CN116263512A - Determination method, device, equipment, storage medium and product of shot offset information - Google Patents
Determination method, device, equipment, storage medium and product of shot offset information Download PDFInfo
- Publication number
- CN116263512A CN116263512A CN202111531938.2A CN202111531938A CN116263512A CN 116263512 A CN116263512 A CN 116263512A CN 202111531938 A CN202111531938 A CN 202111531938A CN 116263512 A CN116263512 A CN 116263512A
- Authority
- CN
- China
- Prior art keywords
- offset
- target
- information
- determining
- shot
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 47
- 230000009471 action Effects 0.000 claims abstract description 355
- 230000033001 locomotion Effects 0.000 claims description 39
- 230000007774 longterm Effects 0.000 claims description 27
- 238000012549 training Methods 0.000 claims description 16
- 230000004888 barrier function Effects 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 claims description 2
- 230000002093 peripheral effect Effects 0.000 description 10
- 230000001133 acceleration Effects 0.000 description 9
- 238000012545 processing Methods 0.000 description 9
- 238000004891 communication Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 238000013461 design Methods 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 239000000919 ceramic Substances 0.000 description 2
- 230000006835 compression Effects 0.000 description 2
- 238000007906 compression Methods 0.000 description 2
- 230000007423 decrease Effects 0.000 description 2
- 230000001788 irregular Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000010304 firing Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 230000006641 stabilisation Effects 0.000 description 1
- 238000011105 stabilization Methods 0.000 description 1
- 239000010409 thin film Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V1/00—Seismology; Seismic or acoustic prospecting or detecting
- G01V1/28—Processing seismic data, e.g. for interpretation or for event detection
- G01V1/30—Analysis
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V1/00—Seismology; Seismic or acoustic prospecting or detecting
- G01V1/28—Processing seismic data, e.g. for interpretation or for event detection
- G01V1/282—Application of seismic models, synthetic seismograms
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Acoustics & Sound (AREA)
- Environmental & Geological Engineering (AREA)
- Geology (AREA)
- General Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Geophysics (AREA)
- Geophysics And Detection Of Objects (AREA)
Abstract
The embodiment of the application provides a method, a device, equipment, a storage medium and a product for determining shot offset information, and belongs to the technical field of seismic exploration. The method comprises the following steps: acquiring a plurality of first target shots distributed in an obstacle area in an exploration work area; for each first target shot point, determining rewarding information of a plurality of first offset actions corresponding to preset positions of the first target shot point according to a pre-trained offset information model, and determining a first target offset action with the largest rewarding information value from the plurality of first offset actions; determining a first target shot point to execute a first target offset action to obtain a new position of shot point layout; if the new position is in the obstacle area, determining at least one second target offset action according to the offset information model; and determining an offset path formed by the first target offset action and at least one second target offset action as offset information of the first target shot point. The method can improve the efficiency of determining the shot point offset information.
Description
Technical Field
The present disclosure relates to the field of seismic exploration, and in particular, to a method, apparatus, device, storage medium, and product for determining shot offset information.
Background
Currently, seismic exploration techniques are an important means of determining the oil and gas reserves of a reservoir. When the reservoir is subjected to seismic exploration, a plurality of shots are required to be distributed at a plurality of preset positions of the reservoir, however, when the preset position of a certain shot is in an obstacle area, the shot cannot be distributed in the obstacle area, so that the preset position of the shot is required to be adjusted according to shot offset information, and then the shot is distributed at the adjusted position. Therefore, for shots whose preset positions are within the obstacle region, it is necessary to determine offset information of the shots before laying the shots.
In the related art, for a shot point in an obstacle area, a worker determines a first distance between the shot point and a left edge of the obstacle area and a second distance between the shot point and a right edge of the obstacle area through manual measurement, determines a shortest 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.
However, in the above-described related art, when the number of target shots is large, the workload of determining shot offset information by manual measurement is large, resulting in a long time taken to determine the shot offset information, so the efficiency of determining the shot offset information is low.
Disclosure of Invention
The embodiment of the application provides a method, a device, equipment, a storage medium and a product for determining shot offset information, which can improve the efficiency of determining shot offset information. The technical scheme is as follows:
in one aspect, the present application provides a method for determining shot offset information, the method including:
acquiring a plurality of first target shots distributed in an obstacle area in an exploration work area;
determining rewarding information of a plurality of first offset actions corresponding to preset positions of the first target shots according to a pre-trained offset information model for each first target shot, wherein the offset information model is used for determining rewarding information based on the positions and the offset actions, the first offset actions are used for enabling the first target shots to move out of the obstacle area from the preset positions, and the rewarding information of the first offset actions is used for representing the first offset movements as contribution values of the first target shots moving out of the obstacle area;
Determining a first target offset action with the largest value of the rewarding information from the plurality of first offset actions;
determining a new position of the shot layout after the first target shot executes the first target offset action;
if the new position is in the obstacle region, determining rewarding information of a plurality of second offset actions corresponding to the new position according to the offset information model, wherein the second offset actions are used for moving the first target shot out of the obstacle region from the new position, and the rewarding information of the second offset actions are used for representing the second offset movements as contribution values of the first target shot moving out of the obstacle region;
determining a second target offset action with the largest value of the rewarding information from the plurality of second offset actions until a new position of the shot point layout is not in the obstacle area after the second target offset action is executed, and obtaining at least one second target offset action;
and determining an offset path formed by the first target offset action and the at least one second target offset action as offset information of the first target shot point.
In one possible implementation manner, a plurality of gun lines are arranged in the exploration work area, and a plurality of gun points are arranged on each gun line; the process of determining the offset information model is as follows:
Determining a target shot line with the largest number of shots arranged in the barrier area from the plurality of shot lines, and determining a plurality of second target shots arranged in the barrier area on the target shot line;
for each second target shot, determining a plurality of positions on any feasible path where the second target shot moves out of the obstacle region from the current position;
determining first rewarding information corresponding to the second target shot points to obtain a plurality of first rewarding information corresponding to a plurality of second target shot points, wherein the first rewarding information comprises rewarding information of a plurality of offset actions corresponding to the second target shot points at a plurality of positions;
training an initial offset information model based on rewarding information of a plurality of offset actions corresponding to the second target shots at the positions to obtain the offset information model.
In another possible implementation manner, the determining the first reward information corresponding to the second target shot includes:
for each position, determining second rewarding information corresponding to the second target shot point at the position, and obtaining a plurality of pieces of second rewarding information corresponding to the plurality of positions, wherein the second rewarding information comprises expected rewarding information of a plurality of third offset actions corresponding to the second target shot point at the position;
And determining a plurality of pieces of second rewarding information corresponding to the plurality of positions as first rewarding information corresponding to the second target shot point.
In another possible implementation manner, the determining the second prize information corresponding to the second target shot point at the position includes:
determining a plurality of third offset actions corresponding to the second target shot points at the positions;
for each third offset action, determining an instant prize for performing the third offset action for representing the third offset movement as a current contribution value for the second target shot to move out of the obstacle region, and determining a long-term prize for performing the third offset action for representing the third offset movement as a long-term contribution value for the second target shot to move out of the obstacle region;
determining expected rewards information corresponding to the third offset actions based on the instant rewards and the long-term rewards, and obtaining a plurality of pieces of expected rewards information corresponding to a plurality of third offset actions;
and determining a plurality of pieces of expected rewards information corresponding to the plurality of third offset actions as second rewards information corresponding to the second target shot at the position.
In another possible implementation, the determining the forward reward for performing the third offset action includes:
determining a new position of the second target shot point after the third offset action is executed;
determining a plurality of fourth offset actions corresponding to new positions of the second target shot, and determining rewarding information corresponding to the fourth offset actions for each fourth offset action to obtain a plurality of rewarding information corresponding to the fourth offset actions, wherein the rewarding information corresponding to the fourth offset actions is used for representing the fourth offset movement as a contribution value of the second target shot moving out of the obstacle area;
determining the most numeric bonus information from the plurality of bonus information as the long-term bonus for executing the third offset action.
In another possible implementation manner, the determining, based on the instant prize and the long-term prize, the expected prize information corresponding to the third offset action includes:
determining a discount coefficient corresponding to the third offset action;
determining expected rewards information corresponding to the third offset action based on the discount coefficient, the instant rewards and the long-term rewards through the following formula I;
Equation one: y=r+γmax a′ Q(S′,a)
Wherein y represents expected rewarding information corresponding to the third offset action, R represents the instant rewards, gamma represents the discount coefficient, and max a′ Q (S ', a) represents the forward reward, S' represents a new location of the second target shot after the third offset action is performed; a' represents a plurality of fourth offset actions corresponding to new positions of the second target shot, and a represents any one of the fourth offset actions.
In another possible implementation manner, the training the initial offset information model based on the reward information of the offset actions corresponding to the second target shots at the positions to obtain the offset information model includes:
for each second target shot, inputting a plurality of offset actions of the second target shot corresponding to the plurality of positions into the initial offset information model, and outputting third rewarding information corresponding to the second target shot, wherein the third rewarding information comprises estimated rewarding information of the plurality of offset actions of the second target shot corresponding to the plurality of positions;
determining a loss parameter between the third rewarding information and the first rewarding information, and if the loss parameter is larger than a preset value, adjusting an offset parameter in the initial offset information model until the loss parameter is not larger than the preset value;
And determining a corresponding target offset parameter when the loss parameter is not larger than the preset value, and obtaining the offset information model.
In another aspect, the present application provides a device for determining shot offset information, the device including:
the acquisition module is used for acquiring a plurality of first target shot points which are distributed in the obstacle area in the exploration work area;
the first determining module is used for determining rewarding information of a plurality of first offset actions corresponding to preset positions of the first target shot points according to a pre-trained offset information model for each first target shot point, the offset information model is used for determining rewarding information based on the positions and the offset actions, the first offset actions are used for enabling the first target shot point to move out of the obstacle area from the preset positions, and the rewarding information of the first offset actions is used for representing the first offset movements as contribution values of the first target shot point moving out of the obstacle area;
a second determining module, configured to determine a first target offset action with a largest value of the bonus information from the plurality of first offset actions;
the third determining module is used for determining a new position of the shot layout after the first target shot executes the first target offset action;
A fourth determining module, configured to determine, according to the offset information model, rewarding information of a plurality of second offset actions corresponding to the new location, where the second offset actions are used to move the first target shot out of the obstacle area from the new location, and the rewarding information of the second offset actions is used to represent a contribution value of the second offset movement as the movement of the first target shot out of the obstacle area;
a fifth determining module, configured to determine a second target offset action with the largest value of the reward information from the plurality of second offset actions, until a new position of shot placement obtained after the execution of the second target offset action is not in the obstacle area, and obtain at least one second target offset action;
and a sixth determining module, configured to determine an offset path formed by the first target offset action and the at least one second target offset action as offset information of the first target shot point.
In one possible implementation manner, a plurality of gun lines are arranged in the exploration work area, and a plurality of gun points are arranged on each gun line; the apparatus further includes a training module, the training module including:
A first determining unit configured to determine a target shot line having a largest number of shots laid in the obstacle region from among the plurality of shot lines, and determine a plurality of second target shots laid in the obstacle region on the target shot line;
a second determining unit configured to determine, for each second target shot, a plurality of positions on any one of the feasible paths in which the second target shot is moved out of the obstacle region from the current position;
a third determining unit, configured to determine first reward information corresponding to the second target shot, to obtain a plurality of first reward information corresponding to a plurality of second target shots, where the first reward information includes reward information of a plurality of offset actions corresponding to the second target shots at the plurality of positions;
the training unit is used for training the initial offset information model based on the rewarding information of a plurality of offset actions corresponding to the second target shots at the positions to obtain the offset information model.
In another possible implementation manner, the third determining unit is configured to determine, for each position, second rewards information corresponding to the second target shot point at the position, and obtain a plurality of second rewards information corresponding to the plurality of positions, where the second rewards information includes expected rewards information of a plurality of third offset actions corresponding to the second target shot point at the position; and determining a plurality of pieces of second rewarding information corresponding to the plurality of positions as first rewarding information corresponding to the second target shot point.
In another possible implementation manner, the third determining unit is configured to determine a plurality of third offset actions corresponding to the second target shot points at the positions; for each third offset action, determining an instant prize for performing the third offset action for representing the third offset movement as a current contribution value for the second target shot to move out of the obstacle region, and determining a long-term prize for performing the third offset action for representing the third offset movement as a long-term contribution value for the second target shot to move out of the obstacle region; determining expected rewards information corresponding to the third offset actions based on the instant rewards and the long-term rewards, and obtaining a plurality of pieces of expected rewards information corresponding to a plurality of third offset actions; and determining a plurality of pieces of expected rewards information corresponding to the plurality of third offset actions as second rewards information corresponding to the second target shot at the position.
In another possible implementation manner, a third determining unit is configured to determine a new position where the second target shot point is located after the third offset action is performed; determining a plurality of fourth offset actions corresponding to new positions of the second target shot, and determining rewarding information corresponding to the fourth offset actions for each fourth offset action to obtain a plurality of rewarding information corresponding to the fourth offset actions, wherein the rewarding information corresponding to the fourth offset actions is used for representing the fourth offset movement as a contribution value of the second target shot moving out of the obstacle area; determining the most numeric bonus information from the plurality of bonus information as the long-term bonus for executing the third offset action.
In another possible implementation manner, the training unit is configured to input, for each second target shot, a plurality of offset actions corresponding to the second target shot at the plurality of positions into the initial offset information model, and output third rewards information corresponding to the second target shot, where the third rewards information includes estimated rewards information of a plurality of offset actions corresponding to the second target shot at the plurality of positions; determining a loss parameter between the third rewarding information and the first rewarding information, and if the loss parameter is larger than a preset value, adjusting an offset parameter in the initial offset information model until the loss parameter is not larger than the preset value; and determining a corresponding target offset parameter when the loss parameter is not larger than the preset value, and obtaining the offset information model.
In another aspect, embodiments of the present application provide a computer device, the computer device comprising: a processor and a memory, wherein at least one piece of program code is stored in the memory, and the at least one piece of program code is loaded and executed by the processor to realize the operation executed by the method for determining the shot point offset information according to any one of the possible implementation manners.
In another aspect, embodiments of the present application provide a computer readable storage medium having at least one program code stored therein, the at least one program code loaded and executed by a processor to implement operations performed by a method for determining shot offset information according to any one of the possible implementations described above.
In another aspect, embodiments of the present application provide a computer program product comprising at least one piece of program code loaded and executed by a processor to implement operations performed by a method for determining shot offset information according to any one of the possible implementations described above.
The beneficial effects of the technical scheme provided by the embodiment of the application at least comprise:
the embodiment of the application provides a method for determining offset information of a shot point, which is characterized in that a first target offset action corresponding to a target shot point at a preset position and a second target offset action corresponding to a new position of the target shot point are determined through a pre-trained offset information model, and further, the offset information corresponding to the target shot point is determined through 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 is required to be determined, and therefore the efficiency of determining the offset information of the shot point is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart illustrating a method of determining shot offset information according to an exemplary embodiment;
FIG. 2 is a schematic illustration of an initial deployment of an obstacle and shot in accordance with an exemplary embodiment;
FIG. 3 is a schematic illustration of an initial deployment of an obstacle and shot in accordance with an exemplary embodiment;
FIG. 4 is a schematic layout of an offset obstruction and shot according to an exemplary embodiment;
FIG. 5 is a schematic layout of an offset obstruction and shot according to an exemplary embodiment;
FIG. 6 is a flowchart of a training method for an offset information model, according to an exemplary embodiment;
FIG. 7 is a block diagram illustrating a determination apparatus of shot offset information according to an exemplary embodiment;
FIG. 8 is a block diagram illustrating a determination apparatus of shot offset information according to an exemplary embodiment;
fig. 9 is a block diagram of a computer device, according to an example embodiment.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present application more apparent, the embodiments of the present application will be described in further detail below with reference to the accompanying drawings.
Fig. 1 is a flowchart of a method of determining shot offset information, performed by a computer device, according to an exemplary embodiment. Referring to fig. 1, the method includes:
101. the computer device obtains a plurality of first target shots disposed within the obstacle region within the survey work area.
In one possible implementation, the computer device determines a plurality of first target shots from the obstacle state information of the shots. Correspondingly, the method comprises the following steps: the method comprises the steps that a computer device obtains barrier state information of a plurality of shot points included in an exploration work area; determining a plurality of first target shots arranged in an obstacle area from the plurality of shots according to the obstacle state information of the plurality of shots; the obstacle state information is used to indicate whether the shot is disposed in the obstacle region.
In one possible implementation, the obstacle state information includes a first value for indicating that the shot is disposed within the obstacle region and a second value for indicating that the shot is not disposed within the obstacle region; correspondingly, the step of acquiring the obstacle state information of a plurality of shots included in the exploration work area by the computer equipment comprises the following steps of: the method comprises the steps that computer equipment obtains a target area where at least one obstacle in an exploration work area is located; for each shot point, determining a preset position of the shot point; and determining the obstacle state information of the shot point according to the preset position and the target area where the obstacle is located, and obtaining the obstacle state information of a plurality of shot points in the exploration work area.
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 area, the computer equipment determines that the obstacle state information of the shot point is 1, and if the preset position corresponding to the shot point is not in the target area, the computer equipment determines that the obstacle state information of the shot point is 0.
In one possible implementation, the number of obstacles within the survey work area, the target area where the obstacles are located, is fixed. The corresponding relation between the work area identification and the number of the obstacles and the area where the obstacles are located are stored in the computer equipment. Correspondingly, the computer equipment acquires a target area where at least one obstacle in the exploration work area is located, and the steps are as follows: the computer equipment acquires a work area identifier of the exploration work area, and determines a target area where at least one obstacle in the exploration work area is located from the stored corresponding relation between the work area identifier, the number of the obstacles and the area where the obstacle is located according to the work area identifier. Alternatively, the work area identification is used to distinguish between different exploration work areas. The work area identification includes at least one of a number, letter, number. For example, the work area designation is work area 1, work area 2, work area 3, etc.
It should be noted that the number of obstacles in the exploration area is one or more. In the embodiment of the present application, the number and shape of the obstacles are not particularly limited, and may be set and modified as needed. For example, with continued reference to fig. 2, the number of obstacles is one and the shape of the obstacle is circular. For another example, referring to FIG. 3, the number of obstacles in the survey area is 3, and the shape of the 3 obstacles is square, rectangular, and irregular.
In one possible implementation manner, the step of determining, by the computer device, the obstacle state information of the shot according to the preset position and the target area where the obstacle is located is: if the preset position corresponding to the shot point is in the target area where the obstacle is located, the computer equipment determines that the obstacle state information of the shot point is a first numerical value; if the preset position corresponding to the shot point is not in the target area where the obstacle is located, the computer equipment determines that the obstacle state information of the shot point is a second numerical value.
In one possible implementation, the preset position of the first target shot is an initial position of the first target shot within the survey work area. The corresponding relation between the shot point identification and the initial position is stored in the computer equipment. Correspondingly, the step of determining the preset position of the first target shot point by the computer equipment comprises the following steps: and the computer equipment determines the target initial position corresponding to the target shot mark as the preset position of the first target shot from the corresponding relation between the stored shot mark and the initial position according to the target shot mark of the first target shot. Optionally, the shot identity is used to distinguish between a plurality of shots. The shot identity comprises at least one of a number, letter, number. For example, shots are identified as 1, 2, 3, etc.
Optionally, the initial position is the coordinates of the shot point. For example, the initial position of shot 1 is (0 m,25 m), the initial position of shot 2 is (0 m,50 m), and the initial position of shot 3 is (0 m,75 m). In the embodiment of the present application, the number and arrangement of the plurality of shots are not particularly limited, and may be set and modified as needed.
In one possible implementation, a plurality of gun lines are arranged in the exploration work area, and a plurality of gun points are arranged on the gun lines; the spacing between any two adjacent shots in the plurality of shots may be the same or different. Alternatively, referring to fig. 2, the spacing between any two adjacent shots is the same, and the shot spacing is a first preset distance. In the embodiment of the present application, the value of the first preset distance is not specifically limited, and may be set and modified as required. Alternatively, the first preset distance is determined according to a scheme designed by the seismic acquisition parameters, for example, the first preset distance may be 20m, 30m, 40m, etc.
In one possible implementation, the step of determining, by the computer device, a plurality of first target shots disposed within the obstacle region from the plurality of shots according to the obstacle state information of the plurality of shots is: and the computer equipment determines that each shot point is a first target shot point if the obstacle state information of the shot point is a first numerical value, so as to obtain a plurality of first target shot points.
102. For each first target shot, the computer equipment determines rewarding information of a plurality of first offset actions corresponding to preset positions of the first target shot according to a pre-trained offset information model, the offset information model is used for determining rewarding information based on the positions and the offset actions, the first offset actions are used for moving the first target shot out of the obstacle area from the preset positions, and the rewarding information of the first offset actions is used for representing the first offset movement as a contribution value of moving the first target shot out of the obstacle area.
In one possible implementation, this step is: for each first target shot point, the computer equipment determines a preset position of the first target shot point and a plurality of first offset actions corresponding to the preset position; and inputting the preset position and each first offset action into an offset information model, outputting the reward information corresponding to the preset position and each first offset action, and obtaining the reward information of a plurality of first offset actions corresponding to the preset position.
Alternatively, the first offset action is one step to the left or one step to the right. The first target shot moves out of the obstacle region from the preset position through a first offset action. The reward information of one step to the left is used for representing a contribution value of moving out of the obstacle area for the first target shot point in one step to the left; the reward information for one step to the right is used to indicate the contribution value for one step to the right to move the first target shot out of the obstacle region. In the embodiment of the present application, the step size of each step is not specifically limited, and may be set and modified according to actual acquisition design parameters. In one possible implementation, the step size is the same as the shot size; alternatively, the step size is an integer multiple of the shot size. Alternatively, the step size may be any value between 5m and 500m, for example, 5m, 10m, 50m, 150m, etc. In one possible implementation, for each shot line, the shot spacing between any two adjacent shots on the shot line is the same.
103. The computer device determines a first target offset action having a largest value of the bonus information from among a plurality of first offset actions.
In this embodiment of the present application, the larger the value of the reward information of the first offset action, the larger the contribution of the first offset movement to move out of the obstacle area as the first target shot, the higher the efficiency of the first target shot to move out of the obstacle area by performing the first offset action, that is, the first target offset movement with the largest value of the reward information is regarded as the optimal offset action.
104. And the computer equipment determines that a new position of the shot layout is obtained after the first target shot performs the first target offset action.
In one possible implementation, the first target shift action is one step to the left or one step to the right; the new position of the shot point layout obtained after the first target offset action is executed can be determined by the coordinates of the preset position, the direction and the step length of the first target offset action. Correspondingly, the method comprises the following steps: if the first target offset action is a left step, the computer equipment determines that the difference between the abscissa of the preset position and the step length is the abscissa of the new position, and determines that the ordinate of the preset position is the ordinate of the new position; if the first target offset action is one step to the right, the computer equipment determines that the sum of the abscissa of the preset position and the step length is the abscissa of the new position, and determines that the ordinate of the preset position is the ordinate of the new position.
For example, the step length of the first target shift action is 20m, and the coordinates of the preset position are (0 m,0 m) with the same gun interval; the first target offset action is one step to the left; the coordinates of the new position of the shot layout obtained after the first target shot performs the first target offset action are (-20 m,0 m).
In the embodiment of the application, after the computer equipment executes the first target offset action to obtain a new position of the shot point layout, determining whether the new position moves out of the barrier area; if the first target shot point executes the first target offset action and then obtains that the new position of shot point layout is not in the obstacle area, the computer equipment determines the first target offset as the offset information of the first target shot point, and step 105 and step 106 are not executed any more; if the first target shot performs the first target offset operation, and then obtains that the new position of the shot layout is in the obstacle region, step 105 is continuously performed.
105. If the new position is in the obstacle area, the computer equipment determines rewarding 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 for moving the first target shot out of the obstacle area from the new position, and the rewarding information of the second offset actions are used for representing the second offset movements as contribution values of moving the first target shot out of the obstacle area.
In one possible implementation, the second offset action is one step to the left or one step to the right. Correspondingly, the method comprises the following steps: the computer equipment inputs the new position and each second offset action into an offset information model, outputs the rewarding information corresponding to the new position and each second offset action, and obtains the rewarding information of a plurality of second offset actions corresponding to the new position. The second offset action is used for moving the first target shot point out of the obstacle area from the new position, and the second offset action is one step leftwards or one step rightwards; the reward information of one step to the left is used for representing a contribution value of moving out of the obstacle area for the first target shot point in one step to the left; the reward information for one step to the right is used to indicate the contribution value for one step to the right to move the first target shot out of the obstacle region.
It should be noted that the direction of the firing line may be either a transverse direction or a longitudinal direction. Correspondingly, the offset direction of the second offset action is perpendicular to the direction of the gun line, or the offset direction of the second offset action is the same as the direction of the gun line. Optionally, when the offset direction is perpendicular to the cannon line direction, one step left or one step right is a lateral movement; when the offset direction is the same as the direction of the gun line, the left step or the right step is vertical movement.
106. And the computer equipment determines a second target offset action with the largest value of the rewarding information from the second offset actions until a new position of the shot point layout is not in the obstacle area after the second target offset action is executed, and at least one second target offset action is obtained.
The first target shot moves out of the obstacle region by performing at least one second target offset action. The number of the at least one second target offset action can be one or more, and when the number of the second target offset actions is one, the first target shot point moves out of the barrier area by executing the second target offset action to obtain a new position of shot point layout; when the number of the second target offset actions is multiple, the first target shot points are moved out of the obstacle area by the new positions of the shot point layout obtained after the second target offset actions are executed.
In one possible implementation, this step is: and the computer equipment determines a second target offset action with the largest value of the rewarding information from the second offset actions until a new position of the shot point layout is not in the obstacle area after the second target offset action is executed, and at least one second target offset action is obtained.
It should be noted that, each time the first target shot performs the second target offset action, a new position is obtained. If the new position of the shot point layout is in the obstacle area after the second target offset action is executed, determining a new second target offset action from a plurality of second offset actions corresponding to the new position; continuing to execute a new second target offset action until a new position of the shot point layout is not in the obstacle region after the second target offset action is executed; at least one second target offset action is determined to be performed.
In the embodiment of the application, as the second target offset is used as the optimal offset action corresponding to each new position, the offset path executed by the first target shot point at the preset position moving out of the obstacle area is ensured to be optimal through a plurality of optimal offset actions, and the accuracy of the determined shot point offset information is further improved.
107. The computer device determines an offset path comprised of the first target offset action and at least one second target offset action as offset information for the first target shot.
In one possible implementation manner, the offset information of the first target shot point includes an offset path, and accordingly, the steps are as follows: the computer device determines an offset path comprised of the first target offset action and at least one second target offset action as offset information for the first target shot.
In another possible implementation, the offset information of the first target shot includes an offset path and a number of times the offset action is performed. Correspondingly, the method comprises the following steps: the computer device determines an offset path consisting of a first target offset action and 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 offset information of the first target shot.
In another possible implementation, the offset information of the first target shot includes an offset path, a number of times the offset action is performed, and bonus information for performing the offset action; correspondingly, the method comprises the following steps: the computer device determines an offset path consisting of a first target offset action and at least one second target offset action, and determines a number of the first target offset action and the at least one second target offset action, and determines a sum of bonus information corresponding to the first target offset action and the at least one second target offset action, and determines the sum of the offset path, the number, and the bonus information as offset information of the first target shot.
For example, the first target shift action is one step to the left, and at least one second target shift action is one step to the left; the number of the at least one second target shift action is 2; the bonus information for executing the first target shift action is "-3"; the rewards information for executing at least one second target offset action is respectively "-2" and "-1"; the computer equipment determines the offset path to be offset to the left by 3 steps; the number of times of executing the offset action is 3, and the rewarding information of executing the offset action is "-6"; the offset information of the first target shot point is determined as follows: shifting 3 steps leftwards; the number of times of performing the offset operation is 3, and bonus information for performing the offset operation is "-6".
It should be noted that the offset information of each first target shot point is different, and one offset information corresponds to one offset strategy. For each first target shot, the offset path corresponding to the offset information of the first target shot is the shortest path, that is, the offset information of the first target shot corresponds to the optimal offset path, that is, the optimal offset strategy.
In one possible implementation, after determining the offset information for the first target shot, the computer device offsets the first target shot according to the shot offset information. Optionally, the computer device shifts the first target shots, and the arrangement diagrams of the shifted obstacles and shots are shown in fig. 4 and 5.
In one possible implementation manner, after the first target shot point is deviated through a deviation path formed by the first target deviation action and at least one second target deviation action, if the distance between the first target shot point and other shot points is smaller than a second preset distance, the shot point deviation information needs to be adjusted, so that the distance between the first target shot point and other shot points is ensured to be not smaller than the second preset distance. In the embodiment of the present application, the value of the second preset distance is not specifically limited, and may be set and modified as required. Alternatively, the second preset distance is any value between 5m and 500m, for example, 10m, 50m, 150m, etc. In one possible implementation, the second preset distance is an integer multiple of the cannon spacing.
In one possible implementation, the computer device adjusts shot offset information to obtain final shot offset information as follows: if the first target shot point is deviated through the deviation path, the distance between the first target shot point and the third target shot point is smaller than the second preset distance, and the distance between the first target shot point and the third target shot point is adjusted to be the second preset distance; the third target shot is other shot except the first target shot in the exploration work area.
In the embodiment of the application, 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 through the pre-trained offset information model, and further the offset information corresponding to the target shot point is determined through 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 is required to be determined, namely, the offset strategy of the shot point in the obstacle area is obtained rapidly, and the efficiency of determining the offset information is improved.
It should be noted that the pre-trained offset information model is a neural network model. The migration information model is, for example, a fully connected neural network (Fully Connected Neural Network). The offset information model is used for determining rewarding information through the positions of shot points and offset actions, so that an offset strategy is obtained quickly. In one possible implementation, a plurality of shot lines are arranged in the exploration work area, and each shot line is provided with a plurality of shot points; the computer equipment trains the initial offset model through the positions, offset actions and rewarding information corresponding to the shots on the target shot lines, and the trained offset information model is obtained. Accordingly, referring to fig. 6, the step of the computer device determining the offset information model includes the following steps 601 to 604:
601. The computer device determines a target shot line having a greatest number of shots disposed within the obstacle region from among the plurality of shot lines, and determines a plurality of second target shots disposed within the obstacle region on the target shot line.
In one possible implementation, this step is: for each shot line, the computer equipment determines the number of shot points of the shot line which are distributed in the barrier area, and determines a target shot line with the largest number of shot points which are distributed in the barrier area from a plurality of shot lines; and determining a plurality of shots arranged in the obstacle area on the target shot line as a plurality of second target shots. The target cannon line is the cannon line with the largest number of cannon points in the obstacle area, namely the cannon line with the most complex state.
In the embodiment of the application, since the target shot lines with the most number of shots and the most complex state are selected from the plurality of shot lines, the offset information of the second target shot point on the target shot line can comprise the offset information of the shots on other shot lines, and further the offset information of each shot point in the barrier area can be determined, that is, only the target shot line with the most complex state needs to be trained, and the offset information of all the shots can be determined according to the offset information obtained by training, so that the efficiency of determining the offset information of the shots is improved.
Optionally, the step of the computer device determining, for each shot line, the number of shots the shot line is arranged in the obstacle region is: and the computer equipment acquires barrier state information of each shot point on each shot line, if the barrier state information is used for indicating that the shot point is arranged in the barrier area, the computer equipment counts the shot points, and the number of the shot points of which the shot lines are arranged in the barrier area is obtained. The method for acquiring the obstacle state information of the shot point by the computer device is the same as the method for acquiring the obstacle state information of the shot point in step 101, and will not be described herein.
602. The computer device determines, for each second target shot, a plurality of positions on any one of the possible paths for the second target shot to move out of the obstacle region from the current position.
For each second target shot, any feasible path moving out of the obstacle area from the current position needs to execute a plurality of offset actions, and each time the offset action is executed, a new position is obtained, and a plurality of positions corresponding to the feasible path are obtained. In one possible implementation, any one of the feasible paths includes a plurality of the feasible paths, each of the feasible paths corresponding to a plurality of the positions; the plurality of positions on any one feasible path is a sum of a plurality of positions corresponding to the plurality of feasible paths.
In one possible implementation, for any position, the offset action is performed by one step leftwards or one step rightwards, and the step length corresponding to each offset action 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.
603. The computer equipment determines first rewarding information corresponding to the second target shot points to obtain a plurality of first rewarding information corresponding to the second target shot points, wherein the first rewarding information comprises rewarding information of a plurality of offset actions corresponding to the second target shot points at a plurality of positions.
In one possible implementation, the step of determining, by the computer device, the first reward information corresponding to the second target shot is: for each position, the computer equipment determines second rewarding information corresponding to the second target shot point at the position to obtain a plurality of pieces of second rewarding information corresponding to a plurality of positions, wherein the second rewarding information corresponding to each position comprises expected rewarding information of a plurality of third offset actions corresponding to the second target shot point at the position; and determining a plurality of pieces of second rewards information corresponding to the plurality of positions as first rewards information corresponding to the second target shot point. Each time the second target shot moves, a new position is obtained, and the new position corresponds to a plurality of third offset actions; the second target shot is moved a plurality of times, and the first bonus information includes a plurality of second bonus information corresponding to a plurality of positions of the plurality of movements.
Optionally, each position corresponds to a plurality of offset actions, and expected reward information corresponding to each position and each offset action is different; the second rewards information corresponding to the second target shot at the location includes expected rewards information for a plurality of offset actions corresponding to the location. Correspondingly, for each position, the computer equipment determines the second rewarding information corresponding to the second target shot point at the position by the steps of: for each position, the computer device determines a plurality of third offset actions corresponding to the position; for each third offset action, determining an instant prize for performing the third offset action, the instant prize for representing the third offset movement as a current contribution value for the second target shot out of the obstacle region, and determining a long-term prize for performing the third offset action for representing the third offset movement as a long-term contribution value for the second target shot out of the obstacle region; determining expected rewarding information corresponding to the third offset action based on the instant rewarding and the long-term rewarding, and obtaining a plurality of pieces of expected rewarding information corresponding to a plurality of third offset actions; and determining a plurality of pieces of expected rewards information corresponding to the third offset actions as second rewards information corresponding to the second target shot positions.
In one possible implementation, the instant prize for the third offset action is related to the number of steps of the third offset action, such as: the corresponding instant prize to the left step is "-1"; the corresponding instant prize for the left two steps is "-2". Optionally, the plurality of third offset actions includes one step left and one step right, and the corresponding immediate prize for the third offset action is "-1".
In one possible implementation, the computer device determines a long-term incentive for the current location to perform the third offset action based on incentive information for the new location to which the third offset action is to be applied. Accordingly, the computer device determines the forward prize for performing the third offset action as: the computer equipment determines a new position of the second target shot point after the third offset action is executed; determining a plurality of fourth offset actions corresponding to new positions of the second target shot, and determining rewarding information corresponding to the fourth offset actions for each fourth offset action to obtain a plurality of rewarding information corresponding to the fourth offset actions, wherein the rewarding information corresponding to the fourth offset actions is used for representing the fourth offset movement as a contribution value of the second target shot moving out of the obstacle area; the prize information having the largest value is determined from the plurality of prize information as the forward prize for performing the third offset action.
In one possible implementation, the step of determining the desired reward information corresponding to the third offset action by the computer device based on the instant reward and the long-term reward is: the computer equipment determines a discount coefficient corresponding to the third offset action; based on the discount coefficient, the instant rewards and the long-term rewards, determining expected rewards information corresponding to the third offset action through the following formula I;
equation one: y=r+γmax a′ Q(S′,a)
Wherein y represents expected rewarding information corresponding to the third offset action, R represents instant rewarding, gamma represents discount coefficient, and max a′ Q (S ', a) represents a long-term reward, S' represents a new position of the second target shot after the third offset action is executed; a' represents a plurality of fourth offset operations corresponding to a new position of the second target shot, and a represents any one of the plurality of fourth offset operations.
In one possible implementation, the correspondence between the position, the offset action, and the bonus information is stored in a computer. Correspondingly, the computer equipment determines a plurality of fourth offset actions corresponding to the new position of the second target shot, and for each fourth offset action, the step of determining the rewarding information corresponding to the fourth offset action is as follows: and the computer equipment determines the reward information corresponding to the fourth offset action from the stored corresponding relation among the position, the offset action and the reward information according to the new position and the fourth offset action.
Alternatively, the position may be represented by S, the offset action may be represented by a, the bonus information may be represented by Q, and the correspondence between the position stored in the computer, the offset action, and the bonus information is an S-a-Q table, abbreviated as S-Q table. In one possible implementation manner, the computer device updates the reward information through Q-learning for each second target shot to obtain the reward information corresponding to each position and each offset action. Correspondingly, the step of the computer device determining the S-Q table is: the computer equipment corresponding to each position and each offset action, determining initial rewards, instant rewards, learning rates, discount factors and long-term rewards for executing the offset action at the position; updating the initial rewards until the difference value of the rewards information obtained by updating the initial rewards in two adjacent times is not larger than a preset threshold value, and determining the rewards information obtained by updating the initial rewards in the last time as the rewards information corresponding to the position and the offset action;
formula II: q' (S, A) ≡Q (S, A) +alpha (R+γmax) a′ Q(S′,a)-Q(S,A))
Wherein Q' (S, A) represents updated incentive information, Q (S, A) represents initial incentive, alpha represents learning rate, gamma represents discount coefficient, max a′ Q (S ', a) represents a long-term reward for executing the offset action, S' represents a new position of the second target shot after executing the offset action; a' represents a plurality of offset actions corresponding to the new position, and a represents any offset action corresponding to the new position.
It should be noted that, if the difference between the updated bonus information and the last updated bonus information is greater than the preset threshold, the updated bonus information is used as the initial bonus, and iterative updating is continuously performed through the formula two until the difference between the bonus information obtained by two adjacent updates is not greater than the preset threshold, that is, the difference between the updated bonus information and the last updated bonus information is not greater than the preset threshold. In one possible implementation, the preset threshold is any value between 0.001 and 0.1, for example, the preset threshold is 0.001, 0.002, 0.003.
In the embodiment of the present application, the values of the initial prize, the learning rate, and the discount coefficient are not particularly limited, and may be set and modified as needed. Optionally, the computer device sets an initial prize value Q (S, a) to 0; discount coefficient γ is 1; the learning rate α was 0.001.
In one possible implementation manner, if the number of updates reaches a preset number, determining that the bonus information obtained by the last update is the bonus information corresponding to the position and the offset action. In the embodiment of the present application, the number of times of the preset is not particularly limited, and may be set and modified as needed. Optionally, the preset number of times is 1000 times.
In one possible implementation, for a plurality of offset actions corresponding to a location, the computer device randomly selects an offset action from the plurality of offset actions. In another possible implementation, for a plurality of offset actions corresponding to a location, the probability that the computer device selects a certain offset action corresponds to epsilon-greedy (greedy policy). Correspondingly, the probability of selecting a certain offset action by the computer equipment is pi (a|s);
where s represents the position, a represents the selected offset action, and pi (a|s) represents the probability of selecting the offset action a at the position s; ε represents the probability parameter of the offset action, |A| represents the number of multiple offset actions, A * Representing a set of multiple offset actions.
In one possible implementation, to ensure that each offset action is selected, the computer device sets a probability parameter for the offset action that is inversely related to the number of times that offset action is performed. Optionally, the relationship between the probability parameter of the offset action and the number of times the offset action is performed is: epsilon=1 x (0.9) m The method comprises the steps of carrying out a first treatment on the surface of the Where ε represents a probability parameter for the offset action and m represents the number of times the offset action is performed. For example, at location S, the computer device first determines the offset action as a1 by ε -greedy; the probability of next choosing the action a1 will decrease.
604. The computer equipment trains the initial offset information model based on a plurality of first rewards information corresponding to a plurality of second target shots to obtain the offset information model.
In one possible implementation, the computer device uses a plurality of first rewards information corresponding to a plurality of second target shots as sample data, and trains the initial offset information model through the sample data to obtain an offset information model. Correspondingly, the method comprises the following steps: for each second target shot point, the computer equipment inputs a plurality of positions corresponding to the second target shot point into an initial offset information model, and outputs third rewarding information corresponding to the second target shot point, wherein the third rewarding information comprises estimated rewarding information of a plurality of offset actions corresponding to the second target shot point at the plurality of positions; determining a loss parameter between the third rewarding information and the first rewarding information, and if the loss parameter is larger than a preset value, adjusting an offset parameter in the initial offset information model until the loss parameter is not larger than the preset value; and determining a corresponding target offset parameter when the loss parameter is not greater than a preset value, and obtaining an offset information model. Optionally, the initial bias information model is a fully connected neural network model.
Optionally, the step of determining the loss parameter between the third bonus information and the first bonus information by the computer device is: the computer equipment determines loss parameters between the third rewarding information and the first rewarding information according to the third rewarding information and the first rewarding information through the following formula III;
and (3) a formula III: loss= (y-Q (S', a|θ)) 2
Where Loss denotes a Loss parameter, θ denotes an offset parameter, y denotes desired bonus information for performing an offset action a at a position S ', and Q (S ', a|θ) denotes estimated bonus information for performing the offset action a at the position S ' when the offset parameter θ is present.
In the embodiment of the present application, the numerical value of the preset value is not particularly limited, and may be set and modified as needed. Optionally, the preset value is any value between 0.001 and 0.1; for example, 0.001, 0.01, 0.05, etc.
In the embodiment of the application, the intelligent determination method for the offset information of the shot point is provided, and in the indoor design stage of seismic acquisition, targeted training can be performed according to the offset requirement of an oil company to obtain an offset information model, so that the offset information of the shot point is determined, the manual working intensity is greatly reduced, and the working efficiency for determining the offset information of the shot point is improved.
The embodiment of the application provides a method for determining offset information of a shot point, which is characterized in that a first target offset action corresponding to a target shot point at a preset position and a second target offset action corresponding to a new position of the target shot point are determined through a pre-trained offset information model, and further, the offset information corresponding to the target shot point is determined through 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 is required to be determined, and therefore the efficiency of determining the offset information of the shot point is improved.
Fig. 7 is a block diagram illustrating a determination apparatus of shot offset information according to an exemplary embodiment. Referring to fig. 7, the apparatus includes:
an acquisition module 701, configured to acquire a plurality of first target shots disposed in an obstacle region in an exploration work area;
a first determining module 702, configured to determine, for each first target shot, rewarding information of a plurality of first offset actions corresponding to preset positions of the first target shot according to a pre-trained offset information model, where the offset information model is configured to determine rewarding information based on the positions and the offset actions, the first offset actions are used for moving the first target shot out of the obstacle region from the preset positions, and the rewarding information of the first offset actions is used for indicating the first offset movement as a contribution value of the first target shot moving out of the obstacle region;
A second determining module 703, configured to determine a first target offset action with the largest value of the bonus information from the plurality of first offset actions;
a third determining module 704, configured to determine a new position of the shot layout obtained after the first target shot performs the first target offset action;
a fourth determining module 705, configured to determine, according to the offset information model, rewarding information of a plurality of second offset actions corresponding to the new location if the new location is in the obstacle area, where the second offset actions are used to move the first target shot out of the obstacle area from the new location, and the rewarding information of the second offset actions is used to represent the second offset movement as a contribution value of the first target shot out of the obstacle area;
a fifth determining module 706, configured to determine a second target offset action with the largest value of the bonus information from the plurality of second offset actions, until a new position of the shot point layout obtained after the execution of the second target offset action is not in the obstacle region, and obtain at least one second target offset action;
a sixth determining module 707 is configured to determine an offset path formed by the first target offset action and at least one second target offset action as offset information of the first target shot.
In one possible implementation, referring to fig. 8, a plurality of shot lines are disposed in the exploration work area, and a plurality of shot points are disposed on each shot line; the apparatus further comprises a training module 708, the training module 708 comprising:
a first determining unit 7081 for determining a target shot line having the largest number of shots laid in the obstacle region from among a plurality of shot lines, and determining a plurality of second target shots laid in the obstacle region on the target shot line;
a second determining unit 7082 for determining, for each second target shot, a plurality of positions on any one of the possible paths in which the second target shot moves out of the obstacle region from the current position;
third determining unit 7083, configured to determine first reward information corresponding to the second target shot, and obtain a plurality of first reward information corresponding to a plurality of second target shots, where the first reward information includes reward information of a plurality of offset actions corresponding to the second target shots at a plurality of positions;
In another possible implementation manner, the third determining unit 7083 is configured to determine, for each position, second rewarding information corresponding to the position of the second target shot, to obtain a plurality of second rewarding information corresponding to a plurality of positions, where the second rewarding information includes expected rewarding information of a plurality of third offset actions corresponding to the position of the second target shot; and determining a plurality of pieces of second rewards information corresponding to the plurality of positions as first rewards information corresponding to the second target shot point.
In another possible implementation manner, the third determining unit 7083 is configured to determine a plurality of third offset actions corresponding to the positions of the second target shot points; for each third offset action, determining an instant prize for performing the third offset action, the instant prize for representing the third offset movement as a current contribution value for the second target shot out of the obstacle region, and determining a long-term prize for performing the third offset action for representing the third offset movement as a long-term contribution value for the second target shot out of the obstacle region; determining expected rewarding information corresponding to the third offset action based on the instant rewarding and the long-term rewarding, and obtaining a plurality of pieces of expected rewarding information corresponding to a plurality of third offset actions; and determining a plurality of pieces of expected rewards information corresponding to the third offset actions as second rewards information corresponding to the second target shot positions.
In another possible implementation manner, the third determining unit 7083 is configured to determine a new position where the second target shot point is located after the third offset action is performed; determining a plurality of fourth offset actions corresponding to new positions of the second target shot, and determining rewarding information corresponding to the fourth offset actions for each fourth offset action to obtain a plurality of rewarding information corresponding to the fourth offset actions, wherein the rewarding information corresponding to the fourth offset actions is used for representing the fourth offset movement as a contribution value of the second target shot moving out of the obstacle area; the prize information having the largest value is determined from the plurality of prize information as the forward prize for performing the third offset action.
In another possible implementation manner, the training unit 7084 is configured to input, for each second target shot, a plurality of offset actions corresponding to the second target shot at a plurality of positions into the initial offset information model, and output third prize information corresponding to the second target shot, where the third prize information includes estimated prize information of the plurality of offset actions corresponding to the second target shot at the plurality of positions; determining a loss parameter between the third rewarding information and the first rewarding information, and if the loss parameter is larger than a preset value, adjusting an offset parameter in the initial offset information model until the loss parameter is not larger than the preset value; and determining a corresponding target offset parameter when the loss parameter is not greater than a preset value, and obtaining an offset information model.
The embodiment of the application provides a determining device for offset information of a shot point, which determines a first target offset action corresponding to a target shot point at a preset position and a second target offset action corresponding to a new position through a pre-trained offset information model, and further determines the offset information corresponding to the target shot point through 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 is required to be determined, and therefore the efficiency of determining the offset information of the shot point is improved.
Fig. 9 shows a block diagram of a computer device 900 provided by an exemplary embodiment of the invention. The computer device 900 may be: a smart phone, a tablet computer, an MP3 player (Moving Picture Experts Group Audio Layer III, motion picture expert compression standard audio plane 3), an MP4 (Moving Picture Experts Group Audio Layer IV, motion picture expert compression standard audio plane 4) player, a notebook computer, or a desktop computer. Computer device 900 may also be referred to by other names as user device, portable computer device, laptop computer device, desktop computer device, etc.
In general, the computer device 900 includes: a processor 901 and a memory 902.
The memory 902 may include one or more computer-readable storage media, which may be non-transitory. The memory 902 may also include high-speed random access memory, as well as non-volatile memory, such as one or more magnetic disk storage devices, flash memory storage devices. In some embodiments, a non-transitory computer readable storage medium in memory 902 is used to store at least one instruction for execution by processor 901 to implement a method of determining shot offset information provided by a method embodiment in the present application.
In some embodiments, the computer device 900 may also optionally include: a peripheral interface 903, and at least one peripheral. The processor 901, memory 902, and peripheral interface 903 may be connected by a bus or signal line. The individual peripheral devices may be connected to the peripheral device interface 903 via buses, signal lines, or circuit boards. Specifically, the peripheral device includes: at least one of radio frequency circuitry 904, a display 905, a camera 906, audio circuitry 907, positioning components 908, and a power source 909.
The peripheral interface 903 may be used to connect at least one peripheral device associated with an I/O (Input/Output) to the processor 901 and the memory 902. In some embodiments, the processor 901, memory 902, and peripheral interface 903 are integrated on the same chip or circuit board; in some other embodiments, either or both of the processor 901, the memory 902, and the peripheral interface 903 may be implemented on separate chips or circuit boards, which is not limited in this embodiment.
The Radio Frequency circuit 904 is configured to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The radio frequency circuit 904 communicates with a communication network and other communication devices via electromagnetic signals. The radio frequency circuit 904 converts an electrical signal into an electromagnetic signal for transmission, or converts a received electromagnetic signal into an electrical signal. Optionally, the radio frequency circuit 904 includes: antenna systems, RF transceivers, one or more amplifiers, tuners, oscillators, digital signal processors, codec chipsets, subscriber identity module cards, and so forth. The radio frequency circuitry 904 may communicate with other computer devices via at least one wireless communication protocol. The wireless communication protocol includes, but is not limited to: metropolitan area networks, various generations of mobile communication networks (2G, 3G, 4G, and 5G), wireless local area networks, and/or WiFi (Wireless Fidelity ) networks. In some embodiments, the radio frequency circuit 904 may also include NFC (Near Field Communication ) related circuits, which are not limited in this application.
The display 905 is used to display a UI (user interface). The UI may include graphics, text, icons, video, and any combination thereof. When the display 905 is a touch display, the display 905 also has the ability to capture touch signals at or above the surface of the display 905. The touch signal may be input as a control signal to the processor 901 for processing. At this time, the display 905 may also be used to provide virtual buttons and/or a virtual keyboard, also referred to as soft buttons and/or a soft keyboard. In some embodiments, the display 905 may be one, providing a front panel of the computer device 900; in other embodiments, the display 905 may be at least two, respectively disposed on different surfaces of the computer device 900 or in a folded design; in still other embodiments, the display 905 may be a flexible display disposed on a curved surface or a folded surface of the computer device 900. Even more, the display 905 may be arranged in an irregular pattern other than rectangular, i.e., a shaped screen. The display 905 may be made of LCD (Liquid Crystal Display ), OLED (Organic Light-Emitting Diode) or other materials.
The camera assembly 906 is used to capture images or video. Optionally, the camera assembly 906 includes a front camera and a rear camera. Typically, the front camera is disposed on a front panel of the computer device and the rear camera is disposed on a rear surface of the computer device. In some embodiments, the at least two rear cameras are any one of a main camera, a depth camera, a wide-angle camera and a tele camera, so as to realize that the main camera and the depth camera are fused to realize a background blurring function, and the main camera and the wide-angle camera are fused to realize a panoramic shooting and Virtual Reality (VR) shooting function or other fusion shooting functions. In some embodiments, camera assembly 906 may also include a flash. The flash lamp can be a single-color temperature flash lamp or a double-color temperature flash lamp. The dual-color temperature flash lamp refers to a combination of a warm light flash lamp and a cold light flash lamp, and can be used for light compensation under different color temperatures.
The audio circuit 907 may include a microphone and a speaker. The microphone is used for collecting sound waves of users and the environment, converting the sound waves into electric signals, and inputting the electric signals to the processor 901 for processing, or inputting the electric signals to the radio frequency circuit 904 for voice communication. For purposes of stereo acquisition or noise reduction, the microphone may be multiple, each disposed at a different location of the computer device 900. The microphone may also be an array microphone or an omni-directional pickup microphone. The speaker is used to convert electrical signals from the processor 901 or the radio frequency circuit 904 into sound waves. The speaker may be a conventional thin film speaker or a piezoelectric ceramic speaker. When the speaker is a piezoelectric ceramic speaker, not only the electric signal can be converted into a sound wave audible to humans, but also the electric signal can be converted into a sound wave inaudible to humans for ranging and other purposes. In some embodiments, the audio circuit 907 may also include a headphone jack.
The location component 908 is used to locate the current geographic location of the computer device 900 to enable navigation or LBS (Location Based Service, location-based services). The positioning component 908 may be a positioning component based on the United states GPS (Global Positioning System ), the Beidou system of China, the Granati system of Russia, or the Galileo system of the European Union.
The power supply 909 is used to power the various components in the computer device 900. The power supply 909 may be an alternating current, a direct current, a disposable battery, or a rechargeable battery. When the power supply 909 includes a rechargeable battery, the rechargeable battery can support wired or wireless charging. The rechargeable battery may also be used to support fast charge technology.
In some embodiments, computer device 900 also includes one or more sensors 910. The one or more sensors 910 include, but are not limited to: acceleration sensor 911, gyroscope sensor 912, pressure sensor 913, fingerprint sensor 914, optical sensor 915, and proximity sensor 916.
The acceleration sensor 911 can detect the magnitudes of accelerations on three coordinate axes of the coordinate system established by the computer device 900. For example, the acceleration sensor 911 may be used to detect components of gravitational acceleration in three coordinate axes. The processor 901 may control the display 905 to display the user interface in a landscape view or a portrait view according to the gravitational acceleration signal acquired by the acceleration sensor 911. The acceleration sensor 911 may also be used for the acquisition of motion data of a game or a user.
The gyro sensor 912 may detect a body direction and a rotation angle of the computer device 900, and the gyro sensor 912 may collect a 3D motion of the user on the computer device 900 in cooperation with the acceleration sensor 911. The processor 901 may implement the following functions according to the data collected by the gyro sensor 912: motion sensing (e.g., changing UI according to a tilting operation by a user), image stabilization at shooting, game control, and inertial navigation.
The pressure sensor 913 may be disposed on a side frame of the computer device 900 and/or on an underside of the display 905. When the pressure sensor 913 is disposed on the side frame of the computer device 900, a holding signal of the computer device 900 by the user may be detected, and the processor 901 performs left-right hand recognition or quick operation according to the holding signal collected by the pressure sensor 913. When the pressure sensor 913 is provided at the lower layer of the display 905, the processor 901 performs control of the operability control on the UI interface according to the pressure operation of the user on the display 905. The operability controls include at least one of a button control, a scroll bar control, an icon control, and a menu control.
The fingerprint sensor 914 is used for collecting the fingerprint of the user, and the processor 901 identifies the identity of the user according to the fingerprint collected by the fingerprint sensor 914, or the fingerprint sensor 914 identifies the identity of the user according to the collected fingerprint. Upon recognizing that the user's identity is a trusted identity, the processor 901 authorizes the user to perform relevant sensitive operations including unlocking the screen, viewing encrypted information, downloading software, paying for and changing settings, etc. The fingerprint sensor 914 may be provided on the front, back, or side of the computer device 900. When a physical key or vendor Logo is provided on the computer device 900, the fingerprint sensor 914 may be integrated with the physical key or vendor Logo.
The optical sensor 915 is used to collect the intensity of ambient light. In one embodiment, the processor 901 may control the display brightness of the display panel 905 based on the intensity of ambient light collected by the optical sensor 915. Specifically, when the ambient light intensity is high, the display luminance of the display screen 905 is turned up; when the ambient light intensity is low, the display luminance of the display panel 905 is turned down. In another embodiment, the processor 901 may also dynamically adjust the shooting parameters of the camera assembly 906 based on the ambient light intensity collected by the optical sensor 915.
A proximity sensor 916, also referred to as a distance sensor, is typically provided on the front panel of the computer device 900. Proximity sensor 916 is used to capture the distance between the user and the front of computer device 900. In one embodiment, when the proximity sensor 916 detects that the distance between the user and the front of the computer device 900 gradually decreases, the processor 901 controls the display 905 to switch from the bright screen state to the off screen state; when the proximity sensor 916 detects that the distance between the user and the front surface of the computer device 900 gradually increases, the display 905 is controlled by the processor 901 to switch from the off-screen state to the on-screen state.
Those skilled in the art will appreciate that the architecture shown in fig. 9 is not limiting of the computer device 900, and may include more or fewer components than shown, or may combine certain components, or employ a different arrangement of components.
In an exemplary embodiment, there is also provided a storage medium including a program code, the computer-readable storage medium storing therein at least one piece of program code, the at least one piece of program code being loaded and executed by a processor to implement the method of determining shot offset information in any one of the possible implementations described above.
In an exemplary embodiment, a computer program product is also provided, comprising at least one piece of program code, which is loaded and executed by a processor to implement a method of determining shot offset information in any of the possible implementations described above.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any adaptations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
The foregoing is illustrative of the present invention and is not to be construed as limiting thereof, but rather as being included within the spirit and principles of the present invention.
Claims (10)
1. A method for determining shot offset information, the method comprising:
acquiring a plurality of first target shots distributed in an obstacle area in an exploration work area;
determining rewarding information of a plurality of first offset actions corresponding to preset positions of the first target shots according to a pre-trained offset information model for each first target shot, wherein the offset information model is used for determining rewarding information based on the positions and the offset actions, the first offset actions are used for enabling the first target shots to move out of the obstacle area from the preset positions, and the rewarding information of the first offset actions is used for representing the first offset movements as contribution values of the first target shots moving out of the obstacle area;
determining a first target offset action with the largest value of the rewarding information from the plurality of first offset actions;
determining a new position of the shot layout after the first target shot executes the first target offset action;
If the new position is in the obstacle region, determining rewarding information of a plurality of second offset actions corresponding to the new position according to the offset information model, wherein the second offset actions are used for moving the first target shot out of the obstacle region from the new position, and the rewarding information of the second offset actions are used for representing the second offset movements as contribution values of the first target shot moving out of the obstacle region;
determining a second target offset action with the largest value of the rewarding information from the plurality of second offset actions until a new position of the shot point layout is not in the obstacle area after the second target offset action is executed, and obtaining at least one second target offset action;
and determining an offset path formed by 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 disposed in the exploration work area, each shot line having a plurality of shots disposed thereon; the process of determining the offset information model is as follows:
determining a target shot line with the largest number of shots arranged in the barrier area from the plurality of shot lines, and determining a plurality of second target shots arranged in the barrier area on the target shot line;
For each second target shot, determining a plurality of positions on any feasible path where the second target shot moves out of the obstacle region from the current position;
determining first rewarding information corresponding to the second target shot points to obtain a plurality of first rewarding information corresponding to a plurality of second target shot points, wherein the first rewarding information comprises rewarding information of a plurality of offset actions corresponding to the second target shot points at a plurality of positions;
training an initial offset information model based on rewarding information of a plurality of offset actions corresponding to the second target shots at the positions to obtain the offset information model.
3. The method of claim 2, wherein the determining the first bonus information corresponding to the second target shot comprises:
for each position, determining second rewarding information corresponding to the second target shot point at the position, and obtaining a plurality of pieces of second rewarding information corresponding to the plurality of positions, wherein the second rewarding information corresponding to each position comprises expected rewarding information of a plurality of third offset actions corresponding to the second target shot point at the position;
and determining a plurality of pieces of second rewarding information corresponding to the plurality of positions as first rewarding information corresponding to the second target shot point.
4. The method of claim 3, wherein the determining second prize information for the second target shot at the location comprises:
determining a plurality of third offset actions corresponding to the second target shot points at the positions;
for each third offset action, determining an instant prize for performing the third offset action for representing the third offset movement as a current contribution value for the second target shot to move out of the obstacle region, and determining a long-term prize for performing the third offset action for representing the third offset movement as a long-term contribution value for the second target shot to move out of the obstacle region;
determining expected rewards information corresponding to the third offset actions based on the instant rewards and the long-term rewards, and obtaining a plurality of pieces of expected rewards information corresponding to a plurality of third offset actions;
and determining a plurality of pieces of expected rewards information corresponding to the plurality of third offset actions as second rewards information corresponding to the second target shot at the position.
5. The method of claim 4, wherein the determining a long-term reward for performing the third offset action comprises:
Determining a new position of the second target shot point after the third offset action is executed;
determining a plurality of fourth offset actions corresponding to new positions of the second target shot, and determining rewarding information corresponding to the fourth offset actions for each fourth offset action to obtain a plurality of rewarding information corresponding to the fourth offset actions, wherein the rewarding information corresponding to the fourth offset actions is used for representing the fourth offset movement as a contribution value of the second target shot moving out of the obstacle area;
determining the most numeric bonus information from the plurality of bonus information as the long-term bonus for executing the third offset action.
6. The method of claim 2, wherein training an initial offset information model based on rewards information of a plurality of offset actions corresponding to the plurality of second target shots at the plurality of positions to obtain the offset information model comprises:
for each second target shot, inputting a plurality of offset actions of the second target shot corresponding to the plurality of positions into the initial offset information model, and outputting third rewarding information corresponding to the second target shot, wherein the third rewarding information comprises estimated rewarding information of the plurality of offset actions of the second target shot corresponding to the plurality of positions;
Determining a loss parameter between the third rewarding information and the first rewarding information, and if the loss parameter is larger than a preset value, adjusting an offset parameter in the initial offset information model until the loss parameter is not larger than the preset value;
and determining a corresponding target offset parameter when the loss parameter is not larger than the preset value, and obtaining the offset information model.
7. A shot point offset information determining apparatus, the apparatus comprising:
the acquisition module is used for acquiring a plurality of first target shot points which are distributed in the obstacle area in the exploration work area;
the first determining module is used for determining rewarding information of a plurality of first offset actions corresponding to preset positions of the first target shot points according to a pre-trained offset information model for each first target shot point, the offset information model is used for determining rewarding information based on the positions and the offset actions, the first offset actions are used for enabling the first target shot point to move out of the obstacle area from the preset positions, and the rewarding information of the first offset actions is used for representing the first offset movements as contribution values of the first target shot point moving out of the obstacle area;
A second determining module, configured to determine a first target offset action with a largest value of the bonus information from the plurality of first offset actions;
the third determining module is used for determining a new position of the shot layout after the first target shot executes the first target offset action;
a fourth determining module, configured to determine, according to the offset information model, rewarding information of a plurality of second offset actions corresponding to the new location, where the second offset actions are used to move the first target shot out of the obstacle area from the new location, and the rewarding information of the second offset actions is used to represent a contribution value of the second offset movement as the movement of the first target shot out of the obstacle area;
a fifth determining module, configured to determine a second target offset action with the largest value of the reward information from the plurality of second offset actions, until a new position of shot placement obtained after the execution of the second target offset action is not in the obstacle area, and obtain at least one second target offset action;
and a sixth determining module, configured to determine an offset path formed by 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, the computer device comprising:
a processor and a memory having stored therein at least one piece of program code that is loaded and executed by the processor to carry out the operations performed by the method of determining shot offset information of any one of claims 1 to 6.
9. A computer readable storage medium having stored therein at least one program code loaded and executed by a processor to perform the operations performed by the method of determining shot offset information according to any one of claims 1 to 6.
10. A computer program product, characterized in that the computer program product comprises at least one piece of program code, which is loaded and executed by a processor to implement the method of determining shot offset information according to any one of claims 1 to 6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111531938.2A CN116263512A (en) | 2021-12-14 | 2021-12-14 | Determination method, device, equipment, storage medium and product of shot offset information |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111531938.2A CN116263512A (en) | 2021-12-14 | 2021-12-14 | Determination method, device, equipment, storage medium and product of shot offset information |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116263512A true CN116263512A (en) | 2023-06-16 |
Family
ID=86723482
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111531938.2A Pending CN116263512A (en) | 2021-12-14 | 2021-12-14 | Determination method, device, equipment, storage medium and product of shot offset information |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116263512A (en) |
-
2021
- 2021-12-14 CN CN202111531938.2A patent/CN116263512A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108619721B (en) | Distance information display method and device in virtual scene and computer equipment | |
US11221726B2 (en) | Marker point location display method, electronic device, and computer-readable storage medium | |
US20200316473A1 (en) | Virtual object control method and apparatus, computer device, and storage medium | |
WO2019153750A1 (en) | Method, apparatus and device for view switching of virtual environment, and storage medium | |
CN108710525B (en) | Map display method, device, equipment and storage medium in virtual scene | |
CN109614171B (en) | Virtual item transfer method and device, electronic equipment and computer storage medium | |
WO2020207204A1 (en) | Method and device for observing virtual article in virtual environment, and readable storage medium | |
CN110986930B (en) | Equipment positioning method and device, electronic equipment and storage medium | |
CN108536295B (en) | Object control method and device in virtual scene and computer equipment | |
CN113763228B (en) | Image processing method, device, electronic equipment and storage medium | |
WO2019105352A1 (en) | Method and device for refreshing resource bases in virtual map and storage medium | |
CN112150560B (en) | Method, device and computer storage medium for determining vanishing point | |
CN111754386B (en) | Image area shielding method, device, equipment and storage medium | |
US20220291791A1 (en) | Method and apparatus for determining selected target, device, and storage medium | |
CN111857793B (en) | Training method, device, equipment and storage medium of network model | |
CN113160031B (en) | Image processing method, device, electronic equipment and storage medium | |
CN112882094B (en) | First-arrival wave acquisition method and device, computer equipment and storage medium | |
CN111383243A (en) | Method, device, equipment and storage medium for tracking target object | |
CN113009573B (en) | Seismic data acquisition method, device, computer equipment and storage medium | |
CN112365088B (en) | Method, device and equipment for determining travel key points and readable storage medium | |
CN111984755B (en) | Method and device for determining target parking spot, electronic equipment and storage medium | |
CN116263512A (en) | Determination method, device, equipment, storage medium and product of shot offset information | |
CN112990421B (en) | Method, device and storage medium for optimizing operation process of deep learning network | |
CN113469322B (en) | Method, device, equipment and storage medium for determining executable program of model | |
CN115545592A (en) | Display positioning method, device, equipment and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |