AR product experience subjective evaluation processing method and device, equipment and medium

Abstract

The invention provides an AR product experience subjective evaluation processing method and device, equipment and a medium. The method comprises the steps that operation data and physiological behavior data in the process that a user experiences an AR product are acquired; performing space-time alignment operation on the operation data and the physiological behavior data to obtain the operation data and the physiological behavior data after space-time alignment; determining a first score attention feature of the operation data after space-time alignment and a second score attention feature of the physiological behavior data after space-time alignment according to the operation data and the physiological behavior data after space-time alignment; and according to the first score attention feature and the second score attention feature, determining a subjective prediction score of the AR product experienced by the user. Effective data can be collected to a greater extent, and the reliability of AR user experience subjective evaluation data is improved.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field, in particular to an AR product experience subjective evaluation processing method and device, equipment and medium. BACKGROUND

[0002] At present, with the development of multimedia technology, augmented reality technology is increasingly applied to various fields such as medical treatment, education and industry. Augmented reality technology (hereinafter referred to as AR) is a new technology of superimposing virtual items on the real world to make real world information and virtual world information "seamless" integration. The goal of this technology is to put the virtual world on the real world on the screen and interact. AR products are emerging in an endless stream. In order to improve user experience and service quality, it is necessary to evaluate AR product applications to realize real-time quality control of AR products. AR products are emerging in an endless stream. In order to improve user experience and service quality, it is necessary to evaluate AR product applications. In addition to the objective parameter evaluation method, the main method used is subjective evaluation.

[0003] The traditional subjective questionnaire is greatly affected by the subjective tendency of the subjects, and there are problems such as arbitrary scoring and understanding deviation. Pure objective indicators (such as time delay and frame rate) cannot effectively reflect the real user experience. Therefore, the current evaluation method cannot realize real-time quality control of AR products. SUMMARY

[0004] In view of the problems existing in the prior art, the application provides an AR product experience subjective evaluation processing method, device, equipment and medium.

[0005] The application provides an AR product experience subjective evaluation processing method, which comprises the following steps: Obtaining operation data and physiological behavior data in the process of user experience AR product; Performing a space-time alignment operation on the operation data and the physiological behavior data to obtain space-time aligned operation data and space-time aligned physiological behavior data; According to the space-time aligned operation data and the space-time aligned physiological behavior data, determining a first scoring attention feature of the space-time aligned operation data and a second scoring attention feature of the space-time aligned physiological behavior data; According to the first scoring attention feature and the second scoring attention feature, determining a subjective predicted score of user experience AR product.

[0006] According to the AR product experience subjective evaluation processing method provided by the application, the method further comprises the following steps: Obtaining a subjective predicted score and a subjective actual score in historical data; According to the subjective predicted score and the subjective actual score in the historical data, determining a mean value and a covariance; determine a confidence value of the user experience AR product according to the currently determined subjective prediction score, the mean value and the covariance of the user experience AR product; determine a processing result of the currently determined subjective prediction score of the user experience AR product according to the confidence value of the user experience AR product.

[0007] According to the AR product experience subjective evaluation processing method provided by the application, the processing result of the currently determined subjective prediction score of the user experience AR product is determined according to the confidence value of the user experience AR product, and the processing result comprises: when the confidence value of the user experience AR product is greater than a preset value, the currently determined subjective prediction score of the user experience AR product and the corresponding subjective actual score are stored in a database; when the confidence value of the user experience AR product is less than or equal to the preset value and a trigger signal for storing the currently determined subjective prediction score of the user experience AR product is sensed, the currently determined subjective prediction score of the user experience AR product and the corresponding subjective actual score are stored in the database.

[0008] According to the AR product experience subjective evaluation processing method provided by the application, the method further comprises: when the confidence value of the user experience AR product is less than or equal to the preset value and a trigger signal for determining the currently determined subjective prediction score of the user experience AR product as invalid data is sensed, a subjective simulation score of the user experience AR product is simulated as the subjective prediction score, and the subjective simulation score and the corresponding subjective actual score are stored in the database.

[0009] According to the AR product experience subjective evaluation processing method provided by the application, the subjective prediction score and the subjective actual score in the historical data are obtained, and the method comprises: a score group in the historical data is obtained, the score group comprising the subjective prediction score and the subjective actual score.

[0010] According to the AR product experience subjective evaluation processing method provided by the application, the method further comprises: if the subjective simulation score exists in the score group, the number of the subjective simulation scores is M; in the historical data, N-M score groups without the subjective simulation score are obtained again.

[0011] The confidence value of the user experience AR product is determined according to the currently determined subjective prediction score, the mean value and the covariance of the user experience AR product, and the method comprises: the difference between the currently determined subjective prediction score of the user experience AR product and the mean value and the transpose of the difference are determined. Determine a confidence value of the user experiencing the AR product according to the difference value, the transpose of the difference value, and the covariance.

[0012] According to the application, a method for subjective evaluation of AR product experience is provided, which comprises the following steps: According to the operation data and the physiological behavior data after the spatio-temporal alignment, determining the first scoring attention feature of the operation data after the spatio-temporal alignment and the second scoring attention feature of the physiological behavior data after the spatio-temporal alignment. According to the feature extraction time sequence point, respectively determining the first scoring attention feature of the operation data after the spatio-temporal alignment and the second scoring attention feature of the physiological behavior data after the spatio-temporal alignment.

[0013] According to the application, a method for subjective evaluation of AR product experience is provided, which comprises the following steps: According to the first scoring attention feature and the second scoring attention feature, determining a cross-fusion feature. According to the cross-fusion feature and a preset corresponding relationship between the cross-fusion feature and the subjective score, determining a subjective predicted score of the user experiencing the AR product.

[0014] According to the application, a method for subjective evaluation of AR product experience is provided, which comprises the following steps: Inputting the operation data and the physiological behavior data after the spatio-temporal alignment into an experience subjective prediction model, and determining the first scoring attention feature of the operation data after the spatio-temporal alignment and the second scoring attention feature of the physiological behavior data after the spatio-temporal alignment by the experience subjective prediction model. The experience subjective prediction model is obtained by taking the operation data, the physiological behavior data, and the subjective score data in the sample as input data and training a neural network model.

[0015] According to the application, a method for subjective evaluation of AR product experience is provided, which comprises the following steps: Obtaining operation change time points and behavior change time points in the process of the user experiencing the AR product. According to the time information of the operation change time points and the behavior change time points, synchronizing to the operation data and the physiological behavior data to obtain the operation data and the physiological behavior data after the spatio-temporal alignment.

[0016] The application further provides an AR product experience subjective evaluation processing device, comprising: An acquisition module is configured to acquire operation data and physiological behavior data during user experience of an AR product. A processing module is configured to perform a space-time alignment operation on the operation data and the physiological behavior data to obtain space-time aligned operation data and space-time aligned physiological behavior data. A determination module is configured to determine a first scoring attention feature of the space-time aligned operation data and a second scoring attention feature of the space-time aligned physiological behavior data based on the space-time aligned operation data and the space-time aligned physiological behavior data. A prediction module is configured to determine a subjective prediction score of user experience of an AR product based on the first scoring attention feature and the second scoring attention feature.

[0017] The application further provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements any of the above-mentioned AR product experience subjective evaluation processing methods when executing the program.

[0018] The application further provides a non-transitory computer-readable storage medium having a computer program stored thereon, wherein the computer program is executable by a processor to implement any of the above-mentioned AR product experience subjective evaluation processing methods.

[0019] The application further provides a computer program product comprising a computer program, wherein the computer program is executable by a processor to implement any of the above-mentioned AR product experience subjective evaluation processing methods.

[0020] The application provides an AR product experience subjective evaluation processing method, device, equipment, and medium, which can collect effective data to a greater extent and improve the reliability of AR user experience subjective evaluation data by performing a space-time alignment operation on operation data and physiological behavior data during user experience of an AR product, determining scoring attention features of the space-time aligned operation data and physiological behavior data, and determining a subjective prediction score of user experience of an AR product based on the scoring attention features. BRIEF DESCRIPTION OF DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the application or prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are some embodiments of the application, and for those skilled in the art, other drawings can also be obtained without creative labor based on these drawings.

[0022] Figure 1It is the flowchart of the AR product experience subjective evaluation processing method provided by the application.

[0023] Figure 2 It is the specific flowchart of the AR product experience subjective evaluation processing method provided by the application.

[0024] Figure 3 It is the structural diagram of the AR product experience subjective evaluation processing device provided by the application.

[0025] Figure 4 It is the structural diagram of the electronic device provided by the application. DETAILED DESCRIPTION

[0026] In order to make the objects, technical solutions and advantages of the present application clearer, the technical solutions in the present application will be described clearly and completely below with reference to the drawings in the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0027] At present, with the development of multimedia technology, augmented reality technology is more and more applied to various fields such as medical treatment, education and industry. Augmented reality technology (hereinafter referred to as AR) is a new technology that superimposes virtual items on the real world, so that real world information and virtual world information are "seamlessly" integrated. The goal of this technology is to put the virtual world on the real world on the screen and interact. AR products are emerging in an endless stream. In order to improve user experience and service quality, it is necessary to evaluate AR product applications in order to realize real-time quality control of AR products.

[0028] In the present application, during the use of AR product applications, the technical parameters of the product and the user's experience perception need to be considered. Therefore, the AR product experience subjective evaluation processing method provided by the present application aims to combine multi-source data to perform subjective evaluation on AR product experience.

[0029] Therefore, Figure 1 The flowchart of the AR product experience subjective evaluation processing method provided by the present application is shown, referring to Figure 1 The method comprises the following steps: Step 11, obtaining operation data and physiological behavior data in the process of user experience AR product.

[0030] Step 12, performing space-time alignment operation on the operation data and physiological behavior data to obtain space-time aligned operation data and physiological behavior data.

[0031] Step 13, determining a first scoring attention feature of the spatio-temporally aligned operation data and a second scoring attention feature of the spatio-temporally aligned physiological behavior data according to the spatio-temporally aligned operation data and the physiological behavior data.

[0032] Step 14, determining a subjective predicted score of the user experiencing the AR product according to the first scoring attention feature and the second scoring attention feature.

[0033] It needs to be explained that for steps 11-14, during the process of the user using the AR product, the user needs to perform corresponding operations on the AR product. For example, the user wears an AR visual device and holds an AR operation handle, and performs operation behaviors (usually involving click behaviors) on the device or the operation handle. These operation behaviors are recorded in the form of operation data, such as generating a click log or an operation log. At the same time, the user also experiences physiological behavior changes in response to the AR application scene, such as dodging when startled by the scene, being stunned by the scene, and holding the operation handle to control the character in the scene to perform a specified action in response to the scene. These physiological behaviors are recorded in the form of physiological behavior data.

[0034] In the present application, during the entire process of the user using the AR product, the user experiences many different stages of application scenes. For example, the AR product application is a game, and the user needs to pass through the application game to use the AR product. Under different application scenes, operation data is collected when actual operation behaviors occur, and physiological behavior data is collected when actual physiological behavior changes occur. The occurrence of operation behaviors does not necessarily immediately produce physiological behavior data. Therefore, it is necessary to perform spatio-temporal alignment operation on the operation data and the physiological behavior data, so that the physiological behavior data can correspond to the category of the operation data, so as to fully express the influence of the operation data on the physiological behavior data, or the physiological behavior data can make the user make corresponding operation data.

[0035] It needs to be further explained that in order to extract data features subsequently, the operation data and the physiological behavior data are quantitatively processed to express the changes of the operation and the physiological behavior in the form of numerical values when the data is acquired and further spatio-temporally aligned. For this purpose, the spatio-temporally aligned preprocessing of the operation data and the physiological behavior data in the present application includes: converting a click sequence (taking a click function as operation data) into a Markov transition matrix; extracting Gamma distribution parameters from a view angle dwell time (taking a view angle dwell behavior as physiological behavior data), and simultaneously interpolating and synchronizing according to a clock stamp on the AR product; collecting a fixation point and generating a heat map entropy value for a user using AR glasses contained in the AR product; collecting a head angular velocity to calculate a frequency domain value and synchronizing with a clock stamp on the AR product. That is, for different types of operation data and different types of physiological behavior data, a corresponding spatio-temporally aligned preprocessing method needs to be configured to express them.

[0036] In the present application, for the data spatio-temporal alignment processing process, summarized as: obtaining the operation change time point and the behavior change time point in the process of user experience AR product; according to the time information of the operation change time point and the behavior change time point, synchronizing to the operation data and the physiological behavior data, obtaining the spatio-temporally aligned operation data and physiological behavior data.

[0037] In the present application, the spatio-temporally aligned operation data and physiological behavior data need to be comprehensively analyzed to obtain the key features that can help to perform product experience subjective evaluation. That is, for the data content on the operation data, there is a certain time point (or spatio-temporal position point) on the data, which can have a corresponding relationship with the data content in a certain category on the physiological behavior data, and the corresponding relationship can reflect the experience of the user using the AR product in this category. Therefore, the subjective prediction score of the user experience AR product is analyzed from the pros and cons of this corresponding relationship. Therefore, the spatio-temporally aligned operation data and physiological behavior data are analyzed, and the first scoring attention feature (i.e. the feature that helps to perform product experience subjective evaluation) is proposed from the spatio-temporally aligned operation data, and the second scoring attention feature (i.e. the feature that helps to perform product experience subjective evaluation) is proposed from the spatio-temporally aligned physiological behavior data.

[0038] In the present application, finally, according to the first scoring attention feature and the second scoring attention feature, the subjective prediction score of the user experience AR product is determined. Further explanation and description, mainly explain a processing method for determining the subjective prediction score of the user experience AR product according to the first scoring attention feature and the second scoring attention feature, as follows: According to the first scoring attention feature and the second scoring attention feature, a cross-fusion feature is determined. According to the cross-fusion feature and the pre-set corresponding relationship between the cross-fusion feature and the subjective score, the subjective prediction score of the user experience AR product is determined.

[0039] The AR product experience subjective evaluation processing method provided by the present application can more effectively collect effective data and improve the reliability of AR user experience subjective evaluation data by spatio-temporally aligning the operation data and physiological behavior data in the process of user experience AR product, determining the scoring attention features of the spatio-temporally aligned operation data and physiological behavior data, and then determining the subjective prediction score of the user experience AR product according to the scoring attention features.

[0040] In the further method of the above method, the application aims to realize real-time quality control of AR products, and for this purpose, the evaluation result in the real-time use state needs to be obtained. At this time, the effective evaluation result needs to be obtained. Therefore, when a new evaluation result (i.e. score) is obtained, it is necessary to further determine whether the score is effective. In the application, the newly obtained score needs to be analyzed by means of the score in the historical data to determine whether it is effective.

[0041] The subjective prediction score and the subjective actual score in the historical data are obtained.

[0042] According to the subjective prediction score and the subjective actual score in the historical data, the mean and the covariance are determined.

[0043] According to the currently determined subjective prediction score of the user experience AR product, the mean and the covariance, the confidence value of the user experience AR product is determined.

[0044] According to the confidence value of the user experience AR product, the processing result of the currently determined subjective prediction score of the user experience AR product is determined.

[0045] It can be seen that it is necessary to determine whether the currently determined subjective prediction score of the user experience AR product is credible. If it is credible, it means that the score is effective and can be stored. If it is not credible, it means that the score is temporarily invalid or invalid. When it is temporarily invalid, further determination is needed.

[0046] In the application, when the confidence value of the user experience AR product is greater than a preset value, the currently determined subjective prediction score of the user experience AR product and the corresponding subjective actual score are stored in the database. Since the historical data is stored according to the subjective prediction score and the subjective actual score as a score group, the currently determined subjective prediction score of the user experience AR product and the corresponding subjective actual score are stored in the database. The subjective actual score can be the subjective score of the user experience AR product.

[0047] When the confidence value of the user experience AR product is less than or equal to the preset value, and the trigger signal of storing the currently determined subjective prediction score of the user experience AR product in the database is sensed, the currently determined subjective prediction score of the user experience AR product and the corresponding subjective actual score are stored in the database. It should be noted that when the confidence value of the user experience AR product is less than or equal to the preset value, it means that the currently determined subjective prediction score of the user experience AR product is not credible from the result of data analysis. At this time, the user can be reminded to determine whether the score is credible. If it is credible, the trigger signal of storing in the database can be triggered, and at this time, the currently determined subjective prediction score of the user experience AR product and the corresponding subjective actual score can be stored in the database.

[0048] Further, when the confidence value of the user experience of the AR product is less than or equal to a preset value, and a trigger signal for determining the currently determined subjective prediction score of the user experience of the AR product as invalid data is sensed, a subjective simulation score of the user experience of the AR product is simulated as the subjective prediction score, and the subjective simulation score and the corresponding subjective actual score are stored. That is, the user considers that the currently determined subjective prediction score of the user experience of the AR product is invalid, at this time, the system can further simulate a subjective simulation score (that is, for each use process, one evaluation result is retained). The subjective simulation score can be simulated based on the operation data and the physiological behavior data in the user experience of the AR product according to a preset score simulation model.

[0049] In the present application, it is further explained that after the AR product application experience evaluation is performed for a certain time, there can be many evaluation results. However, for the judgment of the confidence of the currently determined subjective prediction score of the user experience of the AR product, the evaluation results of the recent use of the AR product are more suitable as the judgment basis, so in the present application, from the historical data, a score group of the previous N times of the user experience of the AR product in the current process is obtained, and the score group includes the subjective prediction score and the subjective actual score. At this time, the mean and the covariance are determined according to the previous N times of the subjective prediction score and the subjective actual score.

[0050] Since the above-mentioned subjective simulation score is to retain one evaluation result for each use process, it can not participate in the judgment of the confidence of the currently determined subjective prediction score of the user experience of the AR product. Therefore, if the subjective simulation score exists as the subjective prediction score in the current N times of the score group, the number of the subjective simulation scores is M, and then the historical data is searched again to obtain N-M score groups without the subjective simulation score.

[0051] In the further method of the above-mentioned method, the process of determining the confidence value of the user experience of the AR product according to the currently determined subjective prediction score of the user experience of the AR product, the mean and the covariance is explained, and is specifically as follows: The difference between the currently determined subjective prediction score of the user experience of the AR product and the mean and the transpose of the difference are determined. The confidence value of the user experience of the AR product is determined according to the difference, the transpose of the difference and the covariance.

[0052] Specifically, it can be: The confidence value of the user experience of the AR product is determined according to the currently determined subjective prediction score of the user experience of the AR product, the mean and the covariance by using the following calculation formula: wherein, is a confidence value, is a subjective prediction score, is a mean value, is a covariance.

[0053] In a further method of the above method, the process of determining the first score attention feature of the spatio-temporally aligned operation data and the second score attention feature of the spatio-temporally aligned physiological behavior data is explained as follows: determining a feature extraction time point according to the spatio-temporally aligned operation data and the physiological behavior data; determining the first score attention feature of the spatio-temporally aligned operation data and the second score attention feature of the spatio-temporally aligned physiological behavior data according to the feature extraction time point, respectively.

[0054] To this end, it should be noted that for the data content on the operation data, the data at a certain time point (or spatio-temporal position point) can have a corresponding relationship with the data content in a certain category on the physiological behavior data, and this corresponding relationship can reflect the user's experience of using the AR product in this category. Therefore, a feature extraction time point is determined according to the spatio-temporally aligned operation data and the physiological behavior data. Then, the first score attention feature of the spatio-temporally aligned operation data and the second score attention feature of the spatio-temporally aligned physiological behavior data are determined according to the feature extraction time point, respectively.

[0055] In a further method of the above method, after obtaining the spatio-temporally aligned operation data and the physiological behavior data, the spatio-temporally aligned operation data and the physiological behavior data can be input into the experience subjective prediction model as original data, and the model output subjective prediction score is adopted.

[0056] To this end, a sample data is used to train the experience subjective prediction model through a neural network model. The sample data includes operation data, physiological behavior data and subjective score data, and the sample data is used as input data to train the neural network model. Because of the existence of subjective score data in the model training process, the model attention mechanism can pay more attention to the features that are helpful for evaluation.

[0057] After the model is trained, when analyzing the spatio-temporally aligned operation data and the physiological behavior data, the process of determining the first score attention feature of the spatio-temporally aligned operation data and the second score attention feature of the spatio-temporally aligned physiological behavior data is explained as follows: The operation data and the physiological behavior data that are spatio-temporally aligned are input into the experience subjective prediction model, and the experience subjective prediction model determines a first scoring attention feature of the operation data that is spatio-temporally aligned and a second scoring attention feature of the physiological behavior data that is spatio-temporally aligned. Accordingly, the experience subjective prediction model determines a subjective prediction score of the user experiencing the AR product according to the first scoring attention feature and the second scoring attention feature.

[0058] Referring to Figure 2 The overall flowchart of the AR product experience subjective evaluation processing method provided by the present application is shown in the figure, and the processing process of the flowchart will not be described here.

[0059] The AR product experience subjective evaluation processing device provided by the present application is described below, and the AR product experience subjective evaluation processing device described below can be referred to in correspondence with the AR product experience subjective evaluation processing method described above.

[0060] Figure 3 The structure of the AR product experience subjective evaluation processing device provided by the present application is shown in the figure, referring to Figure 3 The device comprises an acquisition module 31, a processing module 32, a determination module 33, and a prediction module 34, wherein: The acquisition module is configured to acquire operation data and physiological behavior data in the process of the user experiencing the AR product. The processing module is configured to perform spatio-temporal alignment on the operation data and the physiological behavior data to obtain operation data and physiological behavior data that are spatio-temporally aligned. The determination module is configured to determine a first scoring attention feature of the operation data that is spatio-temporally aligned and a second scoring attention feature of the physiological behavior data that is spatio-temporally aligned according to the operation data and the physiological behavior data that are spatio-temporally aligned. The prediction module is configured to determine a subjective prediction score of the user experiencing the AR product according to the first scoring attention feature and the second scoring attention feature.

[0061] Since the device of the embodiment of the present application has the same principle as the above-mentioned embodiment method, more detailed explanation will not be repeated here.

[0062] It should be noted that the related functional modules in the embodiments of the present application can be realized by a hardware processor.

[0063] The AR product experience subjective evaluation processing device provided by the application can collect effective data to the greatest extent and improve the reliability of AR user experience subjective evaluation data.

[0064] Figure 4 An example of an entity structure diagram of an electronic device is shown in Figure 4 The electronic device can include a processor 41, a communications interface 42, a memory 43 and a communications bus 44, wherein the processor 41, the communications interface 42 and the memory 43 communicate with each other through the communications bus 44. The processor 41 can call the logical instructions in the memory 43 to execute the AR product experience subjective evaluation processing method, which includes: obtaining operation data and physiological behavior data in the process of user experience AR product; performing space-time alignment operation on the operation data and the physiological behavior data to obtain space-time aligned operation data and physiological behavior data; determining the first score attention feature of the space-time aligned operation data and the second score attention feature of the space-time aligned physiological behavior data according to the space-time aligned operation data and physiological behavior data; and determining the subjective predicted score of user experience AR product according to the first score attention feature and the second score attention feature.

[0065] In addition, the logical instructions in the memory 43 described above can be implemented in the form of a software function unit and sold or used as an independent product, which can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the application essentially or the part that contributes to the prior art or part of the technical solutions can be embodied in the form of a software product, which is stored in a storage medium, including a plurality of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the method described in various embodiments of the application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk and various program code storage media.

[0066] In another aspect, the present application also provides a computer program product comprising a computer program, which can be stored on a non-transitory computer readable storage medium, and the computer program is executable by a processor to enable a computer to perform the AR product experience subjective evaluation processing method provided by the above-mentioned methods, and the method comprises: acquiring operation data and physiological behavior data in the process of a user experiencing an AR product; performing a spatio-temporal alignment operation on the operation data and the physiological behavior data to obtain spatio-temporally aligned operation data and physiological behavior data; determining a first scoring attention feature of the spatio-temporally aligned operation data and a second scoring attention feature of the spatio-temporally aligned physiological behavior data according to the spatio-temporally aligned operation data and the physiological behavior data; and determining a subjective predicted score of the user experiencing the AR product according to the first scoring attention feature and the second scoring attention feature.

[0067] In yet another aspect, the present application also provides a non-transitory computer readable storage medium having a computer program stored thereon, and the computer program is executable by a processor to implement the AR product experience subjective evaluation processing method provided by the above-mentioned methods, and the method comprises: acquiring operation data and physiological behavior data in the process of a user experiencing an AR product; performing a spatio-temporal alignment operation on the operation data and the physiological behavior data to obtain spatio-temporally aligned operation data and physiological behavior data; determining a first scoring attention feature of the spatio-temporally aligned operation data and a second scoring attention feature of the spatio-temporally aligned physiological behavior data according to the spatio-temporally aligned operation data and the physiological behavior data; and determining a subjective predicted score of the user experiencing the AR product according to the first scoring attention feature and the second scoring attention feature.

[0068] The device embodiments described above are merely illustrative, wherein the units described as separate components can or can not be physically separated, and the components displayed as units can or can not be physical units, i.e., they can be located in one place, or distributed on multiple network units. Part or all of the modules can be selected to achieve the purpose of the present embodiment scheme according to actual needs. Those skilled in the art can understand and implement it without creative labor.

[0069] Those skilled in the art can clearly understand the technical solutions of the various embodiments from the above description of the embodiments, and the various embodiments can be implemented by means of software with the necessary general hardware platforms, and of course, can also be implemented by hardware. Based on such understanding, the above technical solutions, essentially or in other words, the part of the prior art that makes a contribution, can be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, and the like, and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0070] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, rather than limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for some technical features therein; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for processing subjective evaluation of AR product experience, characterized in that, The method comprises the following steps: obtaining operation data and physiological behavior data in the process of user experience AR product; spatiotemporal alignment operation is performed on the operation data and the physiological behavior data to obtain spatiotemporal aligned operation data and spatiotemporal aligned physiological behavior data; determining a first scoring attention feature of the spatiotemporal aligned operation data and a second scoring attention feature of the spatiotemporal aligned physiological behavior data according to the spatiotemporal aligned operation data and the spatiotemporal aligned physiological behavior data; determining a subjective predicted score of user experience AR product according to the first scoring attention feature and the second scoring attention feature. 2.The AR product experience subjective evaluation processing method according to claim 1, characterized in that, The method further comprises the following steps: obtaining a subjective predicted score and a subjective actual score in historical data; determining a mean value and a covariance according to the subjective predicted score and the subjective actual score in the historical data; determining a confidence value of user experience AR product according to the currently determined subjective predicted score of user experience AR product, the mean value and the covariance; determining a processing result of the currently determined subjective predicted score of user experience AR product according to the confidence value of user experience AR product. 3.The AR product experience subjective evaluation processing method according to claim 2, characterized in that, The step of determining the processing result of the currently determined subjective predicted score of user experience AR product according to the confidence value of user experience AR product comprises the following steps: when the confidence value of user experience AR product is greater than a preset value, storing the currently determined subjective predicted score of user experience AR product and the corresponding subjective actual score in a database; when the confidence value of user experience AR product is less than or equal to the preset value and a trigger signal for storing the currently determined subjective predicted score of user experience AR product is sensed, storing the currently determined subjective predicted score of user experience AR product and the corresponding subjective actual score in the database. 4.The AR product experience subjective evaluation processing method according to claim 2 or 3, characterized in that, The method further comprises the following steps: when the confidence value of user experience AR product is less than or equal to the preset value and a trigger signal for determining the currently determined subjective predicted score of user experience AR product as invalid data is sensed, simulating a subjective simulated score of user experience AR product as the subjective predicted score, and storing the subjective simulated score and the corresponding subjective actual score in the database. 5.The AR product experience subjective evaluation processing method according to claim 4, characterized in that, The step of obtaining the subjective predicted score and the subjective actual score in the historical data comprises the following step: obtaining a score group in the historical data in the previous N times of the current process of user experience AR product, wherein the score group comprises the subjective predicted score and the subjective actual score. 6.The AR product experience subjective evaluation processing method according to claim 5, characterized in that, The method further comprises the following steps: if there is a subjective simulated score as the subjective predicted score in the score group in the previous N times, counting the number of the subjective simulated scores as M; in the historical data, obtaining N-M score groups without the subjective simulated score again.

7. The AR product experience subjective evaluation processing method according to claim 6, characterized by, The step of determining the confidence value of user experience AR product according to the currently determined subjective predicted score of user experience AR product, the mean value and the covariance comprises the following steps: determining a difference value between the currently determined subjective predicted score of user experience AR product and the mean value and a transpose of the difference value; determining the confidence value of user experience AR product according to the difference value, the transpose of the difference value and the covariance. 8.The AR product experience subjective evaluation processing method of claim 1, wherein, The step of determining the first scoring attention feature of the spatiotemporal aligned operation data and the second scoring attention feature of the spatiotemporal aligned physiological behavior data according to the spatiotemporal aligned operation data and the spatiotemporal aligned physiological behavior data comprises the following steps: determine a first scoring attention feature of the operation data and a second scoring attention feature of the physiological behavior data according to the spatio-temporal alignment operation data and the physiological behavior data; determine a first scoring attention feature of the operation data and a second scoring attention feature of the physiological behavior data according to the spatio-temporal alignment operation data and the physiological behavior data. 9.The AR product experience subjective evaluation processing method of claim 1, wherein, The method further includes: determine a cross-fusion feature according to the first scoring attention feature and the second scoring attention feature; determine a subjective prediction score of the user experiencing the AR product according to the cross-fusion feature and a preset corresponding relationship between the cross-fusion feature and the subjective score. 10.The AR product experience subjective evaluation processing method of claim 1, wherein, The method further includes: input the spatio-temporal alignment operation data and the physiological behavior data into an experience subjective prediction model to determine the first scoring attention feature of the operation data and the second scoring attention feature of the physiological behavior data according to the experience subjective prediction model; The experience subjective prediction model is trained by a neural network model using the operation data, the physiological behavior data, and subjective score data in samples as input data. 11.The AR product experience subjective evaluation processing method of claim 1, wherein, The method further includes: obtain operation change time points and behavior change time points in the process of the user experiencing the AR product; synchronize the operation change time points and the behavior change time points to the operation data and the physiological behavior data according to time information of the operation change time points and the behavior change time points to obtain the spatio-temporally aligned operation data and the physiological behavior data. 12.A device for processing subjective evaluation of AR product experience, characterized in that, The method further includes: an obtaining module configured to obtain operation data and physiological behavior data in the process of the user experiencing the AR product; a processing module configured to perform a spatio-temporal alignment operation on the operation data and the physiological behavior data to obtain spatio-temporally aligned operation data and physiological behavior data; a determining module configured to determine a first scoring attention feature of the operation data and a second scoring attention feature of the physiological behavior data according to the spatio-temporally aligned operation data and the physiological behavior data; a prediction module configured to determine a subjective prediction score of the user experiencing the AR product according to the first scoring attention feature and the second scoring attention feature.

13. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor implements the AR product experience subjective evaluation processing method of any one of claims 1-11 when executing the program.

14. A non-transitory computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program implements the AR product experience subjective evaluation processing method of any one of claims 1-11 when executed by the processor.

15. A computer program product comprising a computer program, characterized in that, The computer program implements the AR product experience subjective evaluation processing method of any one of claims 1-11 when executed by the processor.

Images