Association relation determination method and device and storage medium

Abstract

The invention discloses an association relationship determination method, equipment and a storage medium. The method comprises the following steps: acquiring a shooting content association degree between every two pieces of equipment in a plurality of pieces of equipment in a preset area; a to-be-determined device is searched from the multiple devices, the correlation degree between the to-be-determined device and the shooting content of a first correlation device meets a first correlation degree requirement, and the first correlation device is a device which has been determined to have a correlation relation with a target interest point in the preset area; and analyzing a first reference device of which the association degree with the shooting content of the to-be-determined device meets a second association degree requirement, so as to determine whether the to-be-determined device and the target interest point have an association relationship or not. In this way, the efficiency and accuracy of association relation determination can be improved.

Description

Technical Field

[0001] This application relates to the field of big data analytics technology, specifically to a method, device, and storage medium for determining relationships. Background Technology

[0002] With the increasing prevalence of intelligent sensing devices, the importance of sensing data, as a core component of smart city construction, is becoming increasingly prominent. By analyzing various types of sensing data collected by these devices using intelligent algorithms, key information such as the location of target entities and their high-frequency activity areas can be obtained. Therefore, clarifying the relationship between intelligent sensing devices and various locations is crucial.

[0003] However, many POIs (Points of Interest) currently exist as single-point coordinates without clearly defined latitude and longitude coverage areas. This leads to inaccurate associations between POIs and smart sensing devices, and there is currently a lack of effective algorithmic mechanisms to automatically link POIs with smart sensing devices. Therefore, establishing an efficient and accurate association mechanism between smart sensing devices and POIs has become a critical issue that urgently needs to be addressed in the construction of smart cities. Summary of the Invention

[0004] To address the aforementioned technical problems, this application provides a method, apparatus, and storage medium for determining association relationships, thereby improving the efficiency and accuracy of determining the association relationships between intelligent sensing devices and Points of Interest (POIs).

[0005] According to one embodiment of the present invention, a method for determining an association relationship is provided, comprising: Obtain the correlation between the captured content of each pair of devices within a preset area; From the plurality of devices, a device to be determined is found whose content capture content of the first associated device meets the first association requirement. The first associated device is a device that has been determined to have an association with the target point of interest in the preset area. Analyze a first reference device whose content captured by the device to be determined meets the second correlation requirement, in order to determine whether there is a correlation between the device to be determined and the target point of interest.

[0006] To solve the above-mentioned technical problems, one technical solution adopted in this application is to provide an electronic device, including a memory and a processor, wherein the memory is used to store a computer program, and when the computer program is executed by the processor, it is used to implement the method for determining the association relationship in the above-mentioned technical solution.

[0007] To solve the above-mentioned technical problems, one technical solution adopted in this application is to provide a computer-readable storage medium for storing a computer program, which, when executed by a processor, is used to implement the method for determining the association relationship in the above-mentioned technical solution.

[0008] Through the above scheme, the method for determining the association relationship provided in this application obtains the correlation degree between the shooting content of each pair of devices in a preset area, searches for devices to be determined that meet the first correlation degree requirement of the first associated device that has been determined to be associated with the target point of interest in the preset area, and analyzes the first reference device whose shooting content correlation degree meets the second correlation degree requirement of the device to be determined, so as to determine whether there is an association relationship between the device to be determined and the target point of interest. In this way, by searching for devices to be determined that may be associated with the target point of interest through the shooting correlation degree between each pair of devices, and then by analyzing the first reference device that may be associated with the device to be determined, the association relationship between the device to be determined and the target point of interest is determined, thereby more efficiently and accurately determining several devices that have an association relationship with the target point of interest. Attached Figure Description

[0009] 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 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. Wherein: Figure 1 This is a flowchart illustrating an embodiment of the method for determining the association relationship provided in this application; Figure 2 This is a flowchart illustrating another embodiment of the method for determining the association relationship provided in this application; Figure 3 This is a flowchart illustrating the process of determining the association between a POI and a device, as provided in this application. Figure 4 This is a schematic diagram of a simulated POI region provided in this application; Figure 5 This is a schematic diagram of a user interface provided in this application; Figure 6 This is a schematic diagram of another user interface provided in this application; Figure 7 This is a schematic diagram of the structure of an embodiment of the electronic device provided in this application; Figure 8 This is a schematic diagram of an embodiment of the computer-readable storage medium provided in this application. Detailed Implementation

[0010] The present application will now be described in further detail with reference to the accompanying drawings and embodiments. It should be particularly noted that the following embodiments are for illustrative purposes only and do not limit the scope of the application. Similarly, the following embodiments are only some, not all, embodiments of the present application, and all other embodiments obtained by those skilled in the art without inventive effort are within the scope of protection of the present application.

[0011] In this application, the reference to "embodiment" means that a specific feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0012] It should be noted that the terms "first," "second," etc., used in this application are for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Therefore, a feature defined with "first," "second," etc., may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0013] Because the raw data collected by devices (such as video data captured by devices, environmental data recorded by sensors, etc.) itself lacks spatial attributes, only including event and entity features, it is impossible to determine where the data comes from or which specific scenario it corresponds to. Points of Interest (POIs), on the other hand, are geographically defined locations with clear functions. After a device is associated with a POI, the raw data can be labeled with the POI location, giving the collected data spatial meaning. This allows for analysis based on the data collected by the device, leading to the extraction of useful information.

[0014] However, devices are physical entities deployed within an Area of ​​Interest (AOI) or on a Point of Interest (POI) for sensing, execution, computation, or communication. An AOI is a defined geographical area or spatial region in geospatial space, essentially a "surface entity" enclosed by multiple latitude and longitude coordinates. A POI is a point or object in geospatial space with a specific function or meaning, essentially a "point entity" corresponding to latitude and longitude coordinates. Based on the location information of devices or POIs and the extent information of AOIs, the relationships between devices and AOIs, and between POIs and other AOIs, can be initially inferred. However, since both devices and POIs are single-point coordinates, the relationships between devices and POIs cannot be inferred solely from their location information.

[0015] Therefore, this application provides a method for determining association relationships. By obtaining the correlation degree of shooting content between each pair of devices in a preset area, the method searches for devices to be determined that meet the first correlation degree requirement of the first associated device that has been determined to be associated with the target point of interest in the preset area. The method also analyzes first reference devices that meet the second correlation degree requirement of the shooting content correlation degree of the devices to be determined, thereby determining whether there is an association relationship between the devices to be determined and the target point of interest. In this way, by searching for devices to be determined that may be associated with the target point of interest through the shooting correlation degree between each pair of devices, and then by analyzing the first reference devices that may be associated with the devices to be determined, the association relationship between the devices to be determined and the target point of interest is determined, thereby more efficiently and accurately determining several devices that have an association relationship with the target point of interest.

[0016] Please see Figure 1 , Figure 1 This is a flowchart illustrating an embodiment of the method for determining the association relationship provided in this application. It should be noted that if substantially the same result is obtained, this embodiment does not necessarily reflect that outcome. Figure 1 The illustrated process sequence is limited. For example... Figure 1 As shown, this embodiment includes: S110: Obtain the correlation between the shooting content of each pair of devices within a preset area.

[0017] A specific geographical area is predefined as the preset region, which is the area where the relationship between the device and the point of interest needs to be analyzed. Multiple devices within the preset region are then acquired. These devices are intelligent sensing devices, such as cameras or sensors, deployed within the preset region to collect the content captured within the region.

[0018] Obtain the correlation between the captured content of each pair of devices within a preset area in order to analyze the correlation between multiple devices.

[0019] In one embodiment, trajectory information of each target object generated in a preset area is acquired, and the transfer device pairs of trajectory information are statistically analyzed to obtain the number of device transfers between each pair of devices, which is used as the correlation degree of the captured content between each pair of devices. The trajectory information includes several devices that sequentially captured images of the target object in a time sequence, and the transfer device pair consists of two devices that captured images of the target object sequentially and at adjacent times.

[0020] In one embodiment, feature comparison can also be used to determine whether the captured content contains the same entity or a strongly related event. Then, based on the matching results of the same entity or strongly related events between the two devices, the correlation degree is calculated in combination with dimensions such as time, space and features, which serves as the correlation degree of the captured content between the two devices.

[0021] S120: From multiple devices, find the device to be determined whose content relevance to the first associated device meets the first relevance requirement.

[0022] For each target point of interest, identify potential devices that may be related to the target point of interest, and further analyze these potential devices to determine whether there is a relationship between each potential device and the target point of interest. This will enable the accurate and comprehensive acquisition of all devices that are related to the target point of interest.

[0023] Devices that have been identified as having a correlation with target points of interest within a preset area are defined as first associated devices. After obtaining the correlation degree between the captured content of each pair of devices, the devices to be determined are searched from the multiple devices to find those whose captured content correlation degree with the first associated devices meets the first correlation degree requirement.

[0024] In one embodiment, the content relevance is characterized by the number of device transfers between any two devices. The first relevance requirement is the number of devices with the highest number of device transfers to the first associated device. Devices that have a content transfer relationship with the first associated device are identified, and the number of transfers between the first associated device and each device with a transfer relationship is counted. At least two devices with the most transfers to the first associated device are identified as devices that meet the first relevance requirement. Devices among the multiple devices whose content relevance to the first associated device meets the first relevance requirement are identified as devices to be determined.

[0025] In one embodiment, before searching for a device to be determined from multiple devices that meets the first correlation requirement for the content captured by the first associated device, a first associated device in a preset area that is associated with the target point of interest and the target point of interest is determined.

[0026] In one example, several points of interest (POIs) and multiple devices that have spatial relationships with the same POP (Planet of Interest) in a preset area are acquired. This allows for the identification of a target POP within the same POP and the discovery of a first associated device that has a relationship with that target POP. The spatial relationships are determined based on the location information of the POP, the several POPs, and the multiple devices. The target POP is any one of the several POPs.

[0027] In one embodiment, the association between a point of interest and a device can be determined by the name similarity between the point of interest and the device. For example, the name similarity between several points of interest and multiple devices is obtained respectively. In response to the name similarity between a point of interest and a device being greater than a second similarity threshold, it is determined that there is an association between the point of interest and the device, and the device is designated as the first associated device of the point of interest.

[0028] In some cases, if there are multiple points of interest with the same name in a surface of interest, the first associated device with the point of interest can be determined by distance relationship. For example, in response to multiple points of interest with the same device whose name similarity is greater than a second similarity threshold, the nearest point of interest is found from the multiple points of interest, and it is determined that the same device is associated with the nearest point of interest, and the device is regarded as the first associated device of the nearest point of interest.

[0029] In one example, if there are multiple interest surfaces within a preset area, several interest points and several devices can be classified into corresponding interest surfaces based on the location information of all interest surfaces, interest points, and devices within the preset area. This will allow for subsequent analysis of several interest points and several devices within the same interest surface, improving the efficiency of determining the correlation.

[0030] In one embodiment, the location information of all surfaces of interest, all points of interest, and all devices within a preset area is acquired. Based on this location information, the positional relationships between each point of interest and each device within the preset area and each surface of interest are compared. In response to a point of interest or device being located within the location range of a surface of interest, a spatial association between the point of interest or device and the surface of interest is determined. In some embodiments, since the content captured by the device is not limited to the current location of the device, there may be cases where the device's location is not within the area range of a surface of interest, but the captured content overlaps with the area range of the surface of interest. Therefore, in response to a device's location not being within the location range of a surface of interest and the device's maximum acquisition distance being greater than the straight-line distance between the device and the surface of interest, a spatial association between the device and the surface of interest can also be determined.

[0031] S130: Analyze the first reference device whose correlation with the content captured by the device to be determined meets the second correlation requirement, so as to determine whether there is a correlation between the device to be determined and the target point of interest.

[0032] The second correlation requirement is the number of devices with the highest number of device transfers to the device to be determined. The first reference devices are at least two devices with the highest number of device transfers to the device to be determined. By analyzing the correlation between each first reference device and the target point of interest, it is determined whether there is a correlation between the device to be determined and the target point of interest.

[0033] In one embodiment, a device whose correlation with the content captured by the device to be determined meets a second correlation requirement is used as a first reference device. The system then determines whether the first reference device is a first associated device, obtaining a determination result. Based on the determination result, it is determined whether there is a correlation between the device to be determined and the target point of interest.

[0034] In one example, there are at least two first reference devices. The determination results of the first reference devices and the determination results of the association relationships may include the following situations: In response to the fact that each first reference device has an association relationship with the target point of interest, it is determined that the device to be determined has an association relationship with the target point of interest; In response to the fact that each first reference device has no association relationship with the target point of interest and other points of interest, it is determined that the device to be determined has no association relationship with the target point of interest; In response to the fact that each first reference device has an association relationship with other points of interest, the association relationship analysis between the device to be determined and the target point of interest is skipped; In response to the fact that some first reference devices have an association relationship with the target point of interest and other first reference devices have no association relationship with the target point of interest, the device to be determined is determined as a candidate associated device of the target point of interest, and based on the target association confidence of the candidate associated device and the target point of interest, it is determined whether the candidate associated device has an association relationship with the target point of interest.

[0035] The target association confidence score between candidate associated devices and target points of interest can be obtained through the following implementation: based on the locational relationship, name similarity, and content relevance between the candidate associated devices and the target points of interest, multiple association confidence scores are obtained. These multiple association confidence scores are then comprehensively analyzed to obtain the target association confidence score between the candidate associated devices and the target points of interest. In one implementation, the multiple association confidence scores include at least two of the following: (1) A first association confidence level is determined based on the positional relationship between the candidate associated device and the regional range of the target point of interest. For example, in response to the candidate associated device being located within the regional range, the first association confidence level is determined as a first confidence level value. The regional range of the target point of interest is determined based on the positional information of each second associated device that is associated with the target point of interest. That is, by obtaining the positional information of each second associated device that is currently associated with the target point of interest, the spatial range formed by connecting all the second associated devices is used to determine the regional range corresponding to the target point of interest.

[0036] (2) The second association confidence is determined based on the name similarity between the candidate associated device and the target point of interest. For example, in response to the name similarity between the candidate associated device and the target point of interest being greater than the first similarity threshold, the second association confidence is determined as the second confidence value.

[0037] (3) The third association confidence level is determined based on the second reference device whose content association with the candidate associated device meets the third association requirement. For example, the content association includes the number of device transfers between each pair of devices, and the third association requirement is the third number of devices with the highest number of device transfers with the candidate associated device. Preferably, the third number is two. The two devices with the most device transfers with the candidate associated device are used as the second reference devices, including the first device and the second device of the candidate associated device, wherein the content association between the first device and the candidate associated device is higher than the content association between the second device and the candidate associated device.

[0038] In one embodiment, if the device to be determined is a candidate associated device of the target point of interest, in response to the fact that each of the second reference devices of the candidate associated devices has an association relationship with the target point of interest, it is determined that the candidate associated device has an association relationship with the target point of interest.

[0039] In one embodiment, if the device to be determined is a candidate associated device of the target point of interest, and not all the second reference devices of the candidate associated devices are associated with the target point of interest, then the third association confidence of the candidate associated device is determined. The third association confidence level is determined by the association relationship between the first and second devices and the target point of interest and / or other points of interest. This may include several scenarios: If the first device has an association relationship with the target point of interest, and the second device has no association relationship with the target point of interest or any other point of interest, the third association confidence level is determined as the third confidence level value; if the first device has an association relationship with the target point of interest, and the second device has no association relationship with the target point of interest but has an association relationship with other points of interest, the third association confidence level is determined as the fourth confidence level value; if the first device has no association relationship with the target point of interest or any other point of interest, and the second device has an association relationship with the target point of interest, the third association confidence level is determined as the fifth confidence level value; if the first device has no association relationship with the target point of interest but has an association relationship with other points of interest, and the second device has an association relationship with the target point of interest, the third association confidence level is determined as the sixth confidence level value.

[0040] After obtaining multiple association confidence scores for candidate associated devices, these scores are weighted and summed to obtain the target association confidence score between the candidate associated device and the target point of interest. This target association confidence score is used to determine whether the candidate associated device and the target point of interest are associated, i.e., whether there is an association between the device to be determined and the target point of interest. For example, if the target association confidence score of a candidate associated device is greater than a preset similarity threshold, it is determined that the candidate associated device (i.e., the device to be determined) is associated with the target point of interest; otherwise, it is determined that there is no association between the device to be determined and the target point of interest.

[0041] In one embodiment, after determining the association between all devices to be determined and the target point of interest, all associated devices that are associated with the target point of interest are obtained, and the spatial range formed by connecting all associated devices is determined as the area range of the target point of interest. Based on the area range of the target point of interest, the association between devices and the target point of interest can be more accurately determined, providing an analytical basis for practical application scenarios.

[0042] Furthermore, this application also provides a system and interactive interface capable of interacting with users to view and edit the association between points of interest (POIs) and devices. In one embodiment, in response to a user's request to view an input POI, the system can display the area of ​​the input POI on a map, as well as third-party associated devices and the captured content from those third-party associated devices. The area of ​​the input POI can be formed based on the locations of all third-party associated devices. In one embodiment, in response to a user's modification of the association of a third-party associated device, the system adjusts the association between the third-party associated device and the input POI. For example, a user can cancel the association between a third-party associated device and the input POI through the editing interface, or add an association between a device and the input POI. After the change takes effect, the system can automatically change the area of ​​the input POI.

[0043] Please see Figure 2 , Figure 2 This is a flowchart illustrating another embodiment of the method for determining the association relationship provided in this application. It should be noted that if substantially the same result is obtained, this embodiment does not necessarily reflect that outcome. Figure 2 The illustrated process sequence is limited. For example... Figure 2 As shown, this embodiment includes: S210: Obtain the spatial relationships between AOI, POI and devices within a specified area.

[0044] There may be one or more AOIs (Area of ​​Interest) within a specified area. To improve the efficiency of determining the relationship between POIs (Points of Interest) and devices, POIs and devices within the same AOI range are acquired separately to narrow down the matching range of POIs and devices, thereby finding the relationship between the two more quickly.

[0045] This process retrieves information on all devices within a specified area, including device ID, latitude and longitude, and device name. It also retrieves information on all Points of Interest (POIs) within the specified area, including POI name and latitude and longitude. Finally, it retrieves information on Automated Area Units (AOIs) within the specified area, including AOI name and AOI latitude and longitude region. Based on the AOI's latitude and longitude region, the POIs' latitude and longitude, and the devices' latitude and longitude, it associates the POIs and devices located within the AOI's latitude and longitude region with that AOI, obtaining all POI and device information within each AOI.

[0046] It should be noted that since the devices have a certain acquisition distance, for some devices whose latitude and longitude are outside the AOI latitude and longitude area but are relatively close to the AOI, the maximum acquisition distance of the device is determined to be d. If the maximum acquisition distance of the device is greater than the straight-line distance between the device and the AOI, that is, the acquisition content of the device overlaps with the area range of the AOI, the device can also be classified into the AOI and matched with the POIs in the AOI.

[0047] S220: Determine the association between POIs and devices within the same AOI.

[0048] Since the latitude and longitude of a device are both single points, and the latitude and longitude of a POI are also single points, and it is impossible to determine the area range of a POI, and there may be multiple layers within an AOI, it is difficult to determine the relationship between a device and a POI using only latitude, longitude and / or distance.

[0049] In this embodiment, the association between a Point of Interest (POI) and a device is determined for each AOI within a preset area. This association can be determined by comprehensively considering the text similarity between the POI and the device, the transfer between devices, and the latitude and longitude between the device and the POI. Please refer to [link to relevant documentation]. Figure 3 , Figure 3 This application provides a flowchart illustrating the process of determining the association between a Point of Interest (POI) and a device. The specific steps include: S221: Initially associate POIs with devices based on text similarity.

[0050] The device name and POI name are segmented into words. The segmentation method includes, but is not limited to, jieba segmentation. After segmentation, the similarity between the device and the POI is calculated. If the similarity is greater than the preset similarity threshold, it can be determined that the device and the POI are associated. Several devices that are associated with the POI are regarded as high-confidence associated devices corresponding to the POI.

[0051] In some cases, there may be multiple POIs with the same name within an AOI. For example, a large shopping mall may have multiple stores with the same name. Therefore, in order to more accurately associate devices with POIs, the distance between the device and each POI can be calculated. If a device can be matched with multiple POIs, the POI closest to the device can be used to associate the device with the POI.

[0052] In other cases, within a POI's latitude and longitude range, some devices may not be associated with the POI, but their captured content is related to it—for example, they may capture images of objects entering or leaving the POI. These devices may also need to be associated with the POI. Therefore, for devices that may have a relationship, it is necessary to further explore the relationship between them and the POI. For example, the results of exploring the relationships between devices can provide an analytical basis for matching devices with POIs.

[0053] S222: Determine the target POI and obtain trajectory information related to the target POI.

[0054] For devices that cannot be associated with a POI but may be associated with it, the POIs that may be associated with the device are identified as target POIs. The trajectory information related to the target POI is obtained, including the device collection information of the target object entering and leaving the target POI. Based on the trajectory information related to the target POI, the transfer relationship between devices is mined, thereby determining whether the low-confidence associated devices that may be associated are associated with the target POI.

[0055] S223: Based on trajectory information, mine the transfer relationships between devices to identify low-confidence associated devices.

[0056] In this embodiment, based on the transfer relationships between trajectory information mining devices, low-confidence associated devices are identified. The algorithm for mining transfer relationships between devices includes, but is not limited to, utilizing the information collected by the devices on the target object. For example, if there is a target object, the trajectory information recently collected on that target object is... Where 'c' corresponds to the data acquisition device and 't' corresponds to the data acquisition time, the number of device transfers between pairs of devices can be analyzed based on the trajectory information. For example, based on this trajectory information after... The next device is The number of times The previous device was The number of times The system sequentially analyzes the number of transfers between all devices for all target objects, and accumulates the device transfer counts for all target objects. It also obtains the transfer details between each pair of devices. For example, in this trajectory information, the device... and equipment With equipment There is a transition relationship, and the number of transitions are 2 and 1 respectively.

[0057] For each high-confidence associated device with a target POI, obtain the number of transfers between the next and previous transfer devices and the corresponding devices. For example, if there is a device... With a POI location There is a high-confidence correlation between mining and equipment. Equipment that has a transfer relationship but no high-confidence association with the POI location, such as equipment and Further analysis of the equipment and The top two devices with the most transfers, for example, device The second most frequently transferred device is and Further analysis and Do these two devices belong to the same POI (Point of Interest)? If they belong to the same target POI, then the device... This is a high-confidence device for the POI location. If and If neither device belongs to the high-confidence associated devices of the target POI, then the device This means there is no association between the device and the target POI. If the two devices... and If associated with different POIs, then the device will not be affected. Further analysis will be conducted. If both devices... and If one of them can be associated with the target POI, then the device Low-confidence associated devices of the target POI will proceed to the next stage of analysis.

[0058] S224: Calculate the confidence level of the association between low-confidence associated devices and determine the association between low-confidence associated devices and the target POI.

[0059] After identifying all low-confidence associated devices for each target POI in step S223, the association confidence of these devices is calculated to determine the relationship between them and the target POI. The calculation of the association confidence is related to factors such as the locational relationship between the device and the target POI, name similarity, and relevance of the captured content. By calculating multiple association confidences of low-confidence associated devices under different factors, the association relationship between low-confidence associated devices and the target POI is comprehensively analyzed.

[0060] In this embodiment, please refer to Figure 4 , Figure 4 This is a schematic diagram of a simulated POI area provided in this application. The area of ​​each target POI is simulated based on all the high-confidence associated devices currently corresponding to each target POI. Here, p1 represents a target POI, and c1, c2, c3, c4, and c5 are the high-confidence associated devices of the POI. The connection between these high-confidence associated devices can be used to obtain a maximal convex polygon, which is defined as the area of ​​p1.

[0061] Determine whether the latitude and longitude of a low-confidence associated device at the target POI are within the area of ​​the target POI. If the latitude and longitude of the low-confidence associated device are within the area of ​​the target POI, determine the association confidence between the low-confidence associated device and the target POI. .

[0062] Calculate the name similarity between the low-confidence associated devices and the target POI in the current analysis to obtain the association confidence between the low-confidence associated devices and the target POI. .

[0063] Based on trajectory information, we find the top 1 and top 2 devices that have the most transfer relationships with low-confidence associated devices and have the most transfers. We then analyze whether these top 1 and top 2 devices are high-confidence associated devices with the target POI, thereby determining the association confidence of the low-confidence associated devices. Specifically: if the top 1 device is a high-confidence associated device with the target POI, and the top 2 device is not a high-confidence associated device with the target POI, nor is it a high-confidence associated device with any other POI, then the association confidence between the low-confidence associated device and the target POI is determined to be [value missing]. If the top 1 device is a high-confidence associated device with the target POI, and the top 2 device is not a high-confidence associated device with the target POI, but is a high-confidence associated device with other POIs, then the association confidence between the low-confidence associated device and the target POI is determined to be 0. If the TOP1 device is not a high-confidence associated device with the target POI, and is not a high-confidence associated device with any other POI, and the TOP2 device is a high-confidence associated device with the target POI, then the association confidence between the low-confidence associated device and the target POI is determined to be 1. If the TOP1 device is not a high-confidence associated device with the target POI, but is associated with other high-confidence associated devices with other POIs, and the TOP2 device is a high-confidence associated device with the target POI, then the association confidence between the low-confidence associated device and the target POI is determined to be 1. .

[0064] S225: Obtain high-confidence associated devices for the target POI and determine the geographical range of the target POI.

[0065] For each low-confidence associated device, after obtaining its multiple association confidence scores, the target association confidence score of the low-confidence associated device can be calculated comprehensively to determine whether it is a high-confidence associated device of the corresponding target POI. For example, the target association confidence score between the low-confidence associated device and the target POI is calculated. ,like If the low-confidence associated device is a high-confidence associated device for the target POI area, then it is not.

[0066] The above steps can be used to obtain all high-confidence associated devices for each POI in each AOI, and the maximum area range corresponding to each POI can be determined by simulating the high-confidence associated devices of all POIs.

[0067] S230: The association between user interface interaction points of interest and the device.

[0068] Please see Figure 5 , Figure 5 This is a schematic diagram of a user interface provided in this application. As shown in the figure, users can search for the location they want to view based on the name of the POI, and click on the corresponding location in the location list to display the area range of the POI formed by the high-confidence associated devices based on the POI location on the map, as well as display all the high-confidence associated devices associated with the POI area. Clicking on the device can display the corresponding device name and support viewing the recently collected content under the device.

[0069] After viewing the data collected by a device, users can also manually edit whether a device belongs to a specific POI (Point of Interest). For an example, please refer to [link to relevant documentation]. Figure 6 , Figure 6This is a schematic diagram of another user interface provided in this application. Clicking on a device whose association with a POI needs to be changed allows users to change the association between the device and the location to "within the location," "around the location," "exit," and "entrance." It's important to note that here, "exit" and "entrance" are defined as "within the location," while "around the location" is defined as "outside the location." The changes to the POI associated with a device take effect immediately and update the POI's area range. Users can also manually search for the desired device among all devices to associate with a POI.

[0070] Please see Figure 7 , Figure 7 This is a schematic diagram of the structure of an embodiment of the electronic device provided in this application. The electronic device 60 includes a memory 61 and a processor 62 that are interconnected. The memory 61 is used to store a computer program. When the computer program is executed by the processor 62, it is used to implement the method for determining the association relationship in the above embodiment.

[0071] The methods described in the above embodiments can exist in the form of a computer program; therefore, this application proposes a computer-readable storage medium. Please refer to [link / reference needed]. Figure 8 , Figure 8 This is a schematic diagram of an embodiment of a computer-readable storage medium provided in this application. The computer-readable storage medium 80 is used to store a computer program 81, which can be executed to implement the method for determining the association relationship in the above embodiment.

[0072] The computer-readable storage medium 80 can be any medium capable of storing program code, such as a server, USB flash drive, external hard drive, read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0073] If the technical solution of this application involves personal information, the product using this technical solution has clearly informed the user of the personal information processing rules and obtained the user's voluntary consent before processing the personal information. If the technical solution of this application involves sensitive personal information, the product using this technical solution has obtained the user's separate consent before processing the sensitive personal information, and also meets the requirement of "express consent". For example, at personal information collection devices such as cameras, clear and prominent signs are set up to inform users that they have entered the scope of personal information collection and that personal information will be collected. If an individual voluntarily enters the collection scope, it is deemed that they have agreed to the collection of their personal information; or on the personal information processing device, with clear signs / information informing users of the personal information processing rules, authorization is obtained from the individual through pop-up information or by asking the individual to upload their personal information; wherein, the personal information processing rules may include information such as the personal information processor, the purpose of personal information processing, the processing method, and the types of personal information processed.

[0074] The above description is merely an embodiment of this application and does not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A method for determining an association relationship, characterized in that, The method includes: Obtain the correlation between the captured content of each pair of devices within a preset area; From the plurality of devices, a device to be determined is found whose content capture content of the first associated device meets the first association requirement. The first associated device is a device that has been determined to have an association with the target point of interest in the preset area. Analyze a first reference device whose content captured by the device to be determined meets the second correlation requirement, in order to determine whether there is a correlation between the device to be determined and the target point of interest.

2. The method according to claim 1, characterized in that, The step of obtaining the correlation between the captured content of each pair of devices within a preset area includes: Acquire trajectory information generated by each of the target objects in the preset area, wherein the trajectory information includes a number of devices that sequentially captured images of the target objects in a time sequence; The number of device transfers between the two pairs of devices is statistically analyzed to obtain the correlation degree of the shooting content between the two pairs of devices. The two pairs of devices are two devices that have captured the target object successively and whose shooting times are adjacent.

3. The method according to claim 2, characterized in that, The first correlation requirement is the number of devices that have the highest number of device transfers with the first associated device; And / or, the second correlation requirement is the second number of devices that have the highest number of device transfers to the device to be determined.

4. The method according to any one of claims 1 to 3, characterized in that, The analysis of a first reference device whose correlation with the content captured by the device to be determined meets the second correlation requirement is used to determine whether there is a correlation between the device to be determined and the target point of interest, including: The device whose correlation with the content captured by the device to be determined meets the second correlation requirement is used as the first reference device; Determine whether the first reference device is the first associated device, and obtain the determination result; Based on the judgment result, it is determined whether there is a correlation between the device to be determined and the target point of interest.

5. The method according to claim 4, characterized in that, The first reference device is at least two, and the step of determining whether there is a correlation between the device to be determined and the target point of interest based on the judgment result includes at least one of the following steps: In response to the fact that each of the first reference devices has an association with the target point of interest, it is determined that the device to be determined has an association with the target point of interest; In response to the fact that there is no association between each of the first reference devices and the target point of interest as well as other points of interest, it is determined that there is no association between the device to be determined and the target point of interest; In response to the existence of associations between each of the first reference devices and other points of interest, the association analysis between the device to be determined and the target point of interest is skipped; In response to a situation where a portion of the first reference devices have an association with the target point of interest, and another portion of the first reference devices do not have an association with the target point of interest, the device to be determined is identified as a candidate associated device of the target point of interest, and based on the target association confidence between the candidate associated device and the target point of interest, it is determined whether the candidate associated device has an association with the target point of interest.

6. The method according to claim 5, characterized in that, Before determining whether the candidate associated device and the target point of interest have an association relationship based on the target association confidence score between the candidate associated device and the target point of interest, the method further includes: Multiple association confidence scores are obtained, wherein the multiple association confidence scores include at least two of the following: a first association confidence score determined based on the positional relationship between the candidate association device and the target point of interest's regional range; a second association confidence score determined based on the name similarity between the candidate association device and the target point of interest; and a third association confidence score determined based on a second reference device whose content association with the candidate association device meets the third association score requirement. The multiple association confidence scores are weighted and summed to obtain the target association confidence score between the candidate associated device and the target point of interest.

7. The method according to claim 6, characterized in that, Before obtaining the first association confidence score, the process also includes: Obtain the location information of each second associated device that is currently associated with the target point of interest; The spatial range formed by connecting all the second associated devices is determined as the area range corresponding to the target point of interest; And / or, obtaining the first association confidence score includes: In response to the candidate associated device being located within the area, the first association confidence level is determined to be a first confidence value; And / or, obtaining the second association confidence level, including: In response to the fact that the name similarity between the candidate associated device and the target point of interest is greater than a first similarity threshold, the second association confidence is determined as the second confidence value.

8. The method according to claim 6, characterized in that, The correlation between the shooting content of each pair of devices includes the number of device transfers between the two pairs of devices, and the third correlation requirement is the third number of devices with the highest number of device transfers to the candidate associated devices; And / or, the second reference device is at least two, the at least two second reference devices being the first device and the second device of the candidate associated device, wherein the correlation between the first device and the content captured by the candidate associated device is higher than the correlation between the second device and the content captured by the candidate associated device; obtaining the third association confidence score includes at least one of the following steps: In response to the fact that the first device has an association with the target point of interest, and the second device has no association with the target point of interest or any other point of interest, the third association confidence level is determined as the third confidence level value; In response to the first device having an association with the target point of interest, and the second device not having an association with the target point of interest but having an association with other points of interest, the third association confidence is determined as the fourth confidence value; In response to the fact that the first device has no association with the target point of interest and other points of interest, and the second device has an association with the target point of interest, the third association confidence level is determined to be the fifth confidence level value; In response to the first device having no association with the target point of interest but having an association with other points of interest, and the second device having an association with the target point of interest, the third association confidence level is determined to be the sixth confidence level value; And / or, after determining the device to be determined as a candidate associated device of the target point of interest, the method further includes: In response to the fact that each of the second reference devices of the candidate associated devices is associated with the target point of interest, it is determined that the candidate associated devices are associated with the target point of interest.

9. The method according to claim 1, characterized in that, Before searching among the plurality of devices for a device whose content relevance to the first associated device meets the first relevance requirement, the process includes: Acquire a number of points of interest and the plurality of devices that have a spatial relationship with the same interest surface of the preset area, wherein the spatial relationship is determined based on the location information of the interest surface, the number of points of interest and the plurality of devices, and the target point of interest is any one of the number of points of interest. Obtain the name similarity between the several points of interest and the multiple devices; In response to a name similarity between the point of interest and the device exceeding a second similarity threshold, it is determined that the point of interest and the device are associated, and the device is designated as the first associated device for the point of interest; and / or, In response to the existence of multiple points of interest whose name similarity to the same device is greater than the second similarity threshold, the most recent point of interest is found from the multiple points of interest, and it is determined that the same device is associated with the most recent point of interest, and is designated as the first associated device of the most recent point of interest.

10. The method according to claim 9, characterized in that, Before acquiring the plurality of points of interest and the plurality of devices that have a spatial relationship with the same area of ​​interest in the preset region, the method further includes: Obtain the location information of all interest surfaces, all interest points, and all devices within the preset area; Based on the location information, compare the positional relationships between each point of interest and each device within the preset area and each surface of interest. In response to the point of interest or the device being located within the position range of the interest surface, it is determined that the point of interest or the device has a spatial association with the interest surface; and / or, In response to the fact that the location of the device is not within the location range of the surface of interest, and the maximum acquisition distance of the device is greater than the straight-line distance between the device and the surface of interest, it is determined that there is a spatial correlation between the device and the surface of interest.

11. The method according to claim 1, characterized in that, The method further includes: In response to a user's request to view an input point of interest, the map displays the area of ​​the input point of interest and / or displays third associated devices that are related to the input point of interest; In response to a user's modification operation on the association of the third associated device, the association relationship between the third associated device and the input point of interest is adjusted.

12. An electronic device, characterized in that, The electronic device includes a processor and a memory, the processor being coupled to the memory, the processor being configured to perform one or more steps of the method for determining the association as described in any one of claims 1 to 11 based on instructions stored in the memory.

13. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that is executed by a processor to implement the steps of the method for determining the association as described in any one of claims 1 to 11.

Images