or leave the gateway deployment object, and, according to the gateway interaction data, determine the second account behavior of the device account to return to or leave the gateway deployment object;

[0043] According to the first account behavior and the second account behavior, determine the trusted account behavior of the device account for the gateway deployment object.

[0044] In a fifth aspect, the present application further provides a computer program product, including a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0045] Obtain the gateway interaction data corresponding to the gateway of the gateway deployment object, and the device location data of the device account; the gateway interaction data describes the interaction situation between the device account and the gateway;

[0046] Determine the gateway physical location of the gateway;

[0047] Determine a first account behavior of the device account returning to or leaving the gateway deployment object according to the physical location of the gateway and the device location data, and determine a second account behavior of the device account returning to or leaving the gateway deployment object according to the gateway interaction data;

[0048] Determine a trusted account behavior of the device account for the gateway deployment object according to the first account behavior and the second account behavior.

[0049] The above account behavior determination method, device, computer device, computer-readable storage medium, and computer program product can obtain the gateway interaction data corresponding to the gateway of the gateway deployment object and the device location data of the device account. The gateway interaction data describes the interaction between the device account and the gateway. Then, determine the physical location of the gateway, and according to the physical location of the gateway and the device location data, determine a first account behavior of the device account returning to or leaving the gateway deployment object, and according to the gateway interaction data, determine a second account behavior of the device account returning to or leaving the gateway deployment object. Furthermore, according to the first account behavior and the second account behavior, determine a trusted account behavior of the device account for the gateway deployment object. Compared with identifying account behaviors based on a single data source in the related art, by combining the gateway interaction data of the gateway deployment object and the device location data of the device account, the first account behavior and the second account behavior are respectively determined, and then by integrating the first account behavior and the second account behavior, the trusted account behavior is determined, which can break through the limitation of a single data source, help correct the account behavior recognition error of a single data source, and at the same time can realize the complementarity and enhancement of multi-source data in the account behavior recognition process, effectively improving the accuracy of the account behavior recognition result. Brief Description of the Drawings

[0050] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related art, the following will briefly introduce the drawings required for use in the description of the embodiments of the present application or the related art. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0051] Figure 1 It is a schematic flowchart of a method for determining an account behavior in an embodiment;

[0052] Figure 2 It is a schematic flowchart of another method for determining an account behavior in an embodiment;

[0053] Figure 3a It is a schematic diagram of identifying a going-home behavior in an embodiment;

[0054] Figure 3bSchematic diagram of identifying the behavior of leaving home in an embodiment;

[0055] Figure 4 Structural block diagram of an account behavior determination device in an embodiment;

[0056] Figure 5 Internal structure diagram of a computer device in an embodiment. Detailed implementation manners

[0057] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, but not to limit the present application.

[0058] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data need to comply with relevant regulations.

[0059] In order to enable those skilled in the art to better understand the present application, the related technologies will be introduced below first.

[0060] With the rapid development of Internet of Things and big data technologies, the amount of account behavior data generated has increased sharply, and the data types have also become increasingly rich.

[0061] In the related technologies, the account behavior can be analyzed through the data provided by a certain data source. In some possible implementation manners, one way is to only use the base station positioning data, and by analyzing the movement trajectories of the account at different times and locations, the account behavior analysis result is obtained. Another way is to collect network usage data for analysis. The network usage data can include device connection status, traffic usage, application access records, etc., and can reflect the network activity habits of the account.

[0062] However, the inventors found in practice that although the former can capture the movement characteristics of the account, due to the lack of data related to indoor activities, its analysis results are often relatively rough and it is difficult to accurately identify the true intentions and preferences of the account; while the latter is limited to fixed network usage scenarios and has limitations in analyzing the overall behavior pattern of the account. It can be seen that in the related technologies, when identifying account behavior, it often only relies on a single data source, the analysis results are one-sided, and it is impossible to comprehensively reflect the true behavior of the account. The accuracy of account behavior identification still needs to be improved.

[0063] Based on this, it is necessary to provide an account behavior determination method, apparatus, computer device, computer-readable storage medium, and computer program product for the above technical problems.

[0064] In one embodiment, as Figure 1 shown, an account behavior determination method is provided. In this embodiment, it is exemplified that the method is applied to a server. It can be understood that the method can also be applied to a terminal, or to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0065] S101, obtain the gateway interaction data corresponding to the gateway of the gateway deployment object, and the device location data of the device account; the gateway interaction data describes the interaction situation between the device account and the gateway.

[0066] Among them, the gateway deployment object can be a place where a gateway is deployed and corresponds to a specific physical location. In some examples, the gateway deployment object can be divided according to the type of the place. For example, a specific home or enterprise can be used as the gateway deployment object. For example, Company A located at a certain address can be used as the gateway deployment object.

[0067] The device account can be an account corresponding to a terminal device. In some examples, the device account can be determined according to the device identifier, or the account logged in to the terminal device can be used as the device account.

[0068] In this step, on the one hand, the gateway interaction data corresponding to the gateway of the gateway deployment object can be obtained. The gateway interaction data can characterize the interaction situation between the device account and the gateway. Among them, the gateway interaction data can record the type of interaction operation between the device account and the gateway, or the time when the interaction operation occurs between the device account and the gateway. On the other hand, the device location data of the device account can be obtained. The device location data can characterize the location where the device account is located. Of course, it can also record the location where the device account is located and the corresponding time. In some exemplary embodiments, the device location data can include historical location data collected in the past, that is, stock device location data, or can include currently collected real-time location data, that is, incremental device location data.

[0069] In some embodiments, if the gateway deployment object is a household, the gateway of the gateway deployment object can be a home gateway. As an access device for smart home and broadband, the home gateway not only supports basic network access functions, but also can integrate various intelligent service interfaces such as smart home control and data transmission. It can collect home network usage data, such as gateway interaction data, which helps to provide important basis for data analysis. The device location data of the device account can be determined according to the base station location data. The base station location data refers to the approximate location information of the device calculated by combining the data of signal interaction (such as signal strength, transmission delay, etc.) between the device and the base station with a preset specific algorithm. It should be emphasized that the gateway interaction data and device location data involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data need to comply with relevant regulations.

[0070] In an exemplary embodiment, the gateway interaction data for the gateway deployment object and the base station location data of the device can be collected from the gateway of the gateway deployment object and the communication network respectively. Then, data preprocessing is performed on the gateway interaction data and the base station location data. Among them, data preprocessing can include one or more operations such as cleaning, denoising, and timestamp alignment of the collected data to ensure data quality. For example, the device online / offline data of the gateway can be obtained according to the gateway interaction data. Since frequent online / offline actions may occur due to one or more scenarios such as network fluctuations, signal fluctuations, and terminal reconnection, such data is useless for determining the behavior of returning to or leaving the gateway deployment object and can be screened out. Another example is that for the base station location data, the approximate location information of the device calculated by using a specific algorithm through the signal interaction (such as signal strength, transmission delay, etc.) between the device and the base station may have different degrees of deviation. The data with deviation and regression within a short time and the deviation amount exceeding the reasonable range in the data can be screened out. In addition, a data quality evaluation mechanism can be introduced to evaluate the quality of the preprocessed data to ensure the smooth progress of the fusion process. Through the above data preprocessing and data quality control evaluation, the influence of incorrect data on the analysis result is effectively reduced, and the efficiency and accuracy of data fusion are improved. Compared with the prior art, this application can better handle data quality problems and lay a solid foundation for subsequent user behavior analysis.

[0071] S102. Determine the physical location of the gateway.

[0072] In a specific implementation, the physical location of the gateway can be obtained. In some exemplary embodiments, the physical location of the gateway can be recorded when setting the gateway for the gateway deployment object.

[0073] In some other embodiments, if the physical location of the gateway is not pre-recorded, the physical location of the gateway can also be determined based on the gateway interaction data and the device location data. Specifically, the device location data can record the location where the device account is located, and the gateway interaction data can record the interaction situation between the device account and the gateway, such as whether the device account interacts with the gateway. By correlating the device location data and the gateway interaction data, the device location where the device account is located when the device account interacts with the gateway can be determined, and thus the physical location where the gateway is located, that is, the gateway physical location, can be determined according to the device location.

[0074] In some embodiments, the device location data records the location where the device account is located and the corresponding time when the device account is at this location, and the gateway interaction data can record the interaction between the device account and the gateway and the time when the device account interacts with the gateway. Furthermore, the device location data and the gateway interaction data can be aligned by time, the location where the device account is located when the device account interacts with the gateway can be determined, and the gateway physical location of the gateway can be obtained according to this location.

[0075] S103. Determine the first account behavior of the device account to return to or leave the gateway deployment object according to the gateway physical location and the device location data, and determine the second account behavior of the device account to return to or leave the gateway deployment object according to the gateway interaction data.

[0076] In specific implementation, the gateway is often set within a preset range of the gateway deployment object. For example, the home gateway of a certain family will be deployed at the location of the family. In this step, the spatial location can be introduced to perform a correlation analysis on the account behavior of the device account leaving or returning to the gateway deployment object. At the same time, according to the gateway physical location and the device location data, the account behavior of the device account returning to or leaving the gateway deployment object is determined. For the convenience of distinction, the account behavior obtained by analyzing the gateway physical location and the device location data is called the first account behavior. In some embodiments, the device account location can be determined according to the device location data, and then the first account behavior of the device account returning to or leaving the gateway deployment object can be identified according to the distance between the device location data and the gateway physical location.

[0077] On the other hand, the interaction operation between the device account and the gateway can also be used to predict the subsequent account behavior of the device account for the gateway deployment object. For example, when the device account performs a logout operation, the device account may be about to leave the gateway deployment object, and when the device account performs a login operation, the device account may have returned to the gateway deployment object. Based on this, the account behavior of the device account to return to or leave the gateway deployment object can be determined according to the gateway interaction data. For the convenience of distinction, this account behavior is called the second account behavior.

[0078] S104. Determine the trusted account behavior of the device account for the gateway deployment object according to the first account behavior and the second account behavior.

[0079] Since the first account behavior and the second account behavior are determined by analyzing different data sources, after obtaining the first account behavior and the second account behavior, it is possible to identify whether the account has an account behavior against the gateway deployment object according to the first account behavior and the second account behavior. For example, the first account behavior and the second account behavior determined based on different data sources can be integrated to obtain the account behavior recognition result of the device account for the gateway deployment object. For the sake of distinction, in this application, the account behavior determined according to the first account behavior and the second account behavior is referred to as the trusted account behavior.

[0080] In this embodiment, by combining the device location data and the gateway interaction data, the first account behavior and the second account behavior are respectively identified, and then the trusted account behavior is determined by combining the first account behavior and the second account behavior, which helps to break through the limitation of a single data source, correct the data error of a single data source, eliminate the useless data in a single data source, and realize the complementarity and enhancement of multi-source data. At the same time, by integrating the gateway interaction data and the device location data, it is possible to more comprehensively reflect the behavior activities of the device account in different dimensions (such as network activities, movement trajectories, etc.), providing a rich data source for accurately identifying account behaviors. In some embodiments, after obtaining the trusted account behavior, feature extraction can be performed according to various trusted account behaviors of the device account to obtain the behavior features of the device account.

[0081] In some exemplary embodiments, in step S104, determining the trusted account behavior of the device account for the gateway deployment object according to the first account behavior and the second account behavior may include:

[0082] In the case where the first account behavior and the second account behavior match, determine the first account behavior and / or the second account behavior as the trusted account behavior of the device account for the gateway deployment object.

[0083] In practical applications, when the first account behavior and the second account behavior are the same or similar, at least one of the first account behavior and the second account behavior can be determined as the trusted account behavior of the device account for the gateway deployment object. For example, when the first account behavior is the account behavior of returning to the gateway deployment object and the second account behavior is also the account behavior of returning to the gateway deployment object, it can be determined that the device account has a trusted account behavior of returning to the gateway deployment object.

[0084] In some other embodiments, if the first account behavior does not match the second account behavior, it can be determined that there is an abnormality in the account behavior discrimination result, and the first account behavior and the second account behavior can be further analyzed to determine the credible account behavior. For example, according to device location data or other data sources, the credibility of the first account behavior and the second account behavior can be further determined, and the account behavior with higher credibility can be determined as the credible account behavior from the first account behavior and the second account behavior.

[0085] For example, the action of the device account interacting with the gateway can be used as a trigger for specific account behavior determination. When the following conditions are met simultaneously, it is identified as the corresponding credible account behavior: ① It meets the manifestation of the specific behavior in the gateway data; ② It meets the manifestation of the specific behavior in the positioning data; ③ The manifestations in the two types of data can eliminate their respective useless data or correct the errors in the data.

[0086] Compared with the related art, the present application can effectively solve the problem of data anomalies of a single data source in special scenarios, such as the gateway online and offline data noise caused by the power-saving strategy of the terminal device, and the device offline behavior that may not be captured during the automatic switching of multiple routers under a single gateway; through the multi-source data complementarity of the present application, after determining the first account behavior and the second account behavior, and then combining the first account behavior and the second account behavior to determine the final credible account behavior, which improves the comprehensiveness and accuracy of account behavior analysis.

[0087] The above account behavior determination method can obtain the gateway interaction data corresponding to the gateway of the gateway deployment object, and the device location data of the device account. The gateway interaction data describes the interaction situation between the device account and the gateway; then determine the physical location of the gateway, and according to the gateway physical location and the device location data, determine the first account behavior of the device account returning to or leaving the gateway deployment object, and, according to the gateway interaction data, determine the second account behavior of the device account returning to or leaving the gateway deployment object; and then determine the credible account behavior of the device account for the gateway deployment object according to the first account behavior and the second account behavior. Compared with the related art that identifies account behavior based on a single data source, in this embodiment, by combining the gateway interaction data of the gateway deployment object and the device location data of the device account, the first account behavior and the second account behavior are respectively determined, and then by integrating the first account behavior and the second account behavior, the credible account behavior is determined, which can break the limitation of a single data source, help correct the account behavior recognition error of a single data source, and at the same time can achieve the complementarity and enhancement of multi-source data in the account behavior recognition process, effectively improving the accuracy of the account behavior recognition result.

[0088] In addition, during the process of analyzing account behavior, although a large amount of behavior data has been accumulated separately in different dimensions (such as device location data obtained based on mobile communication and gateway interaction data obtained based on gateway deployment), due to differences in data formats, storage methods, processing technologies, etc., data islands have been formed between data in different dimensions. The method of using a single data source to determine account behavior in related technologies is difficult to efficiently and accurately fuse data from different data sources, resulting in the failure to fully explore the relevance between data. At the same time, analyzing network usage data or location data separately also limits the analysis results to the scenario and makes it difficult to conduct a panoramic analysis of account behavior across scenarios. In response to this, through this embodiment, the problems of single data source and insufficient data fusion in identifying account behavior in related technologies can be effectively solved. By combining gateway interaction data and device location data to determine trusted account behavior, efficient and accurate fusion of multi-source data is achieved, breaking the data island, enabling cross-domain, cross-scenario, and multi-dimensional data fusion and account behavior analysis, improving the comprehensiveness and accuracy of account behavior analysis, and also providing a comprehensive and rich data basis for subsequent account behavior analysis.

[0089] In one embodiment, in step S102, determining the gateway physical location of the gateway may include the following steps:

[0090] Determine the device stay location according to the device location data; the device stay location is the location where the stay time and the number of stays meet the preset stay conditions; determine the gateway interaction location of the device account according to the device location data and the gateway interaction data; the gateway interaction location is the location where the device account is located when the device account interacts with the gateway; when the gateway interaction location matches the device stay location, determine the gateway physical location of the gateway according to the device stay location.

[0091] In practical applications, the device location data may record the location where the device account is located and the corresponding time, such as recording that the device account is at location A at 10:20. In this embodiment, by analyzing the device location data, the location where the device account has arrived and the stay time and the number of stays meet the preset stay conditions can be determined, and then this location can be used as the device stay location.

[0092] In some exemplary embodiments, the GeoHash algorithm may be used to aggregate each location included in the device location data, and the location with the cumulative number exceeding the quantity threshold or the stay duration exceeding the preset duration threshold in the aggregation result is marked as the device stay location.

[0093] On the other hand, the gateway interaction location of the device account can be determined according to the device location data and the gateway interaction data. For example, when it is detected that the device account interacts with the gateway, the location where the device account is located at this time can be obtained according to the device account data and determined as the gateway interaction location.

[0094] Furthermore, when the gateway interaction location matches the device stay location, the gateway physical location of the gateway can be determined according to the device stay location. For example, when the gateway interaction location matches the device stay location, the gateway stay location can be used as the gateway physical location of the corresponding gateway.

[0095] Specifically, for example, according to the configuration rules of the GeoHash algorithm, the coding length of the location code can be preset to 6, and the offset tolerance is x kilometers. Different locations within x kilometers can use the same location code, and different location codes are used to represent the location when it exceeds x kilometers. Then, the device location data is aggregated through the GeoHash algorithm, and the locations with the cumulative number or duration exceeding a certain amount in the aggregation result are identified as the stay locations. Subsequently, the action of the terminal device interacting with the gateway can be used as the trigger of the gateway physical location determination executor. When the device account performs an interaction action on the gateway, the location data of the device account is collected, and it is judged whether the current location data is the same location as any of the stay locations. The judgment method is to judge whether it is the same coding area through the GeoHash algorithm (such as setting the coding length to 7 and the offset tolerance to y kilometers) or whether the longitude and latitude distance exceeds the excitation threshold, and the gateway physical location is determined by combining the corresponding weights.

[0096] In this embodiment, by determining the device stay location according to the device location data, and then determining the gateway physical location of the gateway according to the device stay location when the gateway interaction location matches the device stay location, the gateway interaction data and the device location data can be deeply integrated in the time and space dimensions, and the gateway physical location can be inferred more accurately. Compared with other complex and costly gateway positioning technologies, this method further combines the device location data sufficiently, with relatively low cost and easy to implement, providing an efficient and economical method for determining the gateway location.

[0097] In one embodiment, in step S102, determining the gateway physical location of the gateway may include the following steps:

[0098] According to the device location data and the gateway interaction data, determine multiple gateway interaction locations of the device account; the gateway interaction location is the location where the device account is located when the device account interacts with the gateway; if the number of multiple gateway interaction locations is greater than the number threshold and the locations between the multiple gateway interaction locations match, then determine the gateway physical location of the gateway according to the multiple gateway interaction locations.

[0099] In practical applications, multiple gateway interaction locations of the device account can be determined according to the device location data and the gateway interaction data, where the multiple gateway interaction locations are the gateway interaction locations corresponding to the same interaction gateway. The specific determination method of the gateway interaction location can refer to the foregoing embodiments and will not be elaborated here.

[0100] After obtaining multiple gateway interaction locations, the number of multiple gateway interaction locations can be counted, and it can be determined whether the locations of multiple gateway interaction locations match. For example, it can be determined whether the distance between multiple gateway interaction locations is less than a threshold value. If so, it can be determined that they match; if not, it can be determined that they do not match.

[0101] When the number of multiple gateway interaction locations is greater than the quantity threshold and the locations of multiple gateway interaction locations match, the gateway physical location of the gateway can be determined based on multiple gateway interaction locations. For example, one of the multiple gateway interaction locations can be selected as the gateway physical location, or alternatively, the average value of multiple gateway interaction locations can be determined, and the gateway physical location can be determined based on this average value. For example, the action of the terminal device interacting with the gateway can be used as a trigger for the gateway physical location determination executor. When an interaction action occurs, positioning data is collected as the gateway interaction location, and the gateway physical location is determined based on multiple gateway interaction locations and corresponding weights.

[0102] In this embodiment, determining the gateway physical location through multiple gateway interaction locations that match in position can comprehensively judge based on various aspects of information, effectively reduce errors and uncertainties, and more accurately lock the actual physical location of the gateway; at the same time, it avoids positioning deviations caused by errors or interferences of a single gateway interaction location, improves the overall reliability of determining the gateway physical location, and reduces the error rate.

[0103] In one embodiment, in step S103, determining the first account behavior of the device account returning to or leaving the gateway deployment object based on the gateway physical location and device location data may include the following steps:

[0104] Based on the gateway physical location and device location data, determine the change in the distance between the device account and the gateway physical location; if it is determined based on the change in the distance that the device account leaves the gateway physical location and then returns to the gateway physical location after reaching a preset distance, determine the first account behavior of the device account returning to the gateway deployment object; if it is determined based on the change in the distance that the device account leaves the gateway physical location and reaches the preset distance, determine the first account behavior of the device account leaving the gateway deployment object.

[0105] Since the device location data can record the locations where the device account is located at multiple time points and reflect the movement trajectory of the device account, after determining the gateway physical location, in this embodiment, the change in the distance between the device account and the gateway physical location can be determined based on the gateway physical location and device location data.

[0106] Furthermore, the account behavior of the device account returning to or leaving the gateway deployment object can be determined based on the distance change. Specifically, if it is determined according to the distance change that the device account leaves the physical location of the gateway and then returns to the physical location of the gateway after reaching a preset distance, the first account behavior of the device account returning to the gateway deployment object is determined. If it is determined according to the distance change that the device account leaves the physical location of the gateway and reaches the preset distance, the first account behavior of the device account leaving the gateway deployment object is determined. For example, in the case where the physical location of the gateway and the preprocessing of the device location data are known, if it returns to the physical location of the gateway after leaving the physical location of the gateway by more than a distance L1, it is determined to return to the gateway deployment object. If it leaves the physical location of the gateway by more than a distance L2, it is determined to leave the gateway deployment object, where L1 is greater than L2.

[0107] In this embodiment, by determining the distance change between the device account and the physical location of the gateway based on the physical location of the gateway and the device location data, it is possible to accurately judge the behavior pattern of the device account according to the distance change between the device location data and the physical location of the gateway during the process of identifying the account behavior from multi-source data, thereby improving the accuracy of identifying the first account behavior.

[0108] In one embodiment, determining the distance change between the device account and the physical location of the gateway based on the physical location of the gateway and the device location data may include the following steps:

[0109] In the case where it is determined according to the gateway interaction data that the device account performs an online operation on the gateway, determine the online time corresponding to the online operation and the return time when the device account last returned to the gateway deployment object; according to the device location data between the behavior occurrence time and the online time, and the physical location of the gateway, determine the first distance change between the device account and the physical location of the gateway; the first distance change is used to judge whether the device account has the first account behavior of returning to the gateway deployment object; in the case where it is determined according to the gateway interaction data that the device account performs an offline operation on the gateway, determine the offline time corresponding to the offline operation; according to the device location data within a preset time after the offline time, and the physical location of the gateway, determine the second distance change between the device account and the physical location of the gateway; the second distance change is used to judge whether the device account has the first account behavior of leaving the gateway deployment object.

[0110] In a specific implementation, the distance change situation may include at least one of a first distance change situation and a second distance change situation. Among them, the first distance change situation is used to determine whether the device account has a first account behavior of returning to the gateway deployment object, and the second distance change situation is used to determine whether the device account has a first account behavior of leaving the gateway deployment object. In this embodiment, at least one of the first distance change situation and the second distance change situation can be triggered according to the type of interaction operation that the device account has with the gateway.

[0111] Specifically, when it is determined according to the gateway interaction data that the device account performs an online operation on the gateway, it is predicted that the device account may have a behavior of returning to the gateway deployment object. At this time, in order to more accurately identify the account behavior and avoid misjudging the noise points of the online operation data and the situation of automatic switching of multiple routers under a single gateway as the behavior of the device account returning to the gateway deployment object, the online time corresponding to the online operation and the return time when the device account last returned to the gateway deployment object can be determined. Then, according to the device location data between the time when the behavior occurs and the online time, and the physical location of the gateway, the first distance change situation between the physical location of the device account and the gateway is determined.

[0112] On the other hand, when it is determined according to the gateway interaction data that the device account performs an offline operation on the gateway, it is predicted that the device account may have a behavior of leaving the gateway deployment object. At this time, in order to more accurately identify the account behavior and avoid misjudging the noise points of the offline operation data as the behavior of the device account leaving the gateway deployment object, the offline time corresponding to the offline operation can be determined. Then, according to the device location data within a preset time after the offline time and the physical location of the gateway, the second distance change situation between the physical location of the device account and the gateway is determined.

[0113] In this embodiment, by triggering the extraction of the device location data within a specific time period through the gateway interaction data, and then determining the first distance change situation and the second distance change situation in space according to the device location data within the specific time period, the gateway interaction data and the device location data can be deeply integrated in the time and space dimensions, providing a reliable data basis for the subsequent identification of the first account behavior.

[0114] In one embodiment, in step S103, determining the second account behavior of the device account returning to or leaving the gateway deployment object according to the gateway interaction data may include the following steps:

[0115] If it is determined according to the gateway interaction data that the device account performs an online operation on the gateway and the device account maintains the online state for a preset time threshold, then determine the second account behavior of the device account returning to the gateway deployment object; if it is determined according to the gateway interaction data that the device account performs an offline operation on the gateway and the device account maintains the offline state for a preset time threshold, then determine the second leaving behavior of the device account leaving the gateway deployment object.

[0116] In a specific implementation, the operation type performed by the device on the gateway can be determined according to the gateway interaction data. When an online operation is detected, the time for which the device account maintains the online state can be further determined according to the gateway interaction data. If the device account maintains the online state for a preset time threshold, then it can be determined that the device account has the second account behavior of returning to the gateway deployment object. Among them, when calculating the duration of maintaining the online state, it can be calculated starting from the current online time, or a period of time before the current online time can be calculated. When an offline operation is detected, the time for which the device account maintains the offline state can be further determined according to the gateway interaction data. If the device account maintains the online state for a preset time threshold, then it can be determined that the device account has the second account behavior of leaving the gateway deployment object.

[0117] For example, when the device account has an online action on the gateway and there is no offline action in the past preset time (the preset time can depend on the gateway data acquisition error and actual application scenario analysis, for example, the threshold can be set to 15 minutes), then determine that the device account returns to the gateway deployment object; when the device account has an offline action on the gateway and there is no online action in the future preset time (the preset time can depend on the gateway data acquisition error and actual application scenario analysis, for example, the threshold can be set to 15 minutes), then determine that the device account leaves the gateway deployment object.

[0118] In this embodiment, by monitoring and judging the online and offline operations of the device account on the gateway and the time for maintaining the corresponding states, different behavior patterns of the device account can be accurately identified, and the behaviors of the device account returning to and leaving the gateway deployment object can be accurately distinguished.

[0119] To enable those skilled in the art to better understand the above steps, the following provides some examples to exemplarily illustrate the embodiments of the present application, but it should be understood that the embodiments of the present application are not limited thereto.

[0120] In one example, as Figure 2 shown, the following steps may be included:

[0121] S201, obtain the gateway interaction data corresponding to the gateway of the gateway deployment object, and the device location data of the device account.

[0122] S202, determine the location where the device stays according to the device location data.

[0123] S203. Determine the gateway interaction location of the device account based on the device location data and the gateway interaction data; when the gateway interaction location matches the device stay location, determine the gateway physical location of the gateway according to the device stay location.

[0124] S204. Determine multiple gateway interaction locations of the device account based on the device location data and the gateway interaction data; if the number of multiple gateway interaction locations is greater than the quantity threshold and the locations between the multiple gateway interaction locations match, determine the gateway physical location of the gateway according to the multiple gateway interaction locations.

[0125] S205. Determine the distance change situation between the device account and the gateway physical location according to the gateway physical location and the device location data.

[0126] S206. If it is determined according to the distance change situation that the device account leaves the gateway physical location and returns to the gateway physical location after reaching a preset distance, determine the first account behavior of the device account returning to the gateway deployment object; if it is determined according to the distance change situation that the device account leaves the gateway physical location and reaches a preset distance, determine the first account behavior of the device account leaving the gateway deployment object.

[0127] S207. If it is determined according to the gateway interaction data that the device account performs an online operation on the gateway and the device account maintains the online state for a preset time threshold, determine the second account behavior of the device account returning to the gateway deployment object; if it is determined according to the gateway interaction data that the device account performs an offline operation on the gateway and the device account maintains the offline state for a preset time threshold, determine the second leaving behavior of the device account leaving the gateway deployment object.

[0128] S208. Determine the trusted account behavior of the device account for the gateway deployment object according to the first account behavior and the second account behavior.

[0129] For example, as Figure 3a shown, a judgment example regarding the device account's homecoming behavior is provided.

[0130] 1. Data collection: Obtain the gateway interaction data and base station positioning data (i.e., device location data) of the home gateway.

[0131] 2. Data preprocessing: Perform preprocessing operations such as cleaning, denoising, and timestamp alignment on the collected data to ensure data quality.

[0132] 3. Data fusion:

[0133] (1) Identify the gateway physical location based on the feature-based fusion method:

[0134] The device account's gateway online, offline, network request and other actions are used as triggers for the gateway physical location determination actuator. When the above actions occur, the gateway location is marked when the following conditions are met:

[0135] ① By collecting the positioning data of the action time when the device account interacts with the gateway, the geographical locations within a certain distance range (such as 0.05km) are marked as the same location.

[0136] ② When a certain amount of data is accumulated, the geographical location with the most hits is marked as the gateway location.

[0137] (2) Determine the returning behavior based on the feature fusion method:

[0138] The gateway online action of the device account is used as the trigger of the return home behavior determination actuator. When the online action occurs, it is marked as a return home behavior if the following indicators are met at the same time:

[0139] ① Check whether there is any offline action within a certain period of time (such as 15 minutes). If there is, it is judged as a failure.

[0140] ② Check from the last time the returning home behavior was achieved to the time when the current online action occurred. If the positioning data is more than a certain distance (such as 0.6km) from the location of the gateway, it is determined that the returning home behavior is achieved.

[0141] For example, Figure 3b As shown, an example of judging the away-from-home behavior of a device account is provided.

[0142] 1. Data collection: Obtain the gateway interaction data and base station positioning data of the home gateway.

[0143] 2. Data preprocessing: Perform preprocessing operations such as cleaning, denoising, and timestamp alignment on the collected data to ensure data quality.

[0144] 3. Data Fusion:

[0145] (1) Gateway physical location identification based on weighted average fusion method and feature-based fusion method:

[0146] The gateway online, offline, network request and other actions of the terminal device are used as triggers for the gateway physical location determination actuator. When the above actions occur, the gateway location is marked if the following indicators are met:

[0147] ① The positioning data is aggregated using the GeoHash algorithm (e.g., the code length is 6, and the offset tolerance is 0.61km). The aggregation results are marked as stops if the cumulative number of times exceeds a certain number or duration.

[0148] ②Collect the positioning data at the moment when the terminal device interacts with the gateway, and determine whether the current positioning data is at the same location as any of the staying locations. The determination method is to judge whether it is in the same coding area through the GeoHash algorithm (for example, the coding length is 7 and the offset tolerance is 0.076 km) or whether the longitude and latitude distance exceeds a certain distance (for example, 0.05 km). If so, mark the staying location as a possible location of the gateway and accumulate the number of times.

[0149] ③When a certain amount of data is accumulated, mark the location of the staying location with the most hits as the physical location of the gateway.

[0150] (3)Determine the behavior of leaving home based on the feature-based fusion method:

[0151] Use the gateway offline action of the terminal device as the trigger of the home behavior determination executor;

[0152] Use the gateway online action of the terminal device as the terminator of the home behavior determination executor;

[0153] When the offline action occurs, if the following indicators are met simultaneously, it is marked as the behavior of leaving home:

[0154] ④Within a period of time (such as 15 minutes) after the moment when the current offline action occurs, no online action appears.

[0155] Through the cyclic delay task, perform short-period detection to achieve as real-time analysis of the behavior as possible.

[0156] ⑤Within a period of time (such as 15 minutes) after the moment when the current offline action occurs, if the positioning data is more than a certain distance (such as 0.1 km) from the location of the gateway, it is determined that the behavior of leaving home is achieved.

[0157] Through the above processing, the account behavior can be identified in multiple dimensions. During the identification process, by fusing the home gateway interaction data and the base station positioning data, the account behavior can be more comprehensively reflected, providing a rich data source for in-depth analysis of user behavior. At the same time, the security monitoring ability can be enhanced; through continuous monitoring and analysis of the account behavior pattern, abnormal behaviors can be found in time, providing strong support for security monitoring and ensuring the security of user information. In addition, it also promotes the effective utilization of data resources, promotes cross-domain and cross-platform data sharing and fusion, promotes the effective utilization and value mining of data resources, and conforms to the development trend of the big data era.

[0158] In some exemplary embodiments, the present application can be applied to the following scenarios:

[0159] (1)Smart home and security fields

[0160] With the user's authorization, the access situation of home network devices is determined by using gateway interaction data, and at the same time, the base station positioning data is combined to judge whether the relevant device account is at home, so as to realize the intelligent security function. When it is detected that an unknown device attempts to access the home network, the positioning information of the device account is combined to judge whether it is an abnormal situation and trigger the alarm mechanism.

[0161] (2)Account behavior analysis

[0162] With the user's authorization, by analyzing the gateway interaction data and the base station positioning data, the daily activity patterns and travel habits of the device account are understood. Thus, security monitoring services can be provided for relevant family members to monitor whether their daily activities are abnormal.

[0163] (3)Location-sensitive smart home control

[0164] With the user's authorization, by combining the gateway interaction data and the base station positioning data, remote control of smart home devices and automated scenario settings are realized, enabling home devices to automatically adjust according to the location changes of family members. For example, when it is recognized that the device account leaves home, unnecessary electrical appliances at home are automatically turned off; when it is recognized that the device account approaches the home door, devices such as lighting and air conditioners are turned on in advance.

[0165] It can be seen that the present application has the following advantages and effects compared with the related technologies:

[0166] 1. Improve data comprehensiveness and accuracy. The multi-source data fusion algorithm can integrate data from different sensors, devices or algorithms, thereby providing more comprehensive and accurate information. This helps to reduce information deviation caused by errors in a single data source and improve the reliability of the data. By fusing various types of data, the deficiencies in coverage and accuracy of a single data source can be made up, enabling the system to obtain more comprehensive information and thus make more accurate decisions. At the same time, the data barriers between different fields and platforms can be broken, realizing data sharing and fusion, and promoting the effective utilization of data resources.

[0167] 2. Enhance system robustness. Multi-source data fusion reduces the dependence on a single data source. Even if a certain data source has problems, the information of other data sources can still support the system, thereby improving the stability and robustness of the system.

[0168] 3. Improve data quality. Data preprocessing improves the accuracy and integrity of data by removing problems such as noise, outliers, and missing values. This helps to reduce errors in the modeling process and improve the accuracy and generalization ability of the model.

[0169] 4. Reduce the computational complexity. Data preprocessing can perform operations such as normalizing and dimensionality reduction on the original data, reducing the dimensionality and complexity of the data. This helps to reduce the amount of computation, improve the computational speed and efficiency.

[0170] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.

[0171] Based on the same inventive concept, the embodiments of the present application further provide an account behavior determination device for implementing the above-mentioned account behavior determination method. The implementation solutions provided by this device to solve problems are similar to the implementation solutions described in the above method. Therefore, the specific limitations in one or more embodiments of the account behavior determination device provided below can refer to the limitations on the account behavior determination method in the above text, and will not be repeated here.

[0172] In an exemplary embodiment, as Figure 4 shown, an account behavior determination device is provided, including:

[0173] A multi-source data acquisition module 401, configured to acquire gateway interaction data corresponding to the gateway of the gateway deployment object, and device location data of the device account; the gateway interaction data describes the interaction situation between the device account and the gateway;

[0174] A gateway location determination module 402, configured to determine the physical location of the gateway;

[0175] A behavior analysis module 403, configured to determine a first account behavior of the device account returning to or leaving the gateway deployment object according to the physical location of the gateway and the device location data, and determine a second account behavior of the device account returning to or leaving the gateway deployment object according to the gateway interaction data;

[0176] A trusted behavior determination module 404, configured to determine a trusted account behavior of the device account with respect to the gateway deployment object according to the first account behavior and the second account behavior.

[0177] In one embodiment, the gateway location determination module 402 is configured to:

[0178] Determine the device's stay location based on the device location data; the device's stay location is the location where the stay time and the number of stays meet the preset stay conditions;

[0179] Determine the gateway interaction location of the device account based on the device location data and the gateway interaction data; the gateway interaction location is the location where the device account is located when the device account interacts with the gateway;

[0180] When the gateway interaction location matches the device's stay location, determine the gateway physical location of the gateway based on the device's stay location.

[0181] In one embodiment, the gateway location determination module 402 is configured to:

[0182] Determine multiple gateway interaction locations of the device account based on the device location data and the gateway interaction data; the gateway interaction location is the location where the device account is located when the device account interacts with the gateway;

[0183] If the number of the multiple gateway interaction locations is greater than the number threshold and the locations among the multiple gateway interaction locations match, determine the gateway physical location of the gateway based on the multiple gateway interaction locations.

[0184] In one embodiment, the behavior analysis module 403 is configured to:

[0185] Determine the distance change situation between the device account and the gateway physical location based on the gateway physical location and the device location data;

[0186] If it is determined based on the distance change situation that the device account leaves the gateway physical location and then returns to the gateway physical location after reaching a preset distance, determine the first account behavior of the device account returning to the gateway deployment object;

[0187] If it is determined based on the distance change situation that the device account leaves the gateway physical location and reaches a preset distance, determine the first account behavior of the device account leaving the gateway deployment object.

[0188] In one embodiment, the behavior analysis module 403 is configured to:

[0189] In the case of determining that the device account performs an online operation on the gateway according to the gateway interaction data, determine the online time corresponding to the online operation and the return time when the device account last returns to the gateway deployment object;

[0190] Determine a first distance change situation between the device account and the physical location of the gateway according to the device location data between the time when the behavior occurs and the online time, and the physical location of the gateway; the first distance change situation is used to determine whether the device account has a first account behavior of returning to the gateway deployment object.

[0191] When it is determined according to the gateway interaction data that the device account performs a logout operation on the gateway, determine the logout time corresponding to the logout operation.

[0192] Determine a second distance change situation between the device account and the physical location of the gateway according to the device location data within a preset time after the logout time, and the physical location of the gateway; the second distance change situation is used to determine whether the device account has a first account behavior of leaving the gateway deployment object.

[0193] In one embodiment, the behavior analysis module 403 is configured to:

[0194] If it is determined according to the gateway interaction data that the device account performs a login operation on the gateway and the device account maintains the online state for a preset time threshold, determine a second account behavior of the device account returning to the gateway deployment object.

[0195] If it is determined according to the gateway interaction data that the device account performs a logout operation on the gateway and the device account maintains the offline state for a preset time threshold, determine a second leaving behavior of the device account leaving the gateway deployment object.

[0196] Each module in the above account behavior determination device can be implemented in whole or in part by software, hardware, and their combination. The above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0197] In an exemplary embodiment, a computer device is provided. The computer device can be a server, and its internal structure diagram can be as Figure 5As shown in the figure. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store gateway interaction data and device location data. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals through a network connection. When the computer program is executed by the processor, it implements an account behavior determination method.

[0198] Those skilled in the art can understand that Figure 5 the structure shown in the figure is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0199] In one embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory. When the processor executes the computer program, the steps in the above method embodiments are implemented.

[0200] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by the processor, the steps in the above method embodiments are implemented.

[0201] In one embodiment, a computer program product is provided, including a computer program. When the computer program is executed by the processor, the steps in the above method embodiments are implemented.

[0202] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with relevant regulations.

[0203] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in the present application can be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, data processing logics based on quantum computing, artificial intelligence (AI) processors, etc., without limitation.

[0204] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in the present application.

[0205] The above-described embodiments merely represent several implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all fall within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims

1. A method for determining account behavior, characterized in that: The method comprises: Obtaining gateway interaction data corresponding to a gateway of a gateway deployment object and device location data of a device account; the gateway interaction data describes the interaction between the device account and the gateway; determining a gateway physical location of the gateway; Determine, based on the gateway physical location and the device location data, a first account behavior of the device account returning to or leaving the gateway deployment object, and, based on the gateway interaction data, determine a second account behavior of the device account returning to or leaving the gateway deployment object; A trusted account behavior of the device account for the gateway deployment object is determined according to the first account behavior and the second account behavior.

2. The method according to claim 1, characterized in that The determining of the physical location of the gateway comprises: Determine the device's stop location according to the device location data; the device's stop location is a location where the stop time and stop number meet preset stop conditions; Determine the gateway interaction location of the device account according to the device location data and the gateway interaction data; the gateway interaction location is the location of the device account when the device account interacts with the gateway; When the gateway interaction location matches the device stay location, the gateway physical location of the gateway is determined according to the device stay location.

3. The method according to claim 1, characterized in that: The determining of the physical location of the gateway comprises: Determine multiple gateway interaction locations of the device account according to the device location data and the gateway interaction data; the gateway interaction location is the location of the device account when the device account interacts with the gateway; If the number of the multiple gateway interaction positions is greater than the number threshold and the positions of the multiple gateway interaction positions match, the gateway physical position of the gateway is determined according to the multiple gateway interaction positions.

4. The method according to claim 1, characterized in that: The determining, according to the gateway physical location and the device location data, a first account behavior of the device account returning to or leaving the gateway deployment object includes: Determine, based on the physical location of the gateway and the device location data, a change in the distance between the device account and the physical location of the gateway; If it is determined according to the distance change that the device account leaves the physical location of the gateway to reach a preset distance and then returns to the physical location of the gateway, then a first account behavior of the device account returning to the gateway deployment object is determined; If it is determined, based on the distance change, that the device account has left the physical location of the gateway by a preset distance, then a first account behavior of the device account leaving the gateway deployment object is determined.

5. The method according to claim 4, characterized in that The determining, according to the physical location of the gateway and the device location data, a change in the distance between the device account and the physical location of the gateway includes: In a case where it is determined according to the gateway interaction data that the device account performs an online operation on the gateway, determining an online time corresponding to the online operation and a return time when the device account last returned to the gateway deployment object; Determine, based on the device location data between the time when the behavior occurred and the time when the behavior went online, and the physical location of the gateway, a first distance change between the device account and the physical location of the gateway; the first distance change is used to determine whether the device account has a first account behavior of returning to the gateway deployment object; In a case where it is determined according to the gateway interaction data that the device account performs an offline operation on the gateway, determining an offline time corresponding to the offline operation; Based on the device location data within a preset time after the offline time and the physical location of the gateway, a second distance change between the device account and the physical location of the gateway is determined; the second distance change is used to determine whether the device account has a first account behavior of leaving the gateway deployment object.

6. The method according to any one of claims 1 to 5, characterized in that Determining, according to the gateway interaction data, a second account behavior of the device account returning to or leaving the gateway deployment object includes: If it is determined according to the gateway interaction data that the device account performs an online operation on the gateway and the device account maintains the online state for a preset time threshold, then determining a second account behavior of the device account returning to the gateway deployment object; If it is determined according to the gateway interaction data that the device account performs an offline operation on the gateway and the device account maintains the offline state for a preset time threshold, a second leaving behavior of the device account leaving the gateway deployment object is determined.

7. An account behavior determination device, characterized in that: The device comprises: A multi-source data acquisition module, used to acquire gateway interaction data corresponding to a gateway of a gateway deployment object and device location data of a device account; the gateway interaction data describes the interaction between the device account and the gateway; A gateway location determination module, used to determine the gateway physical location of the gateway; a behavior analysis module, configured to determine a first account behavior of the device account returning to or leaving the gateway deployment object based on the gateway physical location and the device location data, and to determine a second account behavior of the device account returning to or leaving the gateway deployment object based on the gateway interaction data; A trusted behavior determination module is used to determine the trusted account behavior of the device account for the gateway deployment object according to the first account behavior and the second account behavior.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images