An open robot interactive signal control system

Abstract

This invention discloses an open robot interaction signal control system, relating to the field of robot interaction control technology. Through a forward / backward analysis unit, all commands intercepted from the user within a preset time period T1 are collected. Based on the initiator and time of the command, several commands are divided into several command strings. Then, the commands in each command string are combined to form a command chain. Inertial command chains are then selected from these command chains. Duplicate inertial command chains are deleted, and the remaining inertial command chains are marked as verified command chains. Based on these verified command chains, the user's next possible command is determined. This application is simple, effective, and easy to use.

Description

Technical Field

[0001] This invention belongs to the field of robot interaction signal control technology, specifically an open robot interaction signal control system. Background Technology

[0002] Patent CN117389416A discloses an interactive control method, device, and robot for an intelligent robot, relating to the field of intelligent robot technology. This interactive control method includes: environmental detection, interaction detection, mode switching, and interaction response. This interactive control device is applicable to this interactive control method, and the robot is adapted to this interactive control method. The interactive control method, device, and robot of this application can ensure that the robot does not respond repeatedly in the service area, thereby improving the user experience of robot interaction. Simultaneously, through the design of interaction detection, the interaction purpose can be clearly defined, avoiding erroneous responses when the user does not need interaction, and the clear execution of response mode switching improves the robot's intelligence level and enhances the efficiency and accuracy of interaction.

[0003] However, for the interactive control of open robots, there is a lack of a method that can generate instruction control recommendations based on user habits, and for some complex instruction sets, there may be errors during operation. Therefore, a solution is provided. Summary of the Invention

[0004] This invention aims to solve at least one of the technical problems existing in the prior art;

[0005] Therefore, this invention proposes an open robot interaction signal control system, comprising:

[0006] The incoming and outgoing analysis unit is used to collect all the commands intercepted from the user within the preset time period T1, and divide the commands into several command strings according to the initiator and the time of issuance.

[0007] Then, for each instruction string, starting with two selected instructions, the corresponding number of adjacent instructions are combined to form an instruction chain. Then, based on the total number of times the instruction chain appears in each instruction string and the number of instruction strings containing the instruction chain, the performance value of the instruction chain is determined, and the inertial instruction chain is selected based on the performance value.

[0008] Then the number of selected instructions is incremented by one each time. Each time this number is updated, the instruction bundles are recombined, and inertial instruction bundles are selected from the instruction bundles in the same way.

[0009] Several inertial command bundles are filtered, and duplicate inertial command bundles are deleted. The remaining inertial command bundles after deletion are marked as approved command bundles.

[0010] Furthermore, all instructions from the user within a preset time period T1 are intercepted through the signal interception unit. The signal interception unit is used to intercept all interaction signals between the user and the robot. The interaction signals include the instructions that drive the robot to react and their corresponding initiators.

[0011] The signal interception unit is used to transmit interactive signals to the forward and backward analysis unit.

[0012] Furthermore, the specific method by which the signal interception unit obtains the instruction string is as follows:

[0013] Get any initiator and get all the instructions issued by them within the last T1 time period, where T1 is a preset time value;

[0014] Sort all instructions in chronological order. Select the first instruction. If the initiator initiates a second instruction within time T2, combine the two instructions into one instruction string. If a next instruction appears within time T2 after the last instruction in the instruction string, include that instruction in the instruction string as well.

[0015] If no next instruction appears within time T2 after the last instruction of the instruction string, the next set of instruction strings will be automatically summarized.

[0016] Repeat the above instruction string summarization process to obtain several sets of instruction strings.

[0017] Furthermore, the specific method for filtering out inertial instruction sequences by combining two instructions in the instruction string is as follows:

[0018] First, select any instruction string. Combine two adjacent instructions from the instruction string. The combined instruction is marked as an instruction string. Then, obtain the total number of times all instruction strings appear and mark it as the appearance count. Next, obtain the number of instruction strings that contain the corresponding instruction string and mark it as the depth count.

[0019] The performance value of the instruction chain is calculated according to the formula: Performance value = Number of appearances + Number of in-depth explorations;

[0020] Obtain the performance values ​​of all instruction chains in the selected instruction string, and then mark the performance values ​​that exceed X1 as inertial instruction chains, where X1 is a preset value;

[0021] Then, the same process is performed on the remaining instruction strings to obtain the performance values ​​of the instruction bundles divided in the corresponding instruction strings. Based on the performance values, the inertial instruction bundles of the remaining instruction strings are determined.

[0022] Furthermore, the method for obtaining all inertial command linkages is as follows:

[0023] The number of commands combined from the command string is incremented by one, and then a new combination is performed. The combination is still in one command string and is in an adjacent position. Then the combined command string is processed in the same way as the command string in the first stage to obtain a new inertial command string. This step is repeated until no new inertial command string can be obtained.

[0024] Obtain all inertial command links.

[0025] Furthermore, the specific method for filtering several inertial command chains is as follows:

[0026] When any inertial command link is completely included by other inertial command links, the included inertial command links are deleted, and the remaining inertial command links are marked as approved command links.

[0027] Furthermore, the incoming and outgoing analysis unit is used to transmit the approved instruction set to the signal interaction library, which receives the approved instruction set transmitted by the incoming and outgoing analysis unit and automatically stores it.

[0028] Furthermore, it also includes:

[0029] The signal receiving unit is used to acquire real-time commands transmitted by the user to the robot and transmit these commands to the processor. The processor then uses the signal interaction library to perform response analysis. The specific method of response analysis is as follows:

[0030] Obtain real-time instructions;

[0031] The real-time command is matched with the approved command set in the signal interaction library to obtain the approved command set containing the real-time command. Then, the position of the real-time command in the approved command set is obtained. The correlation degree of the approved command set is determined according to the position number of the real-time command in the approved command set and the number of commands in the corresponding approved command set. The recommended command set is then determined based on the correlation degree.

[0032] The processor displays recommended instruction sets to the user. The user selects the recommended instruction set to be executed from the recommended instruction sets and marks it as the execution instruction set. If the recommended instruction set does not have the user's required selection during this process, the user can manually enter a new instruction. Based on the user's manually entered new instruction, the processor automatically analyzes the user's next instruction. The specific analysis method is to use the same analysis steps as the previous execution instruction set to obtain a new execution instruction set.

[0033] This process analyzes new commands entered by the user in the same way.

[0034] The system obtains the execution instruction set required by the user and executes it using the execution unit.

[0035] Furthermore, the recommended method for determining the instruction set is as follows:

[0036] The number of instructions in the approved instruction set containing real-time instructions is obtained and marked as the inclusion number. Then, the correlation degree of the approved instruction set is calculated using the formula:

[0037] Relevance = 0.64 * positional order number + 0.36 * number of inclusions;

[0038] The top three most relevant instruction sets are marked as recommended instruction sets.

[0039] Compared with the prior art, the beneficial effects of the present invention are:

[0040] This application uses a call analysis unit to collect all commands intercepted from the user within a preset time period T1. Based on the initiator and the time of issuance of the commands, several commands are divided into several command strings. Then, the commands in each command string are combined to form a command chain, and then the inertial command chain is selected from the command chain.

[0041] Several inertial command bundles are filtered, duplicate inertial command bundles are deleted, and the remaining inertial command bundles are marked as approved command bundles. The user's next possible command is determined based on the approved command bundles. This application is simple, effective, and easy to use. Attached Figure Description

[0042] Figure 1 This is a system block diagram of the present invention. Detailed Implementation

[0043] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0044] Please see Figure 1 This application provides an open robot interaction signal control system;

[0045] As an embodiment of this application, this embodiment specifically includes:

[0046] Signal capture unit, incoming and outgoing analysis unit, and signal interaction library;

[0047] The signal interception unit is used to intercept all interaction signals between the user and the robot and transmit all interaction signals to the analysis unit. The interaction signals include the instructions that drive the robot to react and their corresponding initiators.

[0048] The incoming and outgoing signal analysis unit is used to perform correlation analysis on all interactive signals. The specific method of correlation analysis is as follows:

[0049] First, obtain the instructions from all the interaction signals and then aggregate them. The specific aggregation method is as follows:

[0050] The system acquires the interaction signals between robots and reads out the instructions and their initiators.

[0051] First, obtain any initiator and all instructions issued by them within the last T1 time period. T1 is a preset time value, which can generally be half a year or a year.

[0052] Sort all instructions in chronological order. Select the first instruction. If the initiator initiates a second instruction within time T2, combine the two instructions into one instruction string. If a next instruction appears within time T2 after the last instruction in the instruction string, include that instruction in the instruction string as well. T2 is the preset time.

[0053] If no next instruction appears within time T2 after the last instruction of the instruction string, the next set of instruction strings will be automatically summarized.

[0054] Repeat the above instruction string summarization process to obtain several sets of instruction strings;

[0055] Then, we reproduced and analyzed all the instruction strings. The specific method of reproduction and analysis is as follows:

[0056] First, select any instruction string. Combine two adjacent instructions from the instruction string. The combined instruction is marked as an instruction string. Then, obtain the total number of times all instruction strings appear and mark it as the appearance count. Next, obtain the number of instruction strings that contain the corresponding instruction string and mark it as the depth count.

[0057] The performance value of the instruction chain is calculated according to the formula: Performance value = Number of appearances + Number of in-depth explorations;

[0058] Obtain the performance values ​​of all instruction chains in the selected instruction string, and then mark those with performance values ​​exceeding X1 as inertial instruction chains; X1 is a preset value;

[0059] Then the same process is performed on the remaining instruction strings to obtain the performance value of the instruction bundles divided in the corresponding instruction strings. Based on the performance value, the inertial instruction bundles of the remaining instruction strings are determined.

[0060] Tag the above inertial command couplers with the first-stage label to obtain all inertial command couplers of the first stage;

[0061] Then, select any instruction string, combine three adjacent instructions from the instruction string, and mark it as instruction string 2. Then, in the same way as the instruction strings, calculate the performance value of all instruction string 2, and mark the performance value that exceeds X1 as inertial instruction string.

[0062] Then, the same process is applied to the remaining instruction strings to obtain all the inertial instruction strings for the second stage.

[0063] Then increment the number of commands combined in the command string by one, and then perform a new combination. The combination is still in one command string and is in an adjacent position. Then process the combined command string in the same way as the command string in the first stage to obtain a new inertial command string. Then repeat this step until no new inertial command string can be obtained.

[0064] All inertial command couplers are obtained, and then the inertial command couplers are simplified. The specific simplification process is as follows:

[0065] First, obtain all inertial command bundles. Then, sort them in descending order of the number of commands in each inertial command bundle. After sorting, select the first inertial command bundle. If any inertial command bundles sorted after it contain all the commands in the first inertial command bundle, then delete the inertial command bundles sorted after it.

[0066] Then, select the second-ranked inertial command bundle from the remaining inertial command bundles in sequence, and process it in the same way as selecting the first inertial command bundle, deleting the inertial command bundles that are ranked later.

[0067] Then, the next inertial command bundle is selected in sequence and deleted, until all inertial command bundles are processed in the same way;

[0068] Mark the remaining inertial command bundles as approved command bundles;

[0069] The incoming and outgoing analysis unit is used to transmit the approved instruction set to the signal interaction library. The signal interaction library receives the approved instruction set transmitted by the incoming and outgoing analysis unit and automatically stores it.

[0070] As a second embodiment of this application, this embodiment is implemented based on the first embodiment. The difference between the two embodiments is that this application further includes a processor, a signal receiving unit, and an execution unit.

[0071] The signal receiving unit is used to acquire the control commands, i.e., real-time commands, transmitted by the user to the robot, and transmits the real-time commands to the processor. The processor uses the signal interaction library to perform response analysis. The specific response analysis method is as follows:

[0072] Obtain real-time instructions;

[0073] The real-time instructions are matched with the approved instruction sets in the signal interaction library to obtain approved instruction sets containing real-time instructions. Then, the position of the real-time instructions within these approved instruction sets is determined. The number of instructions in each approved instruction set containing real-time instructions is counted according to their position within the approved instruction set, and this count is marked as the inclusion number. Finally, the correlation degree of the approved instruction sets is calculated using the following formula:

[0074] Relevance = 0.64 * positional order number + 0.36 * number of inclusions;

[0075] The top three most relevant instruction sets are marked as recommended instruction sets.

[0076] The processor displays recommended instruction sets to the user. The user selects the recommended instruction set to be executed from the recommended instruction sets and marks it as the execution instruction set. If the recommended instruction set does not have the user's required selection during this process, the user can manually enter a new instruction. Based on the user's manually entered new instruction, the processor automatically analyzes the user's next instruction. The specific analysis method is to use the same analysis steps as the previous execution instruction set to obtain a new execution instruction set.

[0077] This process analyzes new commands entered by the user in the same way.

[0078] It obtains the execution instructions needed by the user and executes them with the help of the execution unit.

[0079] The above embodiments are only used to illustrate the technical methods of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical methods of the present invention without departing from the spirit and scope of the technical methods of the present invention.

Claims

1. An open-loop robot interactive signal control system, characterized in that, include: The incoming and outgoing analysis unit is used to collect all the commands intercepted from the user within the preset time period T1, and divide the commands into several command strings according to the initiator and the time of issuance. Then, for each instruction string, starting with two selected instructions, the corresponding number of adjacent instructions are combined to form an instruction chain. Then, based on the total number of times the instruction chain appears in each instruction string and the number of instruction strings containing the instruction chain, the performance value of the instruction chain is determined, and the inertial instruction chain is selected based on the performance value. Then the number of selected instructions is incremented by one each time. Each time this number is updated, the instruction bundles are recombined, and inertial instruction bundles are selected from the instruction bundles in the same way. Several inertial command bundles are filtered, duplicate inertial command bundles are deleted, and the remaining inertial command bundles are marked as approved command bundles. The specific method for filtering inertial instruction sequences by combining two instructions in an instruction string is as follows: First, select any instruction string. Combine two adjacent instructions from the instruction string and mark the combined instruction string as an instruction string. Then, obtain the total number of times all instruction strings appear and mark it as the appearance count. Next, obtain the number of instruction strings that contain the corresponding instruction string and mark it as the depth count. The performance value of the instruction chain is calculated according to the formula: Performance value = Number of appearances + Number of in-depth explorations; Obtain the performance values ​​of all instruction chains in the selected instruction string, and then mark the performance values ​​that exceed X1 as inertial instruction chains, where X1 is a preset value; Then the same process is performed on the remaining instruction strings to obtain the performance value of the instruction bundles divided in the corresponding instruction strings. Based on the performance value, the inertial instruction bundles of the remaining instruction strings are determined. The specific method for filtering several inertial command chains is as follows: When any inertial command link is completely included by other inertial command links, the included inertial command links are deleted, and the remaining inertial command links are marked as approved command links.

2. The open robot interactive signal control system according to claim 1, characterized in that, All instructions from the user within a preset time period T1 are captured by the signal interception unit. The signal interception unit is used to capture all interaction signals between the user and the robot. The interaction signals include the instructions that drive the robot to react and their corresponding initiators. The signal interception unit is used to transmit interactive signals to the forward and backward analysis unit.

3. The open robot interactive signal control system according to claim 1, characterized in that, The specific method by which the signal interception unit obtains the instruction string is as follows: Get any initiator and get all the instructions issued by them within the last T1 time period, where T1 is a preset time value; Sort all instructions in chronological order. Select the first instruction. If the initiator of the second instruction initiates it within time T2, then combine the two instructions into one instruction string. If a next instruction appears within time T2 after the last instruction in the instruction string, then include that instruction in the instruction string as well. T2 is a preset value. If no next instruction appears within time T2 after the last instruction of the instruction string, the next set of instruction strings will be automatically summarized. Repeat the above instruction string summarization process to obtain several sets of instruction strings.

4. The open robot interactive signal control system according to claim 1, characterized in that, The method for obtaining all inertial command linkages is as follows: The number of commands combined from the command string is incremented by one, and then a new combination is performed. The combination is still in one command string and is in an adjacent position. Then the combined command string is processed in the same way as the command string in the first stage to obtain a new inertial command string. This step is repeated until no new inertial command string can be obtained. Obtain all inertial command links.

5. The open robot interactive signal control system according to claim 1, characterized in that, The incoming and outgoing analysis unit is used to transmit the approved command string to the signal interaction library. The signal interaction library receives the approved command string transmitted by the incoming and outgoing analysis unit and automatically stores it.

6. The open robot interactive signal control system according to claim 1, characterized in that, Also includes: The signal receiving unit is used to acquire real-time commands transmitted by the user to the robot and transmit these commands to the processor. The processor then uses the signal interaction library to perform response analysis. The specific method of response analysis is as follows: Obtain real-time instructions; The real-time command is matched with the approved command set in the signal interaction library to obtain the approved command set containing the real-time command. Then, the position of the real-time command in the approved command set is obtained. The correlation degree of the approved command set is determined according to the position number of the real-time command in the approved command set and the number of commands in the corresponding approved command set. The recommended command set is then determined based on the correlation degree. The processor displays recommended instruction sets to the user. The user selects the recommended instruction set to be executed from the recommended instruction sets and marks it as the execution instruction set. If the recommended instruction set does not have the user's required selection during this process, the user can manually enter a new instruction. Based on the user's manually entered new instruction, the processor automatically analyzes the user's next instruction. The specific analysis method is to use the same analysis steps as the previous execution instruction set to obtain a new execution instruction set. This process analyzes new commands entered by the user in the same way. The system obtains the execution instruction set required by the user and executes it using the execution unit.

7. An open robot interactive signal control system according to claim 6, characterized in that, The recommended method for determining the instruction set is as follows: The number of instructions in the approved instruction set containing real-time instructions is obtained and marked as the inclusion number. Then, the correlation degree of the approved instruction set is calculated using the formula: Relevance = 0.64 * positional order number + 0.36 * number of inclusions; The top three most relevant instruction sets are marked as recommended instruction sets.

Images