Method and device for sensing changes in operating environment of process robot

Abstract

The present invention provides a method and device for sensing changes in the operating environment of a process robot, the method comprising: obtaining a first screenshot of the operating environment when the process robot was last started, and a second screenshot of the operating environment when the process robot is started this time; extracting multiple corner points of the first screenshot and multiple corner points of the second screenshot respectively; generating multiple groups of corner point pairs according to the multiple corner points of the first screenshot and the multiple corner points of the second screenshot, each corner point pair including a corner point of the first screenshot and a corner point of the second screenshot; judging changes in the operating environment of the process robot according to the multiple groups of corner point pairs. The present invention can obtain changes in the operating environment of the process robot at any time and improve the operating efficiency of the process robot.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a method and device for sensing changes in the operating environment of a process robot. Background Art

[0002] A process robot is a software robot, that is, a software tool that can automatically execute tasks according to certain pre-set rules.

[0003] In modern enterprises, due to operational management and security considerations, there are operations such as reimbursement personnel information processing and report generation. From the perspective of the enterprise, these tasks are highly repetitive. Using process robots to replace manual operations will reduce manual operations, liberate manpower, and reduce costs.

[0004] Although process robots can greatly improve work efficiency by replacing manual repetitive work, they are code generated based on rules and cannot automatically identify whether the interface has changed like humans. They just blindly follow the established rules or processes to obtain elements from the corresponding interface and perform a series of operations such as logging in, clicking, downloading, querying or filling in. One of the necessary conditions for completing these operations is that the process robots need to find these elements accurately and quickly in the entire interface according to their attributes or coordinate positions.

[0005] With the gradual improvement of the degree of electronicization, the speed of updating software or websites is gradually accelerating. However, for the sake of art, the interface of the software or website will often change significantly after the update, and the properties of some key elements may also change. This may cause some elements in the process to be unavailable, resulting in process failure. This failure is not a technical or business problem, but an environmental problem. However, in any case, once the process fails, it will greatly affect the success rate of the process. When technical personnel perform error analysis, they will not immediately think of the fact that the element cannot be found. They need to conduct step-by-step investigations to determine whether the environment has changed and caused the process failure.

[0006] To solve the above problems, business personnel currently log in to the software or website regularly to check whether there are any updates. If there are any updates, they will report them to the technical staff, who will then determine whether the elements have changed. If the elements have changed, they will modify the code, otherwise the process will run normally. However, this method will not only greatly reduce the operating efficiency of the process robot, but also greatly affect the user experience of business personnel. Summary of the invention

[0007] The embodiment of the present invention provides a method for sensing changes in the operating environment of a process robot, so as to obtain changes in the operating environment of the process robot at any time and improve the operating efficiency of the process robot. The method includes:

[0008] Get the first screenshot of the running environment when the process robot was started last time, and the second screenshot of the running environment when the process robot is started this time;

[0009] Extracting multiple corner points of the first screenshot and multiple corner points of the second screenshot respectively;

[0010] Generate multiple groups of corner point pairs according to multiple corner points of the first screenshot and multiple corner points of the second screenshot, each corner point pair includes a corner point of the first screenshot and a corner point of the second screenshot;

[0011] Based on multiple sets of corner point pairs, the changes in the operating environment of the process robot are determined.

[0012] The embodiment of the present invention provides a device for sensing changes in the operating environment of a process robot, which is used to obtain changes in the operating environment of the process robot at any time and improve the operating efficiency of the process robot. The device includes:

[0013] The screenshot acquisition module is used to obtain the first screenshot of the running environment when the process robot was started last time, and the second screenshot of the running environment when the process robot is started this time;

[0014] A corner point extraction module, used to extract multiple corner points of the first screenshot and multiple corner points of the second screenshot respectively;

[0015] A corner point pair generating module, used to generate multiple groups of corner point pairs according to multiple corner points of the first screenshot and multiple corner points of the second screenshot, each corner point pair includes a corner point of the first screenshot and a corner point of the second screenshot;

[0016] The judgment module is used to judge the changes in the operating environment of the process robot based on multiple sets of corner point pairs.

[0017] An embodiment of the present invention further proposes a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned method for sensing operating environment changes of the process robot when executing the computer program.

[0018] An embodiment of the present invention further proposes a computer-readable storage medium, which stores a computer program for executing the above-mentioned method for sensing changes in the operating environment of the process robot.

[0019] In an embodiment of the present invention, a first screenshot of the operating environment when the process robot was last started and a second screenshot of the operating environment when the process robot is started this time are obtained; multiple corner points of the first screenshot and multiple corner points of the second screenshot are extracted respectively; multiple groups of corner point pairs are generated based on the multiple corner points of the first screenshot and the multiple corner points of the second screenshot, each corner point pair includes a corner point of the first screenshot and a corner point of the second screenshot; based on the multiple groups of corner point pairs, the changes in the operating environment of the process robot are judged. In the above process, based on the first screenshot of the operating environment when the process robot was last started and the second screenshot of the operating environment when the process robot is started this time, the changes in the operating environment of the process robot are automatically judged without the need for the technician to judge by himself, so that the changes in the operating environment of the process robot can be obtained at any time, which greatly improves the operating efficiency of the process robot. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0021] Figure 1 It is a flow chart of a method for reading bit data of an electronic detonator in an embodiment of the present invention;

[0022] Figure 2 A detailed flow chart of a method for sensing changes in the operating environment of a process robot according to an embodiment of the present invention;

[0023] Figure 3 Schematic diagram of a device for sensing changes in the operating environment of a process robot according to an embodiment of the present invention;

[0024] Figure 4 Schematic diagram of a computer device in an embodiment of the present invention. DETAILED DESCRIPTION

[0025] To make the purpose, technical solution and advantages of the embodiments of the present invention more clear, the embodiments of the present invention are further described in detail below in conjunction with the accompanying drawings. Here, the exemplary embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0026] In the description of this specification, the terms "include", "including", "have", "contain", etc. are all open terms, which mean including but not limited to. The descriptions with reference to the terms "one embodiment", "a specific embodiment", "some embodiments", "for example", etc. mean that the specific features, structures or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures or characteristics described may be combined in a suitable manner in any one or more embodiments or examples. The order of steps involved in each embodiment is used to schematically illustrate the implementation of the present application, and the order of steps is not limited and can be appropriately adjusted as needed.

[0027] Figure 1 FIG. 1 is a flow chart of a method for reading bit data of an electronic detonator according to an embodiment of the present invention. Figure 1 As shown, the method includes:

[0028] Step 101, obtaining a first screenshot of the operating environment when the process robot was started last time, and a second screenshot of the operating environment when the process robot is started this time;

[0029] Step 102, extracting multiple corner points of the first screenshot and multiple corner points of the second screenshot respectively;

[0030] Step 103, generating a plurality of groups of corner point pairs according to the plurality of corner points of the first screenshot and the plurality of corner points of the second screenshot, each corner point pair including a corner point of the first screenshot and a corner point of the second screenshot;

[0031] Step 104 , judging the change of the operating environment of the process robot according to the multiple groups of corner point pairs.

[0032] In an embodiment of the present invention, based on the first screenshot of the operating environment when the process robot was started last time and the second screenshot of the operating environment when the process robot is started this time, the changes in the operating environment of the process robot are automatically judged without the need for technicians to make their own judgments, thereby obtaining changes in the operating environment of the process robot at any time, greatly improving the operating efficiency of the process robot.

[0033] In specific implementation, each time the process robot starts a process, a screenshot of the operating environment when the process robot is started this time is obtained, that is, the second screenshot, and the screenshot of the operating environment when the process robot was started last time is the first screenshot.

[0034] Then, the process proceeds to step 102, where multiple corner points of the first screenshot and multiple corner points of the second screenshot are extracted respectively. In one embodiment, the process of extracting multiple corner points of the first screenshot and multiple corner points of the second screenshot respectively includes:

[0035] Calculate the Harris corner response function value of each pixel in the first screenshot and the second screenshot respectively;

[0036] For each pixel point, if the Harris corner point response function value of the pixel point is greater than a first threshold, the pixel point is determined to be a corner point.

[0037] Among them, the Harris corner response function was proposed by Harris in 1988. If the difference in contribution weights of different points in the window is considered, the corner response function can be written as:

[0038]

[0039] in, is a two-dimensional Gaussian window function. If the diversity of the offset direction is taken into account, the first-order Taylor approximation can be used to obtain the following formula for calculating the Harris corner response function value of each pixel.

[0040] CRF(u,v)=(A·BC 2 )-k(A+B) 2

[0041]

[0042]

[0043]

[0044] Among them, CRF(u,v) is the Harris corner response function value of the pixel point (u,v);

[0045] I x and I y are the first-order derivatives of the pixel point (u, v) in the horizontal and vertical directions, respectively.

[0046] is a two-dimensional Gaussian window function;

[0047] k is a constant.

[0048] In the above embodiments, k is generally set to 0.04 to 0.06.

[0049] It should be noted that the number of corner points obtained in the first screenshot may be different from the number of corner points obtained in the second screenshot.

[0050] In one embodiment, generating multiple groups of corner point pairs according to multiple corner points of the first screenshot and multiple corner points of the second screenshot includes:

[0051] For each corner point of the first screenshot, the normalized correlation coefficient between the corner point of the first screenshot and each corner point of the second screenshot is calculated respectively, and the corner point of the second screenshot corresponding to the maximum normalized correlation coefficient is determined from multiple normalized correlation coefficients to form a corner point pair with the corner point of the first screenshot.

[0052] In the above embodiment, the method of determining the corner point matching procedure by calculating the normalized correlation coefficient between the corner point of the first screenshot and each corner point of the second screenshot to form a corner point pair is called a normalized cross correlation (NCC) matching algorithm. In one embodiment, the following formula is used to calculate the normalized correlation coefficient between each corner point of the first screenshot and each corner point of the second screenshot:

[0053]

[0054] Among them, (a, b) are the offsets in the horizontal and vertical directions respectively;

[0055] R(a,b) is the normalized correlation coefficient;

[0056] x i+a,j+b is the pixel value of the corner point at (i+a,j+b) of the first screenshot, y ij is the pixel value of the corner point at (i, j) of the second screenshot;

[0057] N1 and N2 are constants.

[0058] In the above embodiment, the larger the R(a, b) value is, the higher the similarity between the two corner points is. Therefore, among the multiple normalized correlation coefficients calculated for a corner point of the first screenshot, the corner point of the second screenshot corresponding to the maximum normalized correlation coefficient forms a corner point pair with the corner point of the first screenshot.

[0059] In addition, in order to improve the accuracy of the present invention in sensing the change of the operating environment, it is necessary to delete the wrongly matched corner point pairs. In one embodiment, after generating multiple groups of corner point pairs, the method further includes:

[0060] For each set of corner point pairs, if the normalized correlation coefficient of the two corner points in the set of corner point pairs is less than the second threshold, the set of corner point pairs is eliminated.

[0061] In the above embodiment, the corner point pairs whose normalized correlation coefficients are smaller than the second threshold are determined to be mismatched corner point pairs.

[0062] In one embodiment, judging the change of the operating environment of the process robot according to the plurality of corner point pairs includes:

[0063] Calculate the pixel difference of each pair of corner points;

[0064] If the pixel difference of any set of corner point pairs is less than the third threshold, it is determined that the operating environment of the process robot has changed.

[0065] In the above embodiment, the pixel difference of each corner point pair can be calculated using the following formula:

[0066] change = abs(imt1-imt2)

[0067] Among them, change is the pixel difference of each set of corner point pairs, imt1 is the pixel value of the corner point in the first screenshot of each set of corner point pairs, and imt2 is the pixel value of the corner point in the second screenshot of each set of corner point pairs.

[0068] If there are five corner point pairs, five pixel differences can be obtained. If the pixel difference of any set of corner point pairs is less than the third threshold, it is determined that the operating environment of the process robot has changed. Afterwards, the difference image formed by the corner point pairs that are less than the third threshold can be sent to the technician to guide the technician to modify the code of the process robot. If the operating environment of the process robot has not changed, the process robot continues to execute the process. If the process reports an error, the error is not an environmental error. This not only reduces the unnecessary workload brought to business personnel or technical personnel by environmental changes, but also reduces the scope of error troubleshooting, relieves the pressure on business personnel to regularly check whether the software or website has been updated, and can greatly reduce the number of process failures caused by environmental problems. It can also reduce the scope of technical personnel's troubleshooting of erroneous processes and release manpower.

[0069] Based on the above embodiment, the present invention proposes the following embodiment to illustrate the detailed process of the method for sensing changes in the operating environment of a process robot: Figure 2 Detailed flow chart of the method for sensing operating environment changes of a process robot according to an embodiment of the present invention, such as Figure 2 As shown, including:

[0070] Step 201, obtaining a first screenshot of the operating environment when the process robot was started last time, and a second screenshot of the operating environment when the process robot is started this time;

[0071] Step 202, respectively calculating the Harris corner response function value of each pixel point in the first screenshot and the second screenshot;

[0072] Step 203, for each pixel point, if the Harris corner point response function value of the pixel point is greater than a first threshold, the pixel point is determined to be a corner point;

[0073] Step 204, for each corner point of the first screenshot, respectively calculate the normalized correlation coefficient between the corner point of the first screenshot and each corner point of the second screenshot, and determine from a plurality of normalized correlation coefficients that the corner point of the second screenshot corresponding to the maximum normalized correlation coefficient forms a corner point pair with the corner point of the first screenshot;

[0074] Step 205: for each corner point pair, if the normalized correlation coefficient of two corner points in the corner point pair is less than a second threshold, the corner point pair is eliminated;

[0075] Step 206, calculating the pixel difference of each set of corner point pairs;

[0076] Step 207: If the pixel difference of any set of corner point pairs is less than the third threshold, it is determined that the operating environment of the process robot has changed, and the technician is notified; otherwise, the process continues to be executed.

[0077] Of course, it is understandable that the above detailed process may have other variations, and the relevant variations should all fall within the protection scope of the present invention.

[0078] In summary, in the method proposed in the embodiment of the present invention, a first screenshot of the operating environment when the process robot was last started and a second screenshot of the operating environment when the process robot is started this time are obtained; multiple corner points of the first screenshot and multiple corner points of the second screenshot are extracted respectively; multiple groups of corner point pairs are generated based on the multiple corner points of the first screenshot and the multiple corner points of the second screenshot, each corner point pair includes a corner point of the first screenshot and a corner point of the second screenshot; based on the multiple groups of corner point pairs, the changes in the operating environment of the process robot are judged. In the above process, based on the first screenshot of the operating environment when the process robot was last started and the second screenshot of the operating environment when the process robot is started this time, the changes in the operating environment of the process robot are automatically judged without the need for the technician to judge by himself, so that the changes in the operating environment of the process robot can be obtained at any time, which greatly improves the operating efficiency of the process robot.

[0079] The embodiment of the present invention further proposes a device for sensing changes in the operating environment of a process robot, the principle of which is similar to the method for sensing changes in the operating environment of a process robot, and will not be described in detail here.

[0080] Figure 3 Schematic diagram of a device for sensing operating environment changes of a process robot according to an embodiment of the present invention, comprising:

[0081] The screenshot acquisition module 301 is used to acquire a first screenshot of the operating environment when the process robot was started last time, and a second screenshot of the operating environment when the process robot is started this time;

[0082] A corner point extraction module 302, used to extract multiple corner points of the first screenshot and multiple corner points of the second screenshot respectively;

[0083] A corner point pair generating module 303, configured to generate a plurality of corner point pairs according to a plurality of corner points of the first screenshot and a plurality of corner points of the second screenshot, each corner point pair including a corner point of the first screenshot and a corner point of the second screenshot;

[0084] The judgment module 304 is used to judge the change of the operating environment of the process robot according to multiple groups of corner point pairs.

[0085] In one embodiment, the corner point extraction module 302 is specifically used for:

[0086] Calculate the Harris corner response function value of each pixel in the first screenshot and the second screenshot respectively;

[0087] For each pixel point, if the Harris corner point response function value of the pixel point is greater than a first threshold, the pixel point is determined to be a corner point.

[0088] In one embodiment, the corner point extraction module 302 is specifically used for:

[0089] The Harris corner response function value of each pixel in the first screenshot and the second screenshot is calculated using the following formula:

[0090] CRF(u,v)=(A·BC 2 )-k(A+B) 2

[0091]

[0092]

[0093]

[0094] Among them, CRF(u,v) is the Harris corner response function value of the pixel point (u,v);

[0095] I x and I y are the first-order derivatives of the pixel point (u, v) in the horizontal and vertical directions, respectively.

[0096] is a two-dimensional Gaussian window function;

[0097] k is a constant.

[0098] In one embodiment, the corner point pair generating module 303 is specifically used for:

[0099] For each corner point of the first screenshot, the normalized correlation coefficient between the corner point of the first screenshot and each corner point of the second screenshot is calculated respectively, and the corner point of the second screenshot corresponding to the maximum normalized correlation coefficient is determined from multiple normalized correlation coefficients to form a corner point pair with the corner point of the first screenshot.

[0100] In one embodiment, the corner point pair generating module 303 is specifically used for:

[0101] The following formula is used to calculate the normalized correlation coefficient between each corner point of the first screenshot and each corner point of the second screenshot:

[0102]

[0103] Among them, (a, b) are the offsets in the horizontal and vertical directions respectively;

[0104] R(a,b) is the normalized correlation coefficient;

[0105] x i+a,j+b is the pixel value of the corner point at (i+a,j+b) of the first screenshot, y ij is the pixel value of the corner point at (i, j) of the second screenshot;

[0106] N1 and N2 are constants.

[0107] In one embodiment, the corner point pair generating module 303 is further used for:

[0108] For each set of corner point pairs, if the normalized correlation coefficient of the two corner points in the set of corner point pairs is less than the second threshold, the set of corner point pairs is eliminated.

[0109] In one embodiment, the determination module 304 is specifically used to:

[0110] Calculate the pixel difference of each pair of corner points;

[0111] If the pixel difference of any set of corner point pairs is less than the third threshold, it is determined that the operating environment of the process robot has changed.

[0112] In summary, in the device proposed in the embodiment of the present invention, a first screenshot of the operating environment when the process robot was last started and a second screenshot of the operating environment when the process robot is started this time are obtained; multiple corner points of the first screenshot and multiple corner points of the second screenshot are extracted respectively; multiple groups of corner point pairs are generated based on the multiple corner points of the first screenshot and the multiple corner points of the second screenshot, each corner point pair includes a corner point of the first screenshot and a corner point of the second screenshot; based on the multiple groups of corner point pairs, the changes in the operating environment of the process robot are judged. In the above process, based on the first screenshot of the operating environment when the process robot was last started and the second screenshot of the operating environment when the process robot is started this time, the changes in the operating environment of the process robot are automatically judged without the need for the technician to judge by himself, so that the changes in the operating environment of the process robot can be obtained at any time, which greatly improves the operating efficiency of the process robot.

[0113] An embodiment of the present application also provides a computer device, Figure 4 Schematic diagram of a computer device in an embodiment of the present invention. The computer device can implement all steps in the method for sensing changes in the operating environment of a process robot in the above embodiment. The electronic device specifically includes the following contents:

[0114] Processor (processor) 401, memory (memory) 402, communication interface (CommunicationsInterface) 403 and bus 404;

[0115] The processor 401, the memory 402, and the communication interface 403 communicate with each other through the bus 404; the communication interface 403 is used to realize information transmission between relevant devices such as the server-side device, the detection device, and the user-side device;

[0116] The processor 401 is used to call the computer program in the memory 402, and when the processor executes the computer program, all the steps in the method for sensing the operating environment change of the process robot in the above embodiment are implemented.

[0117] An embodiment of the present application also provides a computer-readable storage medium that can implement all steps of the method for perceiving changes in the operating environment of a process robot in the above-mentioned embodiment. A computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, all steps of the method for perceiving changes in the operating environment of a process robot in the above-mentioned embodiment are implemented.

[0118] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0119] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0120] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0121] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0122] The specific embodiments described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for sensing changes in the operating environment of a process robot, characterized in that: include: Get the first screenshot of the running environment when the process robot was started last time, and the second screenshot of the running environment when the process robot is started this time; Extracting multiple corner points of the first screenshot and multiple corner points of the second screenshot respectively; Generate multiple groups of corner point pairs according to multiple corner points of the first screenshot and multiple corner points of the second screenshot, each corner point pair includes a corner point of the first screenshot and a corner point of the second screenshot; Based on multiple sets of corner point pairs, the changes in the operating environment of the process robot are determined; After generating multiple groups of corner point pairs, the method further includes: for each group of corner point pairs, if the normalized correlation coefficient of two corner points in the group of corner point pairs is less than a second threshold, eliminating the group of corner point pairs; According to the plurality of corner point pairs, determining the change of the operating environment of the process robot includes: calculating the pixel difference of each corner point pair; if the pixel difference of any corner point pair is less than a third threshold, determining that the operating environment of the process robot has changed; If the operating environment of the process robot has not changed, the process robot continues to execute the process; Based on multiple corner points of the first screenshot and multiple corner points of the second screenshot, multiple groups of corner point pairs are generated, including: for each corner point of the first screenshot, respectively calculating the normalized correlation coefficient between the corner point of the first screenshot and each corner point of the second screenshot, and determining from the multiple normalized correlation coefficients that the corner point of the second screenshot corresponding to the maximum normalized correlation coefficient and the corner point of the first screenshot form a corner point pair.

2. The method for sensing changes in the operating environment of a process robot according to claim 1, characterized in that: Extracting multiple corner points of the first screenshot and multiple corner points of the second screenshot respectively includes: Calculate the Harris corner response function value of each pixel in the first screenshot and the second screenshot respectively; For each pixel point, if the Harris corner point response function value of the pixel point is greater than a first threshold, the pixel point is determined to be a corner point.

3. The method for sensing changes in the operating environment of a process robot according to claim 2, characterized in that: The Harris corner response function value of each pixel in the first screenshot and the second screenshot is calculated using the following formula: CRF(u,v)=(A·B-C 2 )-k(A+B) 2 Among them, CRF(u,v) is the Harris corner response function value of the pixel point (u,v); Ix and I y are the first-order derivatives of the pixel point (u, v) in the horizontal and vertical directions, respectively. is a two-dimensional Gaussian window function; k is a constant.

4. The method for sensing changes in the operating environment of a process robot according to claim 1, characterized in that: The following formula is used to calculate the normalized correlation coefficient between each corner point of the first screenshot and each corner point of the second screenshot: Among them, (a, b) are the offsets in the horizontal and vertical directions respectively; R(a,b) is the normalized correlation coefficient; x i+a,j+b is the pixel value of the corner point at (i+a,j+b) of the first screenshot, y ij is the pixel value of the corner point at (i, j) of the second screenshot; N1 and N2 are constants.

5. A device for sensing changes in the operating environment of a process robot, characterized in that: include: The screenshot acquisition module is used to obtain the first screenshot of the running environment when the process robot was started last time, and the second screenshot of the running environment when the process robot is started this time; A corner point extraction module, used to extract multiple corner points of the first screenshot and multiple corner points of the second screenshot respectively; A corner point pair generating module, used to generate multiple groups of corner point pairs according to multiple corner points of the first screenshot and multiple corner points of the second screenshot, each corner point pair includes a corner point of the first screenshot and a corner point of the second screenshot; A judgment module is used to judge the changes in the operating environment of the process robot based on multiple sets of corner point pairs; The corner point pair generation module is further used to: for each group of corner point pairs, if the normalized correlation coefficient of two corner points in the group of corner point pairs is less than a second threshold, remove the group of corner point pairs; The judgment module is specifically used to: calculate the pixel difference of each set of corner point pairs; if the pixel difference of any set of corner point pairs is less than a third threshold, determine that the operating environment of the process robot has changed; If the operating environment of the process robot has not changed, the process robot continues to execute the process; The corner point pair generation module is used to: for each corner point of the first screenshot, respectively calculate the normalized correlation coefficient between the corner point of the first screenshot and each corner point of the second screenshot, and determine from multiple normalized correlation coefficients that the corner point of the second screenshot corresponding to the maximum normalized correlation coefficient and the corner point of the first screenshot form a corner point pair.

6. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 4 is implemented.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program for executing the method according to any one of claims 1 to 4.

Images