Method, device, equipment, storage medium and product for determining shot point migration information

Abstract

Embodiments of the present application provide a method, device, equipment, storage medium and product for determining shot point offset information, belonging to the technical field of seismic exploration. The method comprises: obtaining a plurality of first target shot points arranged in an obstacle region in an exploration area; for each first target shot point, determining reward information of a plurality of first offset actions corresponding to a preset position of the first target shot point according to a pre-trained offset information model, determining a first target offset action with the maximum reward information value from the plurality of first offset actions; determining a new position of the shot point arrangement after the first target shot point performs the first target offset action; if the new position is in the obstacle region, determining at least one second target offset action according to the offset information model; and determining an offset path composed of the first target offset action and the at least one second target offset action as the offset information of the first target shot point. The above method can improve the efficiency of determining the offset information of the shot point.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of seismic exploration, and particularly relates to a method and device for determining shot point offset information, equipment, a storage medium and a product. BACKGROUND

[0002] At present, the seismic exploration technology is an important means for determining the oil and gas reserves of a reservoir. When the reservoir is explored, a plurality of shot points need to be arranged at a plurality of preset positions of the reservoir. However, when a preset position of a shot point is in an obstacle region, the shot point cannot be arranged in the obstacle region, and therefore, the preset position of the shot point needs to be adjusted according to shot point offset information, and then the shot point is arranged at the adjusted position. Therefore, for a shot point whose preset position is in an obstacle region, the offset information of the shot point needs to be determined before the shot point is arranged.

[0003] In the related art, a worker determines a first distance between a shot point and a left edge of an obstacle region and a second distance between the shot point and a right edge of the obstacle region by manually measuring, determines a target distance from the first distance and the second distance, and determines an offset path corresponding to the target distance as offset information of the target shot point.

[0004] However, in the above related art, when the number of target shot points is large, the workload of determining the offset information of the shot point by manual measurement is large, and therefore, the time for determining the offset information of the shot point is long, and therefore, the efficiency of determining the offset information of the shot point is low. SUMMARY

[0005] The embodiments of the present application provide a method and device for determining shot point offset information, equipment, a storage medium and a product, which can improve the efficiency of determining the offset information of the shot point. The technical solution is as follows:

[0006] In one aspect, the present application provides a method for determining shot point offset information, which comprises:

[0007] obtaining a plurality of first target shot points arranged in an obstacle region in an exploration work area;

[0008] For each first target shot point, determining reward information of a plurality of first offset actions corresponding to a preset position of the first target shot point according to a pre-trained offset information model, the offset information model being used for determining reward information based on a position and an offset action, the first offset action being used for moving the first target shot point out of the obstacle region from the preset position, and the reward information of the first offset action being used for indicating a contribution value of the first offset action for moving the first target shot point out of the obstacle region;

[0009] determining a first target steering action with the maximum reward information value from the plurality of first steering actions;

[0010] determining a new position of the gun location after the first target gun location performs the first target steering action;

[0011] if the new position is in the obstacle region, determining reward information of a plurality of second steering actions corresponding to the new position according to the steering information model, the second steering actions being used to move the first target gun location out of the obstacle region, and the reward information of the second steering actions being used to represent contribution values of the second steering actions to moving the first target gun location out of the obstacle region;

[0012] determining a second target steering action with the maximum reward information value from the plurality of second steering actions until a new position of the gun location after the second target steering action is performed is not in the obstacle region, and obtaining at least one second target steering action;

[0013] determining a steering path composed of the first target steering action and the at least one second target steering action as the steering information of the first target gun location.

[0014] In a possible implementation, a plurality of shooting lines are arranged in the exploration work area, and each shooting line is provided with a plurality of gun locations; and the process of determining the steering information model is as follows:

[0015] determining a target shooting line with the maximum number of gun locations arranged in the obstacle region from the plurality of shooting lines, and determining a plurality of second target gun locations arranged in the obstacle region on the target shooting line;

[0016] for each second target gun location, determining a plurality of positions on any feasible path for moving the second target gun location out of the obstacle region from a current position;

[0017] determining first reward information corresponding to the second target gun location, and obtaining a plurality of first reward information corresponding to the plurality of second target gun locations, the first reward information including reward information of a plurality of steering actions corresponding to the plurality of positions of the second target gun location;

[0018] training an initial steering information model based on the reward information of the plurality of steering actions corresponding to the plurality of positions of the plurality of second target gun locations, and obtaining the steering information model.

[0019] In another possible implementation, the determining the first reward information corresponding to the second target gun location includes:

[0020] For each position, determine second reward information corresponding to the second target shooting point at the position, to obtain a plurality of second reward information corresponding to the plurality of positions, the second reward information including expected reward information of a plurality of third bias actions of the second target shooting point at the position;

[0021] Determine the plurality of second reward information corresponding to the plurality of positions as the first reward information corresponding to the second target shooting point.

[0022] In another possible implementation, the determining the second reward information corresponding to the second target shooting point at the position includes:

[0023] Determine a plurality of third bias actions corresponding to the second target shooting point at the position;

[0024] For each third bias action, determine an immediate reward of performing the third bias action, and determine a long-term reward of performing the third bias action, the immediate reward being used to represent a current contribution value of the third bias action for the second target shooting point moving out of the obstacle region, and the long-term reward being used to represent a long-term contribution value of the third bias action for the second target shooting point moving out of the obstacle region;

[0025] Based on the immediate reward and the long-term reward, determine expected reward information corresponding to the third bias action, to obtain a plurality of expected reward information corresponding to a plurality of third bias actions;

[0026] Determine the plurality of expected reward information corresponding to the plurality of third bias actions as the second reward information corresponding to the second target shooting point at the position.

[0027] In another possible implementation, the determining the long-term reward of performing the third bias action includes:

[0028] Determine a new position of the second target shooting point after performing the third bias action;

[0029] Determine a plurality of fourth bias actions corresponding to the new position of the second target shooting point, for each fourth bias action, determine reward information corresponding to the fourth bias action, to obtain a plurality of reward information corresponding to the plurality of fourth bias actions, the reward information corresponding to the fourth bias action being used to represent a contribution value of the fourth bias action for the second target shooting point moving out of the obstacle region;

[0030] From the plurality of reward information, determine reward information with the maximum value as the long-term reward of performing the third bias action.

[0031] In another possible implementation, the determining of the expected reward information corresponding to the third offset action based on the immediate reward and the long-term reward comprises:

[0032] determining a discount coefficient corresponding to the third offset action;

[0033] determining the expected reward information corresponding to the third offset action based on the discount coefficient, the immediate reward and the long-term reward through Formula I:

[0034] Formula I: y = R + γmax a′ Q(S', a)

[0035] wherein y represents the expected reward information corresponding to the third offset action, R represents the immediate reward, γ represents the discount coefficient, max a′ Q(S', a) represents the long-term reward, S' represents a new position of the second target shot point after the third offset action is performed, a' represents a plurality of fourth offset actions corresponding to the new position of the second target shot point, and a represents any fourth offset action.

[0036] In another possible implementation, the training of the initial offset information model based on the reward information of the plurality of second target shot points in the plurality of positions corresponding to the plurality of offset actions comprises:

[0037] for each second target shot point, inputting the plurality of offset actions corresponding to the plurality of positions of the second target shot point into the initial offset information model, and outputting third reward information corresponding to the second target shot point, the third reward information comprising estimated reward information of the plurality of offset actions corresponding to the plurality of positions of the second target shot point;

[0038] determining a loss parameter between the third reward information and the first reward information, adjusting an offset parameter in the initial offset information model if the loss parameter is greater than a preset value, and stopping until the loss parameter is not greater than the preset value;

[0039] determining a target offset parameter corresponding to the loss parameter when the loss parameter is not greater than the preset value, and obtaining the offset information model.

[0040] In another aspect, the present application provides a determination device for shot point offset information, the device comprising:

[0041] an acquisition module configured to acquire a plurality of first target shot points arranged in an obstacle region in an exploration work area;

[0042] The first determining module is configured to determine, for each first target shot point, reward information of a plurality of first offset actions corresponding to a preset position of the first target shot point according to a pre-trained offset information model, the offset information model being configured to determine reward information based on a position and an offset action, the first offset action being configured to move the first target shot point out of the obstacle region from the preset position, the reward information of the first offset action being configured to represent a contribution value of the first offset action to moving the first target shot point out of the obstacle region.

[0043] The second determining module is configured to determine a first target offset action with the maximum reward information value from the plurality of first offset actions.

[0044] The third determining module is configured to determine a new position of shot point layout after the first target shot point performs the first target offset action.

[0045] The fourth determining module is configured to, if the new position is in the obstacle region, determine reward information of a plurality of second offset actions corresponding to the new position according to the offset information model, the second offset action being configured to move the first target shot point out of the obstacle region from the new position, the reward information of the second offset action being configured to represent a contribution value of the second offset action to moving the first target shot point out of the obstacle region.

[0046] The fifth determining module is configured to determine a second target offset action with the maximum reward information value from the plurality of second offset actions until a new position of shot point layout after the second target offset action is performed is not in the obstacle region, and obtain at least one second target offset action.

[0047] The sixth determining module is configured to determine an offset path composed of the first target offset action and the at least one second target offset action as offset information of the first target shot point.

[0048] In a possible implementation, the exploration work area is provided with a plurality of shot lines, and each shot line is provided with a plurality of shot points; the device further comprises a training module, and the training module comprises:

[0049] The first determining unit is configured to determine a target shot line with the largest number of shot points arranged in the obstacle region from the plurality of shot lines, and determine a plurality of second target shot points arranged in the obstacle region on the target shot line.

[0050] The second determining unit is configured to determine, for each second target shot point, a plurality of positions on any feasible path for moving the second target shot point out of the obstacle region from a current position.

[0051] The third determining unit is configured to determine first reward information corresponding to the second target shot point, and obtain a plurality of first reward information corresponding to a plurality of second target shot points, wherein the first reward information comprises reward information of a plurality of offset actions corresponding to the second target shot point at a plurality of positions.

[0052] The training unit is configured to train an initial offset information model based on the reward information of the plurality of offset actions corresponding to the plurality of positions of the plurality of second target shot points, and obtain the offset information model.

[0053] In another possible implementation, the third determining unit is configured to, for each position, determine second reward information corresponding to the second target shot point at the position, and obtain a plurality of second reward information corresponding to a plurality of positions, wherein the second reward information comprises expected reward information of a plurality of third offset actions corresponding to the second target shot point at the position; and determine the plurality of second reward information corresponding to the plurality of positions as the first reward information corresponding to the second target shot point.

[0054] In another possible implementation, the third determining unit is configured to determine a plurality of third offset actions corresponding to the second target shot point at the position; for each third offset action, determine an immediate reward of performing the third offset action, and determine a long-term reward of performing the third offset action, wherein the immediate reward is used to represent a current contribution value of the third offset action for the second target shot point to move out of the obstacle region, and the long-term reward is used to represent a long-term contribution value of the third offset action for the second target shot point to move out of the obstacle region; determine expected reward information corresponding to the third offset action based on the immediate reward and the long-term reward, and obtain a plurality of expected reward information corresponding to a plurality of third offset actions; and determine the plurality of expected reward information corresponding to the plurality of third offset actions as the second reward information corresponding to the second target shot point at the position.

[0055] In another possible implementation, the third determining unit is configured to determine a new position of the second target shot point after performing the third offset action; determine a plurality of fourth offset actions corresponding to the new position of the second target shot point, and for each fourth offset action, determine reward information corresponding to the fourth offset action, and obtain a plurality of reward information corresponding to a plurality of fourth offset actions, wherein the reward information corresponding to the fourth offset action is used to represent a contribution value of the fourth offset action for the second target shot point to move out of the obstacle region; and determine reward information with the largest value from the plurality of reward information as the long-term reward of performing the third offset action.

[0056] In another possible implementation, the training unit is configured to, for each second target shot point, input the initial offset information model into a plurality of offset actions corresponding to the second target shot point at a plurality of positions, output third reward information corresponding to the second target shot point, the third reward information including estimated reward information of the plurality of offset actions corresponding to the second target shot point at the plurality of positions; determine a loss parameter between the third reward information and the first reward information, and if the loss parameter is greater than a preset value, adjust an offset parameter in the initial offset information model until the loss parameter is not greater than the preset value; and determine a target offset parameter corresponding to when the loss parameter is not greater than the preset value, to obtain the offset information model.

[0057] In another aspect, the embodiments of the present application provide a computer device, which comprises a processor and a memory, and the memory stores at least one program code, and the at least one program code is loaded and executed by the processor to implement the operations performed by the method for determining shot offset information according to any possible implementation manner.

[0058] In another aspect, the embodiments of the present application provide a computer readable storage medium, which stores at least one program code, and the at least one program code is loaded and executed by a processor to implement the operations performed by the method for determining shot offset information according to any possible implementation manner.

[0059] In another aspect, the embodiments of the present application provide a computer program product, which comprises at least one program code, and the at least one program code is loaded and executed by a processor to implement the operations performed by the method for determining shot offset information according to any possible implementation manner.

[0060] The technical scheme provided by the embodiments of the present application has at least the following beneficial effects:

[0061] The method for determining shot offset information provided by the embodiments of the present application has the following beneficial effects: since the first target offset action corresponding to a target shot point at a preset position and the second target offset action corresponding to the target shot point at a new position are determined by using a pre-trained offset information model, and then the offset information corresponding to the target shot point is determined by using the first target offset action and the second target offset action, when the offset information of the target shot point is determined, only the position of the target shot point needs to be determined, so the efficiency of determining the shot offset information is improved. BRIEF DESCRIPTION OF DRAWINGS

[0062] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative effort.

[0063] Figure 1 is a flow chart of a determination method of shot point offset information according to an example embodiment;

[0064] Figure 2 is a schematic diagram of initial arrangement of obstacles and shot points according to an example embodiment;

[0065] Figure 3 is a schematic diagram of initial arrangement of obstacles and shot points according to an example embodiment;

[0066] Figure 4 is a schematic diagram of arrangement of obstacles and shot points after offset according to an example embodiment;

[0067] Figure 5 is a schematic diagram of arrangement of obstacles and shot points after offset according to an example embodiment;

[0068] Figure 6 is a flow chart of a training method of offset information model according to an example embodiment;

[0069] Figure 7 is a block diagram of a determination device of shot point offset information according to an example embodiment;

[0070] Figure 8 is a block diagram of a determination device of shot point offset information according to an example embodiment;

[0071] Figure 9 is a structural block diagram of a computer device according to an example embodiment. DETAILED DESCRIPTION

[0072] In order to make the purpose, technical solutions and advantages of the present application clearer, the embodiments of the present application will be further described in detail below with reference to the drawings.

[0073] Figure 1 is a flow chart of a determination method of shot point offset information according to an example embodiment, executed by a computer device. Referring to Figure 1 , the method comprises:

[0074] 101, the computer device obtains a plurality of first target shot points arranged in an obstacle region in an exploration work area.

[0075] In a possible implementation, the computer device determines a plurality of first target shot points according to the obstacle state information of the shot points. Correspondingly, the step is: the computer device acquires the obstacle state information of a plurality of shot points included in the exploration work area; and determines a plurality of first target shot points arranged in the obstacle region from the plurality of shot points according to the obstacle state information of the plurality of shot points. The obstacle state information is used to indicate whether the shot point is arranged in the obstacle region.

[0076] In a possible implementation, the obstacle state information includes a first value and a second value, the first value is used to indicate that the shot point is arranged in the obstacle region, and the second value is used to indicate that the shot point is not arranged in the obstacle region. Correspondingly, the step of the computer device acquiring the obstacle state information of a plurality of shot points included in the exploration work area is: the computer device acquires a target region where at least one obstacle in the exploration work area is located; for each shot point, determines a preset position of the shot point; and determines the obstacle state information of the shot point according to the preset position and the target region where the obstacle is located, to obtain the obstacle state information of a plurality of shot points included in the exploration work area.

[0077] Optionally, the first value is "1", and the second value is "0". If the preset position corresponding to the shot point is in the target region, the computer device determines that the obstacle state information of the shot point is "1"; if the preset position corresponding to the shot point is not in the target region, the computer device determines that the obstacle state information of the shot point is "0".

[0078] In a possible implementation, the number of obstacles in the exploration work area and the target region where the obstacles are located are fixed. The computer device stores a corresponding relationship between a work area identifier and the number of obstacles and the region where the obstacles are located. Correspondingly, the step of the computer device acquiring the target region where at least one obstacle in the exploration work area is located is: the computer device acquires a work area identifier of the exploration work area, and determines the target region where at least one obstacle in the exploration work area is located from the corresponding relationship between the work area identifier and the number of obstacles and the region where the obstacles are located, which has been stored. Optionally, the work area identifier is used to distinguish different exploration work areas. The work area identifier includes at least one of a number, a letter, and a number.

[0079] It should be noted that the number of obstacles in the exploration work area is one or more. In the embodiments of the present application, the number and shape of the obstacles are not limited, and can be set and modified as needed. For example, referring to Figure 2 , the number of obstacles is one, and the shape of the obstacle is a circle. For another example, referring to Figure 3 , the number of obstacles in the exploration work area is three, and the shapes of the three obstacles are a square, a rectangle, and an irregular shape.

[0080] In one possible implementation, the step of the computer device determining the obstacle status information of the firing point based on the preset location and the target area where the obstacle is located is as follows: if the preset location corresponding to the firing point is within the target area where the obstacle is located, the computer device determines the obstacle status information of the firing point to be a first value; if the preset location corresponding to the firing point is not within the target area where the obstacle is located, the computer device determines the obstacle status information of the firing point to be a second value.

[0081] In one possible implementation, the preset location of the first target shot point is its initial location within the exploration area. The computer device stores a correspondence between shot point identifiers and initial locations. Accordingly, the step of the computer device determining the preset location of the first target shot point is as follows: the computer device, based on the target shot point identifier of the first target shot point, determines the target initial location corresponding to the stored correspondence between shot point identifiers and initial locations as the preset location of the first target shot point. Optionally, the shot point identifier is used to distinguish multiple shot points. The shot point identifier includes at least one of numbers, letters, and serial numbers. For example, the shot point identifiers are 1, 2, 3, etc.

[0082] Optionally, the initial position is the coordinates of the shot point. For example, the initial position of shot point 1 is (0m, 25m), the initial position of shot point 2 is (0m, 50m), and the initial position of shot point 3 is (0m, 75m). In this embodiment, the number and arrangement of multiple shot points are not specifically limited and can be set and modified as needed.

[0083] In one possible implementation, multiple shot lines are set up within the exploration area, and multiple shot points are set up along the shot lines; the distance between any two adjacent shot points can be the same or different. Optionally, see [link to relevant documentation]. Figure 2 The distance between any two adjacent shot points is the same, and the shot spacing is a first preset distance. In this embodiment, the value of the first preset distance is not specifically limited and can be set and modified as needed. Optionally, the first preset distance is determined according to the scheme designed based on the seismic acquisition parameters. For example, the first preset spacing can be 20m, 30m, 40m, etc.

[0084] In one possible implementation, the step of the computer device determining multiple first target gun points deployed in the obstacle area from multiple gun points based on the obstacle state information of multiple gun points is as follows: for each gun point, if the obstacle state information of the gun point is a first value, the computer device determines that the gun point is a first target gun point, thus obtaining multiple first target gun points.

[0085] 102、The computer device determines, for each first target shot point, reward information of a plurality of first movement actions corresponding to the preset position of the first target shot point according to a pre-trained offset information model, the offset information model being used to determine reward information based on a position and a movement action, the first movement action being used to move the first target shot point out of the obstacle region from the preset position, and the reward information of the first movement action being used to represent a contribution value of the first movement action to moving the first target shot point out of the obstacle region.

[0086] In a possible implementation, the step is: the computer device determines, for each first target shot point, a preset position of the first target shot point and a plurality of first movement actions corresponding to the preset position; and inputs the preset position and each first movement action into an offset information model, outputs reward information corresponding to the preset position and each first movement action, and obtains reward information of the plurality of first movement actions corresponding to the preset position.

[0087] Optionally, the first movement action is one step to the left or one step to the right. The first target shot point is moved out of the obstacle region from the preset position through the first movement action. The reward information of one step to the left is used to represent a contribution value of one step to the left to moving the first target shot point out of the obstacle region, and the reward information of one step to the right is used to represent a contribution value of one step to the right to moving the first target shot point out of the obstacle region. In the embodiments of the present application, the step length of each step is not specifically limited, and can be set and modified according to actual acquisition design parameters. In a possible implementation, the step length is the same as the shot interval, or the step length is an integer multiple of the shot interval. Optionally, the step length can be any value between 5 m and 500 m, for example, 5 m, 10 m, 50 m, 150 m, etc. In a possible implementation, for each shot line, the shot interval between any two adjacent shot points on the shot line is the same.

[0088] 103、The computer device determines, from the plurality of first movement actions, a first target movement action with the maximum reward information value.

[0089] In the embodiments of the present application, the greater the reward information value of the first movement action, the greater the contribution of the first movement action to moving the first target shot point out of the obstacle region, and the higher the efficiency of the first target shot point in moving out of the obstacle region by performing the first movement action. That is, the first target movement action with the maximum reward information value is the optimal movement action.

[0090] 104、The computer device determines a new position of the shot point layout after the first target shot point performs the first target movement action.

[0091] In a possible implementation, the first target offset action is moving one step to the left or one step to the right; and the new position of the gun point layout after the first target offset action is performed can be determined according to the coordinates of the preset position, the direction and the step length of the first target offset action. Correspondingly, the step includes: if the first target offset action is moving one step to the left, the computer device determines the difference between the horizontal coordinate of the preset position and the step length as the horizontal coordinate of the new position, and determines the vertical coordinate of the preset position as the vertical coordinate of the new position; or if the first target offset action is moving one step to the right, the computer device determines the sum of the horizontal coordinate of the preset position and the step length as the horizontal coordinate of the new position, and determines the vertical coordinate of the preset position as the vertical coordinate of the new position.

[0092] For example, the step length of the first target offset action is the same as the gun interval, which is 20 m, and the coordinates of the preset position are (0 m, 0 m); the first target offset action is moving one step to the left; and the coordinates of the new position of the gun point layout after the first target gun point performs the first target offset action are (-20 m, 0 m).

[0093] In the embodiment of the application, after the computer device performs the first target offset action to obtain the new position of the gun point layout, it is determined whether the new position moves out of the obstacle region; if the new position of the gun point layout after the first target gun point performs the first target offset action is not in the obstacle region, the computer device determines the first target offset action as the offset information of the first target gun point, and no longer performs step 105 and step 106; or if the new position of the gun point layout after the first target gun point performs the first target offset action is in the obstacle region, step 105 is continuously performed.

[0094] 105. If the new position is in the obstacle region, the computer device determines the reward information of a plurality of second offset actions corresponding to the new position according to the offset information model, the second offset actions are used to move the first target gun point out of the obstacle region from the new position, and the reward information of the second offset actions is used to represent the contribution value of the second offset actions to moving the first target gun point out of the obstacle region.

[0095] In a possible implementation, the second offset action is moving one step to the left or one step to the right. Correspondingly, the step includes: the computer device inputs the new position and each second offset action into the offset information model, outputs the reward information corresponding to the new position and each second offset action, and obtains the reward information of a plurality of second offset actions corresponding to the new position. The second offset actions are used to move the first target gun point out of the obstacle region from the new position, and the second offset actions are moving one step to the left or one step to the right; wherein the reward information of the one step to the left is used to represent the contribution value of the one step to the left to moving the first target gun point out of the obstacle region; and the reward information of the one step to the right is used to represent the contribution value of the one step to the right to moving the first target gun point out of the obstacle region.

[0096] It should be noted that the direction of the line of fire can be transverse or vertical. Correspondingly, the direction of the second target action is perpendicular to the direction of the line of fire, or the direction of the second target action is the same as the direction of the line of fire. Alternatively, when the direction of the second target action is perpendicular to the direction of the line of fire, one step to the left or one step to the right is a transverse movement; when the direction of the second target action is the same as the direction of the line of fire, one step to the left or one step to the right is a vertical movement.

[0097] 106、The computer device determines a second target action with the maximum value of the reward information from a plurality of second target actions, until a new position of the gun point layout obtained after the second target action is executed is not in the obstacle region, and at least one second target action is obtained.

[0098] The first target gun point is moved out of the obstacle region by executing the at least one second target action. The number of the at least one second target action can be one or multiple. When the number of the second target action is one, the first target gun point is moved out of the obstacle region by executing one second target action. When the number of the second target action is multiple, the first target gun point is moved out of the obstacle region by executing multiple second target actions.

[0099] In a possible implementation, the step is: the computer device determines a second target action with the maximum value of the reward information from a plurality of second target actions, until a new position of the gun point layout obtained after the second target action is executed is not in the obstacle region, and at least one second target action is obtained.

[0100] It should be noted that the first target gun point obtains a new position each time the second target action is executed. If the new position of the gun point layout obtained after the second target action is executed is in the obstacle region, a new second target action is determined from a plurality of second target actions corresponding to the new position; the new second target action is continuously executed, until the new position of the gun point layout obtained after the second target action is executed is not in the obstacle region; and at least one second target action executed is determined.

[0101] In the embodiment of the present application, since the second target action is the optimal action corresponding to each new position, the optimal action is ensured to be executed by the first target gun point at the preset position to move out of the obstacle region, so that the accuracy of the determined gun point offset information is improved.

[0102] 107、The computer device determines the offset path composed of the first target action and the at least one second target action as the offset information of the first target gun point.

[0103] In a possible implementation, the offset information of the first target shooting point comprises an offset path, and correspondingly, the step is that the computer device determines the offset path formed by the first target offset action and the at least one second target offset action as the offset information of the first target shooting point.

[0104] In another possible implementation, the offset information of the first target shooting point comprises an offset path and a number of times of performing offset actions. Correspondingly, the step is that the computer device determines the offset path formed by the first target offset action and the at least one second target offset action, and determines the number of the first target offset action and the at least one second target offset action, and determines the offset path and the number as the offset information of the first target shooting point.

[0105] In another possible implementation, the offset information of the first target shooting point comprises an offset path, a number of times of performing offset actions and reward information of performing offset actions; correspondingly, the step is that the computer device determines the offset path formed by the first target offset action and the at least one second target offset action, and determines the number of the first target offset action and the at least one second target offset action, and determines a sum of the reward information corresponding to the first target offset action and the at least one second target offset action, and determines the offset path, the number and the sum of the reward information as the offset information of the first target shooting point.

[0106] For example, the first target offset action is one step to the left, and the at least one second target offset action is also one step to the left; the number of the at least one second target offset action is 2; the reward information of performing the first target offset action is “-3”; the reward information of performing the at least one second target offset action is “-2” and “-1” respectively; the computer device determines that the offset path is 3 steps to the left; the number of times of performing offset actions is 3, and the reward information of performing offset actions is “-6”; and the offset information of the first target shooting point is determined as: offset 3 steps to the left; the number of times of performing offset actions is 3, and the reward information of performing offset actions is “-6”.

[0107] It should be noted that the offset information of each first target shooting point is different, and one offset information corresponds to one offset strategy. For each first target shooting point, the offset path corresponding to the offset information of the first target shooting point is the shortest path, that is, the offset information of the first target shooting point corresponds to the optimal offset path, that is, the optimal offset strategy.

[0108] In a possible implementation, after the computer device determines the offset information of the first target shooting point, the computer device offsets the first target shooting point according to the shooting point offset information. Optionally, the computer device offsets a plurality of first target shooting points to obtain a layout diagram of the offset shooting points and obstacles as shown in FIGS. 2 and 3. Figure 4 and Figure 5 ​

[0109] In a possible implementation, if the distance between the first target shot point and other shot points is less than the second preset distance after the first target shot point is offset by the offset path composed of the first target offset action and the at least one second target offset action, the shot point offset information needs to be adjusted to ensure that the distance between the first target shot point and other shot points is not less than the second preset distance. In the embodiment of the present application, the value of the second preset distance is not specifically limited and can be set and modified as needed. Optionally, the second preset distance is any value between 5 m and 500 m, for example, 10 m, 50 m, 150 m, etc. In a possible implementation, the second preset distance is an integer multiple of the inter-shot distance.

[0110] In a possible implementation, the step of adjusting the shot point offset information by the computer device to obtain the final shot point offset information is: if the distance between the first target shot point and a third target shot point is less than the second preset distance after the first target shot point is offset by the offset path, the computer device adjusts the distance between the first target shot point and the third target shot point to the second preset distance; the third target shot point is a shot point other than the first target shot point in the exploration work area.

[0111] In the embodiment of the present application, since the first target offset action corresponding to the target shot point at the preset position and the second target offset action corresponding to the target shot point at the new position are determined by the pre-trained offset information model, and then the offset information corresponding to the target shot point is determined by the first target offset action and the second target offset action, when the offset information of the target shot point is determined, only the position of the target shot point needs to be determined, that is, the offset strategy of the shot point in the obstacle area is quickly obtained, and therefore the efficiency of determining the offset information is improved.

[0112] It should be noted that the pre-trained offset information model is a neural network model. For example, the offset information model is a fully connected neural network (Fully Connected Neural Network). The offset information model is used to determine the reward information by the position of the shot point and the offset action, so as to quickly obtain the offset strategy. In a possible implementation, a plurality of shot lines are arranged in the exploration work area, and a plurality of shot points are arranged on each shot line; the computer device trains the initial offset model by the position, offset action and reward information of the shot point on the target shot line to obtain the trained offset information model. Correspondingly, referring to Figure 6 , the step of determining the offset information model by the computer device includes the following steps 601 to 604:

[0113] 601、the computer device determines a target firing line with the largest number of firing points in the obstacle region from the plurality of firing lines, and determines a plurality of second target firing points in the target firing line in the obstacle region.

[0114] In a possible implementation, the step is: the computer device determines, for each firing line, the number of firing points in the obstacle region of the firing line, determines a target firing line with the largest number of firing points in the obstacle region from the plurality of firing lines, and determines a plurality of firing points in the target firing line in the obstacle region as the plurality of second target firing points. The target firing line is the firing line with the largest number of firing points in the obstacle region, that is, the most complex firing line.

[0115] In the embodiment, the target firing line with the largest number of firing points and the most complex state is selected from the plurality of firing lines, so that the offset information of the second target firing point in the target firing line can include the offset information of the firing points in other firing lines, and the offset information of each firing point in the obstacle region can be determined, that is, the offset information of all firing points can be determined according to the training offset information by training the most complex target firing line, and therefore the efficiency of determining the offset information of the firing points is improved.

[0116] Optionally, the step of determining, for each firing line, the number of firing points in the obstacle region of the firing line is: the computer device obtains, for each firing point in each firing line, obstacle state information of the firing point, and if the obstacle state information indicates that the firing point is in the obstacle region, the firing point is counted to obtain the number of firing points in the obstacle region of the firing line. The method of obtaining the obstacle state information of the firing point by the computer device is the same as the method of obtaining the obstacle state information of the firing point in step 101, and will not be described here.

[0117] 602、the computer device determines, for each second target firing point, a plurality of positions on any feasible path of the second target firing point moving out of the obstacle region from a current position.

[0118] For each second target firing point, a plurality of offset actions need to be performed on any feasible path of the second target firing point moving out of the obstacle region from a current position, and each time an offset action is performed, a new position is obtained, and a plurality of positions corresponding to the feasible path are obtained. In a possible implementation, any feasible path includes a plurality of paths, each path corresponds to a plurality of positions, and the plurality of positions on any feasible path is the sum of the plurality of positions corresponding to the plurality of paths.

[0119] In a possible implementation, for any position, the executed bias movement is either one step to the left or one step to the right, and the step length of each bias movement is the same; at this time, the plurality of positions are uniformly distributed in the obstacle region, and the interval between any two adjacent positions is one step.

[0120] 603、The computer device determines first reward information corresponding to the second target shot point, obtains a plurality of first reward information corresponding to a plurality of second target shot points, and the first reward information includes reward information of a plurality of bias movements corresponding to a plurality of positions of the second target shot point.

[0121] In a possible implementation, the step of determining, by the computer device, the first reward information corresponding to the second target shot point includes: determining, by the computer device, for each position, second reward information corresponding to the second target shot point at the position, obtaining a plurality of second reward information corresponding to a plurality of positions, and the second reward information corresponding to each position includes expected reward information of a plurality of third bias movements corresponding to the position of the second target shot point; and determining the plurality of second reward information corresponding to the plurality of positions as the first reward information corresponding to the second target shot point. Wherein, each movement of the second target shot point obtains a new position, and the new position corresponds to a plurality of third bias movements; the first reward information includes a plurality of second reward information corresponding to a plurality of positions of a plurality of movements of the second target shot point.

[0122] Optionally, each position corresponds to a plurality of bias movements, and the expected reward information corresponding to each position and each bias movement is different; the second reward information corresponding to the position of the second target shot point includes the expected reward information of the plurality of bias movements corresponding to the position. Correspondingly, the step of determining, by the computer device, for each position, the second reward information corresponding to the position of the second target shot point includes: determining, by the computer device, for each position, a plurality of third bias movements corresponding to the position; determining, for each third bias movement, an immediate reward of executing the third bias movement and a long-term reward of executing the third bias movement, the immediate reward being used to represent a current contribution value of the third bias movement to the second target shot point moving out of the obstacle region, and the long-term reward being used to represent a long-term contribution value of the third bias movement to the second target shot point moving out of the obstacle region; determining, based on the immediate reward and the long-term reward, expected reward information corresponding to the third bias movement, obtaining a plurality of expected reward information corresponding to a plurality of third bias movements; and determining the plurality of expected reward information corresponding to the plurality of third bias movements as the second reward information corresponding to the position of the second target shot point.

[0123] In a possible implementation, the instant reward of the third moving action is related to the number of steps of the third moving action, for example, one step to the left corresponds to an instant reward of "-1"; two steps to the left correspond to an instant reward of "-2". Alternatively, the plurality of third moving actions includes one step to the left and one step to the right, and the instant reward of the third moving action is "-1".

[0124] In a possible implementation, the computer device determines the long-term reward of the third moving action according to reward information of a new position of the second target cannon point after the third moving action is performed. Accordingly, the step of determining the long-term reward of the third moving action includes: determining, by the computer device, the new position of the second target cannon point after the third moving action is performed; determining, by the computer device, a plurality of fourth moving actions corresponding to the new position of the second target cannon point, and for each fourth moving action, determining reward information corresponding to the fourth moving action, to obtain a plurality of reward information corresponding to the plurality of fourth moving actions, the reward information corresponding to the fourth moving action being used to represent a contribution value of the fourth moving action to moving the second target cannon point out of the obstacle region; and determining, by the computer device, reward information with the maximum value from the plurality of reward information as the long-term reward of the third moving action.

[0125] In a possible implementation, the step of determining, by the computer device, the expected reward information corresponding to the third moving action based on the instant reward and the long-term reward includes: determining, by the computer device, a discount coefficient corresponding to the third moving action; and determining, by the computer device, the expected reward information corresponding to the third moving action based on the discount coefficient, the instant reward, and the long-term reward through the following formula one.

[0126] Formula one: y = R + γ max a′ Q(S′, a)

[0127] wherein y represents the expected reward information corresponding to the third moving action, R represents the instant reward, γ represents the discount coefficient, max a′ Q(S′, a) represents the long-term reward, S′ represents the new position of the second target cannon point after the third moving action is performed; a′ represents the plurality of fourth moving actions corresponding to the new position of the second target cannon point, and a represents any fourth moving action in the plurality of fourth moving actions.

[0128] In a possible implementation, the computer memory stores a correspondence relationship among positions, moving actions, and reward information. Accordingly, the step of determining, by the computer device, the plurality of fourth moving actions corresponding to the new position of the second target cannon point and for each fourth moving action, determining reward information corresponding to the fourth moving action includes: determining, by the computer device, the reward information corresponding to the fourth moving action performed at the new position of the second target cannon point according to the new position and the fourth moving action from the stored correspondence relationship among the positions, the moving actions, and the reward information.

[0129] Optionally, the position can be denoted as S, the bias action can be denoted as a, the reward information can be denoted as Q, and the correspondence between the position, the bias action and the reward information stored in the computer is a S-a-Q table, which is referred to as a S-Q table. In a possible implementation, the computer device updates the reward information by Q-learning for each second target shot point, and obtains the reward information corresponding to each position and each bias action. Correspondingly, the step of determining the S-Q table by the computer device is: the computer device determines the initial reward, the immediate reward, the learning rate, the discount factor and the long-term reward of performing the bias action in the position corresponding to each position and each bias action; the initial reward is updated by the following formula two until the difference between the reward information obtained by adjacent two times of updating is not greater than a preset threshold, and the reward information obtained by the last time of updating is determined as the reward information corresponding to the position and the bias action.

[0130] Formula two: Q'(S, A)←Q(S, A)+a(R+Ymax a′ Q(S', a)-Q(S, A))

[0131] Wherein, Q'(S, A) represents the updated reward information, Q(S, A) represents the initial reward, a represents the learning rate, Y represents the discount factor, max a′ Q(S', a) represents the long-term reward of performing the bias action, S' represents a new position of the second target shot point after performing the bias action; a' represents a plurality of bias actions corresponding to the new position, and a represents any bias action corresponding to the new position.

[0132] It should be noted that if the difference between the updated reward information and the reward information updated last time is greater than the preset threshold, the reward information updated this time is taken as the initial reward, and the iteration update is continued by formula two until the difference between the reward information obtained by adjacent two times of updating is not greater than the preset threshold, that is, the difference between the updated reward information and the reward information updated last time is not greater than the preset threshold. In a possible implementation, the preset threshold is any value between 0.001 and 0.1, for example, the preset threshold is 0.001, 0.002 or 0.003.

[0133] In the embodiments of the present application, the values of the initial reward, the learning rate and the discount factor are not specifically limited and can be set and modified as needed. Optionally, the computer device sets the initial reward value Q(S, A) as 0, the discount factor Y as 1, and the learning rate a as 0.001.

[0134] In a possible implementation, if the number of updates reaches a preset number, the reward information obtained by the last update is determined as the reward information corresponding to the position and the bias action. In the embodiments of the present application, the value of the preset number is not specifically limited and can be set and modified as needed. Alternatively, the preset number is 1000.

[0135] In a possible implementation, for a plurality of bias actions corresponding to a position, the computer device randomly selects a bias action from the plurality of bias actions. In another possible implementation, for a plurality of bias actions corresponding to a position, the computer device selects a bias action with a probability conforming to ε-greedy (ε-greedy, greedy strategy). Correspondingly, the probability of selecting a bias action is π(a|s);

[0136]

[0137] wherein s represents the position, a represents the selected bias action, π(a|s) represents the probability of selecting the bias action a at the position s, ε represents the probability parameter of the bias action, |A| represents the number of the plurality of bias actions, and A * represents the set of the plurality of bias actions.

[0138] In a possible implementation, to ensure that each bias action can be selected, the computer device sets the probability parameter of the bias action to be negatively related to the number of times of performing the bias action. Alternatively, the relationship between the probability parameter of the bias action and the number of times of performing the bias action is: ε=1*(0.9) m ; wherein ε represents the probability parameter of the bias action, and m represents the number of times of performing the bias action. For example, at the position s, the bias action a1 is determined by the computer device through ε-greedy for the first time; and the probability of selecting the action a1 next time will be reduced.

[0139] 604、The computer device trains the initial bias information model based on the plurality of first reward information corresponding to the plurality of second target shot points, to obtain a bias information model.

[0140] In a possible implementation, the computer device takes the plurality of first reward information corresponding to the plurality of second target shot points as sample data, trains the initial offset information model through the sample data, and obtains the offset information model. Correspondingly, the step is: for each second target shot point, the computer device inputs the plurality of positions corresponding to the second target shot point into the initial offset information model, outputs third reward information corresponding to the second target shot point, the third reward information includes a plurality of estimated reward information of offset actions corresponding to the second target shot point at the plurality of positions; determines a loss parameter between the third reward information and the first reward information, if the loss parameter is greater than a preset value, adjusts the offset parameter in the initial offset information model until the loss parameter is not greater than the preset value; determines the target offset parameter corresponding to when the loss parameter is not greater than the preset value, and obtains the offset information model. Optionally, the initial offset information model is a fully connected neural network model.

[0141] Optionally, the step of determining the loss parameter between the third reward information and the first reward information by the computer device is: the computer device determines the loss parameter between the third reward information and the first reward information through the following formula three according to the third reward information and the first reward information.

[0142] Formula three: Loss = (y-Q(S', a|θ)) 2

[0143] Wherein, Loss represents the loss parameter, θ represents the offset parameter, y represents the expected reward information of performing the offset action a at the position S', and Q(S', a|θ) represents the estimated reward information of performing the offset action a at the position S' when the offset parameter θ.

[0144] In the embodiments of the present application, the numerical value of the preset value is not specifically limited and can be set and modified as needed. Optionally, the preset value is any numerical value between 0.001 and 0.1; for example, 0.001, 0.01, 0.05, etc.

[0145] In the embodiments of the present application, an intelligent determination method of shot offset information is provided, which can be used to train the offset information model according to the offset requirements of the oil company in the seismic acquisition indoor design stage, and then determine the offset information of the shot point, thereby greatly reducing the artificial work intensity and improving the work efficiency of determining the offset information of the shot point.

[0146] The embodiment of the present application provides a method for determining shot point offset information. The first target offset action corresponding to the preset position of the target shot point and the second target offset action corresponding to the new position of the target shot point are determined through the pre-trained offset information model, and then the offset information corresponding to the target shot point is determined through the first target offset action and the second target offset action. Therefore, when the offset information of the target shot point is determined, only the position of the target shot point needs to be determined, so that the efficiency of determining the shot point offset information is improved.

[0147] Figure 7 is a block diagram of a device for determining shot point offset information according to an exemplary embodiment. Referring to Figure 7 , the device comprises:

[0148] The acquisition module 701 is configured to acquire a plurality of first target shot points arranged in an obstacle region in an exploration work area.

[0149] The first determination module 702 is configured to, for each first target shot point, determine, according to a pre-trained offset information model, reward information of a plurality of first offset actions corresponding to a preset position of the first target shot point. The offset information model is used to determine the reward information based on the position and the offset action. The first offset action is used to move the first target shot point out of the obstacle region from the preset position. The reward information of the first offset action is used to represent a contribution value of the first offset action for moving the first target shot point out of the obstacle region.

[0150] The second determination module 703 is configured to determine, from the plurality of first offset actions, a first target offset action with the maximum reward information value.

[0151] The third determination module 704 is configured to determine a new position of the shot point arrangement after the first target shot point performs the first target offset action.

[0152] The fourth determination module 705 is configured to, if the new position is in the obstacle region, determine, according to the offset information model, reward information of a plurality of second offset actions corresponding to the new position. The second offset action is used to move the first target shot point out of the obstacle region from the new position. The reward information of the second offset action is used to represent a contribution value of the second offset action for moving the first target shot point out of the obstacle region.

[0153] The fifth determination module 706 is configured to determine, from the plurality of second offset actions, a second target offset action with the maximum reward information value, until a new position of the shot point arrangement after the second target offset action is performed is not in the obstacle region, to obtain at least one second target offset action.

[0154] The sixth determination module 707 is configured to determine an offset path composed of the first target offset action and the at least one second target offset action as the offset information of the first target shot point.

[0155] In a possible implementation, referring to Figure 8 The device further includes a training module 708, which includes:

[0156] A first determination unit 7081, configured to determine, from the multiple shooting lines, a target shooting line on which a number of shooting points located in the obstacle region is the largest, and determine multiple second target shooting points located in the obstacle region on the target shooting line.

[0157] A second determination unit 7082, configured to, for each second target shooting point, determine multiple positions on any feasible path through which the second target shooting point moves out of the obstacle region from a current position.

[0158] A third determination unit 7083, configured to determine first reward information corresponding to the second target shooting point, and obtain multiple first reward information corresponding to the multiple second target shooting points, the first reward information including reward information of multiple offset actions corresponding to the second target shooting point at the multiple positions.

[0159] A training unit 7084, configured to train an initial offset information model based on the reward information of the multiple offset actions corresponding to the multiple positions of the multiple second target shooting points, and obtain an offset information model.

[0160] In another possible implementation, the third determination unit 7083 is configured to, for each position, determine second reward information corresponding to the second target shooting point at the position, and obtain multiple second reward information corresponding to the multiple positions, the second reward information including expected reward information of multiple third offset actions corresponding to the second target shooting point at the position; and determine the multiple second reward information corresponding to the multiple positions as the first reward information corresponding to the second target shooting point.

[0161] In another possible implementation, the third determination unit 7083 is configured to determine multiple third offset actions of the second target shooting point at the position; for each third offset action, determine an immediate reward of performing the third offset action, and determine a long-term reward of performing the third offset action, the immediate reward being used to represent a current contribution value of the third offset action to the second target shooting point moving out of the obstacle region, and the long-term reward being used to represent a long-term contribution value of the third offset action to the second target shooting point moving out of the obstacle region; determine expected reward information corresponding to the third offset action based on the immediate reward and the long-term reward, and obtain multiple expected reward information corresponding to the multiple third offset actions; and determine the multiple expected reward information corresponding to the multiple third offset actions as the second reward information corresponding to the second target shooting point at the position.

[0162] In a possible implementation, the third determining unit 7083 is configured to determine a new position of the second target shot point after the third offset action is performed; determine a plurality of fourth offset actions corresponding to the new position of the second target shot point, for each fourth offset action, determine reward information corresponding to the fourth offset action, obtain a plurality of reward information corresponding to the plurality of fourth offset actions, and the reward information corresponding to the fourth offset action is used to represent a contribution value of the fourth offset action to the second target shot point moving out of the obstacle region; and determine, from the plurality of reward information, reward information with the largest value as a long-term reward of performing the third offset action.

[0163] In a possible implementation, the training unit 7084 is configured to, for each second target shot point, input, into an initial offset information model, a plurality of offset actions corresponding to a plurality of positions of the second target shot point, and output third reward information corresponding to the second target shot point, the third reward information including estimated reward information of the plurality of offset actions corresponding to the plurality of positions of the second target shot point; determine a loss parameter between the third reward information and the first reward information, and if the loss parameter is greater than a preset value, adjust an offset parameter in the initial offset information model until the loss parameter is not greater than the preset value; determine a target offset parameter corresponding to a case where the loss parameter is not greater than the preset value, and obtain the offset information model.

[0164] The embodiment of the present application provides a determination device of shot point offset information. Since the first target offset action corresponding to the target shot point at the preset position and the second target offset action corresponding to the target shot point at the new position are determined by the pre-trained offset information model, and then the offset information corresponding to the target shot point is determined by the first target offset action and the second target offset action, so that when the offset information of the target shot point is determined, only the position of the target shot point needs to be determined, and therefore the efficiency of determining the shot point offset information is improved.

[0165] Figure 9 A structural block diagram of a computer device 900 provided by an example embodiment of the present application is shown. The computer device 900 can be a smart phone, a tablet computer, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 (Moving Picture Experts Group Audio Layer IV) player, a notebook computer or a desktop computer. The computer device 900 can also be referred to as a user device, a portable computer device, a laptop computer device, a desktop computer device, and other names.

[0166] Generally, the computer device 900 includes a processor 901 and a memory 902.

[0167] The processor 901 can include one or more processing cores, such as a 4-core processor, an 8-core processor, and the like. The processor 901 can be implemented in at least one of a hardware form of a DSP (Digital Signal Processing), an FPGA (Field-Programmable Gate Array), a PLA (Programmable Logic Array). The processor 901 can also include a main processor and a coprocessor, the main processor being a processor for processing data in an awake state, also known as a CPU (Central Processing Unit), and the coprocessor being a low-power processor for processing data in a standby state. In some embodiments, the processor 901 can be integrated with a GPU (Graphics Processing Unit) that is responsible for rendering and drawing the content required to be displayed by the display screen. In some embodiments, the processor 901 can further include an AI (Artificial Intelligence) processor for processing machine learning-related computing operations.

[0168] The memory 902 can include one or more computer-readable storage media that can be non-transitory. The memory 902 can also include a high-speed random access memory, and a nonvolatile memory such as one or more disk storage devices, flash storage devices. In some embodiments, the non-transitory computer-readable storage medium in the memory 902 is used to store at least one instruction for being executed by the processor 901 to implement the method for determining shot migration information provided by the method embodiments in the present application.

[0169] In some embodiments, the computer device 900 can also optionally include a peripheral device interface 903 and at least one peripheral device. The processor 901, the memory 902, and the peripheral device interface 903 can be connected through a bus or a signal line. Each peripheral device can be connected to the peripheral device interface 903 through a bus, a signal line, or a circuit board. Specifically, the peripheral device includes at least one of a radio frequency circuit 904, a display screen 905, a camera 906, an audio circuit 907, a positioning component 908, and a power supply 909.

[0170] The peripheral interface 903 can be used to connect at least one I / O (Input / Output) related peripheral device to the processor 901 and the memory 902. In some embodiments, the processor 901, the memory 902 and the peripheral interface 903 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 901, the memory 902 and the peripheral interface 903 can be implemented on a separate chip or circuit board, and the present embodiments are not limited in this regard.

[0171] The radio frequency circuit 904 is configured to receive and send RF (Radio Frequency) signals, also known as electromagnetic signals. The radio frequency circuit 904 communicates with communication networks and other communication devices through electromagnetic signals. The radio frequency circuit 904 converts electrical signals to electromagnetic signals for transmission, or converts electromagnetic signals received to electrical signals. Optionally, the radio frequency circuit 904 includes an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a subscriber identity module card, and the like. The radio frequency circuit 904 can communicate with other computer devices through at least one wireless communication protocol. The wireless communication protocol includes, but is not limited to, a metropolitan area network, various generations of mobile communication networks (2G, 3G, 4G and 5G), a wireless local area network and / or a WiFi (Wireless Fidelity) network. In some embodiments, the radio frequency circuit 904 can also include NFC (Near Field Communication) related circuitry, and the present application is not limited in this regard.

[0172] The display screen 905 is configured to display a UI (User Interface). The UI can include graphics, text, icons, video, and any combination thereof. When the display screen 905 is a touch display screen, the display screen 905 is further configured to capture touch signals on or above the surface of the display screen 905. The touch signals can be input to the processor 901 as control signals for processing. In this case, the display screen 905 can also be configured to provide virtual buttons and / or virtual keyboard, also known as soft buttons and / or soft keyboard. In some embodiments, the display screen 905 can be one, arranged on the front panel of the computer device 900; in other embodiments, the display screen 905 can be at least two, arranged on different surfaces of the computer device 900 or in a folding design; in yet other embodiments, the display screen 905 can be a flexible display screen, arranged on a curved surface or a folding surface of the computer device 900. Even, the display screen 905 can also be arranged in an irregular shape, i.e., a special-shaped screen. The display screen 905 can be made of LCD (Liquid Crystal Display), OLED (Organic Light-Emitting Diode), etc.

[0173] The camera assembly 906 is configured to capture images or videos. Optionally, the camera assembly 906 includes a front-facing camera and a rear-facing camera. Typically, the front-facing camera is arranged on the front panel of the computer device, and the rear-facing camera is arranged on the back of the computer device. In some embodiments, the rear-facing camera is at least two, which are any one of a main camera, a depth-of-field camera, a wide-angle camera, and a telephoto camera, to realize the background blur function by fusing the main camera and the depth-of-field camera, the panoramic shooting and VR (Virtual Reality) shooting function by fusing the main camera and the wide-angle camera, or other fusion shooting functions. In some embodiments, the camera assembly 906 can further include a flash. The flash can be a single-color-temperature flash or a dual-color-temperature flash. The dual-color-temperature flash refers to a combination of a warm light flash and a cold light flash, which can be used for light compensation at different color temperatures.

[0174] The audio circuit 907 can include a microphone and a speaker. The microphone is used to collect sound waves of a user and an environment, and convert the sound waves into an electrical signal input to the processor 901 for processing, or input to the radio frequency circuit 904 to realize voice communication. For the purpose of stereo sound collection or noise reduction, the microphone can be multiple, and arranged at different parts of the computer device 900. The microphone can also be an array microphone or an omnidirectional collection microphone. The speaker is used to convert an electrical signal from the processor 901 or the radio frequency circuit 904 into sound waves. The speaker can be a conventional diaphragm speaker, or a piezoelectric ceramic speaker. When the speaker is a piezoelectric ceramic speaker, not only can it convert an electrical signal into a sound wave audible to humans, but also can convert an electrical signal into an inaudible sound wave to humans for ranging purposes. In some embodiments, the audio circuit 907 can also include a headphone jack.

[0175] The positioning component 908 is used to position the current geographic location of the computer device 900 to realize navigation or LBS (Location Based Service). The positioning component 908 can be a positioning component based on the GPS (Global Positioning System) of the United States, the Beidou system of China, the GLONASS system of Russia, or the Galileo system of the European Union.

[0176] The power supply 909 is used to supply power to various components in the computer device 900. The power supply 909 can be alternating current, direct current, disposable batteries, or rechargeable batteries. When the power supply 909 includes rechargeable batteries, the rechargeable batteries can support wired charging or wireless charging. The rechargeable batteries can also be used to support fast charging technology.

[0177] In some embodiments, the computer device 900 further includes one or more sensors 910. The one or more sensors 910 include, but are not limited to, an acceleration sensor 911, a gyroscope sensor 912, a pressure sensor 913, a fingerprint sensor 914, an optical sensor 915, and a proximity sensor 916.

[0178] The acceleration sensor 911 can detect the acceleration in three coordinate axes of the coordinate system established by the computer device 900. For example, the acceleration sensor 911 can be used to detect the components of the gravitational acceleration in three coordinate axes. The processor 901 can control the display screen 905 to display the user interface in a landscape view or a portrait view according to the gravitational acceleration signal collected by the acceleration sensor 911. The acceleration sensor 911 can also be used for gaming or user motion data collection.

[0179] The gyroscope sensor 912 can detect the body direction and rotation angle of the computer device 900, and the gyroscope sensor 912 can cooperate with the acceleration sensor 911 to collect the 3D action of the user on the computer device 900. According to the data collected by the gyroscope sensor 912, the processor 901 can realize the following functions: motion sensing (such as changing the UI according to the user's tilt operation), image stabilization when shooting, game control, and inertial navigation.

[0180] The pressure sensor 913 can be arranged on the side frame of the computer device 900 and / or the lower layer of the display screen 905. When the pressure sensor 913 is arranged on the side frame of the computer device 900, the user's holding signal on the computer device 900 can be detected, and the left and right hand recognition or shortcut operation can be performed by the processor 901 according to the holding signal collected by the pressure sensor 913. When the pressure sensor 913 is arranged on the lower layer of the display screen 905, the operable control on the UI interface can be controlled by the processor 901 according to the pressure operation of the user on the display screen 905. The operable control includes at least one of a button control, a scroll bar control, an icon control, and a menu control.

[0181] The fingerprint sensor 914 is used to collect the fingerprint of the user, and the identity of the user can be recognized by the processor 901 according to the fingerprint collected by the fingerprint sensor 914, or by the fingerprint sensor 914 according to the collected fingerprint. When the identity of the user is recognized as a trusted identity, the processor 901 authorizes the user to perform related sensitive operations, including unlocking the screen, viewing encrypted information, downloading software, payment, and changing settings. The fingerprint sensor 914 can be arranged on the front, back or side of the computer device 900. When the computer device 900 is provided with a physical button or a manufacturer's logo, the fingerprint sensor 914 can be integrated with the physical button or the manufacturer's logo.

[0182] The optical sensor 915 is used to collect the ambient light intensity. In one embodiment, the processor 901 can control the display brightness of the display screen 905 according to the ambient light intensity collected by the optical sensor 915. Specifically, when the ambient light intensity is high, the display brightness of the display screen 905 is increased; when the ambient light intensity is low, the display brightness of the display screen 905 is decreased. In another embodiment, the processor 901 can also dynamically adjust the shooting parameters of the camera assembly 906 according to the ambient light intensity collected by the optical sensor 915.

[0183] The proximity sensor 916, also referred to as a distance sensor, is usually arranged on the front panel of the computer device 900. The proximity sensor 916 is used to collect the distance between the user and the front face of the computer device 900. In an embodiment, when the proximity sensor 916 detects that the distance between the user and the front face of the computer device 900 gradually decreases, the display screen 905 is switched from the bright screen state to the screen-off state under the control of the processor 901; when the proximity sensor 916 detects that the distance between the user and the front face of the computer device 900 gradually increases, the display screen 905 is switched from the screen-off state to the bright screen state under the control of the processor 901.

[0184] Those skilled in the art can understand that the structure shown in the foregoing embodiments does not constitute a limitation on the computer device 900, and the computer device 900 can include more or fewer components than those shown in the drawings, or some components can be combined, or different component arrangements can be adopted. Figure 9 Those skilled in the art can understand that the structure shown in the foregoing embodiments does not constitute a limitation on the computer device 900, and the computer device 900 can include more or fewer components than those shown in the drawings, or some components can be combined, or different component arrangements can be adopted.

[0185] In an exemplary embodiment, a storage medium including program code is also provided, the computer readable storage medium storing at least one program code, the at least one program code being loaded and executed by a processor to implement the method for determining shot point migration information in any possible implementation manner described above.

[0186] In an exemplary embodiment, a computer program product is also provided, the computer program product including at least one program code, the at least one program code being loaded and executed by a processor to implement the method for determining shot point migration information in any possible implementation manner described above.

[0187] Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the features of the disclosure disclosed herein. It is intended that the specification and examples be considered as exemplary only, with the true scope and spirit of the disclosure being indicated by the following claims.

[0188] The above are only optional embodiments of the present application, and do not limit the present application, and any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method of determining shotpoint migration information, characterized by, The method comprises: obtaining a plurality of first target shot points arranged in an obstacle region in a survey area; for each first target shot point, determining reward information of a plurality of first offset actions corresponding to a preset position of the first target shot point according to a pre-trained offset information model, the offset information model being used for determining reward information based on a position and an offset action, the first offset action being used for moving the first target shot point out of the obstacle region from the preset position, the reward information of the first offset action being used for representing a contribution value of the first offset action to moving the first target shot point out of the obstacle region; determining a first target offset action with the maximum reward information value from the plurality of first offset actions; determining a new position of shot point arrangement after the first target shot point performs the first target offset action; if the new position is in the obstacle region, determining reward information of a plurality of second offset actions corresponding to the new position according to the offset information model, the second offset action being used for moving the first target shot point out of the obstacle region from the new position, the reward information of the second offset action being used for representing a contribution value of the second offset action to moving the first target shot point out of the obstacle region; determining a second target offset action with the maximum reward information value from the plurality of second offset actions until a new position of shot point arrangement after the second target offset action is performed is not in the obstacle region, and obtaining at least one second target offset action; determining an offset path composed of the first target offset action and the at least one second target offset action as offset information of the first target shot point.

2. The method of claim 1, wherein, A plurality of shot lines are arranged in the survey area, and each shot line is provided with a plurality of shot points; and a process of determining the offset information model comprises: determining a target shot line with the largest number of shot points arranged in the obstacle region from the plurality of shot lines, and determining a plurality of second target shot points arranged in the obstacle region on the target shot line; for each second target shot point, determining a plurality of positions on any feasible path for moving the second target shot point out of the obstacle region from a current position; determining first reward information corresponding to the second target shot point, obtaining a plurality of first reward information corresponding to a plurality of second target shot points, and the first reward information comprising reward information of a plurality of offset actions corresponding to the plurality of positions of the second target shot point; training an initial offset information model based on the reward information of the plurality of offset actions corresponding to the plurality of positions of the plurality of second target shot points to obtain the offset information model.

3. The method of claim 2, wherein, The determining of the first reward information corresponding to the second target shot point comprises: for each position, determining second reward information corresponding to the position of the second target shot point, obtaining a plurality of second reward information corresponding to the plurality of positions, and the second reward information corresponding to each position comprising expected reward information of a plurality of third offset actions corresponding to the position of the second target shot point; determining the plurality of second reward information corresponding to the plurality of positions as the first reward information corresponding to the second target shot point.

4. The method of claim 3, wherein, The determining the second reward information corresponding to the second target shot point at the position comprises: determining a plurality of third offset actions corresponding to the second target shot point at the position; for each third offset action, determining an immediate reward of performing the third offset action, and determining a long-term reward of performing the third offset action, the immediate reward being used to represent a current contribution value of the third offset action for the second target shot point moving out of the obstacle region, and the long-term reward being used to represent a long-term contribution value of the third offset action for the second target shot point moving out of the obstacle region; based on the immediate reward and the long-term reward, determining expected reward information corresponding to the third offset action, to obtain a plurality of expected reward information corresponding to a plurality of third offset actions; determining the plurality of expected reward information corresponding to the plurality of third offset actions as the second reward information corresponding to the second target shot point at the position.

5. The method of claim 4, wherein, The determining the long-term reward of performing the third offset action comprises: determining a new position of the second target shot point after performing the third offset action; determining a plurality of fourth offset actions corresponding to the new position of the second target shot point, and for each fourth offset action, determining reward information corresponding to the fourth offset action, to obtain a plurality of reward information corresponding to the plurality of fourth offset actions, the reward information corresponding to the fourth offset action being used to represent a contribution value of the fourth offset action for the second target shot point moving out of the obstacle region; determining the reward information with the maximum value from the plurality of reward information as the long-term reward of performing the third offset action.

6. The method of claim 2, wherein, The training the initial offset information model based on the reward information of the plurality of offset actions corresponding to the plurality of second target shot points at the plurality of positions to obtain the offset information model comprises: for each second target shot point, inputting a plurality of offset actions of the second target shot point at the plurality of positions into the initial offset information model, and outputting third reward information corresponding to the second target shot point, the third reward information comprising estimated reward information of the plurality of offset actions of the second target shot point at the plurality of positions; determining a loss parameter between the third reward information and the first reward information, and if the loss parameter is greater than a preset value, adjusting an offset parameter in the initial offset information model until the loss parameter is not greater than the preset value; determining a target offset parameter corresponding to when the loss parameter is not greater than the preset value, to obtain the offset information model.

7. An apparatus for determining shotpoint migration information, characterized by The device comprises: an acquisition module configured to acquire a plurality of first target shot points arranged in an obstacle region in an exploration work area; The first determining module is configured to determine, for each first target shot point, reward information of a plurality of first offset actions corresponding to a preset position of the first target shot point according to a pre-trained offset information model, the offset information model being configured to determine reward information based on a position and an offset action, the first offset action being configured to move the first target shot point out of the obstacle region from the preset position, the reward information of the first offset action being configured to represent a contribution value of the first offset action to moving the first target shot point out of the obstacle region. The second determining module is configured to determine a first target offset action with maximum reward information value from the plurality of first offset actions. The third determining module is configured to determine a new position of shot point layout after the first target shot point performs the first target offset action. The fourth determining module is configured to, if the new position is in the obstacle region, determine reward information of a plurality of second offset actions corresponding to the new position according to the offset information model, the second offset action being configured to move the first target shot point out of the obstacle region from the new position, the reward information of the second offset action being configured to represent a contribution value of the second offset action to moving the first target shot point out of the obstacle region. The fifth determining module is configured to determine a second target offset action with maximum reward information value from the plurality of second offset actions until a new position of shot point layout after the second target offset action is performed is not in the obstacle region, and obtain at least one second target offset action. The sixth determining module is configured to determine an offset path composed of the first target offset action and the at least one second target offset action as offset information of the first target shot point.

8. A computer device, comprising: The computer device comprises: The processor and the memory, the memory stores at least one program code, the at least one program code is loaded and executed by the processor to realize the operation performed by the shot point offset information determination method in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium stores at least one program code, the at least one program code is loaded and executed by the processor to realize the operation performed by the shot point offset information determination method in any one of claims 1 to 6.

10. A computer program product, characterised in that, The computer program product comprises at least one program code, the at least one program code is loaded and executed by the processor to realize the shot point offset information determination method in any one of claims 1 to 6.

Images