Time consumption estimation method and device

Abstract

The embodiment of the invention discloses a time consumption estimation method and device, and the method comprises the steps: obtaining the track information of a user during the sightseeing of a target AOI in each preset hot time period; the track information comprises a track point position and track point time; on the basis of the track information, calculating time consumption of the user in hot time periods for touring the target AOI in each preset hot time period; for each preset unpopular time period, calculating a weight coefficient used for performing weighted calculation on consumed time of the unpopular time period; the weight coefficient of the unpopular time period is used for calculating the time consumption of the unpopular time period for touring the target AOI in the unpopular time period; and based on the time consumption of the hot time period and the weight coefficient, calculating the time consumption of the hot time period when the user touring the target AOI in each preset hot time period. According to the technical scheme, the AOI touring time consumption can be accurately estimated, so that the travel can be better formulated.

Description

Technical Field

[0001] The present disclosure relates to the technical field of location-based information services, and in particular to a time consumption estimation method and device. Background Art

[0002] As people's living standards improve, users' travel demands continue to increase. In the prior art, users usually search for scenic spot information, and then estimate or inquire about the duration of the scenic spot, and then arrange travel, such as determining whether to visit the scenic spot, and arranging a vehicle to pick up near the scenic spot at the end of the tour.

[0003] However, since users are not familiar with the scenic spots, the self-estimation method often cannot accurately estimate the tour duration, while the inquiry method requires users to spend more time and energy, and the accuracy of the inquiry results is uncontrollable, resulting in a poor user experience.

[0004] Therefore, there is an urgent need to provide a time estimation solution to accurately and quickly estimate the time consumed in visiting scenic spots. Summary of the invention

[0005] In order to solve the problems in the related art, the embodiments of the present disclosure provide a time consumption estimation method and device.

[0006] In a first aspect, an embodiment of the present disclosure provides a time consumption estimation method, comprising: Obtaining the trajectory information of the user when visiting the target area of ​​interest AOI during each preset popular time period; the trajectory information includes the location of the trajectory point and the time of the trajectory point; Based on the trajectory information, calculate the time consumed by the user to visit the target AOI during each preset popular time period; For each preset unpopular time period, a weight coefficient for weighting the time spent in the popular time period is calculated; the weight coefficient of an unpopular time period is used to calculate the unpopular time period time spent visiting the target AOI in the unpopular time period; The unpopular time period consumption of the user visiting the target AOI in each preset unpopular time period is calculated based on the popular time period consumption and the weight coefficient.

[0007] In a second aspect, an embodiment of the present disclosure provides a time consumption estimation device, including: A trajectory acquisition module is configured to acquire trajectory information of a user visiting a target area of ​​interest AOI during each preset popular time period; the trajectory information includes a trajectory point location and a trajectory point time; A first calculation module is configured to calculate the popular time period consumption of the user visiting the target AOI in each preset popular time period based on the trajectory information; The second calculation module is configured to calculate, for each preset unpopular time period, a weight coefficient for weighted calculation of the time consumed in the popular time period; the weight coefficient of an unpopular time period is used to calculate the unpopular time period time consumed by visiting the target AOI in the unpopular time period; The third calculation module is configured to calculate the unpopular time period consumption of the user visiting the target AOI in each preset unpopular time period based on the popular time period consumption and the weight coefficient.

[0008] According to the technical solution provided by the embodiment of the present disclosure, for each preset popular time period of the target AOI, the trajectory information of a large number of users visiting the target interest surface AOI during each preset popular time period can be first obtained, and based on the trajectory information, the popular time period time consumed by the users to visit the target AOI during each preset popular time period can be calculated. Since there is more trajectory information in the preset popular time period, the popular time period time consumed by the users to visit the target AOI during the preset popular time period can be accurately calculated; for each preset unpopular time period of the target AOI, since there is less trajectory information in the preset unpopular time period, the unpopular time period time consumed by the users to visit the target AOI during each preset unpopular time period can be estimated based on the popular time period time consumed by the target AOI and its weight coefficient. In this way, the time consumed by the users to visit the target AOI in each time period can be accurately estimated, and then the travel itinerary can be reasonably arranged to provide better travel services for the users.

[0009] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Other features, objectives and advantages of the present disclosure will become more apparent through the following detailed description of non-limiting embodiments in conjunction with the accompanying drawings. In the accompanying drawings:

[0011] Figure 1 A flowchart showing a time consumption estimation method provided by an embodiment of the present disclosure is shown; Figure 2 A schematic diagram showing a reference AOI including two sub-reference AOIs provided by an embodiment of the present disclosure is shown; Figure 3 A structural block diagram of a time consumption estimation device provided by an embodiment of the present disclosure is shown; Figure 4 A structural block diagram of an electronic device according to an embodiment of the present disclosure is shown; Figure 5 A schematic diagram showing the structure of a computer system suitable for implementing the method according to an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0012] Hereinafter, exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings so that those skilled in the art can easily implement them. In addition, for the sake of clarity, parts not related to the description of the exemplary embodiments are omitted in the accompanying drawings.

[0013] In the present disclosure, it should be understood that terms such as "include" or "have" are intended to indicate the presence of features, numbers, steps, behaviors, components, parts, or a combination thereof disclosed in the present specification, and are not intended to exclude the possibility that one or more other features, numbers, steps, behaviors, components, parts, or a combination thereof exist or are added.

[0014] It should also be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present disclosure may be combined with each other. The present disclosure will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0015] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0016] As mentioned above, with the improvement of people's living standards, users' travel demands are constantly increasing. In the prior art, users usually search for scenic spot information, and then estimate or inquire about the tour duration of the scenic spot by themselves, and then arrange travel, such as determining whether to visit the scenic spot, and arranging vehicles to pick up near the scenic spot at the end of the tour. However, since users are not familiar with the scenic spot, the self-estimation method often cannot accurately estimate the tour duration, and the inquiry method requires users to spend more time and energy, and the accuracy of the inquiry results is also uncontrollable, and the user experience is not good.

[0017] The present disclosure provides a time consumption estimation method, which can determine the popular time consumption of a user visiting the target AOI (Area of ​​Interest) during the popular time period according to the trajectory information of the target AOI during the popular time period, and then estimate the unpopular time consumption of the user visiting the target AOI during the unpopular time period according to the popular time consumption of the target AOI. In this way, the visiting time of the target AOI in each time period can be accurately estimated, and the travel itinerary can be reasonably arranged to provide better travel services for users.

[0018] Figure 1 FIG. 1 is a flow chart showing a time consumption estimation method provided by an embodiment of the present disclosure. Figure 1As shown, the time consumption estimation method includes the following steps S101-S104:

[0019] In step S101, the trajectory information of the user visiting the target area of ​​interest AOI in each preset popular time period is obtained; the trajectory information includes the location of the trajectory point and the time of the trajectory point; In step S102, based on the trajectory information, the popular time period consumption of the user visiting the target AOI in each preset popular time period is calculated; In step S103, for each preset unpopular time period, a weight coefficient for weighting the time spent in the popular time period is calculated; the weight coefficient of an unpopular time period is used to calculate the unpopular time period time spent by the user visiting the target AOI in the unpopular time period; In step S104, based on the popular time period consumption and the weight coefficient, the unpopular time period consumption of the user visiting the target AOI in each preset unpopular time period is calculated.

[0020] In a possible implementation, the time consumption estimation method is applicable to a computer, computing device, server, server cluster or other device capable of executing time consumption estimation.

[0021] In a possible implementation, AOI (Area of ​​Interest) refers to a regional geographic entity in a map, which mainly includes four basic information: name, address, category, and regional boundary information. For example, the AOI can be a university, an industrial park, a comprehensive shopping mall, a hospital, a scenic spot, etc. The target AOI can be a target area or a sub-area in the target area. For example, a large scenic area includes multiple secondary scenic spots such as a zoo and an amusement park. The target AOI described in this implementation can be the large scenic area or a secondary scenic spot in the large scenic area.

[0022] In a possible implementation, the popular time period and the unpopular time period of the target AOI can be determined based on the passenger flow of the target AOI in each time period. It should be noted that the division of time periods can be determined based on the tour duration (roughly estimated tour duration) recorded in the information of the target AOI. Alternatively, the popular time period and the unpopular time period recorded in the information can be directly extracted from the information of the target AOI. It can also be determined by combining the roughly estimated tour duration and the passenger flow of each time period. Of course, it is not limited to this.

[0023] In a possible implementation, the trajectory information refers to the trajectory information generated by each user when visiting the target AOI during each preset hot period in history, including the location of the trajectory point and the time of the trajectory point. For a user visiting the target AOI during a preset hot period, the entry time of the user entering the target AOI and the exit time of the user leaving the target AOI can be determined based on the trajectory information of the user in the target AOI, and the difference between the entry time and the exit time is the time spent by the user visiting the target AOI during the hot period.

[0024] In a possible implementation, the trajectory information may be obtained in the following two ways: The first method for acquiring trajectory information includes: based on the boundary of the target AOI, acquiring the historical trajectory information of each user located within the boundary of the target AOI, acquiring the number of trajectory points in the historical trajectory information of the user, determining the trajectory information of the historical trajectory information of the user where the number of trajectory points exceeds a predetermined threshold as the trajectory information of the user when visiting the target AOI, and then acquiring the trajectory information of the user when visiting the target AOI in each preset popular time period from the trajectory information of the user when visiting the target AOI.

[0025] Specifically, AOI is a regional geographic entity in a map, so each AOI has a corresponding boundary, and the user historical trajectory information within the boundary of the AOI can be obtained. These user historical trajectory information are very likely to be the trajectory information generated when the user visits the AOI. At this time, for each user historical trajectory information, the number of trajectory points in the user historical trajectory information can be obtained. If the number of trajectory points exceeds a predetermined threshold, such as 80% of the total number of trajectory points in the trajectory information of the user in the corresponding time period or the predetermined number corresponding to the target AOI, it can be determined that the user is visiting the target AOI, and the trajectory information where the user historical trajectory information is located can be determined as the trajectory information when the user visits the target AOI.

[0026] Correspondingly, the method of determining the entry time of the user into the target AOI and the exit time of the user leaving the target AOI according to the trajectory information of the user in the target AOI can be: based on the trajectory information of the user when touring the target AOI, determine the trajectory point when the user first enters the boundary of the target AOI, and the trajectory points within a first predetermined time period, such as 3 minutes, are all within the boundary of the target AOI, and the trajectory point time of the first trajectory point after the first predetermined time period is determined as the entry time t1 of entering the target AOI; at the same time, according to the trajectory information corresponding to the target AOI, it can be determined whether the distance between the trajectory points for a second predetermined time period, such as 1 minute, and the target AOI is all outside the first predetermined distance, such as 50m. If so, the first trajectory point after the second predetermined time period is used as the exit time t2 of leaving the target AOI.

[0027] The second method for acquiring trajectory information includes: using the navigation information pair corresponding to the target AOI as the user historical trajectory information corresponding to the target AOI, the navigation information pair is the first navigation information of the same user on the same date with the target AOI as the navigation end point, and the second navigation information with the target AOI or the target location point as the navigation starting point, the target location point is a location point within a predetermined distance range from the target AOI, the first navigation information is generated earlier than the second navigation information, and the first navigation information includes trajectory information with the target AOI as the navigation end point.

[0028] Specifically, in some cases, when a user visits the target AOI, there is no track information in the target AOI. At this time, since the user is not familiar with the area where the target AOI is located, it may be necessary to navigate to the target AOI and leave from the target AOI or the target AOI near the target AOI, such as a store (such as a restaurant) around the target AOI after the visit. Therefore, when the same user first takes the target AOI as the navigation end point on the same date, a first navigation information is generated, and the first navigation information includes the user track information with the target AOI as the navigation end point (so that the navigation end time can be used as the entry time of entering the target AOI). Then, the same user takes the target AOI or the target location point as the navigation starting point on the same date for navigation or query, and generates a second navigation information. The navigation information pair formed by the first navigation information and the second navigation information can be used as the track information corresponding to the target AOI. In this way, using these two methods to obtain the track information of the target AOI can increase the amount of track information of each target AOI, thereby making the calculation of the time consumption of the hot period of the target AOI more accurate.

[0029] Correspondingly, the method for determining the entry time of the user into the target AOI and the exit time of the user leaving the target AOI based on the trajectory information of the user in the target AOI can be: taking the trajectory point time of the trajectory point at the end of navigation in the first navigation information as the entry time t1 of the target AOI, and taking the first navigation time in the second navigation information as the exit time t2 of the target AOI; in this way, the entry time t1 of the user into the target AOI and the exit time t2 of the user leaving the target AOI can be obtained.

[0030] In a possible implementation, for the target AOI, the passenger flow in each preset popular time period is relatively large, and there is a large amount of trajectory information. At this time, for each preset popular time period, the average time consumed by each user to visit the target AOI during the preset popular time period can be calculated to obtain the popular time period time consumed by users to visit the target AOI during the preset popular time period.

[0031] In a possible implementation, for the target AOI, the passenger flow in each preset unpopular time period is small, and there is little or even no trajectory information of users visiting the target AOI in the preset unpopular time period. If the unpopular time period time spent visiting the target AOI in the preset unpopular time period is determined based on a small amount of trajectory information in the preset unpopular time period, it may be inaccurate. Therefore, this implementation can estimate the unpopular time period time spent visiting the target AOI in each preset unpopular time period by the popular time period time spent in each preset popular time period.

[0032] In one possible implementation, for each preset unpopular time period, a weight coefficient for weighted calculation of the time spent in the popular time period can be calculated first. For example, the same weight coefficient can be set for the time spent in each popular time period, or a larger weight coefficient can be set for the time spent in the popular time period that is closer to the preset unpopular time period, and a smaller weight coefficient can be set for the time spent in the popular time period that is farther from the preset unpopular time period. Alternatively, the weight coefficient of the time spent in the popular time period can be calculated according to other weight calculation rules, which are not limited here.

[0033] In a possible implementation, for each preset unpopular time period, the time consumption in the popular time period is weightedly calculated using the weight coefficient corresponding to the time consumption in the popular time period, so as to obtain the unpopular time period time consumption for visiting the target AOI in the preset unpopular time period.

[0034] In this way, the time consumed by the user to visit the target AOI during each popular period and the time consumed during unpopular period can be obtained. When traveling, the user can input his or her travel requirements, such as travel duration, scenic spots to be visited, and other information. The server can plan the itinerary based on the travel requirements input by the user and the time consumed in each period corresponding to the corresponding scenic spot AOI estimated based on the above-mentioned time consumption estimation method. For example, the server can reasonably arrange the scenic spot AOIs to be visited daily according to the time consumption corresponding to the corresponding scenic spot AOI, make reservations for pick-up vehicles, and so on.

[0035] In this embodiment, for each preset popular time period of the target AOI, the trajectory information of a large number of users visiting the target interest area AOI in each preset popular time period can be first obtained, and the popular time period time consumed by the users to visit the target AOI in each preset popular time period can be calculated based on the trajectory information. Since there is more trajectory information in the preset popular time period, the popular time period time consumed by the users to visit the target AOI in the preset popular time period can be accurately calculated; for each preset unpopular time period of the target AOI, since there is less trajectory information in the preset unpopular time period, the unpopular time period time consumed by the users to visit the target AOI in each preset unpopular time period is estimated based on the popular time period time consumed by the target AOI and its weight coefficient. In this way, the time consumed by the users to visit the target AOI in each time period can be accurately estimated, and then the travel itinerary can be reasonably arranged to provide better travel services for the users.

[0036] In a possible implementation, for each preset unpopular time period, a weight coefficient for weighting the time consumption of the popular time period is calculated, including: For each preset unpopular time period, a weight coefficient for weighting the time consumption of the popular time period is calculated based on an exponential moving average model.

[0037] In this embodiment, the exponential moving average model (EMA), also called weighted moving average, is an averaging method that gives a higher weight coefficient to recent data. When weighted averaging the time spent in the hot time periods of each preset hot time period, the exponential moving average model can be used to calculate the weight coefficient of the time spent in the hot time period of each preset hot time period, and a larger weight coefficient is set for the preset hot time period that is closer to the preset unpopular time period.

[0038] In a possible implementation, obtaining the trajectory information of the user when visiting the target area of ​​interest AOI during each preset popular time period includes: Determine whether the target AOI is a hot AOI; If yes, then obtain the trajectory information of the user when visiting the target AOI during each preset popular time period.

[0039] In this implementation, the number of track information when the user visits the target AOI can be used to determine whether the target AOI is a hot AOI or a cold AOI. If the number of track information corresponding to the target AOI exceeds a predetermined number, the target AOI is determined to be a hot AOI, otherwise, the target AOI is determined to be a cold AOI. Alternatively, the tag information of the target AOI can be obtained. If the target AOI has a hot tag, it is a hot AOI, and if the target AOI has a cold tag, it is a cold AOI.

[0040] In this implementation, when the target AOI is a popular AOI, the amount of trajectory information of users visiting the target AOI during each preset popular time period will be relatively large, and the popular time period time spent by users visiting the target AOI during each preset popular time period calculated based on this will be relatively accurate.

[0041] In a possible implementation, the method may further include the following steps: If the target AOI is a less popular AOI, determine the cluster where the target AOI is located; wherein the cluster includes multiple AOIs similar to the target AOI; A popular AOI in the cluster is selected as a reference AOI; the time consumption of visiting the reference AOI is known; The time consumed by the user to visit the target AOI is calculated based on the time consumed in each popular time period and the time consumed in each unpopular time period corresponding to the reference AOI.

[0042] In this embodiment, for unpopular AOIs, since the passenger flow of unpopular AOIs is small, the trajectory information corresponding to the user's visit to the unpopular AOI is also small, or even non-existent. If the time consumed to visit the unpopular AOI is determined based on the small amount of trajectory information corresponding to the unpopular AOI, it may be inaccurate. Therefore, this embodiment uses the visiting time consumed in each time period of the popular AOI similar to the unpopular AOI to predict the visiting time consumed in each time period of the unpopular AOI.

[0043] In this implementation, a large number of AOIs can be divided into different clusters in advance through AOI clustering, so that the similarity of AOIs in the same cluster is as large as possible, and the difference of AOIs not in the same cluster is as large as possible, that is, after clustering, AOIs of the same category are clustered together as much as possible, and AOIs of different categories are separated as much as possible. In this way, each cluster will include multiple similar AOIs, and the similarity here refers to the similarity between the feature information of AOIs, and the feature information can be the type of AOI (such as shopping streets, gardens, amusement parks, shopping malls, etc.), AOI built-in content information (such as the proportion of mountain areas and lakes in scenic area AOIs), the geographical area where the AOI is located (such as the province, etc.), etc. The similarity between the feature information of each AOI can be calculated, and clustering can be performed based on the similarity. For example, multiple AOIs whose similarities are within a predetermined threshold can be clustered into a cluster, and so on. When the target AOI is an unpopular AOI, the cluster where the target AOI is located can be determined. The cluster contains AOIs with feature information similar to that of the target AOI. A popular AOI can be selected from the cluster where the target AOI is located as a reference AOI. For example, a popular AOI can be randomly selected as the reference AOI, or a popular AOI can be selected from the cluster where the target AOI is located as the reference AOI according to a predetermined selection rule. The predetermined selection rule can be to select a popular AOI that is most similar to the target AOI (i.e., the most similar feature information) from the cluster where the target AOI is located, or to select a popular AOI that is most similar to the target AOI in terms of distance and AOI type from the cluster where the target AOI is located as the reference AOI, and so on.

[0044] In this embodiment, the reference AOI is a popular AOI, which can be estimated in advance based on the estimation method of the popular time period consumption and the unpopular time period consumption of the above-mentioned popular AOI, the time consumed by the user to visit the popular time period of the hot AOI during the preset popular time period, and the time consumed to visit the unpopular time period of the hot AOI during each preset unpopular time period; that is, the time consumed to visit the reference AOI in each time period is known.

[0045] In this implementation, the tour time corresponding to the target AOI in the same period can be determined based on the tour time corresponding to the reference AOI in the same period. For example, the tour time corresponding to the reference AOI in the same period can be directly used as the tour time corresponding to the target AOI in the same period; or, based on the difference between the feature information of the reference AOI and the target AOI, the tour time corresponding to the reference AOI in the same period can be modified accordingly as the tour time corresponding to the target AOI in the same period. For example, the area ratio between the effective area of ​​the target AOI and the effective area of ​​the reference AOI can be obtained, and the tour time corresponding to the reference AOI in the same period can be multiplied by the area ratio as the tour time of the target AOI in the same period.

[0046] In this implementation, the tour time corresponding to the target AOI may also be calculated based on the weighted average time consumed in each popular time period and the unpopular time period corresponding to the reference AOI; for example, the weighted average time consumed may be directly used as the tour time corresponding to the target AOI; or, based on the difference between the feature information of the reference AOI and the target AOI, the weighted average time consumed may be modified accordingly and used as the tour time corresponding to the target AOI.

[0047] In a possible implementation, before determining the cluster where the target AOI is located, clustering multiple preset AOIs, where the multiple preset AOIs include the target AOI; clustering the multiple preset AOIs includes: Acquire feature information of the plurality of preset AOIs; AOI clustering is performed based on the feature information of the plurality of preset AOIs to obtain clusters, each of which includes a plurality of similar AOIs, and one of the clusters includes the target AOI.

[0048] In this embodiment, the characteristic information of the preset AOI refers to various information that can reflect the characteristics of the preset AOI, and may include at least one of the following information: AOI area, AOI type (such as shopping streets, gardens, amusement parks, shopping malls, etc.), AOI passenger flow information (such as passenger flow, etc.), AOI built-in content information (such as the proportion of mountain areas and lakes in scenic area AOIs, etc.), AOI level information (such as 5A scenic area, 4A scenic area, etc. level information). It should be noted here that when clustering AOIs, the AOIs can be weighted clustered according to the weights of different types of characteristic information of the AOI. For example, when the characteristic information includes AOI passenger flow information, the weight of the AOI passenger flow information can be set to be smaller, so that unpopular AOIs and popular AOIs with similar other characteristic information can be clustered into one category.

[0049] In this way, multiple preset AOIs can be clustered to obtain multiple clusters, each cluster including multiple similar AOIs. Since the multiple preset AOIs include the target AOI, one of the clusters obtained by clustering will include the target AOI. In this way, a popular AOI can be selected from the cluster where the target AOI is located as a reference AOI, and the time consumed by the user to visit the target AOI is calculated based on the time consumed in each popular time period and the time consumed in the unpopular time period corresponding to the reference AOI.

[0050] In a possible implementation, the calculating the time consumed by the user to visit the target AOI based on the time consumed in each popular time period and the time consumed in each unpopular time period corresponding to the reference AOI includes: Obtaining a calibration factor corresponding to the target AOI; Calculating an area ratio of the target AOI to the reference AOI; The visiting time of the target AOI is calculated according to the calibration factor, the area ratio, and the visiting time corresponding to the reference AOI.

[0051] In this embodiment, when calculating the time taken by the user to visit the target AOI based on the time taken during each popular time period and the time taken during each unpopular time period corresponding to the reference AOI, the visiting time taken corresponding to the reference AOI can be obtained first. The visiting time taken corresponding to the reference AOI can be the time taken by time period, that is, the time taken during each popular time period corresponding to each preset popular time period and the time taken during each unpopular time period corresponding to each preset unpopular time period. At this time, the visiting time taken corresponding to the target AOI in the same time period can be determined based on the visiting time taken corresponding to the reference AOI in the same time period, that is, the calculated visiting time taken for the target AOI is also the time taken by time period. Alternatively, the visiting time taken corresponding to the reference AOI does not distinguish between time periods, and the visiting time taken corresponding to the reference AOI is the weighted average time taken of the popular time period taken corresponding to each preset popular time period and the unpopular time period taken corresponding to each preset unpopular time period. At this time, the visiting time taken corresponding to the target AOI can be determined based on the weighted average time taken, that is, the calculated visiting time taken for the target AOI does not distinguish between time periods.

[0052] In this embodiment, when calculating the tour time of the target AOI according to the tour time corresponding to the reference AOI, two aspects need to be considered. One aspect is the accuracy of the tour time of the target AOI. For this, a calibration factor corresponding to the target AOI can be obtained, and the calibration factor is used to calibrate the tour time of the target AOI. On the other hand, it is necessary to consider that the area between the target AOI and the reference AOI is different. Usually, if the area of ​​the AOI is larger, the user's tour time in the AOI will be longer. If the area of ​​the AOI is smaller, the user's tour time in the AOI will be shorter. For this, the area ratio of the area of ​​the target AOI to the area of ​​the reference AOI can be calculated. Taking the above two aspects into consideration, the tour time corresponding to the reference AOI can be corrected based on the calibration factor and the area ratio to calculate the tour time of the target AOI. For example, the calculation formula can be: the tour time of the target AOI = calibration factor * area ratio * tour time corresponding to the reference AOI, and the area ratio = the area of ​​the target AOI / the area of ​​the reference AOI.

[0053] It should be noted here that when calculating the area ratio, some AOIs have only one floor on the ground. In this case, the area of ​​the AOI can be the area of ​​the ground area where the AOI is located. Some AOIs have two or more floors, such as shopping mall AOIs. In this case, the area of ​​the AOI can be the area of ​​the ground area where the AOI is located multiplied by the number of floors; some AOIs have two or more floors in some areas and one floor in other areas. When calculating the area of ​​the AOI, the area of ​​the two-story or multi-story area needs to be multiplied by the number of floors.

[0054] In a possible implementation manner, obtaining a calibration factor corresponding to the target AOI includes: Obtain the average time consumption corresponding to each popular AOI in the cluster; The ratio of the average value to the time consumption corresponding to the reference AOI is calculated as a calibration factor corresponding to the target AOI.

[0055] In this embodiment, the calibration factor corresponding to the target AOI is used to calibrate the tour time corresponding to the target AOI. When the tour time corresponding to the target AOI is divided into time periods, the calibration factor corresponding to the target AOI is also a calibration factor divided into time periods. The average time of each popular AOI in the cluster where the target AOI is located in the same time period can be obtained, and the ratio of the average time to the time corresponding to the reference AOI in the same time period is used as the calibration factor of the target AOI in the same time period. When the tour time corresponding to the target AOI does not distinguish between time periods, the calibration factor corresponding to the target AOI is also a calibration factor that does not distinguish between time periods. The average time corresponding to each popular AOI in the cluster where the target AOI is located (i.e., the weighted average time of each popular time period and the unpopular time period) can be obtained, and the ratio of the average time to the time corresponding to the reference AOI is used as the calibration factor of the target AOI.

[0056] In this embodiment, since the popular AOIs in the same cluster are all similar AOIs, the tour durations of these similar popular AOIs will also have a certain degree of similarity. Therefore, the average tour duration of these popular AOIs / the tour duration corresponding to the reference AOI can be used as the calibration factor corresponding to the target AOI. When the ratio is less than 1, it means that the tour duration corresponding to the reference AOI exceeds the average level. At this time, the tour duration corresponding to the target AOI can be reduced by the calibration factor to avoid the tour duration corresponding to the reference AOI being too long, resulting in the estimated tour duration of the target AOI being too long; when the ratio is greater than 1, it means that the tour duration corresponding to the reference AOI is less than the average level. At this time, the tour duration corresponding to the target AOI can be increased by the calibration factor to avoid the tour duration corresponding to the reference AOI being too short, resulting in the estimated tour duration of the target AOI being too short; in this way, the accuracy of the estimated tour duration of the target AOI can be improved.

[0057] In a possible implementation manner, the time consumption of visiting each sub-reference AOI in the reference AOI is known; and obtaining the calibration factor corresponding to the target AOI includes: Obtain the sum of the time consumption corresponding to each sub-reference AOI; The ratio of the sum value to the time consumption corresponding to the reference AOI is calculated as a calibration factor corresponding to the target AOI.

[0058] In this embodiment, if the reference AOI includes multiple sub-reference AOIs, the trajectory information of the user visiting the sub-reference AOI during each preset popular time period can be obtained for each sub-reference AOI; based on the trajectory information, the popular time period time consumed by the user to visit the sub-reference AOI during each preset popular time period is calculated, and the unpopular time period time consumed by the user to visit the sub-reference AOI during each preset unpopular time period is estimated accordingly, so as to obtain the time consumed in each time period for visiting each sub-reference AOI in the reference AOI.

[0059] For example, Figure 2 A schematic diagram of a reference AOI including two sub-reference AOIs provided by an embodiment of the present disclosure is shown, Figure 2 As shown in the figure, the reference AOI is area A, which contains two sub-reference AOIs, A1 and A2. Figure 2 As shown, after entering the reference AOI area A from gate c, the user first enters A1 for sightseeing and then enters A2 for sightseeing, and then leaves from gate d. Of course, the user can also leave after only visiting A1, which is not limited here. The time spent by the user visiting A1 and A2 during the preset popular time period can be calculated separately. For example, it can be determined based on the trajectory information whether there are continuous third preset time lengths, such as 1 minute or more, in the area where A1 is located after user A first enters the area where A1 is located. If so, the time corresponding to the first trajectory point after the third preset time length is used as the entry time t11 of entering A1; it can be determined based on the trajectory information whether there are continuous fourth preset time lengths and the distance between the trajectory points and the area where A1 is located is all outside the second preset distance, such as 50m, after user A leaves the area where A1 is located on the same day. If so, the first trajectory point after the fourth preset time length is used as the departure time t12 of leaving A1, and then the time consumed by user A to visit A1 during the preset popular time period is calculated as t10= t12-t11. In this way, based on the trajectory information of multiple users, the time consumed by multiple users to visit A1 during the preset popular time period can be calculated, and the average value can be taken to obtain the time consumed by the user to visit A1 during the preset popular time period, and the time consumed by the user to visit A1 during the preset unpopular time period in each of the preset unpopular time periods can be estimated accordingly. Similarly, the time consumed by each time period of A2 can be calculated.

[0060] In this embodiment, the calibration factor corresponding to the target AOI is used to calibrate the tour time corresponding to the target AOI. When the tour time corresponding to the target AOI is divided into time periods, the calibration factor corresponding to the target AOI is also a calibration factor for divided time periods. The sum of the tour time corresponding to each sub-reference AOI in the same time period can be obtained, and the ratio of the sum to the time corresponding to the reference AOI in the same time period can be used as the calibration factor of the target AOI in the same time period. When the tour time corresponding to the target AOI does not distinguish between time periods, the calibration factor corresponding to the target AOI is also a calibration factor that does not distinguish between time periods. The sum of the tour time corresponding to each sub-reference AOI (i.e., the weighted average time of each popular time period and the unpopular time period corresponding to the sub-reference AOI) can be used, and the ratio of the sum to the time corresponding to the reference AOI can be used as the calibration factor of the target AOI.

[0061] In this implementation, when a user visits a reference AOI, he or she may not visit all the sub-reference AOIs of the reference AOI, so the calculated visit duration of the reference AOI may be inaccurate, and the sum of the time consumption corresponding to each sub-reference AOI can accurately reflect the time consumption required to visit all the sub-reference AOIs in the AOI to a certain extent, so the sum value / the time consumption corresponding to the reference AOI can be used as the calibration factor corresponding to the target AOI. When the ratio is less than 1, it means that the visit duration corresponding to the reference AOI exceeds the sum of the time consumption required to visit all the sub-reference AOIs in the AOI, and the visit duration is too high. At this time, by The calibration factor can reduce the tour time corresponding to the target AOI to avoid the tour time corresponding to the reference AOI being too long, resulting in the estimated tour time of the target AOI being too long; when the ratio is greater than 1, it means that the tour time corresponding to the reference AOI is less than the sum of the tour times required for all sub-reference AOIs in the AOI, and the tour time is too low. At this time, the calibration factor can be used to increase the tour time corresponding to the target AOI to avoid the tour time corresponding to the reference AOI being too short, resulting in the estimated tour time of the target AOI being too short; in this way, the accuracy of the estimated tour time of the target AOI can be improved.

[0062] Figure 3 FIG. 1 is a block diagram showing a time-consuming estimation device provided by an embodiment of the present disclosure. The device can be implemented as part or all of an electronic device through software, hardware, or a combination of both. Figure 3 As shown, the time consumption estimation device includes:

[0063] The trajectory acquisition module 301 is configured to acquire the trajectory information of the user when visiting the target area of ​​interest AOI in each preset popular time period; the trajectory information includes the trajectory point position and the trajectory point time; The first calculation module 302 is configured to calculate the popular time period consumption of the user visiting the target AOI in each preset popular time period based on the trajectory information; The second calculation module 303 is configured to calculate, for each preset unpopular time period, a weight coefficient for weighting the time consumption in the popular time period; the weight coefficient of an unpopular time period is used to calculate the unpopular time period consumption for visiting the target AOI in the unpopular time period; The third calculation module 304 is configured to calculate the unpopular time period consumption of the user visiting the target AOI in each preset unpopular time period based on the popular time period consumption and the weight coefficient.

[0064] In a possible implementation manner, for each preset unpopular time period, calculating a weight coefficient for weighted calculation of the time consumption of the popular time period includes: For each preset unpopular time period, a weight coefficient for weighting the time consumption of the popular time period is calculated based on an exponential moving average model.

[0065] In a possible implementation, obtaining the trajectory information of the user when visiting the target area of ​​interest AOI during each preset popular time period includes: Determine whether the target AOI is a hot AOI; If yes, then obtain the trajectory information of the user when visiting the target AOI during each preset popular time period.

[0066] In a possible implementation, the method further includes: If the target AOI is a less popular AOI, determine the cluster where the target AOI is located; wherein the cluster includes multiple AOIs similar to the target AOI; A popular AOI in the cluster is selected as a reference AOI; the time consumption of visiting the reference AOI is known; The time consumed by the user to visit the target AOI is calculated based on the time consumed in each popular time period and the time consumed in each unpopular time period corresponding to the reference AOI.

[0067] In a possible implementation, before determining the cluster where the target AOI is located, clustering multiple preset AOIs, where the multiple preset AOIs include the target AOI; clustering the multiple preset AOIs includes: Acquire feature information of the plurality of preset AOIs; AOI clustering is performed based on the feature information of the plurality of preset AOIs to obtain clusters, each of which includes a plurality of similar AOIs, and one of the clusters includes the target AOI.

[0068] In a possible implementation, the calculating the time consumed by the user to visit the target AOI based on the time consumed in each popular time period and the time consumed in each unpopular time period corresponding to the reference AOI includes: Obtaining a calibration factor corresponding to the target AOI; Calculating an area ratio of the target AOI to the reference AOI; The visiting time of the target AOI is calculated according to the calibration factor, the area ratio, and the visiting time corresponding to the reference AOI.

[0069] In a possible implementation manner, obtaining a calibration factor corresponding to the target AOI includes: Obtain the average time consumption corresponding to each popular AOI in the cluster; The ratio of the average value to the time consumption corresponding to the reference AOI is calculated as a calibration factor corresponding to the target AOI.

[0070] In a possible implementation manner, the time consumption of visiting each sub-reference AOI in the reference AOI is known; and obtaining the calibration factor corresponding to the target AOI includes: Obtain the sum of the time consumption corresponding to each sub-reference AOI; The ratio of the sum value to the time consumption corresponding to the reference AOI is calculated as a calibration factor corresponding to the target AOI.

[0071] In a possible implementation manner, the target AOI is a target area or a sub-area in the target area.

[0072] The technical terms and technical features mentioned in the implementation manner of this device are the same as or similar to the technical terms and technical features mentioned in the implementation manner of the above method. For the explanation and description of the technical terms and technical features involved in this device, reference may be made to the explanation and description of the implementation manner of the above method, and no further details will be given here.

[0073] The present disclosure also discloses an electronic device, Figure 4 A structural block diagram of an electronic device according to an embodiment of the present disclosure is shown.

[0074] like Figure 4 As shown, the electronic device 400 includes a memory 401 and a processor 402, wherein the memory 401 is used to store one or more computer instructions, wherein the one or more computer instructions are executed by the processor 402 to implement the method according to an embodiment of the present disclosure.

[0075] Figure 5 A schematic diagram showing the structure of a computer system suitable for implementing the method according to an embodiment of the present disclosure is shown.

[0076] like Figure 5 As shown, the computer system 500 includes a processing unit 501, which can perform various processes in the above-mentioned embodiments according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage part 508 to a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the computer system 500 are also stored. The processing unit 501, the ROM 502, and the RAM 503 are connected to each other through a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0077] The following components are connected to the I / O interface 505: an input section 506 including a keyboard, a mouse, etc.; an output section 507 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN card, a modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to the I / O interface 505 as needed. A removable medium 511, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 510 as needed, so that a computer program read therefrom is installed into the storage section 508 as needed. Among them, the processing unit 501 can be implemented as a processing unit such as a CPU, a GPU, a TPU, an FPGA, an NPU, etc.

[0078] In particular, according to an embodiment of the present disclosure, the method described above can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes computer instructions, and the computer instructions are executed by a processor to implement the method steps described above. In such an embodiment, the computer program product can be downloaded and installed from a network through the communication part 509, and / or installed from a removable medium 511.

[0079] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0080] The units or modules involved in the embodiments described in the present disclosure may be implemented by software or programmable hardware. The units or modules described may also be set in a processor, and the names of these units or modules do not constitute limitations on the units or modules themselves in some cases.

[0081] As another aspect, the present disclosure further provides a computer-readable storage medium, which may be a computer-readable storage medium included in the electronic device or computer system in the above embodiment; or a computer-readable storage medium that exists independently and is not assembled into a device. The computer-readable storage medium stores one or more programs, and the programs are used by one or more processors to execute the method described in the present disclosure.

[0082] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the present disclosure is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the inventive concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other.

Claims

1. A time consumption estimation method, characterized in that: include: Obtain the trajectory information of users browsing the target AOI during each preset popular time period; The trajectory information includes the trajectory point position and the trajectory point time; Based on the trajectory information, calculate the time consumed by the user to visit the target AOI during each preset popular time period; For each preset unpopular time period, a weight coefficient for weighting the time consumption of the popular time period is calculated; A weight coefficient of a cold period is used to calculate the cold period time consumption of visiting the target AOI in the cold period; The unpopular time period consumption of the user visiting the target AOI in each preset unpopular time period is calculated based on the popular time period consumption and the weight coefficient.

2. The method according to claim 1, characterized in that The step of calculating, for each preset unpopular time period, a weight coefficient for weighting the time consumption of the popular time period includes: For each preset unpopular time period, a weight coefficient for weighting the time consumption of the popular time period is calculated based on an exponential moving average model.

3. The method according to claim 1, characterized in that The step of obtaining the trajectory information of the user when browsing the target area of ​​interest AOI during each preset popular time period includes: Determine whether the target AOI is a hot AOI; If yes, then obtain the trajectory information of the user when visiting the target AOI during each preset popular time period.

4. The method according to claim 3, characterized in that The method further comprises: If the target AOI is a less popular AOI, determine the cluster where the target AOI is located; wherein the cluster includes multiple AOIs similar to the target AOI; A popular AOI in the cluster is selected as a reference AOI; the time consumption of visiting the reference AOI is known; The time consumed by the user to visit the target AOI is calculated based on the time consumed in each popular time period and the time consumed in each unpopular time period corresponding to the reference AOI.

5. The method according to claim 4, characterized in that Before determining the cluster where the target AOI is located, clustering a plurality of preset AOIs, wherein the plurality of preset AOIs include the target AOI; The clustering of the plurality of preset AOIs comprises: Acquire feature information of the plurality of preset AOIs; AOI clustering is performed based on the feature information of the plurality of preset AOIs to obtain clusters, each of which includes a plurality of similar AOIs, and one of the clusters includes the target AOI.

6. The method according to claim 4, characterized in that The calculating the time consumed by the user to visit the target AOI based on the time consumed in each popular time period and the time consumed in each unpopular time period corresponding to the reference AOI includes: Obtaining a calibration factor corresponding to the target AOI; Calculating an area ratio of the target AOI to the reference AOI; The visiting time of the target AOI is calculated according to the calibration factor, the area ratio, and the visiting time corresponding to the reference AOI.

7. The method according to claim 6, characterized in that The obtaining of the calibration factor corresponding to the target AOI includes: Obtain the average time consumption corresponding to each popular AOI in the cluster; The ratio of the average value to the time consumption corresponding to the reference AOI is calculated as a calibration factor corresponding to the target AOI.

8. The method according to claim 6, characterized in that The time consumption of visiting each sub-reference AOI in the reference AOI is known; the step of obtaining the calibration factor corresponding to the target AOI includes: Obtain the sum of the time consumption corresponding to each sub-reference AOI; The ratio of the sum value to the time consumption corresponding to the reference AOI is calculated as a calibration factor corresponding to the target AOI.

9. The method according to claim 1, characterized in that: The target AOI is a target area or a sub-area in the target area.

10. A time consumption estimation device, characterized in that: include: A trajectory acquisition module is configured to acquire trajectory information of a user when browsing a target area of ​​interest AOI during each preset popular time period; The trajectory information includes the trajectory point position and the trajectory point time; A first calculation module is configured to calculate the popular time period consumption of the user visiting the target AOI in each preset popular time period based on the trajectory information; A second calculation module is configured to calculate, for each preset unpopular time period, a weight coefficient for weighted calculation of the time consumption of the popular time period; A weight coefficient of a cold period is used to calculate the cold period time consumption of visiting the target AOI in the cold period; The third calculation module is configured to calculate the unpopular time period consumption of the user visiting the target AOI in each preset unpopular time period based on the popular time period consumption and the weight coefficient.

Images