Information processing method and device

Abstract

The embodiment of the present application discloses an information processing method, which includes: obtaining an analysis instruction; wherein the analysis instruction is used to instruct to analyze a target video, wherein the target video content includes a target object and at least one candidate object; obtaining association information of the target object; determining at least one object to be analyzed from at least one candidate object according to the association information; analyzing at least one object to be analyzed in the target video to obtain a target object; and outputting the target object. The embodiment of the present application also discloses an information processing device.

Description

Technical Field

[0001] The present application relates to the field of data analysis technology, and in particular to an information processing method and device. Background Art

[0002] At present, with the increasing power of computer analysis technology, computer computing power is becoming more and more powerful. Therefore, computer analysis technology has also been widely used, especially in the field of sports. For example, during the training of athletes, the training content of operators is simulated and analyzed through computer analysis technology to improve training efficiency. After the game, the content of the game video is analyzed to summarize the causes of mistakes, which effectively improves efficiency. When analyzing ball sports such as volleyball, when reviewing after training or after the game, it is necessary to sort out the mistakes or wrong actions of the players in the training game, as well as the positioning and analysis of the causes of the mistakes. At present, the above problems are mainly discovered by coaches observing on-site or watching training videos.

[0003] However, currently the above-mentioned problems are mainly analyzed by coaches, resulting in a low level of intelligence and low analysis efficiency. Summary of the invention

[0004] The embodiments of the present application are intended to provide an information processing method and device.

[0005] In a first aspect, an information processing method is provided, the method comprising:

[0006] Obtaining an analysis instruction; wherein the analysis instruction is used to instruct to analyze a target video, wherein the target video content includes a target object and at least one candidate object;

[0007] Acquiring the associated information of the target object;

[0008] Determining at least one object to be analyzed from at least one of the candidate objects according to the association information;

[0009] Analyze at least one of the objects to be analyzed in the target video to obtain a target object;

[0010] The target object is output.

[0011] Optionally, the association information includes: the number of times the target object contacts at least one of the candidate objects.

[0012] Optionally, determining at least one object to be analyzed from at least one candidate object according to the association information includes:

[0013] When the number of contacts is zero, determining a motion trajectory of the target object;

[0014] From the at least one candidate object, a candidate object that is within a first preset range corresponding to the motion trajectory of the target object is determined to obtain at least one object to be analyzed.

[0015] Optionally, analyzing at least one of the objects to be analyzed in the target video to obtain the target object includes:

[0016] Acquire analysis parameters of each of the objects to be analyzed to obtain at least one set of analysis parameters;

[0017] According to at least one set of the analysis parameters, an object to be analyzed whose analysis parameters do not match the preset parameters is determined from at least one of the objects to be analyzed, and the target object is obtained.

[0018] Optionally, the determining at least one object to be analyzed from at least one candidate object according to the association information further includes:

[0019] When the number of contacts is greater than or equal to 1, determining a candidate object that has been in contact with the target object from at least one of the candidate objects to obtain at least one contact object;

[0020] At least one object to be analyzed is determined according to at least one of the contact objects and the selection rule.

[0021] Optionally, the selection rule includes:

[0022] When the number of contacts is 1, the contact object and the candidate object that satisfies the first condition with the contact object are determined as the object to be analyzed.

[0023] Optionally, the selection rule includes:

[0024] When the number of contacts is greater than 1, at least each contact object is determined to be the object to be analyzed.

[0025] Optionally, analyzing at least one of the objects to be analyzed in the target video to obtain the target object includes:

[0026] In the case where there are multiple objects to be analyzed, the multiple objects to be analyzed are sorted in sequence according to the sorting rule;

[0027] The sorted multiple objects to be analyzed are analyzed in sequence to obtain the target object.

[0028] Optionally, in the process of sequentially analyzing the sorted plurality of objects to be analyzed, if the target object is determined, the analysis of the objects to be analyzed that have not been analyzed is stopped.

[0029] In a second aspect, an information processing device is provided, the device comprising: a first acquisition unit, a second acquisition unit, a determination unit, an analysis unit, and an output unit, wherein:

[0030] The first acquisition unit is used to acquire an analysis instruction; wherein the analysis instruction is used to instruct to analyze a target video, wherein the target video includes a target object and at least one candidate object;

[0031] The second acquisition unit is used to acquire the associated information of the target object;

[0032] The determining unit is configured to determine at least one object to be analyzed from at least one candidate object according to the association information;

[0033] The analyzing unit is used to analyze at least one of the objects to be analyzed in the target video to obtain a target object;

[0034] The output unit is used to output the target object.

[0035] The information processing method and device provided in the embodiment of the present application obtains the associated information of the target object by obtaining the analysis instruction, determines at least one object to be analyzed from at least one candidate object according to the associated information, analyzes at least one object to be analyzed in the target video, obtains the target object, and outputs the target object. In this way, at least one object to be analyzed is determined from at least one candidate object according to the associated information, and the target object is obtained by analyzing at least one object to be analyzed, which solves the problem that the current analysis of motion errors in the field of motion mainly relies on manpower, realizes the solution of the cause of motion errors through computer analysis technology, improves the intelligence level in the analysis process, and effectively improves the analysis efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 A flowchart of an information processing method provided in an embodiment of the present application;

[0037] Figure 2 It is a flowchart of another information processing method provided by an embodiment of the present application;

[0038] Figure 3 A flowchart of another information processing method provided in an embodiment of the present application;

[0039] Figure 4 A schematic diagram of the structure of an information processing device provided in an embodiment of the present application;

[0040] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0041] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0042] The embodiment of the present application provides an information processing method, referring to Figure 1 As shown, the method is applied to an electronic device, and the method comprises the following steps:

[0043] Step 101: Get analysis instructions.

[0044] The analysis instruction is used to instruct to analyze the target video, and the target video content includes a target object and at least one candidate object.

[0045] In an embodiment of the present application, the analysis instruction may be obtained by a user performing a corresponding operation input on the electronic device. For example, the user performs a touch operation on the touch display screen of the electronic device, or inputs an analysis instruction through an input device such as a mouse, keyboard, or voice input device that has a communication connection with the electronic device. The target video may be a specific video that includes a target object and at least one candidate object within a period of time and has been intercepted according to the analysis requirements, or it may be a complete video to be analyzed that has not been segmented. At least one candidate object may be determined by dividing an object in the target video content according to team attributes. There is a certain association relationship between the target object and at least one candidate object. The electronic device may be a device with computing capabilities, such as a server, a desktop computer, a laptop computer, a tablet computer, or even a smart phone or other device.

[0046] Exemplarily, taking volleyball as the target object, the target video content may be the complete video content of a volleyball match or volleyball training between volleyball team 1 and volleyball team 2, that is, the video content of the entire game or the training content. The target video content may also be a video content of a volleyball match or volleyball training between volleyball team 1 and volleyball team 2 when one of the volleyball teams makes a batting error. The corresponding received analysis instruction may be an instruction for instructing to analyze a batting error of a certain volleyball team to determine the cause of the error. Accordingly, at least one candidate object is a player belonging to the certain volleyball team and appearing in the target video content.

[0047] Step 102: Obtain relevant information of the target object.

[0048] In the embodiment of the present application, the association information of the target object refers to the association relationship between the target object and at least one candidate object. For example, in the association information of the target object, for a certain missed shot, the number of contacts between the at least one candidate object corresponding to the missed shot and the volleyball before the missed shot.

[0049] Step 103: Determine at least one object to be analyzed from at least one candidate object according to the association information.

[0050] In an embodiment of the present application, the video content corresponding to at least one candidate object in the target video is analyzed to determine at least one object to be analyzed corresponding to the associated information. Exemplarily, the at least one object to be analyzed is an object that may be involved in the missed shot.

[0051] Step 104: Analyze at least one object to be analyzed in the target video to obtain a target object.

[0052] In the embodiment of the present application, the target object is the final analysis result obtained in response to the analysis instruction. Exemplarily, the target object includes at least one candidate object, which is the object that caused the hitting error.

[0053] Step 105: Output the target object.

[0054] In an embodiment of the present application, the electronic device outputs the target object, which can be output to a display area corresponding to the electronic device, or to a communication device that has a communication link with the electronic device, such as a smart mobile device, including a smart phone and a tablet computer.

[0055] The information processing method provided by the embodiment of the present application obtains the associated information of the target object by obtaining the analysis instruction, determines at least one object to be analyzed from at least one candidate object according to the associated information, analyzes at least one object to be analyzed in the target video, obtains the target object, and outputs the target object. In this way, at least one object to be analyzed is determined from at least one candidate object according to the associated information, and the target object is obtained by analyzing at least one object to be analyzed, which solves the problem that the current analysis of motion errors in the field of motion mainly relies on manpower, realizes the solution of the cause of motion errors through computer analysis technology, improves the intelligence level in the analysis process, and effectively improves the analysis efficiency.

[0056] Based on the above embodiments, the present application provides an information processing method, referring to Figure 2 As shown, the method is applied to an electronic device, and the method comprises the following steps:

[0057] Step 201: Get analysis instructions.

[0058] The analysis instruction is used to instruct to analyze the target video, and the target video content includes a target object and at least one candidate object.

[0059] In an embodiment of the present application, a volleyball game video in which the target video is captured by the user and includes only one ball-touching error is used as an example for explanation. After the user inputs the captured target video into an information processing program running in an electronic device, the information processing program running in the electronic device may be automatically triggered to perform analysis. Alternatively, after the user inputs the target video into the electronic device, the user may perform corresponding control processing on the electronic device to send a corresponding analysis instruction to the electronic device.

[0060] It should be noted that when the target video is a video content including at least two hitting errors corresponding to the party to be analyzed, the electronic device needs to segment the target video with the hitting errors as nodes to obtain video content including only one hitting error, and perform corresponding subsequent analysis on each segmented video content. The party to be analyzed includes at least one candidate object.

[0061] For example, the target video is a video of a volleyball game that includes a mistake made by the team to be analyzed. After the user inputs the target video into the computer device, the user controls the computer device accordingly and inputs analysis instructions for analyzing the mistakes made by the team in the target video.

[0062] Step 202: Obtain relevant information of the target object.

[0063] The associated information includes: the number of times the target object contacts at least one candidate object.

[0064] In an embodiment of the present application, for a target video content including only one missed shot, the electronic device counts the number of contacts between at least one candidate object and the target object before the missed shot.

[0065] Exemplarily, after receiving the analysis instruction input by the user, the computer device responds to the analysis instruction, counts the number of times the player of the team touches the volleyball before and during the mistake in the target video, and obtains the associated information of the target object, wherein the player of the team corresponds to at least one of the aforementioned candidate objects, and the volleyball is the aforementioned target object.

[0066] Step 203: Determine at least one object to be analyzed from at least one candidate object according to the association information.

[0067] In the embodiment of the present application, at least one object to be analyzed is determined from at least one candidate object included in the target video information according to the number of contacts between the target object and at least one candidate object.

[0068] For example, when the relevant information counted in the target video is that the player made a mistake after touching the ball once, at least one object to be analyzed is the player who made the mistake, his teammate who received the ball before he received the ball, and his teammate who was within his sight when he received the ball. When the relevant information counted in the target video is that the player made a mistake after touching the ball twice or more, at least one object to be analyzed is the player who made the mistake, his teammate who received the ball before he received the ball, his teammate who was within his sight when he received the ball, and his teammate who touched the ball several times before he hit the ball.

[0069] Step 204: Analyze at least one object to be analyzed in the target video to obtain a target object.

[0070] In an embodiment of the present application, relevant data of at least one object to be analyzed is obtained from the target video for analysis to determine the target object that ultimately causes the hitting error.

[0071] Step 205: Output the target object.

[0072] In an embodiment of the present application, the target object is output to the display area of ​​the electronic device for display, and the corresponding displayed target object may be identification information of the corresponding candidate object, such as the name or number of the target object. When the number of candidate objects included in the target object is equal to 0, information that the target object is zero may be output.

[0073] Based on the above embodiments, in other embodiments of the present application, refer to Figure 2 As shown, step 203 can be implemented by steps 203a to 203b:

[0074] Step 203a: When the number of contacts is zero, determine the motion trajectory of the target object.

[0075] In the embodiment of the present application, the situation where the number of contacts is zero refers to the situation where at least one candidate object touches the target object, but the target object falls within the target area where at least one candidate object is located, causing the party to be analyzed where at least one candidate object is located to lose points, that is, after the opponent hits the ball, no one on the party to be analyzed touches the volleyball, causing the volleyball to fall within the field where the party to be analyzed is located. The motion trajectory of the target object refers to the motion trajectory of the target object corresponding to the time when the target object is hit by the opponent, flies to the target area where the party to be analyzed is located, and falls within the target area where the party to be analyzed is located.

[0076] Exemplarily, after the opponent hits the ball, the team fails to receive the volleyball, and the volleyball falls into the team's court, the movement trajectory of the volleyball in the area corresponding to the team is determined.

[0077] Step 203b: Determine, from at least one candidate object, a candidate object that is within a first preset range corresponding to the motion trajectory of the target object, and obtain at least one object to be analyzed.

[0078] In the embodiment of the present application, the first preset range corresponding to the motion trajectory of the target object includes: a certain range of the motion trajectory of the target object in the air area corresponding to the party to be analyzed projected to the ground area and a certain range of the landing point of the target object in the ground area corresponding to the party to be analyzed. In this way, the candidate object in the first preset range corresponding to the motion trajectory of the target object is used as at least one object to be analyzed, so as to improve the accuracy of subsequent analysis and effectively improve the efficiency and score of subsequent volleyball games or training.

[0079] Exemplarily, it is determined that the motion trajectory of the volleyball in the own area is projected onto the ground area to be a candidate object that can touch the volleyball, thereby obtaining at least one object to be analyzed.

[0080] Correspondingly, step 204 can be implemented by steps 204a to 204b:

[0081] Step 204a: Obtain analysis parameters of each object to be analyzed to obtain at least one set of analysis parameters.

[0082] In the embodiment of the present application, the analysis parameters of each object to be analyzed may include the position parameter and attention parameter of each analysis object, etc. Assuming that three analysis objects are determined, the analysis parameters of the three analysis objects are obtained respectively to obtain three groups of analysis parameters.

[0083] Step 204b: According to at least one set of analysis parameters, from at least one object to be analyzed, determine an object to be analyzed whose analysis parameters do not match preset parameters, and obtain a target object.

[0084] In an embodiment of the present application, each analysis parameter is compared with a preset parameter to obtain an analysis parameter that does not match the preset parameter, and the object to be analyzed corresponding to the analysis parameter that does not match the preset parameter is determined as a target object, wherein the number of candidate objects included in the target object is greater than or equal to 0.

[0085] Among them, if the position parameter included in each analysis parameter is different from the corresponding preset position in the preset parameter, and / or the attention parameter value included in each analysis parameter is lower than the preset attention parameter value, it is determined that each analysis parameter does not match the preset parameter; if the position parameter included in each analysis parameter is the same as the corresponding preset position in the preset parameter, and the attention parameter value included in each analysis parameter is higher than the preset attention parameter value, it is determined that each analysis parameter matches the preset parameter.

[0086] Exemplarily, data such as the position and attention of each object to be analyzed are obtained, and it is determined whether the position of each object to be analyzed is consistent with the expected position and the attention is focused, and the object to be analyzed whose position does not match the expected position and / or whose attention is not focused is determined as the target object from at least one object to be analyzed. In some application scenarios, when the position of each object to be analyzed in at least one object to be analyzed is consistent with the expected position and the attention is focused, the target object is zero, that is, the target object does not exist.

[0087] Based on the above embodiments, in other embodiments of the present application, refer to Figure 3 As shown, step 203 can be implemented by steps 203c to 203d:

[0088] Step 203c: when the number of contacts is greater than or equal to 1, determine a candidate object that has been in contact with the target object from at least one candidate object to obtain at least one contact object.

[0089] In the embodiment of the present application, at least one contact object includes a candidate object that forms a hitting error after hitting the ball and a candidate object that has contacted the target object before the hitting error. When the number of contacts is equal to 1, the contact object obtained is a candidate object that forms a hitting error after hitting the ball. The number of contacts corresponds to the number of contact objects.

[0090] Step 203d: Determine at least one object to be analyzed according to at least one contact object and a selection rule.

[0091] The selection rule includes: when the number of contacts is 1, determining the contact object and the candidate object that meets the first condition with the contact object as the object to be analyzed; when the number of contacts is greater than 1, determining at least each contact object as the object to be analyzed.

[0092] In an embodiment of the present application, the selection rule is a pre-set rule for selecting at least one object to be analyzed. The first condition refers to: the corresponding receiving object before the contact object contacts the target object and the candidate object within the preset line of sight of the contact object when the contact object contacts the target object. When the number of contacts is greater than 1, the at least one object to be analyzed determined includes at least one of the following objects: the number of contact objects corresponding to the number of contacts, the candidate object within the first preset range of the motion trajectory of the target object before the first reference object contacts the target object, and the candidate object within the line of sight of the first reference object when the first reference object contacts the target object, wherein the first reference object is a candidate object for deduction of points for the party to be analyzed where at least one candidate object is located after contacting the target object.

[0093] Correspondingly, step 204 can be implemented by steps 204c to 204d:

[0094] Step 204c: when there are multiple objects to be analyzed, the multiple objects to be analyzed are sorted in sequence according to the sorting rule.

[0095] In an embodiment of the present application, when at least one object to be analyzed includes contact objects corresponding to the number of contacts and the number of contacts is greater than or equal to 2, the corresponding sorting rule may be a sorting rule for sorting according to the order of contacting the target object. When at least one object to be analyzed includes the following objects: contact objects corresponding to the number of contacts, candidate objects within the first preset range of the target object's motion trajectory before the first reference object contacts the target object, and candidate objects within the first reference object's line of sight when the first reference object contacts the target object, the corresponding sorting rule may be: first, at least one object to be analyzed is grouped and sorted in sequence into: contact objects corresponding to the number of contacts, candidate objects within the first preset range of the target object's motion trajectory before the first reference object contacts the target object, and candidate objects within the first reference object's line of sight when the first reference object contacts the target object, and then sort the contact objects: sort the contact objects according to the order of contacting the target object.

[0096] Step 204d: Analyze the sorted multiple objects to be analyzed in sequence to obtain the target object.

[0097] In an embodiment of the present application, according to the group sorting order, the data of the object to be analyzed corresponding to the group sorting order is obtained for analysis. If the target object is not determined to be obtained, the data of the object to be analyzed corresponding to the next adjacent sorting order is obtained for analysis, and this process is repeated until the target object is determined to be obtained; if the target object is determined to be obtained, the subsequent analysis is stopped.

[0098] In other embodiments of the present application, step 204d can be specifically implemented by the following steps: in the process of analyzing the sorted multiple objects to be analyzed in sequence, if the target object is determined, then stop analyzing the objects to be analyzed that have not been analyzed. In this way, there is no need to analyze all the data in the target video, and the target object is determined by analyzing specific data, and the priority of the data to be analyzed is defined in a logical order, and the analysis and processing order is from simple to complex, which reduces the amount of data to be processed, saves video analysis costs, processing calculation time and storage space, reduces the requirements for computing power, and effectively speeds up the processing speed.

[0099] Exemplarily, if the number of contacts in the associated information is 1, then data such as the position and attention of the teammates who receive the ball before the person hits the ball are obtained, and the performance of the teammates is judged by comparing whether the positions of the teammates are consistent with the expected skills and tactics and their attention is focused; if the positions of all the teammates who receive the ball before the person hits the ball are consistent with the expected skills and tactics and their attention is focused, determine whether there are other teammates within the person's field of vision when the person hits the ball; if there are other teammates within the person's field of vision when the person hits the ball, obtain data such as the height, position, position of the volleyball, and flight trajectory of the volleyball of other teammates; analyze the data such as the height, position, position, and flight trajectory of the volleyball of other teammates to determine whether other teammates block the person's view of the volleyball. The player is on the line of sight path, thereby determining whether teammates have affected the player's field of vision, thereby affecting the judgment of the ball and causing a mistake; if it is determined that other teammates are blocking the player's line of sight to the volleyball, the other teammates blocking the player's line of sight to the volleyball are determined as target objects, and no other data are analyzed; if there are no other teammates within the player's line of sight when the player hits the ball, or it is determined that no other teammates are blocking the player's line of sight to the volleyball, the player is determined to be the target object, that is, the error is determined to be caused by the player himself, and no other data are analyzed; if the positions of some of the player's teammates before the player hits the ball are inconsistent with the expected skills and tactics and / or their attention is not focused, these teammates are determined to be target objects.

[0100] In the embodiment of the present application, in the process of sequentially analyzing the sorted multiple objects to be analyzed, if the target object is determined, the step of stopping the analysis of the unanalyzed objects to be analyzed can be implemented by steps a11 to a18:

[0101] Step a11: Obtain the data to be analyzed of each contact object among the contact objects with the contact times in the target video.

[0102] Step a12: Compare and analyze the data to be analyzed for each contact object with the preset data to determine the contact category of each contact object.

[0103] After the electronic device executes step a12, it can choose to execute steps a13 to a17 or a18. If the contact category of the previous contact object adjacent to the first reference object is the first category, steps a13 to a17 are selected to be executed; if the contact category of the previous contact object adjacent to the first reference object is the second category, step a18 is selected to be executed.

[0104] Step a13: if the contact category of the previous contact object adjacent to the first reference object is the first category, obtain analysis parameters of candidate objects within a first preset range of the target object's motion trajectory before the first reference object contacts the target object.

[0105] After the electronic device executes step a13, it may choose to execute step a14 or steps a15 to a17.

[0106] Step a14, based on the analysis parameters and preset parameters of the candidate objects within the first preset range of the motion trajectory of the target object before the first reference object contacts the target object, determine the candidate objects whose analysis parameters do not match the preset parameters from the candidate objects within the first preset range of the motion trajectory of the target object before the first reference object contacts the target object as the target object, and stop subsequent analysis operations.

[0107] Step a15: If the analysis parameters of the candidate objects within the first preset range of the target object's motion trajectory before the first reference object contacts the target object all match the preset parameters, obtain reference data of the candidate objects within the first reference object's line of sight when the first reference object contacts the target object.

[0108] After the electronic device executes step a15, it may choose to execute step a16 or step a17.

[0109] Step a16: Determine the candidate objects whose reference data do not match the preset reference data from the candidate objects within the visual range of the first reference object when the first reference object contacts the target object, obtain the target object, and stop subsequent analysis operations.

[0110] Step a17: If the reference data of the candidate objects within the visual range of the first reference object when the first reference object contacts the target object all match the preset reference data, the first reference object is determined to be the target object.

[0111] Step a18: If the contact category of the previous contact object adjacent to the first reference object is the second category, determine a target contact object whose contact category is the second category and is adjacent to and continuous with the previous contact object from the contact objects with the contact times excluding the first reference object, and determine the previous contact object and the target contact object as the target objects.

[0112] Exemplarily, (1) if the number of contacts is greater than or equal to 2, obtain the data to be analyzed of the N teammates who touched the ball before the player, and the data to be analyzed includes at least one of the following: batting posture, ball touching result and actual landing point; and judge whether the batting posture, such as the upper body backward tilt angle, arm swing amplitude, forearm flip angle, etc., deviates from the ideal posture by more than a first threshold range, and the ball touching result, such as whether the ball trajectory deviates from the expected ideal trajectory by more than a second threshold range, whether the actual landing point deviates from the expected ideal landing point by more than a preset distance, etc., to determine the touch quality of each ball touch before the player.

[0113] Among them, if one of the following conditions is met, it is determined as a general touch of ball quality, which corresponds to the second category mentioned above; the rest of the cases are determined as effective touch of ball quality, which corresponds to the first category mentioned above:

[0114] 1. The deviation of the upper body backward tilt angle, forearm angle, and arm swing amplitude of the batting posture from the ideal posture exceeds the first threshold range. Among them, the ideal posture should be calculated based on the touch type, the incoming ball trajectory, and the ideal landing point of the next ball, including: a) When the touch trajectory is a pass: i. The arc of the incoming ball is high, and the arm angle should be small; the arc of the incoming ball is flat, and the arm angle should be large; ii. If the ideal landing point is far, the arm angle should be slightly larger; if the distance is close, the arm angle should be smaller; iii. The specific angle value should be input into the system in advance based on the coach's prior knowledge, and the system will give it according to the actual situation; b) When the touch trajectory is a spike: i. The upper body should be perpendicular to the ground when taking off; ii. The upper body backward tilt angle when spiking should meet the standard. The specific standard can be input into the system in advance based on the coach's prior knowledge, and the system will give it according to the actual situation.

[0115] 2. The deviation between the trajectory of the ball after touching the ball and the ideal trajectory exceeds the second threshold range. Among them, the ideal trajectory should be determined based on the type of touch and the form on the field: a) When the touch type is a self-made pass, the ideal trajectory standard is that it is easy for the self-made spike: i. There are players who can appear in time at the trajectory landing point; ii. When the touch type is a self-made spike, the ideal trajectory standard is that the height of the ball over the net is not higher than X1 meters and the angle is not greater than X2°. Among them, the specific values ​​can be input into the system in advance based on the coach's prior knowledge and given by the system according to the actual situation.

[0116] 3. The actual landing point of the volleyball does not match the expected landing point. The judgment conditions are as follows: a) The landing point is out of bounds; b) The landing point deviates from the expected landing point calculated based on the predicted trajectory by more than a preset distance.

[0117] (2) If it is determined that the previous touch of the ball before the player's touch is a valid touch, obtain data such as the position and attention of the teammate who received the ball before the player's hit, and compare whether the position of the teammate who received the ball is consistent with the expected skills and tactics and whether the teammate is focused.

[0118] (3) If the positions of teammates before hitting the ball are consistent with the expected skills and tactics and their attention is focused, determine whether there are other teammates within the player's field of vision: If there are other teammates within the player's field of vision when hitting the ball, obtain data such as the height, position, volleyball position, and volleyball flight trajectory of other teammates; analyze the data such as the height, position, volleyball position, and volleyball flight trajectory of other teammates to determine whether other teammates block the player's field of vision when looking at the volleyball, so as to determine whether the teammates affect the player's field of vision, thereby affecting the player's judgment of the ball and causing a mistake; if it is determined that other teammates block the player's field of vision when looking at the volleyball, determine the other teammates blocking the player's field of vision when looking at the volleyball as the target object, and no longer analyze other data; if there are no other teammates within the player's field of vision when hitting the ball, or determine that no other teammates block the player's field of vision when looking at the volleyball, determine the player as the target object, that is, determine that the mistake is caused by the player himself, and no longer analyze other data.

[0119] (4) If there are no other teammates within the line of sight when hitting the ball, it is determined that the person is the target object, which means that the person is the target due to his own reasons, and no other data will be analyzed.

[0120] (5) If the positions of some of the teammates before the player hits the ball do not match the expected skills and tactics and / or their attention is not focused, these teammates are identified as targets.

[0121] (6) If the quality of the first few times that the person touches the ball is average, the object that touches the ball corresponding to the first time that the person touches the ball is determined as the target object.

[0122] For example, when the number of touches is 2, the missed touch is the second touch. When the quality of the first touch is a general touch, the player who touched the ball for the first time is determined to be the target object, that is, the player who touched the ball for the first time caused the mistake, and no other data is analyzed. When the number of touches is 3, the missed touch is the third touch. If the quality of the first touch is an effective touch and the quality of the second touch is a general touch, the player who touched the ball for the second time is determined to be the target object, that is, the player who touched the ball for the second time caused the mistake, and no other data is analyzed; if the quality of the first touch and the second touch are both general touches, the player who touched the ball for the first time and the player who touched the ball for the second time are determined to be the target objects, that is, the player who touched the ball for the first time and the player who touched the ball for the second time jointly caused the mistake, and no other data is analyzed.

[0123] Based on the above embodiments, in other embodiments of the present application, after the electronic device executes step 204, it may also execute steps b11 to b12, or steps b11 and b13, or steps b11 to b13. Which of the above steps to execute after the electronic device executes step 204 may be determined according to the actual application scenario, and no limitation is made here:

[0124] Step b11: Obtain the video to be output from the target video according to the target object.

[0125] The video to be output includes the content of the contact between the target subject and the target object.

[0126] Step b12: determine the first communication device corresponding to the target object, and send the video to be output to the first communication device.

[0127] Step b13: determine a second communication device corresponding to the guidance object associated with the target object, and send the video to be output to the second communication device.

[0128] In the embodiment of the present application, the first communication device and the second communication device can be a computer device or a smart mobile device. In this way, part of the video content is intercepted from the target video and sent to the first communication device and / or the second communication device, which effectively reduces the demand for network resources and facilitates the corresponding personnel to view the process that caused the error, effectively summarizes the experience, and improves the user experience.

[0129] It should be noted that step b12, step b13 or steps b12-b13 may be executed before step 205, or may be executed simultaneously with step 205, and the specific execution order may be determined according to actual conditions.

[0130] Based on the above embodiments, in other embodiments of the present application, step b11 can be implemented by the following steps:

[0131] Step b111: If the target object includes a candidate object, determine from the target video a first video frame corresponding to when a previous object adjacent to the target object contacts the target object, and a second video frame corresponding to when a first reference object contacts the target object.

[0132] The first reference object is a candidate object that has last contacted the target object in the association information.

[0133] In an embodiment of the present application, the previous object adjacent to the target object may be an object that does not belong to the contact target object of the party to be analyzed and that was adjacent to the target object before the target object contacted the target object, or may be a candidate object that belongs to the contact target object of the party to be analyzed and that was adjacent to the target object before the target object contacted the target object.

[0134] Step b112: Obtain video frames between a first number of frames before the first video frame and a second number of frames after the second video frame from the target video to obtain a video to be output.

[0135] In the embodiment of the present application, the first number of frames and the second number of frames are preset empirical values, which may be the same or different, and may be specifically determined according to the actual application scenario.

[0136] Step b113: If the target object includes multiple candidate objects, determine from the target objects a target candidate object that has touched the target object the longest time since the first reference object touched the target object.

[0137] In the embodiment of the present application, it is assumed that the target object includes three candidate objects, and the corresponding contact times of the target object are A, B and C from far to near. Correspondingly, it can be determined that the target candidate object is A.

[0138] Step b114: determining from the video information to be analyzed a third video frame corresponding to when a previous object adjacent to the target candidate object contacts the target object, and a second video frame corresponding to when the first reference object contacts the target object.

[0139] Step b115: Obtain video frames between a third number of frames before the third video frame and a fourth number of frames after the second video frame from the target video to obtain a video to be output.

[0140] In the embodiment of the present application, the third number frame and the fourth number frame are an empirical value and can be the same or different. The third number frame can be the same as or different from the first number frame. Similarly, the fourth number frame can be the same as or different from the second number frame.

[0141] Based on the foregoing embodiment, in other embodiments of the present application, after the electronic device executes step b11, it can also be used to execute step b14:

[0142] Step b14: storing the video to be output to a storage area corresponding to the target object.

[0143] In the embodiment of the present application, the videos to be output are classified and stored in the storage area corresponding to the target object. In this way, the classified storage effectively improves the storage efficiency, so that the videos to be output can be quickly searched when they are analyzed later.

[0144] It should be noted that step b14 can be executed before step b12, step b13 or steps b12-b13, or after step b12, step b13 or steps b12-b13, or simultaneously with step b12, step b13 or steps b12-b13, or before step 205 or after step 205, or simultaneously with step 205. The specific execution order can be determined according to actual conditions.

[0145] It should be noted that, for the description of the same steps and the same contents in this embodiment as those in other embodiments, reference can be made to the description in other embodiments and will not be repeated here.

[0146] The information processing method provided by the embodiment of the present application obtains the associated information of the target object by obtaining the analysis instruction, determines at least one object to be analyzed from at least one candidate object according to the associated information, analyzes at least one object to be analyzed in the target video, obtains the target object, and outputs the target object. In this way, at least one object to be analyzed is determined from at least one candidate object according to the associated information, and at least one object to be analyzed is analyzed to obtain the target object, which solves the problem that the current analysis of sports errors in the sports field mainly relies on manpower to achieve, realizes the solution of the cause of sports errors through computer analysis technology, improves the intelligence level in the analysis process, and effectively improves the analysis efficiency. The target object is determined by the number of contacts between the target object and at least one candidate object, which effectively reduces the number of analysis objects and reduces the resource consumption in the analysis process. When the number of contacts is zero, the candidate object in the first preset range corresponding to the running trajectory of the target object is determined as at least one object to be analyzed, ensuring the accurate object of the analysis that causes the hitting error. There is no need to analyze all objects in the target video. Only specific data needs to be analyzed to obtain the reasons for the player's hitting errors. The data priority that needs to be analyzed is defined in a logical order, and the analysis and processing order is from simple to complex. If there is a judgment result, the analysis data will no longer be processed, which greatly reduces the amount of data that needs to be analyzed and processed, saves video analysis costs, processing computing time and storage space, reduces the requirements for computing power, and speeds up processing efficiency.

[0147] Based on the above embodiments, the embodiments of the present application provide an information processing device, which can be applied to Figures 1 to 3 In the information processing method provided in the corresponding embodiment, refer to Figure 4 As shown, the information processing device 3 includes: a first acquisition unit 31, a second acquisition unit 32, a determination unit 33, an analysis unit 34 and an output unit 35, wherein:

[0148] A first acquisition unit 31 is used to acquire an analysis instruction; wherein the analysis instruction is used to instruct to analyze a target video, wherein the target video includes a target object and at least one candidate object;

[0149] A second acquisition unit 32, used to acquire associated information of the target object;

[0150] A determination unit 33, configured to determine at least one object to be analyzed from at least one candidate object according to the association information;

[0151] An analyzing unit 34, configured to analyze at least one object to be analyzed in a target video to obtain a target object;

[0152] The output unit 35 is used to output the target object.

[0153] In other embodiments of the present application, the association information includes: the number of times the target object contacts at least one candidate object.

[0154] In other embodiments of the present application, the determination unit 33 includes: a first determination module and a second determination module, wherein:

[0155] A first determination module, used to determine the motion trajectory of the target object when the number of contacts is zero;

[0156] The second determination module is used to determine, from at least one candidate object, a candidate object that is within a first preset range corresponding to the motion trajectory of the target object, to obtain at least one object to be analyzed.

[0157] In other embodiments of the present application, the analysis unit 34 includes: an acquisition module and a processing module, wherein:

[0158] An acquisition module, used to acquire analysis parameters of each object to be analyzed, and obtain at least one set of analysis parameters;

[0159] The processing module is used to determine, from at least one object to be analyzed, an object to be analyzed whose analysis parameters do not match preset parameters according to at least one set of analysis parameters, and obtain a target object.

[0160] In other embodiments of the present application, the determination unit 33 further includes: a third determination module and a fourth determination module, wherein:

[0161] A third determination module is used to determine, when the number of contacts is greater than or equal to 1, a candidate object that has been in contact with the target object from at least one candidate object to obtain at least one contact object;

[0162] The fourth determination module is used to determine at least one object to be analyzed according to at least one contact object and a selection rule.

[0163] In other embodiments of the present application, the selection rule is stored in the memory, and the selection rule includes:

[0164] When the number of contacts is 1, the contact object and the candidate objects that meet the first condition with the contact object are determined as the objects to be analyzed.

[0165] In other embodiments of the present application, the selection rule is stored in the memory, and the selection rule includes:

[0166] When the number of contacts is greater than 1, at least each contact object is determined to be an object to be analyzed.

[0167] In other embodiments of the present application, the analysis unit 34 further includes: a sorting module and an analysis module, wherein:

[0168] A sorting module is used to sort the multiple objects to be analyzed in sequence according to the sorting rules when there are multiple objects to be analyzed;

[0169] The analysis module is used to analyze the sorted multiple objects to be analyzed in sequence to obtain the target object.

[0170] In other embodiments of the present application, the analysis module is used to stop analyzing the objects to be analyzed that have not been analyzed if a target object is determined during the process of sequentially analyzing the sorted multiple objects to be analyzed.

[0171] It should be noted that the explanation of the steps between the modules or units in the embodiments of the present application can refer to Figures 1 to 3 The implementation process of the information processing method provided in the corresponding embodiment will not be repeated here.

[0172] The information processing device provided by the embodiment of the present application determines at least one object to be analyzed from at least one candidate object according to the associated information, and analyzes at least one object to be analyzed to obtain the target object, which solves the problem that the current sports error analysis in the field of sports mainly relies on manpower to achieve, realizes the solution of the cause of sports errors through computer analysis technology, improves the intelligence level in the analysis process, and effectively improves the analysis efficiency. The target object is determined by the number of contacts between the target object and at least one candidate object, which effectively reduces the number of analysis objects and reduces the resource consumption in the analysis process. When the number of contacts is zero, the candidate object in the first preset range corresponding to the running track of the target object is determined as at least one object to be analyzed, ensuring the accurate object of the analysis that causes the hitting error. There is no need to analyze all objects in the target video, only specific data needs to be analyzed to analyze the cause of the player's hitting error, and the priority of the data to be analyzed is defined in a logical order, so that the analysis processing order is from simple to complex. If there is a judgment result, the analysis data will no longer be processed, which greatly reduces the amount of data that needs to be analyzed and processed, saves video analysis costs, processing calculation time and storage space, and reduces the requirements for computing power, speeding up processing efficiency.

[0173] Based on the above embodiments, the present application also provides an electronic device, which can be used to implement the following Figures 1 to 3 The information processing method shown is referred to Figure 5 As shown, the electronic device 4 may include: a processor 41, a memory 42 and a communication bus 43, wherein:

[0174] Memory 42, including information processing program;

[0175] A communication bus 43, used to realize the communication connection between the processor 41 and the memory 42;

[0176] The processor 41 is used to execute the information processing program stored in the memory 42, and is specifically implemented as follows: Figures 1 to 3 The information processing method shown will not be described in detail here.

[0177] Based on the foregoing embodiments, the embodiments of the present application further provide a computer-readable storage medium, referred to as a storage medium, which stores one or more programs, and the one or more programs can be executed by one or more processors to implement the following. Figures 1 to 3 The information processing method shown will not be described in detail here.

[0178] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of hardware embodiments, software embodiments, or embodiments in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) that contain computer-usable program code.

[0179] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0180] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0181] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0182] The above description is only a preferred embodiment of the present application and is not intended to limit the protection scope of the present application.

Claims

1. An information processing method, the method comprising: Obtaining an analysis instruction; wherein the analysis instruction is used to instruct to analyze a target video, wherein the target video content includes a target object and at least one candidate object; Acquire association information of the target object; the association information includes: the number of times the target object contacts at least one of the candidate objects; Determine at least one object to be analyzed from at least one of the candidate objects according to the number of contacts; Analyze at least one of the objects to be analyzed in the target video to obtain a target object; Outputting the target object; the target object includes at least one candidate object, and the target object is characterized as an object determined by the analysis result that caused the error; Determining at least one object to be analyzed from at least one candidate object according to the number of contacts includes: When the number of contacts is zero, determining a motion trajectory of the target object; From the at least one candidate object, a candidate object that is within a first preset range corresponding to the motion trajectory of the target object is determined to obtain at least one object to be analyzed.

2. According to the method of claim 1, the step of analyzing at least one of the objects to be analyzed in the target video to obtain the target object comprises: Acquire analysis parameters of each of the objects to be analyzed to obtain at least one set of analysis parameters; According to at least one set of the analysis parameters, an object to be analyzed whose analysis parameters do not match the preset parameters is determined from at least one of the objects to be analyzed, and the target object is obtained.

3. The method according to claim 1, wherein determining at least one object to be analyzed from at least one candidate object according to the number of contacts further comprises: When the number of contacts is greater than or equal to 1, determining a candidate object that has been in contact with the target object from at least one of the candidate objects to obtain at least one contact object; At least one object to be analyzed is determined according to at least one of the contact objects and the selection rule.

4. The method according to claim 3, wherein the selection rule comprises: When the number of contacts is 1, the contact object and the candidate object that satisfies the first condition with the contact object are determined as the object to be analyzed.

5. The method according to claim 3, wherein the selection rule comprises: When the number of contacts is greater than 1, at least each contact object is determined to be the object to be analyzed.

6. The method according to claim 1, wherein the step of analyzing at least one of the objects to be analyzed in the target video to obtain the target object comprises: In the case where there are multiple objects to be analyzed, the multiple objects to be analyzed are sorted in sequence according to the sorting rule; The sorted multiple objects to be analyzed are analyzed in sequence to obtain the target object.

7. The method according to claim 6, wherein in the process of sequentially analyzing the sorted plurality of objects to be analyzed, if the target object is determined, then the analysis of the objects to be analyzed that have not been analyzed is stopped.

8. An information processing device, comprising: A first acquisition unit, a second acquisition unit, a determination unit, an analysis unit, and an output unit, wherein: The first acquisition unit is used to acquire an analysis instruction; wherein the analysis instruction is used to instruct to analyze a target video, wherein the target video includes a target object and at least one candidate object; The second acquisition unit is used to acquire the associated information of the target object; the associated information includes: the number of times the target object contacts at least one of the candidate objects; The determining unit is used to determine at least one object to be analyzed from at least one candidate object according to the number of contacts; The determination unit includes a first determination module and a second determination module, wherein: the first determination module is used to determine the motion trajectory of the target object when the number of contacts is zero; the second determination module is used to determine, from at least one of the candidate objects, a candidate object that is within a first preset range corresponding to the motion trajectory of the target object, to obtain at least one of the objects to be analyzed; The analysis unit is used to analyze at least one of the objects to be analyzed in the target video to obtain a target object; the output unit is used to output the target object; the target object includes at least one candidate object, and the target object is characterized as an object determined by the analysis result that causes an error.

Images