Stage equipment control method, system, equipment and medium

Abstract

The invention discloses a stage equipment control method and system, equipment and a medium, and the control method comprises the steps: obtaining a first keyword sequence of an equipment console, a current gesture image sequence and a candidate keyword sequence corresponding to the current gesture image sequence; the first keyword sequence comprises a plurality of target keywords corresponding to a previous gesture image sequence; performing gesture reasoning recognition on the current gesture image sequence to obtain gesture identification information of the current gesture image sequence; performing keyword mapping screening on the candidate keyword sequence according to the gesture identification information to obtain a target keyword corresponding to the current gesture image sequence; according to the target keyword, adding and updating the first keyword sequence to obtain a second keyword sequence; and performing state control on the stage equipment through the equipment console according to the second keyword sequence. According to the control method, the application range of intelligent control over the stage equipment can be widened. The invention relates to the technical field of intelligent control.

Description

Technical Field

[0001] The present invention relates to the field of intelligent control technology, and in particular to a control method, system, equipment and medium for stage equipment. Background Art

[0002] With the popularization of stage equipment and the rapid development of human-computer interaction technology, gesture recognition, as a natural and intuitive interaction method, has been widely used in smart home, virtual display, equipment console and other fields.

[0003] At present, relevant technologies usually use a single gesture mapping single operation mode to realize intelligent control of stage equipment (such as stage lighting, stage microphones, stage speakers, etc.). This method can often only realize simple and unified instructions, such as turning on all lights, turning off all lights, all lights at low brightness, all lights at high brightness and other simple instructions. It is difficult to meet the scenarios such as equipment consoles that need to support multi-dimensional and complex operation instructions, and its scope of application is limited.

[0004] Therefore, the problems existing in related technologies still need to be solved and optimized urgently. Summary of the Invention

[0005] The purpose of the present invention is to solve one of the technical problems existing in the related art to at least a certain extent.

[0006] To this end, an object of embodiments of the present invention is to provide a control method, system, device, and medium for stage equipment, wherein the control method can improve the applicability of intelligent control of stage equipment.

[0007] In order to achieve the above technical objectives, the technical solutions adopted in the embodiments of the present application include:

[0008] In a first aspect, an embodiment of the present application provides a method for controlling stage equipment, comprising:

[0009] Acquire a first keyword sequence of the device console, a current gesture image sequence, and a candidate keyword sequence corresponding to the current gesture image sequence, wherein the first keyword sequence includes a plurality of target keywords corresponding to previous gesture image sequences;

[0010] Performing gesture inference and recognition on the current gesture image sequence to obtain gesture identification information of the current gesture image sequence;

[0011] Perform keyword mapping screening on the candidate keyword sequence according to the gesture identification information to obtain a target keyword corresponding to the current gesture image sequence;

[0012] Add and update the first keyword sequence according to the target keyword to obtain a second keyword sequence;

[0013] According to the second keyword sequence, the status of the stage equipment is controlled through the equipment console.

[0014] In addition, the method according to the above embodiment of the present application may also have the following additional technical features:

[0015] Furthermore, in one embodiment of the present application, obtaining a candidate keyword sequence corresponding to the current gesture image sequence includes:

[0016] Get the keyword association table;

[0017] Perform keyword extraction on the first keyword sequence to obtain an intermediate keyword, where the intermediate keyword is the last target keyword in the first keyword sequence;

[0018] Performing an associated keyword query on the keyword association table based on the intermediate keyword to obtain a plurality of candidate keywords;

[0019] The candidate keyword sequence is generated according to all the candidate keywords.

[0020] Furthermore, in one embodiment of the present application, performing gesture inference recognition on the current gesture image sequence to obtain gesture identification information of the current gesture image sequence includes:

[0021] Obtain the trained first gesture inference model;

[0022] The current gesture image sequence is input into the trained first gesture inference model for recognition to obtain gesture identification information of the current gesture image sequence.

[0023] Furthermore, in one embodiment of the present application, performing gesture inference recognition on the current gesture image sequence to obtain gesture identification information of the current gesture image sequence includes:

[0024] Acquire several trained second gesture inference models and a first identifier sequence corresponding to the first keyword sequence, where the first identifier sequence includes several first keyword identifiers, each of which corresponds to a target keyword in the first keyword sequence;

[0025] performing model screening on all the trained second gesture reasoning models according to the first identification sequence to obtain a third gesture reasoning model, wherein the third gesture reasoning model is used to represent the trained second gesture reasoning models corresponding to a target reasoning type, where the target reasoning type is the gesture reasoning type indicated by the first identification sequence;

[0026] The current gesture image sequence is input into the third gesture inference model to obtain gesture identification information of the current gesture image sequence.

[0027] Furthermore, in one embodiment of the present application, performing keyword mapping screening on the candidate keyword sequence according to the gesture identification information to obtain a target keyword corresponding to the current gesture image sequence includes:

[0028] Acquire a second identifier sequence corresponding to the candidate keyword sequence, wherein the second identifier sequence includes a plurality of second keyword identifiers, each of which corresponds to a candidate keyword in the candidate keyword sequence;

[0029] Performing identifier matching on the second identifier sequence according to the gesture identifier information to obtain a third keyword identifier, where the third keyword identifier is used to represent the second keyword identifier that successfully matches the gesture identifier information;

[0030] According to the third keyword identifier, mapping extraction is performed on the candidate keyword sequence to obtain a target keyword corresponding to the current gesture image sequence.

[0031] Furthermore, in one embodiment of the present application, controlling the status of the stage equipment through the equipment console according to the second keyword sequence includes:

[0032] Get the first logical keyword;

[0033] performing a matching verification on the last target keyword in the second keyword sequence according to the first logical keyword to obtain a matching verification result;

[0034] If the match verification result is a successful match, the status of the stage equipment is controlled through the equipment console according to the second keyword sequence; or, if the match verification result is an unsuccessful match, the first keyword sequence is updated according to the second keyword sequence, and then the step of obtaining the first keyword sequence of the equipment console, the current gesture image sequence and the candidate keyword sequence corresponding to the current gesture image sequence is returned to execute.

[0035] Furthermore, in one embodiment of the present application, the method further includes:

[0036] performing keyword mapping screening on the candidate keyword sequence according to the gesture identification information to obtain a second logical keyword, where the second logical keyword is used to indicate that there is no candidate keyword corresponding to the gesture identification information in the candidate keyword sequence;

[0037] The state of the stage equipment is controlled according to the second logical keyword and the first keyword sequence.

[0038] In a second aspect, an embodiment of the present application provides a control system for stage equipment, including:

[0039] a first processing unit, configured to obtain a first keyword sequence of a device console, a current gesture image sequence, and a candidate keyword sequence corresponding to the current gesture image sequence, wherein the first keyword sequence includes a plurality of target keywords corresponding to previous gesture image sequences;

[0040] a second processing unit, configured to perform gesture inference and recognition on the current gesture image sequence to obtain gesture identification information of the current gesture image sequence;

[0041] a third processing unit, configured to perform keyword mapping screening on the candidate keyword sequence according to the gesture identification information to obtain a target keyword corresponding to the current gesture image sequence;

[0042] a fourth processing unit, configured to add and update the first keyword sequence according to the target keyword to obtain a second keyword sequence;

[0043] The fifth processing unit is configured to control the status of the stage equipment through the equipment console according to the second keyword sequence.

[0044] In a third aspect, an embodiment of the present application further provides an electronic device, including:

[0045] at least one processor;

[0046] at least one memory for storing at least one program;

[0047] When the at least one program is executed by the at least one processor, the at least one processor implements the above method.

[0048] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, which stores a program executable by a processor, and the program executable by the processor is used to implement the above method when executed by the processor.

[0049] The advantages and benefits of this application will be partially given in the following description, and partially become apparent from the following description, or learned through practice of this application:

[0050] The embodiment of the present application discloses a control method, system, device and medium for stage equipment, wherein the control method obtains a first keyword sequence of the device console, as well as a current gesture image sequence and a candidate keyword sequence corresponding to the current gesture image sequence, wherein the first keyword sequence includes several target keywords corresponding to the previous gesture image sequence; performs gesture inference recognition on the current gesture image sequence to obtain gesture identification information of the current gesture image sequence; performs keyword mapping screening on the candidate keyword sequence based on the gesture identification information to obtain the target keyword corresponding to the current gesture image sequence; adds and updates the first keyword sequence based on the target keyword to obtain a second keyword sequence; and controls the state of the stage equipment through the device console based on the second keyword sequence. The control method obtains the target keyword corresponding to the user's gesture image sequence in a cyclic manner, and controls the stage equipment based on all the obtained target keywords. It can conveniently generate multi-dimensional complex operation instructions for the stage equipment to execute, effectively improving the scope of application of stage equipment control. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following introduction is made to the drawings of the embodiments of the present application or the related technical solutions in the prior art. It should be understood that the drawings introduced below are only for the convenience of clearly expressing some embodiments of the technical solutions of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without any creative work.

[0052] Figure 1 A flow chart of a method for controlling stage equipment provided in an embodiment of the present application;

[0053] Figure 2 A schematic diagram of a flow chart of a second keyword sequence provided in an embodiment of the present application;

[0054] Figure 3 A schematic diagram of a control system for stage equipment provided in an embodiment of the present application;

[0055] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0056] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application and are not to be construed as limiting the present application. For the step numbers in the following embodiments, they are provided only for the convenience of explanation and are not intended to limit the order of the steps. The order of execution of the steps in the embodiments can be adaptively adjusted according to the understanding of those skilled in the art.

[0057] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application pertains. The terms used herein are for the purpose of describing the embodiments of this application only and are not intended to limit this application.

[0058] At present, related technologies usually use a single gesture to map a single operation to achieve intelligent control of stage equipment (such as stage lighting, microphones, and speakers). This method can often only implement simple and unified instructions, such as turning on all lights, turning off all lights, all lights at low brightness, all lights at high brightness, and other simple instructions. In the actual application of equipment consoles or stage equipment, a typical operation instruction "turn on light No. 1" contains three dimensions: operation type ("turn on"), object type ("light"), and object identifier ("No. 1"). If a single gesture is used to map a single operation, then similar operations such as "turn on light No. 2" and "turn on light No. 2" require independent gestures for mapping, and the number of single gestures is relatively limited. It cannot provide a single gesture for each complex operation instruction, cannot meet the needs of multi-dimensional and refined control, and has a limited scope of application.

[0059] In addition, there are some related technologies that use a combination of "navigation interface + basic gestures" to achieve intelligent control of stage equipment. Specifically, this method provides users with a set of basic gestures (such as "up, down, left, right", "confirm", "cancel", etc.) through the equipment console. Users use navigation gestures to focus on specific controls in the user interface, and then perform operations through corresponding gestures. For example, for an interface that contains multiple attribute controls such as "on / off", "lights / other objects", and "numbers", the user must first use navigation gestures to focus on the "on / off" control and set its attribute value through gestures; then, repeat similar operations to locate and set the attribute values of the "lights / other objects" control and the "numbers" control in turn. This method requires users to navigate and gesture multiple times to complete a complex operation instruction. The operation process is cumbersome and inefficient, which greatly reduces the user experience.

[0060] It should be noted that the above-mentioned related technologies are only used to assist in understanding the technical solutions of this application and do not mean that they belong to the disclosed prior art.

[0061] In view of this, an embodiment of the present invention provides a control method, system, device and medium for stage equipment, wherein the control method obtains target keywords corresponding to the user's gesture image sequence in a cyclic manner, and controls the stage equipment based on all the obtained target keywords, which eliminates the need for users to frequently perform navigation operations. At the same time, it can also conveniently generate multi-dimensional complex operation instructions for stage equipment to execute, effectively improving the scope of application and efficiency of stage equipment control, and improving user experience.

[0062] Reference Figure 1 In an embodiment of the present application, a method for controlling stage equipment includes:

[0063] Step 110: Acquire a first keyword sequence of the device console, a current gesture image sequence, and a candidate keyword sequence corresponding to the current gesture image sequence, wherein the first keyword sequence includes several target keywords corresponding to previous gesture image sequences;

[0064] In an embodiment of the present application, the gesture image sequence can be an image sequence or video stream data about the user's gestures collected by the device console through a camera device; the device console is a device for controlling stage lights, microphones and / or speakers, which is used to control parameters such as the brightness, color temperature, light direction lights, and various parameters of the microphones and speakers.

[0065] It is understandable that if the current gesture image sequence is the first gesture image sequence provided by the user, the first keyword sequence of the device console may be a blank sequence, and the corresponding candidate keyword sequence may be a keyword pre-set in the device console.

[0066] Alternatively, if the current gesture image sequence is the second or later gesture image sequence provided by the user, the first keyword sequence of the device console may be the second keyword sequence in the previous cycle, that is, the second keyword sequence corresponding to the previous gesture image sequence of the current gesture image sequence, and the corresponding candidate keyword sequence is a set of candidate keywords that are optional for the current gesture image sequence under the influence of the first keyword sequence.

[0067] In some embodiments, obtaining a candidate keyword sequence corresponding to the current gesture image sequence includes:

[0068] Get the keyword association table;

[0069] Perform keyword extraction on the first keyword sequence to obtain an intermediate keyword, where the intermediate keyword is the last target keyword in the first keyword sequence;

[0070] Performing an associated keyword query on the keyword association table based on the intermediate keyword to obtain a plurality of candidate keywords;

[0071] The candidate keyword sequence is generated according to all the candidate keywords.

[0072] In an embodiment of the present application, the keyword association table records each target keyword and several candidate keywords under each target keyword. Specifically, for a certain loop round, after obtaining the first keyword sequence and the current gesture image sequence in the loop round, the last target keyword in the first keyword sequence in the loop round can be extracted and recorded as the intermediate keyword. Then, based on this intermediate keyword, several candidate keywords corresponding to the intermediate keyword are queried from the keyword association table, and all candidate keywords are integrated to construct a candidate keyword sequence, which is a sequence set of several candidate keywords.

[0073] Step 120: Perform gesture inference recognition on the current gesture image sequence to obtain gesture identification information of the current gesture image sequence;

[0074] In an embodiment of the present application, a neural network model (such as a convolutional neural network CNN, a recursive neural network RNN, etc.) can be used to infer and identify the user's gestures in the current gesture image sequence to obtain gesture identification information of the current gesture image sequence.

[0075] In some embodiments, performing gesture inference recognition on the current gesture image sequence to obtain gesture identification information of the current gesture image sequence includes:

[0076] Obtain the trained first gesture inference model;

[0077] The current gesture image sequence is input into the trained first gesture inference model for recognition to obtain gesture identification information of the current gesture image sequence.

[0078] In an embodiment of the present application, a first implementation method can pre-train a neural network model that can recognize all predefined gestures, which is recorded as a first gesture inference model, and the current gesture image sequence is input into the trained first gesture inference model for recognition. The first gesture inference model is used to identify whether the user gesture in the current gesture image sequence meets one of all predefined gestures, thereby obtaining the gesture identification information of the current gesture image sequence.

[0079] In some embodiments, performing gesture inference recognition on the current gesture image sequence to obtain gesture identification information of the current gesture image sequence includes:

[0080] Acquire several trained second gesture inference models and a first identifier sequence corresponding to the first keyword sequence, where the first identifier sequence includes several first keyword identifiers, each of which corresponds to a target keyword in the first keyword sequence;

[0081] performing model screening on all the trained second gesture reasoning models according to the first identification sequence to obtain a third gesture reasoning model, wherein the third gesture reasoning model is used to represent the trained second gesture reasoning models corresponding to a target reasoning type, where the target reasoning type is the gesture reasoning type indicated by the first identification sequence;

[0082] The current gesture image sequence is input into the third gesture inference model to obtain gesture identification information of the current gesture image sequence.

[0083] In an embodiment of the present application, in a second implementation mode, several neural network models can be pre-trained, and each trained neural network is recorded as a second gesture inference model. Each second gesture inference model is responsible for identifying gestures under a specific gesture inference type. The gesture inference type can specifically include a gesture inference type for controlling the on and off of a gesture recognition function, a gesture inference type for controlling the on and off of a device, a gesture inference type for selecting an operation object (such as a lamp, a microphone, a speaker), a gesture inference type for selecting an operation attribute (such as brightness, color, volume), a gesture inference type for setting an attribute value (such as brightness percentage, color number, volume percentage), etc. The first identification sequence is a sequence set of first keyword identifications corresponding to each target keyword in the first keyword sequence. The first keyword identification can specifically be a gesture ID corresponding to the target keyword.

[0084] It can be understood that for any loop round, after obtaining the first identification sequence under the loop round, the corresponding target reasoning type can be determined based on the first identification sequence and / or the second identification sequence corresponding to the candidate keyword sequence; then all trained second gesture inference models are screened based on the target reasoning type to obtain a second gesture inference model responsible for identifying gestures under the target reasoning type, recorded as the third gesture inference model; then the current gesture image sequence is input into the third gesture inference model for recognition, and the third gesture inference model is used to identify whether the user gesture in the current gesture image sequence meets one of all gestures under the target reasoning type, so as to obtain the gesture identification information of the current gesture image sequence, which can specifically be the gesture ID of the user gesture output by the third gesture inference model.

[0085] Step 130: Perform keyword mapping screening on the candidate keyword sequence according to the gesture identification information to obtain a target keyword corresponding to the current gesture image sequence;

[0086] In the embodiment of the present application, for any loop round, a target keyword corresponding to the user gesture in the current gesture image sequence may be determined from the candidate keyword sequence based on the gesture identification information of the user gesture in the current gesture image sequence.

[0087] In some embodiments, performing keyword mapping screening on the candidate keyword sequence according to the gesture identification information to obtain a target keyword corresponding to the current gesture image sequence includes:

[0088] Acquire a second identifier sequence corresponding to the candidate keyword sequence, wherein the second identifier sequence includes a plurality of second keyword identifiers, each of which corresponds to a candidate keyword in the candidate keyword sequence;

[0089] Performing identifier matching on the second identifier sequence according to the gesture identifier information to obtain a third keyword identifier, where the third keyword identifier is used to represent the second keyword identifier that successfully matches the gesture identifier information;

[0090] According to the third keyword identifier, mapping extraction is performed on the candidate keyword sequence to obtain a target keyword corresponding to the current gesture image sequence.

[0091] In the embodiment of the present application, the second identification sequence and the aforementioned first identification sequence type can be simply derived by analogy. Identification matching can be based on the gesture ID in the gesture identification information, and matched with the second keyword identification of each candidate keyword. When there is a candidate keyword whose second keyword identification is the same as the gesture ID in the gesture identification information, the second keyword identification that successfully matches the gesture identification information can be determined as the third keyword identification, and based on the mapping relationship between the keyword identification and the candidate keyword, the target keyword corresponding to the user gesture in the current gesture image sequence is determined according to the third keyword identification.

[0092] Step 140: Add and update the first keyword sequence according to the target keyword to obtain a second keyword sequence;

[0093] In an embodiment of the present application, after obtaining the target keyword of the current gesture image sequence, the target keyword of the current gesture image sequence can be added to the first keyword sequence. Specifically, the target keyword of the current gesture image sequence can be used as the last sequence element of the first keyword sequence to obtain the second keyword sequence.

[0094] Step 150: Control the status of stage equipment through the equipment console according to the second keyword sequence.

[0095] In an embodiment of the present application, after obtaining the second keyword sequence, the device console can adjust and control the working status of the stage equipment (such as stage lighting, microphone or speaker) indicated by the second keyword sequence based on all target keywords in the second keyword sequence.

[0096] In some embodiments, controlling the status of the stage equipment through the equipment console according to the second keyword sequence includes:

[0097] Get the first logical keyword;

[0098] performing a matching verification on the last target keyword in the second keyword sequence according to the first logical keyword to obtain a matching verification result;

[0099] If the match verification result is a successful match, the status of the stage equipment is controlled through the equipment console according to the second keyword sequence; or, if the match verification result is an unsuccessful match, the first keyword sequence is updated according to the second keyword sequence, and then the step of obtaining the first keyword sequence of the equipment console, the current gesture image sequence and the candidate keyword sequence corresponding to the current gesture image sequence is returned to execute.

[0100] In the embodiment of the present application, the first logical keyword is used as a logical keyword for exiting the loop. Specifically, for any loop round, a match can be performed to verify whether the first logical keyword is identical to the last target keyword in the second keyword sequence. If they are identical, a match verification result can be generated indicating a successful match, indicating that the complex operation instruction corresponding to the second keyword sequence is complete. The device console can then control the status of specific stage equipment based on the complex operation instruction corresponding to the second keyword sequence.

[0101] Alternatively, if they are not the same, a matching verification result indicating an unsuccessful match can be generated, which actually means that the complex operation instruction corresponding to the second keyword sequence is incomplete. At this time, the second keyword sequence of the current cycle can be updated to the first keyword sequence of the next cycle, and the process returns to step 110.

[0102] In some embodiments, the method further comprises:

[0103] performing keyword mapping screening on the candidate keyword sequence according to the gesture identification information to obtain a second logical keyword, where the second logical keyword is used to indicate that there is no candidate keyword corresponding to the gesture identification information in the candidate keyword sequence;

[0104] The state of the stage equipment is controlled according to the second logical keyword and the first keyword sequence.

[0105] In an embodiment of the present application, for step 120 of any loop round, if there is a candidate keyword corresponding to the gesture identification information in the candidate keyword sequence, the target keyword corresponding to the current gesture image sequence can be obtained; conversely, if there is no candidate keyword corresponding to the gesture identification information in the candidate keyword sequence, it means that the user's gesture sequence has been input, and a second logical keyword can be obtained at this time. The second logical keyword is similar to the aforementioned first logical keyword, and is also used as a logical keyword for exiting the loop.

[0106] It can be understood that after obtaining the second logical keyword, the equipment console can exit the loop based on the second logical keyword, and use the first keyword sequence corresponding to the loop round where the second logical keyword is located to determine the complex operation instructions corresponding to the first keyword sequence and perform status control on specific stage equipment.

[0107] Reference Figure 2 The technical solution of this application is described below using one of the specific embodiments.

[0108] Suppose the device console supports operations for three objects: "Light," "Microphone," and "Speaker." "Light" supports operations such as "On," "Off," "Brightness," and "Color," while brightness supports operations such as "0, 1, 2, 3, 4, 5, 6, 7, 8, 9, OK." "Microphone" supports operations such as "On," "Off," and "Recording Volume Adjustment." "Speaker" supports operations such as "On," "Off," and "Playback Volume Adjustment." The first logical keyword is "OK."

[0109] Enable gesture recognition in the device console ( Figure 2 (not shown) and the loop round is 1, the first keyword sequence is a blank sequence, the current gesture image sequence is the first gesture sequence provided by the user, and the candidate keyword sequence includes candidate keywords such as "open", "close", "light", "microphone", and "speaker". Each candidate keyword corresponds to a gesture ID (i.e., keyword identification, Figure 2 not shown).

[0110] The device console can determine the gesture inference model used when the loop round is 1 based on the second identification sequence corresponding to the candidate keyword sequence and / or the first identification sequence corresponding to the first keyword sequence, and recognize the user gesture in the current gesture image sequence based on the gesture inference model, so as to obtain the gesture ID of the user gesture in the first gesture image sequence (i.e., gesture identification information, Figure 2 Not shown); then, the gesture ID of the user gesture is matched with the gesture ID of each candidate keyword and the corresponding candidate keyword is determined as the target keyword, and then the target keyword (for example, "lamp") is added to the first keyword sequence to obtain a second keyword sequence, which is {lamp}.

[0111] After obtaining the second keyword sequence {light}, the second keyword sequence {light} when the loop round is 1 is determined as the first keyword sequence {light} when the loop round is 2, and the current gesture image sequence is the second gesture sequence provided by the user. The candidate keyword sequence when the loop round is 2 includes candidate keywords such as "open", "close", "brightness", and "color". Each candidate keyword corresponds to a gesture ID (i.e., keyword identifier, Figure 2 not shown).

[0112] The device console can determine the gesture inference model used when the loop round is 2 based on the second identification sequence corresponding to the candidate keyword sequence when the loop round is 2 and / or the first identification sequence corresponding to the first keyword sequence, and recognize the user gesture in the second gesture image sequence based on the gesture inference model, so as to obtain the gesture ID of the user gesture in the second gesture image (i.e., gesture identification information, Figure 2Not shown); then, the gesture ID of the user gesture is matched with the gesture ID of each candidate keyword and the corresponding candidate keyword is determined as the target keyword, and then the target keyword (for example, "brightness") is added to the first keyword sequence when the loop round is 2, and the second keyword sequence when the loop round is 2 is obtained. The second keyword sequence when the loop round is 2 is {light, brightness}.

[0113] The subsequent cycles are similar to those in the case of the aforementioned cycle 1 and / or cycle 2, and can be simply deduced by analogy. Figure 2 , when the number of cycles is 6 (i.e. Figure 2 260), at this time, the first keyword sequence when the loop round is 6 is {light, brightness, 1, 0, 0}, the current gesture image sequence is the sixth gesture image sequence provided by the user, and the keyword corresponding to the user gesture in the sixth gesture image sequence is "OK", the matching verification result of the determined target keyword "OK" and the first logical keyword is a successful match, and the loop can be exited at this time, and the brightness of the corresponding stage lamps can be controlled with the "light brightness 100" in the second keyword sequence when the loop round is 6.

[0114] It should be noted that, for ease of understanding, the above specific embodiment is merely a simplified example and does not provide a detailed description of the specific details of the lamp number, microphone, speaker, etc. In actual applications, when determining the target keyword "lamp," the target keyword corresponding to the number of "lamp" can be determined. The contents of the microphone and speaker are similar to those of the aforementioned object "lamp," and can be simply inferred by analogy.

[0115] It is worth mentioning that if the device console needs to support a large number of keywords, it can also add the keywords that need to be supported to the candidate keyword sequence when the loop round is 1 on the basis of supporting the three objects of "light", "microphone" and "speaker". For example, the candidate keyword sequence when the loop round is 1 can also include the candidate keyword "other". The candidate keyword "other" supports operations such as "setting interface", "brightness control interface" and "layout interface". The example of this application is for illustration only and does not limit this application.

[0116] In summary, the embodiment of the present application obtains a keyword sequence corresponding to the user's gesture sequence in a cyclic manner. Each keyword in the keyword sequence represents a dimension, and the combination of multiple dimensions can accurately identify complex control instructions, thereby realizing refined control of specific lamps, microphones, speakers, etc., which can effectively improve the scope of application and efficiency of stage equipment control, as well as improve user experience.

[0117] A control system for stage equipment according to an embodiment of the present application is described in detail below with reference to the accompanying drawings.

[0118] Reference Figure 3 , a control system for stage equipment proposed in an embodiment of the present application includes:

[0119] The first processing unit 101 is configured to obtain a first keyword sequence of a device console, a current gesture image sequence, and a candidate keyword sequence corresponding to the current gesture image sequence, wherein the first keyword sequence includes a plurality of target keywords corresponding to previous gesture image sequences;

[0120] The second processing unit 102 is configured to perform gesture inference and recognition on the current gesture image sequence to obtain gesture identification information of the current gesture image sequence;

[0121] The third processing unit 103 is configured to perform keyword mapping screening on the candidate keyword sequence according to the gesture identification information to obtain a target keyword corresponding to the current gesture image sequence;

[0122] The fourth processing unit 104 is configured to add and update the first keyword sequence according to the target keyword to obtain a second keyword sequence;

[0123] The fifth processing unit 105 is configured to control the status of the stage equipment through the equipment console according to the second keyword sequence.

[0124] It can be understood that the contents of the above method embodiments are all applicable to the present system embodiments, the functions specifically implemented by the present system embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0125] Reference Figure 4 , an embodiment of the present application further provides an electronic device, including:

[0126] at least one processor 201;

[0127] At least one memory 202, configured to store at least one program;

[0128] When the at least one program is executed by the at least one processor 201 , the at least one processor 201 implements the above method embodiment.

[0129] Similarly, it can be understood that the contents of the above method embodiments are applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0130] An embodiment of the present application further provides a computer-readable storage medium, in which a program executable by the processor 201 is stored. The program executable by the processor 201 is used to implement the above-mentioned method embodiment when executed by the processor 201.

[0131] Similarly, the contents of the above method embodiments are applicable to the computer-readable storage medium embodiments. The functions specifically implemented by the computer-readable storage medium embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0132] In some optional embodiments, the functions / operations mentioned in the block diagram may not occur in the order mentioned in the operation diagram. For example, depending on the functions / operations involved, the two boxes shown in succession may actually be executed substantially simultaneously or the boxes can sometimes be executed in reverse order. In addition, the embodiments presented and described in the flow chart of the present application are provided in an exemplary manner for the purpose of providing a more comprehensive understanding of the technology. The disclosed method is not limited to the operations and logic flows presented herein. Optional embodiments are contemplated in which the order of the various operations is changed and the sub-operations described as a part of a larger operation are performed independently.

[0133] In addition, although the present application is described in the context of functional modules, it should be understood that, unless otherwise stated, one or more of the functions and / or features may be integrated into a single physical device and / or software module, or one or more functions and / or features may be implemented in separate physical devices or software modules. It is also understood that a detailed discussion of the actual implementation of each module is not necessary for understanding the present application. More specifically, given the properties, functions, and internal relationships of the various functional modules in the devices disclosed herein, the actual implementation of the module will be understood within the routine skills of an engineer. Therefore, a person skilled in the art can implement the present application as set forth in the claims using ordinary techniques without undue experimentation. It is also understood that the specific concepts disclosed are merely illustrative and are not intended to limit the scope of the present application, which is determined by the full scope of the appended claims and their equivalents.

[0134] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the embodiment method of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0135] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0136] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.

[0137] It should be understood that various parts of the present application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used to implement: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0138] In the above description of this specification, reference to the terms "one embodiment / example," "another embodiment / example," or "certain embodiments / examples" means that the specific features, structures, materials, 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 representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in any appropriate manner in any one or more embodiments or examples.

[0139] Although the embodiments of the present application have been shown and described, those skilled in the art will appreciate that various changes, modifications, substitutions, and variations may be made to the embodiments without departing from the principles and intent of the present application, and that the scope of the present application is defined by the claims and their equivalents.

[0140] The above is a specific description of the preferred implementation of the present application, but the present application is not limited to the embodiments. Those skilled in the art may make various equivalent modifications or substitutions without violating the spirit of the present application, and these equivalent modifications or substitutions are all included in the scope defined by the claims of the present application.

Claims

1. A method for controlling stage equipment, characterized in that: include: Acquire a first keyword sequence of the device console, a current gesture image sequence, and a candidate keyword sequence corresponding to the current gesture image sequence, wherein the first keyword sequence includes a plurality of target keywords corresponding to previous gesture image sequences; Performing gesture inference and recognition on the current gesture image sequence to obtain gesture identification information of the current gesture image sequence; Perform keyword mapping screening on the candidate keyword sequence according to the gesture identification information to obtain a target keyword corresponding to the current gesture image sequence; Add and update the first keyword sequence according to the target keyword to obtain a second keyword sequence; According to the second keyword sequence, the status of the stage equipment is controlled through the equipment console.

2. The method according to claim 1, characterized in that The acquiring of a candidate keyword sequence corresponding to the current gesture image sequence includes: Get the keyword association table; Perform keyword extraction on the first keyword sequence to obtain an intermediate keyword, where the intermediate keyword is the last target keyword in the first keyword sequence; Performing an associated keyword query on the keyword association table based on the intermediate keyword to obtain a plurality of candidate keywords; The candidate keyword sequence is generated according to all the candidate keywords.

3. The method according to claim 1, characterized in that The performing gesture inference and recognition on the current gesture image sequence to obtain gesture identification information of the current gesture image sequence includes: Obtain the trained first gesture inference model; The current gesture image sequence is input into the trained first gesture inference model for recognition to obtain gesture identification information of the current gesture image sequence.

4. The method according to claim 1, wherein The performing gesture inference and recognition on the current gesture image sequence to obtain gesture identification information of the current gesture image sequence includes: Acquire several trained second gesture inference models and a first identifier sequence corresponding to the first keyword sequence, where the first identifier sequence includes several first keyword identifiers, each of which corresponds to a target keyword in the first keyword sequence; performing model screening on all the trained second gesture reasoning models according to the first identification sequence to obtain a third gesture reasoning model, wherein the third gesture reasoning model is used to represent the trained second gesture reasoning models corresponding to a target reasoning type, where the target reasoning type is the gesture reasoning type indicated by the first identification sequence; The current gesture image sequence is input into the third gesture inference model to obtain gesture identification information of the current gesture image sequence.

5. The method according to claim 1, wherein The step of performing keyword mapping screening on the candidate keyword sequence according to the gesture identification information to obtain a target keyword corresponding to the current gesture image sequence includes: Acquire a second identifier sequence corresponding to the candidate keyword sequence, wherein the second identifier sequence includes a plurality of second keyword identifiers, each of which corresponds to a candidate keyword in the candidate keyword sequence; Performing identifier matching on the second identifier sequence according to the gesture identifier information to obtain a third keyword identifier, where the third keyword identifier is used to represent the second keyword identifier that successfully matches the gesture identifier information; According to the third keyword identifier, mapping extraction is performed on the candidate keyword sequence to obtain a target keyword corresponding to the current gesture image sequence.

6. The method according to claim 1, characterized in that The step of controlling the status of the stage equipment through the equipment console according to the second keyword sequence includes: Get the first logical keyword; performing a matching verification on the last target keyword in the second keyword sequence according to the first logical keyword to obtain a matching verification result; If the match verification result is a successful match, the status of the stage equipment is controlled through the equipment console according to the second keyword sequence; or, if the match verification result is an unsuccessful match, the first keyword sequence is updated according to the second keyword sequence, and then the step of obtaining the first keyword sequence of the equipment console, the current gesture image sequence and the candidate keyword sequence corresponding to the current gesture image sequence is returned to execute.

7. The method according to any one of claims 1 to 6, characterized in that The method further comprises: performing keyword mapping screening on the candidate keyword sequence according to the gesture identification information to obtain a second logical keyword, where the second logical keyword is used to indicate that there is no candidate keyword corresponding to the gesture identification information in the candidate keyword sequence; The state of the stage equipment is controlled according to the second logical keyword and the first keyword sequence.

8. A control system for stage equipment, characterized in that: include: a first processing unit, configured to obtain a first keyword sequence of a device console, a current gesture image sequence, and a candidate keyword sequence corresponding to the current gesture image sequence, wherein the first keyword sequence includes a plurality of target keywords corresponding to previous gesture image sequences; a second processing unit, configured to perform gesture inference and recognition on the current gesture image sequence to obtain gesture identification information of the current gesture image sequence; a third processing unit, configured to perform keyword mapping screening on the candidate keyword sequence according to the gesture identification information to obtain a target keyword corresponding to the current gesture image sequence; a fourth processing unit, configured to add and update the first keyword sequence according to the target keyword to obtain a second keyword sequence; The fifth processing unit is configured to control the status of the stage equipment through the equipment console according to the second keyword sequence.

9. An electronic device, characterized in that: include: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a program executable by a processor, characterized in that: The program executable by the processor is used to implement the method according to any one of claims 1 to 7 when executed by the processor.

Images