Trajectory Similarity Determination, Risk Assessment, Risk Tracing Method and Device

Abstract

The present disclosure discloses a method and apparatus for determining trajectory similarity, risk assessment, and risk tracing, which relate to the technical field of trajectory analysis. The method for determining trajectory similarity includes: determining first trajectory data and second trajectory data, where the first trajectory data includes the residence time data of the points of interest passed by a first user, and the second trajectory data includes the residence time data of the points of interest passed by a second user; determining a set of common points of interest corresponding to the first user and the second user based on the first trajectory data and the second trajectory data; and determining the trajectory similarity based on the set of common points of interest. The present disclosure takes into account the residence time data of the points of interest passed by the first user and the second user respectively, so that the trajectory similarity can be calculated in the time dimension, reducing the calculation of complex spatial distances and lowering the computational complexity. In addition, due to the consideration of the time dimension, the timeliness of the trajectory similarity can be improved, and further the accuracy of the trajectory similarity can be improved.

Description

Technical Field

[0001] The present disclosure relates to the technical field of trajectory analysis, and particularly to a method and device for determining trajectory similarity, risk assessment, and risk tracing. Background Art

[0002] The method for determining trajectory similarity has been widely used in the field of trajectory analysis, such as in the field of epidemic prevention and control. Traditional methods for determining trajectory similarity can assist epidemic prevention staff in tracing close contacts (also known as close contacts). However, usually, traditional methods for determining trajectory similarity only determine trajectory similarity based on spatial distance, which not only has a high computational complexity but also lacks timeliness, resulting in poor accuracy. Summary of the Invention

[0003] In view of this, the present disclosure provides a method and device for determining trajectory similarity, risk assessment, and risk tracing to solve the problems of high computational complexity and poor accuracy of traditional methods for determining trajectory similarity.

[0004] In a first aspect, a method for determining trajectory similarity is provided. The method for determining trajectory similarity includes: determining first trajectory data and second trajectory data, where the first trajectory data includes the residence time data of the points of interest passed by a first user, and the second trajectory data includes the residence time data of the points of interest passed by a second user; based on the first trajectory data and the second trajectory data, determining a set of common points of interest corresponding to the first user and the second user, where the set of common points of interest includes M common points of interest and the common residence time data of each of the M common points of interest, and M is a natural number; based on the set of common points of interest, determining the trajectory similarity.

[0005] In a second aspect, a method for risk assessment is provided. The method for risk assessment includes: using the method for determining trajectory similarity mentioned in the first aspect to determine the trajectory similarity corresponding to the trajectory data of a case user and the trajectory data of a user to be evaluated; based on the trajectory similarity, evaluating the close contact risk of the user to be evaluated.

[0006] In a third aspect, a method for risk tracing is provided. The method for risk tracing includes: determining the trajectory data of multiple case users respectively; for each case user among the multiple case users, using the method for determining trajectory similarity mentioned in the first aspect to respectively determine the trajectory similarity between the trajectory data of the case user and the trajectory data of the remaining case users among the multiple case users, obtaining the cumulative data of the trajectory similarity corresponding to the case user; based on the cumulative data of the trajectory similarity corresponding to each of the multiple case users, determining the source user corresponding to the multiple case users.

[0007] Fourth aspect, a trajectory similarity determination device is provided. The trajectory similarity determination device includes a trajectory determination module, a set determination module, and a similarity determination module. The trajectory determination module is used to determine first trajectory data and second trajectory data. Among them, the first trajectory data includes the residence time data of the points of interest passed by the first user, and the second trajectory data includes the residence time data of the points of interest passed by the second user. The set determination module is used to determine the common point of interest set corresponding to the first user and the second user based on the first trajectory data and the second trajectory data. Among them, the common point of interest set includes M common points of interest and the common residence time data of each of the M common points of interest, where M is a natural number. The similarity determination module is used to determine the trajectory similarity based on the common point of interest set.

[0008] Fifth aspect, a risk assessment device is provided. The risk assessment device includes a similarity determination module and a risk assessment module. The similarity determination module is used to determine the trajectory similarity corresponding to the trajectory data of the case user and the trajectory data of the user to be evaluated by using the trajectory similarity determination method mentioned in the first aspect. The risk assessment module is used to assess the close contact risk of the user to be evaluated based on the trajectory similarity.

[0009] Sixth aspect, a risk tracing device is provided. The risk tracing device includes a trajectory determination module, a similarity determination module, and a transmission source determination module. The trajectory determination module is used to determine the trajectory data of multiple case users respectively. The similarity determination module is used to, for each case user among the multiple case users, use the trajectory similarity determination method mentioned in the first aspect to respectively determine the trajectory similarity between the trajectory data of the case user and the trajectory data of the remaining case users among the multiple case users, and obtain the cumulative data of the trajectory similarity corresponding to the case user. The transmission source determination module is used to determine the transmission source users corresponding to the multiple case users based on the cumulative data of the trajectory similarity corresponding to each of the multiple case users.

[0010] Seventh aspect, a computer-readable storage medium is provided. The storage medium stores instructions, and when the instructions are executed, the methods mentioned in the first aspect to the third aspect above can be implemented.

[0011] Eighth aspect, a computer program product is provided, including instructions, and when the instructions are executed, the methods mentioned in the first aspect to the third aspect above can be implemented.

[0012] Ninth aspect, an electronic device is provided. The electronic device includes a memory and a processor. The memory stores executable code, and the processor is configured to execute the executable code to implement the methods mentioned in the first aspect to the third aspect above.

[0013] The trajectory similarity determination method provided by the embodiments of the present disclosure determines the set of common interest points corresponding to the first user and the second user by means of the first trajectory data including the residence time data of the interest points passed by the first user and the second trajectory data including the residence time data of the interest points passed by the second user, and then determines the trajectory similarity based on the set of common interest points. It can be seen that the embodiments of the present disclosure consider the residence time data of the interest points passed by the first user and the second user respectively, so that the trajectory similarity can be calculated in the time dimension based on the set of common interest points, reducing the calculation of complex spatial distances and lowering the computational complexity. In addition, due to the consideration of the time dimension, the timeliness of the trajectory similarity can be improved, and further the accuracy of the trajectory similarity can be improved. Description of the Drawings

[0014] Figure 1 The figure shows a schematic diagram of an application scenario of the trajectory similarity determination method provided by an embodiment of the present disclosure.

[0015] Figure 2 The figure shows a schematic diagram of an application scenario of the trajectory similarity determination method provided by another embodiment of the present disclosure.

[0016] Figure 3 The figure shows a schematic flowchart of the trajectory similarity determination method provided by an embodiment of the present disclosure.

[0017] Figure 4 The figure shows a schematic flowchart of the trajectory similarity determination method provided by another embodiment of the present disclosure.

[0018] Figure 5 The figure shows a schematic flowchart of the trajectory similarity determination method provided by another embodiment of the present disclosure.

[0019] Figure 6 The figure shows a schematic diagram of the trajectory similarity provided by an embodiment of the present disclosure.

[0020] Figure 7 The figure shows a schematic flowchart of the trajectory similarity determination method provided by another embodiment of the present disclosure.

[0021] Figure 8 The figure shows a schematic diagram of the positional relationship between the trajectory point set and the interest point set provided by an embodiment of the present disclosure.

[0022] Figure 9 The figure shows a schematic diagram of the data relationship between the trajectory point set and the interest point set provided by an embodiment of the present disclosure.

[0023] Figure 10 The figure shows a schematic flowchart of determining the interest points respectively matched by the trajectory points included in the trajectory point set provided by an embodiment of the present disclosure.

[0024] Figure 11 The figure shows a schematic flowchart of determining the points of interest (POIs) matched by each of the trajectory points included in a set of trajectory points provided by another embodiment of the present disclosure.

[0025] Figure 12 The figure shows a schematic diagram of grid division provided by an embodiment of the present disclosure.

[0026] Figure 13 The figure shows a schematic diagram of grid indexing provided by an embodiment of the present disclosure.

[0027] Figure 14 The figure shows a schematic flowchart of a risk assessment method provided by an embodiment of the present disclosure.

[0028] Figure 15 The figure shows a schematic flowchart of a risk tracing method provided by an embodiment of the present disclosure.

[0029] Figure 16 The figure shows a schematic structural diagram of a trajectory similarity determination device provided by an embodiment of the present disclosure.

[0030] Figure 17 The figure shows a schematic structural diagram of a risk assessment device provided by an embodiment of the present disclosure.

[0031] Figure 18 The figure shows a schematic structural diagram of a risk tracing device provided by an embodiment of the present disclosure.

[0032] Figure 19 The figure shows a schematic structural diagram of an electronic device provided by an embodiment of the present disclosure. Detailed implementation manners

[0033] Next, the technical solutions in the embodiments of the present disclosure will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all the embodiments.

[0034] Trajectory similarity analysis is an important means for trajectory data analysis, providing an important data basis for subsequent trajectory data analysis such as estimation clustering and trajectory recommendation. Trajectory similarity analysis quickly retrieves the trajectory data most similar to a target trajectory through a predefined trajectory similarity calculation method. Trajectory similarity analysis is widely applied in fields such as transportation and logistics (path planning) and sociology.

[0035] However, traditional trajectory similarity determination methods only consider spatial distance and lack timeliness. For example, traditional trajectory similarity determination methods such as Hausdorff distance, Fréchet distance, and trajectory distance scale (LCSS) all calculate the similarity of the spatial dimension of the trajectory. In other words, traditional trajectory similarity determination methods do not consider the temporal dimension data of the trajectory, making it difficult to accurately evaluate the similarity.

[0036] In order to solve the above problems, the trajectory similarity determination method provided in the embodiment of the present disclosure determines the common interest point set corresponding to the first user and the second user by means of the first trajectory data including the residence time data of the interest point passed by the first user, and the second trajectory data including the residence time data of the interest point passed by the second user, and then determines the trajectory similarity based on the common interest point set. It can be seen that the embodiment of the present disclosure takes into account the residence time data of the interest points passed by the first user and the second user, so that the trajectory similarity can be calculated in the time dimension based on the common interest point set, which reduces the calculation of complex spatial distances and reduces the calculation complexity. In addition, since the time dimension is taken into account, the timeliness of the trajectory similarity can be improved, thereby improving the accuracy of the trajectory similarity.

[0037] The trajectory similarity determination method provided in the embodiment of the present disclosure can be applied to a geographical information system (GIS) of a distributed database. A point of interest set refers to a set of points of interest (POI). In GIS, a point of interest refers to a location point with social functions, such as a store, a bar, a gas station, a hospital, a bus stop, and a bus station. For example, the expression of a point of interest q is q=<lat,lon,name> , where lat represents latitude, lon represents longitude, and name represents name.

[0038] Combine the following Figure 1 and Figure 2 The application scenario of the trajectory similarity determination method provided in the embodiment of the present disclosure is illustrated by examples.

[0039] Figure 1 FIG. 1 is a schematic diagram of an application scenario of a method for determining trajectory similarity provided by an embodiment of the present disclosure. Figure 1As shown, the application scenario mentioned in the embodiments of the present disclosure is the close contact tracing scenario in the field of epidemic prevention and control. This close contact tracing scenario involves a server 110 and user terminals 120 communicatively connected to the server 110. Among them, the server 110 can be used to execute the trajectory similarity determination method mentioned in the present disclosure. In addition, the user terminal 120 can be a mobile phone, laptop, desktop computer, etc. of epidemic prevention staff.

[0040] Exemplarily, in the actual application process, the epidemic prevention staff use the user terminal 120 to send a risk assessment request of a user to be evaluated to the server 110. After receiving the risk assessment request, the server 110 uses the trajectory similarity determination method mentioned in the present disclosure to determine the trajectory similarity corresponding to the trajectory data of the case user and the trajectory data of the user to be evaluated. Then, based on the trajectory similarity, the close contact risk of the user to be evaluated is evaluated, and the risk assessment result of the user to be evaluated is sent to the user terminal 120 so that the epidemic prevention staff can timely understand the risk assessment situation.

[0041] Figure 2 The following shows a schematic diagram of the application scenario of the trajectory similarity determination method provided by another embodiment of the present disclosure. As Figure 2 As shown, the application scenario mentioned in the embodiments of the present disclosure is the risk traceability scenario in the field of epidemic prevention and control. This risk traceability scenario involves a server 210 and user terminals 220 communicatively connected to the server 210. The server 210 can be used to execute the trajectory similarity determination method mentioned in the present disclosure. In addition, the user terminal 220 can be a mobile phone, laptop, desktop computer, etc. of epidemic prevention staff.

[0042] Exemplarily, in the actual application process, the epidemic prevention staff use the user terminal 220 to send a risk traceability request corresponding to multiple case users to the server 210. After receiving the risk traceability request, the server 210 first determines the trajectory data of each of the multiple case users. Then, for each case user among the multiple case users, the server 210 uses the trajectory similarity determination method mentioned in the present disclosure to respectively determine the trajectory similarity between the trajectory data of the case user and the trajectory data of the remaining case users among the multiple case users, obtaining the cumulative data of the trajectory similarity corresponding to the case user. Finally, based on the cumulative data of the trajectory similarity corresponding to each of the multiple case users, the server 210 determines the source user corresponding to the multiple case users and sends the information of the source user corresponding to the multiple case users to the user terminal 120 so that the epidemic prevention staff can timely determine the source user and then timely implement control measures.

[0043] The following Figures 3 to 15 illustrates the method embodiments mentioned in the present disclosure by way of examples.

[0044] Figure 3The following is a schematic flowchart of a method for determining trajectory similarity provided by an embodiment of the present disclosure. As shown in Figure 3 shown, the method for determining trajectory similarity provided by the embodiments of the present disclosure includes the following steps.

[0045] Step S310, determine the first trajectory data and the second trajectory data.

[0046] The first trajectory data includes the residence time data of the points of interest passed by the first user. The second trajectory data includes the residence time data of the points of interest passed by the second user. Among them, the first user and the second user refer to the users for whom the trajectory similarity needs to be determined. The residence time data refers to the residence time period data.

[0047] Exemplarily, the first trajectory data is represented as The second trajectory data is represented as Among them, π n =<ρ n , t sn , t en >>, π m =<ρ m , t sm , t em >>. ρ n represents the point of interest passed by the first user. t sn represents the arrival time point when the first user arrives at this point of interest. t en represents the departure time point when the first user leaves this point of interest. In addition, ρ m represents the point of interest passed by the second user. t sm represents the arrival time point when the second user arrives at this point of interest. t em represents the departure time point when the second user leaves this point of interest.

[0048] Exemplarily, the first trajectory data and the second trajectory data are trajectory data in the same target area. The actual range of the target area can be determined according to the actual situation. It can be the overall area of a city, such as the overall area of City D, or a partial urban area of a city, such as Area E of City D.

[0049] In some embodiments, determining the first trajectory data and the second trajectory data can be performed as: obtaining the first trajectory data and the second trajectory data, such as directly obtaining the first trajectory data and the second trajectory data from other servers or ports. This setting can simplify the calculation amount.

[0050] In some other embodiments, determining the first trajectory data and the second trajectory data can be performed as: generating the first trajectory data and the second trajectory data. That is to say, both the first trajectory data and the second trajectory data are calculated and generated. With such a setting, it is possible to avoid the situation where the trajectory similarity determination method cannot be executed due to the non-existence or inability to obtain pre-generated first trajectory data and second trajectory data.

[0051] Step S320: Based on the first trajectory data and the second trajectory data, determine the set of common interest points corresponding to the first user and the second user.

[0052] The set of common interest points refers to the set formed by the common interest points. As mentioned above, a common interest point refers to an interest point that both the first user and the second user have passed by. Correspondingly, the common residence time data of the common interest point refers to the overlapping time period data between the residence time period of the first user at the common interest point and the residence time period of the second user at the common interest point. For example, the first user and the second user have a common interest point A, and the residence time data of the first user at the common interest point A is from 10:10 to 10:30, and the residence time data of the second user at the common interest point A is from 10:20 to 10:35. Then, the common residence time data of the common interest point A can be from 10:20 to 10:30, for a total of 10 minutes.

[0053] Exemplarily, the set of common interest points includes M common interest points and the common residence time data of each of the M common interest points, where M is a natural number. Here, M being a natural number means that the common interest points can be one, or multiple, or zero.

[0054] Step S330: Based on the set of common interest points, determine the trajectory similarity.

[0055] Since the common residence time data of the common interest points can reflect the contact duration of the first user and the second user within the same geographical location range, the trajectory similarity determined in the embodiments of the present disclosure can reflect the spatio-temporal accompaniment situation of the first user and the second user, and thus can assist epidemic prevention staff in determining close contacts.

[0056] The trajectory similarity determination method provided by the embodiments of the present disclosure determines the set of common interest points corresponding to the first user and the second user by means of the first trajectory data including the residence time data of the interest points passed by the first user and the second trajectory data including the residence time data of the interest points passed by the second user, and then determines the trajectory similarity based on the set of common interest points. It can be seen that the embodiments of the present disclosure consider the residence time data of the interest points passed by the first user and the second user respectively, so that the trajectory similarity can be calculated in the time dimension, reducing the calculation of complex spatial distances and lowering the calculation complexity. In addition, due to the consideration of the time dimension, the timeliness of the trajectory similarity can be improved, and thus the accuracy of the trajectory similarity can be improved.

[0057] The following Figure 4 illustrates the specific implementation manner of determining the common residence time data by way of example. Figure 4 The following shows a schematic flowchart of the trajectory similarity determination method provided by another embodiment of the present disclosure. On the basis of the Figure 3 embodiment shown, an Figure 4 embodiment is extended. The following focuses on describing Figure 4 the differences between the Figure 3 embodiment shown and the

[0058] As Figure 4 shown, in the embodiments of the present disclosure, the step of determining the set of common interest points corresponding to the first user and the second user based on the first trajectory data and the second trajectory data includes the following steps.

[0059] Step S410: Determine M common interest points based on the interest points passed by the first user included in the first trajectory data and the interest points passed by the second user included in the second trajectory data.

[0060] Exemplarily, the interest points included in the first trajectory data are P1, P3, P4, P5, S1 - S3, P7, and the interest points included in the second trajectory data are P1, P2, P4, P7. Then the common interest points corresponding to the first trajectory data and the second trajectory data are P1, P4, P7. Among them, the types of interest points represented by the letter P are different from those represented by the letter S. For example, the interest points represented by the letter P can be independent interest points such as bars and restaurants, and the interest points represented by the letter S can be associated interest points such as bus stops.

[0061] Step S420: Determine the residence time data of the first user at the M common interest points based on the first trajectory data.

[0062] That is, based on the first trajectory data, determine the residence time data of the first user at each of the M common interest points.

[0063] Step S430: Based on the second trajectory data, determine the residence time data of the second user at M common points of interest.

[0064] That is, based on the second trajectory data, determine the residence time data of the second user at each of the M common points of interest.

[0065] Step S440: Based on the residence time data of the first user at M common points of interest and the residence time data of the second user at M common points of interest, determine the common residence time data of each of the M common points of interest.

[0066] Exemplarily, the first user and the second user correspond to common point of interest P1, common point of interest P4, and common point of interest P7. The residence time of the first user at common point of interest P1 is from 10:00 to 10:20, and the residence time of the second user at common point of interest P1 is from 10:00 to 10:25. Then, the common residence time of common point of interest P1 is 20 minutes. Similarly, the residence time of the first user at common point of interest P4 is from 11:00 to 11:10, and the residence time of the second user at common point of interest P4 is from 11:00 to 11:20. Then, the common residence time of common point of interest P4 is 10 minutes. The residence time of the first user at common point of interest P7 is from 11:55 to 12:10, and the residence time of the second user at common point of interest P7 is from 11:55 to 12:05. Then, the common residence time of common point of interest P7 is 10 minutes.

[0067] The embodiments of the present disclosure can ensure the integrity and accuracy of the determined common residence time data, providing an accurate data basis for subsequent determination of trajectory similarity.

[0068] The following gives an example to illustrate the specific implementation manner of determining common points of interest.

[0069] In addition to regarding completely overlapping points of interest as common points of interest as mentioned in the above embodiments, in some embodiments, for each point of interest included in the set of points of interest included in the first trajectory data, if there is a point of interest in the set of points of interest included in the second trajectory data that is located within the same location range as this point of interest, then the points of interest located within the same location range are determined as common points of interest.

[0070] Exemplarily, the points of interest included in the first trajectory data are P1, P3, P4, P5, S1 - S3, P7, and the points of interest included in the second trajectory data are P1, P2, P4, S1 - S3, P7. First, for the point of interest P1 included in the first trajectory data, the points of interest located within the same location range can be found among the points of interest P1, P2, P4, S1 - S3, P7 included in the second trajectory data, that is, the point of interest P1, so as to determine the point of interest P1 as the common point of interest. Then, for the point of interest P3 included in the first trajectory data, the points of interest located within the same location range are searched among the points of interest P1, P2, P4, S1 - S3, P7 included in the second trajectory data. Since no point of interest located within the same location range is found in the second trajectory data, it can be determined that there is no common point of interest corresponding to the point of interest P3. Then, continue to search for the point of interest P4 included in the first trajectory data among the points of interest P1, P2, P4, S1 - S3, P7 included in the second trajectory data, and find the point of interest located within the same location range, that is, the point of interest P4, so as to determine the point of interest P4 as the common point of interest. And so on, until a common point of interest is found or not found for each point of interest in the set of points of interest included in the first trajectory data, thereby obtaining all the common points of interest between the first trajectory data and the second trajectory data.

[0071] The embodiments of the present disclosure can further expand the search range of common points of interest, and further avoid the situation of missing common points of interest, thereby providing a complete and accurate data basis for determining the trajectory similarity subsequently.

[0072] The following combines Figure 5 and Figure 6 to illustrate the specific implementation manner of determining the trajectory similarity by way of example. Figure 5 The flowchart of the trajectory similarity determination method provided by another embodiment of the present disclosure is shown. Figure 6 The schematic diagram of the trajectory similarity provided by an embodiment of the present disclosure is shown. Based on the embodiment shown in Figure 3 the embodiment shown in Figure 5 is extended. The following focuses on describing Figure 5 the differences between the embodiment shown in Figure 3 and the embodiment shown in

[0073] Figure 5 As shown, in the embodiments of the present disclosure, the steps of determining the trajectory similarity based on the set of common points of interest include the following steps.

[0074] Step S510, accumulate the common residence time data of each of the M common points of interest to obtain the contact time data corresponding to the first user and the second user.

[0075] ​Exemplarily, the common residence time of the common point of interest P1 is 20 minutes (i.e., the duration corresponding to the common residence time data is 20 minutes). The common residence time of the common point of interest P4 is 10 minutes. The common residence time of the common points of interest S1 - S3 is 20 minutes. The common residence time of the common point of interest P7 is 10 minutes. Then, the trajectory similarity can be the cumulative common residence time of all the above common points of interest, obtaining a contact time of 60 minutes (i.e., the duration corresponding to the contact time data is 60 minutes).

[0076] Step S520, determine the trajectory similarity based on the contact time data.

[0077] In practical applications, the contact time data can be directly determined as the trajectory similarity, or the contact time data can be processed such as normalized to determine the trajectory similarity.

[0078] Exemplarily, the trajectory similarity can be calculated by the following formula (1).

[0079]

[0080] In formula (1), represents the first trajectory data, represents the second trajectory data, represents the trajectory similarity. |π n ∩π m |=max{0, min(π n .t en , π m .t em ) - max(π n .t sn , π m ·t sm )}, represents the common time length of two visits, that is, the common residence time data of the common point of interest. ρ represents the common point of interest passed by both the first user and the second user. In addition, π n =<ρ n , t sn , t en >, where ρ n represents the point of interest passed by the first user, t en represents the arrival time point when the first user arrives at this point of interest, t en represents the departure time point when the first user leaves this point of interest. π m =<ρ m , t sm , t em ), where ρ mCharacterize the points of interest passed by the second user, t sm Characterize the arrival time point when the second user arrives at the point of interest, t em Characterize the departure time point when the second user leaves the point of interest.

[0081] Exemplarily, such as Figure 6 As shown, the points of interest included in the first trajectory data are P1, P3, P4, P5, S1 - S3, P7, and the points of interest included in the second trajectory data are P1, P2, P4, S1 - S3, P7. Each point of interest corresponds to a residence time data. For example, the residence time data corresponding to the point of interest P1 included in the first trajectory data is 10:00 - 10:20. The residence time data corresponding to other points of interest is as Figure 6 shown. Figure 6 The data in the two - dimensional table shown represents the data obtained during the process of calculating the trajectory similarity between the first trajectory data and the second trajectory data. The calculation method of the data in the two - dimensional table is the data obtained by using formula (1). That is, when the point of interest in the first trajectory data matches a common point of interest in the points of interest of the second trajectory data (or when the point of interest in the second trajectory data matches a common point of interest in the points of interest of the first trajectory data), the common residence time data of the common points of interest is accumulated. When the point of interest in the first trajectory data does not match a common point of interest in the points of interest of the second trajectory data (or when the point of interest in the second trajectory data does not match a common point of interest in the points of interest of the first trajectory data), the common residence time data of the common points of interest is not accumulated. Until all points of interest are calculated, the final trajectory similarity between the first trajectory data and the second trajectory data is obtained.

[0082] Specifically, the number 20 in the first row and the first column of the two - dimensional table corresponds to the point of interest P1 in the first trajectory data and P1 in the second trajectory data. There is a common point of interest P1, that is, it satisfies the condition π in formula (1) n .ρ = π m .ρ. Therefore, according to the common residence time data of the common point of interest P1, the current trajectory similarity between the first trajectory data and the second trajectory data is obtained. The number 30 in the third row and the third column of the two - dimensional table corresponds to the point of interest P4 in the first trajectory data and P4 in the second trajectory data. There is a common point of interest P4, that is, it satisfies the condition π in formula (1) n .ρ = π m .ρ. Therefore, the common residence time data of the common points of interest P1 and P4 is accumulated, and the current trajectory similarity between the first trajectory data and the second trajectory data is obtained.

[0083] The point of interest corresponding to the number 30 in the third row and fourth column of the two-dimensional table is P5 in the first trajectory data and P4 in the second trajectory data. Since P5 in the first trajectory data and P4 in the second trajectory data are not common points of interest, that is, they satisfy the condition "otherwise" in formula (1), therefore, take and the maximum value of. As can be seen from the two-dimensional table, the corresponding table number is 30, the corresponding table number is 20, so take the maximum value 30.

[0084] The point of interest corresponding to the number 50 in the fourth row and fifth column of the two-dimensional table is S1 - S3 in the first trajectory data and S1 - S3 in the second trajectory data. There is a common point of interest S1 - S3, that is, it satisfies the condition π n .ρ = π m .ρ. Therefore, accumulate the common residence time data of the common points of interest P1, P4, and S1 - S3 to obtain the current trajectory similarity of the first trajectory data and the second trajectory data. The point of interest corresponding to the number 60 in the fifth row and sixth column of the two-dimensional table is P7 in the first trajectory data and P7 in the second trajectory data. There is a common point of interest P7, that is, it satisfies the condition π n .ρ = π m .ρ. Therefore, accumulate the common residence time data of the common points of interest P1, P4, S1 - S3, and P7 to obtain the current trajectory similarity of the first trajectory data and the second trajectory data.

[0085] Since the point of interest P7 is the last point of interest of the first trajectory data and the second trajectory data, the trajectory similarity 60 obtained by accumulating to the common point of interest P7 is the final trajectory similarity of the first trajectory data and the second trajectory data.

[0086] By accumulating the common residence time data of each of the M common points of interest, the contact time data corresponding to the first user and the second user is obtained. Then, based on the contact time data, the trajectory similarity is determined. For the currently obtained common points of interest during continuous comparison, there is no need to recalculate the contact time data of the previously obtained common points of interest, and the calculation speed is fast.

[0087] In practical applications, the common residence time data of each of the M common interest points is accumulated in the form of a two-dimensional table, and finally the trajectory similarity is obtained. Each cell of the two-dimensional table is filled with the currently accumulated contact time data. When the interest points of the first trajectory data corresponding to a certain cell and the interest points of the second trajectory data are not common interest points, only the previously calculated contact time data needs to be obtained. When the interest points of the first trajectory data corresponding to a certain cell and the interest points of the second trajectory data are common interest points, only the previously calculated contact time data plus the common residence time data corresponding to the current common interest point needs to be obtained. The calculation is simple, which greatly improves the calculation efficiency.

[0088] The calculation method of the trajectory similarity between the first trajectory data and the second trajectory data can also be expressed in the following way.

[0089] Input: the first trajectory data and the second trajectory data

[0090] Output: trajectory similarity

[0091]

[0092] The principle of the above calculation method is the same as that of formula (1), and the meanings of the letters in the above calculation method are the same as those in formula (1). In addition, π = <ρ, t s , t e >, where ρ represents the common interest point. t s represents the arrival time point when the user arrives at this interest point. t e represents the departure time point when the user leaves this interest point.

[0093] The above calculation method is convenient for the computer to execute and improves the computer's calculation efficiency.

[0094] The following combines Figure 7 to illustrate the specific implementation method of determining the first trajectory data and the second trajectory data by way of example. Figure 7 The following is a schematic flowchart of the trajectory similarity determination method provided by another embodiment of the present disclosure. Based on the embodiment shown in Figure 3 an embodiment shown in Figure 7 is extended. The following focuses on describing Figure 7 the differences between the embodiment shown in Figure 3 and the embodiment shown in

[0095] As Figure 7 shown, in the embodiment of the present disclosure, the steps of determining the first trajectory data and the second trajectory data include the following steps.

[0096] Step S710: Map the set of trajectory points of the first user in the target area to the set of points of interest in the target area to obtain first trajectory data.

[0097] Step S720: Map the set of trajectory points of the second user in the target area to the set of points of interest in the target area to obtain second trajectory data.

[0098] Exemplarily, the set of points of interest in the target area refers to the data set formed by the points of interest included in the target area. The set of trajectory points includes the position data and collection time data of the trajectory points. The set of trajectory points of the first user in the target area includes the position data and collection time data (also referred to as collection timestamp data) of the trajectory points. The set of trajectory points of the second user in the target area includes the position data and collection time data (also referred to as collection timestamp data) of the trajectory points.

[0099] Exemplarily, the set of trajectory points is collected based on hardware devices such as mobile phones carried by the first user and / or the second user, and is also referred to as raw trajectory data. For example, during the process of the first user and / or the second user moving in the target area, the mobile phone carried will call its own Global Positioning System (GPS) function to collect the trajectory points of the first user and / or the second user, thereby generating a set of trajectory points.

[0100] The first trajectory data mentioned in step S710 includes the residence time data of the points of interest passed by the first user. The second trajectory data mentioned in step S720 includes the residence time data of the points of interest passed by the second user. Since the trajectory points included in the set of trajectory points are only position points with timestamps, it can be understood that the trajectory points may fall within the category of the points of interest in the set of points of interest, or may not fall within the category of the points of interest in the set of points of interest.

[0101] With the aid of the set of points of interest in the target area and the set of trajectory points of the first user in the target area, first trajectory data including the points of interest passed by the first user and the residence time of the passed points of interest is mapped and generated. That is to say, the embodiments of the present disclosure enable the generated first trajectory data to include the residence time data of each of the points of interest passed by the first user, thereby providing favorable conditions for improving the accuracy of subsequent trajectory similarity. Similarly, the embodiments of the present disclosure enable the generated second trajectory data to include the residence time data of each of the points of interest passed by the second user, thereby providing favorable conditions for improving the accuracy of subsequent trajectory similarity.

[0102] To further clarify the mapping relationship between the set of trajectory points and the set of points of interest, the following will be combined with Figure 8 and Figure 9 for illustrative examples.

[0103] Figure 8 The figure shows a schematic diagram of the positional relationship between a set of trajectory points and a set of points of interest provided by an embodiment of the present disclosure. As Figure 8 shown, the target area includes a total of three points of interest, namely point of interest A, point of interest B, and point of interest C. Among them, the black dots represent the points of interest, and the dotted circular frames outside the black dots represent the geographical ranges of the points of interest. The white dots represent the trajectory points of the first user in the target area, and the connecting lines between the white dots represent the activity paths of the first user. From Figure 8 this, it can be seen that multiple trajectory points of the first user can fall within the same category of points of interest. Similarly, multiple trajectory points of the second user can also fall within the same category of points of interest.

[0104] Figure 9 The figure shows a schematic diagram of the data relationship between a set of trajectory points and a set of points of interest provided by an embodiment of the present disclosure. As Figure 9 shown, based on the trajectory points 1 to N of the first user (i.e., the set of trajectory points), the points of interest passed by the first user and the residence time of each point of interest (i.e., the first trajectory data) can be mapped. Specifically, if both trajectory points 1 and 2 are within point of interest P1, the residence time of point of interest P1 is determined based on the respective acquisition time data of trajectory points 1 and 2, and the residence times of the remaining points of interest are also determined in a similar manner. Among them, the type of the point of interest represented by the letter P is different from the type of the point of interest represented by the letter S. For example, the point of interest represented by the letter P can be an independent point of interest such as a bar or a restaurant, and the point of interest represented by the letter S can be an associated point of interest such as a bus stop. Similarly, based on the set of trajectory points of the second user, the points of interest passed by the second user and the residence time of each point of interest (i.e., the second trajectory data) can also be mapped.

[0105] In one embodiment, mapping the set of trajectory points of the first user in the target area to the set of points of interest to generate the first trajectory data specifically includes: determining the points of interest respectively matched by the trajectory points included in the set of trajectory points based on the set of points of interest and the set of trajectory points; determining the points of interest passed by the first user and the set of trajectory points corresponding to the points of interest passed by the first user based on the points of interest respectively matched by the trajectory points included in the set of trajectory points; determining the residence time data of the points of interest passed by the first user based on the set of trajectory points corresponding to the points of interest passed by the first user, so as to generate the first trajectory data. Similarly, the second trajectory data can be generated. Compared with the method of calculating the stop points of the first user or the second user by clustering, the embodiment of the present disclosure can avoid the situation that the stop points calculated by clustering cannot completely correspond to the points of interest, thereby increasing the difficulty of trajectory risk judgment.

[0106] In one embodiment, if the type of the two-dimensional table point of interest is an independent point of interest, based on the acquisition time data of the trajectory point with the earliest time in the trajectory point set corresponding to the two-dimensional table point of interest, the arrival time point of the two-dimensional table point of interest is determined, and based on the acquisition time data of the trajectory point with the latest time in the trajectory point set corresponding to the two-dimensional table point of interest, the departure time point of the two-dimensional table point of interest is determined. If the type of the two-dimensional table point of interest is an associated point of interest, based on the acquisition time data of the trajectory point with the earliest time in the trajectory point set corresponding to the two-dimensional table point of interest, the arrival time point of the two-dimensional table point of interest is determined, and the next point of interest that is temporally associated with the two-dimensional table point of interest is determined. Based on the acquisition time data of the trajectory point with the earliest time in the trajectory point set corresponding to the next point of interest of the two-dimensional table, the departure time point of the two-dimensional table point of interest is determined. Based on the arrival time point and the departure time point of the two-dimensional table point of interest, the residence time data of the two-dimensional table point of interest is determined. By classifying the points of interest and differentially processing the points of interest according to their specific types, the accuracy of the determined residence time data of the points of interest is further improved.

[0107] The following combines Figures 10 to 14 to illustrate by way of example the specific implementation manner of determining the points of interest respectively matched by the trajectory points included in the trajectory point set.

[0108] Figure 10 The following shows a schematic flowchart of determining the points of interest respectively matched by the trajectory points included in the trajectory point set provided by an embodiment of the present disclosure. As Figure 10 shown, in the embodiment of the present disclosure, the step of mapping the trajectory point set of the first user in the target area to the point of interest set of the target area to obtain the first trajectory data includes the following steps.

[0109] Step S1010, based on the point of interest set and the trajectory point set of the first user in the target area, determine the points of interest passed by the first user and the trajectory point set corresponding to the points of interest passed by the first user.

[0110] Specifically, first, based on the point of interest set and the trajectory point set of the first user in the target area, determine the points of interest respectively matched by the trajectory points included in the trajectory point set, and then based on the points of interest respectively matched by the trajectory points included in the trajectory point set, determine the points of interest passed by the first user and the trajectory point set corresponding to the points of interest passed by the first user.

[0111] Exemplarily, the points of interest respectively matched by the trajectory points included in the trajectory point set refer to the points of interest into which the trajectory points included in the trajectory point set respectively fall. For example, if the trajectory point G in the trajectory point set falls within the geographical scope of the point of interest A, the point of interest matched by the trajectory point G is the point of interest A. Combining the above Figure 8It can be seen that not every trajectory point has a matching point of interest, and there may also be a situation where multiple trajectory points are all matched with the same point of interest.

[0112] Step S1020: Based on the set of trajectory points corresponding to the points of interest passed by the first user, determine the residence time data of the points of interest passed by the first user, so as to generate the first trajectory data.

[0113] Since the set of trajectory points corresponding to the points of interest passed by the first user contains at least one trajectory point, and each trajectory point corresponds to acquisition time data, therefore, based on the set of trajectory points corresponding to the points of interest passed by the first user, the residence time data of this point of interest can be determined.

[0114] The embodiments of the present disclosure utilize the correspondence between points of interest and trajectory points to achieve the purpose of generating the first trajectory data with time-dimensional data, thereby providing a data basis for subsequent calculation of trajectory similarity. In addition, compared with the method of calculating the stay points of users by clustering, the embodiments of the present disclosure can avoid the situation that the stay points obtained by clustering calculation cannot completely correspond to the points of interest, thereby increasing the difficulty of trajectory risk judgment.

[0115] Figure 11 The following shows a schematic flowchart of determining the points of interest respectively matched by the trajectory points included in the set of trajectory points provided by another embodiment of the present disclosure. As Figure 11 shown, in the embodiments of the present disclosure, the step of mapping the set of trajectory points of the second user in the target area to the set of points of interest in the target area to obtain the second trajectory data includes the following steps.

[0116] Step S1110: Based on the set of points of interest and the set of trajectory points of the second user in the target area, determine the points of interest passed by the second user and the set of trajectory points corresponding to the points of interest passed by the second user.

[0117] Specifically, first, based on the set of points of interest and the set of trajectory points of the second user in the target area, determine the points of interest respectively matched by the trajectory points included in the set of trajectory points, and then based on the points of interest respectively matched by the trajectory points included in the set of trajectory points, determine the points of interest passed by the second user and the set of trajectory points corresponding to the points of interest passed by the second user.

[0118] Step S1120: Based on the set of trajectory points corresponding to the points of interest passed by the second user, determine the residence time data of the points of interest passed by the second user, so as to generate the second trajectory data.

[0119] Since the set of trajectory points corresponding to the points of interest passed by the second user contains at least one trajectory point, and each trajectory point corresponds to acquisition time data, therefore, based on the set of trajectory points corresponding to the points of interest passed by the second user, the residence time data of this point of interest can be determined.

[0120] Steps S1010 and S1020, and steps S1110 and S1120 may be executed simultaneously, or only steps S1010 and S1020, or only steps S1110 and S1120 may be executed, as long as the first trajectory data or the second trajectory data can be generated, which is not specifically limited in the present disclosure.

[0121] The embodiment of the disclosure utilizes the correspondence between points of interest and trajectory points to achieve the purpose of generating second trajectory data with time dimension data, thereby providing a data basis for the subsequent calculation of trajectory similarity. In addition, compared with the method of calculating the user's stay points by clustering, the embodiment of the disclosure can avoid the situation where the stay points calculated by clustering cannot completely correspond to the points of interest, thereby increasing the difficulty of trajectory risk judgment.

[0122] In one embodiment, the track point set may be determined by the following method: first determining the interest point index data of the target area, and then determining the interest points that match the track points included in the track point set based on the interest point index data and the track point set.

[0123] Specifically, the interest point index data refers to the index data (also referred to as directory data) corresponding to the interest point set.

[0124] Exemplarily, the interest point index data is determined based on the interest point set. In some embodiments, determining the interest point index data of the target area can be performed by generating the interest point index data of the target area based on the interest point set. That is, the interest point index data is generated in real time. In some other embodiments, determining the interest point index data of the target area can also be performed by obtaining the interest point index data of the target area generated based on the interest point set. That is, the interest point index data only needs to be generated once, and the initially generated interest point index data can be directly called subsequently.

[0125] The disclosed embodiment not only improves the speed of determining the interest points that match each of the trajectory points included in the trajectory point set, but also reduces the computational complexity by using the interest point index data.

[0126] In some embodiments, the interest point index data is grid index data. In other embodiments, the interest point index data is space index data. The following is an example of grid index data. The grid division method of the grid index data includes an equal size grid division method and an equal number grid division method.

[0127] Steps for determining the interest point index data of the target area may specifically include: dividing the target area based on the geographical coordinate data of the target area to obtain grid data of the target area. Among them, the grid data corresponds to multiple grids, and the sizes of the multiple grids are the same; based on the grid data, mapping the set of interest points to the target area to generate interest point index data.

[0128] The following combines Figure 12 and Figure 13 to illustrate the equal-size grid division method. As Figure 12 shown, the target area can be divided into 100 grids, and the sizes of the 100 grids are the same, that is, the grid widths of the 100 grids are the same, and the grid heights of the 100 grids are the same. Subsequently, as Figure 13 shown, each interest point included in the target area is matched with the 100 grids to determine the grid matched by each interest point. For example, the grid matched by the interest point S1 is grid 12, the grid matched by the interest point P1 is grid 13, and so on. Finally, an interest point list (i.e., interest point index data) as shown on the Figure 13 right is generated.

[0129] The above equal-size grid division method is simple and easy to implement in calculation and convenient to construct.

[0130] In some embodiments, mapping the set of interest points to the target area based on the grid data to generate interest point index data includes: determining the starting latitude data, starting longitude data, and arrangement relationship information corresponding to the multiple grids, as well as the size data of the grids; for each interest point in the set of interest points, determining the latitude data and longitude data of the interest point, and generating index data corresponding to the interest point based on the latitude data, longitude data, starting latitude data, starting longitude data, arrangement relationship information, and size data; generating interest point index data based on the index data corresponding to each interest point included in the set of interest points. With such settings, while ensuring the generation of interest point index data, the calculation amount can be greatly reduced. Exemplarily, it can be specifically implemented based on the following formula (2), that is, in the actual calculation process, each interest point can be mapped to the grid based on the following formula (2).

[0131]

[0132] In formula (2), id represents the grid number corresponding to the interest point, lat represents the latitude of the interest point (which can be regarded as the above-mentioned latitude data), lon represents the longitude of the interest point (which can be regarded as the above-mentioned longitude data), grid.length represents the number of grids in a single row in the grid index (which can be regarded as the above-mentioned arrangement relationship information), lat min represents the starting latitude of the grid index (which can be regarded as the above-mentioned starting latitude data), lonmin The starting longitude representing the grid index (which can be regarded as the starting longitude data mentioned above), grid.height represents the grid height of a single grid (which can be regarded as the size data of the grid mentioned above), and grid.width represents the grid width of a single grid (which can be regarded as the size data of the grid mentioned above).

[0133] As described above in conjunction with Figures 3 to 13 The method for determining trajectory similarity mentioned in the present disclosure has been described in detail. Below, in conjunction with Figure 14 and Figure 15 an example is given to illustrate the application method of the method for determining trajectory similarity.

[0134] Figure 14 The flowchart of the risk assessment method provided by an embodiment of the present disclosure is shown. Exemplarily, the risk assessment method mentioned in the embodiments of the present disclosure is executed by the user terminal of the user to be evaluated or the user terminal of the epidemic prevention and control agency. As Figure 14 shown, the risk assessment method provided by the embodiments of the present disclosure includes the following steps.

[0135] Step S1410, determine the trajectory similarity corresponding to the trajectory data of the case user and the trajectory data of the user to be evaluated.

[0136] Exemplarily, the trajectory similarity corresponding to the trajectory data of the case user and the trajectory data of the user to be evaluated can be obtained based on the method for determining trajectory similarity mentioned in the above embodiments.

[0137] Step S1420, based on the trajectory similarity, evaluate the close contact risk of the user to be evaluated.

[0138] Exemplarily, a similarity threshold can be set. If the trajectory similarity between the trajectory data of the case user and the trajectory data of the user to be evaluated is greater than or equal to the similarity threshold, it can be considered that the user to be evaluated has a close contact risk. If the trajectory similarity between the trajectory data of the case user and the trajectory data of the user to be evaluated is less than the similarity threshold, it can be considered that the user to be evaluated has no close contact risk.

[0139] The method for determining trajectory similarity in the embodiments of the present disclosure takes into account the residence time data of the points of interest passed by the first user and the second user, so that the trajectory similarity can be calculated in the time dimension, improving the timeliness of the trajectory similarity, and further improving the accuracy of the trajectory similarity. Based on the trajectory similarity between the trajectory data of the case user and the trajectory data of the user to be evaluated, the close contact risk of the user to be evaluated is evaluated, and the relatively accurate trajectory similarity is utilized, improving the accuracy of the risk assessment.

[0140] Figure 15The following is a schematic flowchart of the risk tracing method provided by an embodiment of the present disclosure. Exemplarily, the risk tracing method mentioned in the embodiments of the present disclosure is executed by the user terminal of the epidemic prevention and control agency. As Figure 15 shown, the risk tracing method provided by the embodiments of the present disclosure includes the following steps.

[0141] Step S1510, determine the respective trajectory data of multiple case users.

[0142] Exemplarily, determining the respective trajectory data of multiple case users can be performed as: obtaining the respective trajectory data of multiple case users. That is to say, the respective trajectory data of multiple case users are all directly obtained. Such a setting can simplify the calculation amount. In some other embodiments, determining the respective trajectory data of multiple case users can be performed as: generating the respective trajectory data of multiple case users. That is to say, the respective trajectory data of multiple case users are all calculated and generated. Such a setting can avoid the situation where the trajectory similarity determination method cannot be executed due to the non-existence or inability to obtain the pre-generated respective trajectory data of multiple case users.

[0143] Step S1520, for each case user among multiple case users, use the trajectory similarity determination method in the above embodiments to respectively determine the trajectory similarity between the trajectory data of the case user and the trajectory data of the remaining case users among multiple case users, and obtain the cumulative data of the trajectory similarity corresponding to the case user.

[0144] Exemplarily, determining the trajectory similarity between the trajectory data of the case user and the trajectory data of the remaining case users among multiple case users, and obtaining the cumulative data of the trajectory similarity corresponding to the case user can be to sum the trajectory similarities between the trajectory data of the current case user and the trajectory data of the remaining case users, and obtain the cumulative data of the trajectory similarity corresponding to the trajectory data of the current case user.

[0145] Step S1530, based on the cumulative data of the respective trajectory similarities corresponding to multiple case users, determine the source users corresponding to multiple case users.

[0146] Exemplarily, a risk source threshold can be set. If the cumulative data of the trajectory similarity of the trajectory data of the current case user is greater than or equal to the risk source threshold, it is considered that the current case user is a source user. If the cumulative data of the trajectory similarity of the trajectory data of the current case user is less than the risk source threshold, it is considered that the current case user is not a source user.

[0147] The trajectory similarity in the embodiments of the present disclosure takes into account the residence time data of the points of interest passed by the first user and the second user, so that the trajectory similarity can be calculated in the time dimension, improving the timeliness of the trajectory similarity and further improving the accuracy of the trajectory similarity. For each case user among multiple case users, using the trajectory similarity determination method in the above embodiments, the trajectory similarity between the trajectory data of the case user and the trajectory data of the remaining case users among multiple case users is determined respectively, and the cumulative data of the trajectory similarity corresponding to the case user is obtained. Based on the cumulative data of the trajectory similarity corresponding to each of the multiple case users, the source user corresponding to the multiple case users is determined. By using the trajectory similarity with relatively high accuracy, the accuracy of the determined source user is improved.

[0148] As described above in conjunction with Figures 3 to 15 , the method embodiments of the present disclosure have been described in detail. Next, in conjunction with Figures 16 to 19 , the apparatus embodiments of the present disclosure will be described in detail. In addition, it should be understood that the description of the method embodiments corresponds to the description of the apparatus embodiments. Therefore, the parts not described in detail can be referred to the previous method embodiments.

[0149] Figure 16 The following shows a schematic structural diagram of a trajectory similarity determination apparatus provided by an embodiment of the present disclosure. As Figure 16 shown, the trajectory similarity determination apparatus 1600 provided by the embodiments of the present disclosure includes a trajectory determination module 1610, a set determination module 1620, and a similarity determination module 1630. Specifically, the trajectory determination module 1610 is configured to determine first trajectory data and second trajectory data, where the first trajectory data includes the residence time data of the points of interest passed by the first user, and the second trajectory data includes the residence time data of the points of interest passed by the second user. The set determination module 1620 is configured to determine a common point of interest set corresponding to the first user and the second user based on the first trajectory data and the second trajectory data, where the common point of interest set includes M common points of interest and the common residence time data of each of the M common points of interest, and M is a natural number. The similarity determination module 1630 is configured to determine the trajectory similarity based on the common point of interest set.

[0150] In some embodiments, the similarity determination module 1630 is further configured to accumulate the common residence time data of each of the M common points of interest to obtain the contact time data corresponding to the first user and the second user; and determine the trajectory similarity based on the contact time data.

[0151] In some embodiments, the set determination module 1620 is further configured to determine M common points of interest based on the points of interest passed by the first user in the target area included in the first trajectory data and the points of interest passed by the second user in the target area included in the second trajectory data; determine the residence time data of the first user at the M common points of interest based on the first trajectory data; determine the residence time data of the second user at the M common points of interest based on the second trajectory data; and determine the common residence time data of each of the M common points of interest based on the residence time data of the first user at the M common points of interest and the residence time data of the second user at the M common points of interest.

[0152] In some embodiments, the trajectory determination module 1610 is further configured to map the set of trajectory points of the first user in the target area to the set of points of interest in the target area to obtain first trajectory data; map the set of trajectory points of the second user in the target area to the set of points of interest in the target area to obtain second trajectory data; wherein the set of trajectory points includes the position data and acquisition time data of the trajectory points.

[0153] In some embodiments, the trajectory determination module 1610 is further configured to determine the points of interest passed by the first user and the set of trajectory points corresponding to the points of interest passed by the first user based on the set of points of interest and the set of trajectory points of the first user in the target area; and determine the residence time data of the points of interest passed by the first user based on the set of trajectory points corresponding to the points of interest passed by the first user, thereby generating first trajectory data.

[0154] In some embodiments, the trajectory determination module 1610 is further configured to determine the points of interest passed by the second user and the set of trajectory points corresponding to the points of interest passed by the second user based on the set of points of interest and the set of trajectory points of the second user in the target area; and determine the residence time data of the points of interest passed by the second user based on the set of trajectory points corresponding to the points of interest passed by the second user, thereby generating second trajectory data.

[0155] Figure 17 The following shows a schematic structural diagram of a risk assessment device provided by an embodiment of the present disclosure. As Figure 17 shown, the risk assessment device 1700 provided by the embodiment of the present disclosure includes a similarity determination module 1710 and a risk assessment module 1720. Specifically, the similarity determination module 1710 is configured to determine the trajectory similarity corresponding to the trajectory data of the case user and the trajectory data of the user to be evaluated by using the trajectory similarity determination method mentioned in the above embodiment. The risk assessment module 1720 is configured to evaluate the close contact risk of the user to be evaluated based on the trajectory similarity.

[0156] Figure 18 The following shows a schematic structural diagram of a risk tracing device provided by an embodiment of the present disclosure. As Figure 18As shown in the figure, the risk tracing device 1800 provided by the embodiments of the present disclosure includes a trajectory determination module 1810, a similarity determination module 1820, and a propagation source determination module 1830. Specifically, the trajectory determination module 1810 is configured to determine the trajectory data of each of multiple case users. The similarity determination module 1820 is configured to, for each case user among the multiple case users, use the trajectory similarity determination method mentioned in the above embodiments to respectively determine the trajectory similarity between the trajectory data of the case user and the trajectory data of the remaining case users among the multiple case users, and obtain the cumulative data of the trajectory similarity corresponding to the case user. The propagation source determination module 1830 is configured to determine the propagation source user among the multiple case users based on the cumulative data of the trajectory similarity corresponding to each of the multiple case users.

[0157] Figure 19 The figure shows a schematic structural diagram of an electronic device provided by an embodiment of the present disclosure. Figure 19 The illustrated electronic device 1900 (which may be a computer device) includes a memory 1901, a processor 1902, a communication interface 1903, and a bus 1904. Among them, the memory 1901, the processor 1902, and the communication interface 1903 are communicatively connected to each other through the bus 1904.

[0158] The memory 1901 may be a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 1901 may store a program. When the program stored in the memory 1901 is executed by the processor 1902, the processor 1902 and the communication interface 1903 are configured to execute the respective steps of the relevant methods of the embodiments of the present disclosure.

[0159] The processor 1902 may be a general-purpose central processing unit (CPU), a microprocessor, an application specific integrated circuit (ASIC), a graphics processing unit (GPU), or one or more integrated circuits, and is configured to execute the relevant program to implement the functions required to be executed by the units in the relevant devices of the embodiments of the present disclosure.

[0160] The processor 1902 can also be an integrated circuit chip with the ability to process signals. In the implementation process, each step of the relevant methods in the present disclosure can be completed by the integrated logic circuit in the hardware of the processor 1902 or instructions in the form of software. The above-mentioned processor 1902 can also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. It can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present disclosure. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in combination with the embodiments of the present disclosure can be directly embodied as being executed and completed by the hardware decoding processor, or executed and completed by a combination of the hardware and software modules in the decoding processor. The software module can be located in a mature storage medium in the art such as random access memory, flash memory, read-only memory, programmable read-only memory, or electrically erasable programmable memory, registers, etc. This storage medium is located in the memory 1901, and the processor 1902 reads the information in the memory 1901 and combines its hardware to complete the functions required to be executed by the units included in the relevant device in the embodiments of the present disclosure, or execute the relevant methods in the method embodiments of the present disclosure.

[0161] The communication interface 1903 uses a transceiver device such as, but not limited to, a transceiver to implement communication between the electronic device 1900 and other devices or communication networks. For example, the trajectory similarity can be obtained through the communication interface 1903.

[0162] The bus 1904 can include a path for transmitting information between various components of the electronic device 1900 (for example, the memory 1901, the processor 1902, the communication interface 1903).

[0163] It should be understood that the similarity determination module 1620 in the trajectory similarity determination device 1600 can be equivalent to the processor 1902.

[0164] It should be noted that although Figure 19 the shown electronic device 1900 only shows the memory, the processor, and the communication interface, in the specific implementation process, those skilled in the art should understand that the electronic device 1900 also includes other devices necessary for normal operation. At the same time, according to specific needs, those skilled in the art should understand that the electronic device 1900 may also include hardware devices for implementing other additional functions. In addition, those skilled in the art should understand that the electronic device 1900 may also only include the devices necessary for implementing the embodiments of the present disclosure, and do not necessarily include Figure 19All the devices shown in

[0165] Those of ordinary skill in the art will realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this disclosure.

[0166] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described systems, devices, and units can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0167] In several embodiments provided by this disclosure, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there can be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms.

[0168] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0169] In addition, the functional units in each embodiment of this disclosure can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit.

[0170] When the above-mentioned functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present disclosure, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present disclosure. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories, random access memories, magnetic disks, or optical discs that can store program codes.

[0171] As described above, the above are only specific implementation manners of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present disclosure can easily think of changes or substitutions, which should all be covered by the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be subject to the protection scope of the claims.

Claims

1. A method for determining trajectory similarity, comprising: Determine first trajectory data and second trajectory data, wherein the first trajectory data includes residence time data of points of interest passed by a first user, and the second trajectory data includes residence time data of points of interest passed by a second user; Based on the first trajectory data and the second trajectory data, determine a set of common points of interest corresponding to the first user and the second user, wherein the set of common points of interest includes M common points of interest and respective common residence time data of the M common points of interest, M is a natural number, the common points of interest are points of interest passed by both the first user and the second user, and the common residence time data of the common points of interest is coincidence time period data between the residence time period of the first user at the common point of interest and the residence time period of the second user at the common point of interest; Based on the set of common points of interest, determine the trajectory similarity; Wherein, the determining the trajectory similarity based on the set of common points of interest includes: Accumulate the respective common residence time data of the M common points of interest to obtain contact time data corresponding to the first user and the second user; Based on the contact time data, determine the trajectory similarity; Wherein, the determining the trajectory similarity based on the contact time data includes: determining the contact time data as the trajectory similarity; or, The determining the trajectory similarity based on the contact time data includes: performing normalization processing on the contact time data to obtain the trajectory similarity; Wherein, determining the residence time data includes: If the type of the point of interest is an independent point of interest, based on the acquisition time data of the earliest trajectory point in the set of trajectory points corresponding to the point of interest, determine the arrival time point of the point of interest, and based on the acquisition time data of the latest trajectory point in the set of trajectory points corresponding to the point of interest, determine the departure time point of the point of interest; or, If the type of the point of interest is an associated point of interest, based on the acquisition time data of the earliest trajectory point in the set of trajectory points corresponding to the point of interest, determine the arrival time point of the point of interest, and determine the next point of interest that is temporally associated with the point of interest, and based on the acquisition time data of the earliest trajectory point in the set of trajectory points corresponding to the next point of interest, determine the departure time point of the point of interest; Based on the arrival time point of the point of interest and the departure time point of the point of interest, determine the residence time data of the point of interest.

2. The method according to claim 1, wherein the determining the set of common points of interest corresponding to the first user and the second user based on the first trajectory data and the second trajectory data includes: Based on the points of interest passed by the first user included in the first trajectory data and the points of interest passed by the second user included in the second trajectory data, determine the M common points of interest; Based on the first trajectory data, determine the residence time data of the first user at the M common points of interest; Based on the second trajectory data, determine the residence time data of the second user at the M common points of interest. Based on the residence time data of the first user at the M common points of interest and the residence time data of the second user at the M common points of interest, determine the common residence time data of each of the M common points of interest.

3. The method according to claim 1 or 2, wherein the determining of the first trajectory data and the second trajectory data includes: Map the set of trajectory points of the first user in the target area to the set of points of interest in the target area to obtain the first trajectory data; Map the set of trajectory points of the second user in the target area to the set of points of interest in the target area to obtain the second trajectory data; wherein the set of trajectory points includes the position data and the acquisition time data of the trajectory points.

4. The method according to claim 3, The mapping of the set of trajectory points of the first user in the target area to the set of points of interest in the target area to obtain the first trajectory data includes: Based on the set of points of interest and the set of trajectory points of the first user in the target area, determine the points of interest passed by the first user and the set of trajectory points corresponding to the points of interest passed by the first user; Based on the set of trajectory points corresponding to the points of interest passed by the first user, determine the residence time data of the points of interest passed by the first user, thereby generating the first trajectory data; and / or, The mapping of the set of trajectory points of the second user in the target area to the set of points of interest in the target area to obtain the second trajectory data includes: Based on the set of points of interest and the set of trajectory points of the second user in the target area, determine the points of interest passed by the second user and the set of trajectory points corresponding to the points of interest passed by the second user; Based on the set of trajectory points corresponding to the points of interest passed by the second user, determine the residence time data of the points of interest passed by the second user, thereby generating the second trajectory data.

5. A risk assessment method, including: Using the method according to any one of claims 1 to 4, determine the trajectory similarity corresponding to the trajectory data of the case user and the trajectory data of the user to be evaluated; Based on the trajectory similarity, evaluate the close contact risk of the user to be evaluated.

6. A risk tracing method, including: Determine the trajectory data of each of multiple case users; For each case user among the multiple case users, use the method according to any one of claims 1 to 4 to respectively determine the trajectory similarity between the trajectory data of the case user and the trajectory data of the remaining case users among the multiple case users, and obtain the cumulative data of the trajectory similarity corresponding to the case user; Based on the cumulative data of the trajectory similarity corresponding to each of the multiple case users, determine the source user corresponding to the multiple case users; wherein the determining of the trajectory similarity between the trajectory data of the case user and the trajectory data of the remaining case users among the multiple case users, and obtaining the cumulative data of the trajectory similarity corresponding to the case user includes: Sum the trajectory similarities between the trajectory data of the case user and the trajectory data of the remaining case users to obtain the cumulative data of the trajectory similarity corresponding to the trajectory data of the current case user.

7. A trajectory similarity determination device, comprising: A trajectory determination module, configured to determine first trajectory data and second trajectory data, where the first trajectory data includes the residence time data of the points of interest passed by a first user, and the second trajectory data includes the residence time data of the points of interest passed by a second user; A set determination module, configured to determine a set of common points of interest corresponding to the first user and the second user based on the first trajectory data and the second trajectory data, where the set of common points of interest includes M common points of interest and the respective common residence time data of the M common points of interest, M is a natural number, the common points of interest are the points of interest passed by both the first user and the second user, and the common residence time data of the common points of interest is the overlapping time period data between the residence time period of the first user at the common point of interest and the residence time period of the second user at the common point of interest; A similarity determination module, configured to determine a trajectory similarity based on the set of common points of interest; Wherein, determining the trajectory similarity based on the set of common points of interest includes: Accumulating the respective common residence time data of the M common points of interest to obtain the contact time data corresponding to the first user and the second user; Determining the trajectory similarity based on the contact time data; Wherein, determining the trajectory similarity based on the contact time data includes: determining the contact time data as the trajectory similarity; or, Determining the trajectory similarity based on the contact time data includes: performing a normalization process on the contact time data to obtain the trajectory similarity; Wherein, determining the residence time data includes: If the type of the point of interest is an independent point of interest, determining the arrival time point of the point of interest based on the acquisition time data of the earliest trajectory point in the trajectory point set corresponding to the point of interest, and determining the departure time point of the point of interest based on the acquisition time data of the latest trajectory point in the trajectory point set corresponding to the point of interest; or, If the type of the point of interest is an associated point of interest, determining the arrival time point of the point of interest based on the acquisition time data of the earliest trajectory point in the trajectory point set corresponding to the point of interest, and determining the next point of interest that is temporally associated with the point of interest, and determining the departure time point of the point of interest based on the acquisition time data of the earliest trajectory point in the trajectory point set corresponding to the next point of interest; Determining the residence time data of the point of interest based on the arrival time point of the point of interest and the departure time point of the point of interest.

8. A risk assessment device, comprising: A similarity determination module, configured to use the method according to any one of claims 1 to 4 to determine the trajectory similarity corresponding to the trajectory data of the case user and the trajectory data of the user to be evaluated; A risk assessment module, configured to assess the close contact risk of the user to be evaluated based on the trajectory similarity.

9. A risk traceability device, comprising: A trajectory determination module, configured to determine the trajectory data of each of multiple case users; A similarity determination module, configured to, for each case user among the multiple case users, respectively determine the trajectory similarity between the trajectory data of the case user and the trajectory data of the remaining case users among the multiple case users by using the method according to any one of claims 1 to 4, and obtain the cumulative data of the trajectory similarity corresponding to the case user; A transmission source determination module, configured to determine the transmission source user corresponding to the multiple case users based on the cumulative data of the trajectory similarity corresponding to each of the multiple case users; wherein the step of determining the trajectory similarity between the trajectory data of the case user and the trajectory data of the remaining case users among the multiple case users and obtaining the cumulative data of the trajectory similarity corresponding to the case user includes: summing up the trajectory similarities between the trajectory data of the case user and the trajectory data of the remaining case users to obtain the cumulative data of the trajectory similarity corresponding to the trajectory data of the current case user.

10. An electronic device, comprising a memory and a processor, wherein the memory stores executable code, and the processor is configured to execute the executable code to implement the method according to any one of claims 1 to 6.

Images