Augmented reality multi-person cooperation interaction evaluation system and method

Abstract

The invention relates to an augmented reality multi-person cooperation interaction evaluation system and method, and the method comprises the steps: obtaining first-level indexes and all second-level indexes under each first-level index while extracting indexes through setting an evaluation index building module, thereby avoiding the evaluation ambiguity caused by different results of a single index; and the defect that different systems are difficult to compare comprehensively by using an existing evaluation method is overcome. By setting the index weight calculation module, the index weight of each index can be obtained by adopting a fusion method based on an analytic hierarchy process and an improved entropy weight method, so that the advantages of a subjective method and an objective method are fused and used based on the analytic hierarchy process and the improved entropy weight method, the influence of subjective factors is avoided, and the obtained index weight is more objective. Meanwhile, a comprehensive evaluation result is finally obtained in combination with a combination of a comprehensive evaluation module, an index weight calculation module, an evaluation index data establishment module and a membership function construction module.

Description

Technical Field

[0001] The present invention relates to the technical field of collaborative work and human-computer interaction effect evaluation, and in particular to an augmented reality multi-person collaborative interaction evaluation system and method. Background Art

[0002] Collaboration is a process of combined and interdependent activities between collaborators, whether in the same location or remotely, to achieve a common goal. The field of computer-supported cooperative work has focused on the design and development of solutions that support collaboration, aiming to enable communication, mutual assistance, training, learning, and knowledge sharing among collaborators.

[0003] Augmented reality (AR) technology is used to create a visual effect where virtual images seamlessly blend with the real world. By allowing virtual objects to coexist and interact with the real world, AR significantly enriches the way multiple users experience the real world. Over the years, numerous studies have demonstrated AR's advantages, including reducing cognitive load, task duration, and the number of errors, while also improving user experience.

[0004] However, existing evaluation methods for AR multi-person collaborative interactions based on augmented reality technology lack a systematic, standardized approach. Individual conclusions are typically drawn based on metrics such as efficiency, system usability, user experience, workload, and collaborative performance. These fragmented conclusions prevent a holistic analysis of the system and thus fail to meet the needs of objective evaluation. Furthermore, because the functional requirements and objectives of different systems vary significantly, while the human-computer interaction evaluation process focuses solely on individual evaluation elements, the evaluation metrics used in the analysis vary widely, making it difficult to conduct horizontal and vertical comparisons across different systems. This, to a certain extent, hinders the innovation and application of AR multi-person collaborative systems. Summary of the Invention

[0005] The technical problem to be solved by the present invention is how to overcome the technical shortcomings of existing augmented reality multi-person collaborative interaction systems, which suffer from significant differences in evaluation methods and a lack of unified evaluation standards, making it difficult to objectively compare the performance of different systems. To overcome these shortcomings of the existing technology, the present invention provides an augmented reality multi-person collaborative interaction evaluation system and method, specifically comprising an augmented reality multi-person collaborative interaction evaluation system and an augmented reality multi-person collaborative interaction evaluation method.

[0006] The present invention provides an augmented reality multi-person collaborative interactive evaluation system, comprising: An evaluation index establishment module is configured to generate index coverage content, and adopt the Delphi method to obtain multiple first-level indicators from all indicators of the index coverage content, and adopt the network analysis method to obtain all second-level indicators under each first-level indicator from all indicators of the evaluation index coverage content; An indicator weight calculation module is electrically connected to the evaluation indicator establishment module and is configured to obtain the indicator weight of each indicator by adopting a fusion method based on the hierarchical analysis method and the improved entropy weight method; an evaluation index data establishment module, electrically connected to the evaluation index establishment module, configured to collect evaluation index values of all objects participating in the evaluation under all indicators in the human-computer interaction experiment to construct an evaluation index data matrix, and perform indicator forward transformation, dimensionless processing and standardization processing on the evaluation index data matrix to obtain a standardized evaluation index data matrix; A membership function building module is electrically connected to the evaluation index building module and is configured to divide the value range of all indicators into a plurality of intervals and obtain the membership function of each interval by an assignment method; The comprehensive evaluation module is electrically connected to the indicator weight calculation module, the evaluation indicator data establishment module and the membership function construction module, and is configured to allow the membership function to act on the standardized evaluation indicator data matrix to obtain a membership matrix, and use the indicator weights to obtain a comprehensive evaluation result in a weighted summation manner.

[0007] The augmented reality multi-person collaborative interactive evaluation system disclosed in the present invention provides an evaluation index establishment module to obtain the primary index and all secondary indicators under each primary index simultaneously while extracting the index. This system comprehensively considers both subjective and objective indicators, avoids evaluation ambiguity caused by different results of a single index, and overcomes the drawback of existing evaluation methods that make it difficult to comprehensively compare different systems. By providing an index weight calculation module, a fusion method based on the hierarchical analysis method and the improved entropy weight method can be used to obtain the index weights of each index. This fusion method combines the advantages of the hierarchical analysis method and the improved entropy weight method, combines the advantages of subjective and objective methods, avoids the influence of subjective factors, and makes the obtained index weights more objective. At the same time, the combination of the comprehensive evaluation module, the index weight calculation module, the evaluation index data establishment module, and the membership function construction module ultimately obtains a comprehensive evaluation result, which improves the standardization of system evaluation to a certain extent and increases the comparability of the system. It also has a weight adjustment function and a certain degree of adaptability, thus overcoming the technical drawbacks of the existing technology that the evaluation methods are widely different and lack a unified evaluation standard, which makes it difficult to objectively compare the performance of different systems.

[0008] In a possible implementation, the indicator weight calculation module is configured to perform the following steps: A1: Collecting the comparison results of all the first-level indicators and all the second-level indicators by multiple experts to obtain a scale set, and normalizing the scale set to obtain an analytic hierarchy process weight matrix; A2: Collecting the information entropy of the evaluation index values of all indicators of the same evaluation object as in the evaluation index data establishment module to obtain the entropy weight matrix; A3: Calculate the arithmetic mean of the weight matrix of the hierarchical analysis method and the weight matrix of the entropy weight method to obtain the indicator weight of each indicator; This scheme combines the use of hierarchical analysis method and improved entropy weight method, thereby integrating the advantages of subjective and objective methods, further avoiding the influence of subjective factors, and making the obtained indicator weights more objective.

[0009] In a possible implementation, step A1 includes the following steps: A11: Establish an indicator importance comparison scale table, and collect the comparison results of all the first-level indicators and all the second-level indicators, which are obtained by multiple experts according to the contents of the indicator importance comparison scale table, to obtain a scale set; A12: Calculate the arithmetic mean of each scale in the scale set to obtain an arithmetic mean scale matrix; A13: Normalizing the arithmetic mean scale matrix by columns to obtain a normalized scale matrix, and summing the normalized scale matrix by rows to obtain an initial weight matrix; A14: Normalize the initial weight matrix by columns to obtain the AHP weight matrix; This scheme obtains the AHP weight matrix through the AHP, which not only reduces the computational complexity but also avoids the influence of subjective factors, making the results more objective.

[0010] In a possible implementation, step A2 includes the following steps: A21: Collect the evaluation index values of all indicators of the objects participating in the evaluation and calculate the probability of each evaluation index value; A22: The information entropy of each indicator is calculated by using the probability of each evaluation indicator value through the information entropy calculation formula; A23: Calculate the information utility value of each indicator by using the information entropy of each indicator through the information utility value calculation formula, normalize the obtained information utility value to obtain the entropy weight of each indicator, and integrate them to obtain the weight matrix of the entropy weight method; This scheme obtains the entropy weight method weight matrix based on information entropy by improving the entropy weight method, further integrating the advantages of subjective and objective methods, making the obtained indicator weights more objective.

[0011] In a possible implementation, the membership function of each interval obtained by the membership function construction module is calculated as follows: , Where, represents the value of the i-th row and j-th column of the standardized evaluation index data matrix; Represents the left endpoint of the interval defined by the membership function; Represents the right endpoint of the interval defined by the membership function; represents the amount of expansion; The membership function in the above form is a trapezoidal membership function constructed by the assignment method. It realizes the quantification of indicators while ensuring the reduction of computational complexity, and further ensures the objectivity of the comprehensive score.

[0012] In one possible implementation, the comprehensive evaluation module is configured to perform the following steps: B1: allowing the membership function to act on the standardized evaluation index data matrix to obtain a membership matrix; B2: multiplying the score vector formed by the scores of each interval by the membership matrix to obtain the score of each indicator; B3: Perform weighted summation of the score of each indicator and the indicator weight to obtain the comprehensive evaluation result.

[0013] In one possible embodiment, the evaluation system also includes an evaluation system improvement module, which is used for users to modify the indicator content. The evaluation system improvement module is electrically connected to the comprehensive evaluation module and the evaluation indicator establishment module at the same time; thereby, the evaluation indicator content can be directly modified according to the needs of different evaluation standards, thereby achieving optimization adjustment of the indicator content, indicator weight and evaluation results.

[0014] Another technical solution of the present invention is to provide an augmented reality multi-person collaborative interaction evaluation method, comprising the following steps: (1) Generate indicator coverage content through the evaluation indicator establishment module, and use the Delphi method to obtain multiple first-level indicators from the indicators of the indicator coverage content, and use the network analysis method to obtain all second-level indicators under each first-level indicator from the indicators of the evaluation indicator coverage content; (2) The indicator weight calculation module uses a fusion method based on hierarchical analysis method and improved entropy weight method to obtain the indicator weight of each indicator; (3) The evaluation index data establishment module is used to collect the evaluation index values of all the objects participating in the evaluation under all the indicators in the human-computer interaction experiment to construct an evaluation index data matrix, and the evaluation index data matrix is subjected to indicator forward transformation, dimensionless processing and standardization processing to obtain a standardized evaluation index data matrix; (4) Divide the value range of all indicators into several intervals through the membership function construction module, and obtain the membership function of each interval through the assignment method; (5) Using a comprehensive evaluation module, the membership function is applied to the standardized evaluation index data matrix to obtain a membership matrix, and the comprehensive evaluation result is obtained by weighted summation using the index weights.

[0015] The method disclosed in this application uses an evaluation index establishment module to obtain the first-level index and all the second-level indicators under each first-level index while extracting the index, thereby comprehensively considering the subjective index and the objective index, avoiding the evaluation ambiguity caused by the different results of a single index, and making up for the defect that it is difficult to comprehensively compare different systems using existing evaluation methods. Subsequently, the index weight calculation module adopts a fusion method based on the hierarchical analysis method and the improved entropy weight method to obtain the index weight of each index, thereby integrating the advantages of the hierarchical analysis method and the improved entropy weight method, integrating the advantages of the subjective and objective methods, avoiding the influence of subjective factors, and making the obtained index weight more objective. Finally, a comprehensive evaluation result is obtained through the comprehensive evaluation module, which improves the standardization of the system evaluation to a certain extent and increases the comparability of the system. It also has a weight adjustment function and has a certain adaptability, thereby overcoming the technical defects of the existing evaluation methods in the prior art, such as large differences and lack of unified evaluation standards, which make it difficult to objectively compare the performance of different systems.

[0016] In a possible implementation, the evaluation method further includes the following steps: (6) The evaluation system improvement module allows users to modify the indicator content, and transmits the indicator content modified by the user to the evaluation indicator establishment module. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a schematic diagram of the structure of an augmented reality multi-person collaborative interactive evaluation system disclosed in an embodiment of the present application; Figure 2 This is a flow chart of the method disclosed in the embodiments of this application. DETAILED DESCRIPTION

[0018] First, those skilled in the art should understand that these embodiments are merely used to explain the technical principles of the embodiments of the present application and are not intended to limit the scope of protection of the embodiments of the present application. Those skilled in the art may adjust them as needed to suit specific application scenarios.

[0019] In the embodiments of the present application, unless otherwise clearly specified and limited, the electrical connection between the first feature and the second feature means that there is transmission of electrical signals between the first feature and the second feature, that is, there is an electrical relationship, and the way to achieve the transmission of electrical signals may be electrical connection of wires, radio connection, electrical connection of electromagnetic media (such as semiconductors), communication achieved by channels, etc.

[0020] In the embodiments of the present application, unless otherwise expressly specified or limited, a first feature being "above" or "below" a second feature may mean that the first and second features are in direct contact, or that the first and second features are in indirect contact through an intermediate medium. Furthermore, a first feature being "above," "above," and "above" a second feature may mean that the first feature is directly above or obliquely above the second feature, or simply means that the first feature is higher in level than the second feature. A first feature being "below," "below," and "below" a second feature may mean that the first feature is directly below or obliquely below the second feature, or simply means that the first feature is lower in level than the second feature.

[0021] The present application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0022] See also Figures 1 and 2 , the embodiment of the present application discloses an augmented reality multi-person collaborative interactive evaluation system, the structural diagram of the dynamic layer clipping system is as follows Figure 1 As shown, the dynamic layer clipping system includes an evaluation index establishment module, an index weight calculation module, an evaluation index data establishment module, a membership function construction module, a comprehensive evaluation module and an evaluation system improvement module, wherein the index weight calculation module is electrically connected to the evaluation index establishment module, the evaluation index data establishment module is electrically connected to the evaluation index establishment module, the membership function construction module is electrically connected to the evaluation index establishment module, the comprehensive evaluation module is electrically connected to the index weight calculation module, the evaluation index data establishment module and the membership function construction module at the same time, and the evaluation system improvement module is electrically connected to the comprehensive evaluation module and the evaluation index establishment module at the same time.

[0023] In this dynamic layer clipping system, the evaluation index establishment module is set to generate index coverage content, and adopts the Delphi method to obtain multiple first-level indicators from all indicators of the index coverage content, and adopts the network analysis method to obtain all second-level indicators under each first-level indicator from all indicators of the evaluation index coverage content.

[0024] Specifically, in this embodiment, the evaluation indicator establishment module is configured to first determine indicator coverage based on the interaction requirements and basic evaluation content of augmented reality multi-person collaborative interaction. Subsequently, the Delphi method is used to select three indicators: work performance, human-computer interactivity, and multi-person collaboration as first-level evaluation indicators. Finally, a network analysis method is used to select seven indicators, the most commonly used in the field of augmented reality-supported human-computer interaction: overall task completion time (in seconds), average unit task completion time (in seconds), system usability (scale, 0-10 points, higher scores are better), system learnability (scale, 0-10 points, higher scores are better), workload (scale, 0-10 points, lower scores are better), information quality (scale, 0-10 points, higher scores are better), and interface quality (scale, 0-10 points, higher scores are better). Furthermore, two indicators, namely, sense of copresence (scale, 0-10 points, higher scores are better) and collaborative information perception (scale, 0-10 points, higher scores are better), are used as second-level indicators.

[0025] In this embodiment, the correspondence between the first-level indicators and the second-level indicators is as follows: ① There are two second-level indicators under the first-level indicator of work performance, namely, the overall work completion time and the average completion time of unit tasks; ② There are five second-level indicators under the first-level indicator of human-computer interactivity, namely, system availability, system learnability, workload, information quality and interface quality; ③ There are two second-level indicators under the first-level indicator of multi-person collaboration, namely, sense of coexistence and collaborative information perception.

[0026] In the dynamic layer clipping system, the indicator weight calculation module is configured to obtain the indicator weight of each indicator by adopting a fusion method based on the hierarchical analysis method and the improved entropy weight method. In this embodiment, the indicator weight calculation module is configured to perform the following steps:

[0027] A1: Collect the comparison results of all first-level indicators and all second-level indicators obtained by multiple experts to obtain a scale set, and normalize the scale set to obtain the AHP weight matrix.

[0028] In this embodiment, step A1 includes the following steps: A11: establishing an indicator importance comparison scale table, and collecting the comparison results obtained by multiple experts from the pairwise comparison of all first-level indicators according to the contents of the indicator importance comparison scale table and the comparison results obtained by the pairwise comparison of all second-level indicators to obtain a scale set; A12: calculating the arithmetic mean of each scale in the scale set to obtain an arithmetic mean scale matrix; A13: normalizing the arithmetic mean scale matrix by column to obtain a normalized scale matrix, and summing the normalized scale matrix by row to obtain an initial weight matrix; A14: normalizing the initial weight matrix by column to obtain a hierarchical analysis method weight matrix.

[0029] Specifically in this embodiment, the established indicator importance comparison scale table is shown in Table 1.

[0030] Table 1 Index comparison scale scale meaning 1 Indicates that two factors are equally important. 3 Indicates that one factor is slightly more important than the other factor. 5 Indicates that one factor is significantly more important than the other when comparing two factors. 7 Indicates that one factor is more important than the other. 9 Indicates that one factor is extremely more important than the other. 2、4、6、8 The median of the two adjacent judgments above reciprocal If the scale of A compared to B is 3, then B is 1 / 3 compared to A. Let's assume that h experts are invited to compare the first-level and second-level indicators in pairs, and the scale set M is obtained. , , Among them, m ijk It represents the scale value given by the kth expert after comparing the i-th and j-th indicators. Then the arithmetic mean m of each scale value is calculated. ij , and the arithmetic mean scaling matrix is obtained ,

[0031] , , Then normalize by column to get a normalized scale matrix , , , Then sum by row to get the initial weight matrix , , , Finally, normalize by column to get the AHP weight matrix , , .

[0032] A2: Collect the information entropy of the evaluation index values of all indicators of the same evaluation objects as those in the evaluation index data establishment module to obtain the entropy weight matrix.

[0033] In this embodiment, step A2 includes the following steps: A21: collecting the evaluation index values of the objects participating in the evaluation under all indicators, and calculating the probability of each evaluation index value; A22: calculating the information entropy of each indicator by using the probability of each evaluation index value through the information entropy calculation formula; A23: calculating the information utility value of each indicator by using the information entropy of each indicator through the information utility value calculation formula, and normalizing the obtained information utility value to obtain the entropy weight of each indicator, and integrating to obtain the entropy weight method weight matrix.

[0034] The size of the entropy value indicates the degree of dispersion of the indicator. The smaller the dispersion of the indicator, the smaller its impact on the comprehensive evaluation result and the smaller its weight. Specifically, in step A2 of this embodiment, the probability of each evaluation indicator value is first calculated. ,

[0035] , And calculate the information entropy of each indicator , , Then calculate the information utility value of each indicator , , The information utility value is then normalized to obtain the entropy weight of each indicator. , , Finally, the entropy weight method weight matrix is obtained by integration , .

[0036] A3: Calculate the arithmetic mean of the weight matrix of the hierarchical analysis method and the weight matrix of the entropy weight method to obtain the indicator weight of each indicator. Specifically in this embodiment, the comprehensive weight value of each indicator is obtained by combining the hierarchical analysis method and the entropy weight method. With the comprehensive weight matrix ,

[0037] , .

[0038] In this dynamic layer clipping system, the evaluation index data establishment module is set to collect the evaluation index values of all objects participating in the evaluation under all indicators in the human-computer interaction experiment to construct an evaluation index data matrix, and perform indicator forward transformation, dimensionless processing and standardization on the evaluation index data matrix to obtain a standardized evaluation index data matrix.

[0039] Specifically in this embodiment, let's assume that there are f objects participating in the evaluation, g evaluation indicators, and the evaluation indicator data establishment module is set to obtain the evaluation indicator data after the human-computer interaction experiment, and then construct the initial indicator data matrix , .

[0040] Represents the jth evaluation index value of the i-th evaluation object. Among them, the overall work completion time, the average completion time of each unit task, and the workload are negative indicators and need to be transformed to ensure that all evaluation indicators have the same effect.

[0041] , Different indicators have different dimensions and units and cannot be directly compared, so the indicator values need to be standardized. , Represents the standard deviation of the j-th evaluation index after transformation, and finally obtains the index data matrix , .

[0042] In the dynamic layer clipping system, the membership function construction module is set to divide the value range stage ratings of all indicators into several intervals, and obtain the membership function of each interval through the assignment method.

[0043] Specifically, after the evaluation index data establishment module transforms, all indicators are positive indicators, that is, the larger the indicator, the better. The membership function construction module is set to first divide the secondary evaluation indicators into stage ratings, so that each secondary indicator is divided into 5 intervals, namely , , , , The score q of each interval is 0, 25, 50, 75, and 100 respectively.

[0044] Then, the trapezoidal function of the assignment method is used to obtain the membership function of each interval. , in is the left interval, is the right interval, is the expansion amount, is the jth standardized evaluation index value of the i-th evaluation object.

[0045] In this dynamic layer pruning system, the comprehensive evaluation module is configured to apply a membership function to a standardized evaluation index data matrix to obtain a membership matrix, and then utilize the index weights to perform a weighted summation to obtain a comprehensive evaluation result. In this embodiment, the comprehensive evaluation module is configured to perform the following steps: B1: Applying a membership function to the standardized evaluation index data matrix to obtain a membership matrix; B2: Multiplying the membership matrix by the score vector formed by the scores of each interval to obtain a score for each index; B3: Performing a weighted summation of the score for each index and the index weight to obtain a comprehensive evaluation result.

[0046] Specifically, the comprehensive evaluation module is configured to perform the following steps: First, the standardized evaluation index data matrix D is brought into the membership function to calculate the membership of each index and obtain the membership matrix , , in It represents the membership of the i-th evaluation index in the j-th interval.

[0047] Afterwards, the score vector formed by the scores of each interval is multiplied by the membership matrix to obtain the score of each indicator , , Finally, the weighted sum is used to obtain the final evaluation result. , .

[0048] In this dynamic layer cutting system, the evaluation system improvement module is used to allow users to modify the indicator content. Specifically, users can directly modify the evaluation indicator content according to the needs of different evaluation standards, thereby optimizing the indicator weights and evaluation results.

[0049] See also Figure 2 The following will further disclose the usage method of the augmented reality multi-person collaborative interactive evaluation system in this embodiment. Figure 2 The overall flow chart of the method is as follows: (1) Generate indicator coverage content through the evaluation indicator establishment module, and use the Delphi method to obtain multiple first-level indicators in the indicators of the indicator coverage content, and use the network analysis method to obtain all second-level indicators under each first-level indicator in the indicators of the evaluation indicator coverage content.

[0050] (2) The indicator weight calculation module is used to obtain the indicator weight of each indicator by adopting a fusion method based on hierarchical analysis method and improved entropy weight method.

[0051] (3) Through the evaluation index data establishment module, the evaluation index values of all objects participating in the evaluation under all indicators in the human-computer interaction experiment are collected to construct the evaluation index data matrix, and the evaluation index data matrix is sequentially subjected to indicator forward transformation, dimensionless processing and standardization processing to obtain a standardized evaluation index data matrix.

[0052] (4) The value range of all indicators is divided into several intervals through the membership function construction module, and the membership function of each interval is obtained through the assignment method.

[0053] (5) Through the comprehensive evaluation module, the membership function is applied to the standardized evaluation index data matrix to obtain the membership matrix, and the comprehensive evaluation results are obtained by weighted summation using the index weights.

[0054] (6) The evaluation system improvement module is used to allow the user to modify the indicator content, and the indicator content modified by the user is transmitted to the evaluation indicator establishment module to return to step (1).

[0055] The following example illustrates this method in detail. In the evaluation index establishment module, the results of a human-computer experiment in which user 1 used an augmented reality multi-person collaborative interaction system and a traditional method to perform a certain experimental task are shown in Table 1:

[0056] Table 1 Results of human-computer experiment for user 1 Overall work completion time Average completion time per task System availability System learnability Workload Information quality Interface quality Sense of coexistence Collaborative Information Perception Augmented reality system 100 10 8 10 2 8 8 10 9 Traditional methods 244 24 6 10 2 4 5 4 3 After calculation by the indicator weight calculation module, the comprehensive weight matrix is obtained by using the comprehensive hierarchical analysis method and entropy weight method. , After calculations by the evaluation index data establishment module, the membership function construction module, and the comprehensive evaluation module, user 1's scores for each index of the two systems are obtained.

[0057] , , , .

[0058] The corresponding relationship between indicator scores and weights and indicators is shown in Table 2. Table 2 User 1's rating results Overall work completion time Average completion time per task System availability System learnability Workload Information quality Interface quality Sense of coexistence Collaborative Information Perception Augmented reality system 95.75 97.25 91.25 99.25 94 96.75 98.75 99.5 97.5 Traditional methods 13.5 8.25 65.5 99.25 94 41.5 44.25 40.5 38.25 Indicator weight 0.24 0.13 0.21 0.08 0.17 0.05 0.05 0.04 0.03 Finally, the weighted comprehensive evaluation results of user 1 on the augmented reality system and the traditional method are obtained, as shown in Table 3.

[0059] Table 3 Comprehensive evaluation results of user 1 Comprehensive evaluation results Augmented reality system 95.39 Traditional methods 49.04 The augmented reality multi-person collaborative interactive evaluation system disclosed in this embodiment, by setting up an evaluation index establishment module to obtain the first-level index and all the second-level indicators under each first-level index while extracting the index, thus comprehensively considering the subjective index and the objective index, avoiding the evaluation ambiguity caused by the different results of a single index, and making up for the defect that the existing evaluation methods between different systems are difficult to comprehensively compare. By setting up an index weight calculation module, the index weight of each index can be obtained by using a fusion method based on the hierarchical analysis method and the improved entropy weight method, thereby integrating the advantages of the hierarchical analysis method and the improved entropy weight method, integrating the advantages of subjective and objective methods, avoiding the influence of subjective factors, and making the obtained index weight more objective. At the same time, combined with the combination of the comprehensive evaluation module, the index weight calculation module, the evaluation index data establishment module and the membership function construction module, a comprehensive evaluation result is finally obtained, which improves the standardization of the system evaluation to a certain extent and increases the comparability of the system. It also has a weight adjustment function and has a certain adaptability, thus overcoming the technical defects of the existing technology that the evaluation methods are widely different and lack a unified evaluation standard, which makes it difficult to objectively compare the performance of different systems.

[0060] In the description of the embodiments of the present application, it should be noted that in the description of the present application, terms such as "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the accompanying drawings. This is only for the convenience of description and does not indicate or imply that the device or component must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present application.

[0061] In the description of the present application, the description with reference to the terms "one embodiment", "some embodiments", "in the present embodiment", "specific example", or "some examples" means that the specific features, mechanisms, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, mechanisms, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine different embodiments or examples described in this specification and the features of different embodiments or examples, unless they are mutually inconsistent.

[0062] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. An augmented reality multi-person collaborative interaction evaluation system, characterized by: The evaluation system includes: An evaluation index establishment module is configured to generate index coverage content, and adopt the Delphi method to obtain multiple first-level indicators from all indicators of the index coverage content, and adopt the network analysis method to obtain all second-level indicators under each first-level indicator from all indicators of the evaluation index coverage content; An indicator weight calculation module is electrically connected to the evaluation indicator establishment module and is configured to obtain the indicator weight of each indicator by adopting a fusion method based on the hierarchical analysis method and the improved entropy weight method; an evaluation index data establishment module, electrically connected to the evaluation index establishment module, configured to collect evaluation index values of all objects participating in the evaluation under all indicators in the human-computer interaction experiment to construct an evaluation index data matrix, and perform indicator forward transformation, dimensionless processing and standardization processing on the evaluation index data matrix to obtain a standardized evaluation index data matrix; A membership function building module is electrically connected to the evaluation index building module and is configured to divide the value range of all indicators into a plurality of intervals and obtain the membership function of each interval by an assignment method; The comprehensive evaluation module is electrically connected to the indicator weight calculation module, the evaluation indicator data establishment module and the membership function construction module, and is configured to allow the membership function to act on the standardized evaluation indicator data matrix to obtain a membership matrix, and use the indicator weights to obtain a comprehensive evaluation result in a weighted summation manner.

2. The augmented reality multi-person collaborative interaction evaluation system according to claim 1, characterized in that: The indicator weight calculation module is configured to perform the following steps: A1: Collecting the comparison results of all the first-level indicators and all the second-level indicators by multiple experts to obtain a scale set, and normalizing the scale set to obtain an analytic hierarchy process weight matrix; A2: Collecting the information entropy of the evaluation index values of all indicators of the same evaluation object as in the evaluation index data establishment module to obtain the entropy weight matrix; A3: Calculate the arithmetic mean of the AHP weight matrix and the entropy weight method weight matrix to obtain the indicator weight of each indicator.

3. The augmented reality multi-person collaborative interaction evaluation system according to claim 2, characterized in that: The step A1 comprises the following steps: A11: Establish an indicator importance comparison scale table, and collect the comparison results of all the first-level indicators and all the second-level indicators, which are obtained by multiple experts according to the contents of the indicator importance comparison scale table, to obtain a scale set; A12: Calculate the arithmetic mean of each scale in the scale set to obtain an arithmetic mean scale matrix; A13: Normalizing the arithmetic mean scale matrix by columns to obtain a normalized scale matrix, and summing the normalized scale matrix by rows to obtain an initial weight matrix; A14: Normalize the initial weight matrix by columns to obtain the AHP weight matrix.

4. The augmented reality multi-person collaborative interaction evaluation system according to claim 2 or 3, characterized in that: The step A2 comprises the following steps: A21: Collect the evaluation index values of all indicators of the objects participating in the evaluation and calculate the probability of each evaluation index value; A22: The information entropy of each indicator is calculated by using the probability of each evaluation indicator value through the information entropy calculation formula; A23: The information utility value of each indicator is calculated by using the information entropy of each indicator through the information utility value calculation formula, and the obtained information utility value is normalized to obtain the entropy weight of each indicator, and the entropy weight method weight matrix is obtained by integration.

5. The augmented reality multi-person collaborative interaction evaluation system according to claim 4, characterized in that: The membership function formula of each interval obtained by the membership function construction module is as follows: ， Where, represents the value of the i-th row and j-th column of the standardized evaluation index data matrix; Represents the left endpoint of the interval defined by the membership function; Represents the right endpoint of the interval defined by the membership function; Represents the amount of expansion.

6. The augmented reality multi-person collaborative interaction evaluation system according to claim 5, characterized in that: The comprehensive evaluation module is configured to perform the following steps: B1: allowing the membership function to act on the standardized evaluation index data matrix to obtain a membership matrix; B2: multiplying the score vector formed by the scores of each interval by the membership matrix to obtain the score of each indicator; B3: Perform weighted summation of the score of each indicator and the indicator weight to obtain the comprehensive evaluation result.

7. The augmented reality multi-person collaborative interaction evaluation system according to claim 5 or 6, characterized in that: The evaluation system further comprises an evaluation system improvement module, which is used for allowing users to modify indicator content. The evaluation system improvement module is electrically connected to the comprehensive evaluation module and the evaluation indicator establishment module.

8. An augmented reality multi-person collaborative interaction evaluation method, characterized in that: The evaluation method is applicable to the augmented reality multi-person collaborative interaction evaluation system according to any one of claims 1 to 7, comprising the following steps: (1) Generate indicator coverage content through the evaluation indicator establishment module, and use the Delphi method to obtain multiple first-level indicators from the indicators of the indicator coverage content, and use the network analysis method to obtain all second-level indicators under each first-level indicator from the indicators of the evaluation indicator coverage content; (2) The indicator weight calculation module uses a fusion method based on hierarchical analysis method and improved entropy weight method to obtain the indicator weight of each indicator; (3) The evaluation index data establishment module is used to collect the evaluation index values of all the objects participating in the evaluation under all the indicators in the human-computer interaction experiment to construct an evaluation index data matrix, and the evaluation index data matrix is subjected to indicator forward transformation, dimensionless processing and standardization processing to obtain a standardized evaluation index data matrix; (4) Divide the value range of all indicators into several intervals through the membership function construction module, and obtain the membership function of each interval through the assignment method; (5) Using a comprehensive evaluation module, the membership function is applied to the standardized evaluation index data matrix to obtain a membership matrix, and the comprehensive evaluation result is obtained by weighted summation using the index weights.

9. The augmented reality multi-person collaborative interaction evaluation method according to claim 8, characterized in that: The evaluation method further comprises the following steps: (6) The evaluation system improvement module allows users to modify the indicator content, and transmits the indicator content modified by the user to the evaluation indicator establishment module.

Images