Area search processing method and apparatus, electronic device, and storage medium

Abstract

The present disclosure provides a region search processing method and device, electronic equipment and storage medium, and relates to the technical fields of artificial intelligence and intelligent search. The specific implementation scheme is as follows: determining a current position of a current search subject in a search region; determining a neighboring position of the current position in the search region; obtaining search feature information of the current position and search feature information of the neighboring position; and planning next search information of the current search subject in the search region for searching a target object based on the search feature information of the current position and the search feature information of the neighboring position. The present disclosure can effectively improve the efficiency of region search.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of computers, in particular to the technical field of artificial intelligence and intelligent search, and more particularly to a regional search processing method and device, electronic equipment and storage medium. BACKGROUND

[0002] Regional search planning refers to planning a search path in a certain region in order to search for a specified target. Regional search planning can be applied in large complex regions such as unmanned areas, the sea, deep mountains and forests, cities, etc. for personnel search and rescue, target tracking, border control, etc. to improve search efficiency.

[0003] The existing regional search method can realize the planning path of regional search based on a surface coverage algorithm. The surface coverage algorithm mainly realizes full coverage of the search region through a specific mode of search path, such as raster, four-square spiral, Zamboni, etc. This method can be well applied to search for static search targets. SUMMARY

[0004] The present disclosure provides a regional search processing method and device, electronic equipment and storage medium.

[0005] According to an aspect of the present disclosure, a regional search processing method is provided, comprising:

[0006] determining a current position of a current search subject in a search region;

[0007] determining a neighboring position of the current position in the search region;

[0008] obtaining search feature information of the current position and search feature information of the neighboring position;

[0009] planning next search information of the current search subject in the search region for a target object based on the search feature information of the current position and the search feature information of the neighboring position.

[0010] According to another aspect of the present disclosure, a regional search processing device is provided, comprising:

[0011] a determination module configured to determine a current position of a current search subject in a search region;

[0012] The determination module is configured to determine a neighboring position of the current position in the search region;

[0013] an obtaining module configured to obtain search feature information of the current position and search feature information of the neighboring position;

[0014] A planning module is configured to plan next search information of the current search subject in the search area based on the search feature information of the current position and the search feature information of the adjacent position.

[0015] According to still another aspect of the present disclosure, an electronic device is provided, comprising:

[0016] at least one processor; and

[0017] a memory in communication with the at least one processor; wherein

[0018] The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of the aspects and any possible implementation manner described above.

[0019] According to still another aspect of the present disclosure, a non-transitory computer readable storage medium storing computer instructions is provided, the computer instructions being used to cause the computer to perform the method of the aspects and any possible implementation manner described above.

[0020] According to still another aspect of the present disclosure, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the method of the aspects and any possible implementation manner described above.

[0021] According to the technology of the present disclosure, the efficiency of the area search can be effectively improved.

[0022] It should be understood that the content described in this part is not intended to identify key or important features of the embodiments of the present disclosure, nor to limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0023] The accompanying drawings are used to better understand the present scheme, and do not limit the present disclosure. Among them:

[0024] Figure 1 is a schematic diagram according to the first embodiment of the present disclosure;

[0025] Figure 2 is a schematic diagram according to the second embodiment of the present disclosure;

[0026] Figure 3 is a search area schematic diagram provided by the present disclosure;

[0027] Figure 4 is a working principle diagram of the search strategy model of the present disclosure;

[0028] Figure 5is a schematic diagram according to a third embodiment of the present disclosure;

[0029] Figure 6 is a schematic diagram according to a fourth embodiment of the present disclosure;

[0030] Figure 7 is a block diagram of an electronic device for implementing the method of the embodiments of the present disclosure. DETAILED DESCRIPTION

[0031] Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, which include various details of the embodiments of the present disclosure to assist in understanding, and should be considered as merely exemplary. Thus, those skilled in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, for the sake of brevity and clarity, descriptions of well-known functions and constructions are omitted from the following description.

[0032] Obviously, the described embodiments are part of the embodiments of the present disclosure, not all the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present disclosure.

[0033] It should be noted that the terminal device involved in the embodiments of the present disclosure can include, but is not limited to, a mobile phone, a personal digital assistant (PDA), a wireless handheld device, a tablet computer, and the like. The display device can include, but is not limited to, a personal computer, a television, and the like.

[0034] In addition, the term "and / or" in the present disclosure is only a description of the association relationship between the associated objects, which means that there can be three relationships, for example, A and / or B can represent the existence of A alone, the existence of A and B together, and the existence of B alone. In addition, the character " / " in this paper generally represents an "or" relationship between the associated objects before and after it.

[0035] The existing area search method is only applicable to searching for static search targets, and if the search target is movable, the existing area search method cannot be well applied. Based on this, the present disclosure provides an area search processing method with stronger applicability.

[0036] Figure 1 is a schematic diagram according to a first embodiment of the present disclosure; as Figure 1 shown, the present embodiment provides an area search processing method, which can be applied to any area search processing device, and can specifically include the following steps:

[0037] S101, determine the current position of the current search subject in the search area;

[0038] S102, determine the adjacent position of the current position in the search area;

[0039] S103, obtain the search feature information of the current position and the search feature information of the adjacent position;

[0040] S104, based on the search feature information of the current position and the search feature information of the adjacent position, plan the next search information of the current search subject in the search area.

[0041] The execution subject of the area search processing method of the embodiment can be an electronic device similar to a terminal. Or it can also use a software integrated application, which is installed on a terminal device when used to realize area search processing.

[0042] The search area of the embodiment can be a search area with boundaries and surrounding a certain range. For example, the search area can be circular, fan-shaped, rectangular or any other irregular shape, which is not limited here.

[0043] The search subject of the embodiment can be a person, a drone, a vehicle, etc. In the embodiment, it is not limited.

[0044] When the search subject searches for the target object in the search area, it can be located at any position in the search area. When planning the next search information, the current position of the current search subject in the search area needs to be determined first, which can be located in the middle of the search area or at the boundary of the search area, which is not limited here. In addition, in order to effectively plan the next search information, the adjacent position of the search area also needs to be determined. And the search feature information of the current position and the search feature information of the adjacent position are obtained. Since the search feature information of the current position and the search feature information of the adjacent position can identify the properties of the corresponding position in the search, it can play a guiding or reference role for search planning. Therefore, the next search information of the current search subject in the search area can be further obtained based on the search feature information of the current position and the search feature information of the adjacent position.

[0045] The area search processing method of the embodiment can be applied to search for stationary or movable target objects. Moreover, it can be applied to the scenario where multiple search subjects search for the same search target object. By using the area search processing method of the embodiment, the next search information of each search subject can be planned, and through the planning of each search information, the dynamic search path planning in the entire search process can be realized.

[0046] In addition, the target object to be searched in the embodiment can be one, two or more. However, in the area search processing, all states of the target object are completely unknown, for example, whether the target object is moving or stationary is unknown. The area search method of the embodiment can realize area search processing for each target object.

[0047] The area search processing method of the embodiment plans the next search information of the current search subject in the search area by searching the feature information based on the current position and the search feature information of the adjacent position, and further realizes dynamic planning of the search information. Compared with the traditional search path planned statically before search, in the whole search process, each step of search can only obtain the next search information, and the next search information obtained fully refers to the search feature information of all positions around, which can effectively ensure the accuracy of the next search information, and further effectively improve the search efficiency of the area search. Moreover, the technical solution of the embodiment can be applied to search stationary or movable target objects, and has very strong practicability.

[0048] Figure 2 is a schematic view according to the second embodiment of the disclosure; as Figure 2 shown, the embodiment provides an area search processing method, which is based on the technical solution of the embodiment shown in Figure 1 and further discloses the technical solution of the disclosure in more detail. As Figure 2 shown, the area search processing method of the embodiment can specifically include the following steps:

[0049] S201, performing grid processing on the search area to obtain a grid search area;

[0050] Specifically, in order to improve the accuracy of the identification of each search position and adjacent position in the search area and improve the efficiency of the area search processing, in the embodiment, the 2D or 3D search area can be discretized into standardized grids, and the size of each grid should be smaller than the observation distance of the search subject to discover the target object.

[0051] S202, determining the identification of the current grid in which the current search subject is located in the grid search area;

[0052] That is, corresponding to step S101 of the embodiment shown in Figure 1 , the current grid in which the current search subject is located in the grid search area represents the current position of the current search subject.

[0053] S203, determining the identification of a plurality of adjacent grids around the current grid;

[0054] That is, corresponding to step S102 of the embodiment shown in Figure 1In step S102 of the illustrated embodiment, the plurality of adjacent grids around the current grid are the plurality of adjacent positions around the current position of the search subject.

[0055] In this embodiment, in the grid search area, there can be a plurality of adjacent grids around each grid. For example, for a grid located in the middle of the search area, there can be eight nearest neighbor grids, i.e., the upper, lower, left, right, upper left, lower left, upper right, and lower right grids. Alternatively, in actual applications, the nearest neighbor grids of the nearest neighbor grids can also be obtained as the adjacent grids according to requirements. For a grid located at the boundary of the search area, there can be fewer nearest neighbor grids. However, the nearest neighbor grids of the nearest neighbor grids can also be obtained as the adjacent grids.

[0056] In step S204, the search feature information of the current grid and the search feature information of each adjacent grid are obtained, and each search feature information includes at least one of the access times, the access time, the obstacle identification information, and the access information of other search subjects of the corresponding grid by the current search subject.

[0057] Figure 3 FIG. 1 is a schematic diagram of a search area provided by the present disclosure. As shown in the figure, a circular search area is taken as an example, and the search area can include an obstacle area shown by the black line in the figure. The obstacle area in the search area can be an area that cannot be reached by the target object, such as a mountain, a river, or the like. Alternatively, it can also be an area where the target object is known to be impossible to reside. The obstacle area can also be of any regular or irregular shape. Figure 3

[0058] If the obstacle area is identified in the search area, the target object is considered to be impossible to be located in the obstacle area when planning the next step of search information, so as to obtain more accurate next step of search information.

[0059] In combination with the above explanation of the obstacle area, the obstacle identification information in the search feature information of the current grid and the search feature information of the adjacent grid is used to identify whether the corresponding grid is an obstacle. It should be noted that if the obstacle is an area that cannot be reached by both the target object and the search subject, the access times of the search subject to the corresponding grid is 0. If the obstacle is an area that can be reached by both the target object and the search subject, but it has been determined that the target object is impossible to reside in the area during the search, the access times of the corresponding grid can not be 0. That is, the search subject can pass through the grid when searching for the target object.

[0060] The access information of other search subjects can include the access times and the access time of other search subjects to the current grid. Of course, in actual applications, if there is only one search subject, the related information of other search subjects is removed.

[0061] ​The more information content included in each search feature information, the more accurate the planned next step search information. Preferably, each search feature information includes the number of visits, visit time, obstacle identification information and other search subject visit information of the search subject in the corresponding grid.

[0062] The search feature information of the current grid and the search feature information of each adjacent grid directly affect the acquisition of the planned next step search information. For example, according to the obstacle identification information of the adjacent grid, it can be determined whether the adjacent grid can be used as a point on the search path of the next step search information. According to the number of visits and visit time of the current search subject of the adjacent grid, and the number of visits and visit time of other search subjects, it is determined whether the adjacent grid has been searched, and if so, the adjacent grid can be avoided as much as possible in the next search. If the target object is movable, the search path can pass through the same grid point multiple times. At this time, the number of visits and visit time of the current search subject of multiple adjacent grids, and the number of visits and visit time of other search subjects can be referred to, and the direction of the grid point with less visit number can be selected as much as possible in the next search, and so on.

[0063] S205, based on the search feature information of the current grid and the search feature information of each adjacent grid, a pre-trained search strategy model is used to plan the search direction and search speed of the next step search of the current search subject in the search area.

[0064] In this embodiment, the search direction and search speed of the next step search of the current search subject in the search area are planned simultaneously. In actual application, only the search direction of the next step search can also be planned.

[0065] Specifically, the search feature information of the current grid and the search feature information of each adjacent grid can be input into the search strategy model. The search strategy model can perform comprehensive analysis based on the input information, predict and output the search direction of the next step search. Optionally, the search speed of the next search can also be further predicted and output. Especially for movable target objects, the search direction of the next step search is also very useful for search.

[0066] Figure 4 is the working principle diagram of the search strategy model of the present disclosure. As shown in Figure 4 When the above feature information is input into the search strategy model, each feature information can be input as an option. As shown in Figure 4As shown, each grid on the left side represents the current grid and all adjacent grids, and the feature information in the upper right corner represents the feature information corresponding to the grid. For example, the obstacle identification information of the current grid and all adjacent grids can be used to construct a two-dimensional feature matrix. The access time of the current search agent of the current grid and all adjacent grids can be used to construct a two-dimensional feature matrix; the access frequency of the current search agent of the current grid and all adjacent grids can be used to construct a two-dimensional feature matrix; and the access information of other search agents of the current grid and all adjacent grids can be used to construct a two-dimensional feature matrix; and so on. All these two-dimensional feature matrices are input together into the search strategy model. Based on all the input feature information, the search strategy model predicts the next search direction and search speed, and outputs.

[0067] Since the next search direction is determined based on the adjacent grid, the next search direction predicted by the search strategy model can be determined based on the orientation between the current grid and the adjacent grid to which the next step is to be moved. In combination with the orientation relationship between each grid and adjacent grid in the grid search area, up, down, left, right, left up, left down, right up, and right down. Then in use, in combination with the natural direction, for example, if up, down, left, and right are respectively corresponding to the natural directions of north, south, west, and east, then the next search direction can be represented as north, south, west, east, or northeast, northwest, southeast, and southwest.

[0068] In addition, the area search processing method of the present embodiment can be applied to search for movable target objects, so the search speed is also very necessary. However, the search speed range of different types of search agents is completely different. Alternatively, when training the search strategy model, the speed of the corresponding type of search agent can be trained so that the search speed of the next search can be accurately predicted when predicting.

[0069] The search strategy module of the present embodiment can use, but is not limited to, linear regression models, tree models, ensemble models, or neural networks.

[0070] The search strategy module of the present embodiment can be pre-trained through supervised learning before use. The supervised training data set is constructed by the following rules: the training data including the feature information of the search agent position, the access frequency, the access time, the obstacle identification information, and the access information of other search agents is constructed by uniform distribution, for each data, the label of the search direction is the direction of the grid with the least access frequency in the current adjacent grid, and the search speed can be randomly given.

[0071] After the search strategy model is pre-trained, the search strategy model can be dynamically sampled and updated by using a reinforcement learning method. The reinforcement learning method includes, but is not limited to, REINFORCE, A2C, PPO, and the like.

[0072] The state design in the reinforcement learning can be: the current grid where the current search agent is located, the access times of the current search agent in the adjacent grids, the access time, the obstacle identification information, and the access information of other search agents.

[0073] The action design in the reinforcement learning can be: the discrete search direction and the search speed that should be adopted by the current search agent at the current position.

[0074] The reward design in the reinforcement learning is: if the target object is not found after the corresponding operation is performed according to the current action design, the current reward is a negative number, such as -1; if the target object is found after the corresponding operation is performed, the current reward is a positive number, such as 1000.

[0075] By using the above reinforcement learning design, the pre-trained search strategy model can be trained by using an actor-critic algorithm, so that the search strategy model after the reinforcement learning can accurately predict the next search information. In the reinforcement learning, a suitable search speed can be trained based on the type of the search agent.

[0076] The search strategy model of the embodiment can ensure that the algorithm quickly converges to a better result by using the pre-trained strategy, reduce the model training cost, and improve the training efficiency. Furthermore, the model can be further optimized by using the reinforcement learning, and the accuracy of the model can be improved.

[0077] In addition, in the above embodiment, the search strategy model is taken as an example to realize the acquisition of the next search information of the search agent in the search area. In other embodiments of the present disclosure, the next search information of the search agent in the search area can also be directly analyzed based on the search feature information of the current grid and the search feature information of each adjacent grid, and the influence of each feature information on the next search is comprehensively considered.

[0078] Optionally, in an embodiment of the present disclosure, before the current position of the current search agent in the search area is determined, the search feature information database of the search area can also be updated when the current search agent enters the current position.

[0079] That is, the search feature information of all positions of the current search area is stored in the search feature information library. For example, the search feature information library includes the number of visits of each search subject to each position, the visit time, and the obstacle identification information of each position. Each step of the search of the current search subject or other search subjects needs to update the corresponding features in the search feature information library. For example, the current search subject moves to the current position, and the number of visits and the visit time of the current position need to be updated.

[0080] In the scenario of the grid search area in the embodiment, before step S202, when it is detected that the current search subject enters the current grid, the number of visits of the current search subject to the current grid and the visit time in the search feature information library of the search area can be updated. In a similar manner, if there are multiple search subjects, each search subject needs to update the related information in the search feature information library of the search area at each step of the search, so as to improve the prediction accuracy of the next search information.

[0081] Optionally, in one embodiment of the present disclosure, after step S205, when the search direction and the search speed of the next search of the current search subject in the search area are obtained, it is considered that the next search will be performed according to the obtained next search information, and at this time, the search feature information library of the search area is directly updated.

[0082] It should be noted that after the search area is divided into grids, the obstacle identification information of each grid is determined based on the environment of the search area, and will not be updated subsequently.

[0083] Correspondingly, the search feature information of the current grid and the search feature information of each adjacent grid obtained in step S204 are obtained from the search feature information library of the search area.

[0084] The region search processing method of the embodiment can more accurately identify the current position and the adjacent position of the current search subject by performing grid processing on the search area and using grid identification to identify the current position and the adjacent position of the current search subject. More accurate search feature information can be obtained, and then more accurate search direction and search speed of the next search can be obtained, which can effectively improve the search efficiency of the region search.

[0085] The embodiment can realize dynamic planning of search information based on the search direction and the search speed of each step of the search. Compared with the traditional static planning of the search path before the search, the search efficiency of the region search can be further improved. Moreover, the technical solution of the embodiment can be applied to search for stationary or movable target objects, and has very strong practicality.

[0086] Figure 5 is a schematic diagram according to a third embodiment of the present disclosure; as Figure 5 shown, the embodiment provides a region search processing apparatus 500, comprising:

[0087] A determination module 501 is configured to determine a current position of a current search subject in a search region.

[0088] The determination module 501 is configured to determine a neighboring position of the current position in the search region.

[0089] An acquisition module 502 is configured to acquire search feature information of the current position and search feature information of the neighboring position.

[0090] A planning module 503 is configured to plan next search information of the current search subject in the search region based on the search feature information of the current position and the search feature information of the neighboring position.

[0091] The region search processing apparatus 500 of the embodiment realizes the implementation principle and technical effects of the region search processing by using the above modules, and the implementation is the same as that of the above related method embodiments. For details, refer to the description of the above related method embodiments, which will not be repeated here.

[0092] Figure 6 is a schematic diagram according to a fourth embodiment of the present disclosure; as Figure 6 shown, the embodiment provides a region search processing apparatus 600, comprising the same name and same function modules shown in the above Figure 5 : a determination module 601, an acquisition module 602, and a planning module 603.

[0093] Further, as Figure 6 shown, the region search processing apparatus 600 of the embodiment further comprises:

[0094] A processing module 604 is configured to perform grid processing on the search region to obtain a grid search region.

[0095] Further, the determination module 601 is configured to:

[0096] Determine the identity of the current grid in which the current search subject is located in the grid search region.

[0097] Further, the determination module 601 is configured to:

[0098] Determine the identity of a plurality of neighboring grids around the current grid.

[0099] Further, the acquisition module 602 is configured to:

[0100] Obtain search feature information of the current grid and search feature information of each adjacent grid, and each search feature information includes at least one of the following: the number of visits of the current search subject to the corresponding grid, the visit time, obstacle identification information, and visit information of other search subjects.

[0101] Further, the planning module 603 is configured to:

[0102] Based on the search feature information of the current position and the search feature information of the adjacent position, a pre-trained search strategy model is used to plan a search direction of the next search of the current search subject in the search area.

[0103] Further, the planning module 603 is further configured to:

[0104] Based on the search feature information of the current position and the search feature information of the adjacent position, a pre-trained search strategy model is used to plan a search speed of the next search of the current search subject in the search area.

[0105] Further, as Figure 6 indicated, the regional search processing apparatus 600 of the embodiment further includes:

[0106] The updating module 605 is configured to update the search feature information library of the search area when it is detected that the current search subject enters the current position.

[0107] The regional search processing apparatus 600 of the embodiment realizes the implementation principle and technical effect of the regional search processing by using the above modules, and the implementation is the same as that of the above related method embodiments. For details, refer to the description of the above related method embodiments, which will not be repeated here.

[0108] In the technical solution of the present disclosure, the acquisition, storage and application of user personal information comply with relevant laws and regulations and do not violate public order and good customs.

[0109] According to the embodiments of the present disclosure, the present disclosure further provides an electronic device, a readable storage medium and a computer program product.

[0110] Figure 7A schematic block diagram of an example electronic device 700 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0111] like Figure 7 As shown, device 700 includes a computing unit 701, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 702 or a computer program loaded from storage unit 708 into random access memory (RAM) 703. RAM 703 may also store various programs and data required for the operation of device 700. The computing unit 701, ROM 702, and RAM 703 are interconnected via bus 704. Input / output (I / O) interface 705 is also connected to bus 704.

[0112] Multiple components in device 700 are connected to I / O interface 705, including: input unit 706, such as keyboard, mouse, etc.; output unit 707, such as various types of monitors, speakers, etc.; storage unit 708, such as disk, optical disk, etc.; and communication unit 709, such as network card, modem, wireless transceiver, etc. Communication unit 709 allows device 700 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0113] The computing unit 701 can be various general and / or special purpose processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 701 performs various methods and processes described above, such as the above-described methods of the present disclosure. For example, in some embodiments, the above-described methods of the present disclosure can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 708. In some embodiments, part or all of the computer program can be loaded and / or installed onto the device 700 via the ROM 702 and / or the communication unit 709. When the computer program is loaded onto the RAM 703 and executed by the computing unit 701, one or more steps of the above-described methods of the present disclosure described above can be performed. Alternatively, in other embodiments, the computing unit 701 can be configured to perform the above-described methods of the present disclosure by any other suitable means, such as by means of firmware.

[0114] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a complex programmable logic device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0115] Program code for carrying out methods of the present disclosure can be written in any combination of one or more programming languages. The program code can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the program code, when executed by the processor or controller, produces a means for implementing the functions / acts specified in the flowcharts and / or block diagrams. The program code can be executed entirely on a machine, partially on a machine, partially on a machine and partially on a remote machine or entirely on a remote machine or server.

[0116] In the context of this disclosure, a machine-readable medium can be a tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include but is not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0117] To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0118] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0119] The computer system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0120] It should be understood that the various forms of flow shown above can be used to reorder, add, or remove steps. For example, the steps described in the present disclosure can be performed in parallel, in series, or in a different order, without limitation herein, so long as the desired results of the technology described in the present disclosure are achieved.

[0121] The specific implementation described above does not constitute a limitation on the protection scope of the present disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements, and improvements made within the spirit and principles of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A regional search processing method, comprising: determining a current position of a current search subject in a search region; determining adjacent positions of the current position in the search region; obtaining search feature information of the current position and search feature information of the adjacent positions; each of the search feature information comprises at least one of a visit number, a visit time, obstacle identification information and other search subject access information of the current search subject at a corresponding position; based on the search feature information of the current position and the search feature information of the adjacent positions, planning next search information of the current search subject in the search region for searching a target object; based on the search feature information of the current position and the search feature information of the adjacent positions, planning next search information of the current search subject in the search region for searching a target object, comprising: based on the search feature information of the current position and the search feature information of the adjacent positions, using a pre-trained search strategy model to plan a search direction of next search of the current search subject in the search region for searching the target object.

2. The method of claim 1, wherein, Before determining the current position of the current search subject in the search region, the method comprises: performing grid processing on the search region to obtain a grid search region.

3. The method of claim 2, wherein, Determining the current position of the current search subject in the search region comprises: determining an identifier of a current grid in which the current search subject is located in the grid search region.

4. The method of claim 3, wherein, Determining the adjacent positions of the current position in the search region comprises: determining identifiers of a plurality of adjacent grids around the current grid.

5. The method of claim 1, wherein, Based on the search feature information of the current position and the search feature information of the adjacent positions, planning next search information of the current search subject in the search region for searching a target object, further comprises: based on the search feature information of the current position and the search feature information of the adjacent positions, using a pre-trained search strategy model to plan a search speed of next search of the current search subject in the search region for searching the target object.

6. The method of any one of claims 1-5, wherein, Before determining the current position of the current search subject in the search region, the method further comprises: updating a search feature information library of the search region when detecting that the current search subject enters the current position.

7. A regional search processing apparatus, comprising: a determination module configured to determine a current position of a current search subject in a search region; the determination module is configured to determine adjacent positions of the current position in the search region; an acquisition module configured to obtain search feature information of the current position and search feature information of the adjacent positions; each of the search feature information comprises at least one of a visit number, a visit time, obstacle identification information and other search subject access information of the current search subject at a corresponding position; a planning module configured to plan next search information of the current search subject in the search region for searching a target object based on the search feature information of the current position and the search feature information of the adjacent positions; The planning module is configured to plan a search direction of a next search of the current search subject searching for the target object in the search region based on the search feature information of the current position and the search feature information of the adjacent position, and by using a pre-trained search strategy model.

8. The apparatus of claim 7, wherein, The device comprises: A processing module configured to perform grid processing on the search region to obtain a grid search region.

9. The apparatus of claim 8, wherein, The determining module is configured to: Determine an identity of a current grid in which the current search subject is located in the grid search region.

10. The apparatus of claim 9, wherein, The determining module is configured to: Determine identities of a plurality of adjacent grids around the current grid.

11. The apparatus of claim 7, wherein, The planning module is further configured to: Plan a search speed of a next search of the current search subject searching for the target object in the search region based on the search feature information of the current position and the search feature information of the adjacent position, and by using a pre-trained search strategy model.

12. The apparatus of any of claims 7-11, wherein, The device further comprises: An updating module configured to update a search feature information library of the search region when detecting that the current search subject enters the current position.

13. An electronic device comprising: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-6.

14. A non-transitory computer readable storage medium having stored thereon computer instructions, wherein, The computer instructions are used to enable the computer to perform the method of any one of claims 1-6.

15. A computer program product comprising a computer program which, when executed by a processor, implements the method of any one of claims 1-6.

Images