Cut-check method, device and equipment for throwing event, readable storage medium and product

Abstract

The invention relates to a throwing event spot check method, device and equipment, a readable storage medium and a product, and relates to the technical field of logistics. The method comprises the following steps: in response to a throwing event spot check instruction, obtaining historical snapshot information corresponding to each preset spot check combination; the preset spot check combination refers to a combination between each candidate camera and each preset time period in the time period; on the basis of the historical snapshot information, performing spot check weight adjustment on each preset spot check combination to obtain a current spot check weight corresponding to each preset spot check combination; according to the current spot check weight, determining a first spot check probability corresponding to each candidate camera and a second spot check probability corresponding to each preset time period; and executing a throwing event spot check action corresponding to the throwing event spot check instruction based on the first spot check probability and the second spot check probability. By adopting the method, the casual inspection accuracy of the throwing event can be improved.

Description

Technical Field

[0001] This application relates to the field of logistics technologies, and particularly to a method, device, equipment, readable storage medium, and product for spot-checking throwing events. Background Art

[0002] In recent years, with the development of the logistics industry, in order to pursue timeliness, during the process of sorting items, item sorters may perform violent sorting behaviors, such as throwing or kicking items. These behaviors are likely to damage the items, resulting in huge compensation for express delivery companies.

[0003] Therefore, in response to this phenomenon, the prior art proposes a method of spot-checking whether there are illegal throwing behaviors through camera monitoring and subsequent manual spot-checks to reduce the occurrence of throwing events. However, the hit rate of this spot-checking method is not high, resulting in a relatively low accuracy rate of spot-checking for current throwing events. Summary of the Invention

[0004] Based on this, in view of the above technical problems, it is necessary to provide a method, device, computer equipment, computer readable storage medium, and computer program product for spot-checking throwing events that can improve the accuracy rate of spot-checking for throwing events.

[0005] In a first aspect, this application provides a method for spot-checking throwing events. The method includes: in response to a throwing event spot-checking instruction, obtaining historical capture information corresponding to each preset spot-check combination; a preset spot-check combination refers to the combination between each candidate camera and each preset time period within a time cycle; based on the historical capture information, adjusting the spot-check weights for each preset spot-check combination to obtain the current spot-check weights corresponding to each preset spot-check combination; according to the current spot-check weights, determining the first spot-check probability corresponding to each candidate camera and the second spot-check probability corresponding to each preset time period; based on the first spot-check probability and the second spot-check probability, performing a throwing event spot-checking action corresponding to the throwing event spot-checking instruction.

[0006] In a second aspect, this application also provides a device for spot-checking throwing events. The device includes: an obtaining capture information module, configured to obtain historical capture information corresponding to each preset spot-check combination in response to a throwing event spot-checking instruction; a preset spot-check combination refers to the combination between each candidate camera and each preset time period within a time cycle; a weight adjustment module, configured to adjust the spot-check weights for each preset spot-check combination based on the historical capture information to obtain the current spot-check weights corresponding to each preset spot-check combination; a determining spot-check probability module, configured to determine the first spot-check probability corresponding to each candidate camera and the second spot-check probability corresponding to each preset time period according to the current spot-check weights; an executing spot-check behavior module, configured to perform a throwing event spot-checking action corresponding to the throwing event spot-checking instruction based on the first spot-check probability and the second spot-check probability.

[0007] In a third aspect, the present application also provides a computer device. The computer device includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the following steps are implemented: in response to a throwing event sampling instruction, obtain historical capture information corresponding to each preset sampling combination; a preset sampling combination refers to a combination between each candidate camera and each preset time period within a time cycle; based on the historical capture information, adjust the sampling weights of each preset sampling combination to obtain the current sampling weights corresponding to each preset sampling combination; according to the current sampling weights, determine the first sampling probability corresponding to each candidate camera and the second sampling probability corresponding to each preset time period; based on the first sampling probability and the second sampling probability, perform a throwing event sampling action corresponding to the throwing event sampling instruction.

[0008] In a fourth aspect, the present application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented: in response to a throwing event sampling instruction, obtain historical capture information corresponding to each preset sampling combination; a preset sampling combination refers to a combination between each candidate camera and each preset time period within a time cycle; based on the historical capture information, adjust the sampling weights of each preset sampling combination to obtain the current sampling weights corresponding to each preset sampling combination; according to the current sampling weights, determine the first sampling probability corresponding to each candidate camera and the second sampling probability corresponding to each preset time period; based on the first sampling probability and the second sampling probability, perform a throwing event sampling action corresponding to the throwing event sampling instruction.

[0009] In a fifth aspect, the present application also provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the following steps are implemented: in response to a throwing event sampling instruction, obtain historical capture information corresponding to each preset sampling combination; a preset sampling combination refers to a combination between each candidate camera and each preset time period within a time cycle; based on the historical capture information, adjust the sampling weights of each preset sampling combination to obtain the current sampling weights corresponding to each preset sampling combination; according to the current sampling weights, determine the first sampling probability corresponding to each candidate camera and the second sampling probability corresponding to each preset time period; based on the first sampling probability and the second sampling probability, perform a throwing event sampling action corresponding to the throwing event sampling instruction.

[0010] The above-mentioned method, device, computer equipment, computer-readable storage medium and computer program product for spot-checking throwing events first respond to a throwing event spot-checking instruction, obtain historical capture information corresponding to a preset spot-check combination composed of each candidate camera and each preset time period within a time period, and then based on the historical capture information, adjust the spot-check weights of each preset spot-check combination to obtain the current spot-check weights corresponding to each preset spot-check combination. By adjusting the spot-check weights corresponding to each preset spot-check combination in real time, it is convenient to update the spot-check probability in real time later, thereby improving the spot-check accuracy. Then, according to the current spot-check weights, determine the first spot-check probability corresponding to each candidate camera and the second spot-check probability corresponding to each preset time period. Based on the first spot-check probability and the second spot-check probability, and then according to the first spot-check probability, select the cameras to be spot-checked among the candidate cameras, and according to the second spot-check probability, select the time periods to be spot-checked among the preset time periods. Finally, perform the throwing event spot-checking action corresponding to the throwing event spot-checking instruction, that is, spot-check the throwing events of the cameras to be spot-checked during the time periods to be spot-checked. There is no need for manual spot-checking, which improves the spot-check efficiency, and by calculating the spot-check probability to perform the spot-check of throwing events, it is more accurate than manual work. Therefore, the accuracy of the throwing event spot-check is also improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 FIG. is a schematic diagram of an application scenario of a method for spot-checking throwing events in an embodiment;

[0012] Figure 2 FIG. is a schematic flowchart of a method for spot-checking throwing events in an embodiment;

[0013] Figure 3 FIG. is a schematic flowchart of calculating the spot-check probability in an embodiment;

[0014] Figure 4 FIG. is a schematic flowchart of determining the cameras to be spot-checked and the time periods to be spot-checked in an embodiment;

[0015] Figure 5 FIG. is a schematic flowchart of spot-check weight adjustment in an embodiment;

[0016] Figure 6 FIG. is a schematic flowchart of increasing the spot-check weight in an embodiment;

[0017] Figure 7 FIG. is a schematic flowchart of decreasing the spot-check weight in an embodiment;

[0018] Figure 8 FIG. is a schematic flowchart of comparing the spot-check weight with the weight threshold in an embodiment;

[0019] Figure 9 FIG. is a schematic flowchart of the specific process of a method for spot-checking throwing events in an embodiment;

[0020] Figure 10 Schematic diagram of the effect of the random inspection method for throwing events in an embodiment

[0021] Figure 11 Structural block diagram of the random inspection device for throwing events in an embodiment

[0022] Figure 12 Internal structure diagram of a computer device in an embodiment Detailed implementation manners

[0023] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, but not to limit the present application.

[0024] In recent years, with the development of the logistics industry, in order to pursue timeliness, during the process of sorting items, item sorters may perform violent sorting behaviors. For example, there may be phenomena such as throwing or kicking items. These behaviors are likely to damage the items, resulting in huge compensation for express delivery companies. Therefore, in response to this phenomenon, the prior art proposes a method of randomly inspecting through cameras and subsequent manual random inspections to check whether there are behaviors of illegally throwing items, so as to reduce the occurrence of throwing events. However, a large number of cameras require a huge amount of manpower for manual random inspections, and the hit rate of random inspections is uncertain. Moreover, the working hours in different regions and different factories are different, resulting in different probability distributions of throwing phenomena. Therefore, the accuracy rate of random inspections for throwing events in the prior art is relatively low.

[0025] The random inspection method for throwing events provided by the embodiments of the present disclosure can be applied to an application environment as shown in Figure 1 The application environment includes a server 102 and a terminal 104, and the server 102 communicates with the terminal 104. Specifically, the server 102 responds to a random inspection instruction for throwing events sent by the terminal 104, and obtains historical capture information corresponding to each preset random inspection combination; the preset random inspection combination refers to the combination between each candidate camera and each preset time period within a time cycle; the server 102 adjusts the random inspection weights of each preset random inspection combination based on the historical capture information to obtain the current random inspection weights corresponding to each preset random inspection combination; according to the current random inspection weights, determine the first random inspection probability corresponding to each candidate camera and the second random inspection probability corresponding to each preset time period; based on the first random inspection probability and the second random inspection probability, perform a random inspection action for throwing events corresponding to the random inspection instruction for throwing events. Among them, the server 102 can be implemented by an independent server or a server cluster composed of multiple servers, and the terminal 104 can be, but is not limited to, various desktop computers, laptop computers, smart phones, tablet computers, and Internet of Things devices.

[0026] In one embodiment, as Figure 2 shown, a sampling method for throwing events is provided. Taking the server 102 in Figure 1 as an example, the method includes the following steps:

[0027] Step S202, in response to a throwing event sampling instruction, obtain the historical capture information corresponding to each preset sampling combination; a preset sampling combination refers to the combination between each candidate camera and each preset time period within a time cycle.

[0028] Among them, the throwing event sampling instruction may refer to an instruction for sampling throwing events for each preset sampling combination. A preset sampling combination is the combination between each candidate camera and each preset time period within a time cycle. A candidate camera refers to a camera for monitoring and capturing throwing events, and there may be multiple candidate cameras. A preset time period refers to the time period for monitoring throwing events. Taking one day as an example, one day can be divided into 48 time periods based on half an hour, or other division benchmarks can be used for time period division, which can be set according to the actual situation. For example, assuming there are candidate cameras A and B, and preset time periods 1 and 2, then the preset sampling combinations can be camera A - time period 1, camera A - time period 2, camera B - time period 1, camera B - time period 2. The time cycle refers to a preset historical time cycle, which can be one week or one month, or even half a year. The specific time cycle is not limited here and can be adjusted according to the actual situation. Historical capture information refers to the capture information of each preset sampling combination for throwing events within the time cycle.

[0029] Specifically, when the server receives a throwing event sampling instruction initiated by the user through the terminal, it can first retrieve the combination of each online candidate camera and each preset time period within the historical time cycle, and then obtain the capture information of each candidate camera for throwing events in each preset time period within the historical time cycle.

[0030] In one embodiment, for offline cameras, that is, cameras that are not working, weight adjustment can still be performed on them, but subsequent sampling probability calculation and sampling task distribution can be skipped.

[0031] Step S204, based on the historical capture information, adjust the sampling weights of each preset sampling combination to obtain the current sampling weights corresponding to each preset sampling combination.

[0032] Among them, the current sampling weight may refer to the degree to which each preset sampling combination is sampled in this throwing event sampling, and the current sampling weight can be used to calculate the sampling probability corresponding to each preset sampling combination.

[0033] Specifically, after the server obtains the capture information of each preset spot-check combination for throwing events within the historical time period, according to the capture information, it can adjust the spot-check weights of each preset spot-check combination, that is, adjust the spot-check weights of each preset spot-check combination, so as to obtain the extraction weights of each preset spot-check combination in the current throwing event spot-check. The extraction weight adjustment can include weight increase and weight decrease, and different weight adjustment methods can be selected according to the historical capture information.

[0034] Step S206, determine the first spot-check probability corresponding to each candidate camera and the second spot-check probability corresponding to each preset time period according to the current spot-check weight.

[0035] Among them, the first spot-check probability can refer to the spot-check probability corresponding to each candidate camera, and the second spot-check probability can refer to the spot-check probability corresponding to each preset time period.

[0036] Specifically, according to the current spot-check weight, the first spot-check weight corresponding to each candidate camera and the second spot-check weight corresponding to each preset time period can be obtained, so as to calculate the first spot-check probability corresponding to each candidate camera according to the first spot-check weight, and calculate the second spot-check probability corresponding to each candidate camera according to the second spot-check weight.

[0037] Step S208, based on the first spot-check probability and the second spot-check probability, perform the throwing event spot-check action corresponding to the throwing event spot-check instruction.

[0038] Among them, the throwing event spot-check action can refer to issuing a throwing event spot-check task, and all combinations of cameras and time periods that need to be spot-checked can be included in this task.

[0039] Specifically, according to the first spot-check probability and the second spot-check probability, the server can generate a spot-check combination between the cameras and time periods that need to be spot-checked for throwing events. This spot-check combination can be a combination between the cameras to be spot-checked among the candidate cameras and the time periods to be spot-checked among the preset time periods, and summarize these combinations into a throwing event spot-check task for task issuance, facilitating relevant personnel to conduct spot-checks according to this task.

[0040] In this embodiment, in response to the throwing event spot-check instruction, the server obtains the historical capture information corresponding to the preset spot-check combinations composed of each candidate camera and each preset time period within the time period. Then, based on the historical capture information, the server adjusts the spot-check weights of each preset spot-check combination to obtain the current spot-check weights corresponding to each preset spot-check combination. By adjusting the spot-check weights corresponding to each preset spot-check combination in real time, it is convenient to update the spot-check probability in real time later, thereby improving the spot-check accuracy. Then, according to the current spot-check weights, the server determines the first spot-check probability corresponding to each candidate camera and the second spot-check probability corresponding to each preset time period. Based on the first spot-check probability and the second spot-check probability, and then according to the first spot-check probability, the server selects the cameras to be spot-checked from each candidate camera, and according to the second spot-check probability, selects the time periods to be spot-checked from each preset time period. Finally, the server performs the throwing event spot-check action corresponding to the throwing event spot-check instruction, that is, spot-checks the throwing events of the cameras to be spot-checked during the time periods to be spot-checked. There is no need for manual spot-check, which improves the spot-check efficiency. Moreover, by calculating the spot-check probability to perform the spot-check of the throwing event, it is more accurate than manual work. Therefore, the accuracy of the throwing event spot-check is also improved.

[0041] In one embodiment, as Figure 3 shown, determining the first spot-check probability corresponding to each candidate camera and the second spot-check probability corresponding to each preset time period according to the current spot-check weights includes:

[0042] Step S302, extract the first spot-check weights corresponding to each candidate camera and the second spot-check weights corresponding to each preset time period from the current spot-check weights; the first spot-check weight refers to the sum of the spot-check weights of each candidate camera in each preset time period, and the second spot-check weight refers to the sum of the spot-check weights of each candidate camera in each preset time period.

[0043] Specifically, since the current spot-check weight is the spot-check weight corresponding to each preset spot-check combination, this spot-check weight can be both the spot-check weight corresponding to the candidate camera in this preset spot-check combination and the spot-check weight corresponding to the preset time period in this preset spot-check combination. Therefore, according to the current spot-check weights corresponding to all preset spot-check combinations, the sum of the spot-check weights of each candidate camera in all preset time periods, that is, the first spot-check weight, can be calculated, and the sum of the spot-check weights of all candidate cameras in each preset time period, that is, the second spot-check weight, can be calculated.

[0044] Step S304, determine the first spot-check probability according to the first spot-check weight and determine the second spot-check probability according to the second spot-check weight.

[0045] Among them, the first spot-check probability can refer to the spot-check probability corresponding to each candidate camera, and the second spot-check probability can refer to the spot-check probability corresponding to each preset time period.

[0046] Specifically, after obtaining the first spot-check weight corresponding to each candidate camera, it can be input into a preset camera spot-check probability expression to calculate the first spot-check probability corresponding to each candidate camera. Similarly, the second spot-check weight corresponding to each preset time period is input into a preset time-period spot-check probability expression to calculate the second spot-check probability corresponding to each preset time period.

[0047] In one embodiment, the preset camera spot-check probability expression can be:

[0048]

[0049] where represents the first spot-check probability corresponding to candidate camera s, represents the sum of the spot-check weights of candidate camera s in all preset time periods, that is, the first spot-check weight corresponding to candidate camera s.

[0050] In one embodiment, the preset time-period spot-check probability expression can be:

[0051]

[0052] where represents the second spot-check probability corresponding to preset time period t, represents the sum of the spot-check weights of all candidate cameras in preset time period t, that is, the second spot-check weight corresponding to preset time period t.

[0053] In this embodiment, by extracting the first spot-check weight corresponding to each candidate camera to calculate the first spot-check probability corresponding to each candidate camera, and extracting the second spot-check weight corresponding to each preset time period to calculate the second spot-check probability corresponding to each preset time period, it is convenient to generate a new spot-check combination based on the first spot-check probability and the second spot-check probability, improving the accuracy of the new spot-check combination, and thus improving the spot-check hit rate of the throwing event.

[0054] In one embodiment, as Figure 4 shown, based on the first spot-check probability and the second spot-check probability, perform the throwing event spot-check actions corresponding to the throwing event spot-check instruction, including:

[0055] Step S402, select the cameras to be spot-checked among the candidate cameras based on the first spot-check probability.

[0056] Step S404, select the time periods to be spot-checked among the preset time periods based on the second spot-check probability.

[0057] Among them, the camera to be spot-checked refers to the camera selected from each candidate camera that needs to be spot-checked for throwing events. The time period to be spot-checked refers to the time period selected from each preset time period that needs to be spot-checked for throwing events. There can be multiple cameras to be spot-checked and time periods to be spot-checked.

[0058] Specifically, after the server obtains the first spot-check probability corresponding to each candidate camera and the second spot-check probability corresponding to each preset time period, it can randomly generate multiple new spot-check combinations according to the first spot-check probability and the second spot-check probability. The new spot-check combinations are the random combinations between each camera to be spot-checked and each time period to be spot-checked. In an example, the cameras to be spot-checked and time periods to be spot-checked with high spot-check probabilities can be combined. The specific combination method is not limited here and can be adjusted according to the actual situation.

[0059] Step S406: According to the camera to be spot-checked and the time period to be spot-checked, perform the throwing event spot-check action corresponding to the throwing event spot-check instruction.

[0060] Specifically, according to the camera to be spot-checked and the time period to be spot-checked, randomly generate multiple new spot-check combinations, summarize these spot-check combinations to obtain the throwing event spot-check task and issue it, so that relevant personnel can spot-check these new spot-check combinations according to this task.

[0061] In this embodiment, according to the spot-check probability corresponding to each candidate camera and the spot-check probability corresponding to each preset time period, a spot-check combination between the new camera to be spot-checked and the time period to be spot-checked is generated, effectively improving the spot-check hit rate.

[0062] In one embodiment, as Figure 5 shown, based on the historical capture information, adjust the spot-check weights of each preset spot-check combination to obtain the current spot-check weights corresponding to each preset spot-check combination, including:

[0063] Step S502: If there is a capture record corresponding to a preset spot-check combination in the historical capture information, increase the weight of the preset spot-check combination to obtain the first weight; the capture record refers to the record that the preset spot-check combination captures a throwing event.

[0064] Among them, the capture record can refer to the record that the preset spot-check combination captures a throwing event within a preset time. The preset time belongs to the time period, and the preset time can be yesterday, that is, the capture record can refer to the record that the preset spot-check combination captures a throwing event yesterday.

[0065] Specifically, if there is a record in the historical capture information that a preset spot-check combination captures a throwing event at a preset time such as yesterday, it means that this preset spot-check combination needs to be spot-checked frequently, then the weight of this preset spot-check combination can be increased to obtain the increased first weight.

[0066] Step S504, if there is no capture record in the historical capture information, reduce the weight of the preset random inspection combination to obtain a second weight.

[0067] Specifically, if there is no record of the preset random inspection combination capturing a throwing event within the preset time in the historical capture information, it indicates that this group of preset random inspection combinations does not require high-frequency random inspection, so the weight of this preset random inspection combination can be reduced to obtain the reduced second weight.

[0068] In this embodiment, according to the capture records of each preset random inspection combination, it is determined whether each preset random inspection combination needs to be randomly inspected frequently, so as to reasonably increase or decrease the weight, ensuring the accuracy of the random inspection weight, thereby improving the accuracy of the random inspection probability, and further improving the hit rate of the random inspection of throwing events.

[0069] In one embodiment, as Figure 6 shown, increasing the weight of the preset random inspection combination to obtain a first weight includes:

[0070] Step S602, obtain the historical weight corresponding to the preset random inspection combination; the historical weight refers to the weight obtained by the preset random inspection combination after the last weight adjustment.

[0071] Among them, the weight is adjusted in real time. For each random inspection of throwing events, the random inspection weight of each group of random inspection combinations needs to be adjusted. Therefore, if weight adjustment is required, the random inspection combination needs to have a corresponding historical weight. Due to the real-time nature of the weight, each weight adjustment can be made on the basis of the weight obtained after the last weight adjustment. For cameras without historical weights, such as newly added cameras, the weight can be initialized, that is, a new weight is created for it.

[0072] In one embodiment, each group of preset random inspection combinations will have an initial weight, that is, the initial weight. The initial weight can be calculated by collecting the number of throwing events captured by each group of preset random inspection combinations within the past number of days, such as within the past 30 days. In one example, the expression for initializing the weight can be:

[0073]

[0074] Among them, represents the initial weight of the preset random inspection combination between the candidate camera s and the preset time period t, i represents the number of days, represents the past number of days, represents the time period the number of throwing events within, is parameters of. As The higher the increase, the higher the initial weight of the preset sampling combination.

[0075] Step S604: Based on the capture records, determine the weight change information of the preset sampling combination within the time period.

[0076] Step S606: According to the weight adjustment ratios corresponding to the historical weight and the weight change information respectively, perform weight increase to obtain the first weight.

[0077] Among them, the weight change information refers to the change situation of the weight of the preset sampling combination within the time period. The weight adjustment ratio can refer to the coefficient of weight adjustment, and there is an adjustment coefficient corresponding to the historical weight and the weight change information respectively.

[0078] Specifically, after the server obtains the historical weight corresponding to the preset sampling combination and the weight change information of the preset sampling combination within the time period, it inputs them into the preset weight increase expression, and sets an appropriate weight adjustment ratio to calculate and obtain the first weight.

[0079] In one embodiment, the preset weight increase expression can be:

[0080]

[0081] Among them, s represents the candidate camera, t represents the preset time period,

[0082] represents the first weight of the preset sampling combination between the candidate camera s and the preset time period t, represents the historical weight of the preset sampling combination between the candidate camera s and the preset time period t, represents the weight adjustment ratio corresponding to the historical weight, i represents the number of days, T represents the time period, represents the quantity of throwing events within the time period T, is a parameter of represents the weight adjustment ratio corresponding to the weight change information. In one example, can be set to 0.2, can be set to 0.8.

[0083] In this embodiment, by inputting the historical weight and the weight change information into the preset weight increase expression and setting a reasonable weight adjustment ratio to perform weight increase, the accuracy of the first weight corresponding to each preset sampling combination is ensured.

[0084] In one embodiment, as Figure 7 shown, perform weight reduction on the preset sampling combination to obtain the second weight, including:

[0085] Step S702: Obtain the historical weight corresponding to the preset spot-check combination and the weight reduction ratio corresponding to the historical weight.

[0086] Step S704: Based on the weight reduction ratio, perform weight reduction to obtain the second weight.

[0087] Among them, the weight reduction ratio can refer to the proportional coefficient for reducing the historical weight.

[0088] Specifically, after the server obtains the historical weight of the preset spot-check combination, it can input the historical weight into the pre-established weight reduction expression and set a reasonable weight reduction ratio, so as to calculate the second weight corresponding to each preset spot-check combination.

[0089] In one embodiment, the preset weight reduction expression can be:

[0090]

[0091] Among them, represents the weight reduction ratio corresponding to the historical weight. In one example, considering that if the weight drops too fast, it is easy to cause the spot-check probability of the camera with high-frequency throwing to drop rapidly after a few days of spot-checking, and if it is too slow, the camera will still be spot-checked frequently after the throwing behavior is improved. Therefore, through experiments, can be set to 0.6

[0092] In this embodiment, by inputting the historical weight into the preset weight reduction expression and setting a reasonable weight reduction ratio to perform weight reduction, the accuracy of the second weight corresponding to each preset spot-check combination is ensured.

[0093] In one embodiment, as Figure 8 shown, according to the current spot-check weight, determine the first spot-check probability corresponding to each candidate camera and the second spot-check probability corresponding to each preset time period, including:

[0094] Step S802: If the current spot-check weight exceeds the preset weight threshold, then execute the steps: Perform the spot-check behavior of the throwing event corresponding to the throwing event spot-check instruction.

[0095] Among them, the preset weight threshold can refer to the preset weight value, which can be used to determine whether to directly perform the spot-check of the throwing event on the preset spot-check combination.

[0096] Specifically, if the current spot-check weight of the preset spot-check combination exceeds the preset weight threshold, it means that the amount of throwing events captured within the time period is relatively large. Therefore, it needs to be taken as a key spot-check object, and then the spot-check of the throwing event can be directly performed on the preset spot-check combination.

[0097] Step S804: If the current sampling weight does not exceed the preset weight threshold, determine the first sampling probability corresponding to each candidate camera and the second sampling probability corresponding to each preset time period according to the current sampling weight.

[0098] Specifically, if the current sampling weight of the preset sampling combination does not exceed the preset weight threshold, it indicates that the amount of littering events captured within the time period is not very large. Then, the calculation of the sampling probability can be further carried out to select the cameras and time periods to be sampled, and conduct littering event sampling on the cameras and time periods to be sampled.

[0099] In this embodiment, by combining the preset sampling combinations whose current sampling weight exceeds the preset weight threshold and the sampling combinations between the cameras to be sampled and the time periods to be sampled generated according to the sampling probability, littering event sampling is carried out, effectively improving the sampling hit rate.

[0100] In a specific embodiment, as Figure 9 shown, the method for sampling littering events further includes a task initialization module and a task update module. The task initialization module is the process of generating the initial sampling tasks for littering events for the preset sampling combinations between each camera and each time period. First, the historical event volume of each combination of camera and time period can be obtained. The historical event volume is the amount of littering events captured by each combination of camera and time period in the past number of days, so as to calculate the initial weight corresponding to each sampling combination, that is, weight initialization. Then, calculate the sampling probability corresponding to each sampling combination, and then generate the corresponding sampling tasks. In the task update module, first obtain the historical weight of each sampling combination and the amount of littering events captured within the time period, that is, the capture record. If the sampling combination has a historical weight and has captured littering events, its weight is weighted and updated, that is, the weight is increased. If the sampling combination has a historical weight but has not captured littering events, the weight is attenuated, that is, the weight is decreased. For the sampling combination without historical weight but with captured littering events, its weight can be initialized, that is, recalculate its weight. After calculating the current sampling weight of each sampling combination, further detect whether the cameras in each sampling combination are in an offline state. If so, no subsequent sampling probability calculation and sampling task distribution are performed. If not, according to the current sampling weight of each sampling combination, calculate the sampling probability corresponding to each camera and each time period respectively, so as to generate a new sampling combination, and generate a sampling task for the new sampling combination and distribute it, facilitating relevant personnel to conduct littering event sampling according to the sampling task.

[0101] In this embodiment, the spot-check task is defined as a combination of a camera and a time period. By initializing weights, the weights are reasonably allocated to achieve the purpose that the events closer to the current day have a greater impact on the weights, and the farther ones have a smaller impact. During the spot-check every day, the combined weights of the camera and the time period are updated in real time, and their spot-check probabilities are calculated. As Figure 10 shown, under the same server resources, the results before position t are the results of manual spot-checks, and the results after position t are the results of spot-checks using the solution of this embodiment. Compared with the previous manual spot-checks, when using the solution in this embodiment to conduct spot-checks on throwing events, the amount of throwing events triples, greatly improving the hit rate of throwing events, increasing the resource utilization rate, and saving server resources.

[0102] It should be understood that although the steps in the flowcharts involved in the above embodiments are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same moment, but can be executed at different moments. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.

[0103] Based on the same inventive concept, the embodiment of the present application also provides a spot-check device for throwing events for implementing the spot-check method for throwing events involved above. The solution provided by this device to solve the problem is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the spot-check device for throwing events provided below can refer to the limitations on the spot-check method for throwing events in the above text, and will not be repeated here.

[0104] In one embodiment, as Figure 11As shown, a sampling device for throwing events is provided, including: an obtaining capture information module 1102, a weight adjustment module 1104, a determining sampling probability module 1106, and an executing sampling behavior module 1108, where: The obtaining capture information module 1102 is configured to obtain historical capture information corresponding to each preset sampling combination in response to a throwing event sampling instruction; the preset sampling combination refers to the combination between each candidate camera and each preset time period within a time cycle; The weight adjustment module 1104 is configured to adjust the sampling weight of each preset sampling combination based on the historical capture information to obtain the current sampling weight corresponding to each preset sampling combination; The determining sampling probability module 1106 is configured to determine a first sampling probability corresponding to each candidate camera and a second sampling probability corresponding to each preset time period according to the current sampling weight; The executing sampling behavior module 1108 is configured to execute a throwing event sampling action corresponding to the throwing event sampling instruction based on the first sampling probability and the second sampling probability.

[0105] In one embodiment, the determining sampling probability module 1106 is further configured to: extract a first sampling weight corresponding to each candidate camera and a second sampling weight corresponding to each preset time period from the current sampling weight; the first sampling weight refers to the sum of the sampling weights of each candidate camera in each preset time period, and the second sampling weight refers to the sum of the sampling weights of each candidate camera in each preset time period; determine the first sampling probability according to the first sampling weight and determine the second sampling probability according to the second sampling weight.

[0106] In one embodiment, the executing sampling behavior module 1108 is further configured to: select a camera to be sampled from each candidate camera based on the first sampling probability; select a time period to be sampled from each preset time period based on the second sampling probability; execute a throwing event sampling action corresponding to the throwing event sampling instruction according to the camera to be sampled and the time period to be sampled.

[0107] In one embodiment, the weight adjustment module 1104 further includes: a weight increasing unit configured to increase the weight of a preset sampling combination to obtain a first weight if there is a capture record corresponding to the preset sampling combination in the historical capture information; the capture record refers to a record of the preset sampling combination capturing a throwing event; a weight decreasing unit configured to decrease the weight of the preset sampling combination to obtain a second weight if there is no capture record in the historical capture information.

[0108] In one embodiment, the weight increasing unit is further configured to: obtain the historical weight corresponding to the preset sampling combination; the historical weight refers to the weight obtained after the last weight adjustment of the preset sampling combination; determine the weight change information of the preset sampling combination within the time cycle based on the capture record; perform weight increase according to the weight adjustment ratios corresponding to the historical weight and the weight change information respectively to obtain the first weight.

[0109] In one embodiment, the weight reduction unit is further configured to: obtain the historical weight corresponding to the preset spot-check combination and the weight reduction ratio corresponding to the historical weight; and perform weight reduction based on the weight reduction ratio to obtain the second weight.

[0110] In one embodiment, the spot-check probability determination module 1106 is further configured to: if the current spot-check weight exceeds the preset weight threshold, execute the steps of performing the spot-check behavior of the throwing event corresponding to the throwing event spot-check instruction; if the current spot-check weight does not exceed the preset weight threshold, determine the first spot-check probability corresponding to each candidate camera and the second spot-check probability corresponding to each preset time period according to the current spot-check weight.

[0111] Each module in the above-mentioned spot-check device for throwing events can be implemented in whole or in part by software, hardware, and their combination. The above-mentioned modules can be embedded in the processor in the computer device in hardware form or be independent of it, or can be stored in the memory in the computer device in software form so that the processor can call and execute the operations corresponding to the above-mentioned modules.

[0112] In one embodiment, a computer device is provided. The computer device can be a server, and its internal structure diagram can be as Figure 12 shown. The computer device includes a processor, a memory, and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store item recommendation data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it implements a method for spot-checking throwing events.

[0113] Those skilled in the art can understand that Figure 12 the structure shown in

[0114] In one embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory. When the processor executes the computer program, the following steps are implemented: in response to a throwing event spot-check instruction, obtain the historical capture information corresponding to each preset spot-check combination; a preset spot-check combination refers to the combination between each candidate camera and each preset time period within a time cycle; based on the historical capture information, adjust the spot-check weights of each preset spot-check combination to obtain the current spot-check weights corresponding to each preset spot-check combination; according to the current spot-check weights, determine the first spot-check probability corresponding to each candidate camera and the second spot-check probability corresponding to each preset time period; based on the first spot-check probability and the second spot-check probability, perform a throwing event spot-check action corresponding to the throwing event spot-check instruction.

[0115] In one embodiment, when the processor executes the computer program, the following steps are further implemented: extract from the current spot-check weights the first spot-check weights corresponding to each candidate camera and the second spot-check weights corresponding to each preset time period; the first spot-check weight refers to the sum of the spot-check weights of each candidate camera under each preset time period, and the second spot-check weight refers to the sum of the spot-check weights of each candidate camera under each preset time period; determine the first spot-check probability according to the first spot-check weights and determine the second spot-check probability according to the second spot-check weights.

[0116] In one embodiment, when the processor executes the computer program, the following steps are further implemented: based on the first spot-check probability, select a camera to be spot-checked from each candidate camera; based on the second spot-check probability, select a time period to be spot-checked from each preset time period; according to the camera to be spot-checked and the time period to be spot-checked, perform a throwing event spot-check action corresponding to the throwing event spot-check instruction.

[0117] In one embodiment, when the processor executes the computer program, the following steps are further implemented: if there is a capture record corresponding to a preset spot-check combination in the historical capture information, increase the weight of the preset spot-check combination to obtain a first weight; a capture record refers to a record that a preset spot-check combination captures a throwing event; if there is no capture record in the historical capture information, decrease the weight of the preset spot-check combination to obtain a second weight.

[0118] In one embodiment, when the processor executes the computer program, the following steps are further implemented: obtain the historical weight corresponding to a preset spot-check combination; the historical weight refers to the weight obtained after the last weight adjustment of the preset spot-check combination; based on the capture record, determine the weight change information of the preset spot-check combination within a time cycle; according to the weight adjustment ratios corresponding to the historical weight and the weight change information respectively, perform a weight increase to obtain a first weight.

[0119] In one embodiment, when the processor executes the computer program, the following steps are further implemented: obtaining the historical weight corresponding to the preset spot-check combination and the weight reduction ratio corresponding to the historical weight; based on the weight reduction ratio, performing weight reduction to obtain the second weight.

[0120] In one embodiment, when the processor executes the computer program, the following steps are further implemented: if the current spot-check weight exceeds the preset weight threshold, then execute the steps: performing the throwing event spot-check behavior corresponding to the throwing event spot-check instruction; if the current spot-check weight does not exceed the preset weight threshold, then according to the current spot-check weight, determining the first spot-check probability corresponding to each candidate camera and the second spot-check probability corresponding to each preset time period.

[0121] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by the processor, the following steps are implemented: in response to the throwing event spot-check instruction, obtaining the historical capture information corresponding to each preset spot-check combination; the preset spot-check combination refers to the combination between each candidate camera and each preset time period within the time period; based on the historical capture information, adjusting the spot-check weight of each preset spot-check combination to obtain the current spot-check weight corresponding to each preset spot-check combination; according to the current spot-check weight, determining the first spot-check probability corresponding to each candidate camera and the second spot-check probability corresponding to each preset time period; based on the first spot-check probability and the second spot-check probability, performing the throwing event spot-check action corresponding to the throwing event spot-check instruction.

[0122] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: extracting, from the current spot-check weight, the first spot-check weight corresponding to each candidate camera and the second spot-check weight corresponding to each preset time period; the first spot-check weight refers to the sum of the spot-check weights of each candidate camera under each preset time period, and the second spot-check weight refers to the sum of the spot-check weights of each candidate camera under each preset time period; determining the first spot-check probability according to the first spot-check weight and determining the second spot-check probability according to the second spot-check weight.

[0123] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: based on the first spot-check probability, selecting the cameras to be spot-checked among the candidate cameras; based on the second spot-check probability, selecting the time periods to be spot-checked among the preset time periods; according to the cameras to be spot-checked and the time periods to be spot-checked, performing the throwing event spot-check action corresponding to the throwing event spot-check instruction.

[0124] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: If there is a capture record corresponding to a preset spot-check combination in the historical capture information, the weight of the preset spot-check combination is increased to obtain a first weight; the capture record refers to the record of the preset spot-check combination capturing a throwing event; If there is no capture record in the historical capture information, the weight of the preset spot-check combination is decreased to obtain a second weight.

[0125] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: Obtain the historical weight corresponding to the preset spot-check combination; the historical weight refers to the weight obtained after the last weight adjustment of the preset spot-check combination; Based on the capture record, determine the weight change information of the preset spot-check combination within a time period; According to the weight adjustment ratios corresponding to the historical weight and the weight change information respectively, increase the weight to obtain a first weight.

[0126] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: Obtain the historical weight corresponding to the preset spot-check combination and the weight reduction ratio corresponding to the historical weight; Based on the weight reduction ratio, decrease the weight to obtain a second weight.

[0127] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: If the current spot-check weight exceeds the preset weight threshold, execute the steps: Perform the throwing event spot-check behavior corresponding to the throwing event spot-check instruction; If the current spot-check weight does not exceed the preset weight threshold, determine the first spot-check probability corresponding to each candidate camera and the second spot-check probability corresponding to each preset time period according to the current spot-check weight.

[0128] In one embodiment, a computer program product is provided, including a computer program, which when executed by a processor, implements the following steps: In response to a throwing event spot-check instruction, obtain the historical capture information corresponding to each preset spot-check combination; the preset spot-check combination refers to the combination between each candidate camera and each preset time period within a time period; Based on the historical capture information, adjust the spot-check weight of each preset spot-check combination to obtain the current spot-check weight corresponding to each preset spot-check combination; According to the current spot-check weight, determine the first spot-check probability corresponding to each candidate camera and the second spot-check probability corresponding to each preset time period; Based on the first spot-check probability and the second spot-check probability, perform the throwing event spot-check action corresponding to the throwing event spot-check instruction.

[0129] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: extracting, from the current sampling weight, the first sampling weight corresponding to each candidate camera and the second sampling weight corresponding to each preset time period; the first sampling weight refers to the sum of the sampling weights of each candidate camera under each preset time period, and the second sampling weight refers to the sum of the sampling weights of each candidate camera under each preset time period; determining a first sampling probability according to the first sampling weight and determining a second sampling probability according to the second sampling weight.

[0130] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: selecting, based on the first sampling probability, a camera to be sampled from each candidate camera; selecting, based on the second sampling probability, a time period to be sampled from each preset time period; and performing a throwing event sampling action corresponding to the throwing event sampling instruction according to the camera to be sampled and the time period to be sampled.

[0131] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: if there is a capture record corresponding to a preset sampling combination in the historical capture information, increasing the weight of the preset sampling combination to obtain a first weight; the capture record refers to a record of the preset sampling combination capturing a throwing event; if there is no capture record in the historical capture information, decreasing the weight of the preset sampling combination to obtain a second weight.

[0132] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: obtaining the historical weight corresponding to the preset sampling combination; the historical weight refers to the weight obtained after the last weight adjustment of the preset sampling combination; determining the weight change information of the preset sampling combination within a time period based on the capture record; and increasing the weight according to the weight adjustment ratios corresponding to the historical weight and the weight change information respectively to obtain a first weight.

[0133] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: obtaining the historical weight corresponding to the preset sampling combination and the weight reduction ratio corresponding to the historical weight; and reducing the weight based on the weight reduction ratio to obtain a second weight.

[0134] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: if the current sampling weight exceeds a preset weight threshold, performing the step of performing a throwing event sampling behavior corresponding to the throwing event sampling instruction; if the current sampling weight does not exceed the preset weight threshold, determining a first sampling probability corresponding to each candidate camera and a second sampling probability corresponding to each preset time period according to the current sampling weight.

[0135] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data that have been authorized by the user or fully authorized by all parties.

[0136] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the various embodiments provided in this application can include at least one of non-volatile and volatile memories. Non-volatile memory can include Read-Only Memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), etc. The databases involved in the various embodiments provided in this application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., and are not limited thereto. The processors involved in the various embodiments provided in this application can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., and are not limited thereto.

[0137] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the various technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0138] The above embodiments only illustrate several implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all fall within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims

1. A sampling method for throwing events, characterized in that, The method includes: In response to a throwing event spot-check instruction, obtaining historical capture information corresponding to each preset spot-check combination; the preset spot-check combination refers to the combination between each candidate camera and each preset time period within a time cycle; Based on the historical capture information, adjusting the spot-check weights of each of the preset spot-check combinations to obtain the current spot-check weights corresponding to each of the preset spot-check combinations; According to the current spot-check weights, determining a first spot-check probability corresponding to each of the candidate cameras and a second spot-check probability corresponding to each of the preset time periods; Based on the first spot-check probability and the second spot-check probability, performing a throwing event spot-check action corresponding to the throwing event spot-check instruction.

2. The method according to claim 1, characterized in that, The determining a first spot-check probability corresponding to each of the candidate cameras and a second spot-check probability corresponding to each of the preset time periods according to the current spot-check weights includes: Extracting from the current spot-check weights a first spot-check weight corresponding to each of the candidate cameras and a second spot-check weight corresponding to each of the preset time periods; the first spot-check weight refers to the sum of the spot-check weights of each candidate camera under each preset time period, and the second spot-check weight refers to the sum of the spot-check weights of each candidate camera under each preset time period; Determining the first spot-check probability according to the first spot-check weight and determining the second spot-check probability according to the second spot-check weight.

3. The method according to claim 1, wherein The performing a throwing event spot-check action corresponding to the throwing event spot-check instruction based on the first spot-check probability and the second spot-check probability includes: Based on the first spot-check probability, selecting a camera to be spot-checked from each of the candidate cameras; Based on the second spot-check probability, selecting a time period to be spot-checked from each of the preset time periods; According to the camera to be spot-checked and the time period to be spot-checked, performing a throwing event spot-check action corresponding to the throwing event spot-check instruction.

4. The method according to claim 1, characterized in that The current spot-check weights include a first weight and a second weight. The adjusting the spot-check weights of each of the preset spot-check combinations based on the historical capture information to obtain the current spot-check weights corresponding to each of the preset spot-check combinations includes: If there is a capture record corresponding to the preset spot-check combination in the historical capture information, increasing the weight of the preset spot-check combination to obtain the first weight; the capture record refers to the record that the preset spot-check combination captures the throwing event; If there is no such capture record in the historical capture information, decreasing the weight of the preset spot-check combination to obtain the second weight.

5. The method according to claim 4, characterized in that, The increasing the weight of the preset spot-check combination to obtain the first weight includes: Obtaining the historical weight corresponding to the preset spot-check combination; the historical weight refers to the weight obtained after the last weight adjustment of the preset spot-check combination; Based on the capture record, determining the weight change information of the preset spot-check combination within the time cycle; Performing weight increase according to the weight adjustment ratios corresponding to the historical weight and the weight change information respectively to obtain the first weight.

6. The method according to claim 4, wherein The decreasing the weight of the preset spot-check combination to obtain the second weight includes: Obtain the historical weight corresponding to the preset sampling combination, and the weight reduction ratio corresponding to the historical weight; Based on the weight reduction ratio, perform weight reduction to obtain the second weight.

7. The method according to claim 1, wherein The step of determining the first sampling probability corresponding to each of the candidate cameras and the second sampling probability corresponding to each of the preset time periods according to the current sampling weight further includes: If the current sampling weight exceeds a preset weight threshold, execute the step: perform the throwing event sampling behavior corresponding to the throwing event sampling instruction; If the current sampling weight does not exceed the preset weight threshold, determine the first sampling probability corresponding to each of the candidate cameras and the second sampling probability corresponding to each of the preset time periods according to the current sampling weight.

8. A sampling device for throwing events, characterized in that, The device includes: A capture information acquisition module, configured to acquire historical capture information corresponding to each preset sampling combination in response to a throwing event sampling instruction; the preset sampling combination refers to the combination between each candidate camera and each preset time period within a time cycle; A weight adjustment module, configured to adjust the sampling weight of each preset sampling combination based on the historical capture information to obtain the current sampling weight corresponding to each preset sampling combination; A sampling probability determination module, configured to determine the first sampling probability corresponding to each of the candidate cameras and the second sampling probability corresponding to each of the preset time periods according to the current sampling weight; A sampling behavior execution module, configured to execute the throwing event sampling action corresponding to the throwing event sampling instruction based on the first sampling probability and the second sampling probability.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the method according to any one of claims 1 to 7.

11. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the method according to any one of claims 1 to 7.

Images