Instruction execution method, instruction execution device, electronic equipment and readable storage medium

Abstract

The invention discloses an instruction execution method, an instruction execution device, electronic equipment and a readable storage medium, and the method comprises the steps: obtaining an operation instruction sent by each client for target content in a preset time period, the operation instruction being used for indicating the execution of related operation on the target content; in response to judgment that at least two first operation instructions are mutually exclusive, a first tendency degree corresponding to each first operation instruction is obtained, the multiple operation instructions comprise the first operation instructions, and the first tendency degrees are determined based on a tendency analysis model and user behavior data corresponding to a target frame picture of the target content; the target frame picture is a current frame picture; based on the first tendency degree corresponding to each first operation instruction, determining an execution sequence of each first operation instruction; the first instruction set is executed, the first operation instructions are executed in sequence according to the execution sequence, and the first instruction set is a difference set of the multiple operation instructions and at least two first operation instructions.

Description

Technical Field

[0001] The present application belongs to the field of computer technology, and in particular, relates to an instruction execution method, an instruction execution device, an electronic device, and a readable storage medium. Background Art

[0002] Multi-screen interaction refers to the mobile terminal sending multimedia content to the middle and high-end display for display via wireless network. However, in the related technology, multi-screen interaction is only applicable to one-to-one terminals, that is, one mobile terminal corresponds to one display terminal. When multiple mobile terminals operate the projection content at the same time, there is a situation of mutual exclusion of operations, which causes data conflicts. Summary of the invention

[0003] The embodiments of the present application provide an instruction execution method, an instruction execution device, an electronic device and a readable storage medium, which can solve the problem of mutual exclusion of multiple operations.

[0004] In a first aspect, an embodiment of the present application provides an instruction execution method, the method comprising: obtaining operation instructions sent by each client for target content within a preset time period, wherein the operation instructions are used to instruct the execution of related operations on the target content; in response to a judgment that at least two first operation instructions are mutually exclusive, obtaining a first tendency corresponding to each of the first operation instructions, wherein a plurality of the operation instructions include the first operation instruction, and the first tendency is determined based on a tendency analysis model and user behavior data corresponding to a target frame of the target content, and the target frame is a current frame; based on the first tendency corresponding to each of the first operation instructions, determining an execution order of each of the first operation instructions; executing a first instruction set, and executing the first operation instructions in sequence according to the execution order, wherein the first instruction set is a difference set between a plurality of the operation instructions and the at least two first operation instructions.

[0005] In a second aspect, an embodiment of the present application provides an instruction execution device, which includes: a first acquisition module, used to acquire operation instructions sent by each client for target content within a preset time period, wherein the operation instructions are used to instruct the execution of related operations on the target content; a second acquisition module, used to obtain a first tendency corresponding to each of the first operation instructions in response to a judgment that at least two first operation instructions are mutually exclusive, wherein a plurality of the operation instructions include the first operation instruction, and the first tendency is determined based on a tendency analysis model and user behavior data corresponding to a target frame of the target content, and the target frame is a current frame; a determination module, used to determine the execution order of each of the first operation instructions based on the first tendency corresponding to each of the first operation instructions; an execution module, used to execute a first instruction set, and execute the first operation instructions in sequence according to the execution order, wherein the first instruction set is a difference set between a plurality of the operation instructions and the at least two first operation instructions. In a third aspect, an embodiment of the present application provides an electronic device, which includes a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the method described in the first aspect.

[0006] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a program or instruction is stored, and when the program or instruction is executed by a processor, the steps of the method described in the first aspect are implemented.

[0007] In a fifth aspect, an embodiment of the present application provides a chip, comprising a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run a program or instruction to implement the method described in the first aspect.

[0008] In a sixth aspect, a computer program product is provided, the computer program product comprising at least one computer program, and when the computer program is loaded and executed by a processor, the method as described in the first aspect is implemented.

[0009] In an embodiment of the present application, an operation instruction sent by each client for the target content within a preset time period is obtained, wherein the operation instruction is used to instruct to perform a related operation on the target content, and then in response to a judgment that at least two first operation instructions are mutually exclusive, a first tendency corresponding to each first operation instruction is obtained, wherein the multiple operation instructions include a first operation instruction, the first tendency is determined based on a tendency analysis model and user behavior data corresponding to a target frame of the target content, the target frame is the current frame, and then based on the first tendency corresponding to each first operation instruction, the execution order of each first operation instruction is determined, and finally the first instruction set is executed, and in accordance with the execution order, Execute the first operation instructions in sequence, wherein the first instruction set is the difference set of multiple operation instructions and at least two first operation instructions, which solves the problem of multiple operations being mutually exclusive. By setting the execution order for mutually exclusive instructions, other faults such as server crash and flash back can be effectively avoided. At the same time, the mutually exclusive instructions are determined by first executing a simple logical judgment, and then the analysis model is called to perform a tendency analysis on the mutually exclusive instructions. This can effectively reduce the time investment in the calculation process of the complex model and shorten the response time of the operation instructions, thereby improving the interactive experience. In addition, using the tendency as the judgment parameter for setting the execution order of mutually exclusive instructions can ensure that the instructions most relevant to the current frame are executed first. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 It is a flowchart of an instruction execution method provided by an exemplary embodiment of the present application; Figure 2 is another flowchart of an instruction execution method provided by an exemplary embodiment of the present application; Figure 3 is a structural schematic diagram of a similarity analysis model provided by an exemplary embodiment of the present application; Figure 4 is a schematic diagram of an application of a similarity analysis model provided by an exemplary embodiment of the present application; Figure 5 is a structural diagram of an instruction execution device provided by an exemplary embodiment of the present application; Figure 6 It is a schematic diagram of the structure of an electronic device provided by an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0011] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0012] In conjunction with the accompanying drawings, an instruction execution method, an instruction execution device, an electronic device and a readable storage medium provided in an embodiment of the present application are described in detail through specific embodiments and their application scenarios.

[0013] Figure 1 An instruction execution method provided by an embodiment of the present application is shown. The method can be executed by a server, which may include: a server and / or a terminal device. In other words, the method can be executed by software or hardware installed on the server, and the method includes the following steps: S110: Acquire the operation instructions sent by each client for the target content within a preset time period.

[0014] The operation instruction is used to instruct to perform a related operation on the target content.

[0015] It is understandable that, within a preset time period, when multiple clients simultaneously initiate operation instructions for the target content, the operation instructions sent by each client for the target content are obtained.

[0016] Optionally, the client may be a server and / or a terminal device and / or an application installed on the server and / or the terminal device.

[0017] Optionally, the target content may include other screen content such as videos, documents, or pictures.

[0018] In one implementation, before S110, the method further includes: verifying the identity of each client; requesting authentication for each client, and sharing the target content with the client that notifies the identity verification and the authentication request. The implementation is described below through an exemplary embodiment. Figure 2 As shown in the figure, the client first sends the identity verification information to the audio module of the server through the WebSocket ssl (Wss) connection. The audio module of the server verifies the identity of the client after receiving the information. Then the client continues to request the authentication operation from the server, and the server returns the result after authentication to the client. Since the authentication information has been passed, the client only needs to send the identity verification information to the video module of the server for the video. When the identity information and authentication information are passed, the client will request the audio and video format from the server, and the server will open the audio and video encoders to share the target content with the client.

[0019] S120: In response to a determination that at least two first operation instructions are mutually exclusive, obtaining a first tendency corresponding to each of the first operation instructions.

[0020] Among them, the multiple operation instructions include the first operation instruction, the first tendency is determined based on the tendency analysis model and the user behavior data corresponding to the target frame picture of the target content, and the target frame picture is the current frame picture.

[0021] It is understandable that if the corresponding first operation instructions of at least two clients are mutually exclusive instructions, it is necessary to obtain the first tendency corresponding to each first operation instruction, so as to adjust the execution order of each first operation instruction according to the first tendency. Wherein, the first tendency is determined based on the tendency analysis model and the user behavior data corresponding to the target frame screen of the target content. It is understandable that for each first operation instruction, the user behavior data corresponding to the first operation instruction for the target frame screen is input into the tendency analysis model to obtain the first tendency. Wherein, the user behavior data may include touch screen parameters, which include but are not limited to touch screen force, touch screen trajectory, touch screen duration, target button parameters, etc.

[0022] S130: Determine an execution order of each of the first operation instructions based on the first tendency corresponding to each of the first operation instructions.

[0023] It can be understood that, among the at least two first operation instructions, the first operation instructions are sorted according to the first tendency corresponding to each first operation instruction, so as to determine the execution order of each first operation instruction.

[0024] S140: Execute the first instruction set, and execute the first operation instructions in sequence according to the execution order.

[0025] The first instruction set is a difference set between the plurality of operation instructions and the at least two first operation instructions.

[0026] It is understandable that the various operation instructions in the first instruction set are not mutually exclusive, and therefore, the various operation instructions in the first instruction set can be executed simultaneously. Among the at least two first operation instructions, the first operation instruction ranked first in the execution order can be executed simultaneously with the various operation instructions in the first instruction set. In other words, the first operation instruction ranked first in the execution order is executed simultaneously with the first instruction set, and after the execution is completed, the remaining first operation instructions are executed in sequence according to the execution order.

[0027] Exemplarily, assume that the multiple operation instructions include: instruction 1, instruction 2, instruction 3, instruction 4, instruction 5, instruction 6, instruction 7, instruction 8; wherein the first instruction set includes: instruction 1, instruction 2, instruction 3, and at least two first operation instructions include: instruction 4, instruction 5, instruction 6, instruction 7, instruction 8, wherein the execution order of the first operation instructions is: instruction 4, instruction 5, instruction 6, instruction 7, instruction 8. Then, at the same time, instruction 4 is executed simultaneously with instructions 1, instruction 2, and instruction 3 in the first instruction set, and after execution, instructions 5, instruction 6, instruction 7, and instruction 8 are executed in sequence.

[0028] In an embodiment of the present application, an operation instruction sent by each client for the target content within a preset time period is obtained, wherein the operation instruction is used to instruct to perform a related operation on the target content, and then in response to a judgment that at least two first operation instructions are mutually exclusive, a first tendency corresponding to each first operation instruction is obtained, wherein the multiple operation instructions include a first operation instruction, the first tendency is determined based on a tendency analysis model and user behavior data corresponding to a target frame of the target content, the target frame is the current frame, and then based on the first tendency corresponding to each first operation instruction, the execution order of each first operation instruction is determined, and finally the first instruction set is executed, and in accordance with the execution order, Execute the first operation instructions in sequence, wherein the first instruction set is the difference set of multiple operation instructions and at least two first operation instructions, which solves the problem of multiple operations being mutually exclusive. By setting the execution order for mutually exclusive instructions, other faults such as server crash and flash back can be effectively avoided. At the same time, the mutually exclusive instructions are determined by first executing a simple logical judgment, and then the analysis model is called to perform a tendency analysis on the mutually exclusive instructions. This can effectively reduce the time investment in the calculation process of the complex model and shorten the response time of the operation instructions, thereby improving the interactive experience. In addition, using the tendency as the judgment parameter for setting the execution order of mutually exclusive instructions can ensure that the instructions most relevant to the current frame are executed first.

[0029] In one implementation, the determining the execution order of each of the first operation instructions based on the first tendency corresponding to each of the first operation instructions includes: in response to a judgment that the first tendencies corresponding to at least two second operation instructions are the same, obtaining the second tendency corresponding to each of the second operation instructions, wherein the at least two first operation instructions include the second operation instruction, and the second tendency is determined based on a tendency analysis model and user behavior data corresponding to a target frame of the target content, and the target frame is a frame adjacent to the current frame and spaced by a preset number of frames; determining the execution order of each of the second operation instructions based on the second tendency corresponding to each of the second operation instructions, wherein the first execution order of the at least two second operation instructions is located after the execution order corresponding to the second instruction set, and the second instruction set is the difference set of the at least two first operation instructions and the at least two second operation instructions.

[0030] It is understandable that if the first tendency corresponding to at least two second operation instructions is the same, the second tendency corresponding to each second operation instruction is obtained, and the execution order of each second operation instruction is determined based on the second tendency. In other words, when the interface corresponding to the first operation instruction has no relevant historical operation record in the operation instruction library, that is, there is no corresponding user behavior data, then the statistical probability corresponding to the operation behavior initiated by the user is zero, so there is still the problem of mutual exclusion of instructions. To solve this problem, the continuous analysis of the previous and next frames is introduced to expand the time range of the operation data analysis, and the tendency of different second operation instructions within the current time range is judged by combining the operation records of the previous and next frames. In this way, the user's operation tendency can be learned by analyzing the previous and next frames. For example, when watching video data, when two different users simultaneously initiate "1.5 times fast forward" and "2 times fast forward" on the current frame, the commonly used operations within the current time range can be obtained by analyzing the historical operation status of the previous and next frames.

[0031] Exemplarily, assume that multiple operation instructions include: instruction 1, instruction 2, instruction 3, instruction 4, instruction 5, instruction 6, instruction 7, instruction 8; wherein, the first instruction set includes: instruction 1, instruction 2, instruction 3, and at least two first operation instructions include: instruction 4, instruction 5, instruction 6, instruction 7, instruction 8, wherein the execution order of the first operation instructions is: instruction 4, instruction 5, instruction 6, instruction 7, instruction 8; at least two second operation instructions include: instruction 4, instruction 6, instruction 8, and the second instruction set includes instruction 5 and instruction 7. Then, at the same time, instruction 5 in the second instruction set is executed simultaneously with instruction 1, instruction 2, instruction 3 in the first instruction set, and after the execution is completed, instruction 7 in the second instruction set is executed, and after instruction 7 is executed, instruction 4, instruction 6, instruction 8 are executed according to the execution order corresponding to the second tendency.

[0032] In addition, since the first tendency is determined based on the tendency analysis model and the user behavior data corresponding to the target frame of the target content, and the target frame is the current frame, if the first tendency is the same, the user behavior data of the second operation instruction for the current frame is the same, therefore, when calculating the second tendency, it is necessary to calculate the second tendency based on the user behavior data corresponding to the frame adjacent to the current frame and separated by a preset number of frames.

[0033] Furthermore, in another implementation, the method further includes: in a case where the user behavior data corresponding to the target frame image cannot be obtained, adjusting the preset frame number.

[0034] It is understandable that if a frame adjacent to the current frame and separated by a preset number of frames does not have user behavior data corresponding to a second operation instruction, then the preset number of frames is adjusted until the corresponding user behavior data is obtained.

[0035] In one implementation, the obtaining of the operation instructions sent by each client for the target content within a preset time period includes: upon receiving the operation instructions sent by at least two of the clients within the preset time period, instructing each of the clients to display a pop-up window, the pop-up window being used to prompt the user to confirm the operation instructions; and in response to a confirmation operation input by the user based on the pop-up window, obtaining the operation instructions corresponding to the confirmation operation.

[0036] It is understandable that when multiple clients initiate operation instructions at the same time, the server creates a time difference between mutually exclusive instructions by prompting the user through a pop-up window to ask whether there is an "accidental touch". When the user clicks "yes", the instruction requesting control is ignored; that is, the embodiment of the present application staggers the time of the originally initiated operation instructions through the time difference between whether the user clicks "accidental touch" or not, creates a time difference, and thus overcomes the occurrence of mutual exclusion. When the formulation of the time difference fails to achieve the staggering of mutually exclusive instructions, the constructed tendency analysis model is used to perform the tendency analysis of the operation instructions. After receiving multiple operation instructions, the execution order is set by analyzing the tendency of different operation instructions.

[0037] In one implementation, based on the second tendency corresponding to each of the second operation instructions, the execution order of each of the second operation instructions is determined, including: in response to a judgment that the second tendencies corresponding to at least two third operation instructions are the same, based on the target content, obtaining a target playback video of the client corresponding to each of the third operation instructions; obtaining behavioral operation data corresponding to each of the target playback videos; based on the behavioral operation data corresponding to each of the target playback videos, determining the third tendency corresponding to each of the third operation instructions, wherein the third tendency is determined based on the tendency analysis model and the behavioral operation data corresponding to the target playback video; based on the third tendency corresponding to each of the third operation instructions, determining the execution order of each of the third operation instructions, wherein the second execution order of at least two third operation instructions is located after the execution order corresponding to a third instruction set, and the third instruction set is a difference set between the at least two second operation instructions and the at least two third operation instructions.

[0038] It is understandable that if the second tendencies corresponding to at least two third operation instructions are the same, the third tendency corresponding to each third operation instruction is obtained, and the execution order of each second operation instruction is determined based on the third tendency. Among them, the third tendency is determined based on the tendency analysis model and the behavioral operation data corresponding to the target playback video, and the target playback video is the video with the highest similarity to the target content among the videos played by the client corresponding to the third operation instruction. In other words, if the phenomenon of mutual exclusivity of instructions cannot be overcome based on the second tendency, then the target content can be analyzed. For example, the labels and content introductions corresponding to the video data in the resource library are analyzed for similarity with the videos played by the client corresponding to each third operation instruction, so as to dig out the operating habits of users who play similar video resources, thereby calculating the third tendency.

[0039] Further, in another implementation, the obtaining of the target playback video of the client corresponding to each of the third operation instructions based on the target content includes: obtaining a text description corresponding to the target content and its corresponding text semantics, wherein the text semantics include a first semantics of at least one character and / or a second semantics of at least one word corresponding to the text description; and matching the target playback video corresponding to the target content based on the text semantics for at least one historical playback video of the client corresponding to each of the third operation instructions.

[0040] The first semantics may be a semantic vector, and the second semantics may be a word vector. The semantic vector refers to a vector corresponding to the basic meaning of a word or phrase and the original semantic source information.

[0041] It is understandable that the similarity analysis between videos can be converted into a similarity analysis of the text descriptions of the videos. However, since the labels and content summaries of the target content are short texts, their semantic information is insufficient. Therefore, the embodiment of the present application proposes a two-stage analysis method to improve the efficiency of extracting semantic information by bidirectionally fusing the semantic original information with the word vector.

[0042] Exemplarily, an embodiment of the present application provides a similarity analysis model, which uses the similarity analysis model to encode the label and content introduction of the target content, and uses a dual data stream method to obtain the semantic information corresponding to the word and word levels. At the same time, a BiLSTM model is added in the semantic extraction stage at the word level to further extract the semantic original information corresponding to the context. Subsequently, an attention mechanism is introduced in the feature extraction process to obtain the corresponding text features, and finally, after the vector splicing is performed, it is input into the classifier for semantic consistency judgment. In a further embodiment, in order to improve the ability to capture effective information, an attention mechanism is added to focus the learning ability of the model on contextualized learning to better obtain the semantic information of the text. Optionally, a multi-head attention mechanism and a collaborative attention mechanism are used at the same time, and a similarity matrix is ​​introduced, so that the model pays more attention to words with higher similarity and reduces the attention to non-synonymous words. Among them, the data items in the introduced similarity matrix represent the similarity scores of the words and words corresponding to two tokens calculated each time in the attention mechanism.

[0043] Optionally, in the process of performing similarity analysis of the text descriptions of two video resources, parallel data processing is performed on the semantic analysis of the text in combination with the two dimensions of characters and words. Figure 3 As shown, the similarity analysis model used to perform similarity analysis includes a coding layer, an interaction layer and a prediction layer. For the text descriptions of the two video resources to be analyzed, the coding layer is used to encode the read text descriptions, obtain a vector matrix for performing feature analysis, and obtain the corresponding deep semantic information. The interaction layer is used to extract and analyze features of the encoded data. The prediction layer is used to perform fusion analysis on the scattered features and output the final similarity analysis results.

[0044] In the encoding layer, the BERT model is used to encode the character-level text representation to obtain the corresponding semantic representation, and the FastText model is used to encode the word-level text representation to obtain the corresponding word-level semantics. Since the FastText model has the defect of insufficient extraction of context semantics during the semantic extraction process, the output of the FastText model is further transmitted to the BiLSTM model for secondary extraction of semantic information.

[0045] In the interaction layer, a multi-head attention mechanism and a collaborative attention mechanism are introduced for the data output by the encoding layer. By focusing the model's learning ability on contextualized learning, the semantic information of the text can be better obtained. In order to better focus the model's attention on words with high similarity, the introduced attention mechanism is optimized. By introducing a similarity matrix, the model pays more attention to words with high similarity and reduces its attention to non-synonymous words. The optimized attention mechanism is as follows Figure 4 As shown. The data items in the similarity matrix represent the similarity scores of the characters and words corresponding to the two tokens calculated each time in the attention mechanism. The similarity matrix uses the semantic relationship calculation method based on the original meaning in OpenHowNet. For example, the vectors a and b of the two sentences correspond to the similarity matrix S. The value of each cell in S is assigned according to whether the word pair is a synonym in OpenHowNett. When the two are synonyms, the cell value is 1, otherwise it is obtained based on the HowNet topological distance. The value between 0 and 1; in addition, when one of the words is not in OpenHowNet, the value of the cell is 0.

[0046] In the prediction layer, a vector concatenation operation is performed on the vectors obtained in the interaction layer, and the vectors are input into the fully connected layer to obtain the similarity analysis results of the text descriptions of the two video resources.

[0047] Figure 5 A schematic diagram showing the structure of an instruction execution device provided by an embodiment of the present application is shown as follows: Figure 5 As shown, the instruction execution device 500 may include: a first acquisition module 510 , a second acquisition module 520 , a determination module 530 and an execution module 540 .

[0048] In this embodiment, a first acquisition module 510 is used to acquire operation instructions sent by each client for target content within a preset time period, wherein the operation instructions are used to instruct to perform related operations on the target content; a second acquisition module 520 is used to acquire a first tendency corresponding to each of the first operation instructions in response to a judgment that at least two first operation instructions are mutually exclusive, wherein a plurality of the operation instructions include the first operation instruction, and the first tendency is determined based on a tendency analysis model and user behavior data corresponding to a target frame of the target content, and the target frame is a current frame; a determination module 530 is used to determine an execution order of each of the first operation instructions based on the first tendency corresponding to each of the first operation instructions; an execution module 540 is used to execute a first instruction set, and execute the first operation instructions in sequence according to the execution order, wherein the first instruction set is a difference set between a plurality of the operation instructions and the at least two first operation instructions.

[0049] In one implementation, the determination module 530 is specifically used to: in response to a judgment that the first tendencies corresponding to at least two second operation instructions are the same, obtain the second tendency corresponding to each second operation instruction, wherein the at least two first operation instructions include the second operation instruction, and the second tendency is determined based on a tendency analysis model and user behavior data corresponding to a target frame of the target content, and the target frame is a frame adjacent to the current frame and separated by a preset number of frames; based on the second tendency corresponding to each second operation instruction, determine the execution order of each second operation instruction, wherein the first execution order of at least two second operation instructions is located after the execution order corresponding to the second instruction set, and the second instruction set is the difference set of the at least two first operation instructions and the at least two second operation instructions.

[0050] In one implementation, the instruction execution device 500 may further include: an adjustment module, configured to adjust the preset number of frames when the user behavior data corresponding to the target frame cannot be obtained.

[0051] In one implementation, the first acquisition module 510 is specifically used to: when the operation instructions are received from at least two of the clients within the preset time period, instruct each of the clients to display a pop-up window, wherein the pop-up window is used to prompt the user to confirm the operation instructions; in response to the user's confirmation operation based on the pop-up window input, obtain the operation instruction corresponding to the confirmation operation.

[0052] In one implementation, based on the second tendency corresponding to each of the second operation instructions, the execution order of each of the second operation instructions is determined, including: in response to a judgment that the second tendencies corresponding to at least two third operation instructions are the same, based on the target content, obtaining a target playback video of the client corresponding to each of the third operation instructions; obtaining behavioral operation data corresponding to each of the target playback videos; based on the behavioral operation data corresponding to each of the target playback videos, determining the third tendency corresponding to each of the third operation instructions, wherein the third tendency is determined based on the tendency analysis model and the behavioral operation data corresponding to the target playback video; based on the third tendency corresponding to each of the third operation instructions, determining the execution order of each of the third operation instructions, wherein the second execution order of at least two third operation instructions is located after the execution order corresponding to a third instruction set, and the third instruction set is a difference set between the at least two second operation instructions and the at least two third operation instructions.

[0053] In one implementation, obtaining a target playback video of the client corresponding to each of the third operation instructions based on the target content includes: obtaining a text description corresponding to the target content and its corresponding text semantics, wherein the text semantics include a first semantics of at least one character and / or a second semantics of at least one word corresponding to the text description; and matching a target playback video corresponding to the target content based on the text semantics for at least one historical playback video of the client corresponding to each of the third operation instructions.

[0054] An instruction execution device provided in an embodiment of the present application can implement each process implemented in the instruction execution method embodiment, and will not be described again here to avoid repetition.

[0055] The instruction execution device in the embodiment of the present application may be a device, or a component, an integrated circuit, or a chip in an electronic device. The embodiment of the present application does not specifically limit this.

[0056] The instruction execution device in the embodiment of the present application may be a device having an operating system. The operating system may be an Android operating system, an iOS operating system, or other possible operating systems, which are not specifically limited in the embodiment of the present application.

[0057] Optional, such as Figure 6 As shown, an embodiment of the present application also provides an electronic device 600, including a processor 610, a memory 620, and a program or instruction stored in the memory 620 and executable on the processor 610. When the program or instruction is executed by the processor 610, each process of the above-mentioned instruction execution method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.

[0058] An embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the various processes of the above-mentioned instruction execution method embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0059] The processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0060] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned instruction execution method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0061] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0062] An embodiment of the present application also provides a computer program product, which includes at least one computer program. When the computer program is loaded and executed by a processor, it implements the various processes of the above-mentioned instruction execution method embodiment and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0063] It should be noted that, in this article, the terms "comprise", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise one..." do not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0064] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0065] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

Claims

1. A method for executing an instruction, characterized in that: The method comprises: Acquire an operation instruction sent by each client for target content within a preset time period, wherein the operation instruction is used to instruct to perform a related operation on the target content; In response to a determination that at least two first operation instructions are mutually exclusive, a first tendency corresponding to each of the first operation instructions is acquired, wherein the plurality of operation instructions include the first operation instruction, and the first tendency is determined based on a tendency analysis model and user behavior data corresponding to a target frame of the target content, the target frame being a current frame; Determining an execution order of each of the first operation instructions based on a first tendency corresponding to each of the first operation instructions; Execute a first instruction set, and execute the first operating instructions in sequence according to the execution order, wherein the first instruction set is a difference set of a plurality of the operating instructions and the at least two first operating instructions.

2. The method according to claim 1, characterized in that: The determining, based on the first tendency corresponding to each of the first operation instructions, the execution order of each of the first operation instructions comprises: In response to a determination that the first inclinations corresponding to at least two second operation instructions are the same, obtaining a second inclination corresponding to each of the second operation instructions, wherein the at least two first operation instructions include the second operation instruction, and the second inclination is determined based on a tendency analysis model and user behavior data corresponding to a target frame of the target content, wherein the target frame is a frame adjacent to the current frame and separated by a preset number of frames; Based on the second tendency corresponding to each of the second operation instructions, the execution order of each of the second operation instructions is determined, wherein the first execution order of at least two second operation instructions is located after the execution order corresponding to the second instruction set, and the second instruction set is the difference set of the at least two first operation instructions and the at least two second operation instructions.

3. The method according to claim 2, characterized in that The method further comprises: When the user behavior data corresponding to the target frame cannot be obtained, the preset frame number is adjusted.

4. The method according to claim 1, characterized in that: The obtaining of the operation instructions sent by each client for the target content within the preset time period includes: In the case where the operation instructions are received from at least two of the clients within the preset time period, instructing each of the clients to display a pop-up window, where the pop-up window is used to prompt the user to confirm the operation instruction; In response to a confirmation operation of the user based on the pop-up window input, the operation instruction corresponding to the confirmation operation is acquired.

5. The method according to claim 2, characterized in that: Determining the execution order of each of the second operation instructions based on the second tendency corresponding to each of the second operation instructions includes: In response to a determination that the second inclinations corresponding to at least two third operation instructions are the same, acquiring a target playback video of the client corresponding to each of the third operation instructions based on the target content; Acquire behavioral operation data corresponding to each of the target playback videos; Based on the behavior operation data corresponding to each of the target playback videos, determining a third tendency corresponding to each of the third operation instructions, wherein the third tendency is determined based on the tendency analysis model and the behavior operation data corresponding to the target playback video; Based on the third tendency corresponding to each of the third operation instructions, the execution order of each of the third operation instructions is determined, wherein the second execution order of at least two third operation instructions is located after the execution order corresponding to the third instruction set, and the third instruction set is the difference set of the at least two second operation instructions and the at least two third operation instructions.

6. The method according to claim 5, characterized in that The step of acquiring a target playback video of a client corresponding to each of the third operation instructions based on the target content includes: Acquire a text description corresponding to the target content and its corresponding text semantics, wherein the text semantics include a first semantics of at least one character and / or a second semantics of at least one word corresponding to the text description; For at least one historical playback video of the client corresponding to each of the third operation instructions, a target playback video corresponding to the target content is matched based on the text semantics.

7. An instruction execution device, characterized in that: include: A first acquisition module, used to acquire an operation instruction sent by each client for target content within a preset time period, wherein the operation instruction is used to instruct to perform a related operation on the target content; a second acquisition module, configured to acquire, in response to a determination that at least two first operation instructions are mutually exclusive, a first tendency corresponding to each of the first operation instructions, wherein the plurality of operation instructions include the first operation instruction, and the first tendency is determined based on a tendency analysis model and user behavior data corresponding to a target frame of the target content, the target frame being a current frame; a determination module, configured to determine an execution order of each of the first operation instructions based on a first tendency corresponding to each of the first operation instructions; The execution module is used to execute a first instruction set and execute the first operation instructions in sequence according to the execution order, wherein the first instruction set is a difference set of multiple operation instructions and the at least two first operation instructions.

8. An electronic device, characterized in that: include: A processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the instruction execution method according to any one of claims 1 to 6.

9. A readable storage medium, characterized in that: The readable storage medium stores a program or instruction, and when the program or instruction is executed by the processor, the steps of the instruction execution method according to any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that The computer program product comprises at least one computer program, and when the computer program is loaded and executed by a processor, the steps of the instruction execution method according to any one of claims 1 to 6 are implemented.

Images